JP6869065B2 - Abnormality judgment device and abnormality judgment method - Google Patents

Description

The present invention relates to an abnormality determination device including an abnormality determination unit for determining an abnormality of a plurality of the objects based on time-series data of parameters measured in each of the plurality of objects, and an abnormality determination method.

Conventionally, a failure including a parameter measuring unit for measuring an operating state of an internal combustion engine or the like and an abnormality determining unit for determining the possibility of an abnormality of the target based on the measurement result of the parameter measuring unit. A determination device is known (see Patent Document 1).
In the technique disclosed in Patent Document 1, the waveform showing the time change of the measured parameter is compared with the known waveform showing the precursor of failure, and the possibility of abnormality is determined from the comparison result. It is configured in.

Japanese Unexamined Patent Publication No. 2006-214333

In general, failures that cause the above-mentioned abnormalities are roughly classified into wear-related failures due to aging deterioration and the like and sudden failures.
Abrasion-resistant failures due to aged deterioration or the like are failures of rotating bearings of generators, etc., and become apparent when parts gradually deteriorate over a long period of time and the deterioration progresses beyond a certain level. In this case, for example, even on the time-series data in which the vibration of the generator is sensed, the value of the time-series data gradually approaches an abnormal value. Can be detected before the occurrence of. The technique disclosed in Patent Document 1 detects a wear-resistant failure due to such aged deterioration or the like.
On the other hand, in many cases of sudden failures, the cause of the failure does not exist, or it is difficult to detect the abnormality caused by the cause of the failure by a sensor or the like. Therefore, it is relatively difficult to detect the abnormality before the failure occurs. Specific examples of the abnormality include misfire of a cylinder of an internal combustion engine. It is considered that the main cause of the failure is that the combustion region deviates from the normal combustion region due to ignition failure due to soot accumulation in the sub chamber of the subchamber type internal combustion engine and disturbance of the air-fuel ratio due to poor control. , Sensors for detecting these in advance are difficult to install, and even if they can be installed, they are expensive.

However, for example, in the case of the above-mentioned misfire, since a single misfire has occurred before the level of the internal combustion engine is forcibly stopped, the temperature of the exhaust gas due to the single misfire is lowered. It is not impossible to detect a misfire (abnormality). However, since the temperature drop of the exhaust gas due to a single misfire is very small, there is a problem that it is difficult to judge an abnormality with high detection accuracy while suppressing an erroneous judgment by a simple threshold setting. It was.

The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to capture minute abnormalities with high detection accuracy while improving determination accuracy (while suppressing erroneous determination), and to capture a data group. The point is to provide an abnormality determination device capable of executing abnormality determination and an abnormality determination method without the need for setting a threshold value in consideration of the individual properties of the above.

An abnormality determination device for achieving the above object is a time-series data of parameters measured in each of a plurality of objects, and is an exhaust gas measured in each exhaust gas corresponding to a plurality of combustion chambers provided in one engine. An abnormality determination device including an abnormality determination unit that determines an abnormality of a plurality of the objects based on the time-series data of the temperature, and its characteristic configuration is:
A selection unit that selects one abnormality determination target as the target for abnormality determination from the plurality of said targets and selects a plurality of non-abnormality determination targets other than the abnormality determination target from the plurality of said targets.
Regression analysis using the time-series data corresponding to the abnormality determination target selected by the selection unit as the explained variable and the time-series data corresponding to the non-abnormality determination target as the explanatory variable in a predetermined derivation period. Is executed to derive the regression equation, and it is determined from the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target and the standard deviation of the time series data corresponding to the non-abnormality determination target. An abnormality degree deriving unit for deriving the abnormality degree of the abnormality determination target based on the statistical threshold value to be obtained is provided.
The selection unit selects a plurality of the non-abnormality determination targets with respect to the abnormality determination target.
The correlation coefficient between the time-series data corresponding to the abnormality determination target and the time-series data corresponding to the non-abnormality determination target is a high correlation of 0.7 or more and 1 or less.
The abnormality degree derivation unit derives the abnormality degree with respect to one said abnormality determination target and each of a plurality of the non-abnormality determination targets selected by the selection unit.
The abnormality determining unit, on the basis of the degree of abnormality derived by the abnormality degree deriving unit is intended for determining whether or not the abnormality determination target is in an abnormal state,
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is the standard deviation of the time series data corresponding to the non-abnormality determination target. When the statistical threshold determined from is exceeded, it is derived that the degree of abnormality in the derivation period is high.
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is determined from the standard deviation of the time series data corresponding to the non-abnormality determination target. When the following, it is derived that the degree of abnormality in the derivation period is low.
The anomaly degree derivation unit is used in deriving the anomaly degree.
The upper limit statistical threshold value as the statistical threshold value is set to a value of 3 times or more and 5 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
The lower limit statistical threshold value as the statistical threshold value is set to a value of -5 times or more and -3 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
When at least one of the plurality of abnormalities derived by the abnormality degree deriving unit is derived to be equal to or higher than a predetermined reference value, the abnormality determination unit determines that the abnormality determination target is in an abnormal state. ..

The abnormality determination method for achieving the above objectives is
As time-series data of parameters measured in each of a plurality of objects, a plurality of time-series data of the temperature of exhaust gas measured in each exhaust passage corresponding to a plurality of combustion chambers provided in one engine . An abnormality determination method including an abnormality determination step for determining an abnormality of the target, wherein the characteristic configuration thereof is as follows.
A selection step of selecting one abnormality determination target as the target for abnormality determination from a plurality of the targets and selecting a plurality of non-abnormality determination targets other than the abnormality determination target from the plurality of the targets.
The time-series data corresponding to the abnormality determination target selected in the selection step is used as the explained variable, the time-series data corresponding to the non-abnormality determination target is used as the explanatory variable, and regression analysis is executed to perform a regression equation. Is derived, and in a predetermined derivation period, it is determined from the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target and the standard deviation of the time series data corresponding to the non-abnormality determination target. It is provided with an abnormality degree derivation step for deriving the abnormality degree of the abnormality determination target based on the statistical threshold value to be obtained.
In the selection step, a plurality of the non-abnormality determination targets are selected for one abnormality determination target.
The correlation coefficient between the time-series data corresponding to the abnormality determination target and the time-series data corresponding to the non-abnormality determination target is a high correlation of 0.7 or more and 1 or less.
The abnormality degree derivation step derives the abnormality degree with respect to one said abnormality determination target and each of the plurality of non-abnormality determination targets selected in the selection step.
The abnormality determining step, based on the degree of abnormality derived by the abnormality degree deriving step is intended for determining whether or not the abnormality determination target is in an abnormal state,
In the abnormality degree derivation step, in the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is the standard deviation of the time series data corresponding to the non-abnormality determination target. When the statistical threshold determined from is exceeded, it is derived that the degree of abnormality in the derivation period is high.
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is determined from the standard deviation of the time series data corresponding to the non-abnormality determination target. When the following, it is derived that the degree of abnormality in the derivation period is low.
The abnormality degree derivation step is performed in the derivation of the abnormality degree.
The upper limit statistical threshold value as the statistical threshold value is set to a value of 3 times or more and 5 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
The lower limit statistical threshold value as the statistical threshold value is set to a value of -5 times or more and -3 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
When at least one of the plurality of abnormalities derived by the abnormality degree deriving step is derived to be equal to or higher than a predetermined reference value, the abnormality determination step is at a point of determining that the abnormality determination target is in an abnormal state. ..

According to the above feature configuration, first, the anomaly derivation unit uses the time-series data corresponding to the anomaly determination target selected by the selection unit as the explained variable, and the time-series data corresponding to the non-abnormality determination object as the explanatory variable. Then, the regression analysis is executed to derive the regression equation, and the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality judgment target in the predetermined derivation period is the time series data corresponding to the non-abnormality determination target. Since the degree of abnormality of the abnormality determination target is derived based on the number of times the statistical threshold determined from the standard deviation of is exceeded, the statistical threshold determined statistically can be used. For example, it is not necessary to set the threshold value in consideration of the individual characteristics of the internal combustion engine), and the degree of abnormality can be derived with relatively high accuracy.
In particular, according to the above feature configuration, since the output of the regression equation is used as the reference data, for example, the reference value of the time series data corresponding to the abnormality determination target and the time series data corresponding to the non-abnormality determination target ( More specifically, even if the average value) is significantly different, the influence of the difference can be excluded and the degree of abnormality can be appropriately derived.

The statistical threshold value that is statistically determined has a certain range, but when the statistical threshold value is lowered and the sensitivity is set high, it should be normal because the sensitivity is high. There is a high risk that the series data will be erroneously determined to be abnormal. That is, increasing the sensitivity for detecting an abnormality and reducing the possibility of erroneous determination are in a trade-off relationship.
On the other hand, according to the above-mentioned feature configuration, the abnormality degree derivation unit derives the abnormality degree between one abnormality determination target and each of a plurality of non-abnormality determination targets selected by the selection unit. In addition, since the abnormality determination unit determines whether or not the abnormality determination target is in the abnormality state based on the plurality of abnormality degrees derived by the abnormality degree derivation unit, for example, one abnormality determination is tentatively made. Even if the degree of abnormality in the combination of the target and a plurality of non-abnormality judgment targets deviates from the appropriate value, if the degree of abnormality is an appropriate value in other combinations, the appropriate abnormal state can be determined. As a result, the possibility of erroneous judgment can be reduced.
That is, according to the present invention, it is possible to realize an abnormality determination device and an abnormality determination method capable of suppressing the occurrence of erroneous determination while increasing the sensitivity.
Further, according to the above feature configuration, the degree of abnormality can be derived by a relatively simple calculation of whether or not the statistical threshold value determined from the standard deviation is exceeded. Therefore, for example, the individual characteristics of the target (for example, an internal combustion engine) can be determined. Compared with the case of setting the threshold value in consideration, the degree of abnormality can be derived relatively easily and accurately.
Further, according to the above feature configuration, the upper limit statistical threshold as the statistical threshold is set to a value of 3 times or more and 5 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target, and the lower limit statistical threshold as the statistical threshold is set. , Since the value is set to -5 times or more and -3 times or less of the standard deviation of the time series data corresponding to the non-abnormality judgment target, the threshold value is set in consideration of the individual characteristics of the target (for example, the internal combustion engine) as in the prior art. The degree of anomaly can be derived with relatively high accuracy.

Further feature configuration of the abnormality judgment device is
The abnormality determination unit determines whether or not the abnormality determination target is in an abnormal state based on the ratio derived when the abnormality degree is high among the plurality of the abnormality degrees derived by the abnormality degree derivation unit. Is the point to judge.

According to the above-mentioned feature configuration, even when the sensitivity is increased, it is possible to suppress the occurrence of erroneous determination due to the determination of the abnormal state by the logic with a relatively small amount of calculation.

Further feature configuration of the abnormality judgment device is
A steady state determination unit for determining whether or not the target is in a steady state from the time series data is provided.
The abnormality degree derivation unit is at a point of deriving the abnormality degree of the abnormality determination target based on the time series data determined by the steady state determination unit to be in the steady state.

According to the above feature configuration, by using the time series data in a relatively stable steady state, the degree of abnormality associated with the essential abnormality of the object can be appropriately derived.

Further feature configuration of the abnormality judgment device is
A determination accuracy adjusting unit for adjusting the accuracy of determining whether or not the abnormality determination target is in the abnormal state is provided.
The determination accuracy adjusting unit increases the number of non-abnormality determination targets selected by the selection unit as the determination accuracy is adjusted to be high.

According to the above feature configuration, the accuracy of determining the abnormal state can be adjusted by adjusting the number of non-abnormality determination targets selected in the selection unit. Specifically, the more the number of non-abnormality determination targets selected by the selection unit is increased and the number of abnormalities that are the basis of the abnormal state determination is increased, the higher the accuracy of the determination in the abnormal state determination is. Yes, in other words, the possibility of erroneous judgment can be reduced.

As an abnormality judgment device,
A sensitivity adjusting unit for adjusting the sensitivity of whether or not the abnormality determination target is in the abnormal state is provided.
It is preferable that the sensitivity adjusting unit reduces the magnification of the standard deviation of the time series data corresponding to the non-abnormality determination target when setting the statistical threshold value as the sensitivity is adjusted to be high.

Schematic configuration diagram of equipment including an abnormality determination device according to an embodiment Graph diagram for explaining abnormality judgment by abnormality judgment device Graph diagram for explaining abnormality judgment by abnormality judgment device

The abnormality determination device 100 and the abnormality determination method according to the embodiment of the present invention capture minute abnormalities with high accuracy while increasing the determination accuracy (while suppressing erroneous determination), and individual data groups. Abnormality determination can be executed with a relatively low calculation load without the need to set a threshold value in consideration of properties and the like.
Hereinafter, description will be given based on the drawings.

As shown in FIG. 1, the abnormality determination device 100 connects a plurality of cogeneration systems C and a management unit K that manages the plurality of cogeneration systems C in a state in which they can communicate with each other via a network line N. The abnormality determination result in the abnormality determination device 100 can be transmitted to the management unit K.
In the embodiment, the cogeneration system C is mainly composed of an engine 30 that supplies heat and electric power together and a control device Cc including an ECU of the engine 30.
The engine 30 uses a gaseous fuel such as city gas (13A) as fuel, and operates the spark plug at a desired time by reciprocating the piston in the cylinder and opening and closing the intake valve and the exhaust valve. By doing so, each of the intake stroke, the compression stroke, the expansion stroke, and the exhaust stroke is sequentially executed in the combustion chamber. As a result, the reciprocating motion of the piston is output as the rotational motion of the crankshaft via the connecting rod. The configuration is the same as that of a normal 4-stroke internal combustion engine.

Further, the engine 30 is composed of a multi-cylinder gas engine provided with a plurality of combustion chambers, and a temperature sensor S1 for separately measuring the exhaust temperature from each combustion chamber in an exhaust passage and each combustion chamber. The knock sensor S2 that detects the knocking strength in the engine and the rotation speed sensor S3 that measures the rotation speed of the engine in the form of measuring the crank angle of the crankshaft are provided.
The control device Cc includes a control unit (not shown) that controls the operation of the engine 30, a data acquisition unit Cc1 that acquires measurement data of the temperature sensor S1, the knock sensor S2, and the rotation speed sensor S3, and a data acquisition unit. It includes a storage unit DBc that stores the measurement data acquired by Cc1 and a communication unit Cc2 that executes data transmission / reception to and from the outside. In particular, the communication unit Cc2 is configured to be able to transmit the measurement data stored in the storage unit DBc to the abnormality determination device 100 via the network line N. The control device Cc includes a determination unit (not shown) for determining that the measurement data acquired by the data acquisition unit Cc1 has an obvious abnormality, and when the determination unit determines that there is an abnormality, the abnormality is found. It is configured to include a monitor (display unit) Cc3 for displaying. The determination unit determines, for example, that there is an abnormality when the above-mentioned measurement data exceeds the threshold value corresponding to the obvious abnormality.

By the way, the cogeneration system C as described above can satisfactorily detect, for example, a single misfire that occurs in the engine 30 in order to detect (predict) in advance an abnormality that may lead to a serious failure in the engine 30. preferable. Misfire detection is generally based on the measurement of a decrease in exhaust gas temperature. However, since the temperature drop of the exhaust gas due to a single misfire at the stage before the misfire at the level where the engine 30 is forcibly stopped occurs is very small, the simple threshold setting can improve the determination accuracy. However, there is a problem that it is difficult to detect a minute abnormality with high detection accuracy (while suppressing erroneous judgment).

Therefore, the abnormality determination device 100 according to the embodiment includes a communication unit M1 that receives measurement data of the cogeneration system C via the network line N, and a storage unit DB that stores the data received by the communication unit M1. The temperature of the exhaust gas measured in a plurality of combustion chambers (an example of a plurality of objects) provided in the cogeneration system C (specifically, in the exhaust passage corresponding to each combustion chamber by the temperature sensor S1). It is provided with an abnormality determination unit M5 that executes abnormality determination of a plurality of combustion chambers based on time-series data of measured temperature (an example of parameters).

To add an explanation, the abnormality determination device 100 selects one combustion chamber that is an abnormality determination target from a plurality of combustion chambers, and also selects a plurality of non-abnormality determination targets other than the abnormality determination target from the plurality of combustion chambers. The time series data corresponding to the selection unit M3 that selects the item and the combustion chamber that is the abnormality determination target selected by the selection unit M3 in the predetermined derivation period are used as explained variables, and the combustion chamber that is the non-abnormality determination target. Regression analysis is performed to derive the regression equation using the time-series data corresponding to the above as the explanatory variable, and the value obtained by subtracting the output of the regression equation from the time-series data corresponding to the abnormality judgment target corresponds to the non-abnormality judgment target. An abnormality degree deriving unit M4 for deriving an abnormality degree E of an abnormality determination target based on a statistical threshold value determined from a standard deviation of time-series data is provided.
Further, in the abnormality determination device 100, the selection unit M3 selects a plurality of non-abnormality determination target combustion chambers with respect to one abnormality determination target combustion chamber, and the abnormality degree derivation unit M4 is one. The abnormality degree E is derived for each of the combustion chamber of the abnormality determination target and the combustion chambers of the plurality of non-abnormality determination targets selected by the selection unit M3, and the abnormality determination unit M5 determines the abnormality degree. Based on the plurality of abnormality degrees E derived by the out-licensing unit M4, it is determined whether or not the combustion chamber, which is the object of abnormality determination, is in an abnormal state.
The above-mentioned predetermined derivation period is preferably 30 minutes or more, and 3 or 4 hours at the longest, for example, when the measurement cycle of the sensor value (value at each time point of the time series data) is 1 second interval. The score of the sensor value needs to be at least 1,000 to 2,000 from the viewpoint of statistics. Therefore, when the number of data points is recorded at 1-second intervals, it is desirable to derive the data in a period of 30 minutes or more in which 30 × 60 points = 1,800 points are guaranteed. Moreover, since the sensor value is affected by the outside air temperature, it is desirable to set a period in which the outside air temperature is constant as much as possible as the derivation period.
Therefore, it is better to set the derivation period to 3 or 4 hours at the longest.

Hereinafter, a specific description will be added.
Abnormality degree deriving unit M4 relates derives error probability E, one abnormality determination time series data corresponding to the combustion chambers which is the subject and Y _t, the time-series data corresponding to the combustion chamber is one of non-abnormality determination target _Is X it, X _it is an explained variable, Y _t is an explanatory variable, and for example, the regression equation shown in [Equation 1] below is derived.

[Number 1]
_{Y it '= a i × X} it + b i
However, t represents time, i is shown the [1, n] a and a plurality of non-abnormality determination target, a _i, b _i is a constant value regardless of t, determined for each explanatory variable X _it Y _it'is the output of the regression equation.

For each i, as it follows expression (2), to derive a value D _it which subtracts the output Y _{it 'regression} formula from the time-series data Y _t corresponding to a combustion chamber of an abnormality determination target.

[Number 2]
D _it = Y _t- Y _it '

At each time point (meaning t at a specific time point) within the predetermined derivation period, it is determined that the abnormality degree E is high when the predetermined threshold value is exceeded, and each t (each time point) when it is below the predetermined threshold value. It is derived that the degree of abnormality in is low.
_{Here, the predetermined threshold is a statistical threshold determined from the standard deviation δ of the time series data Xit} corresponding to the combustion chamber as the non-abnormality determination target, and the upper limit statistical threshold as the statistical threshold is the non-abnormality determination target. The value is 3 times or more and 5 times or less of the standard deviation of the corresponding time-series data, and the lower limit statistical threshold as the statistical threshold is -5 times or more and -3 times or more of the standard deviation of the time-series data corresponding to the non-abnormality judgment target. It is less than double the value.

The abnormality determination unit M5 determines whether or not the combustion chamber, which is the object of abnormality determination, is in an abnormal state at each time point, based on the abnormality degree E at each time point derived by the abnormality degree derivation unit M4.
Further, in the abnormality determination unit M5, the combustion chamber, which is the abnormality determination target, is abnormal based on the ratio of the plurality of abnormality degrees E derived by the abnormality determination unit M4 that the abnormality degree E is determined to be high. Determine if it is in a state.

Hereinafter, description will be added based on FIGS. 2 and 3.
FIG. 2 is not included in the scope of rights of the present invention, but illustrates the case where i = 1, that is, the case where there is one combustion chamber as a non-abnormality determination target.
As shown in FIG. 2A, the exhaust gas temperature corresponding to the combustion chamber as the abnormality determination target and the exhaust gas temperature corresponding to the combustion chamber as the non-abnormality determination target are, for example, the arrangement of the combustion chambers in the engine 30 and the like. Therefore, an error that is not related to the determination of abnormality has occurred.
Therefore, as shown in FIG. 2B, the output Y1t'of the regression equation is calculated in order to minimize the error.
After that, as shown in FIG. 2C, the value E1t obtained by subtracting the output Y1t'of the regression equation from the time series data Yt corresponding to the combustion chamber as the abnormality determination target is the upper limit statistical threshold value (1) described above at each time point. In FIG. 2 (c), when either the value indicated by α1: 5δ) or the lower limit statistical threshold value (value indicated by α2 in FIG. 2C: -5δ) is exceeded, that is, the upper limit statistical threshold value is exceeded to the higher side. In this case or when the lower limit statistical threshold is exceeded, it is determined that the abnormality degree E at each time point is high, and when both the upper limit statistical threshold value and the lower limit statistical threshold value are not exceeded, the abnormality degree E is determined to be low.
In the following, when it is described as "exceeding the upper limit statistical threshold value", it means "exceeding the upper limit statistical threshold value to the higher side", and when it is described as "exceeding the lower limit statistical threshold value", it means "exceeding the lower limit statistical threshold value". It shall mean "exceeding the lower limit statistical threshold to the lower side".

FIG. 3 illustrates a case where there are a plurality of combustion chambers as non-abnormality determination targets (in FIG. 3, two: i: [1, 2]).
If the combustion chamber as a non-abnormality determination target is more, will be statistically threshold value corresponding to each of the X _it is set, in the example shown in FIG. 3 (b), the upper statistical threshold corresponding to the X _1t The upper limit statistical threshold β1 (5δ in FIG. 3B) and the lower limit statistical threshold β2 (-5δ in FIG. 3B) corresponding to α1 and the lower limit statistical thresholds α2 and X _{2t are set.
The value D 1t} obtained by subtracting _{the output Y 1t'of the} regression equation from the _{time series data Y t} corresponding to the combustion chamber as the abnormality determination target sets either the upper limit statistical threshold α1 or the lower limit statistical threshold α2 corresponding to X _1t. than if, and, the abnormality determination value D _2t from series data Y _t by subtracting the output y2t 'regression formula when corresponding to the combustion chamber as a target, the upper statistical threshold β1 and lower statistical thresholds β2 corresponding to X _2t If it exceeds either one, the abnormality rate is set to 100% as shown at time point t1 in FIG. 3 (c).
_{The value D 1t} obtained by subtracting _{the output Y 1t'of the} regression equation from the _{time series data Y t} corresponding to the combustion chamber as the abnormality determination target does not exceed both the upper limit statistical threshold α1 and the lower limit statistical threshold α2 corresponding to X _1t. If, and, both from the time-series data Y _t corresponding to a combustion chamber of an abnormality determination target value D _2t obtained by subtracting the output _{y2t 'regression} equation, the upper statistical threshold β1 and lower statistical thresholds β2 corresponding to X _2t If it does not exceed, the anomaly rate is set to 0% as shown at time point t3 in FIG. 3 (c).
_{The value D 1t} obtained by subtracting _{the output Y 1t'of the} regression equation from the _{time series data Y t} corresponding to the combustion chamber as the abnormality determination target sets either the upper limit statistical threshold α1 or the lower limit statistical threshold α2 corresponding to X _1t. If it exceeds, or the value D _{2t obtained by subtracting the output Y 2t'of the} regression equation from the _{time series data Y t} corresponding to the combustion chamber as the abnormality judgment target, is the upper limit statistical threshold β1 and the lower limit statistical threshold β2 corresponding to X _2t. If any one of the above is exceeded, the abnormality rate is set to 50% as shown at time point t2 in FIG. 3 (c).

The abnormality determination unit M5 according to the embodiment determines, for example, that the combustion chamber as an abnormality determination target is in an abnormal state when the abnormality rate is 50% or more. That is, in the abnormality determination unit M5, the combustion chamber as the abnormality determination target is in an abnormal state based on the ratio of the plurality of abnormality degrees E derived by the abnormality determination unit M4 that are determined to have a high abnormality degree E. Determine if it is in.
As a result, it is possible to suppress erroneous determination of the abnormal state as compared with the case where the determination of the abnormal state is performed only by a single abnormality degree E.

The abnormality determination unit M5 is configured to be able to execute the determination of the above-mentioned abnormal state by changing the combustion chamber as the abnormality determination target, and sets all the targets as the abnormality determination targets, and whether or not they are in the abnormal state. Is configured to be determinable.

The abnormality determination device 100 according to the embodiment includes a determination accuracy adjusting unit M2 for adjusting the accuracy of determination as to whether or not the combustion chamber Co as an abnormality determination target is in the abnormal state.
The determination accuracy adjusting unit M2 increases the number of combustion chambers Co as non-abnormality determination targets selected by the selection unit M3 as the determination accuracy is adjusted to be high.
For example, the abnormality determination device 100 includes an operation unit (not shown) capable of adjusting the possibility of erroneous determination by an operation by the operator, and the erroneous determination adjustment unit M2 is based on the set value of the operation unit. Adjust the accuracy of the judgment.

Further, the abnormality determination device 100 includes a sensitivity adjusting unit M6 for adjusting the sensitivity of whether or not the combustion chamber as an abnormality determination target is in an abnormal state.
The sensitivity adjusting unit M6 reduces the magnification of the standard deviation of the time series data corresponding to the combustion chamber as the non-abnormality determination target when setting the statistical threshold value as the sensitivity is adjusted to be high.

In the abnormality determination, the correlation coefficient of the two time-series data selected from the time-series data corresponding to the plurality of objects is preferably 0.7 or more and 1 or less.

By using the abnormality determination device 100 described so far, the following abnormality determination method can be executed.
That is, in the abnormality determination method, a combustion chamber as one abnormality determination target is selected from a plurality of combustion chambers of one engine 30, and a combustion chamber other than the abnormality determination target is selected from a plurality of combustion chambers of one engine 30. The exhaust gas temperature (measured by the temperature sensor S1) corresponding to the combustion chamber as the abnormality determination target selected in the selection step in the selection step of selecting the combustion chambers as the plurality of non-abnormality determination targets and the predetermined derivation period. Temperature: an example of time-series data) as an explanatory variable, and the exhaust gas temperature corresponding to the combustion chamber as a non-abnormality determination target (temperature measured by the temperature sensor S1: an example of time-series data) as an explanatory variable. The regression equation is derived by executing the regression analysis, and the value obtained by subtracting the output of the regression equation from the time series data corresponding to the combustion chamber as the abnormality judgment target and the time series data corresponding to the combustion chamber as the non-abnormality judgment target. It is provided with an abnormality degree derivation step of deriving the abnormality degree E of the combustion apparatus as an abnormality determination target based on the statistical threshold value determined from the standard deviation of the above, and the selection process is performed in the combustion chamber as one abnormality determination target. On the other hand, a plurality of combustion chambers as non-abnormality determination targets are selected, and in the abnormality degree derivation step, one combustion chamber as an abnormality determination target and a plurality of non-abnormality determination targets selected in the selection step are selected. The degree of abnormality is derived for each of the combustion chambers of the above, and in the abnormality determination step, the combustion chamber as the abnormality determination target is in an abnormal state based on the degree of abnormality E derived in the abnormality degree derivation step. Judge whether or not.

[Another Embodiment]
(1) In the above embodiment, the abnormality determination is executed with a plurality of targets as determination targets. However, the determination target may be at least one of the plurality of targets.

(2) In the above embodiment, the abnormality determination device 100 is configured to execute the abnormality determination based on the measurement data acquired from the cogeneration system C via the network line N. Indicated.
However, the abnormality determination device 100 is provided side by side with each of the cogeneration system C, for example, and is configured to acquire measurement data from a plurality of targets and execute the abnormality determination without going through the network line N. May be adopted.
Further, the abnormality determination device 100 may adopt a configuration provided as a control device Cc of the cogeneration system C.
Further, the abnormality determination device 100 is provided in parallel with a monitoring device that monitors the cogeneration system C based on the measurement data acquired from the cogeneration system C via the network line N, and is provided as a storage unit of the monitoring device. The configuration may be such that the abnormality determination is executed in the form of acquiring the measurement data from.

(3) The abnormality determination device 100 may employ, for example, a configuration including a steady state determination unit (not shown) for determining whether or not the target is in a steady state from time series data, and an abnormality degree derivation unit may be adopted. The M4 may be configured to derive the abnormality degree E of the abnormality determination target based on the time-series data determined by the steady state determination unit to be in the steady state.
By adopting this configuration, the abnormality degree E can be derived based on stable time-series data, so that the possibility of erroneous determination (erroneous detection) of the abnormal state can be further reduced.

(4) Although the configuration including the erroneous determination adjusting unit M2 and the sensitivity adjusting unit M6 is shown in the above embodiment, the object of the present invention can be satisfactorily achieved even if the configuration does not include these. ..

(5) In the above embodiment, an example is shown in which a plurality of combustion chambers Co of one engine 30 are targeted, and the temperature (exhaust gas temperature) in each of the combustion chambers Co is used as a parameter.
However, the knocking strength detected by the knock sensor S2 described above may be used as a parameter.

(6) Each of the engines 30 of the plurality of cogeneration systems C connected to the abnormality determination device 100 via the network line N is determined to be in a steady state by, for example, the steady state determination unit shown in the above another embodiment. If so, the number of revolutions may be highly correlated.
Therefore, each of the engines 30 of the plurality of cogeneration systems C connected to the abnormality determination device 100 via the network line N is adopted as a plurality of targets, and the rotation speed sensor S3 for measuring the rotation speed of the engine 30 is measured. The result may be adopted as a parameter.

(7) As a plurality of targets, a plurality of servers that constantly communicate with each other can be adopted, and in this case, the data communication amount of each server is adopted as a parameter.
Further, as a plurality of objects, a plurality of bearings supporting one power generation shaft of one power generation facility can be adopted, and in this case, the vibration frequency of each bearing is adopted as a parameter.
Further, as a plurality of targets, the weather conditions of a plurality of adjacent areas can be adopted, and in this case, the temperature and humidity of each of the plurality of areas are adopted as parameters. In this case, a tornado or the like that suddenly occurs is assumed as the abnormal state.

(8) In the above embodiment, an example in which the regression equation is a linear equation is shown. However, the regression equation may be an equation in which ai = 1 and bi is derived.

(9) In the above embodiment, the abnormality degree derivation unit M4 shows an example of deriving the abnormality degree at each time point in a predetermined derivation period.
However, the abnormality degree derivation unit M4 is not limited to each pinpoint time point in the predetermined derivation period, and may separately adopt a configuration in which the anomaly degree is derived in a derivation period having a certain width. ..

The configuration disclosed in the above embodiment (including another embodiment, the same shall apply hereinafter) can be applied in combination with the configuration disclosed in other embodiments as long as there is no contradiction. The embodiments disclosed in the present specification are examples, and the embodiments of the present invention are not limited thereto, and can be appropriately modified without departing from the object of the present invention.

The abnormality determination device and the abnormality determination method of the present invention capture minute abnormalities with high detection accuracy while increasing the determination accuracy (while suppressing erroneous determination), and also consider the individual properties of the data group. It can be effectively used as an abnormality determination device and an abnormality determination method that can execute abnormality determination without requiring the setting of the threshold value.

100: Abnormality determination device C: Cogeneration system E: Abnormality degree M2: False determination adjustment unit M3: Selection unit M4: Abnormality degree derivation unit M5: Abnormality determination unit M6: Sensitivity adjustment unit X _it : Time series data Y _it ': Output Y _t : Time series data α1: Upper limit statistical threshold α2: Lower limit statistical threshold β1: Upper limit statistical threshold β2: Lower limit statistical threshold δ: Standard deviation

Claims (6)

As time-series data of parameters measured in each of a plurality of objects, a plurality of time-series data of the temperature of exhaust gas measured in each exhaust passage corresponding to a plurality of combustion chambers provided in one engine . An abnormality determination device including an abnormality determination unit that determines an abnormality of the target.
A selection unit that selects one abnormality determination target as the target for abnormality determination from the plurality of said targets and selects a plurality of non-abnormality determination targets other than the abnormality determination target from the plurality of said targets.
Regression analysis using the time-series data corresponding to the abnormality determination target selected by the selection unit as the explained variable and the time-series data corresponding to the non-abnormality determination target as the explanatory variable in a predetermined derivation period. Is executed to derive the regression equation, and it is determined from the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target and the standard deviation of the time series data corresponding to the non-abnormality determination target. An abnormality degree deriving unit for deriving the abnormality degree of the abnormality determination target based on the statistical threshold value to be obtained is provided.
The selection unit selects a plurality of the non-abnormality determination targets with respect to the abnormality determination target.
The correlation coefficient between the time-series data corresponding to the abnormality determination target and the time-series data corresponding to the non-abnormality determination target is a high correlation of 0.7 or more and 1 or less.
The abnormality degree derivation unit derives the abnormality degree with respect to one said abnormality determination target and each of a plurality of the non-abnormality determination targets selected by the selection unit.
The abnormality determining unit, on the basis of the degree of abnormality derived by the abnormality degree deriving unit is intended for determining whether or not the abnormality determination target is in an abnormal state,
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is the standard deviation of the time series data corresponding to the non-abnormality determination target. When the statistical threshold determined from is exceeded, it is derived that the degree of abnormality in the derivation period is high.
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is determined from the standard deviation of the time series data corresponding to the non-abnormality determination target. When the following, it is derived that the degree of abnormality in the derivation period is low.
The anomaly degree derivation unit is used in deriving the anomaly degree.
The upper limit statistical threshold value as the statistical threshold value is set to a value of 3 times or more and 5 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
The lower limit statistical threshold value as the statistical threshold value is set to a value of -5 times or more and -3 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
When at least one of the plurality of abnormalities derived by the abnormality degree deriving unit is derived to be equal to or higher than a predetermined reference value, the abnormality determination unit determines that the abnormality determination target is in an abnormal state. .. The abnormality determination unit determines whether or not the abnormality determination target is in an abnormal state based on the ratio derived when the abnormality degree is high among the plurality of the abnormality degrees derived by the abnormality degree derivation unit. The abnormality determination device according to claim 1. A steady state determination unit for determining whether or not the target is in a steady state from the time series data is provided.
The first or second aspect of the present invention, wherein the abnormality degree derivation unit derives the abnormality degree of the abnormality determination target based on the time series data determined by the steady state determination unit to be in the steady state. Abnormality judgment device. It is provided with an erroneous determination adjusting unit for adjusting the possibility of erroneous determination as to whether or not the abnormality determination target is in the abnormal state.
According to any one of claims 1 to 3, the erroneous determination adjusting unit increases the number of non-abnormality determination targets selected by the selection unit as the possibility of erroneous determination is adjusted to be low. The above-mentioned abnormality determination device. A sensitivity adjusting unit for adjusting the sensitivity of whether or not the abnormality determination target is in the abnormal state is provided.
The first aspect of the present invention, wherein the sensitivity adjusting unit reduces the magnification of the standard deviation of the time series data corresponding to the non-abnormality determination target when setting the statistical threshold value as the sensitivity is adjusted to be high. abnormality determination device. As time-series data of parameters measured in each of a plurality of objects, a plurality of time-series data of the temperature of exhaust gas measured in each exhaust passage corresponding to a plurality of combustion chambers provided in one engine . An abnormality determination method including an abnormality determination step for determining an abnormality of the target.
A selection step of selecting one abnormality determination target as the target for abnormality determination from a plurality of the targets and selecting a plurality of non-abnormality determination targets other than the abnormality determination target from the plurality of the targets.
The time-series data corresponding to the abnormality determination target selected in the selection step is used as the explained variable, the time-series data corresponding to the non-abnormality determination target is used as the explanatory variable, and regression analysis is executed to perform a regression equation. Is derived, and in a predetermined derivation period, it is determined from the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target and the standard deviation of the time series data corresponding to the non-abnormality determination target. It is provided with an abnormality degree derivation step for deriving the abnormality degree of the abnormality determination target based on the statistical threshold value to be obtained.
In the selection step, a plurality of the non-abnormality determination targets are selected for one abnormality determination target.
The correlation coefficient between the time-series data corresponding to the abnormality determination target and the time-series data corresponding to the non-abnormality determination target is a high correlation of 0.7 or more and 1 or less.
The abnormality degree derivation step derives the abnormality degree with respect to one said abnormality determination target and each of the plurality of non-abnormality determination targets selected in the selection step.
The abnormality determining step, based on the degree of abnormality derived by the abnormality degree deriving step is intended for determining whether or not the abnormality determination target is in an abnormal state,
In the abnormality degree derivation step, in the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is the standard deviation of the time series data corresponding to the non-abnormality determination target. When the statistical threshold determined from is exceeded, it is derived that the degree of abnormality in the derivation period is high.
In the derivation period, the value obtained by subtracting the output of the regression equation from the time series data corresponding to the abnormality determination target is determined from the standard deviation of the time series data corresponding to the non-abnormality determination target. When the following, it is derived that the degree of abnormality in the derivation period is low.
The abnormality degree derivation step is performed in the derivation of the abnormality degree.
The upper limit statistical threshold value as the statistical threshold value is set to a value of 3 times or more and 5 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
The lower limit statistical threshold value as the statistical threshold value is set to a value of -5 times or more and -3 times or less of the standard deviation of the time series data corresponding to the non-abnormality determination target.
When at least one of the plurality of abnormalities derived by the abnormality degree deriving step is derived to be equal to or higher than a predetermined reference value, the abnormality determination step determines that the abnormality determination target is in an abnormal state. ..

Images