JPH0750491B2 - Quality diagnosis knowledge adjustment method - Google Patents

Description

TECHNICAL FIELD The present invention relates to a knowledge adjustment method used for quality diagnosis in a manufacturing process such as a steel process. Quality diagnosis contributes to the prevention of defective quality characteristics by promptly predicting and evaluating quality characteristics based on the current operating conditions and taking corresponding measures.

[Prior Art] Conventionally, quality diagnosis in a manufacturing process such as a steel process has been performed when quality characteristics can be quantitatively predicted by a mathematical model. However, quality characteristics are often not quantitatively predictable. At that time, a quality diagnosis system is developed by a qualitative or fragmentary empirical rule by a knowledge engineering method such as a rule base.

[Problems to be Solved by the Invention] However, a fixed method has not been established as a knowledge base adjustment method used in this new type of quality diagnosis system, and it is performed by trial and error for each system. The current situation.

The present invention provides a method of adjusting a knowledge base used for quality diagnosis based on an empirical rule of a specialist in a manufacturing process by using a quality prediction value and an actual value, and knowledge adjustment under one standard quality diagnosis method. The purpose is to provide a method.

[Means for Solving the Problems] A quality diagnosis knowledge adjusting method of the present invention is to classify a plurality of operation record data used for quality prediction in a manufacturing process by a deviation from a target value thereof and to perform a plurality of diagnosis. For each quality characteristic item, the deduction value of the quality characteristic due to the deviation of the operation data from the target value is obtained by using the relationship between the rank value of the operation data and the deduction value, and each deduction value for each quality characteristic item. By summing up and subtracting from the deduction value to obtain the evaluation value, and calculating the total value of deductions for each operation data item and arranging them in ascending order, the score display and operation data for each quality characteristic item In the quality diagnosis in which the operation instructions of the above are performed in the order of importance, multiple sets of actual data of the same product standard are selected, and the target value and the actual value of the operation data and each quality characteristic item are selected. The details of the predicted deductions of the operating performance data, the total of the predicted deductions and the actual deductions are displayed in a list on the screen, and the quality prediction knowledge for which operation data item of which quality characteristic item is misaligned is displayed. It consists of inspiring and modifying the knowledge base.

[Operation] A plurality of sets of performance data of the same product standard are selected by an operating engineer who adjusts the knowledge base. For each one of them, the difference between the target value and the actual value of the operation data is recognized, the predicted deduction points of each operation data are displayed for each quality characteristic item at that time, and the total predicted deduction points and the actual deduction points are displayed. It The quality prediction knowledge of which quality characteristic item and which operation data item does not match the actual situation is considered in comparison with daily experience, and the correction is applied to the knowledge base.

[Embodiment] Next, an embodiment of the present invention will be described with reference to the drawings.

In the examples, the knowledge adjustment of the quality diagnosis regarding the film characteristics of the grain-oriented electrical steel sheet will be described. The quality of the coating is diagnosed based on the experience data of the decarburization line based on the experience of a specialist, and the performance of the coating is obtained after about 10 days.
Therefore, the occurrence of coating defects during that time is prevented by this quality diagnosis.

FIG. 1 shows the configuration of a film diagnostic system using a knowledge base adjusted by the knowledge adjusting method of the present invention. The operation result data is input and the quality is evaluated by the inference engine based on this knowledge base. The evaluation value and the like are output in an easy-to-understand manner as a display of the quality diagnosis result.

FIG. 2 shows an overall flow chart of this coating quality diagnosis method.
In step 1 of FIG. 2, the operation result data of the decarburization line is ranked according to the deviation from the target value. Each range of this rank classification is given for each steel grade standard.

FIG. 3 shows an example of the range of each rank for classifying the knowledge for film prediction. In this example, 10 types of operation performance data are up to 7 depending on the deviation from the target value.
Layered to rank.

In step 2 of FIG. 2, a deduction value is calculated for each film quality characteristic item to be diagnosed. For details of this calculation method,
Next, description will be given with reference to FIG.

Briefly, as coating quality characteristics, peroxidation flaw, insufficient oxidation, decarburization abnormality, etc. are evaluated. FIG. 3 shows the score prediction knowledge about the peroxide flaw A, and the operation pattern in which the quality defect occurs is indicated by a thick line. This quality characteristic is
It is evaluated with a maximum of 80 points, and when it shows the largest pattern, it has a predicted score of 40 points.

In addition, the contribution ratio of failure of each operation data is 70%, 5%, 10%,
... is given.

By using this knowledge, it is possible to obtain how much the deviation (rank value) from the target value of each operation data is deducted from the quality characteristic score. For example, if the No. 2 result of the operation result data is rank 6, the deduction value of the evaluation value due to the deviation of the target value of this part is (80-40) × 70/100 as the calculation result of 28 points. Is calculated. For any rank smaller than rank 6, the multiplication coefficient from 0 to 1.0 is calculated by the designated function, and the value is multiplied by the deduction value.
The multiplication coefficient is selected from a plurality of functions shown in FIG. 7 in accordance with the actual phenomenon.

Therefore, if the number 4 function in Fig. 7 is selected when the rank is 5 in the above example, the calculated result of 28 points x log ₄ 3 is 22.
2 is the deduction value. In this way, the deduction value resulting from the deviation from the target value of the operation result data for one coating quality characteristic is obtained.

Other coating quality characteristics are also obtained with similar predictive knowledge.

Referring again to FIG. 2, in step 3, the total of the deduction values of the operation result data is calculated for each film quality characteristic item,
The total value is subtracted from each full score value.

Further, in step 4, a deduction value for each coating quality characteristic item is calculated for each item of operation data.

An example of the calculation performed in steps 3 and 4 is shown in FIG.
In FIG. 4, the vertical direction represents coating quality characteristic items,
The horizontal direction shows operation data items. Each numerical value in the central part indicates the deduction value of each item, the total deduction value of the operation result data for each coating quality characteristic item is shown on the right end, and the total deduction value for each operation data item is shown on the lower end. There is. The larger this value is, the more important it is to improve the quality characteristics. Therefore, in the operation instruction of the operation data, the operation data items are listed from the larger operation data item.

FIG. 5 shows an overall flow chart of the quality diagnosis knowledge adjusting method of the present invention. In step 1 of FIG. 5, dozens of sets of data of the same steel grade standard are selected from the performance data file. Further, in step 2, quality prediction is performed by the method shown in FIG. 2 using the above-mentioned actual data in the current knowledge base. In the next step 3, the quality predictive value and the quality actual value are displayed on the screen as shown in FIG. 6 so that the part of the quality predictive knowledge that does not match the actual condition is conceived. In the next step 4, the knowledge base is modified. In this modification, the knowledge table corresponding to the quality prediction knowledge is modified, and the values in the table are automatically converted into the knowledge base.

After the correction of the knowledge base, the process returns to step 2 of FIG. 5, the quality is predicted, and the same adjustment is performed.

FIG. 6 shows a verification screen for inventing an adjustment part of the knowledge base. Although it is almost the same as the screen in FIG. 4, the actual film property deduction point value is displayed below the predicted value. From this screen, the difference between the target value and the actual value of the operation data is recognized, the predicted demerit degree given by each operational result data for each coating characteristic item at that time is also recognized, and the total coating characteristic predicted deduction point and the actual deduction point are also recognized. The difference is recognized. From this, it can be inferred from the comparison with daily experience how much the quality prediction knowledge for which coating characteristic item and which operation data item does not match the actual.

[Effects of the Invention] As described above, according to the present invention, it is possible for an operation engineer to adjust a knowledge base of a routine quality diagnosis of a manufacturing process, and finely improve the performance of this quality diagnosis system. . As a result, the occurrence of quality defects can be prevented and a great effect can be obtained in improving the quality of the manufacturing process.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of a system for carrying out the present invention. FIG. 2 is an overall flow chart of the coating quality diagnosis method of one embodiment. FIG. 3 is a map showing the contents and divisions of the film prediction knowledge of one embodiment. FIG. 4 is a map showing the deduction point predicted value and the total value in the embodiment. FIG. 5 is an overall flow chart of the quality diagnosis knowledge adjusting method of the embodiment. FIG. 6 is a front view showing the quality diagnosis knowledge verification screen of the embodiment. FIG. 7 is a map showing allocation of multiplication coefficient calculation formulas in the embodiment.

Claims (1)

[Claims] 1. In a manufacturing process, a plurality of operation record data used for quality prediction are ranked according to deviations from the target value, and a plurality of quality characteristic items to be diagnosed from the target value of the operation data. The deduction value of the quality characteristic due to the deviation of the quality characteristic is obtained by using the relationship between the rank value of the operation data and the demerit value, and the demerit value is summed up for each quality characteristic item and subtracted from the full value. By obtaining the evaluation value, and obtaining the total value of each deduction for each operation data item and rearranging in order of higher, in the quality diagnosis in which the score display of each quality characteristic item and the operation instruction of the operation data are performed in the order of importance, Select multiple sets of performance data of the same product standard, and the target value and the performance value of the operation data, and the breakdown of the operation performance data for each quality characteristic item and the total of the points. It is characterized in that the knowledge base is corrected by inventing the quality prediction knowledge for which operation characteristic data item of which quality characteristic item is shifted by sequentially displaying the list of measured deduction point values and the actual deduction point values on the screen. Quality diagnosis knowledge adjustment method.