JP2019040272A - Quality monitoring system and program - Google Patents

Abstract

To suppress the erroneous determination of quality in a batch process.SOLUTION: A quality monitoring system comprises: a result information acquisition unit for acquiring information that indicates the quality of a plurality of products produced in a batch process and values of process variables in the batch process; a start timing decision unit for deciding a timing of start with reference to each of a plurality of batches in the batch process on the basis of the comparison results of values of process variables and a first threshold; a quality determination unit for determining the quality of each of the plurality of products on the basis of the values of process variables in a batch processing period that starts from the start timing with respect to each of the plurality of batches; and a start timing information decision unit for deciding the process variables and the first threshold used for the decision of start timing so that the degree of coincidence between each quality of the plurality of products determined by the quality determination unit and each quality of the plurality of products acquired by the result information acquisition unit exceeds a predetermined value.SELECTED DRAWING: Figure 5

Description

  The present invention relates to a quality monitoring system and a program.

A system for monitoring on-line transient operation in a continuous casting process is known (see, for example, Patent Document 1).
Patent Document 1 US Pat. No. 6,885,907

  In a batch process, the processing time of each batch can vary depending on external conditions such as temperature. In addition, the measurement of the state quantity of each batch may be started before the actual process start timing in order to prevent measurement data near the batch start timing from being lost. Further, the value of the process variable can include an influence such as measurement noise. For this reason, there has been a problem that erroneous determination of quality is likely to occur when determining the quality of a product based on the value of a process variable.

  In a first aspect, a quality monitoring system is provided. The quality monitoring system includes a performance information acquisition unit that acquires information indicating the quality of each of a plurality of products manufactured in a batch process and the values of process variables in the batch process. The quality monitoring system may include a start timing determination unit that determines a start timing of each of the plurality of batches in the batch process based on a comparison result between the value of the process variable and the first threshold value. The quality monitoring system may include a quality determination unit that determines the quality of each of the plurality of products based on the value of the process variable within the batch processing period starting from the start timing for each of the plurality of batches. The quality monitoring system is such that the degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit and the quality of each of the plurality of products acquired by the record information acquisition unit exceeds a predetermined value. You may provide the start timing information determination part which determines the process variable and 1st threshold value which are used in order to determine a start timing.

  The quality determination unit, for each of the plurality of batches, based on a comparison result between the quality determination index calculated based on the value of the process variable within the batch processing period starting from the start timing and the second threshold, The quality of each may be determined.

  The quality monitoring system may determine a product quality abnormality based on a comparison result between the quality determination index and the second threshold. Based on the information indicating the quality acquired by the record information acquisition unit and the determination result of the quality determination unit, the quality monitoring system has at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit. A quality determination threshold value determining unit that determines the second threshold value may be provided so as to be lower than a predetermined value.

  The quality determination threshold value determination unit is configured so that the degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit and the quality of each of the plurality of products acquired by the record information acquisition unit exceeds a predetermined value. In addition, the second threshold may be determined.

  In the second aspect, the quality monitoring system may include a performance information acquisition unit that acquires information indicating the quality of each of a plurality of products manufactured in a batch process and the value of a process variable in the batch process. For each of a plurality of batches in a batch process, the quality monitoring system determines the quality abnormality of a plurality of products based on the comparison result between the quality judgment index calculated based on the value of the process variable within the batch processing period and the threshold value. You may provide the quality determination part to determine. Based on the information indicating the quality acquired by the performance information acquisition unit and the determination result of the quality determination unit, the quality monitoring system has at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit in advance. You may provide the quality determination threshold value determination part which determines a threshold value so that it may become lower than the defined value.

  In the third aspect, the quality monitoring system may include a performance information acquisition unit that acquires information indicating the quality of each of a plurality of products manufactured in a batch process and the value of a process variable in the batch process. The quality monitoring system may include a start timing determination unit that determines a start timing of each of the plurality of batches in the batch process based on a comparison result between the value of the process variable and the first threshold value. The quality monitoring system, for each of the plurality of batches, based on the comparison result between the quality determination index calculated based on the value of the process variable within the processing time starting from the start timing and the second threshold value, You may provide the quality determination part which determines quality abnormality. Based on the information indicating the quality acquired by the performance information acquisition unit and the determination result of the quality determination unit, the quality monitoring system has at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit in advance. You may provide the determination part which determines the process variable and 1st threshold value which are used in order to determine a start timing, and a 2nd threshold value so that it may become lower than the defined value.

  In a fourth aspect, a program is provided. The program causes the computer to function as the quality monitoring system described above.

  The summary of the invention does not enumerate all the features of the present invention. In addition, a sub-combination of these feature groups can also be an invention.

1 shows an example of a device configuration of a process monitoring system 100 according to an embodiment. An example of the data measured in the monitoring object 20 is shown. Process variable data in each batch stored in the process operation database 30 is schematically shown. The process which determines the start timing of the calculation period of a quality determination parameter | index is shown typically. The function structure of the quality monitoring system 10 is shown schematically. An example of performance information stored in the quality database 40 is shown. It is a table which shows an example which evaluates a quality judgment result. The confusion matrix for product normality / abnormality judgment is shown. It is a table | surface which shows the change of the quality determination result by changing a quality determination threshold value. The effect obtained by the change of the quality judgment threshold is shown. It is a table | surface which shows the change of the quality determination result by changing the threshold value for starting timing determination. The effect obtained by the change of the threshold value for starting timing determination is shown. It is a table | surface which shows the quality determination result with respect to the combination of the threshold value for starting timing determination, and a quality determination threshold value. The effect obtained by changing the start timing determination threshold and the quality determination threshold is shown. 2 is a flowchart regarding processing executed by the quality monitoring system 10;

  Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all the combinations of features described in the embodiments are essential for the solving means of the invention.

  FIG. 1 shows an example of a device configuration of a process monitoring system 100 according to an embodiment. The process monitoring system 100 includes a quality monitoring system 10, a monitoring target 20, a process operation database 30, and a quality database 40. The quality monitoring system 10, the monitoring target 20, the process operation database 30, and the quality database 40 are connected through the network 90 and exchange data through the network 90.

  The monitoring target 20 includes a device or plant that performs processing by a batch process to be monitored, a control device that controls the device or plant, and the like. A batch process is a process that divides raw materials and intermediate products into a certain amount of production units, such as a film production process in a petrochemical plant or a blowing process in an iron manufacturing plant, and processes each production unit. The process that repeats this manufacturing unit process by repeatedly using the same equipment.

  The process operation database 30 stores process variable data such as measurement data and manipulated variables in the monitoring target 20 in association with batch numbers. The quality monitoring system 10 acquires data stored in the process operation database 30 and outputs a quality determination result that is a result of product quality determination. For example, the quality monitoring system 10 performs a multivariate analysis on the process variable, calculates a quality determination index for determining normality / abnormality of the product, and for quality determination for determining abnormality of the quality of the product Based on the comparison result between the threshold and the quality determination index, the quality abnormality is determined. The quality determination index can be used as an index representing the degree of abnormality of a product being manufactured in a batch process. The quality determination result by the quality monitoring system 10 can be used when final determination of product abnormality of the product is performed.

  The quality monitoring system 10 determines whether the product is normal or abnormal in consideration of data obtained in the past batch process. The quality database 40 stores information indicating the quality of products manufactured in the past in the monitoring target 20. For example, the quality database 40 stores a batch number of a product whose quality is determined to be normal and a batch number of a product whose quality is determined to be abnormal. The quality monitoring system 10 uses the data stored in the process operation database 30 and the quality database 40 to determine the quality determination threshold value offline so that a desired false detection rate and detection failure rate can be obtained. Further, the quality monitoring system 10 determines information for determining a period for calculating the quality determination index. The period during which the quality determination index is calculated will be described with reference to FIGS.

  FIG. 2 shows an example of data measured on the monitoring target 20. In the monitoring target 20, pressure, temperature, and the like are measured as state quantities in the batch process. The measured data is stored in the process operation database 30 as a process variable. The start timing and end timing of each batch are determined by the control device in the monitoring target 20. Based on the start timing and end timing of each batch, input of raw materials, removal of products, and the like are performed.

  FIG. 3 schematically shows time-series data of process variables in a plurality of batches stored in the process operation database 30. As shown in FIG. 3, in an actual process, the processing time of one batch varies among a plurality of batches depending on external conditions such as product type, temperature, and humidity. Further, in order to prevent data loss near the start point, measurement may be started before the start of the process. Therefore, there may be a deviation in the actual batch processing start timing among a plurality of batches. Therefore, if the quality determination index is calculated using the values of the process variables for the entire period from the start timing to the end timing determined by the monitoring target 20, an erroneous determination may easily occur in the product quality determination.

  FIG. 4 schematically shows processing for determining the start timing of the quality determination index calculation period. FIG. 4 shows temperature and pressure changes over time as an example of process variables. In the manufacturing process, there are cases where the temperature and pressure are changed in order to manufacture a product, and the temperature and pressure are changed during the manufacturing process of the product. In such a case, there is a possibility that the substantial processing start timing in each batch can be determined using changes in temperature and pressure.

For example, FIG. 4A shows the time change of temperature in one batch from time t0. Time t0 is the start timing of the entire batch, and measurement data from time t0 is acquired as batch data. Here, when the threshold value T for determining the start timing with respect to the temperature is set, the time t _T when the temperature has substantially increased can be regarded as the timing at which the substantial process has started.

Similarly, FIG. 4B shows a change in pressure over time in one batch from time t0. Setting the start timing determination threshold P to pressure, the time t _p substantially pressure rises, it can be regarded as a timing substantial processing is started.

The quality monitoring system 10, as the start timing the time t _T or time t _p, calculates a quality judgment indicator from a process variable of a process time to the end time. As a result, the quality determination index can be calculated by substantially excluding the period in which the temperature and pressure are not actually changing. For example, the data immediately after the time t0, but includes information before substantial processing is started, the start timing of the time t _T and the time t _p, by calculating the quality determination index, substantially It is possible to reduce the influence of the information before the start of the processing on the quality determination index.

  As described above, the quality monitoring system 10 determines the start timing in the batch data using the process variable, calculates the quality determination index based on the process variable from the determined start timing, and monitors the quality abnormality. As a result, it is possible to suppress erroneous determination due to deviation of the start timing.

  FIG. 5 schematically shows a functional configuration of the quality monitoring system 10. The quality monitoring system 10 includes a start timing adjustment unit 300, a quality determination index calculation unit 310, a quality determination unit 320, a performance information acquisition unit 280, and a determination information determination unit 270. The determination information determination unit 270 includes a start timing determination unit 200, a start timing information determination unit 220, a quality determination unit 210, and a quality determination threshold determination unit 230.

  First, the operation of the determination information determination unit 270 will be described. The performance information acquisition unit 280 acquires information indicating the quality of each of a plurality of products manufactured by the batch process and the values of process variables in the batch process. Specifically, the determination information determination unit 270 acquires from the process operation database 30 the values of process variables in a batch process of products manufactured in the past. In addition, the determination information determination unit 270 acquires information indicating the quality of a product manufactured in the past from the quality database 40. In the description of the present embodiment, information acquired from the process operation database 30 and the quality database 40 may be collectively referred to as performance information.

  The start timing determination unit 200 determines the start timing of each of a plurality of batches in the batch process based on the comparison result between the process variable value and the start timing determination threshold. The start timing determination threshold is an example of a first threshold.

  The quality determination unit 210 determines the quality of each of the plurality of products based on the value of the process variable within the batch processing period starting from the start timing determined by the start timing determination unit 200 for each of the plurality of batches. The start timing information determination unit 220 is a value in which the degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit 210 and the quality of each of the plurality of products acquired by the record information acquisition unit 280 is determined in advance. The process variable used for determining the start timing and the threshold for determining the start timing are determined so as to exceed. A process variable used for determining the start timing may be referred to as a start timing determination variable.

  For each of a plurality of batches in the batch process, the quality determination unit 210 determines the quality abnormality of the plurality of products based on the comparison result between the quality determination index calculated based on the value of the process variable within the batch processing period and the threshold value. Determine. Specifically, the quality determination unit 210 includes, for each of the plurality of batches, a quality determination index calculated based on the value of the process variable within the batch processing period starting from the start timing determined by the start timing information determination unit 220. Based on the comparison result with the quality determination threshold value, the quality of each of the plurality of products is determined. The quality determination threshold value is an example of a second threshold value.

  The quality determination index may be a statistic. The quality determination unit 210 calculates a quality abnormality index using a quality model constructed by a multivariate analysis method such as multiple regression analysis (MLR), principal component analysis (PCA), or partial least squares (PLS). It's okay. When quality monitoring based on multivariate statistical process management is performed in the quality monitoring system 10, Q statistics, T2 statistics, and the like can be applied as quality determination indexes. When performing quality monitoring based on the Mahalanobis Taguchi method, the Mahalanobis distance can be applied as a quality judgment index.

  The quality determination unit 210 determines product quality abnormality based on the comparison result between the quality determination index and the quality determination threshold. The quality determination threshold value may be a threshold value for determining whether or not the quality determination index exceeds a management limit.

  Based on the information indicating the quality acquired by the record information acquisition unit 280 and the determination result of the quality determination unit 210, the quality determination threshold value determination unit 230 detects the detection omission rate and erroneous detection of a product having a quality abnormality by the quality determination unit 210. The quality determination threshold is determined so that at least one of the rates is lower than a predetermined value. Further, the quality determination threshold value determination unit 230 determines in advance the degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit 210 and the quality of each of the plurality of products acquired by the record information acquisition unit 280. The quality determination threshold value may be determined so as to exceed the measured value.

  Note that the start timing information determination unit 220 and the quality determination threshold determination unit 230 are based on the information indicating the quality acquired by the performance information acquisition unit 280 and the determination result of the quality determination unit 210, and the quality abnormality by the quality determination unit 210. Determine the process variable used for determining the start timing, the threshold for determining the start timing, and the quality judgment threshold so that at least one of the detection omission rate and the false detection rate of a product is lower than a predetermined value. It can function as a determination unit.

  The start timing determination threshold and the start timing determination variable determined by the start timing information determination unit 220 are set in the start timing determination threshold 330 and the start timing determination variable 340, respectively. The quality determination threshold value determined by the quality determination threshold value determination unit 230 is set as the quality determination threshold value 350. The start timing determination threshold 330, the start timing determination variable 340, and the quality determination threshold 350 may be stored in a nonvolatile memory.

  The process of the determination information determination unit 270 is determined to be performed offline. Online product abnormality determination is performed by the functional blocks of the start timing adjustment unit 300, the quality determination index calculation unit 310, and the quality determination unit 320.

  The start timing adjustment unit 300, the quality determination index calculation unit 310, and the quality determination unit 320 are functional blocks for performing quality monitoring on the monitoring target 20. The start timing adjustment unit 300 acquires process variables obtained in a batch process for manufacturing a start target product from the process operation database 30. The start timing adjustment unit 300 generates time series data for calculating a quality determination index, and provides the time determination data to the quality determination index calculation unit 310.

  Specifically, the start timing adjustment unit 300 extracts time series data of the start timing determination variable 340 from the process series time series data acquired from the process operation database 30. Then, the start timing adjustment unit 300 determines the start timing based on the extracted time series data and the start timing determination threshold 330. The start timing adjustment unit 300 cuts out data after the determined start timing from the time series data of the process variables acquired from the process operation database 30 and provides the data to the quality determination index calculation unit 310. The start timing adjustment unit 300 uses the timing at which the start timing determination variable exceeds the start position determination threshold as the start timing, and similarly extracts data from other process variables. Thereby, it is possible to substantially align the start timing with other product batches.

  According to the start timing adjustment unit 300, the start timing is determined using two parameters, which variable is the start timing determination variable and which value is the start position determination threshold value. Process time series data can be adjusted. As described above, the two parameters are determined offline by the start timing information determination unit 220.

  The quality determination index calculation unit 310 calculates a quality determination index based on the time series data of the process variables provided from the quality determination index calculation unit 310. The quality determination index may be a Q statistic, a T2 statistic, a Mahalanobis distance, or the like.

  The quality determination unit 320 determines the quality of the product based on the comparison result between the quality determination index calculated by the quality determination index calculation unit 310 and the quality determination threshold value 350. For example, the quality determination unit 320 may determine that the quality of the product is abnormal when the quality determination index calculation unit 310 is equal to or higher than the quality determination threshold value 350. The quality determination process performed by the functional blocks of the quality determination index calculation unit 310 and the quality determination unit 320 may be the same as the quality determination process performed by the quality determination unit 210.

  The quality monitoring system 10 may be realized by a computer including a processor and a memory. The program may cause the computer to function as the quality monitoring system 10. For example, the function of each part with which the quality monitoring system 10 is provided may be implement | achieved when a processor controls each part of a computer according to a program.

  FIG. 6 shows an example of performance information stored in the quality database 40. The quality database 40 stores the quality determination result in association with the batch number. The batch number is information that identifies the batch that manufactured the product. One batch number is assigned to each product. The quality determination result shown in FIG. 6 is a finally determined determination result. For example, the quality determination result of FIG. 6 may be a determination result determined by performing a performance inspection of a manufactured product.

  In the present embodiment, “◯” indicates that the product is determined to be normal, and “X” indicates that the product is determined to be abnormal. In the present embodiment, a product that is finally determined to be normal may be referred to as a “normal quality product”, and a product that is ultimately determined to be abnormal may be referred to as an “abnormal quality product”. is there.

  FIG. 7 shows an example of evaluating the quality determination result. In FIG. 7, the left area toward the paper is a plot of quality determination indexes based on the batch data of normal quality products. The area on the right side of the page is a plot of quality determination indexes based on batch data of abnormal quality products.

  In the quality monitoring system 10, the quality determination unit 320 determines that a product from which a quality determination index less than the quality determination threshold is obtained is normal. Moreover, the quality determination part 320 determines that the product from which the quality determination index more than a quality determination threshold value was obtained is abnormal. Therefore, the product belonging to the area 700b indicates that a normal quality product is determined to be abnormal. That is, it indicates that a normal quality product is erroneously detected as an abnormal quality product. Further, it indicates that the product belonging to the region 700c is determined to be normal although it has an abnormal quality. That is, it indicates a detection failure of an abnormal quality product.

  FIG. 8 shows a confusion matrix in product normality / abnormality determination. a indicates the number of products determined to be normal based on the quality determination index among normal quality products. b indicates the number of products determined to be abnormal based on the quality determination index among normal quality products. c indicates the number of products determined to be normal based on the quality determination index among products of abnormal quality. d indicates the number of products determined to be abnormal based on the quality determination index among products of abnormal quality.

  The false detection rate indicates the ratio of the number of products determined to be abnormal based on the quality determination index to the number of products of normal quality. The false detection rate is calculated by a / (a + b). The detection omission rate indicates the ratio of the number of products determined not abnormal based on the quality determination index to the number of products of abnormal quality. The detection omission rate is calculated by c / (c + d). In the quality monitoring system 10, the quality determination threshold value determination unit 230 adjusts the quality determination threshold value so that both the detection omission rate and the false detection rate are smaller than predetermined values. Thereby, detection accuracy can be improved.

  Depending on the product, it may be desired to reduce one of the detection omission rate and the false detection rate. For example, it may be desirable to reduce the detection omission rate for a product in which quality abnormalities produce serious results. Therefore, for such a product, the quality determination threshold may be adjusted so that the false detection rate is allowed to be high and only the detection failure rate is smaller than a predetermined value.

  FIG. 9 is a table showing quality determination results for different quality determination threshold values. FIG. 10 shows the effect obtained by changing the quality judgment threshold.

  In the present embodiment, it is assumed that a product from which a quality determination index less than the quality determination threshold is obtained is determined to be normal. Therefore, as shown in FIG. 9 and FIG. 10, when the quality determination threshold value is increased, it is likely to be determined as normal. On the other hand, if the quality determination threshold value is decreased, it is likely to be determined as abnormal.

  Therefore, as shown in FIG. 10, as the quality determination threshold is increased, the number of products determined to be normal increases and the number of products determined to be abnormal decreases. As the quality determination threshold value is decreased, the number of products determined to be normal decreases and the number of products determined to be abnormal increases. Therefore, when the quality determination threshold value is increased, the false detection rate decreases and the detection omission rate increases. On the other hand, when the quality determination threshold is reduced, the false detection rate increases and the detection omission rate decreases. There is a trade-off relationship between the false detection rate and the detection omission rate. However, it is possible to improve the accuracy of online abnormality detection by determining the quality determination threshold value by the quality determination threshold value determination unit 230 so that the false detection rate and the detection omission rate are closest to predetermined values.

  FIG. 11 is a table showing quality determination results for different start timing determination thresholds. By changing the threshold for determining the start timing, the data period for which the quality determination index is calculated changes. Therefore, the quality determination index obtained by the quality determination index calculation unit 310 can be changed by changing the threshold for determining the start timing. Therefore, even when the quality determination threshold is fixed, the determination result can change.

  FIG. 12 shows the effect obtained by changing the threshold for determining the start timing. In the present embodiment, for the sake of easy understanding, it is assumed that the quality determination index is generally reduced when the start timing determination threshold is increased, and the quality determination index is generally increased when the start timing determination threshold is decreased.

  As shown in FIG. 12, as the start timing determination threshold value is increased, the number of products determined to be normal increases and the number of products determined to be abnormal decreases. On the contrary, as the start timing determination threshold value is decreased, the number of products determined to be normal decreases and the number of products determined to be abnormal increases. Therefore, when the start timing determination threshold value is increased, the false detection rate decreases and the detection omission rate increases. On the other hand, when the threshold value for determining the start timing is reduced, the false detection rate increases and the detection omission rate decreases. By adjusting the start timing determination threshold by the start timing information determination unit 220, the quality determination index can be calculated from the time series data of the process variables during the period in which the process is actually performed. Therefore, it can be expected that the accuracy of abnormality determination is improved by adjusting the threshold for determining the start timing so as to match the quality information included in the record information.

  FIG. 13 is a table showing the quality determination result for the combination of the start timing determination threshold and the quality determination threshold. FIG. 13 shows only the quality determination results for the products of batch number 1 and batch number 2.

  FIG. 14 shows the effect obtained by changing the start timing determination threshold and the quality determination threshold. As described with reference to FIGS. 11 and 12, when the threshold value for determining the start timing is increased, the false detection rate decreases and the detection omission rate increases. Here, as shown in FIG. 14, the quality judgment threshold can be made to coincide with the finally obtained quality judgment result by lowering the quality judgment threshold value from 0.07 to 0.06. Thus, by adjusting the start timing determination threshold and the quality determination threshold so as to coincide with the quality information included in the performance information, it can be expected that the accuracy of abnormality determination is increased.

  As described above, by appropriately setting the quality determination threshold value and the start timing determination threshold value, the quality determination result by the quality determination unit 320 starts so as to approach the actual value of the quality determination threshold value obtained by the quality inspection. A timing determination threshold 330 and a quality determination threshold 350 can be set. Specifically, the quality determination threshold value determination unit 230 acquires the quality determination result by the quality determination unit 210 by changing the quality determination threshold value as illustrated in FIG. 9. The quality determination threshold value determination unit 230 sets, as the quality determination threshold value 350, the quality determination threshold value that provides the result that most closely matches the actual result value of the quality determination result.

  Moreover, the start timing information determination part 220 acquires the quality determination result by the quality determination part 210 by changing the threshold value for start timing determination, as illustrated in FIG. The start timing information determination unit 220 sets a start timing determination threshold value 330 as a start timing determination threshold value 330 that provides a result that most closely matches the actual quality determination result value.

  As described with reference to FIG. 4 and the like, when there are a plurality of types of process variables such as temperature and pressure, the start timing determination threshold is changed for each of the plurality of types of process variables to determine the quality. The quality determination result by the unit 210 can be acquired. Then, the start timing information determination unit 220 sets the process variable and the start timing determination threshold that have obtained the result that most closely matches the actual value of the final quality determination result as the start timing determination threshold 330 and the start timing determination, respectively. The variable 340 may be set.

  As described with reference to FIGS. 13 and 14, the determination information determination unit 270 acquires the quality determination result by the quality determination unit 210 by changing the combination of the quality determination threshold value and the start timing determination threshold value. It's okay. Then, the start timing information determination unit 220 sets the quality determination threshold value and the start timing determination threshold value with which the result that best matches the actual value of the final quality determination result, respectively, as the quality determination threshold value 350 and the start timing determination variable. You may set as 340.

  Further, the determination information determination unit 270 may acquire the quality determination result by the quality determination unit 210 by changing the combination of the quality determination threshold, the start timing determination variable, and the start timing determination threshold. Then, the start timing information determination unit 220 sets the quality determination threshold value, the start timing determination variable, and the start timing determination threshold value with which the result that best matches the actual value of the final quality determination result, respectively, as the quality determination threshold value 350 The start timing determination threshold 330 and the start timing determination variable 340 may be set.

  FIG. 15 is a flowchart regarding processing by the quality monitoring system 10. FIG. 15 particularly shows a flowchart of processing for determining the quality determination threshold, the start timing determination variable, and the start timing determination threshold.

  In S <b> 902, the record information acquisition unit 280 acquires process data stored in the process operation database 30 and quality data stored in the quality database 40 as record information.

  In S904, the determination information determination unit 270 starts a loop for the quality determination threshold. In this loop, a specific quality determination threshold value is sequentially selected from a plurality of quality determination threshold values, and an iterative process between S904 and S916 is performed.

  In the loop for the quality determination threshold, the determination information determination unit 270 starts a loop for the start timing determination information. The start timing determination information includes a plurality of combinations of a start timing determination variable and a start timing determination threshold. In each loop, specific start timing determination information is sequentially selected from the plurality of start timing determination information, and the repetition processing between S906 and S914 is performed.

  In the loop for the start timing determination information, the quality determination unit 210 calculates a quality determination index. Specifically, the start timing determination unit 200 extracts the data of the selected start timing determination variable from the time series data of the process variable included in the performance information, and the value of the process variable determines the start timing. The start timing that is equal to or greater than the threshold for use is determined (S908). And the quality determination part 210 calculates a quality determination index | index using the time series data of the process variable after a start timing (S910).

  In S912, the determination information determination unit 270 calculates a coincidence rate, a false detection rate, and a detection omission rate with the past quality determination results. Specifically, the start timing information determination unit 220 determines the past quality data and quality acquired from the quality database 40 based on the quality data included in the performance information, the quality determination index calculated in S910, and the quality determination threshold. The coincidence rate with the quality determination result by the determination unit 210 is calculated. Further, the quality determination threshold value determination unit 230 calculates the false detection rate and the detection omission rate based on the quality data included in the performance information, the quality determination index calculated in S910, and the quality determination threshold value.

  When the loop processing between S904 and S916 ends, in S918, information to be applied as the start timing determination threshold 330, the start timing determination variable 340, and the quality determination threshold 350 is determined. Specifically, the start timing information determination unit 220 and the quality determination threshold value determination unit 230 determine the start timing determination threshold value that provides the highest value as the match rate between the past quality data and the quality determination result by the quality determination unit 210. The start timing determination variable and the quality determination threshold may be determined and set as the start timing determination threshold 330, the start timing determination variable 340, and the quality determination threshold 350. In addition, the start timing information determination unit 220 and the quality determination threshold determination unit 230 include a start timing determination threshold, a start timing determination variable, and a quality determination that provide a false detection rate and a detection omission rate smaller than predetermined values. The threshold may be determined and set as the start timing determination threshold 330, the start timing determination variable 340, and the quality determination threshold 350.

  According to the quality monitoring system 10 described above, it is possible to suppress erroneous determination in product quality management in a batch process based on past performance information.

  In a process system manufacturing process, a process in which products of the same type are continuously made for a long time, such as an oil refinement process in a petrochemical plant or a steelmaking process in an iron manufacturing plant, is called a continuous process. In order to realize a continuous process, a large-scale capital investment is often required, and a batch process occupies most of the medium- and small-scale plants. For this reason, raising the quality of products by the stable operation of the batch process described above is an important issue for the entire manufacturing industry. Therefore, it is desired to detect or predict an abnormality early in the batch process and to deal with the abnormality quickly or before the occurrence of the abnormality. According to the quality monitoring system 10 mentioned above, the monitoring system which can suppress the erroneous determination of the abnormality which concerns can be provided.

  In addition to manufacturing processes, general industrial and consumer devices and facilities often move in a manner similar to batch processes. For example, a reciprocating pump or a compressor repeats a repetitive movement called a reciprocating movement. The refrigeration / freezer and the refrigeration / freezer showcase perform defrosting at regular intervals and repeat similar movements at every defrosting interval. The operation of such devices and equipment can be handled in the same manner as the operation of the batch process in the manufacturing process described above. Even in such devices, it is desired to detect and suppress abnormalities quickly or in advance. The quality monitoring system 10 described above can be applied to a system that determines an abnormality in the operation of a device that performs repeated operations in addition to the manufacturing process.

  In the batch processes and devices described above, it is possible to measure state quantities relating to the manufacturing apparatus or the product itself regularly or continuously and store them in the database as regularly sampled time-series data. . In recent years, a large amount of measurement data can be stored in a database. According to the quality monitoring system 10, it is possible to provide a monitoring system that performs online detection of abnormalities in a batch process, equipment, and the like by using such measurement data.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above embodiment. It is apparent from the description of the scope of claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

  The execution order of each process such as operation, procedure, step, and stage in the apparatus, system, program, and method shown in the claims, the description, and the drawings is particularly “before” or “prior to”. It should be noted that the output can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the specification, and the drawings, even if it is described using “first”, “next”, etc. for the sake of convenience, it means that it is essential to carry out in this order. It is not a thing.

DESCRIPTION OF SYMBOLS 10 Monitoring system 20 Monitoring object 30 Process operation database 40 Quality database 90 Network
100 process monitoring system 200 start timing determination unit 210 quality determination unit 220 start timing information determination unit 230 quality determination threshold determination unit 270 determination information determination unit 280 performance information acquisition unit 300 start timing adjustment unit 310 quality determination index calculation unit 320 quality determination unit 330 Start Timing Determination Threshold 340 Start Timing Determination Variable 350 Quality Determination Threshold 700 Area

Claims (7)

A record information acquisition unit for acquiring information indicating the quality of each of a plurality of products manufactured in a batch process and a value of a process variable in the batch process;
A start timing determination unit that determines a start timing of each of a plurality of batches in the batch process based on a comparison result between the value of the process variable and a first threshold;
For each of the plurality of batches, a quality determination unit that determines the quality of each of the plurality of products based on the value of the process variable within a batch processing period starting from the start timing;
The degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit and the quality of each of the plurality of products acquired by the record information acquisition unit exceeds a predetermined value. A quality monitoring system comprising: the process variable used to determine a start timing and a start timing information determination unit that determines the first threshold value. The quality determination unit, for each of the plurality of batches, based on a comparison result between a quality determination index calculated based on the value of the process variable within a batch processing period starting from the start timing and a second threshold value The quality monitoring system according to claim 1, wherein the quality of each of the plurality of products is determined. The quality determination unit determines a product quality abnormality based on a comparison result between the quality determination index and the second threshold;
Based on the information indicating the quality acquired by the performance information acquisition unit and the determination result of the quality determination unit, at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit The quality monitoring system according to claim 2, further comprising a quality determination threshold value determination unit that determines the second threshold value so as to be lower than a predetermined value. The degree of coincidence between the quality of each of the plurality of products determined by the quality determination unit and the quality of each of the plurality of products acquired by the record information acquisition unit exceeds a predetermined value. The quality monitoring system according to claim 2, further comprising a quality determination threshold value determination unit that determines a second threshold value. A record information acquisition unit for acquiring information indicating the quality of each of a plurality of products manufactured in a batch process and a value of a process variable in the batch process;
For each of a plurality of batches in the batch process, a quality abnormality of the plurality of products is determined based on a comparison result between a quality determination index calculated based on the value of the process variable within a batch processing period and a threshold value. A quality judgment unit;
Based on the information indicating the quality acquired by the record information acquisition unit and the determination result of the quality determination unit, at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit is determined in advance. A quality monitoring system comprising: a quality determination threshold value determination unit that determines the threshold value so as to be lower than a given value. A record information acquisition unit for acquiring information indicating the quality of each of a plurality of products manufactured in a batch process and a value of a process variable in the batch process;
A start timing determination unit that determines a start timing of each of a plurality of batches in the batch process based on a comparison result between the value of the process variable and a first threshold;
For each of the plurality of batches, the quality of the plurality of products based on the comparison result between the quality determination index calculated based on the value of the process variable within the processing time starting from the start timing and the second threshold value. A quality judgment unit for judging abnormality,
Based on the information indicating the quality acquired by the record information acquisition unit and the determination result of the quality determination unit, at least one of a detection omission rate and a false detection rate of a product having a quality abnormality by the quality determination unit is determined in advance. A quality monitoring system comprising: a determination unit configured to determine the process variable, the first threshold value, and the second threshold value used to determine the start timing so as to be lower than a predetermined value.   A program for causing a computer to function as the quality monitoring system according to any one of claims 1 to 6.

Images