JP2019032671A - Cause estimation method and program - Google Patents

Abstract

To easily grasp cause of manufacturing loss of individual products.SOLUTION: A cause estimation method of manufacturing loss comprises the step of acquiring production result information of production processes for each of a plurality of individual products, the step of calculating processing time in the production processes for each of the plurality of individual products based on the production result information, the step of acquiring information on manufacturing events indicating status of the production processes, the step of associating the manufacturing events and the individual products based on the production result information and the manufacturing events, and the step of superimposing and displaying distribution of the processing time of the plurality of individual products and distribution of the processing time of the individual products associated with the manufacturing events on a display device.SELECTED DRAWING: Figure 20

Description

  The present disclosure relates to a cause estimation method and a program for estimating a cause of manufacturing loss.

  Due to globalization and diversification of customer needs in recent years, the manufacturing industry has been making small quantities and a variety of products. Increasing the number of products in small quantities, along with the increase in incidental work time, mainly for the changeover of molds and jigs and tools, as well as for changing the parameter settings of equipment, etc. Various losses have occurred in the manufacturing process of the product, such as deterioration in quality. The effects of losses that occur during the manufacturing process appear in the manufacturing time.

  Therefore, Patent Document 1 describes a display method for specifying a loss occurrence location by centrally visualizing the manufacturing time of each process. In Patent Document 1, a time axis is provided for each process, a processing time for each individual product is described as a vertical bar on the time axis, and a graph in which the vertical bars of the processing time for each process are connected by a line segment is generated. .

  Patent Document 2 describes a display method for analyzing loss factors for overall optimization, not individual optimization such as planning and quality, by displaying process plans, process progress, production results, and quality inspections in a unified manner. ing.

Japanese Patent Laying-Open No. 2015-075795 JP 2004-178150 A

  However, the analysis method described in Patent Document 1 only displays the processing time of a product individual for each production process with a bar on the time axis, and repeatedly occurs under specific conditions across days and weeks. It is difficult to detect manufacturing loss.

  For example, manufacturing loss that occurs at the same time every day, such as a break or a start-up loss immediately after the start of operation, is a loss that occurs repeatedly, so that the priority of countermeasures is high. However, in the analysis method of Patent Document 1, even a loss that occurs repeatedly appears only as a loss that occurs temporarily, and it is difficult to estimate the cause because the loss occurrence condition is unknown.

  In addition, the manufacturing loss may occur in a chain due to another manufacturing loss. However, in the method of Patent Document 1, there is no means for associating a plurality of manufacturing losses, and the effect on the production efficiency is visualized and the cause is It is difficult to estimate. For example, when an abnormal stop of the facility occurs, the worker performs the facility restoration work, so that the process that the worker originally was in charge is delayed. In this way, manufacturing losses that cause other manufacturing losses in a chain will greatly hinder production efficiency, and therefore must be preferentially addressed.

  In addition, in the case of the method described in Patent Document 2, although information related to the production management process is displayed in a unified manner, there is no means for displaying the events at the time of manufacturing such as the start of operation and the relevance between a plurality of manufacturing losses.

  This indication is made in view of the above-mentioned point, and provides the technique which can grasp the cause of manufacture loss of a product individual easily.

  In order to solve the above-mentioned problem, there is a method for estimating the cause of manufacturing loss executed by a computer, the step of obtaining production performance information of a production process for each of a plurality of product individuals, and the plurality of pieces based on the production performance information On the basis of the step of calculating the processing time in the production process for each of the product individual, the step of obtaining information on the manufacturing event indicating the status of the production process, the production performance information and the information on the manufacturing event, The step of associating the manufacturing event with the product individual, the distribution of the processing time of the plurality of product individuals, and the distribution of the processing time of the product individual associated with the manufacturing event are superimposed and displayed. A method for estimating the cause of manufacturing loss, comprising: displaying on the apparatus.

  A step of obtaining production performance information of a production process for each of a plurality of product individuals; a step of calculating a processing time in the production process for each of the plurality of product individuals based on the production performance information; and the production Obtaining information related to a manufacturing event indicating a status of a process; linking the manufacturing event and the product individual based on the production performance information and information related to the manufacturing event; and There is provided a program for causing a computer to execute a process of superimposing the distribution of the processing time and the distribution of the processing time of a product individual associated with the manufacturing event on a display device.

  According to the present disclosure, it is possible to easily grasp the cause of the manufacturing loss of the individual product. Problems, configurations, and effects other than those described above will become apparent from the following description of embodiments.

It is a figure which shows the structure of the estimation system which estimates the cause of the manufacturing loss of a present Example. It is a figure which shows the structure of manufacturing information DB. It is a figure which shows the example of a manufacture performance table. It is a figure which shows the example of an equipment error information table. It is a figure which shows the example of an equipment operation information table. It is a figure which shows the example of a manufacturing event list table. It is a figure which shows the example of a manufacturing event time table. It is a figure which shows the example of a manufacturing event period table. It is a figure which shows the structure of calculation result DB. It is a figure which shows the example of a manufacturing performance table with an event. It is a figure which shows the example of a logarithm normal distribution information table. It is a figure which shows the example of an event correlation table. It is a figure which shows the sequence of the acquisition process of manufacturing information. It is a figure which shows the sequence of a lognormal distribution approximation process. It is a figure which shows the example of the approximated lognormal distribution. It is a figure which shows the sequence of the process which provides event information with respect to a manufacture performance. It is a figure which shows the sequence of the process which calculates | requires the correlation of a manufacturing loss and a manufacturing event. It is an example of GUI which an arithmetic unit outputs to a display apparatus. It is an example of GUI which shows the cause estimation result of a manufacturing loss. It is an example of the detailed screen which shows the correlation of a manufacturing loss and a manufacturing event.

  Hereinafter, an embodiment of the present disclosure will be described based on the drawings. In addition, the Example of this indication is not limited to the Example mentioned later, A various deformation | transformation is possible in the range of the technical idea. Corresponding portions in each drawing used for the description of each embodiment to be described later are denoted by the same reference numerals, and redundant description is omitted.

<Example>
FIG. 1 is a diagram illustrating a configuration of an estimation system that estimates the cause of manufacturing loss according to the present embodiment. As shown in FIG. 1, the estimation system includes a production planning system 101, a manufacturing execution system 102, a manufacturing / inspection facility 103, a facility abnormality detection system 104, a computing device 110, and a display device 120.

  The production planning system 101 is a system for formulating types and number of products to be manufactured, work schedules of workers and facilities, raw materials and parts necessary for manufacturing products, and has been introduced in many manufacturing industries. This is a well-known system.

  The manufacturing execution system 102 is a system that collects work instructions and information on manufacturing results for equipment and workers. The equipment abnormality detection system 104 is a system that monitors the state of equipment via a sensor or the like and detects an abnormality that leads to equipment failure.

  The arithmetic device 110 includes a data acquisition unit 111 that acquires data related to manufacturing of individual products, a manufacturing event processing unit 112 that generates a manufacturing event from the data acquired by the data acquisition unit 111, and associates the manufacturing results with the manufacturing event. A statistical processing unit 113 that statistically processes the processed data and estimates the cause of the manufacturing loss, a manufacturing information DB 114 that stores the manufacturing data acquired by the data acquisition unit 111, and an operation result DB 115 that stores the processing result of the statistical processing unit 113. .

  The arithmetic device 110 includes a recording unit (not shown), and mathematical formulas for determining lognormal distribution parameters μ, σ and variance v, which will be described later, are recorded in the recording unit. Various programs are recorded in the recording unit, and the arithmetic device 110 can function as the data acquisition unit 111, the manufacturing event processing unit 112, and the statistical processing unit 113 by executing the program. In addition, the arithmetic device 110 is connected to the display device 120.

  The data acquisition unit 111 acquires data (production result information and information about manufacturing events) related to manufacturing of individual products from the production planning system 101, manufacturing execution system 102, manufacturing and inspection equipment 103, and equipment abnormality detection system 104. The result of the cause estimation process stored in the calculation result DB 115 is output to the display device 120.

  FIG. 2 is a diagram illustrating a configuration of the manufacturing information DB 114. The manufacturing information DB 114 includes a manufacturing result table 201, an equipment error information table 202, an equipment operation information table 203, a manufacturing event list table 204, a manufacturing event time table 205, and a manufacturing event period table 206. The data held by each table will be described below.

  FIG. 3 is a diagram illustrating an example of the manufacturing performance table 201. The manufacturing result table 201 includes a product number for identifying a product individual or a lot, a process ID for uniquely identifying a manufacturing process, a start time and a completion time of each product individual in a process identified by the process ID, and a start time. And the processing time which is the difference between the completion time and the completion time.

  Here, in the item “processing time”, for example, the processing time for each of a plurality of individual products in the production process, which is calculated based on the start time and the completion time by the arithmetic device 110, is stored. In FIG. 3, only process 1 is described as the process ID, but data relating to other process IDs is also recorded.

  FIG. 4 is a diagram illustrating an example of the equipment error information table 202. The equipment error information table 202 stores equipment ID that uniquely identifies equipment in which an error has occurred, error occurrence time, and error information indicating the content of the error. In the example of FIG. 4, it is recorded in the first row that a tool damage error has occurred in the equipment with the equipment ID mac_a at 10:10 on March 2, 2017.

  FIG. 5 is a diagram illustrating an example of the equipment operation information table 203. The equipment operation information table 203 includes an equipment ID for uniquely identifying equipment, equipment state such as operation or stop, an event that causes stop or operation such as maintenance and production, and a duration of equipment state (start date and time of equipment state) And end date and time). For example, in the first row of the equipment operation information table 203, it is recorded that the equipment with the equipment ID mac_a was operating and producing products from 9:00 to 12:00 on March 2, 2017. ing.

  FIG. 6 is a diagram illustrating an example of the manufacturing event list table 204. The manufacturing event list table 204 is a table for registering manufacturing events, and includes an event ID that uniquely represents the event and an event name. In FIG. 6, an event ID including “t” in the character string of the ID name is an event that occurs with a time width, and the other event IDs are events that occur at a temporary point.

  FIG. 7 is a diagram illustrating an example of the manufacturing event time table 205. The manufacturing event time table 205 stores the occurrence date and time of a manufacturing event (manufacturing event whose event ID does not include “t”) having no time width among the manufacturing events registered in the manufacturing event list table 204. It is a table. In the manufacturing event time table 205, manufacturing events are arranged in order of occurrence date and time.

  FIG. 8 is a diagram illustrating an example of the manufacturing event period table 206. The manufacturing event period table 206 stores the start date and time and the end date and time of a manufacturing event (a manufacturing event including an event ID “t”) that continues for a certain period of time among manufacturing events registered in the manufacturing event list table 204. It is.

  FIG. 9 is a diagram illustrating a configuration of the calculation result DB 115. The calculation result DB 115 includes an event-added manufacturing performance table 901, a lognormal distribution information table 902, and an event correlation table 903. The data held by each table will be described below.

  FIG. 10 is a diagram illustrating an example of the production record with event table 901. The manufacturing result table with event 901 is obtained by adding information on whether or not a manufacturing event has occurred to the manufacturing result table 201, and true for a column of a manufacturing event that has occurred and false for a column of a manufacturing event that has not occurred. Is stored. A method for determining whether or not a manufacturing event has occurred will be described below.

  First, the computing device 110 determines a period during which the manufacturing event is considered to have an influence based on at least one of the occurrence date and time and the end date and time of the manufacturing event. The period is, for example, a predetermined period determined based on experience for each process, and is a period during which a manufacturing event is considered to affect the processing time of a product individual. The arithmetic device 110 associates the product individual and the manufacturing event with the determined period and the manufacturing period overlapping, and sets the column of the manufacturing event to true.

  For example, if the period in step 1 is 600 seconds before and after the date and time of occurrence of the manufacturing event, the start time of the individual product with the product number 0001 and the date and time of occurrence of eve_1 are both 9:00, and the manufacturing event has been affected. Since the possible period overlaps with the production period of the individual product, the eve_1 column is true.

  In addition, the arithmetic unit 110 determines a time difference indicating the time perspective between the generated manufacturing event and the manufacturing time of the product individual associated with the manufacturing event for each product individual, and stores the time difference in the manufacturing result table with event 901. . The time difference is determined based on at least one of the occurrence date and time and the end date and time of the manufacturing event, and at least one of the start time and the completion time of the individual product associated with the manufacturing event.

  For example, in the case of an event having no time width, the time difference is defined as the difference between the occurrence date and time and the start time of the product individual. For example, in the case of the product individual with the product number 0033, since the start time of manufacture is 13:05 and the occurrence time of the manufacture event is 13:00, a time difference of −300 seconds is recorded. Here, a positive time difference is set when the manufacturing start time is past than the manufacturing event, and a negative time difference is set when the manufacturing start time is later than the manufacturing event.

  Further, in the case of an event having a time width, that is, an event having a time interval from the occurrence to the end, for example, the minimum value of the difference between any time point of the time interval and the start time of the individual product is set to Time difference. For example, if the start time or completion time of the individual product is during the event occurrence period, the time difference is zero.

ユーザは、例えば、工程が含む製造ロスの多寡を評価するために分散を利用することができる。製造ロスを含む工程は処理時間のばらつき、つまり分散が大きくなる。 FIG. 11 is a diagram illustrating an example of the lognormal distribution information table 902. The log normal distribution information table 902 stores results obtained by approximating the distribution of processing times of each process with a log normal distribution and calculating parameters, variances, and log likelihoods of probability density functions corresponding to the log normal distribution. Yes. In the example shown in FIG. 11, μ and σ in the following probability density function are stored. μ and σ are parameters that characterize the probability density function, and e represents the number of Napiers.

The user can use variance, for example, to evaluate the amount of manufacturing loss that a process contains. In the process including the manufacturing loss, the processing time varies, that is, the dispersion increases.

  FIG. 12 is a diagram illustrating an example of the event correlation table 903. The event correlation table 903 stores a process ID, an event ID, an event time log likelihood, a log likelihood difference, and a time difference (seconds). The log likelihood at the event indicates the log likelihood when it is assumed that the distribution of the population whose element is the processing time of the product individual linked to the manufacturing event follows the determined lognormal distribution. The above-mentioned population extracts only the processing time of the product individual linked to a specific manufacturing event from the first population of the entire processing time of one process, and is the same as the number of elements of the first population. This is the second population obtained by randomly replicating the elements of processing time.

  In other words, the processing time of the product individual linked to the event Y (eve_1, eve_2...) Is extracted from the first population of the entire processing time of processX (X = 1, 2...), And the number of samples is as described above. Logarithmic likelihood in the case where the set obtained by duplicating is set as the second population, and the distribution of the second population follows the lognormal distribution obtained by fitting to the distribution of the first population. The log likelihood of the event.

  The log likelihood difference is a difference between the log likelihood stored in the log normal distribution information table 902 and the event time log likelihood stored in the event correlation table 903. That is, the difference between the log likelihood when it is assumed that the first population follows the lognormal distribution obtained by fitting and the log likelihood when the second population follows the same lognormal distribution is the log likelihood. It is a degree difference.

  FIG. 13 is a diagram illustrating a sequence of manufacturing information acquisition processing. Hereinafter, each step of the sequence will be described.

(Step 1301)
First, the data acquisition unit 111 acquires information related to the manufacturing performance of the individual product from the manufacturing execution system 102 or the manufacturing / inspection equipment 103 and stores the information in the manufacturing performance table 201. The data acquisition unit 111 acquires equipment error information from the manufacturing / inspection equipment 103 or the equipment abnormality detection system 104 and stores it in the equipment error information table 202. Further, the data acquisition unit 111 acquires equipment operation information from the production planning system 101, the manufacturing execution system 102, or the manufacturing / inspection equipment 103, and stores it in the equipment operation information table 203.

(Step 1302)
The data acquisition unit 111 calculates the processing time in the production process for each of the plurality of product individuals based on the start time and completion time of the production process of the plurality of product individuals acquired in Step 1301 (manufacturing performance information). And stored in the manufacturing result table 201. In the case of the example shown in FIG. 3, the processing time of process 1 of product number 0001 is 600 seconds, which is the difference between the start time 09:00:00 and the completion time 09:10:00.

(Step 1303)
The manufacturing event processing unit 112 converts the information about the manufacturing event included in the equipment error information and the equipment operation information acquired in step 1301 into an event ID registered in the manufacturing event list table 204. The manufacturing event processing unit 112 stores the occurrence date and time of a manufacturing event having no time width and the event ID of the manufacturing event in the manufacturing event time table 205. In addition, the manufacturing event processing unit 112 stores the event ID, the occurrence date and time and the end date and time in the manufacturing event period table 206 for the manufacturing event having a time width.

  For example, in the case of the example shown in FIG. 4, an error has occurred in the equipment whose equipment ID is mac_a at 2017/03/02 10:10:00. In the example shown in FIG. 6, since the event ID of the mac_a equipment error is eve_6, the record of event ID: eve_6 and occurrence time: 2017/03/02 10:10:00 is the manufacturing event time table 205. Stored in

  In the case of the example shown in FIG. 5, the mac_b facility is stopped during maintenance from 2017/03/02 10:10:00 to 2017/03/02 10:20:00. In the example shown in FIG. 6, since the event ID indicating that mac_b is under maintenance is eve_t_6, event ID: eve_t_6, start date / time: 2017/03/02 10:10:00, end date / time : Record of 2017/03/02 10:20:00 is stored in the manufacturing event period table 206.

  FIG. 14 is a diagram illustrating a sequence of lognormal distribution approximation processing. Hereinafter, each step of the sequence will be described.

(Step 1401)
The statistical processing unit 113 sets a set of processing times of one process among the processing times of the plurality of product individuals calculated in step 1302 as a population, and performs a process of fitting a histogram of the population with a lognormal distribution for all the processes. Execute throughout the process. The statistical processing unit 113 obtains parameters μ and σ that characterize the lognormal distribution for each process. Further, the statistical processing unit 113 calculates the log likelihood when it is assumed that the histogram of the population follows the log normal distribution fitted. In addition, fitting by log normal distribution is implemented using the least squares method or the maximum likelihood estimation method, for example.

  FIG. 15 is a diagram illustrating an example of an approximate lognormal distribution. In FIG. 15, a histogram of processing time for one process and an approximate lognormal distribution are drawn together. In FIG. 15, the vertical axis represents a ratio, and indicates the number of samples of processing time included in a specific section with respect to the number of samples of total processing time. Therefore, the sum of the values over all sections of the histogram is 1.

(Step 1402)
The statistical processing unit 113 obtains the variance v from the parameters μ and σ calculated in step 1401 by the following formula, and stores the parameters μ, σ, variance v, and log likelihood in the log normal distribution information table 902.

  FIG. 16 is a diagram illustrating a sequence of a process for assigning event information to manufacturing results. Hereinafter, each step of the sequence will be described.

(Step 1601)
The manufacturing event processing unit 112 repeats the processing of subsequent steps 1602 and 1603 for all the events described in the manufacturing event time table 205 and the manufacturing event period table 206.

(Step 1602)
First, the manufacturing event processing unit 112 searches for a product individual manufactured at the same time as the manufacturing event described in the manufacturing event time table 205 and the manufacturing event period table 206. The manufacturing event processing unit 112 searches for a product individual manufactured at the same time as the manufacturing event based on at least one of the occurrence date and time and the end date and time of the manufacturing event and at least one of the start time and completion time of the product individual. To do.

  Specifically, the manufacturing event processing unit 112 searches for a product individual whose manufacturing period overlaps with a predetermined period in which the manufacturing event is considered to have influenced. The predetermined period is a predetermined time width determined for each production process centered on at least one time point of a production event occurrence date and time and an end date and time. Since the influence of the manufacturing event on the processing time differs depending on the product to be manufactured and the production process, the predetermined time width is determined by the experience of the process manager, for example. Further, “the predetermined period and the manufacturing period overlap” means, for example, that at least one of the start time and the completion time of the product individual is included in the predetermined period.

  For example, the event: eve_1 described in FIG. 7 occurs at 2017/03/02 09:00:00, and the start time in the process: process 1 of the product number 0001 described in FIG. 3 is 09:00: 00. That is, the occurrence time of the event: eve_1 and the start time in the process: process1 of the product number 0001 are the same. Therefore, since the engine affected by the manufacturing event and the manufacturing period overlap, the search by the manufacturing event processing unit 112 is hit.

  Also, the event: eve_t_6 shown in FIG. 8 occurred at 2017/03/02 10:10:00 and ended at 2017/03/02 10:20:00 and is shown in FIG. Process number 0011: The end time of process 1 is included in the event occurrence period. Therefore, since the engine affected by the manufacturing event and the manufacturing period overlap, the search by the manufacturing event processing unit 112 is hit.

(Step 1603)
Subsequently, the manufacturing event processing unit 112 assigns the manufacturing event information used for the search to the information related to the manufacturing results of the product individual hit in the search in step 1601, and the merged information is added to the manufacturing result table with event 901. Store. That is, the manufacturing event processing unit 112 associates the manufacturing event with the product individual based on the production result information and the information related to the manufacturing event.

  For example, in the case of searching for eve_1 exemplified in step 1602, since the start date and time of eve_1 and the process of product number 0001: process1 start time overlap, eve_1 of the record of product number 0001 as shown in FIG. Is stored as true. In the case of the search for eve_t_6 exemplified in step 1601, since the start time of the process: process1 of the product 0011 is duplicated, true is similarly stored in eve_t_6 of the record of the product number 0011.

  FIG. 17 is a diagram illustrating a processing sequence for obtaining a correlation between a manufacturing loss and a manufacturing event. Hereinafter, each step of the sequence will be described.

(Step 1701)
The subsequent processing from step 1702 to step 1705 is repeatedly executed for all events described in the manufacturing event list table 204. Hereinafter, the manufacturing event is described as event i (0 <i <total number of events + 1).

(Step 1702)
The subsequent processing from step 1703 to step 1705 is repeatedly executed for all process IDs. Hereinafter, the j-th process ID is described as process j (0 <j <total number of processes + 1).

(Step 1703)
The statistical processing unit 113 acquires the manufacturing results (product manufacturing results at the event) of the product individual for which the flag of event i is true for process j. Specifically, the statistical processing unit 113 acquires the processing time of the product individual for which event i flag is true for process j.

  Subsequently, the statistical processing unit 113 displays a logarithm in which a histogram of a set of processing times of individual products associated with the manufacturing event is represented by a lognormal distribution parameter of process j stored in the lognormal distribution information table 902. Logarithmic likelihood (event log likelihood) when assuming normal distribution is calculated. At this time, since the log likelihood comparison is executed in step 1704, the number of processing times related to process j of the product individual linked to event i is the same as the number of processing times of all product individuals related to process j. In addition, the processing time is replicated randomly.

(Step 1704)
The statistical processing unit 113 obtains a difference between the log likelihood of the event calculated in step 1703 and the log likelihood of process j stored in the log normal distribution information table 902 and stores the difference in the event correlation table 903.

  The statistical processing unit 113 calculates an average time difference (an average value of the time difference of each product individual) between a product individual for which event i flag of process j is true and event i, and stores it in the event correlation table 903. Note that the statistical processing unit 113 may store an intermediate value, maximum value, or minimum value of time differences in the event correlation table 903 instead of the average value of time differences.

Hereinafter, an output example of the manufacturing loss cause estimation result obtained by the cause estimation method of the present embodiment will be described.
FIG. 18 is an example of a GUI that the arithmetic device 110 outputs to the display device 120. In the GUI, inefficient processes in which manufacturing loss has occurred are displayed in order. For example, the computing device 110 refers to the variance stored in the lognormal distribution information table 902 and displays the inefficient processes on the display device 120 in descending order of variance of the processing time. Each process is accompanied by a cause analysis button. When the button is pressed, a transition is made to a screen for displaying a cause estimation result.

  FIG. 19 is an example of a GUI showing the cause estimation result of the manufacturing loss. For example, for the process to which the cause analysis button pressed on the screen of FIG. 18 belongs, the arithmetic device 110 extracts a manufacturing event having a log likelihood difference of a certain value or more from the event correlation table 903. Then, the arithmetic device 110 acquires the log likelihood difference and the average time difference associated with the extracted manufacturing event, and displays the manufacturing event names on the display device 120 in the order of the average time difference. In the example shown in FIG. 19, manufacturing events with a small average time difference are displayed in order from the left.

  Between the manufacturing event name and the process name displayed on the GUI, an arrow from the manufacturing event name to the process name and a log likelihood difference are displayed. Each arrow is displayed with its thickness changed based on the magnitude of the log likelihood difference. Specifically, a thicker arrow is displayed for a manufacturing event having a larger log likelihood difference. That is, a manufacturing event with a thick arrow is a manufacturing event in which the distribution of processing time is greatly shifted and a manufacturing event that causes a large manufacturing loss. Each manufacturing event name is displayed from top to bottom in descending order of log likelihood difference.

  As described above, the GUI indicating the cause estimation result of the manufacturing loss determines the two-dimensional arrangement of the manufacturing event name and the process name according to the magnitude of the log likelihood difference and the average time difference. In addition, the process name and each manufacturing event name are connected by an arrow, and the thickness of the arrow is changed. By displaying in this way, the user can visually understand the magnitude of the influence of the manufacturing event on the processing time of the process and the strength of the correlation between the manufacturing event and the manufacturing loss.

  In the example of FIG. 19, it can be seen that the three manufacturing events of product type switching, inspection equipment: failure detected in ins2, and manufacturing equipment: error generated in mac2 are greatly related to the variation in process 1 processing time. . Furthermore, it can be seen that the product type was affected over a long time in the order of product type switching, ins2_defective, and mac2_error. From the above, it is suggested that, for example, the quality is not stable immediately after the product type switching, a defect occurs, and the process 1 may be delayed due to correction of the defect.

  In the GUI shown in FIG. 19, when any arrow is pressed by the user, a transition is made to a screen that displays in detail the correlation between the processing time variation in the process and the manufacturing event. The above screen will be described below.

  FIG. 20 is an example of a detailed screen showing the correlation between the manufacturing loss and the manufacturing event. In the above detailed screen, the processing time histogram of multiple product individuals (normal histogram) that is not limited to when a manufacturing event occurs and the processing time histogram of the product individual linked to the manufacturing event are superimposed and displayed. Yes. Therefore, the user can visually recognize how much normal processing time is extended when which manufacturing event occurs.

<Modification 1>
In the embodiment, the lognormal distribution is given as an example of the distribution curve to be fitted to the processing time histogram. However, the processing time histogram may be fitted using a distribution curve (probability distribution function) other than the lognormal distribution. For example, fitting using a general probability distribution such as a normal distribution, a Poisson distribution, or a gamma distribution is possible. In this specification, log likelihood is used as an example of a method for evaluating the relationship between a manufacturing loss and a manufacturing event, but evaluation may be performed using likelihood.

<Modification 2>
Further, in the embodiment, a lognormal distribution with respect to a histogram of processing times of all product individuals (both product individuals associated with manufacturing events and product individuals not associated with manufacturing events) in one process. The curve was fitted. Distribution curve fitting may be performed on a histogram of a population from which samples of processing times that are outliers are removed. For the detection of outliers, a general outlier detection method such as a method in which a value having a predetermined difference from the average value of processing times is used as an outlier, Tukey-Kramer test, Sumirnov-Grubbs test, or the like can be used.

[Summary]
As described above, the estimation system of the present disclosure includes the histogram of the processing time of the entire product manufactured in a certain process and the processing time of the product individual linked to the manufacturing event among the entire product manufactured in the above process. Are displayed on the display device 120 in a superimposed manner. Therefore, the user can visually understand the influence of the manufacturing event on the processing time of the individual product.

  In addition, the estimation system according to the present disclosure includes, for example, the likelihood (or log likelihood) of the probability distribution function fitted to the histogram of the processing time of the entire product manufactured in a certain process, and the product manufactured in the above process. The event time likelihood (or event time log likelihood) is calculated assuming that the processing time histogram of the product individual linked to the manufacturing event follows the probability distribution function, and the difference (likelihood) (Degree difference or log-likelihood difference). By checking the likelihood difference (or log likelihood difference), the user can understand the degree of influence of a certain manufacturing event on the processing time of the product individual.

  In addition, the estimation system of the present disclosure determines, for each product individual, a time difference indicating a time perspective between a manufacturing event and a product individual associated with the manufacturing event, and calculates an average thereof. By checking the average time difference, the user can understand how long a manufacturing event affects the processing time of manufacturing a product individual.

  In addition, the estimation system according to the present disclosure displays, for example, one or more manufacturing events on the display device 120 together with information indicating the difference between the likelihood and the event time likelihood in the order of the average magnitude of the time difference. The user can understand at a glance the temporal effect and degree of the manufacturing event on the processing time of manufacturing the individual product. Further, the user can obtain auxiliary knowledge for recognizing the relationship between a plurality of manufacturing events.

  In addition, the estimation system according to the present disclosure links, for example, a product event and a product event in which a predetermined time period and a manufacturing time period considered to have affected the manufacture of the product product. In other words, the estimation system of the present disclosure has effectively extracted the processing time that is considered to have caused the manufacturing loss due to the manufacturing event from the set of the entire processing time, and what manufacturing event affected the processing time in the production process. Can be effectively shown to the user.

  The predetermined period is, for example, a predetermined time width determined for each production process centered on at least one time point of a production event occurrence date and time and an end date and time. Since the processing time of a product event varies depending on the type of production process, if a predetermined period is set as described above, a sample of the processing time affected by the manufacturing event can be appropriately extracted.

  In addition, the estimation system of the present disclosure, for example, when a predetermined probability distribution function is fitted to a distribution of processing times of a plurality of product individuals, a predetermined outlier detection method from the distribution of processing times of the plurality of product individuals The predetermined probability distribution function is fitted to the distribution from which outliers have been removed by. Thus, the estimation accuracy of the cause of manufacturing loss can be improved by removing the outlier.

  In addition, this invention is not limited to an above-described Example, Various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Further, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment. Further, it is possible to add, delete, and replace other configurations for a part of the configuration of each embodiment. Each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, and an SSD, or a recording medium such as an IC card, an SD card, and a DVD.

101: Production planning system, 102: Manufacturing execution system, 103: Manufacturing / inspection equipment, 104: Equipment abnormality detection system, 110: Computing device, 111: Data acquisition section, 112: Manufacturing event processing section, 113: Statistical processing section, 114: Manufacturing information DB, 115: Calculation result DB, 120: Display device, 201: Manufacturing result table, 202: Equipment error information table, 203: Equipment operation information table, 204: Manufacturing event list table, 205: Manufacturing event time table 206: Manufacturing event period table, 901: Manufacturing result table with event, 902: Log normal distribution information table, 903: Event correlation table

Claims (8)

A method for estimating the cause of manufacturing loss performed by a computer,
Obtaining production performance information of the production process for each of a plurality of product individuals;
Calculating a processing time in the production process for each of the plurality of product individuals based on the production record information;
Obtaining information on a manufacturing event indicating the status of the production process;
Linking the manufacturing event and the product individual based on the production performance information and information on the manufacturing event;
Displaying the distribution of the processing times of the plurality of product individuals and the distribution of the processing times of the product individuals associated with the manufacturing event on a display device in a superimposed manner;
Method for estimating cause of manufacturing loss including The step of calculating the processing time is a step of calculating the processing time based on a start time and a completion time included in the production performance information,
The step of associating the manufacturing event with the product individual is based on at least one of the occurrence date and time and the end date and time included in the information related to the manufacturing event, and at least one of the start time and the completion time of the product individual. , A step of linking the manufacturing event and the product individual.
The method for estimating the cause of manufacturing loss according to claim 1. Fitting a predetermined probability distribution function to the distribution of the processing times of the plurality of product individuals;
Calculating a likelihood when assuming that the distribution of the processing time follows a probability distribution function determined by fitting;
Calculating the event time likelihood when assuming that the distribution of the processing time of the product individual associated with the manufacturing event follows the probability distribution function obtained by fitting;
Calculating a difference between the likelihood and the event likelihood;
The cause estimation method according to claim 1, further comprising: Based on at least one of the occurrence date and time and the end date and time of the manufacturing event, and at least one of the start time and completion time of the product individual associated with the manufacturing event, the manufacturing event and the manufacturing event are Determining a time difference indicating temporal perspective with respect to the associated product individual for each product individual and calculating an average thereof;
The cause estimation method according to claim 3, further comprising: Displaying one or more manufacturing events on a display device in order of the average magnitude of the time differences together with information indicating a difference between the likelihood and the event time likelihood;
The cause estimation method according to claim 4, further comprising: The step of associating the manufacturing event with the product individual includes:
A step of associating the manufacturing event with a product individual whose manufacturing period overlaps with a predetermined period in which the manufacturing event is considered to have influenced the manufacture of the product individual.
The cause estimation method according to claim 1. Fitting the predetermined probability distribution function to the distribution of the processing times of the plurality of product individuals,
Fitting the predetermined probability distribution function to a distribution obtained by removing outliers by a predetermined outlier detection method from the distribution of the processing times of the plurality of product individuals.
The cause estimation method according to claim 3. Obtaining production performance information of the production process for each of a plurality of product individuals;
Calculating a processing time in the production process for each of the plurality of product individuals based on the production record information;
Obtaining information on a manufacturing event indicating the status of the production process;
Linking the manufacturing event and the product individual based on the production performance information and information on the manufacturing event;
Displaying the distribution of the processing times of the plurality of product individuals and the distribution of the processing times of the product individuals associated with the manufacturing event on a display device in a superimposed manner;
A program that causes a computer to execute.

Images