WO2022059183A1

WO2022059183A1 - Information processing device, information processing method, and information processing program

Info

Publication number: WO2022059183A1
Application number: PCT/JP2020/035512
Authority: WO
Inventors: 直輝伊藤
Original assignee: 三菱電機株式会社
Priority date: 2020-09-18
Filing date: 2020-09-18
Publication date: 2022-03-24
Also published as: CN116194945A; JPWO2022059183A1; JP7154468B2; TW202230060A

Abstract

In the present invention, an improvement location analysis unit (103) designates, as a designated element, an element for which performance is to be improved from among three or more elements. The improvement location analysis unit (103) also extracts, as relation elements, two or more elements in a significant relationship with the designated element from among elements other than the designated element. The improvement location analysis unit (103) furthermore analyzes the effect of the performance of each of the two or more extracted relation elements on the performance of the designated element and estimates, from among the two or more relation elements, a relation element to be improved, which is a relation element for which the performance is to be improved in order to improve the performance of the designated element.

Description

Information processing equipment, information processing methods and information processing programs

This disclosure relates to a technique for performing analysis to improve performance.

In production systems such as factories, priority targets are set according to the situation from time to time among management indicators such as quality, cost, delivery date, and production quantity. Then, production control is performed to achieve the set priority target.
The priority goal is called KGI (Key Goal Indicator). For example, when quality is set in KGI, daily production control is performed so as to achieve the quality target value. Production control collects information on the current operational status from the production system, compares the current value with the target value, and if the current value does not reach the target value, improves so that the current value achieves the target value. To carry out activities. Improvement activities include activities such as strengthening equipment in the production system, adjusting parameters, training workers, reviewing work procedures, and reviewing materials and / or inventories.

Conventionally, such improvement activities are often carried out based on the experience of production system managers, and there has been a problem that improvement activities that do not necessarily contribute to the achievement of priority goals or improvement activities that are less effective are carried out.
In recent years, such problems have been solved by promoting the introduction of IoT (Internet of Things) in production systems. Specifically, the following activities will solve the problems. In addition to the current value of KGI in a production system, detailed data on the process, equipment, and equipment status in the equipment at that time is collected. Then, by analyzing the collected data, the relationship of the data in the production system is clarified. Then, the clarified relationship is used as a reference for production control.

For example, Patent Document 1 defines a hierarchical structure of relationships between a plurality of KPIs (Key Performance Indicators), each of which is a management index for a plurality of processes and / or a plurality of facilities. Further, in Patent Document 1, information for calculating KPI is collected from the process and / or equipment. Then, in Patent Document 1, by correlating each KPI, an alarm for notifying the administrator of the abnormality when an abnormality occurs is efficiently selected.

Japanese Unexamined Patent Publication No. 2019-117464

However, in the correlation analysis used in the technique of Patent Document 1, since the influence when the collected information is an outlier is large, complicated preprocessing is required to remove this influence. In addition, since correlation analysis analyzes 1: 1 relationships for KPIs in different processes, it is not possible to analyze one-to-many information relationships such as relationships between KGIs and multiple KPIs. There is.

As described above, in the technique of Patent Document 1, when improvement activities are performed in a system composed of a large number of elements such as a production system, an element for improving KGI, that is, an element for improving performance and other elements are used. It is difficult to analyze the relationship with multiple factors. Therefore, the technique of Patent Document 1 has a problem that it is not easy to identify other elements that contribute to the improvement of the performance of the element for which the performance is to be improved.

One of the main purposes of this disclosure is to solve such problems. More specifically, the main object of the present disclosure is to efficiently identify the elements that contribute to the improvement of the performance of the elements for which the performance should be improved.

The information processing device according to this disclosure is
A designated part that designates an element whose performance should be improved among three or more elements as a designated element,
An extraction unit that extracts two or more elements that have a significant relationship with the designated element from the elements other than the designated element as related elements.
To improve the performance of the designated element from among the two or more related elements by analyzing the influence of the performance of each of the two or more related elements extracted by the extraction unit on the performance of the designated element. It has an estimation unit that estimates related elements to be improved, which are related elements for which performance should be improved.

According to the present disclosure, it is possible to efficiently identify the elements that contribute to the improvement of the performance of the elements for which the performance should be improved.

The figure which shows the functional composition example of the improvement part analysis apparatus which concerns on Embodiment 1. FIG. The figure which shows the hardware configuration example of the improvement part analysis apparatus which concerns on Embodiment 1. FIG. The figure which shows the structural example of the information model which concerns on Embodiment 1. The figure which shows the example of the setting item which concerns on Embodiment 1. The flowchart which shows the operation example of the evaluation part which concerns on Embodiment 1. The figure which shows the example of the evaluation result by the evaluation unit which concerns on Embodiment 1. FIG. The figure which shows the example of the evaluation result by the evaluation unit which concerns on Embodiment 1. FIG. The flowchart which shows the operation example of the improvement part analysis part which concerns on Embodiment 1. The flowchart which shows the operation example of the improvement part analysis part which concerns on Embodiment 1. The figure which shows the example of the analysis target which concerns on Embodiment 1. The figure which shows the example of the analysis condition which concerns on Embodiment 1. FIG. The figure which shows the example of the analysis result of the improvement part analysis part which concerns on Embodiment 1. The figure which shows the example of the setting item which concerns on Embodiment 2. The figure which shows the example of the analysis condition which concerns on Embodiment 2. The figure which shows the example of the effect obtained by Embodiment 2. The figure which shows the example of the setting item which concerns on Embodiment 3. The figure which shows the structural example of the information model which concerns on Embodiment 4. The figure which shows the example of the analysis condition which concerns on Embodiment 4. The flowchart which shows the operation example of the improvement part analysis part which concerns on Embodiment 4. The figure which shows the example of the analysis condition which concerns on Embodiment 5. The figure which shows the output example which concerns on Embodiment 5. The figure which shows the functional composition example of the improvement part analysis apparatus which concerns on Embodiment 6. The figure which shows the example of the improvement result which concerns on Embodiment 6. The figure which shows the example of the analysis condition which concerns on Embodiment 6. The figure which shows the output example which concerns on Embodiment 6. The figure which shows the example of the analysis condition which concerns on Embodiment 7. The figure which shows the functional structure example of the machine learning apparatus which concerns on Embodiment 7. The flowchart which shows the operation example of the machine learning apparatus which concerns on Embodiment 7. The flowchart which shows the correction procedure of the analysis result output which concerns on Embodiment 7. The figure which shows the example of the neural network which concerns on Embodiment 7.

Hereinafter, embodiments will be described with reference to figures. In the following description and drawings of the embodiments, those having the same reference numerals indicate the same parts or corresponding parts.

Embodiment 1.
*** Explanation of configuration ***
FIG. 1 shows an example of a functional configuration of the improved location analysis device 100 according to the present embodiment.
The improved location analysis device 100 according to the present embodiment is connected to the analysis target 200 via the network 300. In this embodiment, the analysis target 200 is a production system.
The improvement location analysis device 100 corresponds to an information processing device. Further, the operation procedure of the improvement point analysis device 100 corresponds to the information processing method.

As shown in FIG. 1, the improvement location analysis device 100 includes an information storage unit 101, an evaluation unit 102, an improvement location analysis unit 103, and an information collection unit 104.
Details of the information storage unit 101, the evaluation unit 102, the improvement location analysis unit 103, and the information collection unit 104 will be described later.

FIG. 2 shows an example of the hardware configuration of the improved location analyzer 100.
The improvement location analyzer 100 is a computer.
The improvement location analysis device 100 includes a processor 901, a storage device 902, and a communication interface 903 as hardware. The processor 901, the storage device 902, and the communication interface 903 are connected to each other by the bus 905.
The storage device 902 stores the program 904. The program 904 is a program for realizing the functions of the evaluation unit 102, the improvement point analysis unit 103, and the information collection unit 104 shown in FIG.
The processor 901 reads the program 904 from the storage device 902 and executes the program 904. When the processor 901 executes the program 904, the functions of the evaluation unit 102, the improvement point analysis unit 103, and the information collection unit 104, which will be described later, are realized.
Program 904 corresponds to an information processing program.
Although not shown, the storage device 902 stores various information necessary for realizing the function of the improvement point analysis device 100 according to the present embodiment, in addition to the program 904. The information storage unit 101 shown in FIG. 1 is realized by the storage device 902.
The communication interface 903 is used for communication with the production system which is the analysis target 200.

FIG. 3 shows a configuration example of the information model used in this embodiment.
In the information model, a plurality of elements constituting the production system, which is the analysis target 200, are shown. Further, in the information model, the relationship between each element is shown by a hierarchical structure and / or a logical structure. In FIG. 3, the solid line shows the relationship by the hierarchical structure, and the broken line arrow shows the relationship by the logical structure.

In the information model of FIG. 3, the hierarchies include production lines, processes, equipment and equipment.
Then, "Product A production lead time" is defined as an element constituting the hierarchy: production line. FIG. 3 shows an example in which "Product A production lead time" is set as the KGI of the production system and production is controlled.
As the lower hierarchy of "Product A production lead time", "process # 1 lead time", "process # 2 lead time" and "process # 3 lead time", which are the lead times of each process of the production system, are defined. ing. "Process # 1 lead time", "process # 2 lead time" and "process # 3 lead time" are connected to "product A production lead time" by a hierarchical structure. That is, the "process # 1 lead time", "process # 2 lead time", and "process # 3 lead time" may affect the "product A production lead time". Further, each process is connected by a relationship by a logical structure based on the production process. Here, an example in which production is performed in the order of "process # 1", "process # 2", and "process # 3" is shown. In addition, in this specification, "lead time" means required time. That is, the "product A production lead time" is the time required to complete the production of the product A.
Similarly, the relationship between the equipment and equipment hierarchies and the elements of the upper hierarchy is shown.
Specifically, as the elements that make up the hierarchy: equipment, "equipment # 1-1 lead time", "equipment # 1-2 lead time", "equipment # 2-1 lead time", "equipment # 3-1""Leadtime" and "Equipment # 3-2 lead time" are defined. “Equipment # 1-1 lead time” and “equipment # 1-2 lead time” can affect “process # 1 lead time”. Further, the "equipment # 2-1 lead time" may affect the "process # 2 lead time". Further, "equipment # 3-1 lead time" and "equipment # 3-2 lead time" may affect "process # 3 lead time".
Hierarchy: As elements that make up the device, "PLC # 1-1-1 cycle time", "servo # 1-1-2 motor current value", "sensor # 1-1-3 target angle", "PLC""# 1-2-1 cycle time" and "robot # 1-2-2 arrival rate" are defined. "PLC # 1-1-1 cycle time", "servo # 1-1-2 motor current value" and "sensor # 1-1-3 target angle" affect "equipment # 1-1 lead time". obtain. Further, "PLC # 1-2-1 cycle time" and "robot # 1-2-2 arrival rate" may affect "equipment # 1-2 lead time". Further, the "servo # 1-1-2 motor current value" may affect the "PLC # 1-1-1 cycle time" and the "sensor # 1-1-3 target angle". In addition, "sensor # 1-1-3 target angle" affects "robot # 1-2-2 arrival rate", and "robot # 1-2-2 arrival rate" is "PLC # 1-2-1". It can affect the "cycle time".

Here, the information storage unit 101, the evaluation unit 102, the improvement point analysis unit 103, and the information collection unit 104 shown in FIG. 1 will be described.

The information storage unit 101 stores the information model illustrated in FIG.
Further, the information storage unit 101 stores the setting items described later.
Further, the information storage unit 101 stores the evaluation result by the evaluation unit 102.
Further, the information storage unit 101 stores the analysis result by the improvement location analysis unit 103.
Further, the information storage unit 101 stores the information collected by the information collection unit 104.

The evaluation unit 102 evaluates whether or not the performance matches the performance standard for each element included in the analysis target 200. The evaluation unit 102 evaluates whether or not the performance of each element matches the performance standard defined for each element.
Further, although each element constitutes a plurality of layers as described above, the evaluation unit 102 may evaluate whether or not the performance of each element meets the performance standard with a different time width for each layer. good.
Further, the evaluation unit 102 may output the evaluation result each time the evaluation is performed.

Based on the evaluation result by the evaluation unit 102, the improvement point analysis unit 103 designates an element whose performance should be improved among the elements included in the analysis target 200 as a designated element.
Further, the improvement point analysis unit 103 may designate the estimated improvement target related element (described later) as a new designated element. Further, the improvement point analysis unit 103 may repeatedly designate the estimated new improvement target related element as a new designated element every time a new improvement target related element is estimated.

Further, the improvement point analysis unit 103 extracts one or more elements having a significant relationship with the designated element from the elements other than the designated element as related elements. In the present embodiment, since it is possible to analyze the 1: 1 relationship between the designated element and the related element, the improvement point analysis unit 103 will explain an example of extracting one or more elements as the related element. When analyzing the relationship between one designated element and each of the plurality of related elements, the improvement point analysis unit 103 extracts two or more elements as related elements. A "significant relationship" is a relationship that can affect the performance of a designated element. More specifically, in the information model of FIG. 3, at the starting point of the broken line arrow (relationship by logical structure) toward the element of the lower hierarchy connected by the solid line (relationship by hierarchical structure) or the designated element. It is a located element.
For example, when "Product A production lead time" is designated as a designated element by the evaluation unit 102, the improvement point analysis unit 103 sets it as an element (related element) having a significant relationship with "Product A production lead time". Extract "process # 1 lead time", "process # 2 lead time", and "process # 3 lead time". Further, for example, when "process # 2 lead time" is designated as a designated element by the evaluation unit 102, the improvement point analysis unit 103 has an element (related element) having a significant relationship with "process # 2 lead time". As, "process # 1 lead time" and "equipment # 2-1 lead time" are extracted. The "performance" is a value obtained by measurement and / or calculation. For example, the performance of "Product A production lead time" is a time obtained by measuring the required time of each process and adding the required time of each process. Further, for example, the performance of the "servo # 1-1-2 motor current value" is the motor current value obtained by actually measuring the servo # 1-1-2.

Further, the improvement point analysis unit 103 analyzes the influence of the performance of each of the extracted one or more related elements on the performance of the designated element, and improves the performance of the designated element from among the one or more related elements. Estimate the related elements to be improved, which are the related elements that should improve the performance. The improvement point analysis unit 103 uses that the performance of the designated element is improved (or deteriorated) as the conclusion unit, and is conditioned on the condition that the performance of each of the one or more related elements is improved (or deteriorated). Perform the association analysis used in the department to estimate the factors related to the improvement target. Association analysis will be described later.
Further, the improvement point analysis unit 103 analyzes the influence of the performance of each improvement target-related element on the performance of other improvement target-related elements when a plurality of improvement target-related elements are estimated, and a plurality of improvement target-related elements. Set priorities between related elements.
Further, when a new designated element is designated by the evaluation unit 102, the improvement point analysis unit 103 sets one or more elements other than the new designated element, which have a significant relationship with the new designated element, as a new related element. Extract as. Then, the improvement point analysis unit 103 analyzes the influence of the performance of each of the extracted one or more new related elements on the performance of the new designated element, and from among the one or more new related elements, a new one. Estimate new related elements whose performance should be improved in order to improve the performance of the specified element as new improvement target related elements.
Further, the improvement point analysis unit 103 repeatedly extracts one or more elements other than the designated new designated element as a new related element every time a new designated element is designated, and one or more new designated elements. Every time the related element is extracted, the estimation of the new improvement target related element may be repeated.
The improvement location analysis unit 103 corresponds to a designation unit, an extraction unit, and an estimation unit. Further, the processing performed by the improvement point analysis unit 103 corresponds to the designated processing, the extraction processing, and the estimation processing.

Here, association analysis will be described.
Association analysis (also called basket analysis, association rules, etc.) is known as a method for analyzing the relationship between a plurality of pieces of information.
In the association analysis, statistical information is used as an input, and the degree of support, reliability, and lift value are calculated for the relationship between the condition part and the conclusion part. The degree of support is the ratio of data including both the condition part and the conclusion part to the total number of data. The reliability is the ratio of the data including both the condition part and the conclusion part to the number of data including the condition part. The lift value is a value obtained by dividing the reliability by the number of data including the conclusion part. Generally, when the lift value is larger than 1, the influence of the condition part on the conclusion part is large, and it can be quantitatively determined that there is a relationship between the conclusion part and the condition part.
However, in the association analysis, it is necessary to calculate the support level, the reliability, and the lift value for each combination of input information, so that the amount of calculation becomes enormous. Therefore, there is a problem that association analysis cannot be simply applied to a production system having many kinds of information.
In the present embodiment, the improvement point analysis unit 103 determines that the calculation maintenance condition is not satisfied in any of the plurality of calculation items (support degree, reliability, lift value) included in the association analysis. Do not calculate uncalculated calculation items among multiple calculation items. By doing so, in the present embodiment, the association analysis is effectively applied to the production system having many kinds of information.

The information collecting unit 104 collects information about each element shown in FIG. 3 from the production system which is the analysis target 200.
For example, the information collecting unit 104 collects performance for each element shown in FIG. Specifically, the information collecting unit 104 collects the time required for each measured process as the performance of the "product A production lead time", adds the time required for each process, and the time required for the production of the product A. To get. Further, the information collecting unit 104 collects the motor current value obtained by actually measuring the servo # 1-1-2 as the performance of the "servo # 1-1-2 motor current value".
The information collecting unit 104 stores the collected information in the information storage unit 101.

FIG. 4 shows an example of setting items of the information collecting unit 104.
The information collecting unit 104 collects information on each element included in the information model according to the setting items shown in FIG.
In FIG. 4, elements, collection targets, monitoring periods, and determination criteria are defined as setting items of the information collection unit 104.
Among the setting items of FIG. 4, the element included in the information model is shown in the element column.
The collection target column indicates how to collect information. As a collection method, there are a method of collecting information directly from any device existing in the production system and a method of calculating based on the information collected from any device. When collecting information directly from a device, the device from which the information was collected is indicated in the collection target column.
In the monitoring period column, the time width for applying the criterion is shown.
In the column of determination criteria, criteria used for evaluation by the evaluation unit 102, that is, performance criteria are shown.
The information collected by the information collecting unit 104 is held by the evaluation unit 102 as time-series data as shown in the stored contents.

*** Explanation of operation ***
FIG. 5 is a flowchart showing an operation example of the evaluation unit 102.
FIG. 6 shows an example of the evaluation result of the evaluation unit 102 in a graph format.
FIG. 7 shows an example of the evaluation result of the evaluation unit 102 in a table format.
FIG. 8 is a flowchart showing an operation example of the improvement point analysis unit 103.
FIG. 9 is a flowchart showing the details of step S204 of FIG.
FIG. 10 shows an example of an analysis target according to the present embodiment.
FIG. 11 shows an example of the analysis conditions according to the present embodiment.
FIG. 12 shows an example of the analysis result of the improvement point analysis unit 103.
Hereinafter, an operation example of the improved location analysis device 100 according to the present embodiment will be described with reference to FIGS. 1 to 12.

Pre-setting phase The manager or designer of the production system generates the information model shown in FIG. 3 and the setting items shown in FIG. 4 for the management of the production system. Then, the manager or the designer of the production system stores the generated information model and setting items in the information storage unit 101 of the improvement point analysis device 100.
It is desirable to generate the information model and setting items based on the design information of the production system.

Information collection phase The information collection unit 104 collects information from the production system, which is the analysis target 200, based on the setting items in FIG. Then, the collected information is stored in the information storage unit 101.
Even if the information collecting unit 104 acquires information collected by an external device other than the improvement location analysis device 100 from the external device and stores the information acquired from the external device in the information storage unit 101 in association with the setting items. good.

Evaluation Phase Next, as an evaluation phase, the evaluation unit 102 performs the flowchart shown in FIG.
Specifically, the evaluation unit 102 reads the setting items shown in FIG. 4 from the information storage unit 101 (step S101).
Next, the evaluation unit 102 reads the information collected by the information collection unit 104 from the information storage unit 101 (step S102).
Next, the information collecting unit 104 evaluates the performance of each element using the setting items and the collected information, and stores the evaluation result in the information storage unit 101 (step S103). That is, the information collecting unit 104 determines whether or not the information collected by the information collecting unit 104 meets the determination criteria for each element shown in the setting item in the unit of the monitoring period. When the "collection target" is defined as "calculation" as in the "product A production lead time", the evaluation unit 102 performs a calculation based on the information collected by the information collection unit 104, and the calculation is performed. Compare the obtained values with the criteria.

6 and 7 show an example of the evaluation result by the evaluation unit 102. FIG. 6 shows the evaluation results in a graph format, and FIG. 7 shows the evaluation results in a table format.
For example, the determination standard of "Product A production lead time" is the threshold value X1. When the performance (required time) of the "product A production lead time" exceeds the threshold value X1 in a certain monitoring period, the evaluation unit 102 evaluates it as HIGH (1 in the binary value). Further, when the performance (required time) of the "product A production lead time" is equal to or less than the threshold value X1 in another monitoring period, the evaluation unit 102 evaluates it as LOW (0 in the binary value). In this embodiment, since the "product A production lead time" is set to KGI, the productivity decreases when the performance (required time) of the "product A production lead time" is higher than the judgment standard (= HIGH). It means that you are doing it.
The evaluation unit 102 may sequentially output the evaluation results to the HMI (Human Machine Interface). With this configuration, the person in charge of improving the production system can understand the situation of the production system in real time by referring to the HMI and determine the necessity of improvement.

Improvement location analysis phase The person in charge of improving the production system refers to the evaluation result by the evaluation unit 102 and determines the necessity of improvement from the evaluation status of the evaluation unit 102 for KGI. For example, as shown in FIGS. 6 and 7, when the “product A production lead time” is higher than the criterion, that is, there are multiple periods in which the productivity is reduced, the person in charge of improving the production system is in charge of improving the production system. Judge that improvement is necessary.
When it is determined that improvement is necessary, the person in charge of improving the production system instructs the improvement point analysis device 100 to analyze by the improvement point analysis unit 103.
The improvement point analysis unit 103 executes the flow of FIG. 8 based on the instruction from the person in charge of improvement of the production system.
Here, an example is shown in which the improvement point analysis unit 103 executes the flow of FIG. 8 based on an instruction from the person in charge of improvement of the production system, but the improvement point analysis unit 103 periodically executes the flow of FIG. You may. Alternatively, when a specified number of evaluation results by the evaluation unit 102 are accumulated, the improvement point analysis unit 103 may execute the flow of FIG. Further, when the improvement point analysis unit 103 determines the necessity of improvement by referring to the evaluation result by the evaluation unit 102 and determines that improvement is necessary, the flow of FIG. 8 may be executed.

As shown in FIG. 8, the improvement location analysis unit 103 reads the information model shown in FIG. 3 from the information storage unit 101 (step S201).
Further, the improvement point analysis unit 103 reads the evaluation result by the evaluation unit 102 from the information storage unit 101 (step S202).
The order of step S201 and step S202 may be changed, or step S201 and step S202 may be performed in parallel.

Next, the improvement point analysis unit 103 designates a designated element to be analyzed, and sets or reads the analysis condition (step S203).
The improvement point analysis unit 103 may specify the designated element according to the instruction of the person in charge of improvement of the production system, or may analyze the evaluation result by the evaluation unit 102 and specify the designated element. For example, the improvement point analysis unit 103 designates the element of the highest hierarchy among the elements whose performance does not meet the determination criteria a plurality of times as the designated element.
The details of the analysis conditions will be described later.

Next, the improvement location analysis unit 103 performs analysis and stores the analysis result in the information storage unit 101 (step S204).
Further, when the analysis is continued (YES in step S205), the process returns to step S203, and the improvement point analysis unit 103 designates a new designated element. The improvement point analysis unit 103, for example, designates the improvement target related element obtained in step S204 as a new designated element.

FIG. 9 shows the details of step S204. Hereinafter, the details of step S204 will be described with reference to FIG.

First, the improvement point analysis unit 103 extracts a significant combination of the conclusion unit and the condition unit in the association analysis from the information model (step S2041).
A significant combination means that the conclusion part and the condition part are consistent in terms of both the hierarchical relationship and the logical relationship in the information model. That is, a significant combination means that the conclusion part and the condition part are connected in the correct direction in the relation by the hierarchical structure, or are connected in the correct direction in the relationship by the logical structure. Elements that are connected in the correct direction in the relationship between the elements of the conclusion part and the hierarchical structure and elements that are connected in the correct direction in the relationship between the elements of the conclusion part and the logical structure affect the performance of the elements of the conclusion part. It is an element that can be given.
Specifically, the improvement point analysis unit 103 sets the designated element specified in step S203 in the conclusion unit. Then, the improvement point analysis unit 103 determines the elements connected in the correct direction in the relationship between the designated element and the hierarchical structure and the element connected in the correct direction in the relationship between the designated element and the logical structure based on the information model. Set in the condition section. The element set in the condition part corresponds to the related element.
For example, when the improvement point analysis unit 103 specifies "product A production lead time" as a designated element in step S203, the improvement point analysis unit 103 has the correct direction in the relationship between the "product A production lead time" and the hierarchical structure. The "process # 1 lead time", "process # 2 lead time", and "process # 3 lead time" connected by are extracted as related elements.
In this case, as shown in FIG. 10, the improvement point analysis unit 103 sets in the conclusion unit that "the value of the product A production lead time is higher than the judgment standard", and sets "process # 1 lead time" and ". "Process # 2 lead time" and "process # 3 lead time" are set in the condition unit.
Further, for example, when the improvement point analysis unit 103 specifies "process # 1 lead time" as a designated element in step S203, "process # 2 lead time" and "process # 3 lead time" are related by a logical structure. Inconsistent with, and the combination is not significant (even if the lead time of step # 2 or step # 3 changes, the lead time of step # 1 does not change). Therefore, the improvement point analysis unit 103 does not extract "process # 2 lead time" and "process # 3 lead time" as related elements.

Next, the improvement point analysis unit 103 executes an association analysis for the combination of the extracted condition unit and the conclusion unit (step S2042).
Here, the improvement point analysis unit 103 shall calculate the support level, the reliability, and the lift value in the association analysis. The calculation order of these calculation items is not particularly specified.
The improvement point analysis unit 103 may stop the calculation of the uncalculated calculation item when the calculation maintenance condition is not satisfied in any of the calculation items with reference to the analysis condition. With this configuration, the amount of calculation for association analysis can be reduced.
FIG. 11 shows an example of analysis conditions.
In the analysis conditions of FIG. 11, the section (time width) to be analyzed and the calculation maintenance conditions of each calculation item of the association analysis are defined.
In the example of FIG. 11, the condition of the section is a constant section regardless of the hierarchy. It is common for elements in the upper hierarchy to be collected in a longer cycle, and may include a certain delay until changes in the elements in the lower hierarchy are transmitted to the upper hierarchy. In such a case, it is advisable to shift the section (time width) to be analyzed between the elements of the upper layer and the elements of the lower layer.
Further, in the example of FIG. 11, it is shown that the calculation / maintenance condition of the lift value is 1 or more, the calculation / maintenance condition of the support degree is larger than 0.001, and the calculation / maintenance condition of the reliability is larger than 0.001.

FIG. 12 shows an example of the analysis result by the improvement point analysis unit 103.
In FIG. 12, the combination in which the support, reliability, and lift value are all canceled by diagonal lines is a combination that was not the target of the association analysis because it is not a significant combination.

The upper part of FIG. 12 shows the result obtained by analyzing the influence of the lead time of each process on the product A production lead time by the improvement point analysis unit 103. As described above, the improvement point analysis unit 103 extracts and analyzes only significant combinations. Therefore, in the upper part of FIG. 12, "Product A production lead time" is set in the conclusion part, and each of "process # 1 lead time", "process # 2 lead time", and "process # 3 lead time" is a condition. The result of the association analysis performed by setting the part is shown.
In the upper example of FIG. 12, the association analysis is based on the condition that "process # 1 lead time" is higher than the judgment standard (= HIGH), and the case where "process # 2 lead time" is higher than the judgment standard (= HIGH). In the association analysis with the condition part, the lift value is larger than 1. Therefore, it is highly possible that "process # 1 lead time" and "process # 2 lead time" are factors of deterioration of "product A production lead time". Therefore, the improvement location analysis unit 103 estimates that the “process # 1 lead time” and the “process # 2 lead time” are related elements to be improved. That is, the improvement point analysis unit 103 extracts "process # 1 lead time" and "process # 2 lead time" as elements for which the performance should be improved in order to improve the performance of "product A production lead time".

In the lower part of FIG. 12, the improvement point analysis unit 103 analyzes the influence of each of "process # 1 lead time", "process # 2 lead time" and "process # 3 lead time" on the lead time of other processes. The results obtained are shown below.
In the upper part of FIG. 12, since there are a plurality of combinations having a lift value larger than 1, the improvement point analysis unit 103 also analyzes the influence of the lead time of each process on the lead time of other processes. That is, the improvement point analysis unit 103 designates each process as a new designated element, extracts processes other than the process designated as the new designated element as a new related element, and performs association analysis.
In the lower example of FIG. 12, an association in which the case where the "process # 1 lead time" is higher than the judgment criterion (= HIGH) is set in the condition section and the "process # 2 lead time" is set in the conclusion section. In the analysis, the lift value is greater than 1. Therefore, it is highly possible that the “process # 1 lead time” is a factor in the deterioration of the “process # 2 lead time”. Therefore, the improvement point analysis unit 103 extracts the “process # 1 lead time” as an element for which the performance should be improved in order to improve the performance of the “process # 2 lead time”.
As a result, the improvement point analysis unit 103 estimates that "process # 1 lead time" is the highest priority related element for improvement. That is, the improvement point analysis unit 103 determines that "process # 1 lead time" is the most effective improvement target related element for improving the performance of "product A production lead time", and determines that "process # 2 lead time" is the most effective. Is the next effective improvement target related element.
When a plurality of improvement target-related elements are obtained as in the upper example of FIG. 12, the improvement point analysis unit 103 gives priority among the plurality of improvement target-related elements as in the lower example of FIG. To set.

From the above analysis results, the improvement point analysis unit 103 can presume that "the deterioration of the product A production lead time is caused by the deterioration of the process # 1 lead time and the deterioration of the process # 2 lead time". Further, the improvement point analysis unit 103 can presume that "the deterioration of the process # 2 lead time is due to the deterioration of the process # 1 lead time". Therefore, the improvement point analysis unit 103 may propose the improvement point to the person in charge of improving the production system, saying, "First, the process # 1 lead time, which is a factor of deterioration of both lead times, should be improved." can.
The improvement location analysis unit 103 outputs such an analysis result (proposal of improvement location) to the HMI, and stores the analysis result in the information storage unit 101 (step S2043).

Further, the improvement point analysis unit 103 can deeply analyze the cause of the deterioration of the “process # 1 lead time” as needed (step S205 in FIG. 8).
Specifically, the improvement point analysis unit 103 sets "process # 1 lead time" as a new designated element in the conclusion unit based on the relationship of the hierarchical structure of the information model in FIG. 3, and "equipment # 1-". Perform the association analysis with "1 lead time" and "equipment # 1-2 lead time" set in the condition section as new related elements.
After the analysis of the equipment hierarchy is completed, the improvement point analysis unit 103 may further perform an association analysis in which the element of the equipment hierarchy is set in the condition unit as a new related element, if necessary. In this way, the improvement point analysis unit 103 can perform deep analysis. As an analysis condition, the number of repetitions of such an analysis may be set.

*** Explanation of the effect of the embodiment ***
As described above, according to the present embodiment, it is possible to efficiently identify the elements that contribute to the improvement of the performance of the elements whose performance should be improved.
That is, the improvement point analysis device 100 according to the present embodiment analyzes the relationship between the KGI and the plurality of information stepwise and logically while referring to the relationship by the hierarchical structure and the logical structure defined in the information model. Therefore, according to the present embodiment, it is possible to efficiently identify the improvement points that contribute to the improvement of KGI.

Further, according to the present embodiment, the evaluation unit 102 sequentially outputs the evaluation results to the HMI, so that the person in charge of improving the production system understands the situation of the production system in real time and immediately determines the necessity of improvement. be able to.

Further, according to the present embodiment, the improvement point analysis unit 103 refers to the analysis condition, and if any of the calculation items does not correspond to the calculation maintenance condition, the uncalculated calculation item is not calculated, so that the analysis is performed. The amount of time calculation can be reduced.

Further, according to the present embodiment, by providing the number of repetitions for deep digging of the analysis by the improvement point analysis unit 103, the person in charge of improving the production system does not have to wait for the final result of the improvement point analysis device 100 by himself / herself. Analysis results can be obtained within the range where the experience of the above can be applied, and improvement activities can be streamlined.

Further, according to the present embodiment, when the improvement point analysis unit 103 is an analysis target having a different hierarchy, the analysis section can be adjusted according to the hierarchy, so that the analysis can be effectively performed.

Embodiment 2.
***Purpose***
In the first embodiment, the evaluation results obtained by the evaluation by a single criterion are binarized. In the method of the first embodiment, there is a possibility that it is not possible to clearly analyze which value the element of the device hierarchy affects the performance of the designated element, especially when improving the device hierarchy in the information model. be.
The second embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the first embodiment will be mainly described.
The matters not described below are the same as those in the first embodiment.

*** Explanation of configuration ***
Also in this embodiment, the configuration of the improved location analyzer 100 is as shown in FIGS. 1 and 2.
In the present embodiment, as shown in FIG. 13, additional determination criteria are provided for the setting items (FIG. 4) in the information collection shown in the first embodiment. Further, as shown in FIG. 14, subdivision conditions are provided in the analysis conditions (FIG. 11).
In FIG. 13, among the setting items in information collection, the threshold value X6 is set as the first judgment criterion for “sensor # 1-1-3 target angle”, and the threshold values X7 and X8 are set as additional judgment criteria. is doing. Further, in FIG. 14, as the conditions for subdivision, a case where the lift value is larger than 2 and a case where the support degree is larger than 0.5 are set.

*** Explanation of operation ***
In the present embodiment, the same operation as in the first embodiment is performed until the improvement point analysis phase is completed.
At this time, when the analysis result as shown in FIG. 12 is obtained and the conditions for subdividing the analysis conditions of FIG. 14 are satisfied, the evaluation unit 102 further evaluates with the additional determination criteria of FIG. conduct.
FIG. 15 shows an example of the effect in the second embodiment.
That is, in the present embodiment, the improvement point analysis unit 103 sets "equipment # 1-1 lead time" as the conclusion unit and "sensor # 1-1-3 target angle" as the condition unit, and performs association analysis. There is. Then, the improvement point analysis unit 103 estimates "sensor # 1-1-3 target angle" as an improvement target related element. The result of the association analysis satisfies the above-mentioned subdivision condition (FIG. 14). Therefore, as the evaluation unit 102 subdivides, does the performance of the "sensor # 1-1-3 target angle", which is an element related to the improvement target, match the judgment standard 2 (threshold values X7 and X8) which is an additional judgment standard? We are evaluating whether or not. FIG. 15 shows the evaluation results obtained by the evaluation using the determination criterion 2.
Although not shown in FIG. 15, it is possible to also show the results (lift value, support degree, reliability) of the analysis using the determination criterion 2 newly by subdivision. In this case, when the "sensor # 1-1-3 target angle" is the specific value, the "sensor # 1-1-3 target angle" is the performance of the "equipment # 1-1 lead time". It is possible to analyze whether it affects the deterioration.

*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, a plurality of determination criteria are provided, and conditions for subdivision for the evaluation unit 102 to apply the plurality of determination criteria are provided. Therefore, according to the present embodiment, the evaluation result in a single judgment criterion can be subdivided by a plurality of judgment criteria, and the element that can affect the performance of the designated element is specifically any value. If this happens, it can be clearly determined whether the performance of the specified element will be affected.

Embodiment 3.
***Purpose***
In the first and second embodiments, it is premised that the determination criteria of the setting items in the information collection unit 104 and the analysis conditions in the improvement point analysis unit 103 are set in advance with reference to design information and the like.
However, if the design information cannot be obtained or if there is a difference between the design information and the actual state of the production system, the effects in the first and second embodiments may not be obtained.
The third embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the first embodiment will be mainly described.
The matters not described below are the same as those in the first embodiment.

*** Explanation of configuration ***
Also in this embodiment, the configuration of the improved location analyzer 100 is as shown in FIGS. 1 and 2. However, in the present embodiment, the method of setting the determination criteria of the information collecting unit 104 is shown in FIG.
In FIG. 16, statistical processing for the collected information is defined as a determination criterion in the setting item of the information collecting unit 104. Statistical processing is set, for example, "mean value". In addition to this, those in which the standard deviation is taken into consideration in the mean value (mean value ± standard deviation), the mode value in the frequency distribution, the minimum value, and the like are also suitable, but are not limited thereto.

*** Explanation of operation ***
In the present embodiment, the same operation as in the first embodiment is performed until the middle of the information collection and evaluation phase.
In the present embodiment, in the flowchart of FIG. 5, in step S103, the evaluation unit 102 performs statistical processing on the information collected by the information collecting unit 104 and stored in the information storage unit 101. Then, the evaluation unit 102 sets the result of the statistical processing as the determination criterion in FIG. Then, the evaluation unit 102 evaluates by comparing the individual information collected by the information collection unit 104 and stored in the information storage unit 101 with the result of the statistical processing set as the determination standard. After that, the evaluation unit 102 stores the evaluation result in the information storage unit 101.
After that, in the improvement point analysis phase, the same operation as in the first embodiment is performed.

*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, since the result of the statistical processing is set as the determination criterion, the effects of the first and second embodiments can be obtained even when the design value of the analysis target cannot be obtained.
Further, by setting the result of statistical processing as the determination standard, it is possible to reduce the trouble of having to set the determination standard in advance.

Embodiment 4.
***Purpose***
In the first to third embodiments, it is premised that the relation by the hierarchical structure and / or the logical structure is defined by the information model.
However, especially in the equipment hierarchy, it is difficult to strictly define the information of the equipment because the designer is different from the designer of the production system. Therefore, it may not be possible to accurately define the relationship by the hierarchical structure and / or the logical structure. If the relationship is misdefined or cannot be defined, the wrong analysis result may be output. Also, analysis may occur for all possible combinations. In such a case, the efficiency is reduced.
The fourth embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the first embodiment will be mainly described.
The matters not described below are the same as those in the first embodiment.

*** Explanation of configuration ***
Also in this embodiment, the configuration of the improved location analyzer 100 is as shown in FIGS. 1 and 2. In the present embodiment, the configuration of the information model and the analysis conditions and the flowchart of the improvement point analysis unit 103 are different.
FIG. 17 shows an example of the information model according to the fourth embodiment. In FIG. 17, in the device hierarchy, the relationship by the hierarchical structure and the logical structure is not defined. That is, in the information model shown in FIG. 17, only the elements existing in the device hierarchy are defined.
FIG. 18 shows additional items under the analysis conditions in the fourth embodiment. In FIG. 18, an item related to the relationship is added to the analysis conditions. As a condition related to the relationship, it is conceivable to define, for example, "automatically generate the relationship of the device hierarchy". It may be defined to automatically generate the relationship of the hierarchy other than the device hierarchy, or it may be defined to generate the relationship by a method other than the automatic generation. Furthermore, it may be defined to periodically check the relationship once generated.
FIG. 19 shows an additional procedure performed by the improvement point analysis unit 103 in step S204 (execution and storage of analysis) of FIG.

*** Explanation of operation ***
The same operations as those in the first embodiment are performed up to the information collection phase, the evaluation phase, and step S203 in FIG.
In step S204, the flow of FIG. 19 is performed prior to the flow of FIG. That is, when the relationship between any of the elements is unknown, the improvement point analysis unit 103 estimates the relationship between the elements whose relationship is unknown and automatically generates the relationship between the elements.
Specifically, the improvement point analysis unit 103 refers to the setting item of FIG. 18 and executes the flow of FIG. 19 in order to automatically generate the relationship for the device hierarchy.
In FIG. 19, among the elements included in the equipment hierarchy, a special relationship is not defined with "PLC # 1-1-1 cycle time" in which the hierarchical structure with the equipment hierarchy which is the upper layer is defined. The procedure for automatically generating the relationship with "servo # x-1 motor current value" is shown.
First, in step S301, the improvement location analysis unit 103 executes an association analysis of the “PLC # 1-1-1 cycle time” and the “servo # x-1 motor current value”. In the example of FIG. 19, the improvement point analysis unit 103 sets that the “PLC # 1-1-1 cycle time” is higher than the determination criterion (= HIGH) in the condition unit, and sets the “servo # x-1 motor current”. The support, reliability, and lift value of the combination (hereinafter referred to as "combination 1") in which the "value" is set to be higher than the judgment criterion (= HIGH) in the conclusion unit are calculated. Further, the improvement point analysis unit 103 sets in the condition unit that the "servo # x-1 motor current value" is higher than the determination standard (= HIGH), and determines the "PLC # 1-1-1 cycle time". The support, reliability, and lift value of the combination (hereinafter referred to as "combination 2") in which the conclusion is set to be higher than the standard (= HIGH) are calculated. When the meaning of the information is unknown, it is desirable that the improvement point analysis unit 103 execute the association analysis including the combination when the value of each element is lower than the judgment criterion (= LOW).
Next, in step S302, the improvement point analysis unit 103 evaluates the analysis result of step S301. Here, the improvement point analysis unit 103 evaluates which combination of the support, reliability, and lift value of the analysis result gives the highest value. That is, the improvement point analysis unit 103 evaluates which of the combination 1 and the combination 2 gives the higher value. In the association analysis, if the evaluation result of the lift value is larger than 1, it can be evaluated that there is a relationship between the condition part and the conclusion part. Therefore, the improvement point analysis unit 103 may evaluate the results of each item with weights so as to emphasize the lift value. These weights may be provided in the setting items of FIG. Further, the condition for generating the relationship may be similarly provided in the setting item of FIG.
Finally, in step S303, the improvement location analysis unit 103 constructs a relationship between the elements with reference to the evaluation result, and stores the constructed relationship between the elements in the information storage unit 101.
In the example of FIG. 19, it is set in the condition part that the "servo # x-1 motor current value" is higher than the judgment standard, and the conclusion part that the "PLC # 1-1-1 cycle time" is higher than the judgment standard. In the combination set to (Combination 1), the support, reliability, and lift value are high. Therefore, the improvement point analysis unit 103 adds to the information model the relationship that the "servo # x-1 motor current value" affects the performance of the "PLC # 1-1-1 cycle time".
In this example, the procedure for automatically generating the relationship between "PLC # 1-1-1 cycle time" and "servo # x-1 motor current value" is shown. For the “sensor # x-2 target angle” and “robot # x-3 arrival rate” for which the relationship is not defined as shown in FIG. 17, the improvement point analysis unit 103 automatically generates the relationship by the same procedure. do.

*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, when the relationship between any of the elements is unknown, the improvement point analysis unit 103 estimates the relationship between the elements whose relationship is unknown, and determines the relationship between the elements. Automatically generated. Therefore, according to the present embodiment, even when the relation by the hierarchical structure and / or the logical structure cannot be accurately defined in the information model, the relation between the elements is constructed based on the actually collected information. And the analysis can be performed efficiently.
In addition, even if the relationship between elements is erroneously defined, the information model can be modified by evaluating the relationship between elements based on the information actually collected.

Embodiment 5.
***Purpose***
In the first to fourth embodiments, the analysis results are output in a plurality of items such as support, reliability, and lift value. It is necessary to determine the factors to be improved in consideration of the output of these multiple items. However, there is a problem that it is difficult for a production system administrator who is unfamiliar with analysis to determine which factor is an improvement point.
The fifth embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the first embodiment will be mainly described.
The matters not described below are the same as those in the first embodiment.

*** Explanation of configuration ***
Also in this embodiment, the configuration of the improved location analyzer 100 is as shown in FIGS. 1 and 2. In the present embodiment, the analysis conditions of the improvement location analysis unit 103 are different.
FIG. 20 shows the analysis conditions according to the fifth embodiment. In FIG. 20, a new analysis result output item is added as compared with FIG. As a condition for outputting the analysis result, for example, the calculation formula "A1 + A2 + A3" is defined. In addition, "A1" is set to 1 when the support degree is larger than 0.1, and 0 when the support degree is smaller than 0.1. Similarly, "A2" is set to 1 when the reliability is greater than 0.1 and 0 when the reliability is less than 0.1. In "A3", the lift value is set as it is when the lift value is 1 or more, and 0 is set when the lift value is smaller than 1.
The calculation formula may be adjusted so as to emphasize any of support, reliability, and lift value. For example, the weight α is used to make adjustments such as A1 + A2 + A3 × α. The weight α is set by the designer of the production system or the person in charge of improvement.
In the present embodiment, as shown in FIG. 20, the improvement point analysis unit 103 performs a calculation using a plurality of calculated values for a plurality of calculated items included in the association analysis, and performs a calculation using the plurality of calculated values. Outputs the calculated value of.

*** Explanation of operation ***
The same operation as that of the first embodiment is performed up to step S2042 in FIG. 9 of the information collection phase, the evaluation phase, and the improvement point analysis phase.
In step S2043, the improvement point analysis unit 103 calculates the analysis result output according to the calculation formula of the analysis result output of FIG. 20, outputs the calculation result, and stores the calculation result in the information storage unit 101.
FIG. 21 shows an example of the output according to the fifth embodiment. As shown in FIG. 21, the output according to the present embodiment includes the analysis result obtained according to the calculation formula of the analysis result output of FIG. 20.

*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, the analysis result output calculation method is defined in the analysis conditions, and the analysis result calculated according to the calculation method is output. Therefore, according to the present embodiment, the production system administrator who is unfamiliar with the analysis can easily determine which element is the improvement point.

Embodiment 6.
***Purpose***
In the fifth embodiment, it is necessary for the designer of the production system or the person in charge of improvement to appropriately set the calculation formula for outputting the analysis result of the improvement portion. However, especially in a complicated production system, the analysis result output and the actual improvement point may be different.
The sixth embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the fifth embodiment will be mainly described.
The matters not described below are the same as those in the fifth embodiment.

*** Explanation of configuration ***
FIG. 22 shows a configuration example of the improved location analysis device 100 according to the sixth embodiment. In the configuration of FIG. 22, the improvement record storage unit 105 is added to the configuration of FIG. 1. The improvement record is stored in the improvement record storage unit 105. It is the same as that shown in FIG. 1 except for the improvement record storage unit 105.
FIG. 23 shows an example of the improvement record stored in the improvement record storage unit 105. The improvement results shown in FIG. 23 include the events that have occurred and the factors (improvement points) of the events. It is desirable to describe the events and factors in detail, including specific values. The improvement results are described by the person in charge of improvement while operating the analysis target. Alternatively, if there is an improvement record of the same type of analysis target, the improvement record of the same type of analysis target may be diverted. However, in this case, it is desirable to describe it so that it can be understood that it is an improvement record of another analysis target. Alternatively, the correct / incorrect evaluation result or the evaluation result accompanied by the numerical value given to the analysis result output through the HMI by the person in charge of improvement referring to the analysis result output shown in the fifth embodiment may be used as the improvement result. At this time, it is desirable that the contents described in the improvement record storage unit 105 have a relationship defined in the information model. If the relationship is not defined in the information model, it may be configured so that the relationship is defined in the information model.
FIG. 24 shows an example of the analysis conditions according to the sixth embodiment. In FIG. 24, as a condition for outputting the analysis result, a calculation formula that reflects the improvement result in the output is defined. In FIG. 24, the number of actual improvements is described as the correction value “A4”, and “A4” is also included in the calculation formula.

*** Explanation of operation ***
The same operation as that of the first embodiment is performed up to step S2042 in FIG. 9 of the information collection phase, the evaluation phase, and the improvement point analysis phase.
In step S2043, the improvement point analysis unit 103 calculates the analysis result output according to the analysis result output calculation formula of FIG. 24, outputs the calculation result, and stores the calculation result in the information storage unit 101. That is, in step S2043, the improvement location analysis unit 103 corrects the calculated value obtained by the calculation formula “A1 + A2 + A3” using the improvement results for the related elements corresponding to the condition unit in the association analysis, and obtains the corrected calculated value. Output.
FIG. 25 shows an example of analysis result output according to the sixth embodiment. As shown in FIG. 25, in the present embodiment, the improvement result of FIG. 23 is output as a correction value, and the corrected analysis result output based on the number of improvement results is output.

*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, the improvement results are stored and the analysis result output is corrected according to the improvement results. Therefore, according to the present embodiment, it is possible to output the improvement points according to the actual conditions of the production system.

Embodiment 7.
***Purpose***
In the fifth and sixth embodiments, the analysis result output is calculated using the calculation formula, and the obtained analysis result output is output to obtain a more accurate analysis result.
However, in the case of a large-scale or complicated production system, the types of elements are enormous and the relationships between the elements are complicated. Therefore, it may be difficult to define a calculation formula so that the analysis result output matches the actual condition of the analysis target.
The seventh embodiment has a main purpose of solving such a problem.
In this embodiment, the difference from the fifth embodiment will be mainly described.
The matters not described below are the same as those in the fifth embodiment.

*** Explanation of configuration ***
FIG. 26 shows the setting of the analysis conditions according to the seventh embodiment. In FIG. 26, it is set to calculate the analysis result output in FIG. 20 or 24 by utilizing a trained model learned by using machine learning described later.
FIG. 27 shows a configuration example of the machine learning device 400 utilized by the improvement location analysis device 100. The machine learning device 400 includes a data acquisition unit 401, a teacher data acquisition unit 402, a learning unit 403, a learned model storage unit 405, and an output unit 404. The machine learning device 400 includes a processor, a storage device, a communication interface, and a bus as a hardware configuration, as in FIG. 2. The data acquisition unit 401, the teacher data acquisition unit 402, and the learning unit 403 are realized by, for example, a program. The program is executed by the processor. The trained model storage unit 405 is realized by a storage device.

The data acquisition unit 401 acquires the condition unit, the conclusion unit, the support degree, the reliability, and the lift value shown in FIGS. 10, 11, 20, and 24 as state variables. The data acquisition unit 401 may acquire the evaluation results of the evaluation unit 102 shown in FIGS. 6 and 7.
The teacher data acquisition unit 402 acquires the factors and events shown in the improvement results of FIG. 23.
The learning unit 403 is a data set created based on a combination of a condition unit output from the data acquisition unit 401, a conclusion unit, a support level, a reliability, a lift value, and factors and events output from the teacher data acquisition unit 402. Learn how to correct the output based on. That is, the learning unit 403 analyzes from the condition unit, the conclusion unit, the support level, the reliability, the lift value, which are the analysis results of the improvement point analysis unit 103 of the improvement point analysis device 100, and the factors and events which are the actual improvement results. Generate a trained model that infers how to correct the result output. Here, the data set is data in which state variables and teacher data are associated with each other.

The machine learning device 400 is used to learn how to correct the output of the improvement point analysis device 100. For example, the machine learning device 400 and the improvement point analysis device 100 connected to the improvement point analysis device 100 via a network. May be a separate device. Further, the machine learning device 400 may be built in the improvement point analysis device 100. Further, the machine learning device 400 may exist on the cloud server.

Any learning algorithm may be used as the learning algorithm used by the learning unit 403. In this embodiment, a case where a neural network is applied will be described as an example.
The learning unit 403 learns the output correction method by, for example, supervised learning according to a neural network model. Here, supervised learning is a model in which a large number of sets of data of a certain input and a result (label) are given to the machine learning device 400, the features in those data sets are learned, and the result is estimated from the input. To say.
A neural network is composed of an input layer composed of a plurality of neurons, an intermediate layer (hidden layer) composed of a plurality of neurons, and an output layer composed of a plurality of neurons. The intermediate layer may be one layer or two or more layers.
For example, in the case of a three-layer neural network as shown in FIG. 30, when a plurality of input data are input to the input layer (X1-X3), the value of each input data is multiplied by the weight W1 (w11-w16). Each input data multiplied by the weight W1 is input to the intermediate layer (Y1-Y2). Then, the result of the intermediate layer (Y1-Y2) is further multiplied by the weight W2 (w21-w26), and the result of the intermediate layer (Y1-Y2) multiplied by the weight W2 is output from the output layer (Z1-Z3). .. The output result changes depending on the value of the weight W1 and the value of the weight W2.
In the present application, the neural network is created based on the combination of the condition part, the conclusion part, the support degree, the reliability, the lift value acquired by the data acquisition unit 401, and the factors and events acquired by the supervised data acquisition unit 402. According to the data set, the output correction method is learned by so-called supervised learning.
That is, the neural network inputs the condition part, the conclusion part, the support degree, the reliability, and the lift value to the input layer, and adjusts the weights W1 and W2 so that the result output from the output layer approaches the factor and the event. Learn by.
The neural network can also learn the output correction method by so-called unsupervised learning. In unsupervised learning, a large amount of input data is given to the machine learning device 400, and the machine learning device 400 learns how the input data is distributed. In unsupervised learning, it is possible to perform learning by compressing, classifying, shaping, etc. on the input data without giving the corresponding teacher output data. That is, in unsupervised learning, features in multiple datasets can be clustered among similar people. The output can be predicted by using the clustering result and assigning the output so as to optimize the clustering result by setting some criteria. Semi-supervised learning is an intermediate problem setting between unsupervised learning and supervised learning. In semi-supervised learning, only a part of the set of input data and output data exists, and the others exist only of input data.

The learning unit 403 generates a trained model by executing the above learning.
The trained model storage unit 405 stores the trained model generated by the learning unit 403.
The output unit 404 outputs a correction method of the analysis result output of the improvement point analysis device 100 obtained by using the trained model. That is, by inputting the condition unit, the conclusion unit, the support degree, the reliability, and the lift value into the data acquisition unit 401, the condition unit, the conclusion unit, the support degree, the reliability, and the lift are input from the output unit 404 based on the trained model. An output correction method suitable for the value can be obtained.
In this embodiment, the output unit 404 of the machine learning device 400 outputs the correction method of the analysis result output to the improvement point analysis device 100 using the learned model obtained by the learning in the learning unit 403. However, the improved part analysis device 100 may acquire a trained model and acquire a correction method for an analysis result output based on the trained model.

*** Explanation of operation ***
Next, the process of learning by the machine learning device 400 will be described with reference to FIG. 28. FIG. 28 is a flowchart relating to the learning process of the machine learning device 400.
First, in step S401, the data acquisition unit 401 acquires the condition unit, the conclusion unit, the support degree, the reliability, and the lift value as state variables.
Next, in step S402, the teacher data acquisition unit 402 acquires factors and events that are actual improvements. In this embodiment, the data is acquired in the order described above, but it is sufficient if the condition part, the conclusion part, the support level, the reliability, the lift value, and the factors and events can be input in association with each other. They may be executed at the same time or in reverse order.
Further, in step S403, the learning unit 403 is a combination of the condition unit, the conclusion unit, the support level, the reliability, the lift value acquired by the data acquisition unit 401, and the factors and events acquired by the teacher data acquisition unit 402. According to the data set created based on, the correction method of the analysis result output is learned by so-called supervised learning, and the trained model is generated.
Finally, in step S404, the trained model storage unit 405 stores the trained model generated by the learning unit 403.

Next, with reference to FIG. 29, a process for obtaining a correction method for the analysis result output using the machine learning device 400 will be described.
First, in step S501, the data acquisition unit 401 acquires the condition unit, the conclusion unit, the support level, the reliability, and the lift value.
Next, in step S502, the learning unit 403 inputs the condition unit, the conclusion unit, the support level, the reliability, and the lift value into the trained model stored in the trained model storage unit 405, and corrects the analysis result output. obtain. The learning unit 403 outputs the correction method of the obtained analysis result output to the output unit 404.
Further, in step S503, the output unit 404 outputs a correction method for the analysis result output obtained by the trained model.
Finally, in step S504, the improvement point analysis unit of the improvement point analysis device 100 corrects the analysis result by using the correction method of the output analysis result output, and outputs the corrected analysis result. As a result, it is possible to output improvement points that match the actual conditions of the production system.

In the present embodiment, the case where supervised learning is applied to the learning algorithm used by the learning unit 403 has been described, but the present invention is not limited to this. As for the learning algorithm, it is also possible to apply reinforcement learning, unsupervised learning, semi-supervised learning, or the like, in addition to supervised learning.
Further, the learning unit 403 may learn the output correction method according to the data sets collected from the plurality of improvement point analysis devices 100.
The learning unit 403 may acquire a data set from a plurality of improvement point analyzers 100 used in the same area. Alternatively, the learning unit 403 may learn the correction method of the analysis result output by using the data set collected from the plurality of improvement point analysis devices 100 that operate independently in different areas. Further, the learning unit 403 can add an improvement point analysis device 100 for collecting a data set on the way. Alternatively, the learning unit 403 can conversely remove any of the improvement location analysis devices 100 from the improvement location analysis device 100 that collects the data set.
Further, the machine learning device 400 that has learned the correction method of the analysis result output for a certain improvement point analysis device 100 is applied to another improvement point analysis device 100, and the analysis result output for the other improvement point analysis device 100. You may relearn and update the correction method of.
Further, as the learning algorithm used in the learning unit 403, deep learning that learns the extraction of the feature amount itself can also be used, and other known methods such as genetic programming, functional logic programming, and support can be used. Machine learning may be performed according to a vector machine or the like.
*** Explanation of the effect of the embodiment ***
As described above, in the present embodiment, the correction method of the analysis result output is acquired by utilizing machine learning. Therefore, according to the present embodiment, even if the analysis target is a large-scale or complicated production system, it is possible to output the improvement points according to the actual state of the production system.

Although the embodiments 1 to 7 have been described above, two or more of these embodiments may be combined and implemented.
Alternatively, one of these embodiments may be partially implemented.
Alternatively, two or more of these embodiments may be partially combined and carried out.
In addition, the configurations and procedures described in these embodiments may be changed as necessary.

*** Supplementary explanation of hardware configuration ***
Finally, a supplementary explanation of the hardware configuration of the improved location analyzer 100 will be given.
The processor 901 shown in FIG. 2 is an IC (Integrated Circuit) that performs processing.
The processor 901 is a CPU (Central Processing Unit), a DSP (Digital Signal Processor), or the like.
The storage device 902 shown in FIG. 2 is a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an HDD (Hard Disk Drive), or the like.
The communication interface 903 shown in FIG. 2 is an electronic circuit that executes data communication processing.
The communication interface 903 is, for example, a communication chip or a NIC (Network Interface Card).

An OS (Operating System) is also stored in the auxiliary storage device 902.
Then, at least a part of the OS is executed by the processor 901.
The processor 901 executes the program 904 while executing at least a part of the OS.
When the processor 901 executes the OS, task management, memory management, file management, communication control, and the like are performed.
Further, at least one of the information, data, signal value, and variable value indicating the processing result of the evaluation unit 102, the improvement point analysis unit 103, and the information collection unit 104 is a register and a cache memory in the storage device 902 and the processor 901. It is stored in at least one of them.
Further, the program 904 may be stored in a portable recording medium such as a magnetic disk, a flexible disk, an optical disk, a compact disc, a Blu-ray (registered trademark) disc, or a DVD. Then, a portable recording medium in which the program 904 is stored may be distributed.

Further, the "section" of the evaluation unit 102, the improvement point analysis unit 103, and the information collection unit 104 may be read as "circuit" or "process" or "procedure" or "processing".
Further, the improved location analysis device 100 may be realized by a processing circuit. The processing circuit is, for example, a logic IC (Integrated Circuit), a GA (Gate Array), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate Array).
In this case, the evaluation unit 102, the improvement location analysis unit 103, and the information collection unit 104 are each realized as a part of the processing circuit.
In this specification, the superordinate concept of the processor and the processing circuit is referred to as "processing circuit Lee".
That is, the processor and the processing circuit are specific examples of the "processing circuit Lee", respectively.

100 improvement location analysis device, 101 information storage unit, 102 evaluation unit, 103 improvement location analysis unit, 104 information collection unit, 105 improvement record storage unit, 200 analysis target, 300 network, 400 machine learning device, 401 data acquisition unit, 402 Teacher data acquisition unit, 403 learning unit, 404 output unit, 405 trained model storage unit, 901 processor, 902 storage device, 903 communication interface, 904 program, 905 bus.

Claims

A designated part that designates an element whose performance should be improved among three or more elements as a designated element,
An extraction unit that extracts two or more elements that have a significant relationship with the designated element from the elements other than the designated element as related elements.
To improve the performance of the designated element from among the two or more related elements by analyzing the influence of the performance of each of the two or more related elements extracted by the extraction unit on the performance of the designated element. An information processing device having an estimation unit that estimates related elements to be improved, which are related elements whose performance should be improved.
The estimation unit
When a plurality of improvement target related elements are estimated, the influence of the performance of each improvement target related element on the performance of other improvement target related elements is analyzed, and the priority is set among the plurality of improvement target related elements. The information processing apparatus according to claim 1.
The designated part is
The improvement target related element estimated by the estimation unit is designated as a new designated element, and the improvement target related element is designated as a new designated element.
The extraction unit
Two or more elements other than the new designated element, which have a significant relationship with the new designated element, are extracted as new related elements.
The estimation unit
The influence of the performance of each of the two or more new related elements extracted by the extraction unit on the performance of the new designated element is analyzed, and the new designation is made from the two or more new related elements. The information processing apparatus according to claim 1, wherein a new related element whose performance should be improved in order to improve the performance of the element is estimated as a new improvement target related element.
The designated part is
Every time a new improvement target related element is estimated by the estimation unit, the estimated new improvement target related element is repeatedly designated as a new designated element.
The extraction unit
Every time a new designated element is designated by the designated unit, two or more elements other than the designated new designated element are repeatedly extracted as new related elements.
The estimation unit
The information processing apparatus according to claim 3, wherein every time two or more new related elements are extracted by the extraction unit, a new improvement target related element is repeatedly estimated.
The estimation unit
An association analysis is performed using the improvement of the performance of the designated element as the conclusion part and the improvement of the performance of each of the two or more related elements as the condition part, and the related element to be improved is estimated. The information processing apparatus according to claim 1.
The estimation unit
In claim 5, when the calculation maintenance condition is not satisfied in any of the plurality of calculation items included in the association analysis, the uncalculated calculation item in the plurality of calculation items is not calculated. The information processing device described.
The information processing device further
Each element has an evaluation unit that evaluates whether or not the performance meets the performance criteria.
The designated part is
The information processing apparatus according to claim 1, wherein an element evaluated by the evaluation unit as not meeting the performance standard is designated as the designated element.
The evaluation unit
The information processing apparatus according to claim 7, wherein it is evaluated whether or not the performance of each element meets the performance standard defined for each element.
The three or more elements constitute a plurality of layers.
The evaluation unit
The information processing apparatus according to claim 7, wherein it is evaluated whether or not the performance of each element meets the performance standard in a time width different for each layer.
The evaluation unit
The information processing apparatus according to claim 7, which outputs an evaluation result each time an evaluation is performed.
The evaluation unit
An improvement target is defined in the improvement target related element estimated by the estimation unit, and when the condition for applying the additional performance standard to the improvement target related element is satisfied, the improvement target is satisfied. The information processing apparatus according to claim 7, wherein the performance of the related element is evaluated as to whether or not the performance of the related element meets the criteria of the additional performance.
The evaluation unit
The information processing apparatus according to claim 7, wherein the evaluation is performed using the performance standard obtained by statistical processing.
The estimation unit
The information processing apparatus according to claim 1, wherein when the relationship between any two or more of the three or more elements is unknown, the relationship between the elements whose relationship is unknown is estimated.
The estimation unit
The information processing apparatus according to claim 5, wherein a calculation using a plurality of calculated values for a plurality of calculated items included in the association analysis is performed, and the calculated value of the calculation using the plurality of calculated values is output.
The estimation unit
The calculated values obtained by the calculation using the plurality of calculated values for the plurality of calculated items included in the association analysis are corrected based on the improvement results for at least one of the two or more related elements, and the corrected values are corrected. The information processing apparatus according to claim 5, which outputs a calculated value.
The estimation unit
The correction method of the calculated value obtained by the calculation using the plurality of calculated values for the plurality of calculated items included in the association analysis is acquired by machine learning, and the acquired correction method is used for the calculation using the plurality of calculated values. The information processing apparatus according to claim 5, which corrects the obtained calculated value and outputs the corrected calculated value.
The computer specifies the element that should improve the performance among the three or more elements as the specified element,
The computer extracts two or more elements having a significant relationship with the designated element from the elements other than the designated element as related elements.
The computer analyzes the influence of the performance of each of the two or more extracted related elements on the performance of the designated element, and among the two or more related elements, in order to improve the performance of the designated element. An information processing method that estimates related elements to be improved, which are related elements that should improve performance.
Designation process that specifies the element that should improve the performance among 3 or more elements as the specified element,
Extraction processing that extracts two or more elements that have a significant relationship with the designated element from the elements other than the designated element as related elements.
To improve the performance of the designated element from among the two or more related elements by analyzing the influence of the performance of each of the two or more related elements extracted by the extraction process on the performance of the designated element. An information processing program that causes a computer to perform estimation processing that estimates related elements to be improved, which are related elements that should improve performance.