JP2022086320A - Monitoring method for production process - Google Patents

Abstract

To provide a monitoring method for a production process by which the quality of a production process in operation can be accurately predicted.SOLUTION: A monitoring method for a production process includes the steps of: collecting performance status data and performance quality data of a plurality of operated lots in a previously performed process; setting virtual status data of a plurality of virtual lots corresponding to different states in a virtual process, and collecting virtual quality data of the virtual lots; dividing the operated lots and the virtual lots into a plurality of groups on multi-dimensional coordinates in which a plurality of principal component scores derived from the status data is set on each of coordinate axes; and determining whether a monitoring process belongs to any of the groups or does not belong to any groups, based on the status data indicating a status of the monitoring process.SELECTED DRAWING: Figure 6

Description

The present invention relates to a method for monitoring a process for manufacturing a product (product) or a process for providing a service (hereinafter, collectively referred to as a "production process").

In Patent Document 1, principal component analysis and cluster analysis are applied to quality data and state data related to the manufacturing process, lots of the manufacturing process are divided into a plurality of groups, the quality of each group is judged, and judgment criteria are generated in advance. However, a method for monitoring a production process for determining the quality of an operating manufacturing process based on whether or not the principal component score derived from the operating manufacturing process meets the determination criteria is disclosed (for example, Patent Document 1). reference).

Japanese Unexamined Patent Publication No. 2016-167205

However, according to the method described in Patent Document 1, a criterion is generated based on a manufacturing process that has been operated in the past. Therefore, when the manufacturing process in operation hits a manufacturing state that has never been experienced in the past, it is in operation. There was a problem that it was not possible to flexibly judge the quality of the manufacturing process.

Therefore, a technical problem to be solved in order to accurately predict the quality of the production process during operation arises, and an object of the present invention is to solve this problem.

In order to achieve the above object, the production process monitoring method according to the present invention is a production process monitoring method for producing a product or service, and is a plurality of operations in an operated process which is a production process implemented in the past. The step of collecting the actual status data, which is the status data indicating the status of the completed lot, and the actual quality data, which is the quality data indicating the quality of the product or service, and the different status in the virtual process imitating the production process are supported. A step of setting virtual state data which is state data indicating the state of a plurality of virtual lots and collecting virtual quality data which is quality data indicating the quality of the product or service, and a plurality of steps derived from the state data. Based on the step of dividing the operated lot and the virtual lot into a plurality of groups on the multidimensional coordinates in which the principal component score is set for each coordinate axis, and the state data indicating the state of the monitoring process which is the production process to be monitored. The monitoring process includes a step of determining which of the groups belongs to or does not belong to any of the groups.

According to this configuration, the virtual state data of the virtual lot is set to be different from the actual state data of the operated lot, and the virtual quality data corresponding to the virtual state data of the virtual lot is obtained by a virtual process such as an experiment or a simple simulation. By being collected, the monitoring in operation is based on the determination of whether the operating monitoring process belongs to any group that divides the operating lot and the virtual lots set to complement it. The quality of the process can be predicted with high accuracy.

Further, the production process monitoring method according to the present invention preferably further includes a step of predicting quality data indicating the quality of the product or service in the monitoring process from the quality data of the group to which the monitoring process belongs.

According to this configuration, the quality data of the product or service produced by the monitoring process can be predicted based on the quality data of the experienced lot or the virtual lot belonging to the group determined to belong to the monitoring process.

Further, in order to achieve the above object, the production process monitoring method according to the present invention is a production process monitoring method for producing a product or service, and corresponds to different states in a virtual process imitating the production process. A step of setting virtual state data which is state data indicating the state of a plurality of virtual lots and collecting virtual quality data which is quality data indicating the quality of the product or service, and a plurality of derived from the state data. Monitoring is based on the step of dividing the virtual lot into a plurality of groups and the state data indicating the state of the monitoring process, which is the production process to be monitored, on the multidimensional coordinates in which the principal component score of is set to each coordinate axis. It comprises a step of determining which of the above groups the process belongs to or does not belong to.

According to this configuration, virtual state data is set so as to be different from each other for a plurality of virtual lots, and virtual quality data corresponding to the virtual state data of the virtual lot is collected by a virtual process such as an experiment or a simple simulation. This makes it possible to accurately determine the quality of the operating monitoring process based on the determination of whether or not the operating monitoring process belongs to any group that divides the virtual lot based on the virtual state data and the virtual quality data. Can be predicted.

In addition, the production process monitoring method according to the present invention provides actual status data, which is status data indicating the status of a plurality of operated lots in an operated process, which is a production process executed in the past, and the quality of the product or service. It is preferable to further include a step of collecting actual quality data, which is the quality data to be shown, and to divide the operated lot and the virtual lot into a plurality of groups on the multidimensional coordinates.

According to this configuration, in addition to the virtual state data and virtual quality data of the virtual lot, the actual state data and the actual quality data of the operated lot are taken into consideration to accurately predict the quality of the monitoring process during operation. Can be done.

The present invention can accurately predict the quality of the monitoring process during operation.

The schematic diagram which shows the structure of the distillation column to which the monitoring method of the production process which concerns on one Embodiment of this invention is applied. A table showing status and quality data for operational and virtual lots. A table showing the amount of information and groups of the main components for each operated lot. A graph plotting the principal component scores for each operated lot. A table showing the amount of information and quality data of the main components for each virtual lot. A graph plotting the principal component scores for each virtual lot. A graph plotting the principal component scores of operated lots and virtual lots.

An embodiment of the present invention will be described with reference to the drawings. In the following, when the number, numerical value, quantity, range, etc. of the components are referred to, the number is limited to the specific number unless it is explicitly stated or the principle is clearly limited to the specific number. It is not a thing, and it may be more than or less than a specific number.

The analysis method according to this embodiment is applied to the production process. Production processes include processes that consist only of mechanical equipment and all processes are automated, processes that include manual work processes by workers, and manufacturing processes that are automated by mechanical equipment and manual work by workers. A process including a process is included. Further, the production process is not limited to the process of producing a product, and includes services such as cleaning of waste liquid and analysis of clinical trial results in drug development.

Hereinafter, the case where this analysis method is applied to the purification of NMP (N-methyl-2-pyrrolidone), which is an example of the production process, will be described as an example. Needless to say, the production process to which the present invention is applied includes other production lines and processes for providing services.

FIG. 1 is a schematic diagram showing a distillation column 1 for purifying NMP. The distillation column 1 purifies high-purity NMP from, for example, a raw material (NMP before purification) recovered from a Li-ion secondary battery manufacturing process or the like. Pre-purification NMP mainly contains NMP, H2O, NMP precursors, safety-related substances and impurities. The ratio of various products contained in the pre-purified NMP varies depending on the Li-ion secondary battery manufacturing process and is not always uniform.

The distillation column 1 is divided into a recovery unit 2 provided at the lower part and a concentration unit 3 provided at the upper part, and raw materials are supplied from the boundary between the recovery unit 2 and the concentration unit 3.

The raw material charged into the distillation column 1 is heated by the steam supplied by the heating device (riboira) 4 from the bottom of the recovery unit 2, and the low boiling point components evaporate first to reach the top of the distillation column 1. Ascend towards.

A shelf-like structure is installed inside the distillation column 1, and the vapor rising from the lower part and the liquid descending from the upper part come into contact with each other. Due to the contact between the vapor and the liquid (gas-liquid contact), the heat required for the liquid to evaporate (latent heat of vaporization) is exchanged between the vapor and the liquid. At this time, the generated vapor contains a large amount of components having a boiling point lower than that of the liquid, while the liquid contains a large amount of components having a boiling point higher than that of the liquid.

Further, since gas-liquid contact is performed in the distillation column 1, the steam is returned to the liquid (reflux) again by using the cooling device (condenser) 5 at the top of the column.

In this way, in the distillation column 1, in order to carry out gas-liquid contact in the entire column, cooling at the top of the column and heating at the bottom of the column are simultaneously performed to reflux, and at the top of the distillation column 1, a component having a low boiling point is contained. At the bottom of the distillation column 1, components having a high boiling point are separated and recovered.

The distillation column 1 is provided with a sensor (not shown) for measuring various values. The measurement targets of the sensor are the composition of the raw material, the input amount of the raw material, the temperature inside the column, the set temperature of the heating device 4, the amount of recirculation of the liquid recirculated into the column via the cooling device 5, and the like.

The various configurations constituting the distillation column 1 are controlled by the control device 10. The control device 10 includes, for example, a device control unit 11 having a CPU, a memory, or the like, an input / output unit 12 for controlling input / output of data, a display unit 13 for displaying data, and a storage unit 14 for storing data. I have. The function of the control device 10 may be realized by controlling using software, or may be realized by operating using hardware.

The control device 10 performs the processing described later based on the state data indicating the operating state of the distillation column 1 measured by the sensor and the quality data indicating the quality information of the NMP after purification. The state data includes manufacturing data indicating the purification conditions of the production process (operating conditions of various devices constituting the distillation column 1 and the like) and material data indicating the composition of the pre-purification NMP.

The device control unit 11 determines the control unit 11a that controls each device, the analysis unit 11b that performs the processing described later for the state data, the verification unit 11c that verifies the virtual lot described later, and the monitoring process described later. The function is divided into the determination unit 11d and the determination unit 11d.

The input / output unit 12 includes, for example, a keyboard, a mouse, a communication control device, a printing device, and the like. The display unit 13 has, for example, a display. Various data and the like used in various processes are stored in the storage unit 14.

Next, the procedure of the monitoring method of the production process according to the present embodiment will be described.

[Operated lot analysis]
First, the steps for analyzing the state and quality of a plurality of operated lots in the production process will be specifically described.

The analysis unit 11b collects the state data (actual state data) measured by the sensor and the quality data of the refined NMP (actual quality data) for each operated lot for the operated production process (step S1).

The state data and quality data collected in step S1 are stored in the storage unit 14. FIG. 2 is a table containing the status data and quality data of the operated lots, and the lots belonging to the type “experienced” in the table 2 correspond to the operated lots, and the “operated lots” in the table 2 are related to the operated lots. The "raw material composition" column is state data showing the composition of the pre-purified NMP charged into the distillation column 1 in each operated lot, and the "determination" column for the operated lot is the purified NMP in the operated lot. It is quality data indicating quality, and "○" in the table means that the NMP has cleared the shipping standard after purification and no safety problem has occurred.

Next, the state data and quality data collected in step S1 are standardized and converted into an intermediate function (step S2).

The state data standardization process performed in step S2 is known, and specifically, the analysis unit 11b performs the state data standardization process based on the mathematical formula 1.

Next, the principal component load and the principal component score are obtained based on the intermediate variables obtained in step S2 (step S3).

Specifically, first, the correlation coefficient matrix in the intermediate variable is created, and the eigenvalues and eigenvectors of the correlation coefficient matrix are derived. In the correlation coefficient matrix, when the intermediate variables are x1, x2, x3 ..., The first principal component PC1 is expressed as shown by Equation 2. Further, the Nth principal component PCn is expressed as shown by the mathematical formula 3. Then, the correlation coefficient matrix is formed by using the coefficients a11, a12, a13 ... As the elements in the first row and the coefficients an1, an2, an3 ... As the elements in the nth row.

Next, the principal component score is obtained from the eigenvector of the correlation coefficient matrix. In addition, the contribution rate of each principal component is obtained from the eigenvalues of the correlation coefficient matrix. The contribution rate of the principal component is obtained by dividing the eigenvalues by the sum of the eigenvalues. Here, the first principal component, the second principal component, and the Nth principal component are determined from the one having the larger eigenvalue.

Specifically, the analysis unit 11b determines the values of the first principal component PC1, the second principal component PC2, and so on, based on the intermediate variables x1, x2, x3 of each lot and each coefficient of the correlation coefficient matrix. , The principal component score is calculated. FIG. 3 is a table showing the amount of information of the main component for each operated lot.

Next, the analysis unit 11b applies cluster analysis to the principal component scores shown in FIG. 3 to divide each lot into a plurality of groups (step S4).

"Cluster analysis" is a method of classifying analysis target data (clusters) into a plurality of groups focusing on similarity, and hierarchical clustering, classification optimization clustering, and the like are known. The "similarity" that the cluster analysis pays attention to in this embodiment means the distance between the principal component scores of each lot.

As a method of cluster analysis, for example, aggregated hierarchical clustering, which is one of hierarchical clustering, is known. Further, as a method for calculating the distance between clusters, Ward's method or the like that can obtain a stable solution is used. The "Ward's method" is to select the cluster that minimizes the increase in the sum of squared deviations when the two clusters are merged. For example, when clusters A and B are merged to generate cluster C, the sums of deviation squares Sa, Sb, and Sc in the clusters A, B, and C are expressed as formulas 4 to 6, respectively.

According to Equations 4 to 6, the deviation sum of squares Sc in the cluster C is as follows.

ΔSab in Equation 7 means that it is an increment of the sum of squared deviations when clusters A and B are merged to form cluster C. Therefore, clustering is advanced by selecting and merging clusters so that ΔSab is minimized at each merging stage.

In this embodiment, as shown in FIG. 4, the operated lots are divided into three groups 1 to 3 in the three-dimensional space of the first to third eigenvectors (EV1 to EV3 in FIG. 4). FIG. 4 is a graph obtained by plotting the composite vector of EV1 to EV3 in the operated lot on the above-mentioned three-dimensional space and projecting it on the EV1-EV3 plane (the plane in which EV1 is set on the horizontal axis and EV3 is set on the vertical axis). Is. Further, in FIG. 4, the operated lots constituting the same group are plotted with the same reference numerals. Further, the right column "group" in the table of FIG. 3 indicates the group to which each operated lot belongs. The number of eigenvectors is not limited to three, and may be two or less or four or more. Further, the number of groups is not limited to three, and may be two or less or four or more.

Next, the superiority or inferiority of the quality data between the groups is determined based on the quality data of the operated lots belonging to each group (step S5). Specifically, the control device 10 calls an intermediate variable obtained from quality data (purity of NMP after purification, content of impurities, etc.) for each lot, and determines the superiority or inferiority of the quality data between groups. The superiority and inferiority of the quality of each group was in the order of group 3, group 2, and group 1, and group 3 was the most superior.

The superiority or inferiority of the quality data is preferably based on the average value in a plurality of lots (lot groups) constituting the same group. As a result, the variation in the quality data of a plurality of lots within the group is leveled, and the tendency of the quality data between the groups can be grasped from a broad perspective.

[Virtual lot verification]
Next, the steps for verifying the quality in a lot (virtual lot) assuming an inexperienced state of the production process will be specifically described.

The verification unit 11c is based on the state data (virtual state data) and quality data (virtual quality data) for each of a plurality of virtual lots in the same manner as the analysis of the already operated production process (steps S1 to S5) described above. Divide the virtual lot into multiple groups.

Specifically, first, virtual state data set for each of a plurality of virtual lots in a virtual process imitating a production process is stored in the storage unit 14 (step S6).

Here, the "virtual process" is not a production process in which the distillation column 1 is actually operated, but what kind of virtual quality is assumed when the distillation column 1 is operated with arbitrarily set virtual state data. It is set to imitate a production process that has already been operated in order to verify that data can be obtained.

Further, the "virtual state data" assumes an inexperienced state of the production process, that is, the operating conditions of the distillation column 1 and the composition of the raw material are arbitrarily set so as to be in a state different from the above-mentioned operated lot. Means the state data that is changed and set.

In the present embodiment, only the composition of the raw material charged into the distillation column 1 is randomly changed so that the "virtual state data" does not match the actual state data of the operated lot, and other purification conditions are described above. The status data of the virtual lot matched with the production process was used. Lots belonging to the type "inexperienced" in Table 2 correspond to virtual lots, and the column of "raw material composition" for virtual lots in Table 2 is virtual state data showing the composition of raw materials in each virtual lot.

Next, the virtual quality data for each virtual lot acquired based on the virtual state data is stored in the storage unit 14 (step S7).

The "virtual quality data" means the quality data of the NMP after purification and the presence or absence of a safety problem when the distillation column 1 purifies the raw material with the virtual state data. In the present embodiment, the "virtual quality data" is the quality data (whether there is a quality or safety problem of the NMP after purification) acquired by an experiment reproducing the production process or a simple simulation based on the virtual state data. did.

The column of "determination" regarding the virtual lot in the table of FIG. 2 is the virtual quality data in each virtual lot. In addition, "Weeping" in the table of FIG. 2 indicates that the raw material in the upper stage drips excessively in the distillation column 1 and the degree of purification deteriorates. “Flooding” indicates that the steam increased excessively in the distillation column 1 and the raw material did not flow down and the degree of purification deteriorated. "Safety problem" means that the raw material concentrated on the bottom of the tower is concentrated to a predetermined concentration or more, which is an explosive substance related to safety.

Next, in the same manner as in steps S2 and 3, the analysis unit 11b standardizes the virtual state data and virtual quality data collected in step S6, converts them into intermediate functions, and then uses the main component load and the main component load based on the intermediate variables. The main component score is obtained (step S8). FIG. 5 is a table showing the amount of information of the main component and the virtual quality data for each virtual lot.

Next, the verification unit 11c divides each virtual lot into four groups 4 to 7 based on the virtual quality data (step S9). FIG. 6 is a graph obtained by plotting a composite vector of EV1 to EV3 in a virtual lot on the above-mentioned three-dimensional space and projecting it on an EV1-EV3 plane (a plane in which EV1 is set on the horizontal axis and EV3 is set on the vertical axis). be.

Group 4 in FIG. 6 is a group to which virtual lots having no problem in post-purification NMP belong, and group 5 is a group to which virtual lots having problems in quality of post-purification NMP due to the occurrence of Weeping belong. Group 6 is a group to which a virtual lot having a problem in the quality of NMP after purification due to the occurrence of Flood belongs, and group 7 is a group to which a virtual lot having a safety problem belongs. It should be noted that FIG. 7 is an enlargement of a part of the graph in which FIGS. 4 and 6 are superimposed, and the group 4 and the groups 5 to 7 are shown separately.

[Monitoring process prediction]

Next, the steps for predicting the quality of the production process (monitoring process) to be monitored will be specifically described.

First, the state data of the monitoring process in operation is collected (step S10). The state data of the monitoring process is measured by various sensors and stored in the storage unit 14.

Next, in the determination unit 11d, the status data of the monitoring process measured in step S10 belongs to either groups 1 to 3 related to the operated lot classified in step S4 or groups 4 to 7 related to the virtual lot classified in step S9. (Step S11).

Specifically, the analysis unit 11b calls the state data of the monitoring process stored in the storage unit 14, and derives the principal component load amount and the principal component score in the same manner as in steps S2 and S3.

Then, the determination unit 11d belongs to any of the groups 1 to 3 of the operated lots classified in step S4 or the groups 4 to 7 of the virtual lots classified in step S9 for the principal component score derived by the analysis unit 11b. Or determine if it does not belong to any group.

Next, the procedure for determining whether the principal component score according to the status data of the monitoring process belongs to the group 1 to 3 of the operated lot or the group 4 to 7 of the virtual lot is specifically described. explain.

First, the principal component scores of the operated arbitrary lots in the three-dimensional space from the first to third eigenvectors (EV1 to EV3) are set to EV1, EV2, and EV3, and the principal component scores according to the state data of the monitoring process are set to X1. When X2 and X3 are used, the closest synthetic vector, the operated lot or the virtual lot, is specified. The distance D between the synthetic vector (X1, X2, X3) of the monitoring process in the three-dimensional space of EV1 to 3 and the synthetic vector (EV1, EV2, EV3) of the operated lot or the virtual lot is calculated by the formula 8. To.

Then, the group (recent group) to which the lot with the shortest distance D (recent lot) belongs is determined as the group to which the monitoring process belongs.

In this way, the virtual state data of the virtual lot is set differently from the actual state data of the operated lot, and the virtual quality data corresponding to the virtual state data of the virtual lot is collected by a virtual process such as an experiment or a simple simulation. By doing so, it is predicted that the quality of the monitoring process in operation (for example, the monitoring process will proceed in the same way as the past operated lots) based on the operated lot and the virtual lot set to complement it. Or the monitoring process deviates from the operated lot, but proceeds in the same way as the virtual lot for which the virtual quality data is grasped in advance). The procedure for determining whether the principal component score according to the status data of the monitoring process belongs to the group 1 to 3 of the operated lot or the group 4 to 7 of the virtual lot is described above. Not limited.

Next, the quality data of the monitoring process is predicted based on the quality data of the group to which the monitoring process belongs (step S12).

If the principal component score according to the status data of the monitoring process belongs to any of the groups 1 to 3 of the operated lots classified in step S5, the monitoring process is based on the actual quality data of the group to which the main component score belongs. The quality data of the products produced in Japan can be accurately predicted from the results of past production processes.

On the other hand, if the principal component score according to the status data of the monitoring process belongs to any of the groups 4 to 7 of the virtual lot classified in step S9, the monitoring process is based on the quality data of the group to which the main component score belongs. The quality data of the products produced in Japan can be predicted without preparing an advanced simulation model.

Further, when it is determined that the monitoring process belongs to any of the groups 4 to 7, the control device 10 determines the quality data of the monitoring process according to the virtual quality data of the virtual lots belonging to the groups 4 to 7. In order to stabilize the above, a predetermined guidance may be displayed on the display unit 13.

As such guidance, for example, when the monitoring process belongs to group 4, since the virtual quality data is good, it is presumed that the quality data of the monitoring process is also good. be.

In addition, if the monitoring process belongs to group 5, "Weeping" may occur, so it is conceivable to display guidance to increase the amount of recirculation.

In addition, if the monitoring process belongs to Group 6, "Flooding" may occur, so it is conceivable to display guidance to reduce the amount of raw materials input.

Furthermore, if the monitoring process belongs to Group 7, safety-related substances may be concentrated at the bottom of the tower, so it is conceivable to display guidance to increase the amount of high-concentration components extracted from the bottom of the tower. Be done.

In this way, even if the monitoring process progresses in an inexperienced state, by providing guidance on the factors that deviate and how to deal with it, the operator of the distillation column 1 can proceed with the operation. A sense of security can be given.

Further, by displaying the graph shown in FIG. 7 on which the principal component scores of the monitoring process are superimposed on the display unit 13, the user can visually recognize the quality of the NMP after purification.

On the other hand, because the distance D calculated by the formula 8 is significantly far from the size of each group 1 to 7, the main component score according to the state data of the monitoring process is the operated lot classified in step S4. If it is determined that the data does not belong to any of the groups 1 to 3 of the above or the groups 4 to 7 of the virtual lots classified in step S9, the monitoring process may be different from either the operated lot or the virtual lot. High sex. In this case, the control device 10 may display a guidance to call attention to the display unit 13.

Further, in the present embodiment, the case where the quality data of the monitoring process is predicted based on the state data and quality data of the experienced lot and the state data and quality data of the virtual lot has been described as an example, but a plurality of virtual lots have been described. The quality and quality of the monitoring process may be predicted based on the determination of whether or not the data belongs to any of a plurality of groups classified based on the virtual state data and the virtual quality data.

It should be noted that the present invention can be modified in various ways as long as it does not deviate from the spirit of the present invention, and it is natural that the present invention extends to the modified ones.

1: Distillation column 2: Recovery unit 3: Concentration unit 4: Heating device 5: Cooling device 10: Control device 11: Device control unit 11a: Control unit 11b: Analysis unit 11c: Verification unit 11d: Judgment unit 12: Input / output unit 13: Display unit 14: Storage unit

Claims (4)

A method of monitoring the production process that produces a product or service.
A step of collecting actual status data, which is status data indicating the status of a plurality of operated lots in an operated process, which is a production process executed in the past, and actual quality data, which is quality data indicating the quality of the product or service. ,
Virtual quality data, which is quality data indicating the quality of the product or service, is set while setting virtual state data indicating the states of a plurality of virtual lots corresponding to different states in the virtual process imitating the production process. And the steps to collect
A step of dividing the operated lot and the virtual lot into a plurality of groups on multidimensional coordinates in which a plurality of principal component scores derived from the state data are set on each coordinate axis.
A step of determining whether the monitoring process belongs to any of the groups or not based on the state data indicating the state of the monitoring process which is the production process to be monitored, and
A method of monitoring a production process, characterized by including. The monitoring method for a production process according to claim 1, further comprising a step of predicting quality data indicating the quality of the product or service in the monitoring process from the quality data of the group to which the monitoring process belongs. A method of monitoring the production process that produces a product or service.
Virtual quality data, which is quality data indicating the quality of the product or service, is set while setting virtual state data indicating the states of a plurality of virtual lots corresponding to different states in the virtual process imitating the production process. And the steps to collect
A step of dividing the virtual lot into a plurality of groups on multidimensional coordinates in which a plurality of principal component scores derived from the state data are set on each coordinate axis.
A step of determining whether the monitoring process belongs to any of the groups or not based on the state data indicating the state of the monitoring process which is the production process to be monitored, and
A method of monitoring a production process, characterized by including. A step of collecting actual status data, which is status data indicating the status of a plurality of operated lots in an operated process, which is a production process executed in the past, and actual quality data, which is quality data indicating the quality of the product or service. Including more
The monitoring method for a production process according to claim 3, wherein the operated lot and the virtual lot are divided into a plurality of groups on the multidimensional coordinates.

Images