JP7042189B2 - Quality evaluation system - Google Patents

Description

The present invention relates to a quality evaluation system, a quality evaluation method, and a computer program.

In the manufacturing industry, it is desired to detect a sign of a major damage or defect before it occurs and take measures in advance. Patent Document 1 describes that a production line monitoring device capable of identifying the cause of a production defect with high accuracy and reducing the amount of analysis data and the amount of calculation to perform real-time processing is provided. Patent Document 2 discloses a method and an apparatus for inspecting production quality on a production line for tobacco products.

International Publication No. 2014/049872 Japanese Unexamined Patent Publication No. 2006-262900

In the conventional technology, when a product is produced through a plurality of processing processes, a sign that a defect occurs due to a single factor or a sign that a defect occurs due to a plurality of factors can be detected at an early stage and with high accuracy at each stage of the process. Can not do it.

In the prior art, the quality of the product is inspected when the final process is completed, the quality of the product is judged, and the transition of data fluctuation in a single series is evaluated. Therefore, it is difficult to identify the process that causes the defect at an early stage.

Further, in the prior art, in each process, the product is evaluated based on a single measurement axis in the target process. Therefore, it is difficult to detect a defect caused by a combined factor of the processing performed in the target process and the processing performed on the product in each process prior to the target process.
That is, with the prior art, it is difficult to detect at an early stage a sign that a defect occurs due to a single factor or a plurality of factors.

The present invention has been made in view of the above problems, and is a quality evaluation system, a quality evaluation method, which enables evaluation of product quality using data of predetermined sensors up to the inspection stage at each inspection stage. And provide computer programs.

The quality evaluation system according to one aspect of the present invention is a quality evaluation system that evaluates the quality of a product produced through a plurality of processes, and includes data from each sensor that measures the processing state of the product at each inspection stage. The first evaluation model showing the range of data of each sensor when the product is judged to be non-defective based on the data from the inspection function that finally inspects the product that has completed all the inspection stages, and the first evaluation model. An evaluation model management function that creates a second evaluation model based on one evaluation model, and a stage-by-stage evaluation function that evaluates the data of a predetermined sensor up to the inspection stage based on the second evaluation model at each inspection stage. To prepare for.

According to the present invention, it is possible to detect at an early stage a sign that a defect occurs due to a single factor or a plurality of factors.

It is a block diagram of the quality evaluation system which concerns on 1st Example. It is a sequence diagram which creates an evaluation model. It is a sequence diagram that creates and distributes an evaluation model for each stage. It is a sequence diagram to evaluate at each processing stage. It is an evaluation model diagram in the case of evaluating a product in advance based on the data of three sensors. It is an evaluation model diagram in the case of evaluating a product in advance based on the data of two sensors. It is an evaluation model diagram in the case of evaluating a product in advance based on the data of one sensor. It is a flowchart of the process which manages an evaluation model. It is a flowchart which shows the evaluation process in the 1st stage. It is a flowchart which shows the evaluation process in the Nth stage. It is a management table of sensor data used to create an evaluation model. It is a management table for evaluation of sensor data. It is a block diagram of the quality evaluation system according to the 2nd Example. It is a sequence diagram which creates an evaluation model. It is a sequence diagram which concerns on 2nd Embodiment and evaluates at each stage. It is a block diagram of the quality evaluation system according to the 3rd Embodiment. It is an evaluation sequence diagram. It is a flowchart which shows the quality evaluation management of the evaluation management machine which concerns on 3rd Example. It is a flowchart which shows the evaluation process in the Nth stage. It is a hardware configuration diagram of the evaluation model management machine. It is a figure which shows the storage contents of the main memory. It is a figure which shows the content stored in the memory of a grade evaluation machine. It is the flowchart of the evaluation model management process which concerns on 4th Embodiment. It is a block diagram of the quality evaluation system which concerns on 5th Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. The quality evaluation system according to the present embodiment calculates a range of values in which the sensor data in each process is a good product for a non-defective product (product) completed through a plurality of processes, and creates a first evaluation model. Further, based on the first evaluation model, a second evaluation model used for product evaluation in each process is created. This makes it possible to evaluate the product in advance in each process before the product is completed. Therefore, it is possible to detect and deal with the process causing the defect at an early stage, and it is possible to improve the production efficiency.

In the following description, the case where the inspection stage and the work process have a one-to-one correspondence is mainly described as an example, but the present invention is not limited to this, and the inspection process and the work process are many-to-one or many. This embodiment is also applicable to the case of dealing with many-to-many. In the work process, for example, mechanical work such as cutting, bending, welding, drilling, painting, chemical work such as vulcanization, molding, distillation, mixing, and physical work such as drying, heating, and cooling. Of the assembly work such as mounting the board on the housing, incorporating the device into the control panel, connecting the cable to the board or device, and electrical work such as soldering, initial value registration, correction, and program installation. At least one task is included.

In this embodiment, since the case where the inspection stage and the work process have a one-to-one correspondence is mainly described, the process may be referred to as a stage.

The first embodiment will be described with reference to FIGS. 1 to 12. However, the present invention is not limited to the description of the embodiments shown below. A person skilled in the art may change the configuration without departing from the idea or purpose of the present invention.

The position, size, shape, range, etc. of each configuration in the drawings, etc. are described for facilitating the understanding of the invention, and may not represent the actual position, size, shape, range, etc. be. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings and the like.

In the following, a plurality of homozygous configurations such as the grade evaluation machines "11-1", "11-2", and "11-N" are displayed with branch numbers. Unless otherwise specified, the subscripts are omitted as in the grade evaluation machine 11.

In this embodiment, each of the cases where the finished product 20 is a non-defective product is measured by measuring the range of values that are non-defective products for a plurality of process processes applied to the non-defective product (produced product). A first evaluation model showing a range of values of the sensor 31 is created. Further, in this embodiment, mapping data is created for each process for the dimension having a plurality of data axes measured by each sensor 31 by each process 21.

In this embodiment, by using a combination of a plurality of measurement data (also referred to as sensor data) measured up to that process and a second evaluation model for each process, it is within the range of values necessary for producing a good product. Judge whether or not. Therefore, in this embodiment, the data range (second evaluation model and allowable range) required in each process to become a non-defective product is calculated from the data measured for the finished product 20 of a non-defective product, and in each process 21. The product can be evaluated in advance.

Preliminary evaluation in each step 21 includes individual evaluation and combined evaluation, as will be described later. The independent evaluation is an evaluation based only on the data of the sensor 31 associated with the target process 21. In the single evaluation, it is determined whether or not the data of the sensor 31 associated with the target process falls within a predetermined allowable range. The combination evaluation is an evaluation based on the combination of data of each sensor 31 associated with each process up to the target process. Each sensor up to the target process may be referred to as a predetermined sensor. In the combination evaluation, it is determined whether or not a combination of data of a predetermined sensor exists in the second evaluation model.

In this embodiment, a case will be described in which the data measured in each evaluation stage is notified to the evaluation machine 11 and the model management machine 10 in each subsequent stage, and the evaluation model is created and the measurement data is evaluated. ..

The configuration of the quality evaluation system 1 according to the present embodiment and the operation of the components 10 and 11 constituting the quality evaluation system 1 will be described with reference to FIGS. 1 to 12.

FIG. 1 shows the configuration of the quality evaluation system 1. In the production line targeted by the quality evaluation system 1, the material 4 undergoes a plurality of processes (first process 21-1, second process 21-2 to Nth process 21-N), and the finished product 20 is manufactured. ..

A sensor 31 is associated with each step 21. That is, the first sensor 31-1 is in the first step 21-1, the second sensor 31-2 is in the second step 21-2, and the N sensor 31-N is in the Nth step 21-N. It is associated. The state of the finished product 20 is finally inspected by the inspection machine 30.

The sensor corresponding only to the step 21-1 is the sensor 31-1. The sensor corresponding only to the step 21-2 is the sensor 31-2. The sensor corresponding only to the process 21-N is the sensor 31-N.

On the other hand, the sensor corresponding to the process 21-1 is only the sensor 31-1. This is because step 21-1 is the first step, and there is no step before that. The sensors corresponding to the steps 21-2 are the sensor 31-1 and the sensor 31-2. The sensors corresponding to the steps 21-3 (not shown) are the sensor 31-1, the sensor 31-2, and the sensor 31-3 (not shown). The sensors corresponding to steps 21-N are sensors 31-1 and 31-2 ,. .. .. , 31-N.

In the following description, "up to the process" means each process (including the target process) from the first process to the target process. For example, the "steps up to the second step 21-2" mean the first step 21-1 and the second step 21-2.

Examples of the sensor 31 include a temperature sensor, a pressure sensor, a flow rate sensor, a current sensor, a voltage sensor, a frequency sensor, a color sensor, a thickness sensor, a magnetic sensor, a continuity sensor, an image processing sensor and the like.

The quality evaluation system 1 includes, for example, one evaluation model management machine 10 and a plurality of stage evaluation machines 11. The quality evaluation system 1 may be configured by one computer or may be configured by linking a plurality of computers. That is, each of the evaluation model management machine 10 and each stage evaluation machine 11 may be configured from a separate computer, or the function of the evaluation model management machine 10 and the function of each stage evaluation machine 11 are provided in one computer. You may.

The user interface device (not shown) that exchanges information with the worker in each process or the user who uses the quality evaluation system 1 is a device separate from the computer that constitutes all or part of the quality evaluation system 1. Can be provided as. The user interface device may be a device that only provides information to users and the like.

The evaluation model management machine 10 is an example of the “evaluation model management function”. The evaluation model management machine 10 manages a model for evaluating whether or not the process processing necessary for the finished product 20 to become a non-defective product has been executed for the processes up to each process. Although the details will be described later, the evaluation model management machine 10 creates a basic evaluation model MB as a first evaluation model. Further, the evaluation model management machine 10 includes models MS1, MS2, and so on, which are used in each stage evaluation machine 11 from the basic evaluation model MB. .. .. , MSN is created as the second evaluation model. Hereinafter, unless otherwise specified, it is abbreviated as evaluation model MS. The evaluation model MS is used in the stage evaluation machine 11 for each inspection stage (or step by process). The evaluation model management machine 10 transmits the evaluation model MS for each stage created from the basic evaluation model MB to each stage evaluation machine 11 for setting.

The stage evaluation machine 11 is an example of the “stage-by-stage evaluation function”. The stage evaluation machine 11 determines whether the process processing up to each process satisfies the necessary conditions for making the finished product 20 a good product. That is, the stage evaluation machine 11 evaluates whether the product (work in process) processed in the target process may be completed as a good product in the future before completion. The evaluation before completion can be paraphrased as, for example, a preliminary judgment, a preliminary inspection, and the like.

The evaluation by the stage evaluation machine 11 includes an individual evaluation and a combination evaluation. In the independent evaluation, it is determined whether or not the product has a possibility of becoming a non-defective product based on the data of only the sensor 31 associated with the target process 21. The stage evaluation machine 11 determines that if the data of the sensor 31 corresponding to the target process 21 is within a predetermined allowable range, it is highly likely that the product will be completed as a non-defective product, and in other cases, it will be a defective product. It is determined that there is a possibility of becoming.

In the combination evaluation, the product (work in process) processed in the target process is based on each data from the sensor 31 associated with each process including the target process from the first process 21-1. Evaluate whether or not it may be completed as a good product in the future before completion. Here, the sensor associated with each step including the target step from the first step 21-1 is referred to as a predetermined sensor. In the combination evaluation, it is determined whether or not the data of the predetermined sensor exists in the stage-by-stage evaluation model MS set in the stage evaluation machine 11 corresponding to the target process.

An example of specific processing in each step 21 will be described. The material acquisition treatment, heat treatment, etc. described below are examples for explanation.

The first sensor 31-1 measures the amount of the material acquisition process executed in the first step 21-1, which is the first step, and notifies the evaluation model management machine 10 of the measured amount. When the stage evaluation machine 11-1 evaluates the process state, the first sensor 31-1 uses the measured amount as the first stage evaluation machine 11-1 and each stage evaluation machine 11- corresponding to the subsequent process. Notify 2 to 11-N respectively.

The second sensor 31-2 measures the temperature state of the heating of the material 4 executed in the second step 21-2 and notifies the evaluation model management machine 10. When the stage evaluation machine 11-2 evaluates the process state, the second sensor 31-2 uses the measured temperature value as the second stage evaluation machine 11-2 and each stage evaluation machine 11 corresponding to the subsequent process. Notify -3 (not shown) to 11-N respectively.

The Nth sensor 31-N in the final stage measures the length after cutting the unnecessary portion of the cutting process executed in the Nth step 21-N, and notifies the evaluation model management machine 10. When the final stage evaluation machine 11-N evaluates the process state, the Nth sensor 31-N notifies the Nth stage evaluation machine 11-N of the measured length value.

The inspection machine 30 inspects the finished product 20 that has completed the final process, the Nth process 21-N, for any abnormalities such as cracks by using a laser beam or the like, and evaluates whether or not the finished product is a good product. The result is notified to the evaluation model management machine 10.

The evaluation model management machine 10 creates a basic evaluation model MB from the measurement data (sensor data) from each sensor 31-1 to 31-N and the inspection result data from the inspection machine 30. The basic evaluation model MB is a model showing the range of measured value data by a predetermined sensor up to each process required for the production of non-defective products.

The evaluation model management machine 10 creates an evaluation model MS used in each stage evaluation machine 11-1 to 11-N from the data of the basic evaluation model MB. In the stage-by-step evaluation model MS, each stage evaluation machine 11 determines whether or not the processing in each process 21 executed up to the target process (target inspection stage) is within the range of processing required for non-defective product production. It is an evaluation model for evaluation. The evaluation model MS can be called an evaluation model for up to the target process, an evaluation model for up to the target inspection stage, and a stage-by-step evaluation model. The evaluation model management machine 10 notifies each stage evaluation machine 11 of the created evaluation model MS and causes it to be set.

Specifically, the evaluation model management machine 10 creates an evaluation model MSN from the basic evaluation model MB to the Nth stage, and notifies the evaluation model MSN to the Nth stage evaluation machine 11-N. Further, the evaluation model management machine 10 creates an evaluation model for up to the Nth stage from the evaluation model MSN up to the Nth stage, and notifies the Nth stage-1 evaluation machine (not shown). Similarly, the evaluation model management machine 10 creates the evaluation model MS2 up to the second stage from the evaluation model MS3 (not shown) up to the third stage, and notifies the second stage evaluation machine 11-2.

Further, the evaluation model management machine 10 creates the evaluation model MS1 up to the first stage from the evaluation model MS2 up to the second stage, and notifies the first stage evaluation machine 11-1. Each stage evaluation machine 11-1 to 11-N uses the values measured by the sensor 31 up to each process to determine whether or not the process processing required for non-defective product production has been executed in each process, and produces non-defective products. If it is determined that the necessary process processing has not been executed, an alert is presented. The presented alert is displayed on the screen, for example, via a user interface device connected to the evaluation model management machine 10.

As described above, the quality evaluation system 1 of the present embodiment evaluates the state of the product in process after the completion of each process, including the process processing executed before that. As a result, the quality evaluation system 1 can detect the occurrence of defects due to the combination of processes up to each inspection stage (each process). Further, the quality evaluation system 1 can identify the process causing the occurrence of defective products and prompt the user to take prompt action without waiting for the final inspection by the inspection machine 30.

FIG. 2 is a sequence diagram for creating an evaluation model. The evaluation model management machine 10 acquires data from each sensor 31 and the inspection machine 30 when creating the basic evaluation model MB and the stage-by-step evaluation model MS. Hereinafter, the step may be abbreviated as "S".

In the above example, the first sensor 31-1 measures the amount of the material acquisition process executed in the first step 21-1, and notifies the evaluation model management machine 10 of the measured value (S11). ). The second sensor 31-2 measures the temperature state of the heating of the material executed in the second step 21-2, and notifies the evaluation model management machine 10 of the measured value (S12). The Nth sensor 31-N measures the length after cutting for the cutting process of the unnecessary portion executed in the Nth step 21-N, and notifies the evaluation model management machine 10 of the measured value (the measured value). S13).

The inspection machine 30 evaluates whether or not the finished product 20 is a non-defective product by inspecting the finished product 20 that has completed the Nth process for any abnormalities such as cracks, and evaluates the evaluation result as an evaluation model. Notify the management machine 10 (S14).

After that, the steps of steps S11 to S14 described above are repeatedly executed, and are continued until the acquisition of measurement data necessary for producing a predetermined number (for example, 100) of non-defective products is completed.

Eventually, the first sensor 31-1 notifies the evaluation model management machine 10 of the measurement data (S21), the second sensor 31-2 notifies the evaluation model management machine 10 of the measurement data (S22), and the Nth sensor 31. When the measurement data is notified to the evaluation model management machine 10 by N (S23) and the inspection result is notified to the evaluation model management machine 10 by the inspection machine 30 (S24), the evaluation model management machine 10 is predetermined. This means that we have acquired the measurement data necessary to produce a number of good products.

The evaluation model management machine 10 has a range of measurement data received by the sensor 31 from each sensor 31 and a plurality of inspection result data received from the inspection machine 30 to each process required for production of a non-defective product. A basic evaluation model MB showing the above is created (S25). The basic evaluation model MB may be created using, for example, the Mahalanobis distance.

FIG. 3 is a sequence diagram in which the evaluation model management machine 10 creates and distributes the evaluation model MS for each stage up to each stage. The evaluation model management machine 10 creates an evaluation model MS for each stage from the data of the created basic evaluation model MB, and notifies the evaluation machines 11-1 to 11-N of each stage.

The evaluation model management machine 10 sets the data of the basic evaluation model MB as the evaluation model MSN up to the Nth stage (S31). Further, the evaluation model management machine 10 maps the data of the evaluation model MSN up to the Nth stage to the dimension of the data type measured by the plurality of sensors 31 up to the N-1th stage, thereby performing the N-1th stage. Create an evaluation model for up to (not shown).

Similarly, the evaluation model management machine 10 maps the data of the evaluation model MS3 for up to the third stage to the two-dimensional space of the temperature dimension and the quantity dimension measured by the second stage. , Create an evaluation model MS2 for up to the second stage (S32). Model MS3 is omitted in the figure.

The evaluation model management machine 10 maps the data of the evaluation model MS2 up to the second stage to the one-dimensional space of the quantity measured by the first stage, so that the evaluation model MS1 up to the first stage Is created (S33).

When the evaluation model management machine 10 creates the evaluation model MS1 for up to the first stage, it calculates the data of the evaluation model MSN for up to the Nth stage and the allowable range data of the measured values of the Nth sensor, and evaluates the Nth stage. Notify the machine 11-N (S34). The permissible range data of the measured value of the Nth sensor indicates that the data of the sensor 31-N associated with the Nth step satisfies the predetermined quality expected in the Nth step for the product in process. It is a range. Similarly, for example, if the measured value of the second sensor 31-2 falls within the allowable range for the second sensor, it is determined that the product in process in the second step satisfies the quality expected in the second step. ..

The evaluation model management machine 10 calculates the data of the evaluation model MS2 for up to the second stage and the allowable range data of the measured values of the second sensor 31-2, and notifies the second stage evaluation machine 11-2 (S35). ). Further, the evaluation model management machine 10 notifies the first stage evaluation machine 11-1 of the data of the evaluation model MS1 up to the first stage (S36).

FIG. 4 is a sequence diagram of evaluation performed in each step (each step). In this embodiment, the quality of the product in process is controlled in each process 21. In the figure, the name of the configuration may be simplified and described. For example, in FIG. 4, the grade evaluation machine is abbreviated as "evaluation".

The first sensor 31-1 measures the measured amount of material to the first stage evaluation machine 11-1 and the second stage evaluation machine 11-2 to the second stage evaluation machine 11-, which are the stage evaluation machines of the subsequent process. Notify N of each (S41 to S43).

The first-stage evaluation machine 11-1, which is the first evaluation machine, evaluates only the data (single data) measured by the first sensor 31-1 (S44). The evaluation performed based on the data (single data) of only the sensor 31 corresponding to the target process 21 is referred to as "single evaluation" in the present specification. The first-stage evaluation machine 11-1 determines whether the data of the first sensor 31-1 exists within the first permissible range set by the evaluation model management machine 10 (S44).

Here, the first permissible range is the permissible range data of the measured values of the first sensor 31-1 and is a value (predetermined quality) required for the product in process to become a non-defective finished product 20. Shows that it has. Similarly, the Nth permissible range is the permissible range data used for evaluating the single data of the Nth sensor 31-N.

The first-stage evaluation machine 11-1 evaluates whether or not the data is within the first permissible range of data of the first sensor 31-1 (S44). The first-stage evaluation machine 11-1 can output an alert when it is determined that the data of the first sensor 31-1 is out of the first permissible range (S44). The alert is given to the user, for example, as a display, a warning sound, a reading of a warning message, an output to an email, a chat, or the like. The user who receives the alert can take measures such as suspending the production line or confirming the process in which the problem has occurred.

The second sensor 31-1 notifies each evaluation machine of the second stage evaluation machine 11-2 and the Nth stage evaluation machine 11-N of the subsequent process of the measured temperature value (S45, S46). The second stage evaluation machine 11-2 carries out individual evaluation (S47) and combination evaluation (S48).

First, the second stage evaluation machine 11-2 performs an independent evaluation. In the stand-alone evaluation, it is determined whether or not the value of the stand-alone data measured by the second sensor 31-2 is within the range of the value required for the production of non-defective products, that is, whether or not it is within the second permissible range (2nd permissible range). S47). The second stage evaluation machine 11-2 outputs an alert when it is determined that the measured single data (temperature value data) is out of the second allowable range (S47).

When the second stage evaluation machine 11-2 determines that the single data exists within the second permissible range, the second stage evaluation machine 11-2 executes the combination evaluation. In the combination evaluation, the combination of the data of the sensors 31-1 and 31-2 corresponding to each process including the process 21-1 of the first stage to the process 21-2 of the second stage exists in the second evaluation model MS2. It is determined whether or not to do (S48). As described above, the data of each sensor before the target process is referred to as the data of a predetermined sensor. The second-stage evaluation machine 11-2 outputs an alert when it is determined that the combination of data of the predetermined sensors 31-1 and 31-2 is out of the range of the second evaluation model MS2.

The Nth sensor 31-N notifies the Nth stage evaluation machine 11-N of the measured length value (S49). The N-stage evaluation machine 11-N also performs individual evaluation (S50) and combination evaluation (S51).

The Nth stage evaluation machine 11-N evaluates whether or not the value of the single data measured by the Nth sensor 31-N is within the Nth permissible range (S50). The Nth stage evaluation machine 11-N outputs an alert when the single data (temperature value data) is out of the Nth allowable range (S50).

The Nth stage evaluation machine 11-N performs a combination evaluation when the single data is within the Nth allowable range. In the Nth stage evaluation machine 11-N, whether or not the combination of data of the sensors (predetermined sensors) of each process including the first process 21-1 to the Nth operation 21-N is included in the Nth evaluation model. (S51). The Nth stage evaluation machine 11-N outputs an alert when it is determined that the combination of data of a predetermined sensor is out of the range of the Nth evaluation model (S51).

The inspection machine 30 measures the state of the finished product 20 using a laser or the like (S52), and evaluates the state of the finished product 20 based on the measurement data (S53). The inspection machine 30 outputs whether or not the finished product 20 is a non-defective product as a result of the final inspection (S53). As described in FIG. 2, the result of the final inspection is notified to the evaluation model management machine 10 (S14, S24 in FIG. 2).

FIG. 5 is an explanatory diagram showing an evaluation model used in the third stage. In this embodiment, there is a one-to-one correspondence between the process and the inspection stage. Therefore, as the step 21 progresses by one, the data type of the sensor 31 also increases by one. In the third step 21-3, a total of three sensors 31-1, 31-2, and 31-3 are involved in the product being processed in the third step 21-3. Considering the data of each sensor as one axis, the evaluation model MS3 corresponding to the third step 21-3 involving the three sensors has three dimensions as shown in FIG.

In this embodiment, for example, the value of the amount of the material 4 is measured by the first sensor 31-1 shown on the x-axis, and then the temperature value is measured by the second sensor 31-2 shown on the y-axis. The length value is measured by the third sensor 31-3 shown on the z-axis.

The evaluation model MS3 for up to the third stage has a quantity value (x), a temperature value (y), and a length value (z) measured when a predetermined number (for example, 100 pieces) of non-defective products are produced. It can be expressed as a range of three-dimensional data. For example, the model MS3 for up to the third stage can be expressed by the following equation (1).

(x-3) ^ 2 + (y-2) ^ 2 + (z-4) ^ 2 ≤ 1 ・ ・ ・ Equation (1)

In the independent evaluation in the third stage, if the z-axis data, which is the independent data in the third stage, falls within the predetermined allowable range (value za to value zb), the product in process is the predetermined product required in the third stage. It is evaluated to have the quality of. In the combination evaluation using the evaluation model MS3 for up to the third stage, the data value (x) of the first sensor 31-1 on the x-axis, the data value (y) of the second sensor 31-2 on the y-axis, and further. When the data value (z) of the third sensor 31-3 on the z-axis satisfies the equation (1), it is evaluated that the product in progress has a quality that can be completed as a good product. The same is true for other stages.

Then, in order for the product that has reached the third step to be finally completed as a non-defective product, at least the values measured by the sensors 31-1, 31-2, 31-3 measured up to the third step are used. The combination needs to be within the range of the evaluation model MS3 for up to the third stage.

FIG. 6 is an explanatory diagram showing the evaluation model MS2 used in the second stage. The value of the amount of the product in process that has reached the second stage (second step 21-2) is measured by the first sensor 31-1 of the first step 21-1, and the second step 21- The value of the temperature is measured by the second sensor 31-2 of 2.

The evaluation model MS2 for up to the second stage shows the range of two-dimensional data of the measured quantity value (x) and the temperature value (y) when a predetermined number (for example, 100) of non-defective products are produced. That is, the evaluation model MS2 used by the second-stage evaluation machine 11-2 includes an x-axis which is the data axis of the first sensor 31-1 and a y-axis which is the data axis of the second sensor 31-2. It can be defined as a dimensional data range.

The evaluation model MS2 can be expressed as, for example, the following equation (2). The region allowed as the value of the first sensor 31-1 and the region allowed as the value of the second sensor 31-2 correspond to the region obtained by mapping (parallel projection) the above equation (1) onto the xy plane. ..

(x-3) ^ 2 + (y-2) ^ 2 ≤ 1 ・ ・ ・ Equation (2)

In the independent evaluation in the second stage, when the data of the second sensor 31-2 on the y-axis is within the range from the value ya to the value yb, the product in process has the predetermined quality required in the second stage. Evaluated to have. In the combination evaluation using the evaluation model MS2 for up to the second stage, the data value (x) of the first sensor 31-1 on the x-axis and the data value (y) of the second sensor 31-2 on the y-axis are used. When the formula (2) is satisfied, it is evaluated that the product in progress has a quality that can be completed as a good product.

FIG. 7 is an explanatory diagram showing the evaluation model MS1 used in the first stage. In the first step (first step 21-1), the value of the amount of the material 4 is measured by the first sensor 31-1.

The evaluation model MS1 for up to the first stage can be defined as a range of one-dimensional data of the measured quantity values when a predetermined number (for example, 100) of non-defective products are produced. For example, the model MS1 for up to the first stage can be expressed by the following equation (3). The region allowed as the value of the first sensor 31-1 corresponds to the region in which the equation (2) is mapped (parallel projection) to the x-axis.

2 ≤ x ≤ 4 ・ ・ ・ Equation (3)

For up to the first stage In the evaluation model MS1, when the data of the first sensor 31-1 on the x-axis is within the range from the value xa to the value xb, the product in process is of the predetermined quality required in the first stage. Is evaluated as having.

FIG. 8 is a flowchart showing the management of the evaluation model. The process shown in FIG. 8 can be executed at a predetermined timing. The predetermined timing may be, for example, when the product to be produced is changed, when the factory is started, or when all or part of the process is changed or replaced.

When the evaluation model management program P101, which will be described later in FIG. 21, is started, the evaluation model management machine 10 determines whether sensor data (data measured by the sensor) necessary for producing a predetermined number of non-defective products has been accumulated. (S101). Sensor data necessary for producing a predetermined number of non-defective products may be referred to as "predetermined number of non-defective product data".

The evaluation model management machine 10 periodically executes step S101 until a predetermined number of non-defective product data is accumulated, and waits (S101: NO). When the evaluation model management machine 10 determines that a predetermined number of non-defective product data has been accumulated (S101: YES), the evaluation model management machine 10 includes a plurality of measurement data acquired from each sensor 31 and a plurality of inspection result data acquired from the inspection machine 30. Based on the above, a basic evaluation model MB showing the range of data of each sensor up to each process, which is required for the production of non-defective products, is created (S102).

The evaluation model management machine 10 sets the data of the basic evaluation model MB for the finished product as the evaluation model MSN for up to the Nth stage (S103).

Further, the evaluation model management machine 10 maps the evaluation model data MSN up to the Nth stage to the dimension of the data type measured by each sensor up to the N-1th stage, thereby evaluating the evaluation up to the N-1th stage. Create a model (S104).

The evaluation model management machine 10 determines whether or not all the evaluation models used in each stage have been created (S105). When there is an unprepared evaluation model (S105: NO), the evaluation model management machine 10 creates an evaluation model to be used in the stage immediately before the stage corresponding to the latest evaluation model (S104).

The evaluation model management machine 10 repeatedly executes steps S104 and S105 to create an evaluation model up to the N-1 stage to an evaluation model MS1 up to the first stage. The created data of each evaluation model is stored in the memory as the evaluation model data D102 described later in FIG. 21 (S105).

When the evaluation model management machine 10 creates an evaluation model for up to the first stage, a predetermined value for determining the quality of the evaluation model data used in each stage and the single data measured by the sensor 31 in each stage is determined. An allowable range is set (S106), and the set evaluation model data and the allowable range data are notified to each stage evaluation machine 11 (S107). Since the first-stage evaluation machine 11-1 uses only the data of the first sensor 31-1, the range of the one-dimensional evaluation model MS1 and the data of the range in which the data of the first sensor 31-1 is allowed are as follows. Match. Therefore, only the evaluation model MS1 for the first stage is notified from the evaluation model management machine 10 to the first stage evaluation machine 11-1. The evaluation model management machine 10 ends this process when step S107 is completed.

FIG. 9 is a flowchart showing the evaluation method in the first stage. When the first-stage evaluation machine 11-1 starts the first-stage evaluation program, which is one of the stage evaluation programs P111 described later in FIG. 22, the first-stage evaluation machine 11-1 receives the evaluation model MS1 for the evaluation model management machine 10 to the first stage. It is determined whether or not it has been done (S111).

When the first stage evaluation machine 11-1 determines that the evaluation model MS1 has not been received (S111: NO), the first stage evaluation machine 11-1 waits until the evaluation model MS1 is received from the evaluation model management machine 10.

When the first-stage evaluation machine 11-1 determines that the evaluation model MS1 has been received (S111: YES), it determines whether the sensor data (measured value data) from the first sensor 31-1 has been received (S112). .. The first-stage evaluation machine 11-1 waits until the data of the first sensor 31-1 is received (S112: NO).

When the first-stage evaluation machine 11-1 determines that the data of the first sensor 31-1 has been received (S112: YES), the received data (measured value) of the first sensor 31-1 is the evaluation model MS1. It is determined whether it is within the range of (S113).

When the first stage evaluation machine 11-1 determines that the value measured by the first sensor 31-1 is within the range of the evaluation model MS1 (S113: YES), it returns to step S112 and returns to the first sensor 31-. Wait for new data from 1.

When the first-stage evaluation machine 11-1 determines that the value measured by the first sensor 31-1 is out of the range of the evaluation model MS1 (S113: NO), the data of the first sensor 31-1 is evaluated. An alert indicating that the model MS1 is out of range is output (S114).

As described above, since the first step 21-1 is the first step and there is no other step before that, only the independent evaluation according to the step 113 is executed. In each step (21-2 to 21-N) from the second step to the subsequent steps, since the product is processed in the pre-steps leading up to the target step, not only individual evaluation but also combined evaluation is performed. The evaluation processing by each stage evaluation machine 11 from the second stage evaluation machine 11-2 to the Nth stage evaluation machine 11-N differs only in the evaluation model used and the sensor used, and the basic operation is common. .. Therefore, the N-stage evaluation machine 11-N will be described as a representative.

FIG. 10 is a flowchart showing the evaluation method in the Nth stage. In each stage evaluation machine 11 after the second stage, the evaluation process as shown in FIG. 10 is executed. That is, the process shown in FIG. 10 can be considered to be the evaluation process in the stage evaluation machine 11. However, the first stage evaluation machine 11-1 does not execute the step related to the combination evaluation in FIG.

When the N-stage evaluation machine 11-N starts the N-stage evaluation program, which is one of the stage evaluation programs P111, the data of the evaluation model MSN and the allowable range of the N-sensor 31-N are up to the N-stage. It is determined whether or not the data is received from the evaluation model management machine 10 (S121). The Nth stage evaluation machine 11-N waits until the evaluation model MSN and the data of the allowable range are received from the evaluation model management machine 10 (S121: NO).

When the Nth stage evaluation machine 11-N determines that the evaluation model MSN and the data in the allowable range have been received (S121: YES), it determines whether the data has been received from the Nth sensor 31-N (S122). When the N-th stage evaluator 11-N determines that the data has not been received from the N-th sensor 31-N (S122: NO), the N-th stage evaluator 11-N waits until the data is received.

When the Nth stage evaluation machine 11-N determines that the data has been received from the Nth sensor 31-N (S122: YES), the value of the single data of the Nth sensor 31-N is a predetermined value required for good product production. It is determined whether the quality is within the allowable range (S123).

When the N-th stage evaluation machine 11-N determines that the value of the single data of the N-th sensor 31-N is out of the range of the value required for the production of non-defective products (S123: NO), the single data is out of the allowable range. An alert indicating that there is is output (S124).

When the N-stage evaluation machine 11-N determines that the single data of the N-th sensor 31-N is within a predetermined allowable range (S123: YES), each sensor measured up to the N-th sensor 31-N. It is determined whether the combination of the data of 31-1 to 31-N is within the range of the evaluation model MSN up to the Nth stage (S125). When the N-stage evaluation machine 11-N determines that the combination of data of the predetermined sensors 31-1 to 31-N is within the range of the evaluation model MSN (S125: YES), the process returns to step S122.

On the other hand, when the N-stage evaluation machine 11-N determines that the combination of the data measured by the predetermined sensors 31-1 to 31-N is out of the range of the evaluation model MSN (S125: NO), it issues an alert. Output (S126). The alert output in step S126 indicates that the combination of data of the predetermined sensor is out of the range of the evaluation model MSN.

FIG. 11 shows a table T1 that manages data (measured values) from each sensor 31. This management table T1 is used when creating an evaluation model. Here, for the sake of easy understanding, a production line consisting of three steps 21-1 to 21-3 will be described as an example. In the following description, each row of the table is identified by using the material identifier.

The measured value management table T1 includes, for example, the identifier C11 of the material 4, the data C12 measured by the first sensor 31-1, the data C13 measured by the second sensor 31-2, and the third sensor 31-3. The data C14 measured by the inspection machine 30, the evaluation result data C15 inspected by the inspection machine 30, and the identifier C16 of the finished product 20 determined to be a good product by the inspection of the inspection machine 30 are provided.

In the first line (material ID = MA1), the data of the first sensor 31-1 is the value x1, the data of the second sensor 31-2 is the value y1, and the data of the third sensor 31-3 is the value. It is z1 and the result of the final inspection is a good product (PASS), indicating that the identifier P1 has been given as a finished product.

Similarly, in the second row (MA2) to the sixth row (MA6), the values of the data measured by the sensors 31-1 to 31-3 for each process processed on the material 4 and the inspection machine 30 The result of the final inspection (final evaluation) by the above and the finished product identifier in the case of a non-defective product are managed.

In the seventh line (MA7), the data of the first sensor 31-1 is the value x7, the data of the second sensor 31-2 is the value y7, and the data of the third sensor 31-3 is the value z7. , The evaluation of the inspection machine 30 is a defective product (FAIL), and the finished product identifier is not given.

The same applies to the eighth row (MA8) to the last row (MA103). In the final line (MA103), the identifier P100 as a finished product is set. The identifier P100 indicates that 100 finished products 20 have been manufactured as an example of a predetermined number. In the example of FIG. 11, the identifier P100 of the finished product is three less than the identifier MA103 of the material. This means that three defective products have occurred.

FIG. 12 shows a measured value management table T2 that manages the evaluation of each stage evaluation machine 11 and inspection machine 30 with respect to the data of each sensor 31. Similar to FIG. 11, FIG. 12 will be described by taking a production line including three steps as an example.

The measured value management table T2 includes, for example, the material identifier C21, the data evaluation C22 up to the first sensor held by the first stage evaluation machine 11-1, and the second sensor held by the second stage evaluation machine 11-2. Data evaluation C23 up to, data evaluation C24 up to the third sensor held by the third stage evaluation machine 11-3, final evaluation C25 held by the inspection machine 30, and finished product identifier C26 in the case of a non-defective product are provided. .. Hereinafter, the evaluation by the first stage evaluation machine may be referred to as the first evaluation, the evaluation by the second stage evaluation machine may be referred to as the second evaluation, the evaluation by the third stage evaluation machine may be referred to as the third evaluation, and the evaluation by the inspection machine may be referred to as the final evaluation. ..

In the first evaluation C22 of the first line (material identifier = MA101), as a result of the processing of the first step, the data value x101 of the first sensor is within the allowable range (xa to xb) of the x-axis, and is a good product (good product (xa to xb). It is shown that it is determined to be PASS) (single evaluation).

In the second evaluation C23 of the first row (MA101), as a result of the processing of the second step, the data value y101 of the second sensor is within the allowable range (ya to yb) of the y-axis, and is a non-defective product (PASS). It has been shown to be present (single evaluation). Further, in the second evaluation, it is shown that the combination of the value x101 and the value y101 exists within the range of the evaluation model MS2 for the second stage and is determined to be a non-defective product (combination). evaluation).

Similarly, in the third evaluation C24 of the first row (MA101), as a result of the processing of the third step, the data value z101 of the third sensor is within the allowable range (za to zb) of the z-axis and is a good product. It is shown that it is judged as (single evaluation). Further, in the third evaluation, it is shown that the combination of the value x101, the value y102, and the value z101 exists within the range of the evaluation model MS3 up to the third stage, and is determined to be a good product. Yes (combination evaluation).

In the final evaluation C25 of the first line (MA101), it is shown that the final evaluation of the quality by the inspection machine is also a good product. As a result, the product which is the target of the first row is given the identifier P101 as a finished product.

In the first evaluation C22 of the second row (MA102), as a result of the processing of the first step, the data value x102 of the first sensor is within the allowable range (xa to xb) of the x-axis, and it is determined that the product is a good product. It has been shown to be (single evaluation).

In the second evaluation C23 of the second row (MA102), as a result of the processing of the second step, the data value y102 of the second sensor is within the allowable range (ya to yb) of the y-axis, and it is determined that the product is a good product. It has been shown to be (single evaluation). Further, in the second evaluation, it is shown that the combination of the value x102 and the value y102 exists within the range of the evaluation model MS2 up to the second stage and is determined to be a non-defective product (combination). evaluation).

In the third evaluation C24 of the second row (MA102), as a result of the processing of the third step, it is determined that the data value z102 of the third sensor exists outside the allowable range (za to zb) of the z-axis (FAIL). Has been done. Therefore, the final evaluation C25 is a defective product (FAIL), and an identifier as a finished product is not given.

In the first evaluation C22 of the third row (MA103), as a result of the processing of the first step, the data value x103 of the first sensor is within the allowable range (xa to xb) of the x-axis, and it is determined that the product is a good product. It is shown to be.

In the second evaluation C23 of the third row (MA103), as a result of the processing of the second step, it is shown that the data value y103 of the second sensor is out of the allowable range (ya to yb) of the y-axis. Yes (FAIL). Since the evaluation by the second stage evaluation machine is a defective product (FAIL), the third step of the latter stage has not been carried out. This is because even if a product in process, which has a high possibility of being defective, is processed, it will not be a good product. Since it is evaluated as a defective product at the time of the second step, the final evaluation C25 is also a defective product, and the defective product is not given an identifier of the finished product.

In the first evaluation C22 of the fourth row (MA104), it is shown that the data value x104 of the first sensor is outside the allowable range (xa to xb) of the x-axis. Therefore, the second step and the third step in the latter stage are omitted. The final evaluation C25 is a defective product (FAIL), and no identifier as a finished product is given.

In the first evaluation C22 of the fifth row (MA105), it is determined that the data value x105 of the first sensor is within the allowable range of the x-axis.

In the second evaluation C23 of the fifth row (MA105), it is determined that the data value y105 of the second sensor is also within the allowable range of the y-axis (single evaluation). The combination of the value x105 and the value y105 is also determined to be in the evaluation model MS2 up to the second stage (combination evaluation).

In the third evaluation C24 of the fifth row (MA105), it is determined that the data value z105 of the third sensor exists within the allowable range of the z-axis. However, it is determined that the combination of the value x105, the value y105, and the value z105 exists outside the evaluation model MS3 up to the third stage, and the product in process is evaluated as a defective product. Therefore, the final evaluation C25 is also a defective product, and the identifier of the finished product is not given.

In the first evaluation C22 of the sixth row (MA106), it is determined that the data value x106 of the first sensor exists within the allowable range of the x-axis.

In the second evaluation C23 of the sixth row (MA106), it is determined that the data value y106 of the second sensor exists within the allowable range of the y-axis (single evaluation). However, the combination of the value x106 and the value y106 is determined to be outside the evaluation model MS2 up to the second stage, and the product in process is evaluated as a defective product (combination evaluation). Therefore, the third step in the latter stage is not carried out. The final evaluation C25 is a defective product, and no identifier for the finished product is given.

According to this embodiment configured in this way, not only the final evaluation is performed after the completion of all the steps, but also the basic evaluation model MB is created from the accumulation of the final evaluation, and the evaluation from the basic evaluation model MB is performed at each stage. An evaluation model MS is created for each stage to be used, and the product in progress is evaluated in advance by using the evaluation model MS at each stage.

Therefore, according to this embodiment, the occurrence of defective products (or signs of defective products) can be detected at an early stage in the process prior to that without waiting for the final evaluation by the inspection machine 30, and prompt measures are taken. be able to. As a result, according to the present embodiment, the yield of the product can be increased by identifying and improving the process in which defects are likely to occur at an early stage or omitting the process in which defects are likely to occur.

Further, in this embodiment, in each step (each inspection step) after the first step (first inspection step), an independent evaluation based only on the sensor data corresponding to the target step (target inspection step) is performed. The combination evaluation based on the data of the predetermined sensor provided from the first step to the target step is executed. As a result, it is possible to perform a plurality of evaluations different from the evaluation of the target process alone and the evaluation reflecting the background up to the target process, and the inspection accuracy can be improved.

In this embodiment, a first evaluation model showing the range of data of each sensor when the product is judged to be non-defective and a second evaluation model based on the first evaluation model are created, and each inspection stage is performed. The data of a predetermined sensor up to the inspection stage can be evaluated based on the second evaluation model. In addition, since the basic evaluation model MB is created from the data of each sensor accumulated by the time a predetermined number of non-defective products are completed, it is possible to efficiently evaluate the quality even when producing while switching between a wide variety of products. can. Furthermore, new products can be dealt with promptly, and production efficiency can be improved.

The second embodiment will be described with reference to FIGS. 13 to 15. In each of the following examples including this embodiment, the differences from the first embodiment will be mainly described. The quality evaluation system 1A of this embodiment includes a measurement data management machine 12 that centrally manages the data of each sensor 31.

That is, this embodiment is a modification of the first embodiment, and the measurement data management machine 12 manages the data measured at each inspection stage. When the measurement data management machine 12 receives a predetermined number of sensor data (measurement data), the measurement data management machine 12 transmits the data to the evaluation model management machine 10.

FIG. 13 is a block diagram of the quality evaluation system 1A. In the quality evaluation system 1A of this embodiment, as compared with the quality evaluation system 1 described with reference to FIG. 1, a measurement data management machine 12 is provided between each sensor 31 and each stage evaluation machine 11 and the evaluation model management machine 10. It is provided.

When the measurement data management machine 12 acquires the measurement data necessary for producing a predetermined number (for example, 100) of non-defective products at the time of creating the evaluation model, the measurement data management machine 12 notifies the evaluation model management machine 10 of the data shown in FIG. do.

The evaluation model management machine 10 creates a basic evaluation model MB and an evaluation model MS for each stage based on the data received from the measurement data management machine 12. The evaluation model management machine 10 transmits the created evaluation model MS to each stage evaluation machine 11 for setting.

The data sent to each stage evaluation machine 11 is the same as that of the first embodiment. When the measurement data management machine 12 receives data from the sensor 31 of each stage, the measurement data management machine 12 transmits the data not only to the stage evaluation machine 11 corresponding to the stage but also to each stage evaluation machine 11 located at the subsequent stage of the target process. ..

Each stage evaluation machine 11 evaluates whether the product in process is a good product based on the stage-by-stage evaluation model MS received from the evaluation model management machine 10 and the data of the predetermined sensor 31. As described above, the evaluation includes individual evaluation and combined evaluation.

FIG. 14 is a sequence diagram for creating an evaluation model. In FIG. 14, the sensor is abbreviated as “SR”.

The first sensor 31-1 measures the amount of the process (for example, the material acquisition process) executed in the first step 21-1, and notifies the measurement data management machine 12 of the measured value (S131). The second sensor 31-2 measures the state (for example, temperature state) of the process (for example, heat process) executed in the second step 21-2, and notifies the measurement data management machine 12 of the measured value (for example, the temperature state). S132). The Nth sensor 31-N measures the state (for example, the length after cutting) of the processing (for example, cutting processing) executed in the Nth step 21-N, and transfers the measured value to the measurement data management machine 12. Notify (S133).

On the other hand, the inspection machine 30 evaluates whether or not the finished product is a good product by inspecting the finished product after the Nth step for any abnormalities such as cracks according to a predetermined standard. The evaluation result is notified to the measurement data management machine 12 (S134).

The same steps as in steps S131 to S134 are repeatedly executed until the measurement data management machine 12 acquires the measurement data necessary for producing a predetermined number (for example, 100) of non-defective products.

Data transmission of the first sensor 31-1 (S141), data transmission of the second sensor 31-2 (S142), data transmission of the Nth sensor 31-N (S143), transmission of the evaluation result of the inspection machine 30 (S144). It is assumed that the measurement data management machine 12 has acquired the measurement data necessary for producing a predetermined number of non-defective products. When the measurement data management machine 12 confirms that a predetermined number of data has been acquired (S145), the measurement data management machine 12 notifies the evaluation model management machine 10 of the data of each sensor 31 and the inspection result (evaluation result) of the inspection machine 30 (S146). ..

The evaluation model management machine 10 has a plurality of measurement data in each sensor 31 received from the measurement data management machine 12 and a plurality of inspection result data from the inspection machine 30 to each process required for non-defective product production. A basic evaluation model MB showing the range of the measured value data by the sensor 31 is created (S147).

FIG. 15 is a sequence diagram of evaluation performed in each step (each step). When the quality control for the processing performed in each process is started, the first sensor 31-1 notifies the measurement data management machine 12 of the measured value (S151).

The measurement data management machine 12 notifies the first stage evaluation machine 11-1 of the received data of the first sensor 31-1 (S152). The first-stage evaluation machine 11-1 collates the evaluation model MS1 received in advance from the evaluation model management machine 10 with the independent measurement data received from the measurement data management machine 12 by the first sensor 31-1. Thereby, it is determined whether or not an appropriate process is executed in the first step (S153).

The first-stage evaluation machine 11-1 notifies the measurement data management machine 12 of the evaluation result in step S153 (S154).

The second sensor 31-2 notifies the measurement data management machine 12 of the measured value (S155). The measurement data management machine 12 notifies the second stage evaluation machine 11-2 of the received data of the second sensor 31-2 and the data of the first sensor 31-1 acquired before that (S156).

The second-stage evaluation machine 11-2 determines whether the value of the data of the second sensor is included in the allowable range received in advance from the evaluation model management machine 10 (S157). Further, the second stage evaluation machine 11-2 is a combination of the evaluation model MS2 received in advance from the evaluation model management machine 10 and the data measured by the predetermined sensors 31-1 and 31-2 up to the second stage. By collating the above, it is determined whether the product in process is a good product (S158). A good product in process means that the product in process has the quality expected in the process. As a result, there is a high possibility that the product in process will be a good product when it is completed.

The second-stage evaluation machine 11-2 notifies the measurement data management machine 12 of the result of the single evaluation in step S157 and the result of the combination evaluation in step S158 (S159).

The Nth sensor 31-N notifies the measurement data management machine 12 of the measured value (S160). The measurement data management machine 12 combines the data measured by the third sensor 31-N and the data measured by each sensor (sensors 31 up to the N-1 stage) provided in the previous process. Notify the N-stage evaluation machine 11-N (step S1631).

The Nth stage evaluation machine 11-N determines whether the single measurement data received from the measurement data management machine 12 by the Nth sensor 31-N is within the permissible range received in advance from the measurement data management machine 12. (Step S162).

The Nth stage evaluation machine 11-N collates the evaluation model MSN for up to the Nth stage with the combination of the data measured by the predetermined sensor 31 up to the Nth stage, so that the product in process is a good product. It is determined whether or not there is (S163). The N-stage evaluation machine 11-N notifies the measurement data management machine 12 of the result of the single evaluation in step S162 and the result of the combination evaluation in step S163 (step S164).

In this embodiment, the data measured by the Nth sensor 31-N and the data measured by each sensor 31 up to the Nth stage are notified to the Nth stage evaluation machine 11-N at once. However, it is not limited to this. For example, when the data measured in each process alone is within a predetermined allowable range, the N-stage evaluation machine 11-N may inquire the data management machine 30 to acquire the data necessary for the evaluation. ..

This embodiment configured in this way also has the same effect as that of the first embodiment. Further, in this embodiment, since the measurement data management machine 12 that centrally manages the data of each sensor 31 is provided, the data necessary for each stage evaluation machine 11 is transmitted even if the arrangement of the sensors 31 changes. And can quickly follow changes in the production line.

The third embodiment will be described with reference to FIGS. 16 to 22. This embodiment is a modification of the first embodiment, and the evaluation model MS for evaluating the quality of process processing at each stage is updated at any time.

FIG. 16 is a block diagram of the quality evaluation system 1B of this embodiment. The quality evaluation system 1B has the same basic configuration as the quality evaluation system 1 described in the first embodiment, but its operation is different. Therefore, the operation of the quality evaluation system 1B will be described.

In the quality evaluation system 1 of the first embodiment, each stage evaluation machine 11 evaluates the processing quality for the processes up to each stage, and outputs an alert when a defect occurs. On the other hand, in this embodiment, the evaluation model management machine 10 receives the quality evaluation result from each stage evaluation machine 11 and aggregates and outputs the alert.

Further, in the quality evaluation system 1 of the first embodiment, the evaluation model management machine 10 has not received data from each sensor 31 and the inspection machine 30 in the operation stage of determining the evaluation up to each process. On the other hand, in this embodiment, the evaluation model management machine 10 receives data from each sensor 31 and the inspection machine 30 even in the operation stage of determining the evaluation up to each process.

When the evaluation model management machine 10 acquires the data measured by each sensor 31 when producing a predetermined number (for example, 100) of non-defective products, the evaluation model management machine 10 creates a basic evaluation model MB for the finished product and the basic evaluation model. From MB, the evaluation model MS up to each stage required for non-defective product production and the permissible range of sensor measurement values at that stage are created.

The evaluation model management machine 10 notifies each stage evaluation machine 11 of the created evaluation model MS up to each stage and the allowable range of the sensor measurement value of the stage. The evaluation machine 11 at each stage evaluates the quality of the process processing performed on the product in process based on the received evaluation model MS up to each stage and the allowable range of the sensor measurement value at that stage.

FIG. 17 is a sequence diagram for creating an evaluation model. When the quality control for the processing executed in each process is started, the first sensor 31-1 transfers the measured value to the first stage evaluation machine 11-1 and each stage evaluation machine 11-2-11- in the subsequent process. Notify N and the evaluation model management machine 10 (S171 to S174), respectively.

The first-stage evaluation machine 11-1 evaluates whether or not the value of the single data measured by the first sensor 31-1 is within the permissible range required for the production of non-defective products (S175). The first-stage evaluation machine 11-1 notifies the evaluation model management machine 10 of the evaluation result of step S175 (S176). The evaluation model management machine 10 outputs the evaluation result received from the first-stage evaluation machine 11-1 to, for example, a monitor display or the like, which is one of the user interface devices, and presents it to the user (S177).

The second sensor 31-1 notifies each evaluation machine up to the second stage evaluation machine 11-2 and the second stage evaluation machine 11-N and the evaluation model management machine 10 of the measured value (S178). ~ S180).

The second-stage evaluation machine 11-2 evaluates whether the value of the single data measured by the second sensor 31-2 is within a predetermined allowable range required for non-defective product production (S181). When the value of the single data measured by the second sensor 31-2 is within a predetermined allowable range, the second stage evaluation machine 11-2 uses the data of the first sensor 31-1 and the second sensor 31-2. It is evaluated whether or not the combination with the data is within the range of the evaluation model MS2 (S182).

The second-stage evaluation machine 11-2 notifies the evaluation model management machine 10 of the evaluation result in step S181 and the evaluation result in step S182 (S183). The evaluation model management machine 10 presents the received evaluation result to the user by outputting it to a display or the like (184).

The Nth sensor 31-N notifies the Nth stage evaluation machine 11-N and the evaluation model management machine 10 of the measured value (S185, S186). The N-stage evaluation machine 11-N evaluates whether the value of the single data measured by the N-th sensor 31-N is within a predetermined allowable range required for the production of non-defective products (S187).

When the value of the single data measured by the Nth sensor 31-N is within the predetermined allowable range, the combination of the data of the first sensor 31-1 to the Nth sensor 31-N is used up to the Nth stage. It is evaluated whether it is within the range of the evaluation model MSN (S188). The N-stage evaluation machine 11-N notifies the evaluation model management machine 10 of the evaluation result in step S187 and the evaluation result in step S188 (S189). The evaluation model management machine 10 presents the received evaluation result to the user by outputting it to a display or the like (S190).

The inspection machine 30 measures the state of the finished product (S191). The inspection machine 30 evaluates the state of the finished product based on the measured data, and determines whether or not the product is a good product (S192).

The inspection machine 30 notifies the evaluation model management machine 10 of the evaluation result in step S192 (S193). The evaluation model management machine 10 provides the received evaluation result to the user through a display or the like (S194).

When the evaluation model management machine 10 acquires the data of each sensor 31 measured at the time of production of a predetermined number (for example, 100) of non-defective products, it creates a basic evaluation model MB for finished products, and from the basic evaluation model, non-defective products. Create the evaluation model MS up to each stage and the allowable range of the sensor measurement value at that stage, which are necessary for production. Further, the evaluation model management machine 10 notifies the evaluation machine 11 of each stage of the created evaluation model MS and the allowable range (S195).

FIG. 18 is a flowchart showing quality evaluation management in the evaluation model management machine 10. After starting the quality evaluation program P102 (see FIG. 21), the evaluation model management machine 10 determines whether or not the data measured by the sensor 31 has been received (S201). When the evaluation model management machine 10 determines that the data has been received from the sensor 31 (S201: YES), the evaluation model management machine 10 stores and holds the received data in a memory or the like (S202), and proceeds to step S203.

On the other hand, when the evaluation model management machine 10 determines that the data has not been received from the sensor 31 (S201: NO), the evaluation model management machine 10 skips step S202 and proceeds to step S203.

In step S203, the evaluation model management machine 10 determines whether or not the evaluation has been received from the stage evaluation machine 11. When the evaluation model management machine 10 determines that the evaluation has been received from the stage evaluation machine 11 (S203: YES), the evaluation model management machine 10 presents the evaluation result to the user by displaying it on the display (S204). After that, the process proceeds to step S205.

When the evaluation model management machine 10 determines that the evaluation has not been received from the stage evaluation machine 11 (S203: NO), the evaluation model management machine 10 skips step S204 and proceeds to step S205.

The evaluation model management machine 10 determines whether or not the evaluation has been received from the inspection machine 30 (S205). When the evaluation model management machine 10 determines that the evaluation has been received from the inspection machine 30 (S205: YES), the evaluation model management machine 10 displays the evaluation result on the display and provides the evaluation result to the user (S206). Then, the process proceeds to step S207.

On the other hand, if the evaluation model management machine 10 determines that the evaluation has not been received from the inspection machine 30 (S205: NO), the evaluation model management machine 10 skips step S206 and proceeds to step S207.

The evaluation model management machine 10 determines whether or not a predetermined number of measurement data (data for non-defective products) when a finished product of non-defective products is obtained is accumulated (S207).

When the evaluation model management machine 10 determines that a predetermined number of non-defective product data has been accumulated in step S202 (S207: YES), the evaluation model management machine 10 creates a basic evaluation model MB from the predetermined number of non-defective product data (S208). Further, the evaluation model management machine 10 creates an evaluation model MS up to each stage from the basic evaluation model MB (S208). Further, the evaluation model management machine 10 calculates an allowable range of the measured value by the sensor 31 at each stage (S208). Then, the evaluation model management machine 10 notifies the corresponding stage evaluation machine 11 of the created evaluation model MS for each stage and the permissible range of each sensor (S208). Then, the process returns to step S201.

On the other hand, when the evaluation model management machine 10 determines that a predetermined number of non-defective product data has not been accumulated (S207: NO), the process returns to step S201.

FIG. 19 is a flowchart showing an evaluation process in the stage evaluation machine. In the first-stage evaluation machine, only individual evaluation is performed, but in each subsequent stage evaluation machine 11, the process shown in FIG. 19 is executed.

Since the evaluation process shown in FIG. 19 corresponds to a modification of the evaluation process described with reference to FIG. 10, the differences from the evaluation process of FIG. 10 will be mainly described. Since steps S211 to S213 and S215 shown in FIG. 19 are the same as steps S121 to S123 and S125 described in FIG. 10, description thereof will be omitted.

When the stage evaluation machine 11 determines that the single data of the sensor 31 corresponding to the stage is not within the predetermined allowable range (S213: NO), the stage evaluation machine 11 determines that the data measured by the sensor 31 is out of the allowable value range. , Notify the evaluation model management machine 10 (S214).

When the stage evaluation machine 11 determines that the combination of data measured by each predetermined sensor up to the sensor 31 is not included in the range of the stage-by-stage evaluation model MS (S215: NO), the stage evaluation machine 11 manages the evaluation model to that effect. Notify the machine 10 (S216).

The stage evaluation machine 11 evaluates that the data of the sensor 31 is within the allowable value range and that the combination of the data measured by each predetermined sensor up to the sensor 31 is within the range of the evaluation model MS. Notify the model management machine 10 (S217). That is, the stage evaluation machine 11 informs the evaluation model management machine 10 that the single evaluation indicates a non-defective product and the combination evaluation also indicates a non-defective product.

FIG. 20 shows the hardware configuration of the evaluation model management machine 10. The evaluation model management machine 10 can be realized by using a computer.

The evaluation model management machine 10 includes, for example, a CPU 101 as an example of a processor unit, a main memory 102 and a storage 103 as an example of a storage unit, and an input / output interface 104 as an example of an interface unit for transmitting and receiving data via a network. Each of these configurations is connected to each other via a bus 105.

A storage medium 106 can also be connected to the input / output interface 104. The computer program or the like described in FIG. 21 can be stored in the storage medium 106 in advance. By installing the computer program stored in the storage medium 106 in the computer, the computer may function as the evaluation model management machine 10. Instead of the storage medium 106, a computer program may be installed in the computer via a communication network.

The evaluation model management machine 10 may be further connected to a user interface device (UI device in the figure) 107. The user interface device 107 includes at least an information output device. The user interface device 107 may include an information input device.

The information output device includes, for example, a display, a printer, a voice synthesizer, and the like. The information input device includes, for example, a keyboard, a touch panel, a voice input device, and the like.

The CPU 101 controls each part of the evaluation model management machine 10. The CPU 101 loads a computer program stored in the storage 103 into the main memory 102, and executes the program to execute various functions as the evaluation model management machine 10.

The main memory 102 includes the evaluation model management program P101 and the quality evaluation management program P102 executed by the CPU 101, and work data (measurement value management table D101 for creating an evaluation model, evaluation model data D102) necessary for executing these programs P101 and P102. , Measurement value management table D103) for evaluation of measurement data is stored. The storage contents of the main memory 102 will be described later with reference to FIG.

For the storage 103, for example, a large-capacity storage device such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive) can be used. In this embodiment, the evaluation model management program P101 and the quality evaluation management program P102 are stored in advance in the storage 103.

FIG. 21 is an explanatory diagram showing an example of a program and data held in the main memory 102 of the evaluation model management machine 10.

The evaluation model management program P101 is loaded and executed in the main memory 102 as the first phase.

The processing work in the evaluation model management program P101 is described in FIG. The evaluation model management program P101 creates the measurement value management data D101 for creating an evaluation model based on the data received from the sensor or the like, and creates and holds the evaluation model data D102 from the data D101. A specific example of the measurement value management table D101 for creating an evaluation model corresponds to the measurement value management table T1 described in FIG.

As the second phase, the quality evaluation management program P102 is loaded into the main memory 102 and executed by the CPU 101. The processing of the quality evaluation control program P102 is described in FIG. The quality evaluation management program P102 creates measurement value management data D103 for measurement data evaluation based on data received from a sensor or the like and evaluation data from a stage evaluation machine, and creates evaluation model data D102 based on the data D103. Update.

By aggregating and managing the data of the management table T2 described with reference to FIG. 12 by the evaluation model management machine 10, the measurement value management table D103 for evaluation of measurement data is created.

FIG. 22 shows an example of data held in the main memory 112 of the stage evaluation machine 11. Each stage evaluation machine 11 can also be configured by using a computer having a CPU, a main memory, and the like as described in FIG. Here, the main memory 102 will be described.

The stage evaluation program P111 is loaded into the main memory 102, and the program P111 is executed by the CPU of the stage evaluation machine 11. The processing of the graded evaluation program is as described with reference to FIG. The stage evaluation program P111 creates measurement data D111 based on the data measured by the sensor 31.

In the main memory 102, data indicating an allowable range of each sensor and the evaluation model MS of each stage are received from the evaluation model management machine 10 and stored.

This embodiment configured in this way also has the same effect as that of the first embodiment. Further, in this embodiment, the evaluation result of each stage evaluation machine 11 is notified to the evaluation model management machine 10. The evaluation model management machine 10 of this embodiment can update the evaluation models MB and MS based on the evaluation results from each stage evaluation machine 11 and distribute the latest evaluation model MS to each stage evaluation machine 11. Therefore, in this embodiment, even if the data measured by the sensor 31 changes, it is possible to create an evaluation model that follows the change and improve the evaluation by the stage evaluation machine 11 at any time.

The fourth embodiment will be described with reference to FIGS. 23 and 24. In this embodiment, the evaluation model MS is not set for all the processes (steps), but the evaluation model MS is set only for a predetermined process.

FIG. 23 is a flowchart showing the management process of the evaluation model. When the evaluation model management program P101 is started, the evaluation model management machine 10 determines whether or not measurement data necessary for producing a predetermined number (for example, 100) of non-defective products has been accumulated (S221).

When the evaluation model management machine 10 determines that the measurement data necessary for producing a predetermined number of non-defective products is not accumulated (S221: NO), the evaluation model management machine 10 waits until the data is accumulated.

When the evaluation model management machine 10 determines that the measurement data necessary for producing a predetermined number of non-defective products has been accumulated (S221: YES), the measurement value that caused the defect determination is selected from the accumulated data. The output sensor is extracted (S222).

For example, the evaluation model management machine 10 has an average value of values measured by each sensor of each process executed on a finished product that has become a non-defective product, and each process executed on a finished product determined to be a defective product. Compare with the average value measured by the sensor. Then, the evaluation model management machine 10 extracts a sensor whose average difference is a predetermined value (for example, 30%) or more as a sensor (defect-related sensor) provided in a process considered to be a cause of defective products. do. Hereinafter, a case where a plurality of defect-related sensors are extracted will be described as an example.

The evaluation model management machine 10 is a non-defective product in a dimension composed of a group of defect-related sensors extracted based on a plurality of data acquired from each sensor 31 and a plurality of inspection result data acquired from the inspection machine 30. A basic evaluation model MB showing a range of measured value data by a predetermined sensor 31 up to each process required for production is created (S223).

The evaluation model management machine 10 sets the basic evaluation model BM as an evaluation model up to the stage S for evaluating the measured value of the sensor in the final stage in the defect-related sensor group (S224).

In the defect-related sensor group, the evaluation model management machine 10 maps the evaluation model for up to stage S to the dimension configured by the defect-related sensor group up to one stage before, thereby using the evaluation model MS one stage before. Create (S225).

The evaluation model management machine 10 determines whether or not the evaluation model MS for each stage regarding the defect-related sensor group has been created (S226).

When the evaluation model management machine 10 creates an evaluation model MS for each stage related to the defect-related sensor group, the evaluation model management machine 10 notifies the corresponding stage evaluation machine 11 of the evaluation model MS and the allowable range set for each defect-related sensor. Let it be set (S227).

This embodiment configured in this way also has the same effect as that of the first embodiment. Further, in this embodiment, the evaluation model and the allowable range of measured values are set only for the process (step) that seems to be the cause of the evaluation of the finished product as a defective product. Therefore, according to this embodiment, the evaluation model can be created and updated more efficiently than in the first embodiment, the quality evaluation of the entire production line can be promptly performed, and countermeasures against defective products can be devised. You can also.

The fifth embodiment will be described with reference to FIG. 24. In this embodiment, a case where a plurality of sensors 31 are provided for one or a plurality of steps 21 will be described.

FIG. 24 is a block diagram of the quality evaluation system 1C. The system 1C shown in FIG. 24 has the same configuration as the system 1 described in the first embodiment, but the correspondence between the process 21 and the sensor 31 is different.

In this embodiment, for example, a plurality of sensors 31-1 and sensors 31-2 are provided in the first step 21-1. The sensors 31-1 and 31-2 may be the same type of sensor or different types of sensors. Further, three or more sensors may be provided in step 21.

The measurement timings of the sensor 31-1 and the sensor 31-2 may be the same or different. Sensor 31-1 may measure first, and sensor 31-2 may measure later, or vice versa.

Although a plurality of sensors 31-1 and 31-2 are provided in step 21-1, the stage evaluation machines 11-1 and 11-2 may be provided for each sensor 31-1 and 31-2. ..

In addition, as a process of associating a plurality of sensors, for example, one or more processes such as rearrangement or heating, or one or more inspections are grouped in a predetermined spatial or temporal division. You may assume the process.

This embodiment configured in this way also has the same effect as that of the first embodiment. Further, in this embodiment, since a plurality of sensors can be associated with one or a plurality of processes, the processing state executed in the process can be measured in more detail, and an evaluation model MS suitable for the process can be obtained. Can be created. Therefore, according to this embodiment, it is possible to detect more detailed defects.

The present invention is not limited to each of the above embodiments, and includes various modifications. For example, each of the above embodiments is described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the configurations described. Each embodiment can also be used in combination as appropriate.

Each of the above configurations, functions, processing units, processing means, and the like may be realized by hardware, for example, by designing a part or all of them by an integrated circuit. Further, each of the above configurations, functions, processing units, processing means and the like may be realized in a cloud system by designing a part or all of them in a virtual machine, for example.

Each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be placed in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

The control lines and information lines indicate what is considered necessary for explanation, and do not necessarily indicate all the control lines and information lines in the product. In practice, it can be considered that almost all configurations are interconnected.

Each component of the present invention can be arbitrarily selected, and the invention including the selected configuration is also included in the present invention. Further, the configurations described in the claims can be combined in addition to the combinations specified in the claims.

1,1A, 1B, 1C: Quality evaluation system, 10: Evaluation model management machine, 11: Stage evaluation machine, 12: Measurement data management machine, 21: Process, 30: Inspection machine, 31: Sensor, MB: Basic evaluation model , MS: Stage-by-step evaluation model

Claims (1)

It is a quality evaluation system that evaluates the quality of products produced through multiple processes.
The product is determined to be non-defective based on the data from each sensor that measures the processing status of the product at each inspection stage and the data from the inspection function that finally inspects the product that has completed all of the inspection stages. An evaluation model management function that creates a first evaluation model that indicates the range of data of each sensor and a second evaluation model based on the first evaluation model.
For each inspection stage, a stage-by-stage evaluation function that evaluates the data of a predetermined sensor up to the inspection stage based on the second evaluation model, and
Equipped with
Each of the second evaluation models is from the first evaluation model as a model showing the range of data of the predetermined sensor up to each inspection stage when it is determined to have a predetermined quality in each inspection stage. Has been created and
The evaluation function for each stage is based on whether or not the data of the predetermined sensor up to the inspection stage corresponding to the evaluation function for each stage exists in the second evaluation model corresponding to the evaluation function for each stage. Evaluate and
The data measured by the sensor corresponding to each inspection stage is the stage-by-stage evaluation function corresponding to the inspection stage, another stage-by-stage evaluation function located after the stage-by-stage evaluation function, and the evaluation model management function. Sent to and
The evaluation model management function maps the data of the first evaluation model to a dimension composed of the data of the predetermined sensor corresponding to the second evaluation model to be created, so that the second evaluation model is created. Create an evaluation model and
The evaluation model management function is a predetermined allowable range for comparison with the data of the sensor belonging to the inspection stage corresponding to the evaluation function for each stage, and indicates that the product in the inspection stage has a predetermined quality. The predetermined allowable range is created, and the created predetermined allowable range is transmitted to the evaluation function for each stage.
The evaluation function for each stage corresponds to an independent evaluation for determining whether or not the data of only the sensor in the inspection stage corresponding to the evaluation function for each stage exists within the predetermined allowable range, and the evaluation function for each stage. The combination evaluation for determining whether or not the combination of the data of the predetermined sensor up to the inspection stage is present in the second evaluation model is executed.
The evaluation function for each stage notifies the evaluation model management function of the results of the individual evaluation and the combination evaluation.
The evaluation model management function updates the first evaluation model and the second evaluation model based on the evaluation results notified from the evaluation function for each stage .
The evaluation function for each stage is based on the combination evaluation when it is determined by the single evaluation that the data of only the sensor in the inspection stage corresponding to the evaluation function for each stage exists within the predetermined allowable range. It is determined whether or not a combination of data of the predetermined sensor up to the inspection stage corresponding to each evaluation function exists in the second evaluation model.
Quality evaluation system.

Images