Inference device, machine learning device, and processing system

Abstract

The inference device (3) includes a data acquisition unit (35) that acquires inference data including processing condition time-series data including time-series data indicating a transition of processing conditions applied to the processing machine up to a specific point in time and processing conditions to be used in the next processing, and specific time degradation degree data (D14) indicating a transition of a deterioration degree of a consumable used by the processing machine up to a specific point in time, and an inference unit (36) that infers and outputs the next deterioration degree data from the inference data input from the data acquisition unit (35) using a learning model for inferring next deterioration degree data indicating the deterioration degree of the consumable at the time the next processing is completed from the processing condition time-series data and the specific time degradation degree data (D14).

Description

[Technical field]

[0001] The present disclosure relates to an inference device, a machine learning device, and a processing system that infer the degree of deterioration of a consumable used by a processing machine. [Background technology]

[0002] In machining machines such as wire electric discharge machines, workpieces are machined using consumables such as machining fluid permeable filters. It is desirable to predict the degree of deterioration of these consumables and replace them at an appropriate time based on the predicted degree of deterioration.

[0003] The machine learning device described in Patent Document 1 learns the deterioration degree of consumables used by a processing machine through machine learning. This machine learning device generates a learning model through supervised learning using the machining conditions of electric discharge machining and the deterioration degree of the consumables after electric discharge machining under these machining conditions. Then, a prediction device inputs the machining conditions of electric discharge machining into the generated learning model and predicts the deterioration degree of the consumables after electric discharge machining under these machining conditions. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2021 / 177237 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology of Patent Document 1 does not take into account the transition of processing conditions that affect the deterioration degree of the consumables, and only learns the deterioration degree of the consumables corresponding to the processing conditions used in one processing. Therefore, the technology of Patent Document 1 has a problem that it cannot accurately infer the deterioration degree of the consumables.

[0006] The present disclosure has been made in consideration of the above, and has an object to provide an inference device that can accurately infer the degree of deterioration of a consumable item. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the inference device of the present disclosure includes a data acquisition unit that acquires inference data including processing condition time-series data including time-series data indicating the transition of processing conditions applied to a processing machine up to a specific time point and processing conditions used in a next processing, and specific time degradation degree data indicating the transition of the degradation degree of a consumable used by the processing machine up to a specific time point. The inference device of the present disclosure also includes an inference unit that infers and outputs the next degradation degree data from the inference data input from the data acquisition unit using a learning model for inferring next degradation degree data indicating the degradation degree of the consumable at the time the next processing is completed from the processing condition time-series data and the specific time degradation degree data. Effect of the Invention

[0008] The inference device according to the present disclosure has the effect of being able to infer the degree of deterioration of a consumable with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a configuration of a learning inference system according to an embodiment. [Diagram 2] FIG. 1 is a diagram for explaining a neural network used by a machine learning device according to an embodiment. [Diagram 3] 1 is a flowchart showing a procedure of a learning process executed by a machine learning device according to an embodiment; [Figure 4] 1 is a flowchart showing a procedure of an inference process executed by an inference device according to an embodiment; [Diagram 5] FIG. 1 is a diagram for explaining input data and output data used for learning by a machine learning device according to an embodiment. [Figure 6] FIG. 1 is a diagram for explaining an inference process performed by an inference device according to an embodiment and an inference process of a comparative example; [Figure 7] FIG. 1 is a diagram for explaining the relationship between the accumulated amount of processing waste and the pressure loss of a filtration filter, which is learned by the machine learning device according to the embodiment. [Figure 8] FIG. 1 is a diagram for explaining the relationship between the accumulated amount of processing waste inferred by the inference device according to the embodiment and the pressure loss of a filtration filter. [Figure 9] FIG. 1 is a diagram showing a configuration of a processing system according to an embodiment; [Figure 10] FIG. 1 is a diagram showing an example of the configuration of a processing circuit included in an inference device according to an embodiment when the processing circuit is realized by a processor and a memory. [Figure 11] FIG. 1 is a diagram showing an example of a processing circuit in an inference device according to an embodiment, the processing circuit being configured with dedicated hardware; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An inference device, a machine learning device, and a processing system according to embodiments of the present disclosure will be described below in detail with reference to the drawings.

[0011] Embodiment FIG. 1 is a diagram showing a configuration of a learning inference system according to an embodiment. The learning inference system 1 includes a machine learning device 2, an inference device 3, and a learning model storage unit 5. The inference device 3 is a lifespan prediction device that predicts the lifespan of a consumable by inferring the deterioration level (degree of deterioration) of the consumable. The lifespan of a consumable is the time when replacement of the consumable is recommended, and corresponds to the deterioration level of the consumable.

[0012] The inference device 3 predicts the life of consumables used by machining machines such as wire electric discharge machines, die-sinking electric discharge machines, small-hole electric discharge machines, and laser machining machines. Consumables in wire electric discharge machines include wire electrode wires, filtration filters, ion exchange resins, power supply dies, and electrode wire guide rollers. Consumables in die-sinking electric discharge machines include tool electrodes and filtration filters. Consumables in small-hole electric discharge machines include pipe electrodes and filtration filters. Consumables in laser machining machines include dust collection filters, machining lenses, and bend mirrors.

[0013] In the following, we will explain the case where the machining machine for which the inference device 3 predicts the degree of deterioration of consumables is a wire electric discharge machining machine, but the machining machine for which the inference device 3 predicts the degree of deterioration of consumables may be any type of machining machine.

[0014] In the following, an example of the deterioration level of a consumable item will be described in which the pressure loss of a filter for filtering machining fluid in a wire electric discharge machine is taken as an example. The filter is a machining fluid permeable filter that blocks machining debris mixed in the machining fluid and filters the machining fluid by allowing it to pass through.

[0015] In wire electric discharge machining using a wire electric discharge machine, machining fluid is used to remove machining debris generated during machining. Machining debris that has become mixed into the machining fluid is removed by a filtration filter, and the machining fluid is reused. When machining fluid passes through a filtration filter, a differential pressure occurs between the primary side (upstream side) and secondary side (downstream side). The value of this differential pressure is the pressure loss of the filtration filter. When machining debris accumulates on the filtration filter, the pressure loss increases, and if the pressure loss exceeds a certain value, the filtration filter will burst, so the filtration filter must be replaced before it bursts. The pressure loss of the filtration filter corresponds to the degree of deterioration of the filtration filter, which is a consumable item.

[0016] In the embodiment, learning inference system 1 learns the deterioration level of the filtration filter based on the pressure loss of the filtration filter, and infers the deterioration level of the filtration filter when the next processing is completed.

[0017] In the learning inference system 1, a machine learning device 2 generates a learning model by learning the deterioration degree of a filtration filter, and an inference device 3 infers the deterioration degree of the filtration filter using the learning model.

[0018] The learning model generated by the machine learning device 2 is a learning model for inferring the degree of deterioration of the filtration filter when the next machining is completed, from time series data showing the transition of machining conditions, which are the machining conditions applied to the wire EDM machine, and time series data showing the transition of the accumulated amount of machining waste, which is an example of a physical quantity of a consumable that has a significant impact on the degree of deterioration of the consumable.

[0019] The machine learning device 2 is disposed in a processing machine such as a wire electric discharge machine. The machine learning device 2 may be disposed outside the wire electric discharge machine. The machine learning device 2 includes a schedule creation unit 21, a calculation unit 22, a measurement unit 23, a deterioration degree acquisition unit 24, a data acquisition unit 20, and a model generation unit 27. The data acquisition unit 20 includes an input data acquisition unit 25 and a label acquisition unit 26.

[0020] The schedule creation unit 21 creates data of planned machining conditions including a planned machining speed and a planned machining time (hereinafter, referred to as planned machining condition data D1) to obtain the planned machining condition data D1. The planned machining speed is the planned machining speed in wire electric discharge machining. The planned machining time is the planned machining time in wire electric discharge machining.

[0021] The schedule creation unit 21 may create the planned machining condition data D1, for example, based on a machining program used to control the wire electric discharge machine, or may create the planned machining condition data D1 based on machining conditions set by the user in the wire electric discharge machine.

[0022] The schedule creation unit 21 may create scheduled processing condition data D1 including a processing path length instead of the scheduled processing condition data D1 including a scheduled processing speed and a scheduled processing time. The schedule creation unit 21 may create time-series data of scheduled processing conditions (scheduled processing conditions) instead of the scheduled processing condition data D1. In this case, the scheduled processing condition data D1 includes data of processing conditions from the past up to a specific time point and data of processing conditions scheduled to be performed next time.

[0023] The schedule creation unit 21 sends the planned machining condition data D1 to the calculation unit 22 and the input data acquisition unit 25. The planned machining condition data D1 sent by the schedule creation unit 21 to the input data acquisition unit 25 may include the surface finish accuracy of the workpiece. The surface finish accuracy is the finish accuracy of the surface of the workpiece set for wire electric discharge machining.

[0024] The measurement unit 23 acquires time series data (hereinafter referred to as measurement result time series data D3) of measurement data (measurement results) including the machining speed and machining time actually measured during wire electric discharge machining. The measurement result time series data D3 is data of actual measurements (measurement values) acquired during each machining from the past to a specific point in time. The specific point in time is, for example, the present time. Note that the specific point in time is not limited to the present time, but may be a specific point in the immediate past or a point in the past slightly earlier than the immediate past. The measurement unit 23 acquires the measurement result time series data D3 from the wire electric discharge machine.

[0025] The measurement data included in the measurement result time series data D3 is time series data showing the transition of machining conditions such as machining speed and machining time. The machining conditions (machining speed and machining time) included in the measurement result time series data D3 are actual machining conditions, and the machining conditions (machining speed and machining time) included in the planned machining condition data D1 are planned machining conditions.

[0026] In addition, when the schedule creation unit 21 creates the time series data of the planned processing conditions, the machine learning device 2 may not include the measurement unit 23. The machine learning device 2 may use the planned processing speed and planned processing time included in the time series data of the planned processing conditions created by the schedule creation unit 21, or may use the processing speed and processing time measured by the measurement unit 23. In other words, the machine learning device 2 may use the planned processing conditions as the processing conditions from the past to a specific time point, or may use the actual processing conditions measured by the measurement unit 23. The processing condition time series data includes the time series data indicating the transition of the processing conditions from the past to a specific time point and the processing conditions to be used in the next processing.

[0027] The measurement data may include data on temperature during wire electric discharge machining, data on surface finish accuracy, etc. The measurement unit 23 sends the measurement result time-series data D3 to the calculation unit 22 and the input data acquisition unit 25.

[0028] The calculation unit 22 calculates time-series data of calculation data (calculation results) (hereinafter referred to as calculation result time-series data D2) based on the processing conditions included in the planned processing condition data D1 acquired by the schedule creation unit 21 and the processing conditions (measurement data) included in the measurement result time-series data D3 acquired by the measurement unit 23. The calculation data acquired by the calculation unit 22 through calculation is, for example, the accumulated processing waste amount (accumulated amount of processing waste). The calculation result time-series data D2 is an example of physical quantity time-series data indicating the transition of the physical quantity of the consumable up to a specific point in time.

[0029] The cumulative amount of machining debris is the cumulative amount of machining debris that has been mixed into the machining fluid since the filter was replaced and use of the new filter was started. The cumulative amount of machining debris that has been mixed into the machining fluid corresponds to the cumulative amount of machining debris that has been filtered by the filter.

[0030] The calculation result time series data D2 includes calculation data of the accumulated machining waste amount from the past to a specific time point and calculation data of the accumulated machining waste amount after the next machining to be performed is completed. The accumulated machining waste amount from the past to a specific time point is not only the accumulated machining waste amount at the specific time point, but also the transition of the accumulated machining waste amount from the past to the specific time point.

[0031] The calculation unit 22 calculates, for example, the accumulated amount of machining waste from the product of the machining depth calculated from the surface finishing accuracy, the machining speed, and the machining time. When the calculation unit 22 uses the surface finishing accuracy, data on the surface finishing accuracy is included in the scheduled machining condition data D1 or the measurement result time-series data D3. The calculation unit 22 may calculate the accumulated amount of machining waste from the product of the machining speed and the machining time without using the surface finishing accuracy.

[0032] When the surface finish accuracy is included in the planned machining condition data D1, the surface finish accuracy is the planned surface finish accuracy defined in the machining program, etc. When the surface finish accuracy is included in the measurement result time series data D3, the surface finish accuracy is the surface finish accuracy actually measured after machining.

[0033] The calculation unit 22 uses the machining speed and machining time acquired from the measurement unit 23 for the machining speed and machining time from the past to a specific time point. Also, the calculation unit 22 uses the planned machining speed and planned machining time acquired from the schedule creation unit 21 for the machining speed and machining time of the next machining.

[0034] The accumulated amount of processing waste calculated by the calculation unit 22 increases as the number of processing days increases. The calculation unit 22 calculates the time series data of the accumulated amount of processing waste as the calculation result time series data D2. The calculation unit 22 sends the calculation result time series data D2 to the input data acquisition unit 25.

[0035] The machining speed and machining time from the past to a specific time are, for example, the machining speed and machining time applied between the (TN)th day and the Tth day (specific time), where T and N (T>N) are natural numbers. The next machining speed and machining time are, for example, the planned machining speed and planned machining time applied between the Tth day and the (T+1)th day. The cumulative machining waste amount from the past to a specific time is the cumulative machining waste amount applied between the (TN)th day and the Tth day. The next cumulative machining waste amount is, for example, the cumulative machining waste amount at the time when the machining applied between the Tth day and the (T+1)th day is completed. The Tth day, which is a specific time, is the time when the machining on the Tth day is completed, and the (T+1)th day is the time when the machining on the (T+1)th day is completed. Therefore, the specific time (present) in this embodiment is the time when the Tth day ends.

[0036] In this embodiment, the case where the deterioration level of the filtration filter is learned and inferred on a daily basis will be described, but the deterioration level of the filtration filter may also be learned and inferred on an hourly or minutely basis.

[0037] It is assumed that the processing from the (TN)th day to the (T+1)th day has been executed before the machine learning device 2 generates the learning model. In other words, the machine learning device 2 generates the learning model after the processing from the (TN)th day to the (T+1)th day has been executed.

[0038] The machine learning device 2 acquires in advance the processing speed and processing time from the (TN)th day to the Tth day (specific time point) and the planned processing speed and planned processing time on the (T+1)th day. The reason why the processing speed and processing time on the (T+1)th day are the planned processing speed and planned processing time is that when the deterioration degree of the filtration filter is inferred, the actual processing speed and processing time have not been measured at the time of inference. In other words, since the deterioration degree of the filtration filter is inferred using the planned processing speed and planned processing time during inference, the machine learning device 2 learns the deterioration degree of the filtration filter using the planned processing speed and planned processing time during learning as well.

[0039] Deterioration level acquisition unit 24 acquires time series data (hereinafter referred to as specific time degradation level data D4) of the deterioration level of the filtration filter after each processing from the past to a specific time point. The deterioration level from the past to a specific time point is the deterioration level from the (TN)th day to the Tth day. When the deterioration level of the consumable is the deterioration level of the filtration filter, this deterioration level is the pressure loss of the filtration filter.

[0040] The deterioration level acquiring unit 24 also acquires time-series data (hereinafter, referred to as next deterioration level data D5) of the deterioration level of the filtration filter at the time when the next processing is completed. The next deterioration level is, for example, the deterioration level at the time when the processing on the (T+1)th day is completed.

[0041] The degradation level acquiring unit 24 sends the specific time point degradation level data D4 and the next degradation level data D5 to the data acquiring unit 20. That is, the degradation level acquiring unit 24 sends the specific time point degradation level data D4 to the input data acquiring unit 25, and sends the next degradation level data D5 to the label acquiring unit 26.

[0042] The input data acquisition unit 25 acquires planned processing condition data D1 from the schedule creation unit 21, acquires measurement result time series data D3 from the measurement unit 23, acquires calculation result time series data D2 from the calculation unit 22, and acquires specific point in time deterioration degree data D4 from the deterioration degree acquisition unit 24.

[0043] In this manner, input data acquisition unit 25 acquires the processing conditions, measurement data, accumulated processing waste amount, and pressure loss of the filtration filter. Input data acquisition unit 25 acquires data from day (TN) to day (T+1) from schedule creation unit 21, calculation unit 22, measurement unit 23, and deterioration degree acquisition unit 24. Specifically, input data acquisition unit 25 acquires processing conditions for day (T+1) from schedule creation unit 21, and acquires processing conditions from day (TN) to day T from measurement unit 23. Input data acquisition unit 25 also acquires accumulated processing waste amount from day (TN) to day (T+1) from calculation unit 22, and acquires deterioration degree (pressure loss of the filtration filter) from day (TN) to day T from deterioration degree acquisition unit 24.

[0044] The input data acquiring unit 25 sends the planned processing condition data D1, the measurement result time series data D3, the calculation result time series data D2, and the specific point-in-time degradation degree data D4 to the model generating unit 27 as input data.

[0045] Label acquisition unit 26 acquires next degradation degree data D5, which is the pressure loss of the filtration filter on the (T+1)th day, from degradation degree acquisition unit 24, and sends next degradation degree data D5 to model generation unit 27 as label data (result data).

[0046] In this manner, the data acquiring unit 20 acquires learning data including the planned processing condition data D1, the measurement result time series data D3, the calculation result time series data D2, the specific time degradation degree data D4, and the next degradation degree data D5.

[0047] Model generation unit 27 learns the pressure loss of the filtration filter based on learning data created based on a combination of input data sent from input data acquisition unit 25 and label data sent from label acquisition unit 26. That is, model generation unit 27 learns the pressure loss of the filtration filter based on learning data created based on the processing conditions, measurement data, and calculation data (accumulated processing waste amount) output from input data acquisition unit 25 and the deterioration degree (pressure loss of the filtration filter) acquired by deterioration degree acquisition unit 24. Model generation unit 27 learns the pressure loss of the filtration filter based on learning data created based on a combination of processing data from the past to a specific time point and data of the next processing. Here, the learning data is data in which data of processing from the past to a specific time point and data of the next processing are associated with each other.

[0048] The model generation unit 27 generates a learning model based on the processing conditions from the past to a specific time point and the next time, the accumulated processing waste amount from the past to a specific time point and the next time processing is completed, and the pressure loss of the filtration filter from the past to a specific time point and the next time processing is completed, which are received from the input data acquisition unit 25 and the label acquisition unit 26.

[0049] In this way, model generation unit 27 generates a learning model that predicts the pressure loss of the filtration filter with high accuracy from the machining conditions of the wire electric discharge machine, the accumulated amount of machining waste, and the pressure loss of the filtration filter.

[0050] The learning model generated by the model generation unit 27 is a learning model for inferring the next deterioration degree at the time of completion of the next processing from the processing conditions from the past to the specific time point, the calculation data from the past to the specific time point, the measurement data from the past to the specific time point, the specific time deterioration degree from the past to the specific time point, the next processing conditions, and the next calculation data. In this way, the learning model generated by the model generation unit 27 is a learning model for predicting the deterioration degree of the consumable after processing under the processing conditions to be performed next time.

[0051] For example, if T is 100 and N is 30, the learning model learns the correspondence between the data from the 70th to the 100th day and the data from the 101st day that corresponds to the data from the 70th to the 100th day.

[0052] The model generation unit 27 stores the generated learning model in the learning model storage unit 5. The learning model storage unit 5 may be disposed inside the machine learning device 2, or may be disposed outside the machine learning device 2. The learning model storage unit 5 may be disposed inside the inference device 3. The learning model storage unit 5 may be disposed both inside the machine learning device 2 and inside the inference device 3.

[0053] The learning data used by the model generating unit 27 does not necessarily have to include the calculation data (accumulated amount of machining waste). In this case, the input data acquiring unit 25 does not have to acquire the accumulated amount of machining waste. In addition, the machine learning device 2 does not have to include the calculation unit 22.

[0054] The inference device 3 is disposed in a processing machine such as a wire electric discharge machine. The inference device 3 may be disposed outside the wire electric discharge machine. The inference device 3 includes a schedule creation unit 31, a calculation unit 32, a measurement unit 33, a deterioration degree acquisition unit 34, a data acquisition unit 35, and an inference unit 36.

[0055] The schedule creation unit 31 has a function similar to that of the schedule creation unit 21, and the calculation unit 32 has a function similar to that of the calculation unit 22. In addition, the measurement unit 33 has a function similar to that of the measurement unit 23, and the deterioration level acquisition unit 34 has a function similar to that of the deterioration level acquisition unit 24.

[0056] The schedule creation unit 31 creates data of planned processing conditions including a planned processing speed and a planned processing time (hereinafter, referred to as planned processing condition data D11) to obtain the planned processing condition data D11. The planned processing condition data D11 is the same data as the planned processing condition data D1.

[0057] The schedule creation unit 31 may create the planned machining condition data D11, for example, based on a machining program used to control the wire electric discharge machine, or may create the planned machining condition data D11 based on machining conditions set by the user in the wire electric discharge machine.

[0058] The schedule creation unit 31 may create the scheduled processing condition data D11 including the processing path length instead of the scheduled processing condition data D11 including the scheduled processing speed and the scheduled processing time. The schedule creation unit 31 may also create time-series data of the scheduled processing condition data D11.

[0059] When the schedule creation unit 31 creates the machining condition time-series data, the inference device 3 does not need to include the measurement unit 33. The inference device 3 may use the planned machining speed and planned machining time included in the machining condition time-series data created by the schedule creation unit 31, or may use the machining speed and machining time measured by the measurement unit 33.

[0060] The schedule creation unit 31 sends the planned machining condition data D11 to the calculation unit 32 and the data acquisition unit 35. The planned machining condition data D11 sent by the schedule creation unit 31 to the data acquisition unit 35 may include the surface finish accuracy of the workpiece.

[0061] The measurement unit 33 acquires time-series data (hereinafter referred to as measurement result time-series data D13) of measurement data (measurement results) including machining speeds and machining times actually measured during wire electric discharge machining from the past to a specific point in time. The measurement result time-series data D13 is the same data as the measurement result time-series data D3.

[0062] The measurement result time series data D13 is the measurement data at the time of inference, and the measurement result time series data D3 is the measurement data at the time of learning. The measurement unit 33 acquires the measurement result time series data D13 from the wire electric discharge machine. The measurement data may include data on the temperature during wire electric discharge machining, data on surface finish accuracy, etc. The measurement unit 33 sends the measurement result time series data D13 to the calculation unit 32 and the data acquisition unit 35.

[0063] The calculation unit 32 calculates time-series data of calculation data (calculation results) (hereinafter, referred to as calculation result time-series data D12) based on the processing conditions included in the planned processing condition data D11 acquired by the schedule creation unit 31 and the processing conditions (measurement data) included in the measurement result time-series data D13 acquired by the measurement unit 33. The calculation result time-series data D12 is the same data as the calculation result time-series data D2.

[0064] The calculation unit 32, like the calculation unit 22, calculates, for example, the amount of machining waste from the product of the machining depth calculated from the surface finishing accuracy, the machining speed, and the machining time. When the calculation unit 32 uses the surface finishing accuracy, time-series data of the surface finishing accuracy is included in the planned machining condition data D11 or the measurement result time-series data D13. Note that the calculation unit 32 may calculate the accumulated amount of machining waste from the product of the machining speed and the machining time without using the surface finishing accuracy.

[0065] When the surface finish accuracy is included in the planned machining condition data D11, the surface finish accuracy is the planned surface finish accuracy defined in the machining program, etc. When the surface finish accuracy is included in the measurement result time-series data D13, the surface finish accuracy is the surface finish accuracy actually measured after machining.

[0066] The calculation unit 32 uses the machining speed and machining time acquired from the measurement unit 33 as the machining speed and machining time from the past to a specific time point. Also, the calculation unit 32 uses the planned machining speed and planned machining time acquired from the schedule creation unit 31 as the machining speed and machining time of the next machining.

[0067] The accumulated amount of processing waste calculated by the calculation unit 32 increases as the number of processing days increases. The calculation unit 32 calculates the time series data of the accumulated amount of processing waste as the calculation result time series data D12. The calculation unit 32 sends the calculation result time series data D12 to the data acquisition unit 35.

[0068] The machining speed and machining time from the past to a specific time point are, for example, the machining speed and machining time from the (tn)th day to the tth day (specific time point), where t and n (t>n) are natural numbers. The next machining speed and machining time are, for example, the planned machining speed and planned machining time on the (t+1)th day. The accumulated machining waste amount from the past to a specific time point is the accumulated machining waste amount from the (tn)th day to the tth day. The next accumulated machining waste amount is, for example, the accumulated machining waste amount at the time when machining on the (t+1)th day is completed.

[0069] It is assumed that the processing from the (tn)th day to the tth day has been executed before the inference device 3 infers the deterioration degree of the filtration filter after the next processing. That is, the inference device 3 infers the deterioration degree of the filtration filter on the (t+1)th day after the processing from the (tn)th day to the tth day has been executed. The tth day is, for example, the present, and the (t+1)th day is tomorrow.

[0070] The deterioration level acquiring unit 34 acquires time series data (hereinafter referred to as "specific time deterioration level data D14") of the deterioration level (specific time deterioration level) of the consumables (filtration filters) after each processing from the past to a specific time point. The deterioration level from the past to a specific time point is the deterioration level from the (tn)th day to the tth day. The deterioration level acquiring unit 34 sends the specific time deterioration level data D14 to the data acquiring unit 35.

[0071] The data acquiring unit 35 acquires planned machining condition data D11 from the schedule creating unit 31, acquires measurement result time series data D13 from the measuring unit 33, acquires calculation result time series data D12 from the calculation unit 32, and acquires specific time point deterioration degree data D14 from the deterioration degree acquiring unit 34. In this manner, the data acquiring unit 35 acquires the machining conditions, measurement data, accumulated amount of machining waste, and pressure loss of the filtration filter from the past to a specific time point.

[0072] The data acquiring unit 35 acquires data from the (tn)th day to the (t+1)th day from the schedule creating unit 31, the calculation unit 32, the measurement unit 33, and the deterioration degree acquiring unit 34. Specifically, the data acquiring unit 35 acquires the processing conditions for the (t+1)th day from the schedule creating unit 31, and acquires the processing conditions from the (tn)th day to the tth day from the measurement unit 33. In addition, the data acquiring unit 35 acquires the accumulated processing waste amount from the (tn)th day to the (t+1)th day from the calculation unit 32, and acquires the deterioration degree (pressure loss of the filtration filter) from the (tn)th day to the tth day from the deterioration degree acquiring unit 34.

[0073] The data acquiring unit 35 included in the inference device 3 is a first data acquiring unit, and the data acquiring unit 20 included in the machine learning device 2 is a second data acquiring unit. The data acquiring unit 35 sends inference data including the planned processing condition data D11, the measurement result time-series data D13, the calculation result time-series data D12, and the specific point-in-time degradation degree data D14 to the inference unit 36 ​​as input data.

[0074] The inference unit 36 ​​reads out the learning model from the learning model storage unit 5. The inference unit 36 ​​applies the inference data, which is input data, to the learning model to calculate an inference result corresponding to the input data. That is, the inference unit 36 ​​infers the processing conditions and the accumulated amount of processing waste from the (tn)th day to the (t+1)th day, and the deterioration degree of the filtration filter on the (t+1)th day corresponding to the deterioration degree of the filtration filter from the (tn)th day to the tth day.

[0075] t is a value larger than T. For example, when t is 101 and n is 30, the inference unit 36 ​​uses the learning model to infer the data of the 102nd day corresponding to the data from the 70th day to the 101st day. When t is 200 and n is 50, the inference unit 36 ​​uses the learning model to infer the data of the 201st day corresponding to the data from the 150th day to the 200th day.

[0076] In this way, the inference unit 36 ​​predicts the pressure loss of the filtration filter obtained by using the learning model, and outputs inference data that is the prediction result. That is, the inference unit 36 ​​inputs the processing conditions, the accumulated processing waste amount, and the deterioration degree of the filtration filter acquired from the data acquisition unit 35 into the learning model, thereby inferring the next deterioration degree data D15 that is the deterioration degree (pressure loss) of the filtration filter after the next processing is completed, and can output the next deterioration degree data D15 that is the inference data.

[0077] The inference data used by the inference unit 36 ​​does not necessarily have to include the calculation data (accumulated amount of machining waste). In this case, the data acquisition unit 35 does not have to acquire the accumulated amount of machining waste. Also, the inference device 3 does not have to include the calculation unit 32.

[0078] The machine learning device 2 and the inference device 3 are used to learn the pressure loss of the filtration filter of the processing machine, but may be devices connected to the processing machine via a network and separate from the processing machine. The machine learning device 2 and the inference device 3 may be built into the processing machine. Furthermore, the machine learning device 2 and the inference device 3 may exist on a cloud server.

[0079] The learning algorithm used by the model generation unit 27 may be a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. As an example, a case where a neural network is applied to the model generation unit 27 will be described.

[0080] The model generation unit 27 learns the pressure loss of the filtration filter by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a method in which a learning device is provided with a set of data of input and result (label), and the learning device learns the features of the learning data and predicts the result from the input.

[0081] A neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0082] 2 is a diagram for explaining a neural network used by the machine learning device according to the embodiment. For example, in the case of a three-layered neural network as shown in FIG. 2, when multiple inputs are input to the input layer (X1 to X3), the values ​​are multiplied by weights W1 (shown as w11 to w16 in FIG. 2) and input to the intermediate layer (Y1 to Y2). The results are then further multiplied by weights W2 (shown as w21 to w26 in FIG. 2) and output from the output layer (Z1 to Z3). This output result varies depending on the values ​​of weights W1 and W2.

[0083] The neural network used by the machine learning device 2 learns the deterioration level of the filtration filter corresponding to the input data by so-called supervised learning in accordance with learning data generated based on a combination of the input data and label data acquired by the input data acquiring unit 25 and the label acquiring unit 26. In other words, the neural network used by the machine learning device 2 learns the output data (deterioration level of the filtration filter) corresponding to the input data by so-called supervised learning in accordance with the input data and label data generated based on a combination of the first input and the second input (correct answer) acquired by the input data acquiring unit 25 and the label acquiring unit 26.

[0084] In other words, the neural network learns by adjusting the weights W1 and W2 so that the result output from the output layer after inputting the first input, which is input data, approaches the second input, which is the label data (correct answer).

[0085] In this way, the neural network learns by inputting input data to the input layer and adjusting the weights W1 and W2 so that the result output from the output layer approaches the label data. The neural network learns the correspondence between the input data and the label data, thereby generating a learning model that can output an appropriate deterioration level of the filtration filter corresponding to the label data when the input data is input. In this way, the machine learning device 2 learns a learning model that can output a deterioration level of the filtration filter that is the correct answer when input data such as the accumulated amount of processing waste is input.

[0086] The model generation unit 27 generates a learning model by executing the above-mentioned learning, and outputs the learning model to the learning model storage unit 5. The learning model storage unit 5 stores the learning model output from the model generation unit 27.

[0087] Note that the machine learning device 2 may divide the data from the (tN)th day to the (t+1)th day into multiple parts and perform multiple rounds of machine learning. In other words, when the machine learning device 2 acquires data for L days (L is a natural number), the machine learning device 2 may generate learning data for M times (M is a natural number) from the data for L days and perform machine learning M times.

[0088] For example, when the machine learning device 2 acquires 100 days' worth of data, the machine learning device 2 may divide the 100 days' worth of data into data from the 1st to the 50th days and data from the 50th to the 100th days. In this case, the machine learning device 2 performs machine learning using the data from the 1st to the 50th days as first-round learning data, and performs machine learning using the data from the 51st to the 100th days as second-round learning data.

[0089] When the data from the 1st to the 50th day is the learning data, the degradation degree from the 1st to the 49th day is the specific time degradation degree, and the data on the 50th day is the next degradation degree. Similarly, when the data from the 51st to the 100th day is the learning data, the degradation degree from the 51st to the 99th day is the specific time degradation degree, and the data on the 100th day is the next degradation degree.

[0090] Furthermore, the machine learning device 2 may perform machine learning using the data from the 1st to 50th days as first-round learning data, perform machine learning using the data from the 25th to 75th days as second-round learning data, and perform machine learning using the data from the 50th to 100th days as third-round learning data. In other words, the machine learning device 2 may use the acquired data for multiple machine learning processes.

[0091] Next, a description will be given of a processing procedure for the machine learning device 2 to learn a learning model. Fig. 3 is a flowchart showing the processing procedure for the learning process executed by the machine learning device according to the embodiment.

[0092] The input data acquisition unit 25 and the label acquisition unit 26, which are the data acquisition unit 20, acquire learning data used for learning (step S10). Specifically, the input data acquisition unit 25 acquires the processing conditions (processing speed and processing time) from the (T-1)th day to the Tth day as the measurement result time series data D3. In addition, the input data acquisition unit 25 acquires the planned processing conditions (planned processing speed and planned processing time) for the (T+1)th day as the planned processing condition data D1. In addition, the input data acquisition unit 25 acquires the accumulated processing waste amount from the (T-1)th day to the (T+1)th day as the calculation result time series data D2. In addition, the input data acquisition unit 25 acquires the deterioration degree of the consumables from the (T-1)th day to the Tth day as the specific time deterioration degree data D4. In addition, the label acquisition unit 26 acquires the deterioration degree of the consumables on the (T+1)th day as the next deterioration degree data D5.

[0093] The input data acquiring unit 25 sends the planned processing condition data D1, the measurement result time series data D3, the calculation result time series data D2, and the specific point-in-time degradation degree data D4 as input data to the model generating unit 27. In addition, the label acquiring unit 26 sends the next degradation degree data D5 as label data to the model generating unit 27. A combination of the input data acquired by the input data acquiring unit 25 and sent to the model generating unit 27 and the label data acquired by the label acquiring unit 26 and sent to the model generating unit 27 is learning data.

[0094] In this embodiment, the input data acquisition unit 25 and the label acquisition unit 26 acquire data simultaneously, but it is sufficient that the input data acquisition unit 25 and the label acquisition unit 26 acquire the data in an associated manner. Therefore, the input data acquisition unit 25 and the label acquisition unit 26 may acquire data at different timings. That is, the data acquisition unit 20 (the input data acquisition unit 25 and the label acquisition unit 26) may acquire the planned processing condition data D1, the measurement result time series data D3, the calculation result time series data D2, the specific time degradation degree data D4, and the next degradation degree data D5 at different timings. The input data acquisition unit 25 and the label acquisition unit 26 transmit the acquired data to the model generation unit 27.

[0095] The model generation unit 27 executes a learning process using the input data sent from the input data acquisition unit 25 and the label data sent from the label acquisition unit 26 (step S20). Specifically, the model generation unit 27 learns the label data corresponding to the input data by so-called supervised learning according to learning data generated based on a combination of the input data and the label data acquired by the input data acquisition unit 25 and the label acquisition unit 26, and generates a learning model.

[0096] The input data here includes the following information: - Processing speed and processing time from the past to a specific point in time - Accumulated amount of machining waste from the past to a specific point in time (calculated value) -Pressure loss of a filter from a past time to a specific point in time - Planned processing speed and time for the next processing - Cumulative amount of machining waste at the time the next machining is completed (calculated value)

[0097] The label data here includes the following information: Pressure loss of the filter when the next process is completed

[0098] The model generation unit 27 sends the generated learning model to the learning model storage unit 5. The learning model storage unit 5 stores the learning model generated by the model generation unit 27 (step S30).

[0099] Next, a process procedure of the inference device 3 inferring the pressure loss of the filtration filter at the time when the next processing is completed using the learning model will be described. Fig. 4 is a flowchart showing the process procedure of the inference process executed by the inference device according to the embodiment.

[0100] The data acquiring unit 35 acquires inference data used to infer the pressure loss of the filtration filter at the time when the next processing is completed (step S110). Specifically, the data acquiring unit 35 acquires the processing conditions from the (t-1)th day to the tth day as the measurement result time series data D13. The data acquiring unit 35 also acquires the planned processing conditions for the (t+1)th day as the planned processing condition data D11. The data acquiring unit 35 also acquires the accumulated processing waste amount from the (t-1)th day to the (t+1)th day as the calculation result time series data D12. The data acquiring unit 35 also acquires the deterioration degree of the consumables (such as the pressure loss of the filtration filter) from the (t-1)th day to the tth day as the specific time deterioration degree data D14.

[0101] Although the data acquisition unit 35 acquires the data simultaneously here, it is sufficient that the data acquisition unit 35 acquires the data in an associated manner. Therefore, the data acquisition unit 35 may acquire each piece of data at a different timing. That is, the data acquisition unit 35 may acquire the planned processing condition data D11, the measurement result time series data D13, the calculation result time series data D12, and the specific point-in-time degradation degree data D14 at different timings. The data acquisition unit 35 sends the acquired data to the inference unit 36 ​​as inference data (input data).

[0102] The inference unit 36 ​​acquires data for inference from the data acquisition unit 35. The inference unit 36 ​​also acquires a learning model from the learning model storage unit 5. The inference unit 36 ​​inputs the data for inference to the learning model (step S120), and acquires an inference result (the pressure loss of the filtration filter at the time when the next processing is completed) corresponding to the data for inference.

[0103] The inference unit 36 ​​outputs the inference result, that is, the pressure loss of the filtration filter at the time when the next processing is completed, to a display device (not shown) or the like (step S130). As a result, the display device displays the pressure loss of the filtration filter in the next processing as the life of the consumables (step S140).

[0104] In this embodiment, the inference device 3 infers the pressure loss of the filtration filter using a learning model learned by the machine learning device 2 of the processing machine. However, the inference device 3 may also obtain a learning model from an external source, such as another processing machine, and output the pressure loss of the filtration filter based on this learning model.

[0105] Here, the input data and output data used for learning by the machine learning device 2 will be described. Fig. 5 is a diagram for explaining the input data and output data used for learning by the machine learning device according to the embodiment. The end point of the Tth day in Fig. 5 is a specific point in time (the current point in time).

[0106] The input data input to the model generation unit 27 of the machine learning device 2 includes the machining conditions and calculation data (accumulated machining waste amount) from the (TN)th day to the Tth day, and the machining conditions and calculation data (accumulated machining waste amount) from the end of the Tth day to the (T+1)th day. From the (TN)th day to the Tth day is from the start of the (TN)th day to the end of the Tth day. Moreover, from the end of the Tth day to the (T+1)th day is from the end of the Tth day to the end of the (T+1)th day.

[0107] The input data input to model generation unit 27 includes the deterioration degree of the consumables (pressure loss of the filtration filter) from the (TN)th day to the Tth day. Note that the input data input to model generation unit 27 may also include measurement data (such as temperature) from the (TN)th day to the Tth day.

[0108] Moreover, the model generation unit 27 uses the deterioration degree of the consumable as the label data (actual measurement value). The model generation unit 27 compares the output data (predicted value) output during inference with the label data (actual measurement value), and generates a learning model based on the input data and the label data so that the output data (predicted value) output during inference approaches the label data (actual measurement value).

[0109] This enables the learning model to infer the degree of deterioration of the consumable after the next processing is completed based on the processing conditions and calculation data from the past to a specific point in time that were set at the time of inference, the processing conditions and calculation data after the next processing is completed, and the degree of deterioration of the consumable from the past to a specific point in time.

[0110] Next, an inference process performed by the inference device 3 of the present embodiment and an inference process of a comparative example will be described. Fig. 6 is a diagram for explaining an inference process performed by the inference device according to the embodiment and an inference process of a comparative example.

[0111] 6, a first processing example of the inference processing is shown in the upper part, and a second processing example of the inference processing is shown in the lower part. The second processing example is an example of the inference processing by the inference device 3, and the first processing example is a comparative example of the inference processing.

[0112] In the first processing example, the input data used for inference is data at a specific time point, and in the second processing example, the data used for inference is data from the past up to a specific time point and future data.

[0113] In the first processing example, the degree of deterioration of a consumable after one processing run (pressure loss of the filtration filter) is inferred based on the processing conditions used for one processing run at a specific point in time, and output data (predicted value) that is the inference result is output.

[0114] In the second processing example, the inference device 3 infers the deterioration degree of the consumables after the next processing (here, after the end of the (t+1) day) based on the processing conditions and calculation data (accumulated processing waste amount) from the (tn)th day to the tth day, the processing conditions and calculation data (accumulated processing waste amount) from the end of the tth day to the (t+1)th day, and the deterioration degree of the consumables (pressure loss of the filtration filter) from the (tn)th day to the tth day, and outputs output data (predicted value) that is the inference result.

[0115] In addition, the inference device 3 may infer the deterioration degree of the consumable after the next processing is completed using the next processing conditions and calculation data (accumulated processing waste amount) for one processing cycle after the end of the t day, instead of the processing conditions and calculation data (accumulated processing waste amount) for one processing cycle after the end of the t day up to the (t+1) day.

[0116] In this way, in the second processing example, the inference device 3 infers the degree of deterioration of the consumable after the next processing step using data from the past up to a specific point in time and future data, thereby enabling accurate inference.

[0117] Furthermore, in the second processing example, the inference device 3 infers the degree of deterioration of the consumable after the next processing based on information on a physical quantity that has a significant effect on the degree of deterioration of the consumable (the accumulated amount of processing waste of the filtration filter), thereby enabling accurate inference.

[0118] 7 is a diagram for explaining the relationship between the accumulated amount of processing waste and the pressure loss of a filtration filter learned by the machine learning device according to the embodiment. The horizontal axis of the graph shown in FIG. 7 is the accumulated amount of processing waste V, and the vertical axis is the pressure loss P of the filtration filter.

[0119] FIG. 7 shows a graph in which the relationship between the accumulated processing waste amount V of the filters Fa, Fb, and Fc and the pressure loss P of the filtration filter is plotted for each unit time Δt (e.g., one day). The pressure loss P of the filtration filter increases with the accumulated processing waste amount V, and the accumulated processing waste amount V is a parameter that is highly correlated with the pressure loss P of the filtration filter. This relationship between the accumulated processing waste amount V and the pressure loss P of the filtration filter differs for each of the filters Fa, Fb, and Fc. In other words, the filters Fa, Fb, and Fc are different in at least one of the processing machine in which they are placed, the processing conditions of the processing machine, the user who uses the processing machine, and the processing environment, and as a result, each of them shows different changes.

[0120] In this way, the relationship between the accumulated processing waste amount V and the pressure loss P of the filtration filter is different for each filter Fa, Fb, and Fc. Therefore, even if the accumulated processing waste amount V is determined, the pressure loss P is not necessarily uniquely determined. 0 ) is the same, the pressure loss P may differ for each of the filters Fa, Fb, and Fc.

[0121] In addition, the cumulative amount of machining waste V 0 Even if the pressure loss P is the same for each of the filters Fa, Fb, and Fc, the rate of change (ΔP / ΔV) of the pressure loss P relative to the accumulated amount of machining waste V also differs for each of the filters Fa, Fb, and Fc.

[0122] In Fig. 7, the cumulative amount of machining waste V 0 1. Even if the pressure loss P is the same, the pressure loss P differs for each of the filters Fa, Fb, and Fc, and the rate of change (ΔP / ΔV) of the pressure loss P with respect to the accumulated amount of machining waste V also differs for each of the filters Fa, Fb, and Fc.

[0123] The machine learning device 2 generates a learning model by learning the relationship between the accumulated amount of machining waste V and the pressure loss P of the filtration filter as shown in FIG.

[0124] In addition, if the cumulative amount of machining waste V is determined, the pressure loss P may be uniquely determined. 0If the pressure loss P is the same for each filter when the accumulated amount of machining waste V is the same, the rate of change (ΔP / ΔV) of the pressure loss P with respect to the accumulated amount of machining waste V is also the same for each filter. In this case, the machine learning device 2 may learn the correspondence relationship between the accumulated amount of machining waste V and the pressure loss P. In other words, the machine learning device 2 may generate a learning model without using time-series data.

[0125] In this case, the data acquisition unit 20 of the machine learning device 2 acquires learning data including the accumulated machining waste amount V and the pressure loss P at the time when the next machining is completed. The model generation unit 27 uses the learning data to generate a learning model for inferring the pressure loss P from the accumulated machining waste amount V. In other words, the learning model generated by the model generation unit 27 learns the correspondence relationship between the accumulated machining waste amount and the pressure loss of the filtration filter. In this case, the inference unit 36 ​​infers the pressure loss of the filtration filter from the accumulated machining waste amount by applying the accumulated machining waste amount to the learning model.

[0126] 8 is a diagram for explaining the relationship between the accumulated amount of processing waste inferred by the inference device according to the embodiment and the pressure loss of the filtration filter. The horizontal axis of the graph shown in FIG. 8 is the accumulated amount of processing waste V, and the vertical axis is the pressure loss P of the filtration filter.

[0127] 8 shows a graph in which the relationship between the accumulated processing waste amount V of the filters Fa, Fb, and Fc and the pressure loss P of the filtration filter is plotted for each unit time Δt (e.g., one day), as in Fig. 7. The inference device 3 uses the relationship between the accumulated processing waste amount V from the past to a specific time point and the pressure loss P of the filtration filter as input data for a learning model, and infers the pressure loss P of the filtration filter corresponding to the accumulated processing waste amount V when the next processing is completed.

[0128] 8, the relationship between the accumulated machining waste amount V from the (tn)th day to the tth day and the pressure loss P of the filtration filter, which is indicated by a filled marker, is input data to the inference unit 36. In this embodiment, not only information on the accumulated machining waste amount V on the tth day, which is a specific point in time, but also time-series data on the accumulated machining waste amount V from the specific point in time up to N unit times ago is used as input data to the inference unit 36.

[0129] For example, let V be the time series data of the cumulative amount of machining waste V from the (tn)th day to the (t+1)th day. t-n , V t-n+1 , , ,V t-1 , V t , V t+1 In addition, the time series data of pressure loss P from the (tn)th day to the (t+1)th day is P t-n , P t-n+1 , , P t-1 , P t , P t+1 In addition, the time series data of the processing conditions from the (tn)th day to the (t+1)th day is X t-n , X t-n+1 , , X t-1 , X t , X t+1 Let us assume that.

[0130] In this case, the inference unit 36 ​​receives as input data the time series data of the accumulated machining waste volume V from the (tn)th day to the (t+1)th day, the time series data of the machining conditions from the (tn)th day to the (t+1)th day, and the time series data of the pressure loss P from the (tn)th day to the tth day, and infers the pressure loss P on the (t+1)th day, which is a future point in time one unit time later. That is, the inference unit 36 ​​infers the pressure loss P on the (t+1)th day, which is a future point in time one unit time later. t-n , V t-n+1 , , ,V t-1 , V t , V t+1 And X from (tn)th day to (t+1)th day t-n , X t-n+1 , , X t-1 , X t , X t+1 And P from (tn)th day to tth day t-n , P t-n+1 , , P t-1 , P t So, P on the (t+1)th day t+1 Infer that.

[0131] In this way, the learning model learns the pressure loss P of the filtration filter based on the most recent trend information (increase, decrease, stagnation, etc.), so the inference unit 36 ​​is able to predict the pressure loss P of the filtration filter with high accuracy based on the most recent trend information.

[0132] In this way, since the inference unit 36 ​​can predict the pressure loss P of the filter with high accuracy, the user can arrange for a replacement filter before the filter reaches the end of its life, thereby reducing production loss due to waiting for the delivery of the filter. Furthermore, since the inference unit 36 ​​can predict the pressure loss P of the filter with high accuracy, the user can set an appropriate machining sequence according to the remaining life of the filter. This allows the user to prevent the filter from reaching the end of its life in the middle of machining, thereby optimizing the machining process of the wire electric discharge machining.

[0133] In this embodiment, a case has been described in which supervised learning is applied to the learning algorithm used by the model generating unit 27, but the learning algorithm is not limited to supervised learning. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, etc. can also be applied in addition to supervised learning.

[0134] The model generating unit 27 may learn the pressure loss of the filtration filter according to learning data created for a plurality of processing machines. The model generating unit 27 may acquire learning data from a plurality of processing machines used in the same area, or may learn the pressure loss of the filtration filter using learning data collected from a plurality of processing machines operating independently in different areas. It is also possible to add or remove a processing machine from which learning data is collected during the process. Furthermore, a machine learning device that has learned the pressure loss of the filtration filter for a certain processing machine may be applied to another processing machine, and the pressure loss of the filtration filter for the other processing machine may be re-learned and updated.

[0135] In addition, the learning algorithm used in the model generation unit 27 may be deep learning that learns to extract the features themselves, or machine learning may be performed according to other known methods, such as genetic programming, functional logic programming, and support vector machines.

[0136] In the filter of a wire electric discharge machine, machining debris accumulates as it repeatedly adheres to and peels off. In a wire electric discharge machine, when machining debris accumulates on the filter, the pressure loss of the filter increases. In this case, if the amount of machining debris in the machining fluid increases slowly over time, the amount of machining debris peeling off from the filter increases, and the amount of machining debris accumulating on the filter decreases. On the other hand, if the amount of machining debris in the machining fluid increases rapidly over time, the amount of machining debris peeling off from the filter decreases, and a large amount of machining debris accumulates on the filter.

[0137] In the embodiment, the inference device 3 infers the next deterioration degree using time series data such as the planned machining condition data D11, the measurement result time series data D13, the calculation result time series data D12, and the specific time point deterioration degree data D14. This enables the inference device 3 to infer the next deterioration degree according to the transition of the situation (machining conditions, etc.) that affects the deterioration degree of the consumable. The inference device 3 can infer, for example, the pressure loss according to the transition of the accumulated amount of machining waste and the deposition of machining waste on the filtration filter, so that it becomes possible to accurately infer the next deterioration degree.

[0138] 9 is a diagram showing a configuration of a machining system according to an embodiment. The machining system 100 has a wire electric discharge machine 10. An example of the wire electric discharge machine 10 is a wire electric discharge machine as described above. The wire electric discharge machine 10 has an inference device 3, a machine learning device 2, and a learning model storage unit 5.

[0139] In the wire electric discharge machine 10, the machine learning device 2 generates a learning model using information (learning data) acquired from the wire electric discharge machine 10. This learning model is stored in the learning model storage unit 5. The inference device 3 infers the pressure loss of the filtration filter when the next machining is completed, based on the information (inference data) acquired from the wire electric discharge machine 10 and the learning model read out from the learning model storage unit 5.

[0140] The machine learning device 2 may be disposed outside the wire electric discharge machine 10. Furthermore, the machine learning device 2 may generate a learning model using information acquired from a machining machine other than the wire electric discharge machine 10. Furthermore, the inference device 3 may be disposed outside the wire electric discharge machine 10.

[0141] Furthermore, the learning model storage unit 5 may be disposed outside the wire electric discharge machine 10. The learning model stored in the learning model storage unit 5 may be a learning model generated using information obtained from a machine other than the wire electric discharge machine 10.

[0142] When the machine learning device 2 is disposed outside the wire electric discharge machine 10, the machine learning device 2 is connected to the wire electric discharge machine 10 via a network. When the inference device 3 is disposed outside the wire electric discharge machine 10, the inference device 3 is connected to the wire electric discharge machine 10 via a network. When the learning model storage unit 5 is disposed outside the wire electric discharge machine 10, the learning model storage unit 5 is connected to the machine learning device 2 and the inference device 3 via a network. At least one of the machine learning device 2, the inference device 3, and the learning model storage unit 5 may exist on a cloud server.

[0143] Next, we will explain the hardware configurations of the machine learning device 2 and the inference device 3. Note that the machine learning device 2 and the inference device 3 have similar hardware configurations, so here we will explain the hardware configuration of the inference device 3.

[0144] The inference device 3 is realized by a processing circuit. This processing circuit may be a processor and memory that executes a program stored in a memory, or may be dedicated hardware. The processing circuit is also called a control circuit.

[0145] FIG. 10 is a diagram showing an example of the configuration of a processing circuit in the inference device according to the embodiment, in the case where the processing circuit is realized by a processor and a memory. The processing circuit 90 shown in FIG. 10 is a control circuit, and includes a processor 91 and a memory 92. When the processing circuit 90 is configured using the processor 91 and the memory 92, each function of the processing circuit 90 is realized by software, firmware, or a combination of software and firmware. The software or firmware is described as a program and stored in the memory 92. In the processing circuit 90, each function is realized by the processor 91 reading and executing the program stored in the memory 92. That is, the processing circuit 90 includes a memory 92 for storing an inference program that results in the processing of the inference device 3 being executed. This inference program can also be said to be a program for causing the inference device 3 to execute each function realized by the processing circuit 90. This inference program may be provided by a storage medium in which the program is stored, or may be provided by other means such as a communication medium.

[0146] The inference device 3 is realized by the processor 91 executing an inference program stored in the memory 92. That is, the inference program executed by the inference device 3 has a modular configuration including a schedule creation unit 31, a calculation unit 32, a measurement unit 33, a degradation level acquisition unit 34, a data acquisition unit 35, and an inference unit 36, which are loaded onto a main storage device and generated on the main storage device. The process executed by at least one of the schedule creation unit 31, the calculation unit 32, the measurement unit 33, and the degradation level acquisition unit 34 may be executed by a program other than the inference program.

[0147] The learning program used by the machine learning device 2 has a modular configuration including a schedule creation unit 21, a calculation unit 22, a measurement unit 23, a degradation level acquisition unit 24, an input data acquisition unit 25, a label acquisition unit 26, and a model generation unit 27, which are loaded onto a main storage device and generated on the main storage device. The process executed by at least one of the schedule creation unit 21, the calculation unit 22, the measurement unit 23, and the degradation level acquisition unit 24 may be executed by a program other than the learning program.

[0148] Here, the processor 91 is, for example, a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor), etc. Also, the memory 92 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (Electrically EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc), etc.

[0149] Fig. 11 is a diagram showing an example of a processing circuit in the inference device according to the embodiment, which is configured with dedicated hardware. The processing circuit 93 shown in Fig. 11 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination of these.

[0150] The processing circuits 90, 93 may be partially realized by dedicated hardware and partially realized by software or firmware. In this way, the processing circuits 90, 93 can realize the above-mentioned functions by dedicated hardware, software, firmware, or a combination of these. The inference device 3 may be realized by one processing circuit or multiple processing circuits.

[0151] In this manner, the inference device 3 of the embodiment uses a learning model for inferring the next deterioration degree data at the time when the next processing is completed from the processing condition time-series data and the specific time deterioration degree data D14 to infer the next deterioration degree data from the inference data (processing condition time-series data and specific time deterioration degree data D14) input from the data acquisition unit 35. This allows the inference device 3 to accurately infer the deterioration degree of the consumable based on the processing condition time-series data.

[0152] Moreover, the machine learning device 2 of the embodiment generates a learning model for inferring the next deterioration level data D5 from the processing condition time-series data and the specific time deterioration level data D4, using learning data including the processing condition time-series data, the specific time deterioration level data D4, and the next deterioration level data D5. This enables the machine learning device 2 to generate learning data capable of accurately inferring the deterioration level of the consumable based on the processing condition time-series data.

[0153] In addition, since the machine learning device 2 generates a learning model based on information on physical quantities (such as the accumulated amount of processing waste) that have a significant effect on the deterioration degree of consumables, it is possible to generate a learning model in machine learning with a small amount of data.

[0154] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies. Parts of the configurations may be omitted or modified without departing from the spirit of the invention. [Explanation of symbols]

[0155] 1 learning inference system, 2 machine learning device, 3 inference device, 5 learning model memory unit, 10 wire electric discharge machine, 20, 35 data acquisition unit, 21, 31 schedule creation unit, 22, 32 calculation unit, 23, 33 measurement unit, 24, 34 deterioration degree acquisition unit, 25 input data acquisition unit, 26 label acquisition unit, 27 model generation unit, 36 inference unit, 90, 93 processing circuit, 91 processor, 92 memory, 100 machining system, D1, D11 planned machining condition data, D2, D12 calculation result time series data, D3, D13 measurement result time series data, D4, D14 specific time point deterioration degree data, D5, D15 next deterioration degree data, Fa, Fb, Fc filter, P pressure loss, V, V 0 Accumulated machining waste volume, weights W1 and W2, and Δt unit time.

Claims

1. A data acquisition unit acquires time-series data of processing conditions, including processing conditions used in the next processing step, and inference data, including time-series data showing the progression of processing conditions applied to the processing machine up to a specific point in time, and processing conditions used in the next processing step, as well as specific point-in-time degradation data showing the progression of the degradation of consumables used in the processing machine up to a specific point in time. An inference unit that uses a learning model for inferring next-generation degradation data, which indicates the degree of degradation of the consumable at the time the next processing is completed, from the processing condition time-series data and the degradation degree data at a specific point in time, to infer and output the next-generation degradation data from the inference data input from the data acquisition unit, Equipped with, An inference device characterized by the following features.

2. The inference data further includes data on the physical quantities of the consumables calculated based on the processing conditions. The training data used when generating the aforementioned learning model includes the time-series data of processing conditions, the data on the degree of deterioration at a specific point in time, the data on the degree of deterioration for the next time, and the data on the physical quantities. The inference unit, Using a learning model for inferring the next degradation degree data from the processing condition time series data, the degradation degree data at a specific point in time, and the physical quantity data, the next degradation degree data is inferred from the inference data input from the data acquisition unit. The inference device according to feature 1.

3. The data for the physical quantity includes time-series data of the physical quantity showing its progression up to a specific point in time, and the physical quantity at the time when the next processing is completed. The inference device according to feature 2.

4. The aforementioned machining equipment is a wire electrical discharge machine, The aforementioned consumable is a filter that removes processing debris mixed into the processing fluid. The aforementioned physical quantity data represents the cumulative amount of processing debris mixed into the processing fluid. The degree of deterioration of the aforementioned consumable is the pressure loss of the filtration filter. The inference device according to feature 2 or 3.

5. A data acquisition unit acquires learning data including time-series data showing the progression of processing conditions applied to a processing machine up to a specific point in time, processing condition time-series data including processing conditions used in the next processing, specific point in time degradation data showing the progression of the degradation of consumables used by the processing machine up to a specific point in time, and next degradation data showing the degradation of the consumables at the time the next processing is completed. A model generation unit generates a learning model for inferring the next degradation degree data from the processing condition time series data and the degradation degree data at a specific point in time, using the aforementioned training data. Equipped with, A machine learning device characterized by the following features.

6. The aforementioned training data includes data on the physical quantities of the consumables calculated based on the processing conditions. The model generation unit uses the training data to generate a training model for inferring the next degradation degree data from the processing condition time series data, the physical quantity data, and the degradation degree data at a specific time point. The machine learning apparatus according to feature 5.

7. The data for the physical quantity includes time-series data of the physical quantity showing its progression up to a specific point in time, and the physical quantity at the time when the next processing is completed. The machine learning apparatus according to feature 6.

8. The processing conditions used in the following processing are the planned processing conditions. A machine learning device according to any one of claims 5 to 7.

9. The time-series data showing the changes in the aforementioned processing conditions up to a specific point in time represents either the planned processing conditions or the measured actual processing conditions. A machine learning device according to any one of claims 5 to 7.

10. The aforementioned machining equipment is a wire electrical discharge machine, The aforementioned consumable is a filter that removes processing debris mixed into the processing fluid. The aforementioned physical quantity data represents the cumulative amount of processing debris mixed into the processing fluid. The degree of deterioration of the aforementioned consumable is the pressure loss of the filtration filter. The machine learning apparatus according to claim 6 or 7.

11. Processing machine and An inference device for inferring the degree of deterioration of consumables used in the aforementioned processing machine, It has, The inference device is A first data acquisition unit acquires time-series data of processing conditions, including time-series data showing the progression of processing conditions applied to the processing machine up to a specific point in time and processing conditions used in the next processing, and inference data including specific point-in-time degradation degree data showing the progression of the degradation degree of the consumables up to a specific point in time. An inference unit that uses a learning model for inferring next-generation degradation data, which indicates the degree of degradation of the consumable at the time the next processing is completed, from the processing condition time-series data and the degradation degree data at a specific point in time, to infer and output the next-generation degradation data from the inference data input from the first data acquisition unit, Equipped with, A processing system characterized by the following:

12. The system further comprises a learning device that generates the aforementioned learning model, The learning device is A second data acquisition unit acquires learning data including the processing condition time series data, the degradation degree data at a specific point in time, and the next degradation degree data. A model generation unit that generates the learning model using the aforementioned training data, Equipped with, The processing system according to feature 11.

Images