Program, information processing method, and vacuum heat treatment system

Abstract

To provide a program and the like capable of efficiently deriving quality data of an object to be heat treated when performing a heat treatment on the object to be heat treated in a vacuum heat treatment furnace.SOLUTION: The program is configured for a computer to obtain object data relating to the object to be heat treated in a vacuum heat treatment furnace, and obtain operation data of the vacuum heat treatment furnace when heat treating the object to be heat treated in the vacuum heat treatment furnace, then execute a process for deriving quality data of the object to be heat treated during the heat treatment, based on the object data and the operation data having been obtained.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a program, an information processing method, and a vacuum heat treatment system. [Background technology]

[0002] A known vacuum heat treatment furnace includes a furnace body with a treatment space for the workpieces formed by furnace walls, a heating device for heating the workpieces installed in the furnace body, a cooling gas supply device for supplying cooling gas into the treatment space, a first refrigerant circulation system for cooling the workpieces via the cooling gas using a heat exchanger installed in the treatment space, and a decompression device for decompressing the treatment space (see, for example, Patent Document 1). In the vacuum heat treatment furnace described in Patent Document 1, the workpieces are loaded into the furnace body through an opening in the furnace body, the opening is closed, the furnace body is evacuated, and the workpieces are heated and heat-treated. After that, gas is introduced into the furnace body and the cooling gas is cooled to cool the workpieces. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-216344 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the vacuum heat treatment furnace of Patent Document 1 does not take into consideration the derivation of quality data of the heat treatment object in a series of heat treatment processes including a heating step and a cooling step.

[0005] The present invention has been made in consideration of the above circumstances, and aims to provide a program or the like that can efficiently derive quality data of an object to be heat-treated when the object is heat-treated in a vacuum heat treatment furnace. [Means for solving the problem]

[0006] The program according to this embodiment causes a computer to acquire object data relating to an object to be heat-treated using a vacuum heat treatment furnace, acquire operation data of the vacuum heat treatment furnace when the object to be heat-treated is heat-treated using the vacuum heat treatment furnace, and execute a process of deriving quality data of the object to be heat-treated during the heat treatment based on the acquired object data and operation data.

[0007] The information processing method of this aspect acquires object data related to an object to be heat-treated using a vacuum heat treatment furnace, acquires operation data of the vacuum heat treatment furnace when the object to be heat-treated is heat-treated using the vacuum heat treatment furnace, and causes a computer to execute a process of deriving quality data of the object to be heat-treated during the heat treatment based on the acquired object data and operation data.

[0008] The vacuum heat treatment system of this embodiment is a vacuum heat treatment system that includes a vacuum heat treatment furnace for heat-treating a heat treatment object, and an information processing device, wherein the information processing device acquires object data related to the heat treatment object, acquires operation data of the vacuum heat treatment furnace when the heat treatment object is heat-treated by the vacuum heat treatment furnace, and derives quality data of the heat treatment object during heat treatment based on the acquired object data and operation data. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a program or the like that efficiently derives quality data of an object to be heat-treated when the object is heat-treated in a vacuum heat treatment furnace. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing an example of the configuration of a vacuum heat treatment system according to a first embodiment. [Figure 2] FIG. 1 is a diagram illustrating an example of the configuration of an information processing device included in a vacuum heat treatment system. [Figure 3] 2 is a functional block diagram illustrating functional units included in a control unit of the information processing device. FIG. [Figure 4] 10 is a flowchart illustrating a processing procedure performed by a control unit of an information processing device. [Figure 5] FIG. 10 is a diagram illustrating an example of a management screen of a vacuum heat treatment furnace. [Figure 6] FIG. 10 is an explanatory diagram illustrating an example of a quality index model according to the second embodiment. [Figure 7] 10 is a flowchart illustrating a processing procedure performed by a control unit of an information processing device. [Figure 8] 10 is a flowchart illustrating a processing procedure by a control unit of an information processing device according to a third embodiment (recovery processing). [Figure 9] FIG. 10 is an explanatory diagram showing an example of an assumed quality model according to the fourth embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a management screen of a vacuum heat treatment furnace.

[0011] (Embodiment 1) Hereinafter, embodiments of the present invention will be described. FIG. 1 is a diagram showing an example of the configuration of a vacuum heat treatment system S according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of an information processing device 2 included in the vacuum heat treatment system S. The vacuum heat treatment system S includes a vacuum heat treatment furnace 1 that heat-treats a heat treatment object W, and an information processing device 2 that derives quality data (degree of quality abnormality) of the heat treatment object W during or immediately after the heat treatment based on operation data of the vacuum heat treatment furnace 1. The information processing device 2 is communicably connected to a product information server SS that stores and manages object data (product data) including the dimensions, material, etc. of the heat treatment object W. The information processing device 2 acquires the object data (product data) of the heat treatment object W from the product information server SS.

[0012] The vacuum heat treatment furnace 1 includes a furnace body 11, an in-furnace heater 12, a vacuum pump 13, and an in-furnace cooling fan 14. The furnace body 11 has, for example, a cylindrical shape, and a treatment space (treatment chamber) for the heat treatment object W is formed inside by the furnace wall.

[0013] A plurality of temperature sensors 101 and pressure sensors 102 are provided inside the furnace body 11 (processing chamber), and the temperature (furnace temperature) and pressure (furnace pressure, degree of vacuum) at a plurality of points inside the furnace body 11 are detected by these temperature sensors 101 and pressure sensors 102. The temperature sensors 101 and pressure sensors 102 are communicably connected to an information processing device 2, and the information processing device 2 acquires the detected values ​​(furnace temperature) from each of the temperature sensors 101. The sensor values ​​detected by these temperature sensors 101 and pressure sensors 102 may be acquired from a data logger connected to the temperature sensors 101, etc.

[0014] The furnace heater 12 is provided, for example, along the inner wall surface of the furnace body 11, and functions as a heating device for heating the object W to be heat-treated.

[0015] The vacuum pump 13 is in communication with the furnace body 11 via a pipe inserted through the furnace body 11, and functions as a pressure reducing device that reduces the internal pressure of the furnace body 11 (furnace pressure, degree of vacuum).

[0016] The in-furnace cooling fan 14 is in communication with the furnace body 11 via a pipe inserted through the furnace body 11, and functions as a cooling gas supply device that blows a cooling gas such as nitrogen into the inside (processing chamber) of the furnace body 11. Each of the peripheral devices such as the in-furnace heater 12, the vacuum pump 13, and the in-furnace cooling fan 14 is provided with a current sensor 103 that detects the value of a current flowing through the peripheral device, and the detected value (current value) from the current sensor 103 may be output to the information processing device 2.

[0017] The vacuum heat treatment furnace 1 operates the furnace heater 12, vacuum pump 13, and furnace cooling fan 14 under the control of a control panel or a PLC (Programmable Logic Controller), and performs heating and cooling processes according to various heat treatments such as quenching, tempering, and annealing in a nitrogen atmosphere at a predetermined vacuum level.

[0018] As described above, the information processing device 2 acquires the in-furnace temperature and degree of vacuum (in-furnace pressure) output from the temperature sensor 101 and pressure sensor 102 provided in the furnace body 11 as operation data of the vacuum heat treatment furnace 1. Furthermore, the information processing device 2 acquires, as equipment data, current values ​​flowing through peripheral devices such as the vacuum pump 13 and the in-furnace cooling fan 14 from the current sensors 103 provided in these peripheral devices. Furthermore, if vibration sensors are provided in the peripheral devices such as the vacuum pump 13 and the in-furnace cooling fan 14, the information processing device 2 may acquire vibration data of each peripheral device as equipment data. The sensor value detected by the current sensor 103 may be acquired via a relay device (IoT gateway) connected to the current sensor 103.

[0019] The information processing device 2 periodically, regularly, or steadily acquires operation data, including the temperature inside the furnace and the degree of vacuum, during the heat treatment process of the heat treatment object W in the vacuum heat treatment furnace 1. The information processing device 2 derives quality data (quality index) indicating the quality of the heat treatment object W based on the sequentially acquired operation data and object data (product data) of the heat treatment object W acquired from the product information server SS. The information processing device 2 may also acquire equipment data, including current values ​​and vibration data of peripheral devices, along with the operation data, and derive quality data (quality index) indicating the quality of the heat treatment object W based on the object data, operation data, and equipment data. The information processing device 2 may also acquire alarm information from a PLC or the like. The alarm information is, for example, a signal or data indicating an equipment abnormality such as a cooling water supply abnormality or overheating. The information processing device 2 may also derive quality data (quality index) indicating the quality of the heat treatment object W based on the operation data, equipment data, and alarm information.

[0020] The information processing device 2 may be, for example, an edge computer, a personal computer, or a server device, and may also function as a control panel or a programmable logic controller (PLC) that controls the operation of the vacuum heat treatment furnace 1. Alternatively, the PLC or the like that controls the operation of the vacuum heat treatment furnace 1 may be provided as a separate device from the information processing device 2, and the information processing device 2 may communicate with the PLC via the communication unit 6 to acquire operation data such as the temperature and degree of vacuum (furnace pressure) inside the furnace and equipment data such as the current value of the furnace heater 12, etc. In this case, the information processing device 2 may be, for example, a cloud server connected to an external network such as the Internet, and may function as a central server that communicates with each of the vacuum heat treatment furnaces 1 (PLCs) installed at multiple production sites and acquires operation data and derives quality data (quality indicators) for each of the multiple vacuum heat treatment furnaces 1.

[0021] The information processing device 2 includes a control unit 3, a memory unit 4, a communication unit 6, and an input / output I / F 5, and communicates with various sensors such as a temperature sensor 101, a PLC, and external servers such as a product information server SS via the communication unit 6 or the input / output I / F 5.

[0022] The control unit 3 has one or more central processing units (CPUs), micro-processing units (MPUs), graphics processing units (GPUs), or other processing devices with timing functions, and performs various processes or controls related to the derivation of quality data by reading and executing a program P (program product) stored in the memory unit 4.

[0023] The storage unit 4 includes a volatile storage area such as a static random access memory (SRAM), a dynamic random access memory (DRAM), or a flash memory, and a non-volatile storage area such as an EEPROM or a hard disk. The storage unit 4 pre-stores a program P (program product) and data referenced during processing. The program P stored in the storage unit 4 may be a program P (program product) read from a recording medium readable by the control unit 3. Alternatively, the program P (program product) may be downloaded from an external computer (not shown) connected to a communication network (not shown) and stored in the storage unit 4. The storage unit 4 also stores a quality DB 40 that stores acquired object data, operational data, and derived quality data. Furthermore, the storage unit 4 may store entity files of the learning model (described later), for example, as modules of the program P.

[0024] The communication unit 6 is, for example, a communication module or communication interface conforming to the Ethernet (registered trademark) standard, and an Ethernet cable is connected to the communication unit 6. The communication unit 6 is not limited to being a wired communication module such as an Ethernet cable, but may be a communication interface compatible with wireless communication such as a short-range wireless communication module such as Wi-Fi (registered trademark) or Bluetooth (registered trademark), or a wide-area wireless communication module such as 4G or 5G.

[0025] The input / output I / F 5 is a communication interface that complies with a communication standard such as RS232C or USB. An input device such as a keyboard or a display device 51 such as a liquid crystal display is connected to the input / output I / F 5. The input / output I / F 5 may include an Ethernet communication module or the like.

[0026] 3 is a functional block diagram illustrating functional units included in the control unit 3 of the information processing device 2. The control unit 3 of the information processing device 2 executes a program P stored in the storage unit 4, thereby functioning as an acquisition unit 31, an item identification unit 32, a suitability determination unit 33, an index generation unit 34, and an output unit 35.

[0027] The acquisition unit 31 acquires a work form including the type of heat treatment and the model number of the heat treatment object W, and operation data. The acquisition unit 31 acquires the work form when starting the heat treatment process. The acquisition of the work form may be performed, for example, by acquiring data of the work form read by a barcode reader or the like connected to the input / output I / F 5 of the information processing device 2.

[0028] The work slip contains the type of heat treatment and the model number of the heat treatment object W, which allows the heat treatment object W and the type of heat treatment to be identified. The acquisition unit 31 outputs the type of heat treatment and the model number of the heat treatment object W contained in the work slip to the item identification unit 32. After the heat treatment process has started, the acquisition unit 31 periodically acquires operation data (furnace temperature, vacuum level) output from the temperature sensor 101 and pressure sensor 102 provided in the furnace body 11.

[0029] The item specifying unit 32 specifies quality confirmation items (check items) for the heat treatment object W during the heat treatment process based on the type of heat treatment and the model number of the heat treatment object W from the acquiring unit 31. There are multiple quality confirmation items (check items) to be specified, and a checklist for the quality of the heat treatment object W is generated from these multiple quality confirmation items (check items).

[0030] The checklist may be, for example, a checklist template prepared for each model number or classification of the heat treatment object W. Alternatively, the checklist may be one in which the quality confirmation items (check items) included in the checklist are specified for each type of heat treatment (tempering, quenching, annealing), for example. Checklist templates are prepared for each classification of the heat treatment object W or each type of heat treatment, and these checklist templates are stored in advance in the storage unit 4.

[0031] The item identification unit 32 identifies the heat treatment object W based on the model number, product number, or part number of the heat treatment object W included in the work slip, accesses the product information server SS, and acquires object data (product data) including dimensional data and material of the identified heat treatment object W. The object data (product data) is, for example, CAD data or specification data of the heat treatment object W.

[0032] The item identification unit 32 may use the acquired object data (product data) to identify parameters for each quality check item (check item). The parameters are values ​​used as judgment values ​​for determining whether or not a quality check item (check item) is met. That is, a checklist consisting of multiple quality check items (check items) includes quality check items (check items) determined by the type of heat treatment, and judgment values ​​(parameters) for determining whether or not the quality check item is met, which are determined according to the material and dimensions of the heat treatment object W. As a result, a checklist is derived for each type of heat treatment that is tailored to the material and dimensions of each individual heat treatment object W.

[0033] When identifying parameters corresponding to the material and dimensions of the heat treatment object W and deriving a checklist, the item identifying unit 32 may identify the parameters corresponding to the material and dimensions of the heat treatment object W based on parameters (reference parameters) of a reference object (primitive model). The item identifying unit 32 may calculate a ratio or conversion coefficient of dimensions, etc. between the primitive model and the heat treatment object W, and identify the judgment value (parameter) of the heat treatment object W by applying the ratio, etc. to the reference parameters (reference judgment value) of the primitive model. The item identifying unit 32 outputs the generated checklist (plurality of quality check items and judgment values) to the suitability determining unit 33.

[0034] The suitability determination unit 33 determines suitability of the checklist generated by the suitability determination unit 33, i.e., the suitability of each of the multiple quality check items, based on the operation data (furnace temperature, degree of vacuum) from the acquisition unit 31. That is, for each of the multiple check items included in the checklist, the suitability determination unit 33 outputs a suitability determination for each of these check items, i.e., a determination result indicating conformance or non-conformance, based on the furnace temperature and furnace pressure (degree of vacuum) during heat treatment in the vacuum heat treatment furnace 1.

[0035] The acquisition unit 31 periodically, cyclically, or steadily acquires the furnace temperature and pressure during heat treatment in the vacuum heat treatment furnace 1 and sequentially outputs them to the suitability assessment unit 33. Based on the acquired time series of furnace temperatures and pressures, the suitability assessment unit 33 calculates, for example, the temperature change rate, temperature change velocity, pressure change rate, or pressure change velocity over time within a predetermined period during which both the temperature and pressure are equal to or greater than a threshold value. Alternatively, the suitability assessment unit 33 may calculate the temperature change rate, temperature change velocity, pressure change rate, or pressure change velocity over time within a predetermined period during which both the temperature and pressure are less than a threshold value. The temperature change rate indicates, for example, the rate of change (T2-T1 / T1) of temperature (T2) after a predetermined period from the temperature (T1) at a reference point in time. The temperature change rate is, for example, the temperature difference (ΔT) between two points in time divided by the time interval (s) between the two points in time (ΔT / s). It corresponds to the heating rate when the temperature rises and the cooling rate when the temperature drops. Alternatively, the suitability assessment unit 33 may calculate an accumulated excess temperature amount and an accumulated excess pressure amount, which are calculated by integrating the excess amounts over the thresholds during a predetermined period in which both the temperature and pressure exceed the thresholds. Alternatively, the suitability assessment unit 33 may measure the time (high-temperature holding time) during which a predetermined high-temperature state is maintained during the transition from the heating process to the cooling process. In this way, the suitability assessment unit 33 calculates various values ​​(individual operating data) indicating the operating status of the vacuum heat treatment furnace 1 using the operating data (furnace temperature and furnace pressure) sequentially acquired multiple times during the heat treatment using the vacuum heat treatment furnace 1. In the above embodiment, the suitability determination unit 33 calculates the above-mentioned temperature change rate, etc. (individual operation data) based on the acquired time series of multiple furnace temperatures and furnace pressures, for example, during a predetermined period in which both the temperature and the pressure are equal to or greater than a threshold value or less than a threshold value. However, this is not limited to this. The suitability determination unit 33 may calculate the above-mentioned temperature change rate, etc. (individual operation data) during a predetermined period in which at least one of the temperature and the pressure is equal to or greater than a threshold value or less than a threshold value. Alternatively, the suitability determination unit 33 may calculate the above-mentioned temperature change rate, etc. (individual operation data) during a predetermined period in which one of the temperature and the pressure is equal to or greater than a threshold value and the other is less than the threshold value.That is, the suitability determination unit 33 may calculate the above-mentioned temperature change rate, etc. (individual operating data) based on (in response to) the result of comparing at least one parameter (value) of temperature, pressure, etc. with a threshold value.

[0036] The suitability determination unit 33 compares these calculated or measured values ​​(individual operation data) with the judgment values ​​defined for the corresponding quality check items (check items) to determine suitability for each check item and derive the result as a conformance result. In making this suitability determination, the suitability determination unit 33 may perform the determination from various perspectives using numerical calculations, logical calculations, etc., such as whether the various calculated or measured values ​​(individual operation data) match the judgment values ​​defined for the corresponding check items, whether they reach the values, or whether they fall within a predetermined range (normal range) based on the values. The suitability determination unit 33 outputs the judgment results for the multiple quality check items to the index generation unit 34. The suitability determination unit 33 sequentially performs judgments for the multiple quality check items and outputs the judgment results in accordance with the operation data sequentially input from the acquisition unit 31.

[0037] The index generating unit 34 associates the judgment result from the pass / fail judgment unit 33 with the quality check item corresponding to the judgment result, and generates (derives) this as quality data (quality index). As described above, the derived quality data (quality index) is data including multiple quality check items (check items). The pass / fail of each of these multiple quality check items is judged based on the operation data acquired up to the present time, depending on the progress of the heat treatment process. That is, during the heat treatment process, these multiple quality check items include judged items whose pass / fail has been judged and unjudged items whose pass / fail has not yet been judged, depending on the progress of the heat treatment process.

[0038] The index generating unit 34 associates the judgment results with the quality check items judged by the suitability judging unit 33 based on the operation data acquired up to the present time for each of the multiple quality check items from the item specifying unit 32, and generates (derives) quality data (quality indexes) indicating that the quality check items for which suitability has not yet been judged are unjudged. The index generating unit 34 outputs the generated quality data (quality indexes) to the output unit 35.

[0039] The output unit 35 generates a management screen (screen data) showing the operating status of the vacuum heat treatment furnace 1 using the quality data (quality index), object data (product data), and operation data (furnace temperature and vacuum level) output from each functional unit, and outputs the management screen (screen data) to, for example, the display device 51 or a mobile terminal of an administrator of the vacuum heat treatment furnace 1. In the present embodiment, the output unit 35 (controller 3 of the information processing device 2) independently generates the management screen (screen data), but this is not limited to this. The output unit 35 may generate the management screen (screen data) in cooperation with another server (screen generation server) separate from the information processing device 2. Alternatively, the output unit 35 may output the object data, operation data, and quality data to a database server (described later) and store the data in the database server. For example, the data storage may trigger the screen generation server to access the database server and generate a management screen (screen data) using the data and output the management screen (screen data) to the display device 51. In other words, each functional unit in this embodiment is not limited to being embodied only by the control unit 3 of the information processing device 2, but may also operate in cooperation with other servers such as a DB server, a screen generation server (application server) that are communicatively connected to the information processing device 2.

[0040] The acquisition unit 31 and the output unit 35 may register various data acquired by their respective functional units in the quality DB 40. For example, the output unit 35 associates operation data (furnace temperature and vacuum level), object data (product data), and quality data (quality indexes) and registers the associated data in the quality DB 40. In this case, for example, the job form number (job form number) may be used as a primary key to associate these pieces of data. In the present embodiment, the quality DB 40 is stored in the storage unit 4 of the information processing device 2, but this is not limited thereto. The quality DB 40 may be stored in a DB server that is a device separate from the information processing device 2. In this case, the information processing device 2 communicates with the DB server to store the object data, operation data, and quality data in the quality DB 40.

[0041] FIG. 4 is a flowchart illustrating a processing procedure performed by the control unit 3 of the information processing device 2. The control unit 3 of the information processing device 2 included in the vacuum heat treatment system S receives an operation from an operator using, for example, a keyboard connected to the input / output I / F 5, and performs the following processing based on the received operation.

[0042] The control unit 3 of the information processing device 2 acquires heat treatment type data relating to the type of heat treatment and object data (product data) relating to the heat treatment object W (S101). The control unit 3 of the information processing device 2 acquires the heat treatment type data included in the work form by acquiring data read by, for example, a barcode reader, and the like. The control unit 3 of the information processing device 2 performs search-based access to the product information server SS using the type of the heat treatment object W, and acquires object data (product data) including the dimensional data and material of the heat treatment object W.

[0043] The control unit 3 of the information processing device 2 identifies quality check items (S102). Based on the heat treatment type data and the object data (product data), the control unit 3 of the information processing device 2 identifies multiple quality check items (check items) and judgment values ​​for determining whether the quality check items are appropriate. These multiple quality check items and judgment values ​​may be derived as a checklist.

[0044] The control unit 3 of the information processing device 2 acquires operation data including the furnace temperature and degree of vacuum (furnace pressure) (S103). The control unit 3 of the information processing device 2 acquires, as operation data, the detection values ​​(furnace temperature, degree of vacuum) output by the temperature sensor 101 and the pressure sensor 102 provided in the furnace body 11. When acquiring the operation data, the control unit 3 of the information processing device 2 may associate the operation data with time information (timestamp) indicating the time or date when the operation data was acquired. The control unit 3 of the information processing device 2 may, for example, buffer multiple pieces of operation data acquired in a predetermined processing unit period and perform the following processes.

[0045] The control unit 3 of the information processing device 2 determines whether the quality check items are met based on the acquired operation data (S104). The control unit 3 of the information processing device 2 calculates values ​​(individual operation data) corresponding to each quality check item (check item) using the acquired operation data, and determines whether each quality check item is met by comparing the calculated values ​​with the judgment values ​​set for the quality check items.

[0046] The control unit 3 of the information processing device 2 derives quality data (quality index) based on the judgment results of suitability for the quality check items (S105). The control unit 3 of the information processing device 2 aggregates the judgment results of suitability for each quality check item and derives quality data (quality index) that associates each quality check item with the judgment result.

[0047] The control unit 3 of the information processing device 2 outputs a management screen that displays the derived quality data (quality index) (S106). The control unit 3 of the information processing device 2 generates a management screen (screen data) that shows the operating status of the vacuum heat treatment furnace 1 using the derived quality data (quality index) and the acquired operation data and object data, and outputs the management screen (screen data) to, for example, the display device 51 or a mobile terminal of an administrator of the vacuum heat treatment furnace 1. In this embodiment, the control unit 3 of the information processing device 2 generates and outputs the management screen (screen data), but this is not limited to this. The control unit 3 of the information processing device 2 may output the derived quality data (quality index) to another server (DB server) different from the information processing device 2, and the other server or an application server communicably connected to the other server may generate and output the management screen (screen data).

[0048] The control unit 3 of the information processing device 2 outputs the management screen (screen data) to the display device 51, and then performs loop processing to execute the processing of S102 again. This makes it possible to sequentially derive quality indices using sequentially acquired operational data at a predetermined cycle, and periodically redisplay (update) the management screen reflecting the sequentially derived quality indices. This makes it possible to output in real time the conformance results for multiple quality check items included in the quality indices, following the progress of the heat treatment process.

[0049] 5 is a diagram illustrating an example of a management screen of the vacuum heat treatment furnace 1. The management screen of the vacuum heat treatment furnace 1 includes, for example, a bibliographic information display area showing various items related to heat treatment by the vacuum heat treatment furnace 1, a quality index display area showing quality data (quality index) in list form, an operation data quality index display area showing operation data (equipment parameters), and an operation data graph display area showing a graph of the progress of the operation data.

[0050] The bibliographic information display area has display fields for displaying the operating status of the vacuum heat treatment furnace 1, the work slip number, the type of heat treatment, the start date and time and elapsed time of the heat treatment process, the product type of the heat treatment object W, the material of the heat treatment object W, and the dimensions. The display field for displaying the dimensions of the heat treatment object W may have a hyperlink set to display a pop-up of CAD data or the like of the heat treatment object W.

[0051] The quality index display area displays, for example, in the form of a checklist, multiple quality check items (check items) for each type of heat treatment according to the material and dimensions of each heat treatment object W. The quality check items include, for example, the temperature change rate, the temperature change rate, the pressure change rate, the exceedance of the threshold temperature, and the exceedance of the threshold pressure, and the calculated operation data values ​​(individual operation data) and the judgment results (OK, NG, unjudged) corresponding to each quality check item are displayed.

[0052] The operation data quality index display area displays operation data such as the current furnace temperature and vacuum level. The operation data graph display area displays multiple operation data (furnace temperature and vacuum level) that are periodically acquired and arranged in chronological order in graph format. The horizontal axis of the operation data graph indicates the elapsed time from the start of the heat treatment process to the present time, and the vertical axis indicates the furnace temperature (left side) and vacuum level (right side). The management screen of the vacuum heat treatment furnace 1 may also display information regarding current values ​​and vibration data of peripheral devices such as the furnace heater 12, vacuum pump 13, and furnace cooling fan 14.

[0053] According to this embodiment, when the heat treatment object W is subjected to heat treatment in the vacuum heat treatment furnace 1, i.e., during the heat treatment process, the information processing device 2 (controller 3) derives quality data (quality index) of the heat treatment object W based on object data including the dimensions and material of the heat treatment object W and operation data including the temperature and degree of vacuum (inner furnace pressure) of the vacuum heat treatment furnace 1. This makes it possible to efficiently derive quality data according to the dimensions, etc. of the heat treatment object W based on the operation data of the vacuum heat treatment furnace 1 during the heat treatment process, and to monitor and evaluate the quality of the heat treatment object W (product) being heat treated in real time.

[0054] According to this embodiment, the information processing device 2 (controller 3) identifies quality check items based on the type of heat treatment (heat treatment type data) and object data including the dimensions and material of the heat treatment object W, thereby efficiently identifying appropriate quality check items corresponding to the type of heat treatment and the heat treatment object W. Each of the multiple quality check items (check items) has a judgment value set to determine whether the item is in compliance or non-compliance. The information processing device 2 (controller 3) determines compliance for each individual quality check item by comparing, collating, or collating various values ​​calculated based on the acquired operational data with the judgment values ​​set for the corresponding quality check item. In this way, the derived quality data (quality index) includes multiple quality check items (check items) and compliance results for each of the quality check items. Therefore, compliance results for multiple quality check items can be output in real time as the heat treatment process progresses.

[0055] According to this embodiment, the information processing device 2 (controller 3) sequentially derives quality data (quality indexes) based on operation data acquired periodically, periodically, or steadily during the heat treatment process (partway through the process) when the heat treatment object W is being heat treated. This allows current quality data to be derived in real time during the heat treatment process based on multiple pieces of operation data consisting of the most recently acquired time series. By continuing to sequentially acquire operation data and sequentially derive quality data, the information processing device 2 (controller 3) can continuously derive (update) quality data (quality indexes) based on the latest operation data as the heat treatment process progresses.

[0056] (Embodiment 2) 6 is an explanatory diagram showing an example of a quality index model 301 according to embodiment 2. The control unit 3 of the information processing device 2 uses training data for the quality index model 301 to train, for example, a neural network. As a result, the control unit 3 of the information processing device 2 receives as input object data (product data) of the heat treatment object W and operation data of the vacuum heat treatment furnace 1 during heat treatment of the heat treatment object W, and generates the quality index model 301 (learning model) that outputs quality data (quality index) of the heat treatment object W.

[0057] The object data (product data) of the heat treatment object W includes, for example, the dimensions and material of the heat treatment object W, and may further include physical property values ​​such as hardness, surface roughness, and magnetism. The operation data of the vacuum heat treatment furnace 1 includes, for example, a plurality of temperatures and degrees of vacuum (inner furnace pressures) inside the furnace, and may further include current values ​​and vibration data of peripheral devices such as the in-furnace cooling fan 14. The operation data may be a group of operation data at a plurality of time points that are sampled periodically within a predetermined period and are arranged in a time series.

[0058] The training data includes question data and answer data, with object data and operation data corresponding to the question data, and quality data (quality index) of the heat treatment object W corresponding to the answer data. The object data of the heat treatment object W and operation data of the vacuum heat treatment furnace 1 are sequentially stored as operation history data, for example, by a data logger, as the vacuum heat treatment furnace 1 operates. The quality data (quality index) of the heat treatment object W can be obtained by aggregating quality confirmation results of products that have undergone a heat treatment process. Using these data, training data for the quality index model 301 can be generated. The dataset of question data and answer data included in the training data for learning a learning model, such as the quality index model 301, is synonymous with the dataset of input data and output data when using the learning model (such as the quality index model 301). Therefore, if a definition is made in one dataset, it naturally applies to the other dataset as well.

[0059] The neural network (quality index model 301) trained using the training data is expected to be used as a program module that is part of artificial intelligence software. The quality index model 301 is used in the information processing device 2 that includes the control unit 3 and memory unit 4 as described above, and when executed by the information processing device 2 that has such calculation processing capabilities, a neural network system is formed. That is, the control unit 3 of the information processing device 2 performs calculations to extract feature quantities of the object data and operation data input to the input layer in accordance with instructions from the quality index model 301 stored in the memory unit 4, and outputs quality data of the heat treatment object W from the output layer.

[0060] The quality index model 301 is configured, for example, by a deep neural network (DNN) and includes an input layer that accepts input of object data and operation data, an intermediate layer that extracts features of the object data and operation data, and an output layer that outputs quality data. The input layer has multiple neurons that accept input of character strings and values ​​contained in the object data and operation data, and passes the input values ​​to the intermediate layer. The intermediate layer is defined using an activation function such as a ReLu function or a sigmoid function, and has multiple neurons that extract features of each input value, and passes the extracted features to the output layer. Parameters of the activation function, such as weighting coefficients and bias values, are optimized using the backpropagation algorithm. The output layer is configured, for example, by a fully connected layer, and outputs information related to quality data based on the features output from the intermediate layer.

[0061] In this way, by inputting object data including the shape and material of the heat treatment object W and operation data of the vacuum heat treatment furnace 1 (furnace temperature and furnace pressure) periodically acquired during the heat treatment into the quality index model 301, it is possible to derive quality data (quality index) at the current time during the heat treatment in real time. Alternatively, the quality index model 301 may output, as quality data (quality index), a quality abnormality degree that quantifies the degree of abnormality in the heat treatment of the heat treatment object W.

[0062] The quality index model 301 may output an estimation result of conformance or non-conformance for each of a plurality of quality index items (quality check items). In this case, the output layer of the quality index model 301 may be configured, for example, with a softmax layer, and each node of the output layer corresponding to each of the plurality of quality index items (quality check items) may output an estimation result of conformance or non-conformance for the quality check item, or a percentage indicating conformance, etc. In this way, by using the quality index model 301 that outputs conformance or non-conformance for each of a plurality of quality index items (quality check items), it is possible to derive the conformance or non-conformance of each of a plurality of quality check items in real time, following the progress of heat treatment on the heat treatment object W.

[0063] The quality index model 301 may include, for example, a different model for each type of heat treatment (tempering, quenching, annealing). That is, the quality index model 301 may include, for example, a quality index model 301 for tempering, a quality index model 301 for quenching, and a quality index model 301 for annealing. The information processing device 2 can improve the accuracy of the quality index to be output by using different quality index models 301 according to, for example, the type of heat treatment included in the work slip.

[0064] In this embodiment, the quality index model 301 is assumed to be a DNN, but is not limited to this, and may be a quality index model 301 constructed using other learning algorithms, such as neural networks other than DNN, transformers, BERT, GPT, RNN (Recurrent Neural Network), LSTM (Long-short term model), CNN, SVM (Support Vector Machine), Bayesian networks, linear regression, regression trees, multiple regression, random forests, and ensembles.

[0065] FIG. 7 is a flowchart illustrating a processing procedure performed by the control unit 3 of the information processing device 2. The control unit 3 of the information processing device 2 acquires heat treatment type data relating to the type of heat treatment and object data (product data) relating to the heat treatment object W (S201). The control unit 3 of the information processing device 2 acquires operation data including the temperature inside the furnace and the degree of vacuum (inside the furnace pressure) (S202). The control unit 3 of the information processing device 2 performs the processes of S201 and S202 similar to the processes of S101 and S103 in the first embodiment.

[0066] The control unit 3 of the information processing device 2 inputs the acquired object data and operation data into a quality index model 301 (learning model) (S203). The quality index model 301 may be a different model for each type of heat treatment (tempering, hardening, annealing). In this case, the control unit 3 of the information processing device 2 may select one of the quality index models 301 for tempering, the quality index model 301 for hardening, and the annealing quality index model 301 according to the type of heat treatment included in the acquired job slip, and use the selected quality index model 301 (the quality index model 301 according to the type of heat treatment).

[0067] The control unit 3 of the information processing device 2 derives quality data (quality index) by acquiring the quality data from the quality index model 301 (S204). The quality index model 301, to which the object data and operation data have been input, outputs the quality data (quality index). The control unit 3 of the information processing device 2 derives the quality data (quality index) by acquiring the quality data (quality index) from the quality index model 301. The quality data (quality index) may be suitability (compliance or non-compliance) for an overall quality index related to the heat treatment of the heat treatment object W. Alternatively, the quality data (quality index) may be a quality abnormality degree that quantifies the degree of abnormality in the heat treatment of the heat treatment object W. Alternatively, the quality data (quality index) may be a determination result of compliance or non-compliance for each of a plurality of quality index items (quality confirmation items).

[0068] The control unit 3 of the information processing device 2 outputs a management screen that displays the derived quality data (quality index) (S205). The control unit 3 of the information processing device 2 performs the process of S205 in the same manner as the process S106 in the first embodiment.

[0069] According to this embodiment, by inputting object data including the shape and material of the heat treatment object W and periodically acquired operating data (furnace temperature and furnace pressure) of the vacuum heat treatment furnace 1 during heat treatment of the heat treatment object W into the quality index model 301, it is possible to efficiently derive the current quality index (quality data) during the heat treatment.

[0070] (Embodiment 3) FIG. 8 is a flowchart illustrating a processing procedure performed by the control unit 3 of the information processing device 2 according to the third embodiment (recovery processing). The control unit 3 of the information processing device 2 acquires heat treatment type data relating to the type of heat treatment and object data (product data) relating to the heat treatment object W (S301). The control unit 3 of the information processing device 2 identifies quality check items (S302). The control unit 3 of the information processing device 2 acquires operation data including the furnace temperature and the degree of vacuum (furnace pressure) (S303). The control unit 3 of the information processing device 2 determines whether the quality check items are met based on the acquired operation data (S304). The control unit 3 of the information processing device 2 derives quality data (quality index) based on the determination result of whether the quality check items are met (S305). The control unit 3 of the information processing device 2 outputs a management screen displaying the derived quality data (quality index) (S306). The control unit 3 of the information processing device 2 performs the processes of S301 and S306 in the same manner as the processes of S101 to S106 in the first embodiment.

[0071] The control unit 3 of the information processing device 2 determines whether recovery processing is necessary based on the derived quality data (quality index) (S307). The derived quality data (quality index) is data including multiple quality check items (check items). The pass / fail of each of these multiple quality check items is determined based on the operation data acquired up to the present time, depending on the progress of the heat treatment process. That is, during the heat treatment process, these multiple quality check items include determined items whose pass / fail has been determined depending on the progress of the heat treatment process, and undetermined items whose pass / fail has not yet been determined.

[0072] The control unit 3 of the information processing device 2 determines whether any quality check items that have been judged to be non-compliant are currently included among the quality check items that have been judged to be non-compliant. If any quality check items have been judged to be non-compliant, the control unit 3 of the information processing device 2 determines that recovery processing is required for the quality check items that have been judged to be non-compliant. If no quality check items have been judged to be non-compliant, i.e., if all quality check items that have been judged to be non-compliant are judged to be compliant, the control unit 3 of the information processing device 2 determines that recovery processing is not required.

[0073] If it is determined that recovery processing is necessary (S307: YES), that is, if there is a quality check item determined to be non-compliant, the control unit 3 of the information processing device 2 executes recovery processing corresponding to the quality check item determined to be non-compliant (S308). In identifying the recovery processing, the control unit 3 of the information processing device 2 may refer to a lookup table (recovery processing table) in which quality check items are associated with recovery processing.

[0074] The recovery process table is stored, for example, in the storage unit 4 of the information processing device 2, and the recovery process to be performed when the quality check item is determined to be non-compliant is stored in association with each quality check item. For example, if the period during which the threshold pressure and threshold temperature defined in any quality check item are exceeded is longer than a predetermined period and the quality check item is determined to be non-compliant, a process of lengthening the high-temperature retention time when transitioning from the heating process to the cooling process is identified as the recovery process.

[0075] The control unit 3 of the information processing device 2 executes the identified recovery process. When executing the identified recovery process, the control unit 3 of the information processing device 2 generates a control signal for executing the recovery process and outputs the generated control signal to peripheral devices such as the furnace heater 12, the vacuum pump 13, or the furnace cooling fan 14 provided in the vacuum heat treatment furnace 1. Alternatively, the control unit 3 of the information processing device 2 may output the generated control signal to a PLC or the like that controls these peripheral devices. When executing the recovery process, the control unit 3 of the information processing device 2 may output to the display device 51 a management screen (screen data) that indicates the correspondence between the quality check items determined to be nonconforming and the contents of the recovery process to be executed.

[0076] If it is determined that the recovery process is not necessary (S307: NO), or after the process of S308, the control unit 3 of the information processing device 2 performs the loop process to execute the process of S303 again, as in the first embodiment.

[0077] According to this embodiment, when the quality data contains a negative judgment result, for example, when any quality check item included in the quality data is nonconforming, the information processing device 2 (controller 3) generates a control signal for executing a recovery process corresponding to the negative judgment result and outputs the control signal to the vacuum heat treatment furnace 1. The recovery process is predetermined for each quality check item. For example, the information processing device 2 (controller 3) may identify the recovery process for the quality check item determined to be nonconforming by referring to a lookup table in which recovery processes to be executed when the quality check item is nonconforming are associated with each quality check item. The information processing device 2 (controller 3) executes the recovery process by outputting the control signal generated in response to the recovery process to, for example, the furnace heater 12, the vacuum pump 13, or the furnace cooling fan 14 provided in the vacuum heat treatment furnace 1. When a computer such as a PLC or control panel that controls the in-furnace heaters 12 and the like installed in the vacuum heat treatment furnace 1 is installed separately from the information processing device 2 that derives the quality data, the information processing device 2 may output a control signal for executing a recovery process to the PLC, etc. By performing an appropriate recovery process in accordance with the quality data (quality index) thus derived in real time, the quality of the heat treatment object W can be efficiently improved.

[0078] (Embodiment 4) 9 is an explanatory diagram showing an example of an expected quality model 302 according to embodiment 4. The control unit 3 of the information processing device 2 causes a neural network to learn based on training data in which a plurality of time-series quality abnormality degrees (quality data) are used as question data and quality abnormality degrees at a plurality of time points in the future are used as answer data. As a result, the control unit 3 of the information processing device 2 constructs (generates) the expected quality model 302 (second learning model) in which a plurality of time-series quality abnormality degrees are used as input and quality abnormality degrees (expected quality data) at a plurality of time points in the future are output.

[0079] The multiple quality abnormality degrees (quality data) in a time series refer to, for example, quality data derived periodically during a heat treatment process. The quality data may be, for example, quality abnormality degrees output by the quality index model 301 of embodiment 2, acquired in a time series. The quality abnormality degrees at multiple future time points refer to quality abnormality degrees (expected quality data) predicted (anticipated) at multiple future time points, such as the point next to the current time point (predetermined time point) and the point after that point.

[0080] The input layer has one or more neurons that receive multiple quality anomaly levels in a time series and passes each input quality anomaly level to the intermediate layer. The intermediate layer includes an autoregressive layer that includes multiple neurons. The autoregressive layer is implemented, for example, as an LSTM (Long Short-Term Memory) model, and a neural network that includes such an autoregressive layer is called an RNN (Recurrent Neural Network). The intermediate layer outputs the amount of change due to each of the multiple quality anomaly levels input sequentially along the time series. The output layer has one or more neurons that output quality anomaly levels at multiple time points in the future and outputs quality anomaly levels at multiple time points in the future based on the amount of change due to each of the multiple quality anomaly levels output from the intermediate layer. Learning for such an RNN is performed using, for example, the BPTT (Backpropagation Through Time) algorithm.

[0081] The training data may be stored in an array format. When the training data is in an array format, for example, the values ​​of the elements from 0 to 4 (t-4 to t) of the array number may be used as question data, and the values ​​of the elements from 5 to 7 (t+1 to t+3) of the array number may be used as answer data. The time-series question data (t-2, t-1, t) input from the input layer is sequentially passed to an LSTM (autoregressive layer), which outputs output values ​​to the output layer and to itself, thereby processing sequence information including temporal changes and order.

[0082] The control unit 3 of the information processing device 2 may, for example, serially connect the quality index model 301 of embodiment 2 and the expected quality model 302 of this embodiment, and sequentially input the quality anomaly degrees consisting of time series sequentially output by the quality index model 301 based on sequentially acquired operation data into the expected quality model 302, thereby deriving the quality anomaly degrees (expected quality data) predicted (assumed) from the present time onwards. The control unit 3 of the information processing device 2 outputs a management screen (screen data) including the derived expected quality data to, for example, the display device 51 or a mobile terminal of the manager of the vacuum heat treatment furnace 1, as in embodiment 1.

[0083] 10 is a diagram illustrating an example of the management screen of the vacuum heat treatment furnace 1. In addition to the areas displayed on the management screen of embodiment 1, the management screen of the vacuum heat treatment furnace 1 in this embodiment further includes a quality abnormality degree display area showing the derivation history of the quality abnormality degree, a quality abnormality degree graph display area showing a graph of the future changes in the quality abnormality degree, and a comment display area showing comments generated based on the predicted (assumed) quality abnormality degree (assumed quality data).

[0084] The quality abnormality degree display area displays, in list form, history information of quality abnormality degrees that have been periodically derived up to the present time (time of derivation, value of the derived quality abnormality degree).

[0085] The quality abnormality degree graph display area displays a graph showing the transition of the derived quality abnormality degree, with the horizontal axis representing elapsed time and the vertical axis representing the quality abnormality degree. The line showing the transition of the quality abnormality degree includes an actual line up to the present time and a forecast line for the future from the present time onwards. The quality abnormality degree (expected quality data) shown by the forecast line is based on values ​​estimated by the expected quality model 302. The graph displays the threshold value of the quality abnormality degree as a dotted line, which improves the visibility of the comparison relationship between the current and future quality abnormality degrees and the threshold value.

[0086] The comment display area displays a comment derived based on the future trend of the quality abnormality degree (prediction line). The control unit 3 of the information processing device 2 may generate the comment based on whether the future quality abnormality degree will exceed the threshold value or not, and the estimated elapsed time until the threshold value is exceeded.

[0087] According to this embodiment, the information processing device 2 (controller 3) sequentially derives multiple quality data during the heat treatment process, thereby continuously outputting multiple time-series quality data. The quality data output in this time series may be a quality abnormality degree indicating the degree of quality abnormality in the heat treatment object W. The information processing device 2 (controller 3) derives predicted (estimated) quality data from the present time onward, i.e., future quality data (estimated quality data), based on the multiple time-series quality data (quality abnormality degrees) continuously output during the heat treatment process, thereby making it possible to grasp the transition or trend of the quality data if the vacuum heat treatment furnace 1 continues to operate in the current control mode.

[0088] The embodiments disclosed herein are illustrative in all respects and should not be considered limiting. The technical features described in each embodiment can be combined with each other, and the scope of the present invention is intended to include all modifications within the scope of the claims and the scope equivalent to the claims. [Explanation of symbols]

[0089] S Vacuum Heat Treatment System SS product information server W Heat treatment object 1. Vacuum heat treatment furnace 11 Furnace body 12 Furnace heater 13 Vacuum pump 14 Furnace cooling fan 101 Temperature Sensor 102 Pressure Sensor 103 Current Sensor 2. Information processing equipment 3. Control Unit 31 Acquisition Department 32 Item Specification Section 33 Compliance Determination Section 34 Index generator 35 Output section 301 Quality Indicator Model (Learning Model) 302 Expected Quality Model (Second Learning Model) 4 Storage section 40 Quality DB 41 Recording Media P Program (Program Product) 5 Input / Output Interface 51 Display device 6. Communications Department

Claims

1. On the computer, Acquire object data for an object to be heat-treated in a vacuum heat treatment furnace, the object data including at least one of dimensions and material of the object to be heat-treated; Acquire operational data regarding the vacuum heat treatment furnace when the heat treatment object is heat-treated by the vacuum heat treatment furnace, the operational data including at least one of an internal temperature and a degree of vacuum of the vacuum heat treatment furnace; deriving quality data of the heat treatment object during the heat treatment based on the acquired object data and operation data; Identifying quality check items based on the acquired object data; The quality data is derived by determining whether the quality check items are met based on the acquired operational data. A program that executes a process.

2. acquiring heat treatment type data relating to the type of heat treatment; Identifying the quality confirmation items based on the acquired heat treatment type data and object data. The program according to claim 1.

3. The judgment result of the suitability of the quality check items is output to a display device connected to the computer so as to be able to communicate with the computer. The program according to claim 1 or 2.

4. The quality data is derived by inputting the acquired object data and operation data into a learning model that has been trained to output quality data when the object data and operation data are input. The program according to any one of claims 1 to 3.

5. When the heat treatment object is heat-treated, operation data of the vacuum heat treatment furnace is sequentially acquired; Deriving the quality data based on the acquired object data and a plurality of sequentially acquired operation data. The program according to any one of claims 1 to 4.

6. When the heat treatment object is heat treated, a plurality of time-series quality data are derived; Derive expected quality data that is expected from the present time onward based on the plurality of quality data. The program according to any one of claims 1 to 5.

7. If the derived quality data includes a negative determination result, a control signal is output to execute a recovery process corresponding to the negative determination result. The program according to any one of claims 1 to 6.

8. Acquire object data for an object to be heat-treated in a vacuum heat treatment furnace, the object data including at least one of dimensions and material of the object to be heat-treated; Acquire operational data regarding the vacuum heat treatment furnace when the heat treatment object is heat-treated by the vacuum heat treatment furnace, the operational data including at least one of an internal temperature and a degree of vacuum of the vacuum heat treatment furnace; deriving quality data of the heat treatment object during the heat treatment based on the acquired object data and operation data; Identifying quality check items based on the acquired object data; The quality data is derived by determining whether the quality check items are met based on the acquired operational data. An information processing method that causes a computer to execute a process.

9. A vacuum heat treatment system including a vacuum heat treatment furnace for heat treating an object to be heat treated and an information processing device, The information processing device includes: Acquire object data for an object to be heat-treated in a vacuum heat treatment furnace, the object data including at least one of dimensions and material of the object to be heat-treated; Acquire operational data regarding the vacuum heat treatment furnace when the heat treatment object is heat-treated by the vacuum heat treatment furnace, the operational data including at least one of an internal temperature and a degree of vacuum of the vacuum heat treatment furnace; deriving quality data of the heat treatment object during the heat treatment based on the acquired object data and operation data; Identifying quality check items based on the acquired object data; The quality data is derived by determining whether the quality check items are met based on the acquired operational data. Vacuum heat treatment system.

Images