Maintenance strategy generation method, system, equipment, medium and product for CNC machine tools

Abstract

The present application discloses a maintenance strategy generation method, system, device, medium and product for CNC machine tools, and relates to the technical field of fault maintenance. The disclosed maintenance strategy generation method for CNC machine tools includes: obtaining the corresponding working status data and working communication data of each person to be assigned, and based on each working communication data, obtaining the corresponding emotional tendency of each person to be assigned; inputting the fault information, each working status data and each emotional tendency of the machine tool to be repaired into a preset reinforcement learning model to obtain the maintenance strategy of the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendency and corresponding actual maintenance strategy in advance. The technical solution of the present application aims to solve the technical problem of how to allocate maintenance work to improve maintenance efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of fault repair, and in particular to a method, system, device, medium and product for generating a maintenance strategy for a CNC machine tool. Background Art

[0002] In the actual execution of maintenance work, although the experience and free time of maintenance personnel are often used as the main basis for allocating maintenance tasks, this allocation strategy has obvious drawbacks due to its single standard and lack of flexibility. Specifically, over-reliance on these allocation criteria often fails to fully adapt to the diversity and dynamic changes of maintenance tasks, resulting in low maintenance efficiency.

[0003] Therefore, how to allocate maintenance work to improve maintenance efficiency is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0004] The main purpose of this application is to provide a maintenance strategy generation method, system, equipment, medium and product for a CNC machine tool, aiming to solve the technical problem of how to allocate maintenance work to improve maintenance efficiency.

[0005] To achieve the above objectives, the present application proposes a maintenance strategy generation method for a CNC machine tool, the method comprising:

[0006] When a machine tool to be repaired is detected, the work status data and work communication data corresponding to each person to be assigned are obtained, and based on each of the work communication data, the emotional tendency corresponding to each person to be assigned is obtained, wherein the work communication data includes data generated by communication between each person to be assigned during the historical maintenance process, and / or data generated by communication between each person to be assigned and the user during the historical maintenance process;

[0007] The fault information of the machine tool to be repaired, the working status data and the emotional tendencies are input into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies and corresponding actual maintenance strategies.

[0008] In one embodiment, the step of obtaining the emotional tendency corresponding to each of the persons to be assigned based on each of the work communication data includes:

[0009] Convert each of the work communication data into communication texts respectively, and detect whether there is a preset emotional feature word in each of the communication texts;

[0010] If it is detected that the preset emotional characteristic word exists in each of the communication texts, determining the number of occurrences of the preset emotional characteristic word in each of the communication texts;

[0011] According to the preset emotional characteristic words and the number of occurrences, the emotional tendency corresponding to each of the persons to be assigned is determined.

[0012] In one embodiment, the maintenance strategy includes maintenance plan, maintenance sequence and personnel allocation information;

[0013] The step of inputting the fault information of the machine tool to be repaired, each of the working status data and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired comprises:

[0014] Determining a maintenance plan corresponding to the fault information of the machine tool to be repaired based on the reinforcement learning model;

[0015] Determine the maintenance order corresponding to each maintenance step according to the preset priority corresponding to each maintenance step in the maintenance plan;

[0016] According to each of the maintenance steps, each of the maintenance sequences, and each of the emotional tendencies, the personnel allocation information is determined.

[0017] In one embodiment, after the step of inputting the fault information of the machine tool to be repaired, each of the working status data, and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, the method further includes:

[0018] Maintaining the machine tool to be maintained according to the maintenance strategy, and acquiring maintenance communication data in real time during the maintenance process, wherein the maintenance communication data includes data generated by communication between a maintenance personnel and other maintenance personnel when maintaining the machine tool to be maintained, and / or data generated by communication between a maintenance personnel and a user when maintaining the machine tool to be maintained;

[0019] Based on the maintenance communication data, a maintenance emotion tendency is obtained, and if it is detected that the maintenance emotion tendency represents a negative maintenance emotion, the personnel allocation information in the maintenance strategy is adjusted;

[0020] The machine tool to be maintained is maintained by using the adjusted maintenance strategy.

[0021] In one embodiment, the step of adjusting the personnel allocation information in the maintenance strategy includes:

[0022] The maintenance step corresponding to the maintenance emotional tendency is taken as the target maintenance step, and based on the emotional tendency corresponding to each of the persons to be assigned, a target maintainer of the target maintenance step is determined from among the persons to be assigned;

[0023] The personnel allocation information corresponding to the target maintenance step in the maintenance strategy is adjusted to the information of the target maintainer.

[0024] In addition, to achieve the above purpose, the present application also proposes a maintenance strategy generation system for a CNC machine tool, the maintenance strategy generation system for a CNC machine tool comprising:

[0025] An acquisition module is used to acquire the work status data and work communication data corresponding to each person to be assigned when detecting the existence of a machine tool to be repaired, and obtain the emotional tendency corresponding to each person to be assigned based on each of the work communication data, wherein the work communication data includes data generated by the communication between each person to be assigned during the historical maintenance process, and / or data generated by the communication between each person to be assigned and the user during the historical maintenance process;

[0026] A generation module is used to input the fault information of the machine tool to be repaired, the working status data and the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies and corresponding actual maintenance strategies.

[0027] In addition, to achieve the above-mentioned purpose, the present application also proposes a maintenance strategy generation device for a CNC machine tool, the maintenance strategy generation device for a CNC machine tool comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the maintenance strategy generation method for a CNC machine tool as described above.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the maintenance strategy generation method for CNC machine tools as described above are implemented.

[0029] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the maintenance strategy generation method for a CNC machine tool as described above are implemented.

[0030] In the present application, when a machine tool to be repaired is detected, the work status data and work communication data corresponding to each person to be assigned are obtained, and based on each of the work communication data, the emotional tendency corresponding to each person to be assigned is obtained, wherein the work communication data includes data generated by communication between each person to be assigned during historical maintenance, and / or data generated by communication between each person to be assigned and the user during historical maintenance, so that the work status corresponding to each person to be assigned, such as whether it is busy, can be obtained, and the communication data of each person to be assigned when performing maintenance work at the current moment can also be obtained, so that the emotional tendency corresponding to each person to be assigned can be obtained according to the work communication data; then the fault information of the machine tool to be repaired, each of the work status data and each of the emotional tendencies are input into a preset reinforcement learning model to obtain the maintenance strategy of the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual work status data, actual emotional tendencies and corresponding actual maintenance strategies, and can generate a maintenance strategy corresponding to the machine tool to be repaired based on the specific fault information of the machine tool and the working status and emotional tendencies of each person to be assigned.

[0031] In this application, the emotional inclination of the person to be assigned can be integrated into the maintenance task allocation process through a reinforcement learning model. This not only enhances the flexibility of task allocation, but also ensures that employees with more positive emotional states are given priority in being assigned to maintenance tasks that require a high level of meticulousness, thereby improving the overall maintenance efficiency of CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0034] Figure 1 A flow chart of a maintenance strategy generation method for a CNC machine tool according to an embodiment of the present invention;

[0035] Figure 2 A flow chart of an embodiment of a method for generating a maintenance strategy for a CNC machine tool according to the present application;

[0036] Figure 3 A flow chart of another embodiment of the method for generating a maintenance strategy for a CNC machine tool of the present application;

[0037] Figure 4 A schematic diagram of the module structure of a maintenance strategy generation system for a CNC machine tool according to an embodiment of the present application;

[0038] Figure 5 It is a schematic diagram of the equipment structure of the hardware operating environment involved in the maintenance strategy generation method for CNC machine tools in the embodiment of the present application.

[0039] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0040] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0041] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0042] The main solution of the embodiment of the present application is: when a machine tool to be repaired is detected, the work status data and work communication data corresponding to each person to be assigned are obtained, and based on each of the work communication data, the emotional tendency corresponding to each person to be assigned is obtained, wherein the work communication data includes data generated by communication between each person to be assigned during the historical maintenance process, and / or data generated by communication between each person to be assigned and the user during the historical maintenance process; the fault information of the machine tool to be repaired, each of the work status data and each of the emotional tendencies are input into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual work status data, actual emotional tendencies and corresponding actual maintenance strategies.

[0043] Nowadays, the allocation of tasks based on experience and free time often cannot fully adapt to the diversity and dynamic changes of maintenance tasks, resulting in low maintenance efficiency. To solve the above technical problems, this application proposes a maintenance strategy generation method for CNC machine tools.

[0044] It should be noted that the execution subject of the maintenance strategy generation method for CNC machine tools of the present application can be a maintenance strategy generation device for CNC machine tools with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a server, etc. The following takes a server as an example to illustrate various embodiments of the maintenance strategy generation method for CNC machine tools of the present application.

[0045] The present application embodiment provides a maintenance strategy generation method for a CNC machine tool, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the maintenance strategy generation method for a CNC machine tool of the present application.

[0046] In this embodiment, the maintenance strategy generation method for a CNC machine tool includes steps S10 to S20:

[0047] Step S10, when it is detected that there is a machine tool to be repaired, the work status data and work communication data corresponding to each person to be assigned are obtained, and based on each work communication data, the emotional tendency corresponding to each person to be assigned is obtained, wherein the work communication data includes data generated by communication between each person to be assigned during the historical maintenance process, and / or data generated by communication between each person to be assigned and the user during the historical maintenance process;

[0048] It should be noted that the persons to be assigned refer to all machine tool maintenance personnel. Work status data refers to data associated with the work of machine tool maintenance personnel. For example, work status data may include the professional skills of each maintenance personnel, the busyness of the maintenance personnel, and the current task status of the maintenance personnel (whether they are currently idle, whether they are repairing other equipment). Work communication data may include communication voices between maintenance personnel, communication voices between maintenance personnel and users, maintenance reports, etc. Emotional tendency refers to emotional characteristics, and emotional tendencies may include positive, negative, neutral, etc.

[0049] It is understandable that machine tool maintenance has a certain degree of danger, and the emotions of machine tool maintenance personnel will have a positive or negative impact on machine tool maintenance operations. In addition, maintenance personnel with good emotions are more friendly and professional when communicating with customers, can better understand customer needs and provide high-quality services, thereby improving customer satisfaction and trust.

[0050] Therefore, in this embodiment, in order to reasonably allocate maintenance tasks, the specific working status of each machine tool maintenance personnel can be obtained. In the process of machine tool maintenance personnel performing maintenance work, the communication voices between machine tool maintenance personnel and between machine tool maintenance personnel and users can be obtained, and the emotional tendency of machine tool maintenance personnel can also be extracted based on the communication voices, so as to allocate maintenance tasks based on the emotional tendency of machine tool maintenance personnel.

[0051] In this embodiment, emotional inclination will affect work efficiency. In order to avoid the negative impact of the negative emotions of machine tool maintenance personnel on maintenance work, this application can use the emotional inclination of maintenance personnel as the basis for dividing maintenance tasks, thereby achieving the purpose of improving maintenance efficiency.

[0052] In a feasible implementation manner, the above step S10 further includes:

[0053] Step S101, converting each work communication data into communication text, and detecting whether there is a preset emotional feature word in each communication text;

[0054] It should be noted that the communication text refers to the communication data in text form. The preset emotional characteristic words refer to the words that are pre-set to represent a certain emotional characteristic. For example, the preset emotional characteristic words corresponding to negativity may be "trouble", "no", "annoying", "irritable", etc.

[0055] It is understandable that if the work communication data is in voice form, the work communication data in voice form can be converted into text form through a neural network-based speech recognition algorithm or a deep learning-based speech recognition algorithm, and then it can be detected whether there are pre-set words corresponding to emotional characteristics in the communication text, and the emotional tendency can be identified based on the detection results.

[0056] Step S102, if it is detected that there is a preset emotional feature word in each communication text, then the number of occurrences of the preset emotional feature word in each communication text is determined;

[0057] Step S103, determining the emotional tendency corresponding to each person to be assigned according to the preset emotional feature words and the number of occurrences of each word.

[0058] It is understandable that if a preset emotional characteristic word is detected in the communication text, the emotional tendency of the maintenance personnel can be determined based on the number of times the emotional characteristic word appears and the correspondence between the emotional characteristic word and the emotional tendency.

[0059] Exemplarily, if "trouble" appears once and "no" appears twice in the communication text corresponding to a maintenance personnel, it can be determined that the emotional tendency of the maintenance personnel is moderately negative. Among them, the degree of influence of emotional tendency can be set according to actual needs, and this application does not limit this. For example, in this example, the number of occurrences is limited to two to four times as moderate. Therefore, based on the conclusion that "trouble" appears once and "no" appears twice, a result with a moderate degree of influence can be obtained. Thus, a moderately negative result can be obtained. Then, work can be assigned to the maintenance personnel based on the emotional tendency, skills, free time, experience and other basis of the maintenance personnel. For example, when the maintenance personnel is in a moderately negative state, a relatively simple maintenance task corresponding to his skills, free time and experience can be assigned to the maintenance personnel.

[0060] In this embodiment, the present application converts speech into text and determines the emotional tendency of maintenance personnel through text. It can determine the emotional tendency only by text, avoiding the problem of processing large amounts of data when determining emotional tendency and the heavy performance burden of the maintenance strategy generation equipment of CNC machine tools.

[0061] Exemplarily, the emotional tendency can also be identified by a model. Specifically, the model can be ERNIE (Enhanced Representation through Knowledge Integration, a knowledge pre-training language model). In a feasible implementation, the ERNIE model can be used to convert the preprocessed text data into a text representation, that is, each text sequence is converted into a semantic vector representation of a fixed dimension. At the same time, the text data is labeled as positive, negative or neutral emotions, and the emotional classification task is trained. Then, based on the existing labeled data set, the ERNIE model is used for supervised learning to obtain a sentiment classification model. In the trained sentiment classification model, since the hidden state of the penultimate layer contains the semantic information of the text and can better express the emotional information of the text, the hidden state of the penultimate layer of the ERNIE model can be extracted as the emotional tendency. Then, these hidden states are averaged or max pooled to obtain a fixed-dimensional emotional tendency representation of each text sequence. It is worth mentioning that these emotional tendencies can also be fused with other features (such as word frequency, part of speech, etc.) to obtain richer and more specific emotional tendencies.

[0062] It is understandable that the accuracy of the identified emotional tendency is related to the preset corresponding relationship in the above-mentioned speech-to-text technology to determine the emotional tendency through text. If the corresponding relationship is set inaccurately, the identified emotional tendency is also inaccurate. However, this embodiment uses the model automatic recognition method to determine the emotional tendency of each maintenance personnel through the emotional classification method learned autonomously by the model, thereby increasing the probability of accurately identifying the emotional tendency.

[0063] For example, when the performance of the device is poor and it is difficult to support the operation of the model, the emotional tendency can be extracted by the above-mentioned speech-to-text method. When the performance of the device is good, the emotional tendency can be extracted by the model classification method in this embodiment.

[0064] In addition, it should be noted that after obtaining the working status data and working communication data, the working status data and working communication data can also be preprocessed, namely: word segmentation, removal of stop words, conversion into word vectors, etc., so as to reduce noise and improve model effects, thereby improving the overall maintenance efficiency.

[0065] Step S20, input the fault information, working status data and emotional tendencies of the machine tool to be repaired into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies and corresponding actual maintenance strategies.

[0066] It should be noted that the machine tool to be repaired refers to the machine tool that needs to be repaired at the current moment, and the fault information refers to the fault content of the machine tool to be repaired, such as abnormal spindle vibration, control system error, etc. The actual fault information refers to the known fault information used to train the reinforcement learning model, the actual working status data refers to the pre-set working status data of each maintenance personnel used to train the reinforcement learning model, and the actual emotional tendency refers to the pre-set emotional tendency of each maintenance personnel used to train the reinforcement learning model. The actual maintenance strategy is a pre-set maintenance strategy corresponding to the actual fault information, actual working status data, and actual emotional tendency.

[0067] It is understandable that the present application can automatically output the maintenance strategy corresponding to the machine tool to be repaired through the reinforcement learning model.

[0068] For example, the maintenance process of high-end CNC machine tools can be modeled as a reinforcement learning environment. Then define the states: the state of high-end CNC machine tool equipment, the working state of maintenance personnel, and the emotional tendency of maintenance personnel; and define the actions in the reinforcement learning environment as maintenance strategies (including maintenance plans, maintenance sequences, maintenance time, tool use, and personnel allocation); and the reward function can also be defined based on factors such as maintenance efficiency, cost, emotional state of maintenance personnel, and user maintenance satisfaction, where maintenance cost, efficiency, and emotional state of maintenance personnel are intensive returns, and user maintenance satisfaction is only returned from the environment in the last step. Therefore, after outputting the maintenance strategy, maintenance can be carried out according to the maintenance strategy, and the maintenance process can be scored based on the time and efficiency of the maintenance process to judge the maintenance satisfaction.

[0069] In addition, in order to improve the matching degree between the output maintenance strategy and the machine tool to be maintained, a reinforcement learning strategy can be designed according to whether the maintenance action is a discrete or continuous variable. Specifically, a policy gradient-based method (Proximal Policy Optimization) can be used to learn and optimize the strategy. Thus, through continuous iterative training, the maintenance process of the machine tool to be maintained can be output.

[0070] In a feasible implementation manner, the maintenance strategy includes a maintenance plan, a maintenance sequence, and personnel allocation information. The above step S20 includes:

[0071] Step S201, determining a maintenance plan corresponding to the fault information of the machine tool to be repaired based on the reinforcement learning model;

[0072] It is understandable that in the action space of the reinforcement learning model, maintenance plans corresponding to various fault types are pre-set. Therefore, after obtaining the fault information, the fault type corresponding to the fault information can be determined, and then the maintenance plan corresponding to the fault type can be selected according to the fault type. Among them, the maintenance plan can be discrete or continuous. For example, when the maintenance plan is discrete, you can choose plan A or plan B, and the fault problem can be solved by executing plan A alone or plan B alone. When the maintenance plan is continuous, multiple plans need to be executed in sequence.

[0073] Step S202, determining the maintenance order corresponding to each maintenance step according to the preset priority corresponding to each maintenance step in the maintenance plan;

[0074] It is understandable that there are multiple maintenance steps in the maintenance plan, and each maintenance step has a certain priority. In order to give priority to repairing the faults that cause serious impact, the maintenance order corresponding to each maintenance step can be determined according to the priority corresponding to each maintenance step.

[0075] For example, the maintenance steps with high priority can be arranged in front, and the maintenance steps with low priority can be arranged in the back. In addition, the maintenance sequence can be adjusted based on the prerequisite relationship between each maintenance step to improve the maintenance efficiency.

[0076] Step S203, determining personnel allocation information according to each maintenance step, each maintenance sequence, and each emotional tendency.

[0077] It should be noted that the personnel allocation information refers to the correspondence between maintenance steps and maintenance personnel.

[0078] For example, after obtaining the maintenance sequence corresponding to each maintenance step, the maintenance time corresponding to each maintenance step can be determined based on the preset maintenance time corresponding to each maintenance step. Then, the personnel allocation information of each maintenance step in the maintenance strategy can be determined according to the professional skill requirements of each maintenance step for the maintenance personnel, the maintenance time corresponding to each maintenance step, the idle time of each maintenance personnel, and the emotional tendency of each maintenance personnel.

[0079] It is understandable that the above steps S201 to S203 are all implemented in the action space of the reinforcement learning model. Since the reinforcement learning model used in this application is designed based on the PPO strategy, this application can obtain a maintenance strategy that matches the machine tool to be repaired based on the reinforcement learning model, and can also assign appropriate maintenance steps based on the emotional tendency of the maintenance personnel, thereby further improving the maintenance efficiency.

[0080] In this embodiment, the present application obtains the work status data and work communication data corresponding to each person to be assigned, and obtains the emotional tendency corresponding to each person to be assigned based on the work communication data, wherein the work communication data includes the data generated by the communication between each person to be assigned during the historical maintenance process, and / or the data generated by the communication between each person to be assigned and the user during the historical maintenance process, so that the work status corresponding to each person to be assigned, such as whether it is busy, can be obtained, and the communication data of each person to be assigned when performing maintenance work at the current moment can also be obtained, so that the emotional tendency corresponding to each person to be assigned can be obtained according to the work communication data; then the fault information of the machine tool to be repaired, the work status data and the emotional tendency are input into the preset reinforcement learning model to obtain the maintenance strategy of the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on the actual fault information, the actual work status data and the actual emotional tendency and the corresponding actual maintenance strategy, and can generate the maintenance strategy corresponding to the machine tool to be repaired based on the specific fault information of the machine tool and the work status and emotional tendency of each person to be assigned.

[0081] In this application, the emotional inclination of the person to be assigned can be integrated into the maintenance task allocation process through a reinforcement learning model. This not only enhances the flexibility of task allocation, but also ensures that employees with more positive emotional states are given priority in being assigned to maintenance tasks that require a high level of meticulousness, thereby improving the overall maintenance efficiency of CNC machine tools.

[0082] Based on the first embodiment of the maintenance strategy generation method for a CNC machine tool of the present application, a second embodiment of the maintenance strategy generation method for a CNC machine tool of the present application is proposed.

[0083] Please refer to Figure 2 In this embodiment, after the above step S20, the method further includes:

[0084] Step S30, maintaining the machine tool to be maintained according to the maintenance strategy, and acquiring maintenance communication data in real time during the maintenance process, wherein the maintenance communication data includes data generated by communication between the maintenance personnel and other maintenance personnel when maintaining the machine tool to be maintained, and / or data generated by communication between the maintenance personnel and the user when maintaining the machine tool to be maintained;

[0085] It should be noted that the above-mentioned working communication data is the communication data output by the maintenance personnel when they are repairing other machine tools. For example, when the maintenance personnel are repairing other machine tools, machine tool A fails and reports, then the communication data (working communication data) output by the maintenance personnel when they are repairing other machine tools can be obtained to determine the emotional tendency of the maintenance personnel, so as to assign maintenance personnel to machine tool A based on the emotional tendency of each maintenance personnel. Then, when the assigned maintenance personnel repairs machine tool A, the communication data (maintenance communication data) output by the maintenance personnel is obtained.

[0086] In this embodiment, after obtaining the maintenance strategy corresponding to the machine tool to be maintained, the machine tool to be maintained can be maintained according to the maintenance strategy, and the communication data output by the maintenance personnel during the maintenance process can be obtained in real time to determine the emotional state of the maintenance personnel when repairing the current machine tool.

[0087] Step S40, based on the maintenance communication data, obtaining the maintenance emotion tendency, if it is detected that the maintenance emotion tendency represents negative maintenance emotion, adjusting the personnel allocation information in the maintenance strategy;

[0088] It should be noted that the maintenance emotional tendency refers to the emotional tendency determined based on the maintenance communication data when the current machine tool is being repaired.

[0089] Step S50: maintaining the machine tool to be maintained by using the adjusted maintenance strategy.

[0090] It is understandable that if it is detected through the maintenance emotional tendency that the current maintenance personnel have a relatively negative emotion, the maintenance personnel can be replaced to improve the maintenance efficiency.

[0091] Please refer to Figure 3 In a feasible implementation manner, the above step S40 further includes:

[0092] Step S401, taking the maintenance step corresponding to the maintenance emotional tendency as the target maintenance step, and determining the target maintainer of the target maintenance step from among the persons to be assigned based on the emotional tendencies corresponding to the persons to be assigned;

[0093] Step S402: adjusting the personnel allocation information corresponding to the target maintenance step in the maintenance strategy to the information of the target maintainer.

[0094] It is understandable that different maintenance steps can be performed by different maintenance personnel. When it is detected that the current maintenance personnel has a negative emotion, in order to avoid reducing the maintenance efficiency, the maintenance step corresponding to the current maintenance personnel can be used as the target maintenance step, and a new maintenance personnel can be determined from each maintenance personnel for the target maintenance step, that is, the target maintainer can be determined. Therefore, the present application can improve the maintenance efficiency by replacing the maintenance personnel in a timely manner.

[0095] In this embodiment, the present application determines the emotional tendencies of maintenance personnel during the maintenance process and reselects maintenance personnel when their emotional tendencies are negative. On the one hand, this can avoid the problems of long maintenance time and low maintenance efficiency caused by the maintenance personnel's negative attitude. On the other hand, different maintenance plans can be designed for maintenance personnel with different emotional states based on their emotional tendencies, thereby improving the work experience of the maintenance personnel.

[0096] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the maintenance strategy generation method for CNC machine tools of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0097] This application also provides a maintenance strategy generation system for CNC machine tools, please refer to Figure 4 , the maintenance strategy generation system of the CNC machine tool comprises:

[0098] The acquisition module 10 is used to acquire the work status data and work communication data corresponding to each person to be assigned when detecting the existence of a machine tool to be repaired, and obtain the emotional tendency corresponding to each person to be assigned based on each of the work communication data, wherein the work communication data includes the data generated by the communication between each person to be assigned during the historical maintenance process, and / or the data generated by the communication between each person to be assigned and the user during the historical maintenance process;

[0099] The generation module 20 is used to input the fault information of the machine tool to be repaired, the working status data and the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies and corresponding actual maintenance strategies.

[0100] In one embodiment, the acquisition module 10 is further used for:

[0101] Convert each of the work communication data into communication texts respectively, and detect whether there is a preset emotional feature word in each of the communication texts;

[0102] If it is detected that the preset emotional characteristic word exists in each of the communication texts, determining the number of occurrences of the preset emotional characteristic word in each of the communication texts;

[0103] According to the preset emotional characteristic words and the number of occurrences, the emotional tendency corresponding to each of the persons to be assigned is determined.

[0104] In one embodiment, the maintenance strategy includes a maintenance plan, a maintenance sequence, and personnel allocation information. The generation module 20 is further used to:

[0105] Determining a maintenance plan corresponding to the fault information of the machine tool to be repaired based on the reinforcement learning model;

[0106] Determine the maintenance order corresponding to each maintenance step according to the preset priority corresponding to each maintenance step in the maintenance plan;

[0107] According to each of the maintenance steps, each of the maintenance sequences, and each of the emotional tendencies, the personnel allocation information is determined.

[0108] In one embodiment, the maintenance strategy generation system for a CNC machine tool further includes:

[0109] a maintenance monitoring module, used to maintain the machine tool to be maintained according to the maintenance strategy, and to obtain maintenance communication data in real time during the maintenance process, wherein the maintenance communication data includes data generated by the communication between the maintenance personnel and other maintenance personnel when maintaining the machine tool to be maintained, and / or data generated by the communication between the maintenance personnel and the user when maintaining the machine tool to be maintained;

[0110] A personnel adjustment module, configured to obtain a maintenance emotion tendency based on the maintenance communication data, and if it is detected that the maintenance emotion tendency represents a negative maintenance emotion, adjust the personnel allocation information in the maintenance strategy;

[0111] The continuing maintenance module is used to maintain the machine tool to be maintained by using the adjusted maintenance strategy.

[0112] In one embodiment, the personnel adjustment module is further used to:

[0113] The maintenance step corresponding to the maintenance emotional tendency is taken as the target maintenance step, and based on the emotional tendency corresponding to each of the persons to be assigned, a target maintainer of the target maintenance step is determined from among the persons to be assigned;

[0114] The personnel allocation information corresponding to the target maintenance step in the maintenance strategy is adjusted to the information of the target maintainer.

[0115] The maintenance strategy generation system for CNC machine tools provided by the present application adopts the maintenance strategy generation method for CNC machine tools in the above-mentioned embodiment, and can solve the technical problem of how to allocate maintenance work to improve maintenance efficiency. Compared with the prior art, the beneficial effects of the maintenance strategy generation system for CNC machine tools provided by the present application are the same as the beneficial effects of the maintenance strategy generation method for CNC machine tools provided by the above-mentioned embodiment, and other technical features in the maintenance strategy generation system for CNC machine tools are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0116] The present application provides a maintenance strategy generation device for a CNC machine tool, the maintenance strategy generation device for a CNC machine tool comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the maintenance strategy generation method for the CNC machine tool in the above-mentioned embodiment one.

[0117] Reference below Figure 5 , which shows a structural schematic diagram of a maintenance strategy generating device for a CNC machine tool suitable for implementing an embodiment of the present application. Figure 5 The maintenance strategy generating device for a CNC machine tool shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0118] like Figure 5 As shown, the maintenance strategy generation device for a numerically controlled machine tool may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the maintenance strategy generation device for a numerically controlled machine tool are also stored in RAM1004. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the maintenance strategy generation device for a CNC machine tool to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a maintenance strategy generation device for a CNC machine tool with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0119] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0120] The maintenance strategy generation device for CNC machine tools provided by the present application adopts the maintenance strategy generation method for CNC machine tools in the above-mentioned embodiment, which can solve the technical problem of how to allocate maintenance work to improve maintenance efficiency. Compared with the prior art, the beneficial effects of the maintenance strategy generation device for CNC machine tools provided by the present application are the same as the beneficial effects of the maintenance strategy generation method for CNC machine tools provided by the above-mentioned embodiment, and other technical features in the maintenance strategy generation device for CNC machine tools are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0121] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the maintenance strategy generating method for a CNC machine tool in the above-mentioned embodiment.

[0124] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0125] The computer-readable storage medium may be included in the maintenance strategy generating device for a numerically controlled machine tool; or may exist independently without being assembled into the maintenance strategy generating device for a numerically controlled machine tool.

[0126] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the maintenance strategy generating device of the CNC machine tool, the maintenance strategy generating device of the CNC machine tool: when detecting the existence of a machine tool to be repaired, obtains the work status data and work communication data corresponding to each person to be assigned, and based on each of the work communication data, obtains the emotional tendency corresponding to each person to be assigned, wherein the work communication data includes the data generated by the communication between each person to be assigned during the historical maintenance process, and / or the data generated by the communication between each person to be assigned and the user during the historical maintenance process; inputs the fault information of the machine tool to be repaired, each of the work status data and each of the emotional tendencies into a preset reinforcement learning model to obtain the maintenance strategy of the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on the actual fault information, the actual work status data, the actual emotional tendency and the corresponding actual maintenance strategy.

[0127] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0130] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned maintenance strategy generation method for CNC machine tools, and can solve the technical problem of how to allocate maintenance work to improve maintenance efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the maintenance strategy generation method for CNC machine tools provided by the above-mentioned embodiments, and will not be repeated here.

[0131] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for generating a maintenance strategy for a CNC machine tool when executed by a processor.

[0132] The computer program product provided by the present application can solve the technical problem of how to allocate maintenance work to improve maintenance efficiency. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the maintenance strategy generation method for CNC machine tools provided by the above embodiment, which will not be repeated here.

[0133] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A maintenance strategy generation method for a CNC machine tool, characterized in that: The maintenance strategy generation method of the CNC machine tool comprises: When a machine tool to be repaired is detected, the work status data and work communication data corresponding to each person to be assigned are obtained, and based on each of the work communication data, the emotional tendency corresponding to each of the persons to be assigned is obtained, wherein the work communication data includes data generated by communication between the persons to be assigned during the historical maintenance process, and / or data generated by communication between the persons to be assigned and the user during the historical maintenance process; Inputting the fault information of the machine tool to be repaired, each of the working status data, and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies, and corresponding actual maintenance strategies in advance; The maintenance strategy includes maintenance plan, maintenance sequence and personnel allocation information; The step of inputting the fault information of the machine tool to be repaired, each of the working status data and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired comprises: Determining a maintenance plan corresponding to the fault information of the machine tool to be repaired based on the reinforcement learning model; Determine the maintenance order corresponding to each maintenance step according to the preset priority corresponding to each maintenance step in the maintenance plan; Determine personnel allocation information according to each of the maintenance steps, each of the maintenance sequences, and each of the emotional tendencies; After the step of inputting the fault information of the machine tool to be repaired, each of the working status data and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, the method further includes: Maintaining the machine tool to be maintained according to the maintenance strategy, and acquiring maintenance communication data in real time during the maintenance process, wherein the maintenance communication data includes data generated by communication between a maintenance personnel and other maintenance personnel when maintaining the machine tool to be maintained, and / or data generated by communication between a maintenance personnel and a user when maintaining the machine tool to be maintained; Based on the maintenance communication data, a maintenance emotion tendency is obtained, and if it is detected that the maintenance emotion tendency represents a negative maintenance emotion, the personnel allocation information in the maintenance strategy is adjusted; Maintaining the machine tool to be maintained by using the adjusted maintenance strategy; The step of adjusting the personnel allocation information in the maintenance strategy includes: The maintenance step corresponding to the maintenance emotional tendency is taken as the target maintenance step, and based on the emotional tendency corresponding to each of the persons to be assigned, a target maintainer of the target maintenance step is determined from among the persons to be assigned; The personnel allocation information corresponding to the target maintenance step in the maintenance strategy is adjusted to the information of the target maintainer.

2. The maintenance strategy generation method for a CNC machine tool according to claim 1, characterized in that: The step of obtaining the emotional tendency corresponding to each of the persons to be assigned based on each of the work communication data includes: Convert each of the work communication data into communication texts respectively, and detect whether there is a preset emotional feature word in each of the communication texts; If it is detected that the preset emotional characteristic word exists in each of the communication texts, determining the number of occurrences of the preset emotional characteristic word in each of the communication texts; According to the preset emotional characteristic words and the number of occurrences, the emotional tendency corresponding to each of the persons to be assigned is determined.

3. A maintenance strategy generation system for a CNC machine tool, characterized in that: The maintenance strategy generation system of the CNC machine tool comprises: An acquisition module is used to acquire the work status data and work communication data corresponding to each person to be assigned when detecting the existence of a machine tool to be repaired, and obtain the emotional tendency corresponding to each person to be assigned based on each of the work communication data, wherein the work communication data includes data generated by the communication between each person to be assigned during the historical maintenance process, and / or data generated by the communication between each person to be assigned and the user during the historical maintenance process; A generation module, used to input the fault information of the machine tool to be repaired, each of the working status data and each of the emotional tendencies into a preset reinforcement learning model to obtain a maintenance strategy for the machine tool to be repaired, wherein the reinforcement learning model is a model obtained by reinforcement training based on actual fault information, actual working status data, actual emotional tendencies and corresponding actual maintenance strategies in advance; The maintenance strategy includes maintenance plan, maintenance sequence and personnel allocation information; the generation module is also used to: Determining a maintenance plan corresponding to the fault information of the machine tool to be repaired based on the reinforcement learning model; Determine the maintenance order corresponding to each maintenance step according to the preset priority corresponding to each maintenance step in the maintenance plan; Determine personnel allocation information according to each of the maintenance steps, each of the maintenance sequences, and each of the emotional tendencies; The maintenance strategy generation system of the CNC machine tool also includes: a maintenance monitoring module, used to maintain the machine tool to be maintained according to the maintenance strategy, and to obtain maintenance communication data in real time during the maintenance process, wherein the maintenance communication data includes data generated by the communication between the maintenance personnel and other maintenance personnel when maintaining the machine tool to be maintained, and / or data generated by the communication between the maintenance personnel and the user when maintaining the machine tool to be maintained; A personnel adjustment module, configured to obtain a maintenance emotion tendency based on the maintenance communication data, and if it is detected that the maintenance emotion tendency represents a negative maintenance emotion, adjust the personnel allocation information in the maintenance strategy; A continuing maintenance module, used for maintaining the machine tool to be maintained by using the adjusted maintenance strategy; The personnel adjustment module is also used for: The maintenance step corresponding to the maintenance emotional tendency is taken as the target maintenance step, and based on the emotional tendency corresponding to each of the persons to be assigned, a target maintainer of the target maintenance step is determined from among the persons to be assigned; The personnel allocation information corresponding to the target maintenance step in the maintenance strategy is adjusted to the information of the target maintainer.

4. A maintenance strategy generating device for a CNC machine tool, characterized in that: The maintenance strategy generating device for a CNC machine tool comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the maintenance strategy generating method for a CNC machine tool as described in any one of claims 1 to 2.

5. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the maintenance strategy generation method for a CNC machine tool as described in any one of claims 1 to 2 are implemented.

6. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for generating a maintenance strategy for a numerically controlled machine tool according to any one of claims 1 to 2 are implemented.

Images