WO2023044632A1

WO2023044632A1 - Industrial equipment maintenance strategy generation method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023044632A1
Application number: PCT/CN2021/119719
Authority: WO
Inventors: 孙维; 张亮; 王洋; 胡黎红
Original assignee: 西门子股份公司; 西门子（中国）有限公司
Priority date: 2021-09-22
Filing date: 2021-09-22
Publication date: 2023-03-30

Abstract

The present application provides an industrial equipment maintenance strategy generation method and apparatus, an electronic device, and a storage medium. The industrial equipment maintenance strategy generation method is used for generating a maintenance strategy for failed industrial equipment. The method comprises: obtaining failure information and operation information of the industrial equipment, the failure information being used for indicating a failure occurring in the industrial equipment, and the operation information being used for indicating the operation status of the industrial equipment when the failure occurs; according to the failure information and the operation information, determining, from alternative maintenance solutions, at least one target maintenance solution matching the failure occurring in the industrial equipment, and determining, from alternative maintenance personnel information, at least one piece of target maintenance personnel information matching the failure occurring in the industrial equipment; and generating a maintenance strategy comprising the at least one target maintenance solution and the at least one piece of target maintenance personnel information. The present solution can improve the efficiency of maintaining the industrial equipment.

Description

Industrial equipment maintenance strategy generation method, device, electronic device and storage medium

technical field

The present application relates to the technical field of industrial equipment maintenance, and in particular to a method, device, electronic equipment and storage medium for generating an industrial equipment maintenance strategy.

Background technique

With the continuous development and progress of industrial technology, various types of industrial equipment are used for the processing and assembly of parts, replacing manual operations with industrial equipment to improve the efficiency of industrial production and reduce the labor intensity of personnel. When industrial equipment fails, it is necessary to formulate corresponding maintenance strategies to maintain industrial equipment, so that industrial equipment can quickly resume production and ensure the progress and efficiency of industrial production. The maintenance strategy specifically includes maintenance schemes and maintenance personnel. The maintenance schemes include measures to solve the failures of industrial equipment, and the maintenance personnel are engineers who execute the maintenance schemes.

At present, when formulating the maintenance strategy of industrial equipment, according to the task volume of each engineer, the engineer with a small task volume is determined as the maintenance personnel of the industrial equipment, and then the maintenance personnel determine the maintenance plan of the industrial equipment based on experience.

Since different engineers are good at different fields, when determining the maintenance personnel according to the engineer's task volume, the determined maintenance personnel may not be good at solving the failures of industrial equipment, and thus cannot formulate and implement an appropriate maintenance plan. , to quickly and effectively solve the faults of industrial equipment, so it will take a long time to complete the maintenance of industrial equipment, or the situation of replacing maintenance personnel due to the inability to complete the maintenance of industrial equipment, resulting in the efficiency of industrial equipment maintenance lower.

Contents of the invention

In view of this, the industrial equipment maintenance strategy generation method, device, electronic equipment, and storage medium provided by the present application can improve the efficiency of industrial equipment maintenance.

According to the first aspect of the embodiments of the present application, there is provided a method for generating a maintenance strategy for industrial equipment, which is used to generate a maintenance strategy for industrial equipment that has failed, and the method includes:

Acquiring fault information and operation information of the industrial equipment, the fault information is used to indicate the fault of the industrial equipment, and the operation information is used to indicate the operation status of the industrial equipment when the fault occurs;

According to the fault information and the operation information, determine at least one target maintenance plan that matches the fault of the industrial equipment from the alternative maintenance plans, and determine from the candidate maintenance personnel information At least one target maintainer information matching the fault;

A maintenance policy including the at least one target maintenance plan and the at least one target maintenance personnel information is generated.

In a first possible implementation manner, in combination with the first aspect above, the at least one target matching the fault of the industrial equipment is determined from alternative maintenance schemes according to the fault information and the operation information maintenance plan, and determine at least one target maintenance personnel information that matches the failure of the industrial equipment from the alternative maintenance personnel information, including:

According to a preset matching rule, at least one first maintenance plan that matches the fault information is determined from the alternative maintenance plans, and at least one first maintenance plan that matches the fault information is determined from the candidate maintenance personnel information. 1. maintenance personnel information;

Using a pre-trained matching model, determine at least one second maintenance plan that matches the fault information and the operation information from the candidate maintenance plans, and determine from the candidate maintenance personnel information that is compatible with the fault information and the operation information. At least one second maintenance personnel information matching the above operation information;

From the at least one first maintenance plan and the at least one second maintenance plan, select at least one maintenance plan that has a higher degree of matching with the failure of the industrial equipment as the target maintenance plan;

From the at least one first maintenance personnel information and the at least one second maintenance personnel information, at least one maintenance personnel information having a higher degree of matching with the fault of the industrial equipment is selected as the target maintenance personnel information.

In a second possible implementation manner, in combination with the first possible implementation manner above, the at least one first maintenance scheme that matches the fault information is determined from alternative maintenance schemes according to a preset matching rule. scheme, and determine at least one first maintenance personnel information that matches the fault information from the candidate maintenance personnel information, including:

According to the preset plan matching rules, the first keyword is extracted from the fault description information included in the fault information, the second keyword is extracted from the alternative maintenance plan, and according to the first keyword and the second The number of the same keywords in the keywords, determine the matching degree of the alternative maintenance plan and the fault information, and determine the alternative maintenance plan whose matching degree with the fault information is greater than the preset matching degree threshold as the first maintenance plan;

According to a preset personnel matching rule, candidate maintenance personnel information including skill information and professional information matching the failure type in the failure information is determined as the first maintenance personnel information.

In a third possible implementation manner, in combination with the first possible implementation manner above, at least one first maintenance scheme that matches the fault information and the operation information is determined from alternative maintenance schemes through a pre-trained matching model. Two maintenance schemes, and determining at least one second maintenance personnel information matching the fault information and the operation information from the candidate maintenance personnel information, including:

inputting the operating information into a first sub-model included in the matching model, and converting the operating information into an operating information vector through the first sub-model;

Inputting the fault information and the operating information vector into a second sub-model included in the matching model, converting the fault information and the operating information vector into an equipment information vector through the second sub-model;

Calculate the similarity between the equipment information vector and the scheme vector corresponding to each alternative maintenance scheme, and select the maintenance alternative corresponding to the scheme vector whose similarity with the equipment information vector is greater than the preset first similarity threshold The scheme is determined as the second maintenance scheme, wherein a scheme vector corresponding to an alternative maintenance scheme is obtained by performing vector conversion on the alternative maintenance scheme by the pre-trained first vector conversion model;

Calculate the similarity between the equipment information vector and the personnel vector corresponding to each candidate maintenance personnel information, and select the maintenance candidate corresponding to the personnel vector whose similarity with the equipment information vector is greater than the preset second similarity degree threshold The personnel information is determined as the second maintenance personnel information, wherein a personnel vector corresponding to a candidate maintenance personnel information is obtained by performing vector conversion on the candidate maintenance personnel information by a pre-trained second vector transformation model.

In a fourth possible implementation manner, in combination with the foregoing third possible implementation manner, the scheme vector and the personnel vector are stored in a pre-created database.

In a fifth possible implementation manner, the method for generating an industrial equipment maintenance strategy further includes:

The operation information vector is input into the fault detection sub-model included in the matching model, and the abnormal event information output by the fault detection sub-model is obtained, and the abnormal event information is used to indicate the abnormal event occurred in the industrial equipment.

In a sixth possible implementation manner, in combination with the above first aspect or any possible implementation manner of the first aspect, the method for generating an industrial equipment maintenance policy further includes:

Acquiring the maintenance record of the industrial equipment, the maintenance record is used to indicate the maintenance plan, maintenance personnel and maintenance results adopted when the industrial equipment is maintained;

The candidate maintenance scheme and the candidate maintenance personnel information are updated according to the maintenance record.

According to the second aspect of the embodiment of the present application, there is also provided an industrial equipment maintenance strategy generating device, which is used to generate a maintenance strategy for industrial equipment that has failed, and the device includes:

An acquisition module, configured to acquire fault information and operation information of the industrial equipment, the fault information is used to indicate a failure of the industrial equipment, and the operation information is used to indicate the operation status of the industrial equipment when a failure occurs;

A matching module, configured to determine at least one target maintenance plan that matches the fault of the industrial equipment from alternative maintenance plans according to the fault information and operation information acquired by the acquisition module, and determine from the alternative maintenance plans Determine at least one target maintenance personnel information in the personnel information that matches the fault of the industrial equipment;

A generation module, configured to generate a maintenance strategy including the at least one target maintenance scheme and the at least one target maintenance personnel information determined by the matching module.

In the third aspect, the embodiment of the present application also provides an electronic device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete the mutual communication through the communication bus. Communication;

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the industrial equipment maintenance strategy generation method provided in the first aspect or any possible implementation of the first aspect .

In a fourth aspect, the embodiment of the present application also provides a computer-readable storage medium, where computer instructions are stored on the computer-readable storage medium, and when the computer instructions are executed by a processor, the processor executes The method for generating an industrial equipment maintenance policy as provided in the first aspect or any possible implementation manner of the first aspect.

In the fifth aspect, the embodiment of the present application also provides a computer program, including computer-executable instructions. When executed, the computer-executable instructions cause at least one processor to perform any one of the above-mentioned first aspect or the first aspect. A method for generating an industrial equipment maintenance strategy is provided by a possible implementation.

In a sixth aspect, the embodiment of the present application further provides a computer program product, the computer program product is tangibly stored on a computer-readable medium and includes computer-executable instructions, and when executed, the computer-executable instructions use At least one processor executes the method for generating an industrial equipment maintenance policy as provided in the first aspect or any possible implementation manner of the first aspect.

It can be seen from the above technical scheme that after the industrial equipment fails, according to the fault information and operation information of the industrial equipment, the maintenance plan is matched from the alternative maintenance plan, and the maintenance personnel information is matched from the alternative maintenance personnel information, so as to determine the applicable Solve the target maintenance plan for the failure of industrial equipment, and determine the maintenance personnel who have the skills and experience to solve the failure of industrial equipment, and then generate a maintenance strategy including the target maintenance plan and target maintenance personnel information to recommend suitable for industrial equipment Maintenance plan and maintenance personnel to complete the maintenance of industrial equipment quickly and effectively, solve the failure of industrial equipment, so as to improve the efficiency of maintenance of industrial equipment.

Description of drawings

FIG. 1 is a flow chart of a method for generating an industrial equipment maintenance strategy provided in Embodiment 1 of the present application;

Fig. 2 is a flow chart of a maintenance plan and a maintenance personnel information matching method provided in Embodiment 2 of the present application;

Fig. 3 is a schematic diagram of a second maintenance plan and a method for determining second maintenance personnel information provided in Embodiment 2 of the present application;

FIG. 4 is a schematic diagram of an industrial equipment maintenance strategy generation device provided in Embodiment 3 of the present application;

FIG. 5 is a schematic diagram of an electronic device provided in Embodiment 4 of the present application.

List of reference signs:

101: Obtain fault information and operation information of industrial equipment

102: According to the fault information and operation information, determine the target maintenance plan that matches the fault of the industrial equipment

103: According to the fault information and operation information, determine the target maintenance personnel information that matches the fault of the industrial equipment

104: Generate a maintenance strategy including target maintenance plan and target maintainer information

201: Determine the first maintenance plan and the first maintenance personnel information according to the preset matching rules

202: Determine the second maintenance scheme and the second maintenance personnel information according to the pre-trained matching model

203: From the first maintenance plan and the second maintenance plan, select the target maintenance plan that has a high degree of matching with the fault

204: From the information of the first/second maintenance personnel, filter the information of the target maintenance personnel that has a higher degree of matching with the fault

100: Generation method of industrial equipment maintenance strategy 200: Matching method of maintenance plan and maintenance personnel information

300: Matching model 301: The first sub-model 302: The second sub-model

303: Function module 304: Fault detection sub-model 305: Running information

306: Fault information 307: Equipment information vector 308: Solution vector

309: Personnel vector 310: Second maintenance plan 311: Second maintenance personnel information

312: Abnormal event information 401: Get module 402: Match module

403: Build Module 500: Electronics 502: Processor

504: Communication interface 506: Memory 508: Communication bus

510: Procedure

Detailed ways

As mentioned above, after industrial equipment fails, it is necessary to maintain the industrial equipment as soon as possible, so that the industrial equipment can quickly resume production and ensure the progress and efficiency of industrial production. When maintaining the industrial equipment that has failed, it is necessary to assign an engineer to maintain the industrial equipment. The engineer formulates a maintenance plan according to the failure of the industrial equipment, and then executes the maintenance plan to complete the maintenance of the industrial equipment. At present, after industrial equipment fails, according to the task load of each engineer, engineers with a small task load are assigned to maintain the industrial equipment. However, different engineers are good at different technical fields, and the engineers assigned according to the task load may not be good at it. Solve the failures of industrial equipment, so that engineers cannot formulate an appropriate maintenance plan to solve the failure of industrial equipment, or it takes a long time to formulate an appropriate plan and complete the maintenance of industrial equipment, so it takes a long time In order to complete the maintenance of industrial equipment, the efficiency of maintenance of industrial equipment is low.

In the embodiment of the present application, the information of multiple alternative maintenance schemes and multiple alternative maintenance personnel is obtained in advance, and when the industrial equipment fails, the fault information used to indicate the failure of the industrial equipment is acquired, and the information used to indicate the industrial equipment The operating information of the operating status when a fault occurs, and then according to the fault information and operating information, determine the target maintenance plan that matches the fault of the industrial equipment from each alternative maintenance plan, and determine the industrial maintenance plan from each alternative maintenance personnel information. The information of the target maintenance personnel matched with the faults of the equipment, and then generate the maintenance strategy including the target maintenance plan and the information of the target maintenance personnel. Assign engineers to maintain industrial equipment according to the target maintenance personnel information included in the maintenance strategy, so that the assigned engineers are good at solving the failures of industrial equipment, and engineers can maintain industrial equipment according to the maintenance plan included in the maintenance strategy, ensuring fast , Effectively solve the failure of industrial equipment, complete the maintenance of industrial equipment, so as to improve the efficiency of maintenance of industrial equipment.

The method and device for generating an industrial equipment maintenance strategy provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Example with

FIG. 1 is a flowchart of a method 100 for generating an industrial equipment maintenance strategy provided by an embodiment of the present application. As shown in FIG. 1 , the method 100 for generating an industrial equipment maintenance strategy includes the following steps:

Step 101, acquiring fault information and operation information of industrial equipment.

The fault information is used to indicate the fault of the industrial equipment, and the fault information includes information such as device identification, fault type, fault description, and time stamp. Device identification is the ID or name of an industrial device. The failure type indicates the type of failure of the industrial equipment, such as mechanical failure, programming failure or other failure. The fault description is text information, which is used to describe the reason why the industrial equipment cannot work. For example, the fault description is "the main shaft cannot rotate". Timestamps are used to record when industrial equipment fails.

The operation information is used to indicate the operation state of the industrial equipment when a fault occurs, and the operation information includes the operation parameters and related data of the industrial equipment. Operating parameters include information such as voltage, current, speed, and pressure during the operation of industrial equipment. Relevant data includes sensor data and production data. Sensor data is collected by sensors on industrial equipment, such as vibration data collected by vibration sensors on motors and bearings. Production data includes industrial equipment production orders and processed materials. Because industrial Equipment operates differently when generating different orders and materials.

The fault information may be input by an operator of the industrial equipment, or may be acquired from a control system or a fault detection system outside the industrial equipment. In addition, the fault description included in the fault information can be extracted from the alarm information of the industrial equipment.

When obtaining the operation information of industrial equipment, the time period when the industrial equipment fails can be determined according to the time stamp included in the failure information, and then the operation parameters of the industrial equipment within this time period can be obtained. For example, take (time stamp -5s, time stamp +5s) as the time period when the industrial equipment fails.

Before and after the failure of industrial equipment, the operating status of industrial equipment will change, so the operation information of industrial equipment can reflect the failure of industrial equipment, and the failure information indicates the type of industrial equipment, the type of failure and describes the specific performance of the failure, so The fault information and operation information can reflect the faults of industrial equipment, that is, different faults of industrial equipment correspond to different fault information and operation information.

Step 102, according to the fault information and operation information, determine the target maintenance plan matching the fault of the industrial equipment from the alternative maintenance plans.

Multiple alternative maintenance schemes are created in advance, and different alternative maintenance schemes are used to solve the same or different failures of industrial equipment. The alternative maintenance scheme includes the steps of solving the response failure, and the maintenance personnel can solve the corresponding failure according to the alternative maintenance scheme.

Fault information and operation information can reflect the failure of industrial equipment, and the alternative maintenance scheme is used to solve the failure of industrial equipment. Since the fault information, operation information and alternative maintenance scheme are related to the failure of industrial equipment, it can be based on Fault information and operation information, determine the alternative maintenance plan that matches the fault of industrial equipment, and then determine the alternative maintenance plan that matches the fault of industrial equipment as the target maintenance plan. The target maintenance plan is determined based on the fault information and operation information of industrial equipment, so the target maintenance plan is suitable for solving the faults of industrial equipment, and maintenance personnel can maintain industrial equipment according to the target maintenance plan.

Since the same fault of industrial equipment can be solved by one maintenance solution, or can be solved separately by different maintenance solutions, the number of target maintenance solutions can be one or more.

Step 103 , according to the fault information and operation information, determine the target maintenance personnel information matching the fault of the industrial equipment from the candidate maintenance personnel information.

A plurality of candidate maintenance personnel information is stored in advance, and different candidate maintenance personnel information is used to indicate different maintenance personnel, and the maintenance personnel are engineers who maintain the industrial equipment. The candidate maintenance personnel information includes the maintenance personnel's identification, profession, skill type, skill proficiency, service time, etc.

Fault information and operation information reflect the faults of industrial equipment, and the profession, skill type, skill proficiency and service time of alternative maintenance personnel are suitable for solving different faults. The faults of industrial equipment are related, so according to the fault information and operation information, the candidate maintenance personnel information that matches the industrial equipment faults can be determined, and then the candidate maintenance personnel information that matches the industrial equipment faults can be determined as Target maintainer information.

The target maintenance personnel information is determined based on the fault information and operation information of the industrial equipment, that is, the maintenance personnel indicated by the target maintenance personnel information have the skills or experience to solve the faults of the industrial equipment, and then the maintenance personnel indicated by the target maintenance personnel information can Maintenance of industrial equipment to solve the failure of industrial equipment.

According to the type of failure of industrial equipment, industrial equipment can be maintained by one maintenance personnel, or by multiple maintenance personnel. Therefore, the number of target maintenance personnel information can be one or more, and different targets The maintainer information indicates different maintainers.

Step 104, generating a maintenance policy including target maintenance scheme and target maintainer information.

The target maintenance plan is suitable for solving the faults of industrial equipment. The maintenance personnel indicated by the target maintainer information have the skills and experience to solve the faults of industrial equipment. A maintenance strategy including the target maintenance plan and target maintainer information is generated to pass the maintenance strategy The maintenance personnel indicated by the recommended target maintenance personnel information maintains the industrial equipment, and the industrial equipment is maintained by collecting target maintenance schemes through maintenance strategy recommendations.

In the embodiment of this application, after the industrial equipment fails, according to the fault information and operation information of the industrial equipment, the maintenance plan is matched from the alternative maintenance plan, and the maintenance personnel information is matched from the alternative maintenance personnel information, so as to determine the applicable The target maintenance plan for solving the faults of industrial equipment, and determine the maintenance personnel who have the skills and experience to solve the faults of industrial equipment, and then generate the maintenance strategy including the target maintenance plan and target maintenance personnel information, to recommend suitable for industrial The equipment maintenance plan and maintenance personnel can quickly and effectively complete the maintenance of industrial equipment and solve the faults of industrial equipment, so as to improve the efficiency of industrial equipment maintenance.

Embodiment two

On the basis of the industrial equipment maintenance strategy generation method provided in Embodiment 1, when determining the target maintenance plan and target maintenance personnel information according to the fault information and operation information, the maintenance plan and the target maintenance personnel information can be determined respectively through a rule-based engine and a model-based Maintainer information, and then determine the target maintenance plan and target maintainer information from the maintenance plan and maintainer information determined by the two engines.

Fig. 2 is a flowchart of a maintenance plan and maintenance personnel information matching method 200 provided in Embodiment 2 of the present application. As shown in Fig. 2, the maintenance plan and maintenance personnel information matching method 200 includes the following steps:

Step 201 , according to preset matching rules, determine a first maintenance plan that matches the fault information from the candidate maintenance plans, and determine the first maintenance personnel information that matches the fault information from the candidate maintenance personnel information.

The faults of industrial equipment need to be solved through corresponding maintenance plans, and the faults of industrial equipment need to be solved by maintenance personnel with corresponding professional skills or experience. Therefore, the faults of industrial equipment have corresponding maintenance plans and maintenance personnel information. relationship, so that the matching rule can be determined according to the relationship, and the maintenance plan and maintenance personnel information matching the fault of the industrial equipment can be determined through the matching rule.

Since the fault information is used to indicate the faults of industrial equipment, the first maintenance plan that matches the fault information can be determined from the alternative maintenance plans according to the preset matching rules, as the rule-based engine recommended maintenance plan. As a result, the first maintenance personnel information matching the fault information is determined from the candidate maintenance personnel information as a result of the rule-based engine recommending maintenance personnel.

It should be noted that, for the same reason as the number of target maintenance programs and target maintenance personnel information can be one or more, the number of first maintenance programs can be one or more, and the number of first maintenance personnel information can also be one or more.

Step 202, according to the pre-trained matching model, determine the second maintenance plan that matches the fault information and operation information from the alternative maintenance plans, and determine the second maintenance plan that matches the fault information and operation information from the candidate maintenance personnel information. 2. Maintenance personnel information.

Since the fault information and operation information can reflect the faults of industrial equipment, and the faults of industrial equipment need to be solved by the corresponding maintenance plan and maintenance personnel, there is a certain relationship between the fault information and operation information and the maintenance plan and maintenance personnel information. The corresponding relationship, through the training of the machine learning model, a matching model reflecting the corresponding relationship can be obtained. Inputting the fault information and operation information into the matching model, the second maintenance plan matching the fault information and operation information can be determined from the alternative maintenance plans, as a result of the model-based engine recommended maintenance plan, and can be obtained from the alternative maintenance personnel The second maintenance personnel information matching the fault information and the operation information is determined in the information, as a result of recommending maintenance personnel based on the model.

It should be noted that, for the same reasons as the aforementioned first maintenance scheme and the number of first maintenance personnel information may be one or more, the number of second maintenance schemes may be one or more, and the number of second maintenance personnel information may also be Can be one or more.

Step 203 , from the first maintenance plan and the second maintenance plan, select a target maintenance plan that has a higher degree of matching with the fault of the industrial equipment.

The first maintenance plan is determined according to the fault information and matches the fault of the industrial equipment, and the second maintenance plan is the maintenance plan that matches the fault of the industrial equipment determined based on the fault information and operation information. Both the first maintenance plan and the second maintenance plan match the faults of industrial equipment, but the first maintenance plan and the second maintenance plan have different matching degrees with the faults of industrial equipment, and the different first maintenance plans are not compatible with industrial equipment. The faults of equipment have different matching degrees, and the different second maintenance plans also have different matching degrees with the faults of industrial equipment. Therefore, the faults of industrial equipment can be screened from the first maintenance plan and the second maintenance plan. One or more maintenance schemes with a high degree of matching are used as the final recommended target maintenance scheme to ensure that the determined target maintenance scheme can solve the failure of the industrial equipment.

The matching degree between the first maintenance plan and the faults of industrial equipment can be determined according to the matching degree between the first maintenance plan and the fault information. The higher the matching degree between the first maintenance plan and the fault information, the higher the matching degree of the first maintenance plan The higher the match, the higher the failure.

The matching degree between the second maintenance plan and the faults of industrial equipment can be determined according to the similarity output of the matching model, and the matching degree output by the matching model is used to indicate the correspondence between the vector corresponding to the second maintenance plan and the vector corresponding to the fault information and operation information Similarity, the greater the similarity of the output of the matching model, the higher the matching degree between the second maintenance scheme and the failure of the industrial equipment.

Step 204 , from the first maintenance personnel information and the second maintenance personnel information, screen the target maintenance personnel information that has a higher degree of matching with the faults of the industrial equipment.

The first maintenance personnel information is the maintenance personnel information matched with the industrial equipment faults determined according to the fault information, and the second maintenance personnel information is the maintenance personnel matched with the industrial equipment faults determined according to the fault information and operation information. Personnel information, although the information of the first maintenance personnel and the information of the second maintenance personnel both match the faults of industrial equipment, but the information of the first maintenance personnel and the information of the second maintenance personnel have different matching degrees with the faults of industrial equipment, and Different first maintenance personnel information has different matching degrees with industrial equipment failures, and different second maintenance personnel information has different matching degrees with industrial equipment failures. Therefore, from the first maintenance personnel information and the second Among the maintenance personnel information, one or more maintenance personnel information with a high degree of matching with industrial equipment failures are screened as the final recommended target maintenance personnel information to ensure that the maintenance personnel corresponding to the determined target maintenance personnel information can implement Targeted maintenance programs to address failures in industrial equipment.

In this embodiment of the application, the rule-based engine recommends the first maintenance plan and the first maintenance personnel information according to the preset matching rules, and the model-based engine recommends the second maintenance plan and the second maintenance personnel information according to the pre-trained matching model. Personnel information, and then select the maintenance plan with a higher degree of matching with the fault from the first maintenance plan and the second maintenance plan as the target maintenance plan, and filter the maintenance plan with a higher degree of fault matching from the first maintenance personnel information and the second maintenance personnel information The high maintenance personnel information is used as the target maintenance personnel information, and finally recommends to the user a maintenance strategy including the target maintenance plan and the target maintenance personnel information, to ensure that the faults of industrial equipment can be solved through the target maintenance plan, and to ensure the maintenance indicated by the target maintenance personnel information Personnel can implement the target maintenance plan to maintain the industrial equipment to solve the failure of the industrial equipment, thereby ensuring the success rate and efficiency of the maintenance of the industrial equipment.

The matching model is obtained through sample training. The samples include fault information and operation information of industrial equipment, the maintenance plan adopted for the maintenance of industrial equipment and the maintenance personnel information corresponding to the maintenance personnel. In the initial stage of deployment of industrial equipment maintenance strategy generation scheme , due to insufficient samples, the matching accuracy of the matching model is poor, and the matching model cannot accurately match the maintenance plan and maintenance personnel information suitable for industrial equipment failures. At this time, the second maintenance plan determined by the matching model and the second maintainer information have a low matching degree with the failure of the industrial equipment, so the rule-based engine is dominant.

When the rule-based engine is in a dominant position, compared with the model-based engine, the rule-based engine can more accurately determine the maintenance plan and maintenance personnel information that match the failure of the industrial equipment. Therefore, the first maintenance plan and the industrial The matching degree of the failure of the equipment is greater than the matching degree of the second maintenance plan and the failure of the industrial equipment, and the matching degree of the first maintenance personnel information and the failure of the industrial equipment is greater than the matching degree of the second maintenance personnel information and the failure of the industrial equipment , so the target maintenance plan is the first maintenance plan, and the target maintainer information is the first maintainer information.

After the matching model training is completed, the second maintenance scheme and the second maintenance personnel information determined by the matching model based on the fault information and operation information are more accurate than the first maintenance scheme and the first maintenance personnel information determined only based on the fault information. It is suitable for failures of industrial equipment, where the model-based engine is dominant, the determined target maintenance plan is the second maintenance plan, and the determined target maintenance personnel information is the second maintenance personnel information.

When the model-based engine is in a dominant position, compared with the rule-based engine, the model-based engine can more accurately determine the maintenance plan and maintenance personnel information that match the failure of the industrial equipment. Therefore, the second maintenance plan and the industrial The matching degree of the failure of the equipment is greater than the matching degree of the first maintenance plan and the failure of the industrial equipment, and the matching degree of the second maintenance personnel information and the failure of the industrial equipment is greater than the matching degree of the first maintenance personnel information and the failure of the industrial equipment , so the target maintenance plan is the second maintenance plan, and the target maintainer information is the second maintainer information.

In the embodiment of this application, at the initial stage of deployment of the industrial equipment maintenance strategy generation plan, since the matching model cannot accurately match the maintenance plan and maintenance personnel suitable for industrial equipment failures, the rule-based engine is in a dominant position at this time, according to Part or all of the first maintenance plan determined by the matching rules will be used as the target maintenance plan, and part or all of the first maintenance personnel information determined according to the preset matching rules will be used as the target maintenance personnel information. After the accuracy of the matching model reaches a certain level, the matching model can accurately match the maintenance plan and maintenance personnel suitable for industrial equipment failures. At this time, the model-based engine is in a dominant position, and some or all The second maintenance scheme will be used as the target maintenance scheme, and part or all of the second maintenance personnel information determined through the matching model will be used as the target maintenance personnel information. It can be seen that at different stages of the deployment of industrial equipment maintenance strategy generation schemes, different engines are in a dominant position, so that the target maintenance scheme and target maintenance personnel information can be determined through different engines to ensure that they can always be accurately matched to the occurrences of industrial equipment. The fault maintenance plan and maintenance personnel can quickly and effectively solve the faults of industrial equipment, thereby improving the efficiency of industrial equipment maintenance.

In a possible implementation, when determining the first maintenance plan that matches the fault information from the alternative maintenance plans, the first key can be extracted from the fault description information included in the fault information according to the preset plan matching rules. words, and extract the second keyword from the alternative maintenance scheme, and then determine the matching degree between the alternative maintenance scheme and the fault information according to the number of the same keywords in the first keyword and the second keyword, and then compare the matching degree with the fault information The alternative maintenance scheme whose matching degree is greater than the preset matching degree threshold is determined as the first maintenance scheme.

In the embodiment of this application, the fault description information included in the fault information is text information, which is used to describe the reason why the industrial equipment cannot work, and the first key word is extracted from the fault description information, and the second key word is extracted from the alternative maintenance plan If the first keyword and the second keyword contain many identical keywords, it means that the fault information has a high degree of matching with the alternative maintenance scheme. The higher the matching degree between the fault information and the alternative maintenance plan, the greater the probability that the alternative maintenance plan can solve the failure of industrial equipment, so the alternative maintenance plan with a matching degree with the fault information greater than the preset matching degree threshold is determined As the first maintenance plan, select the maintenance plan that can solve the failure of industrial equipment with a higher probability from each alternative maintenance plan as the first maintenance plan, and then ensure that the final target maintenance plan can solve the failure of industrial equipment .

It should be noted that when extracting keywords from the fault description information and alternative maintenance plans, the Term Frequency–Inverse Document Frequency (TF-IDF) algorithm can be used to extract keywords from the fault description information and alternative maintenance plans, respectively. Keywords are extracted from the maintenance plan, and then the similarity between the extracted first keyword and the second keyword is calculated as the matching degree between the candidate maintenance plan and the fault information.

In a possible implementation manner, when determining the first maintenance personnel information that matches the fault information from the candidate maintenance personnel information, according to the preset personnel matching rules, include The candidate maintenance personnel information matching the skill information and professional information is determined as the first maintenance personnel information.

In the embodiment of this application, maintenance personnel with different professions and skills are good at solving different types of faults. Through the personnel matching rules involving the skills and professions of maintenance personnel, according to the skill information and professional information included in the maintenance personnel information, it will include The candidate maintenance personnel information of skill information and professional information matching the fault type in the fault information is used as the first maintenance personnel information to ensure that the maintenance personnel indicated by the determined first maintenance personnel information have the ability to solve the faults of industrial equipment. ability, and then ensure that the maintenance personnel indicated by the finally determined target maintenance personnel information can solve the faults of industrial equipment.

The personnel matching rule is based on information such as the maintenance personnel's profession, skills, service time (cumulative time engaged in related work), etc., and the first maintenance personnel information is screened from the candidate maintenance personnel information. The personnel matching rules can include one rule or multiple rules. For example, the personnel matching rules include the following three rules:

Rule 1. Sort engineers according to their service hours, and give priority to matching engineers with longer service hours. Since the longer the service time of the engineer, the more experience the engineer has, so choose an engineer with a longer service time to ensure that the recommended engineer has more experience, so as to improve the effect and efficiency of industrial equipment maintenance.

Rule 2. If the industrial equipment is controlled by a programmable logic controller (Programmable Logic Controller, PLC), priority will be given to matching engineers with PLC programming skills.

Rule 3. If the fault description is that the motor is noisy, it is preferred to match the motor professional engineer.

In a possible implementation, when the model-based engine determines the second maintenance plan and the information of the second maintenance personnel that match the fault of the industrial equipment, the fault information and operation information, the alternative maintenance vector and the backup The selected maintenance personnel information is converted into a vector, and the second maintenance scheme and the second maintenance personnel information are determined by calculating the similarity between the vectors.

Fig. 3 is a schematic diagram of a second maintenance plan and a second maintenance personnel information determination method provided in Embodiment 2 of the present application. As shown in Fig. 3, the matching model 300 includes a first sub-model 301, a second sub-model 302 and a function Module 303.

After the running information 305 is input into the first sub-model 301, the first sub-model 301 converts the running information 305 into a running information vector. After the fault information 306 and the running information vector are input into the second sub-model 302 , the second sub-model 302 converts the fault information 306 and the running information vector into a device information vector 307 .

After inputting the solution vector 308 and the equipment information vector 307 corresponding to each alternative maintenance solution into the function module 303, the function module 303 calculates the similarity between the input equipment information vector 307 and the solution vector 308. After the function module 303 calculates the similarity between the scheme vector 308 corresponding to each alternative maintenance scheme and the equipment information vector 307, the alternative maintenance scheme corresponding to the scheme vector 308 whose similarity with the equipment information vector 307 is greater than the first similarity threshold It is output as the second maintenance plan 310 .

After inputting the personnel vector 309 and equipment information vector 307 corresponding to each candidate maintenance personnel information into the function module 303, the function module 303 calculates the similarity between the input equipment information vector 307 and the personnel vector 309. After the function module 303 calculates the similarity between the personnel vector 309 corresponding to each candidate maintenance personnel information and the equipment information vector 307, the candidate maintenance personnel corresponding to the personnel vector 309 whose similarity with the equipment information vector 307 is greater than the second similarity threshold The personnel information is output as the second maintenance personnel information 311 .

In the embodiment of the present application, after converting the fault information and operation information into the equipment information vector, by calculating the similarity between the equipment information vector and the scheme vector, the second maintenance scheme with a high degree of matching with the industrial equipment failure can be determined, By calculating the similarity between the equipment information vector and the personnel vector, the second maintenance personnel information with a high degree of matching with the industrial equipment fault can be determined. Convert the fault information and operation information into equipment information vectors by matching the first sub-model and the second sub-model included in the model, and determine the maintenance plan and maintenance personnel information that match the faults of industrial equipment by calculating the similarity between the vectors , can more accurately determine the maintenance plan and maintenance personnel information that match the faults of industrial equipment, and then ensure that the maintenance plan and maintenance personnel recommended to users match the faults of industrial equipment, and complete industrial equipment quickly and with high quality. maintenance and improve user experience.

It should be noted that both the first sub-model and the second sub-model included in the matching model can be obtained based on language representation pre-training models such as BERT (Bidirectional Encoder Representations from Transformer), so that the first sub-model and the second sub-model can be more Accurately understand the text meaning of fault information and operation information, thereby improving the accuracy of recommended maintenance programs and maintenance personnel. In addition, training the first sub-model and the second sub-model based on BERT can shorten the time for model training, thereby reducing the cost of generating industrial equipment maintenance strategies.

It should also be noted that when training the matching model, the first vector conversion model and the second vector conversion model are trained simultaneously with the matching model. The first vector conversion model can perform vector conversion on the candidate maintenance solution to obtain a solution vector corresponding to the candidate maintenance solution. The second vector conversion model can perform vector conversion on the candidate maintenance personnel information to obtain a personnel vector corresponding to the candidate maintenance personnel information. In the process of training the matching model and the first vector conversion model, for a maintenance plan that can solve the fault, the matching model converts the fault information corresponding to the fault into an equipment information vector, and the first vector conversion model converts the maintenance plan into The scheme vectors of have a large similarity. For the maintenance scheme that cannot solve the fault, the matching model converts the fault information corresponding to the fault into the equipment information vector, and the first vector conversion model converts the maintenance scheme into the scheme vector. small similarities. In the process of training the matching model and the second vector conversion model, for the maintenance personnel who can solve the fault, the matching model converts the fault information corresponding to the fault into an equipment information vector, and the second vector conversion model corresponds to the maintenance personnel The personnel vector converted from the maintenance personnel information has a large similarity. For the maintenance personnel who cannot solve the fault, the matching model converts the fault information corresponding to the fault into the equipment information vector, and the second vector conversion model corresponds to the maintenance personnel. The personnel vector converted from the maintenance personnel information has a small similarity.

From the above training methods of the matching model, the first vector conversion model, and the second vector conversion model, it can be known that by determining the similarity between the equipment information vector converted by the matching model and the solution vector converted by the first vector conversion model, the alternative Whether the maintenance plan can solve the fault indicated by the fault information, so as to determine the second maintenance plan that can solve the fault indicated by the fault information, by determining the equipment information vector converted from the matching model and the personnel vector converted from the second vector conversion model can determine whether the maintenance personnel indicated by the candidate maintenance personnel information can solve the failure indicated by the failure information, thereby determining the second maintenance personnel information of the maintenance personnel who can solve the failure indicated by the failure information.

In the embodiment of the present application, the plan vector corresponding to the candidate maintenance plan and the personnel vector corresponding to the candidate maintenance personnel information may be pre-stored in the database. When calculating the similarity between the program vector and the equipment information vector, the program vector is directly read from the database, and when the similarity between the personnel vector and the equipment information vector is calculated, the personnel vector is directly read from the database, so as to maintain industrial equipment When the strategy is generated, only the equipment information vector needs to be calculated, which can save the time for converting scheme vectors and personnel vectors, and shorten the time for generating industrial equipment maintenance strategies.

As shown in Figure 3, the matching model 300 also includes a fault detection sub-model 304. After the first sub-model 301 calculates the operation information vector, it inputs the operation information vector into the fault detection sub-model 304 to obtain the abnormal events output by the fault detection sub-model 304 Information 312, wherein the abnormal event information 312 is used to indicate an abnormal event occurred in the industrial equipment.

In the embodiment of the present application, the pre-trained fault detection sub-model can detect abnormal events of industrial equipment based on the operation information of the industrial equipment, and after converting the operation information into an operation information vector, input the operation information vector into the fault detection sub-model, The fault detection sub-model outputs abnormal event information based on the running information vector, and then can output the abnormal event information. When maintaining industrial equipment, maintenance personnel can determine the abnormal events that occur when industrial equipment fails based on the abnormal event information, so that the abnormal event information can be used as reference information to maintain industrial equipment, which helps to improve the maintenance of industrial equipment. efficiency and accuracy.

In a possible implementation, on the basis of the industrial equipment maintenance policy generation method 100 shown in FIG. The maintenance plan, maintenance personnel and maintenance results adopted during the maintenance of industrial equipment, and then the information of the alternative maintenance scheme and the alternative maintenance personnel can be updated according to the maintenance records.

In this embodiment of the application, after the maintenance personnel complete the maintenance of the industrial equipment, the maintenance records input by the maintenance personnel are obtained, and the pre-stored alternative maintenance schemes and information of the alternative maintenance personnel can be updated according to the maintenance records, so as to further After some industrial equipment fails, the maintenance plan and maintenance personnel can be recommended based on the updated alternative maintenance scheme and alternative maintenance personnel information, and the rationality of the recommended maintenance scheme and maintenance personnel can be improved.

Maintenance records include identification of industrial equipment, failure type, failure description, time stamp, identification of maintenance personnel, response time, repair time, maintenance plan, and maintenance result (whether the maintenance was successful or not). Updating the alternative maintenance plan according to the maintenance records mainly refers to adding a new alternative maintenance plan, that is, storing the maintenance plan adopted by the maintenance personnel when maintaining the industrial equipment as a new alternative maintenance plan for subsequent industrial equipment When a failure occurs, it is used as an alternative object together with the original alternative maintenance plan. In order to facilitate the conversion of the maintenance plan into the corresponding plan vector, the maintenance plan in the maintenance record can include the title of the maintenance plan, the summary of the maintenance plan and each maintenance step, etc., so that when converting the maintenance plan into a plan vector, the Each item included in the maintenance plan is converted into a vector element including multiple dimensions, and then the vector elements corresponding to each item form a plan vector.

Optional maintenance personnel information includes static information and dynamic information. Static information refers to the maintenance personnel’s identification, specialty, skill type, skill proficiency, service time, etc. Dynamic information refers to the fault type, response, etc. corresponding to the maintenance tasks performed by maintenance personnel. Time, repair time, success or failure and other information. Updating the candidate maintenance personnel information according to the maintenance records mainly refers to updating the dynamic information included in the candidate maintenance personnel information.

It should be noted that the industrial equipment maintenance strategy generation method provided by each embodiment of the present application is applicable to multiple industrial equipment of different types or the same type. With the accumulation of industrial equipment failures and corresponding maintenance plans, it can continuously The matching model is optimized to generate maintenance strategies for various types of industrial equipment, which has strong applicability. In addition, when training the matching model, positive samples and negative samples can be used to train the matching model, wherein the positive samples include fault information, operation information, maintenance personnel information and maintenance plans for resolved faults, and negative samples include fault information , operation information, maintenance personnel information, and maintenance solutions that fail to resolve faults.

It should also be noted that the matching model provided in each embodiment of the present application can be an end-to-end machine learning model, thereby making the training of the matching model more convenient and reducing manual participation in the training process Spend.

Embodiment Three

FIG. 4 is a schematic diagram of an industrial equipment maintenance strategy generating device 400 provided in Embodiment 3 of the present application, which is used to generate a maintenance strategy for industrial equipment that has failed. As shown in FIG. 4 , the industrial equipment maintenance strategy generating device 400 include:

The obtaining module 401 is used to obtain fault information and operation information of industrial equipment, the fault information is used to indicate the failure of the industrial equipment, and the operation information is used to indicate the operation status of the industrial equipment when the fault occurs;

The matching module 402 is configured to determine from the alternative maintenance schemes at least one target maintenance scheme that matches the failure of the industrial equipment according to the fault information and operation information acquired by the acquisition module 401, and determine from the alternative maintenance personnel information At least one target maintainer information matching the fault of the industrial equipment;

The generating module 403 is configured to generate a maintenance policy including information on at least one target maintenance scheme and at least one target maintainer determined by the matching module 402 .

In this embodiment of the application, the acquiring module 401 can be used to execute step 101 in the first embodiment above, the matching module 402 can be used to execute step 102 and step 103 in the first embodiment above, and the generation module 403 can be used to execute the first embodiment above Step 104 in .

In a possible implementation manner, the matching module 402 is configured to perform the following operations:

According to a preset matching rule, at least one first maintenance plan matching the fault information is determined from the alternative maintenance plans, and at least one first maintenance personnel information matching the fault information is determined from the candidate maintenance personnel information ;

Using a pre-trained matching model, determine at least one second maintenance plan that matches the fault information and operating information from the alternative maintenance plans, and determine at least one that matches the fault information and operating information from the candidate maintenance personnel information Second maintainer information;

From at least one first maintenance plan and at least one second maintenance plan, select at least one maintenance plan that has a greater degree of matching with the failure of the industrial equipment as the target maintenance plan;

According to the preset plan matching rules, the first keyword is extracted from the fault description information included in the fault information, and the second keyword is extracted from the alternative maintenance plan. According to the same keyword in the first keyword and the second keyword, Determine the matching degree of the alternative maintenance plan and the fault information, and determine the alternative maintenance plan whose matching degree with the fault information is greater than the preset matching degree threshold as the first maintenance plan;

According to a preset personnel matching rule, candidate maintenance personnel information including skill information and professional information matching the fault type in the fault information is determined as the first maintenance personnel information.

inputting the operating information into the first sub-model included in the matching model, and converting the operating information into an operating information vector through the first sub-model;

inputting the fault information and the operation information vector into the second sub-model included in the matching model, and converting the fault information and the operation information vector into the equipment information vector through the second sub-model;

Calculate the similarity between the equipment information vector and the scheme vector corresponding to each alternative maintenance scheme, and determine the alternative maintenance scheme corresponding to the scheme vector whose similarity with the equipment information vector is greater than the preset first similarity threshold as the second maintenance A scheme, wherein, a scheme vector corresponding to an alternative maintenance scheme is obtained by performing vector conversion on the alternative maintenance scheme by a pre-trained first vector transformation model;

Calculate the similarity between the equipment information vector and the personnel vector corresponding to each candidate maintenance personnel information, and determine the candidate maintenance personnel information corresponding to the personnel vector whose similarity with the equipment information vector is greater than the preset second similarity degree threshold as The second maintenance personnel information, wherein, a personnel vector corresponding to a candidate maintenance personnel information is obtained by performing vector conversion on the candidate maintenance personnel information by a pre-trained second vector transformation model.

In a possible implementation manner, the scheme vector and the personnel vector are stored in a pre-created database.

In a possible implementation, the matching module 402 is also configured to input the operation information vector into the fault detection sub-model included in the matching model, and obtain the abnormal event information output by the fault detection sub-model, and the abnormal event information is used to indicate the occurrence of industrial equipment. unusual event.

In a possible implementation manner, on the industrial equipment maintenance strategy generation device 400 shown in FIG. 4 , the industrial equipment maintenance strategy generation device 400 may further include:

The receiving module is used to obtain maintenance records of industrial equipment, and the maintenance records are used to indicate the maintenance plan, maintenance personnel and maintenance results adopted when maintaining the industrial equipment;

The updating module is used to update the information of the candidate maintenance plan and the candidate maintenance personnel according to the maintenance records received by the receiving module.

It should be noted that the interaction between the various modules in the above-mentioned device embodiment is based on the same inventive concept as that of the foregoing method embodiment, and details can be found in the description of the foregoing method embodiment, which will not be repeated here.

Embodiment four

FIG. 5 is a schematic diagram of an electronic device provided in Embodiment 4 of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device. Referring to FIG. 5 , an electronic device 500 provided by an embodiment of the present application includes: a processor (processor) 502 , a communication interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 . in:

The processor 502 , the communication interface 504 , and the memory 506 communicate with each other through the communication bus 508 .

The communication interface 504 is used for communicating with other electronic devices or servers.

The processor 502 is configured to execute the program 510, and specifically, may execute relevant steps in the above embodiment of the method for generating an industrial equipment maintenance strategy.

Specifically, the program 510 may include program codes including computer operation instructions.

The processor 502 may be a central processing unit CPU, or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be of the same type, such as one or more CPUs, or may be different types of processors, such as one or more CPUs and one or more ASICs.

The memory 506 is used for storing the program 510 . The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 510 may be specifically configured to enable the processor 502 to execute the method for generating an industrial equipment maintenance policy in any of the foregoing embodiments.

For the specific implementation of each step in the program 510, refer to the corresponding description of the corresponding steps and units in the above-mentioned embodiment of the method for generating an industrial equipment maintenance strategy, and details are not repeated here. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the foregoing method embodiments, and details are not repeated here.

With the electronic equipment of this embodiment, after the industrial equipment fails, according to the fault information and operation information of the industrial equipment, the maintenance plan is matched from the alternative maintenance plans, and the maintenance personnel information is matched from the information of the maintenance personnel alternatives, so as to determine the It is applicable to the target maintenance plan for solving the faults of industrial equipment, and determines the maintenance personnel who have the skills and experience to solve the faults of industrial equipment, and then generates the maintenance strategy including the target maintenance plan and target maintenance personnel information, to recommend suitable for The maintenance plan and maintenance personnel of industrial equipment can quickly and effectively complete the maintenance of industrial equipment and solve the faults of industrial equipment, so as to improve the efficiency of maintenance of industrial equipment.

The present application also provides a computer-readable storage medium storing instructions for enabling a machine to execute the method for generating an industrial equipment maintenance strategy as described herein. Specifically, a system or device equipped with a storage medium may be provided, on which a software program code for realizing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU of the system or device) ) to read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, so the program code and the storage medium storing the program code constitute a part of the present application.

Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), Tape, non-volatile memory card, and ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

In addition, it should be clear that not only by executing the program code read by the computer, but also by making the operating system on the computer complete part or all of the actual operations through instructions based on the program code, so as to realize the function of any one of the embodiments.

In addition, it can be understood that the program code read from the storage medium is written into the memory provided in the expansion board inserted into the computer or written into the memory provided in the expansion module connected to the computer, and then based on the program code The instruction causes the CPU installed on the expansion board or the expansion module to perform some or all of the actual operations, thereby realizing the functions of any one of the above-mentioned embodiments.

An embodiment of the present application further provides a computer program, including computer executable instructions, and when executed, the computer executable instructions cause at least one processor to execute the method for generating an industrial equipment maintenance strategy provided in the foregoing embodiments.

The embodiment of the present application also provides a computer program product, the computer program product is tangibly stored on a computer-readable medium and includes computer-executable instructions, and the computer-executable instructions cause at least one processor to Execute the methods for generating industrial equipment maintenance strategies provided by the above embodiments. It should be understood that the solutions in this embodiment have the corresponding technical effects in the foregoing method embodiments, and details are not repeated here.

It should be noted that not all the steps and modules in the above flow charts and device structure diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as required. The system structures described in the above embodiments may be physical structures or logical structures, that is, some modules may be realized by the same physical entity, or some modules may be realized by multiple physical entities, or may be realized by multiple Certain components in individual devices are implemented together.

In the above embodiments, the hardware modules may be implemented mechanically or electrically. For example, a hardware module may include permanently dedicated circuitry or logic (such as a dedicated processor, FPGA or ASIC) to perform the corresponding operations. The hardware modules may also include programmable logic or circuits (such as general-purpose processors or other programmable processors), which can be temporarily set by software to complete corresponding operations. The specific implementation (mechanical way, or a dedicated permanent circuit, or a temporary circuit) may be determined based on cost and time considerations.

The above has shown and described the application in detail through the accompanying drawings and preferred embodiments, but the application is not limited to these disclosed embodiments, and those skilled in the art based on the above-mentioned multiple embodiments can know that the above-mentioned different embodiments can be combined The code auditing means in the present application obtains more embodiments, and these embodiments are also within the protection scope of the present application.

Claims

A method (100) for generating a maintenance strategy for industrial equipment, used for generating a maintenance strategy for industrial equipment that has failed, the method comprising:

Acquiring fault information and operation information of the industrial equipment, the fault information is used to indicate the fault of the industrial equipment, and the operation information is used to indicate the operation status of the industrial equipment when the fault occurs;

According to the fault information and the operation information, determine at least one target maintenance plan that matches the fault of the industrial equipment from the alternative maintenance plans, and determine from the candidate maintenance personnel information At least one target maintainer information matching the fault;

A maintenance policy including the at least one target maintenance plan and the at least one target maintenance personnel information is generated.
The method according to claim 1, wherein, according to the fault information and the operation information, at least one target maintenance plan matching the fault of the industrial equipment is determined from the alternative maintenance plans, and from The information of at least one target maintenance personnel determined to match the failure of the industrial equipment in the candidate maintenance personnel information includes:

According to a preset matching rule, at least one first maintenance plan that matches the fault information is determined from the alternative maintenance plans, and at least one first maintenance plan that matches the fault information is determined from the candidate maintenance personnel information. 1. maintenance personnel information;

Using a pre-trained matching model, determine at least one second maintenance plan that matches the fault information and the operation information from the candidate maintenance plans, and determine from the candidate maintenance personnel information that is compatible with the fault information and the operation information. At least one second maintenance personnel information matching the above operation information;

From the at least one first maintenance plan and the at least one second maintenance plan, select at least one maintenance plan that has a higher degree of matching with the failure of the industrial equipment as the target maintenance plan;

From the at least one first maintenance personnel information and the at least one second maintenance personnel information, at least one maintenance personnel information having a higher degree of matching with the fault of the industrial equipment is selected as the target maintenance personnel information.
The method according to claim 2, wherein, according to the preset matching rules, at least one first maintenance plan that matches the fault information is determined from the candidate maintenance plans, and the information of the candidate maintenance personnel Determining at least one piece of first maintenance personnel information that matches the fault information, including:

According to the preset plan matching rules, the first keyword is extracted from the fault description information included in the fault information, the second keyword is extracted from the alternative maintenance plan, and according to the first keyword and the second The number of the same keywords in the keywords, determine the matching degree of the alternative maintenance plan and the fault information, and determine the alternative maintenance plan whose matching degree with the fault information is greater than the preset matching degree threshold as the first maintenance plan;

According to a preset personnel matching rule, candidate maintenance personnel information including skill information and professional information matching the failure type in the failure information is determined as the first maintenance personnel information.
The method according to claim 2, wherein, through a pre-trained matching model, at least one second maintenance plan matching the fault information and the operation information is determined from the alternative maintenance plans, and from the alternative maintenance Determining at least one second maintenance personnel information that matches the fault information and the operation information in the personnel information includes:

inputting the operating information into a first sub-model included in the matching model, and converting the operating information into an operating information vector through the first sub-model;

inputting the fault information and the operating information vector into a second sub-model included in the matching model, and converting the fault information and the operating information vector into an equipment information vector through the second sub-model;

Calculating the similarity between the equipment information vector and the scheme vector corresponding to each alternative maintenance scheme, and determining the alternative maintenance scheme corresponding to the scheme vector whose similarity with the equipment information vector is greater than a preset first similarity threshold is the second maintenance plan, wherein, a plan vector corresponding to an alternative maintenance plan is obtained by performing vector conversion on the alternative maintenance plan by the pre-trained first vector conversion model;

Calculate the similarity between the equipment information vector and the personnel vector corresponding to each candidate maintenance personnel information, and select the maintenance candidate corresponding to the personnel vector whose similarity with the equipment information vector is greater than the preset second similarity degree threshold The personnel information is determined as the second maintenance personnel information, wherein a personnel vector corresponding to a candidate maintenance personnel information is obtained by performing vector conversion on the candidate maintenance personnel information by a pre-trained second vector conversion model.
The method according to claim 4, wherein the scheme vector and the personnel vector are stored in a pre-created database.
The method according to claim 4, said method further comprising:

The operation information vector is input into the fault detection sub-model included in the matching model, and the abnormal event information output by the fault detection sub-model is obtained, and the abnormal event information is used to indicate the abnormal event occurred in the industrial equipment.
The method according to any one of claims 1-6, further comprising:

Acquiring the maintenance record of the industrial equipment, the maintenance record is used to indicate the maintenance plan, maintenance personnel and maintenance results adopted when the industrial equipment is maintained;

The candidate maintenance scheme and the candidate maintenance personnel information are updated according to the maintenance record.
An industrial equipment maintenance strategy generating device (400), used for generating a maintenance strategy for industrial equipment in failure, the device comprising:

An acquisition module (401), configured to acquire fault information and operation information of the industrial equipment, the fault information is used to indicate a failure of the industrial equipment, and the operation information is used to indicate the failure of the industrial equipment Operating status;

A matching module (402), configured to determine at least one target maintenance plan that matches the fault of the industrial equipment from alternative maintenance plans according to the fault information and operation information acquired by the acquisition module (401) , and determine at least one target maintenance personnel information matching the fault of the industrial equipment from the candidate maintenance personnel information;

A generation module (403), configured to generate a maintenance strategy including the at least one target maintenance scheme and the at least one target maintenance personnel information determined by the matching module (402).
An electronic device (500), comprising: a processor (502), a communication interface (504), a memory (506) and a communication bus (508), the processor (502), the memory (506) and the The communication interface (504) completes mutual communication through the communication bus (508);

The memory (506) is used to store at least one executable instruction, and the executable instruction causes the processor (502) to execute the corresponding method of the industrial equipment maintenance strategy generation method according to any one of claims 1-7. operate.
A computer-readable storage medium, where computer instructions are stored on the computer-readable storage medium, and when the computer instructions are executed by a processor, the processor performs the method described in any one of claims 1-7. method.
A computer program comprising computer-executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1-7.
A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions which, when executed, cause at least one processor to perform the any one of the methods described.