Maintenance strategy evaluation method, device and computer equipment for industrial equipment

Abstract

The present application relates to a maintenance strategy evaluation method, device and computer equipment for industrial equipment. The method includes: obtaining information of the industrial equipment to be maintained; the information of the industrial equipment includes risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and at least one of non-quantified losses; based on the information of the industrial equipment, determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained; the maintenance strategy to be evaluated includes the expected downtime, replaced parts and maintenance personnel information; inputting the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and outputting the predicted cost of the maintenance strategy to be evaluated through the evaluation model; obtaining the evaluation result according to the maintenance strategy to be evaluated and the predicted cost. The use of this method can improve the accuracy, comprehensiveness and objectivity of the evaluation.

Description

Technical Field

[0001] The present application relates to computer technology and production management technology, and in particular to a maintenance strategy evaluation method, device, computer equipment and storage medium for industrial equipment. Background Art

[0002] With the intensification of enterprise competition and the rise of operating costs, effective maintenance management has become essential. Traditional maintenance methods may lead to over-maintenance or under-maintenance, increase unnecessary costs or cause equipment failure. Therefore, a scientific method is needed to evaluate the maintenance cost of faulty equipment to meet the needs of refined management of modern enterprises.

[0003] Today's maintenance strategies for industrial equipment are usually evaluated by maintenance managers based on their experience, which is greatly influenced by the experience of maintenance managers, making it difficult to provide accurate and objective maintenance strategies. Summary of the invention

[0004] Based on this, it is necessary to provide a maintenance strategy evaluation method, device, computer equipment, computer-readable storage medium and computer program product for industrial equipment that can improve accuracy and objectivity in response to the above technical problems.

[0005] In a first aspect, the present application provides a maintenance strategy evaluation method for industrial equipment. The method comprises:

[0006] Acquire information of the industrial equipment to be maintained; the information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss;

[0007] Based on the information of the industrial equipment, determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained; the maintenance strategy to be evaluated includes an estimated downtime, replaced parts, and maintenance personnel information;

[0008] Inputting the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and outputting the predicted cost of the maintenance strategy to be evaluated through the evaluation model;

[0009] An evaluation result is obtained according to the maintenance strategy to be evaluated and the predicted cost.

[0010] In one embodiment, obtaining an evaluation result according to the maintenance strategy to be evaluated and the predicted cost includes:

[0011] At least one of the maintenance strategies to be evaluated is sorted according to the predicted cost, and an evaluation result is obtained according to the sorting result and the predicted cost of each maintenance strategy to be evaluated.

[0012] In one embodiment, the method further comprises:

[0013] Displaying a maintenance strategy analysis page; the maintenance strategy analysis page includes an industrial equipment information area and a strategy evaluation area; the industrial equipment information area is used to display the information of the industrial equipment to be maintained; the strategy evaluation area includes a maintenance strategy filter bar, each filter bar is used to set at least one dimension of maintenance strategy information;

[0014] The step of determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment includes:

[0015] In response to a trigger operation on any filter bar, displaying a maintenance strategy recommendation page;

[0016] Recommending at least one candidate maintenance strategy for the industrial equipment based on the information of the industrial equipment, and displaying the candidate maintenance strategy on the maintenance strategy recommendation page;

[0017] At least one maintenance strategy to be evaluated selected from the at least one candidate maintenance strategy is obtained, or the maintenance strategy to be evaluated input through the filter bar is obtained.

[0018] In one embodiment, the step of recommending at least one candidate maintenance strategy for the industrial equipment based on the information of the industrial equipment includes:

[0019] Filter out similar industrial equipment according to the information of the industrial equipment;

[0020] At least one candidate maintenance strategy is recommended for the industrial equipment to be maintained according to the maintenance strategies that have been executed historically for the similar industrial equipment.

[0021] In one of the embodiments, displaying the candidate maintenance strategies on the maintenance strategy recommendation page includes:

[0022] On the maintenance strategy recommendation page, the similar industrial equipment and the candidate maintenance strategy corresponding to each similar industrial equipment are displayed in descending order of similarity between the similar industrial equipment and the industrial equipment to be maintained.

[0023] In one embodiment, the method further comprises:

[0024] When it is detected that the industrial equipment has reached the daily maintenance time, the industrial equipment is determined to be equipment to be maintained; or,

[0025] When fault information of the industrial equipment is detected, the industrial equipment is determined to be equipment to be maintained.

[0026] In one embodiment, the method further comprises:

[0027] Obtaining a sample set, each sample in the sample set includes information and maintenance strategies of industrial equipment, the industrial equipment and information including risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss, and actual maintenance cost;

[0028] Input samples of the sample set into the evaluation model to be trained; the evaluation model is constructed based on LightGBM; wherein the evaluation model includes multiple decision trees, and feature processing is performed on each node of the decision tree of the evaluation model to obtain a prediction cost;

[0029] Wherein, a root node is initialized through the evaluation model, and the root node includes all samples;

[0030] Calculate all possible split points and find the split point that can minimize the loss function. At the split point, divide the data into two parts to form two new leaf nodes.

[0031] Repeat the process among all leaf nodes of the current level to find a node that can minimize the loss function and split it. At the split point, the data is divided into two parts to form two new leaf nodes of the next level until the preset maximum number of leaf nodes is reached or the loss function cannot be further reduced.

[0032] In a second aspect, the present application also provides a maintenance strategy evaluation device for industrial equipment. The device comprises:

[0033] An information acquisition module, used to acquire information of the industrial equipment to be maintained; the information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss;

[0034] A strategy determination module, configured to determine at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment; the maintenance strategy to be evaluated includes an estimated downtime, parts to be replaced, and maintenance personnel information;

[0035] A prediction module, used for inputting the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and outputting the predicted cost of the maintenance strategy to be evaluated through the evaluation model;

[0036] An evaluation module is used to obtain an evaluation result according to the maintenance strategy to be evaluated and the predicted cost.

[0037] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the maintenance strategy evaluation method for industrial equipment in the above-mentioned embodiments are implemented.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the maintenance strategy evaluation method for industrial equipment in the above-mentioned embodiments.

[0039] In a fifth aspect, the present application further 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 evaluation method for industrial equipment in the above-mentioned embodiments are implemented.

[0040] The above-mentioned maintenance strategy evaluation method, device, computer device, storage medium and computer program product for industrial equipment, on the one hand, can comprehensively evaluate the impact of various factors on maintenance costs by considering the basic information of the equipment, production plan, economic value related to the production plan, object fluctuation factors and non-quantified losses when evaluating the maintenance strategy, thereby improving the accuracy and comprehensiveness of the evaluation. On the other hand, the evaluation model is trained using machine learning methods, and the cost of the maintenance strategy is predicted through the evaluation model. This method is not limited by human experience and improves the accuracy and objectivity of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A diagram of an application environment of a maintenance strategy evaluation method for industrial equipment in one embodiment;

[0042] Figure 2 A schematic diagram of a process flow of a maintenance strategy evaluation method for industrial equipment in one embodiment;

[0043] Figure 3 A schematic diagram of an interface of a maintenance strategy analysis page in one embodiment;

[0044] Figure 4 This is a schematic diagram of the interface of a maintenance strategy recommendation page according to another embodiment;

[0045] Figure 5 This is a schematic diagram of an interface of a maintenance strategy analysis page in another embodiment;

[0046] Figure 6 A schematic diagram of the architecture of a recommendation model in one embodiment;

[0047] Figure 7 is a schematic diagram for explaining node splitting in one embodiment;

[0048] Figure 8 is a schematic diagram illustrating a residual network in one embodiment;

[0049] Fig. 9 A structural block diagram of a maintenance strategy evaluation device for industrial equipment in one embodiment;

[0050] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] An application environment of a maintenance strategy evaluation method for industrial equipment is as follows Figure 1 As shown, it includes a terminal 102 and a server 104. The terminal 102 communicates with the server 104 through a network. The terminal 102 can run an application or web page for maintenance strategy evaluation, and the server 104 provides maintenance strategy evaluation services. The terminal 102 sends an evaluation request and related data to the server 104, and the server 104 responds to the evaluation request, performs the evaluation to obtain the evaluation result, and returns the evaluation result to the terminal 102 for display. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0053] In one embodiment, Figure 2 As shown, a maintenance strategy evaluation method for industrial equipment is provided. Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0054] Step 202, obtaining information of the industrial equipment to be maintained; the information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss.

[0055] Specifically, the industrial equipment to be maintained refers to the industrial equipment that has reached the maintenance conditions.

[0056] In one embodiment, when it is detected that the industrial equipment has reached the daily maintenance time, the industrial equipment is determined to be a device to be maintained; or, when fault information of the industrial equipment is detected, the industrial equipment is determined to be a device to be maintained. That is, in this embodiment, maintenance can be divided into daily maintenance and fault maintenance.

[0057] The basic information of industrial equipment includes maintenance type and equipment information. Equipment information may include equipment location, equipment type, service life, service time, maintenance history, and parts replacement record. The maintenance type includes routine maintenance and fault maintenance; if the maintenance type is fault maintenance, the equipment information also includes fault part information.

[0058] Existing evaluation methods ignore some hidden costs, such as the indirect impact of workflow interruptions caused by maintenance on other related departments. The quantification of indirect costs such as production losses and quality decline is often subjective and uncertain, and difficult to calculate accurately. For example, when evaluating production losses caused by equipment downtime, only the direct reduction in output may be considered, without fully considering the potential impact on customer relationships due to delayed delivery. For another example, focusing only on current direct expenditures makes it difficult to accurately predict future cost changes that may be caused by factors such as technological advances and price fluctuations.

[0059] In view of this situation, in this embodiment, the production plan of industrial equipment, the economic value related to the production plan, the object fluctuation factor and the non-quantitative loss are also obtained. Among them, the production plan of industrial equipment can be obtained from the production management system, and the economic value related to the production plan can be determined according to the corresponding production order. Among them, the object fluctuation factor and the non-quantitative loss can be a coefficient maintained by the staff on a daily basis. By considering the production plan, the economic value related to the production plan, the object fluctuation factor and the non-quantitative loss when evaluating the maintenance strategy, it is possible to consider the impact of factors such as production influencing factors, technological progress or price fluctuation factors on changes in maintenance costs, thereby improving the accuracy and comprehensiveness of the evaluation.

[0060] Step 204: Based on the information of the industrial equipment, determine at least one maintenance strategy to be evaluated for the industrial equipment to be maintained; the maintenance strategy to be evaluated includes the estimated downtime, replaced parts, and maintenance personnel information.

[0061] The maintenance manager may input at least one maintenance strategy to be evaluated based on experience according to the information of the industrial equipment, or may recommend at least one maintenance strategy to be evaluated for the industrial equipment based on the information of the industrial equipment in combination with big data.

[0062] The maintenance strategy to be evaluated includes attributes of multiple dimensions, including but not limited to the expected downtime, replaced parts, and maintenance personnel information. The maintenance personnel information may include the maintenance personnel's age or maintenance personnel cost.

[0063] Step 206: input the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and output the predicted cost of the maintenance strategy to be evaluated through the evaluation model.

[0064] In this embodiment, the evaluation model is obtained based on the sample set training in advance. Each sample in the sample set includes the risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss of the industrial equipment, and the corresponding maintenance strategy, and its annotated data is the actual cost of the maintenance strategy. After the evaluation model training is completed, the information of the industrial equipment and the maintenance strategy are input, and the predicted cost can be output.

[0065] Step 208: obtaining an evaluation result according to the maintenance strategy to be evaluated and the predicted cost.

[0066] The above-mentioned maintenance strategy evaluation method for industrial equipment, on the one hand, can comprehensively evaluate the impact of various factors on maintenance costs by considering the basic information of the equipment, production plan, economic value related to the production plan, object fluctuation factors and non-quantified losses when evaluating the maintenance strategy, thereby improving the accuracy and comprehensiveness of the evaluation. On the other hand, the evaluation model is trained using machine learning methods, and the cost of the maintenance strategy is predicted through the evaluation model. This method is not limited by human experience and improves the accuracy and objectivity of the evaluation.

[0067] In another embodiment, obtaining an evaluation result based on the maintenance strategies to be evaluated and the predicted costs includes: sorting at least one of the maintenance strategies to be evaluated according to the predicted costs, and obtaining an evaluation result based on the sorting result and the predicted costs of each of the maintenance strategies to be evaluated.

[0068] Specifically, to facilitate user selection, the at least one maintenance strategy may be sorted according to the predicted cost, for example, the at least one maintenance strategy may be sorted in descending order of predicted cost, so as to facilitate the user to compare the difference in predicted costs of different maintenance strategies. On this basis, the evaluation result includes the sorting of the predicted costs of the maintenance strategies and the predicted costs of each maintenance strategy.

[0069] In another embodiment, the maintenance strategy evaluation method for industrial equipment further includes: displaying a maintenance strategy analysis page. This step may be performed when a user triggers a maintenance strategy evaluation operation. Figure 3 As shown, the maintenance strategy analysis page includes an industrial equipment information area 301 and a strategy evaluation area 302. The industrial equipment information area is used to display the information of the industrial equipment to be maintained. The strategy evaluation area 302 is used to display the maintenance strategy and its evaluation results. The strategy evaluation area 302 includes a filter bar 3021 for the maintenance strategy, and each filter bar 3021 is used to set at least one dimension of maintenance strategy information. Figure 3 As shown, three filter bars 3021 are included, which are used to set the downtime of the maintenance strategy, replacement parts and maintenance personnel information respectively.

[0070] The method of determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment includes: displaying a maintenance strategy recommendation page in response to a trigger operation in any filter bar; recommending at least one candidate maintenance strategy for the industrial equipment based on the information of the industrial equipment, and displaying the candidate maintenance strategy on the maintenance strategy recommendation page; obtaining at least one maintenance strategy to be evaluated selected from the at least one candidate maintenance strategy, or obtaining the maintenance strategy to be evaluated input through the filter bar.

[0071] There are two ways to determine the maintenance strategy to be evaluated: the first way is that the user manually inputs the maintenance strategy to be evaluated through the filter bar according to the information of the industrial equipment.

[0072] The second method is that the system recommends maintenance strategies for the industrial equipment based on the information of the industrial equipment. Figure 4 As shown, when the user triggers any one of the filter bars 3021, a maintenance strategy recommendation page 303 is displayed, and at least one candidate maintenance strategy is recommended for the industrial equipment on the maintenance strategy recommendation page 303; and at least one maintenance strategy to be evaluated selected from the at least one candidate maintenance strategy is obtained. In this way, the maintenance strategy to be evaluated can be quickly configured, and this way is not affected by human experience.

[0073] Specifically, based on the information of the industrial equipment, at least one candidate maintenance strategy is recommended for the industrial equipment, including: screening out similar industrial equipment based on the information of the industrial equipment; and recommending at least one candidate maintenance strategy for the industrial equipment to be maintained based on the maintenance strategies that have been historically executed for the similar industrial equipment.

[0074] That is, the method for the system to recommend the maintenance strategy to be evaluated is to screen similar industrial equipment based on the information of the industrial equipment, and then use the historically executed maintenance strategies of the similar industrial equipment as candidate maintenance strategies. This method can use the maintenance experience of similar industrial equipment to recommend maintenance strategies.

[0075] Among them, displaying the candidate maintenance strategies on the maintenance strategy recommendation page includes: on the maintenance strategy recommendation page, displaying the similar industrial equipment and the candidate maintenance strategies corresponding to each of the similar industrial equipment in descending order of similarity between the similar industrial equipment and the industrial equipment to be maintained.

[0076] Specifically, to facilitate users to select maintenance strategies, similar industrial equipment and their corresponding candidate maintenance strategies can be displayed on the maintenance strategy recommendation page in descending order of similarity between the similar industrial equipment and the industrial equipment to be maintained. Because the higher the similarity, the more similar the risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss of the industrial equipment to be maintained and the similar industrial equipment are, and the greater the possibility of adopting similar maintenance strategies. Furthermore, to facilitate user selection, the similarity value between the two and similar content can also be displayed on the maintenance strategy recommendation page for user reference.

[0077] Among them, Figure 5 As shown, when a user inputs multiple strategies to be evaluated, on the maintenance strategy analysis page, the maintenance strategies to be evaluated are sorted and displayed according to the descending order of the predicted cost, so as to facilitate the user's viewing.

[0078] In another embodiment, a method for training an evaluation module includes: obtaining a sample set, each sample in the sample set includes industrial equipment information and a maintenance strategy, the industrial equipment information includes basic information, a production plan and an economic value related to the production plan, and the labeled data of the sample is the actual maintenance cost of the maintenance strategy; inputting the samples of the sample set into the evaluation model to be trained; the evaluation model is constructed based on LightGBM; wherein the evaluation model includes multiple decision trees, and feature processing is performed on each node of the decision tree of the evaluation model to obtain a predicted cost.

[0079] First, the samples in the acquired sample set are preprocessed. For example, the risk item is converted into a numerical value (1, 2, 3, 4, 5, 6, 7) according to the risk level, represented by x1; the location is converted into a numerical value according to the occupied area, represented by x2; the service life of the equipment is converted into a numerical feature, represented by x3; the maintenance history is classified and coded, represented by x4; the maintenance personnel's working hours are converted into numerical values ​​according to hours, represented by x5; the degree of damage is converted into numerical values ​​according to the price of damaged parts, represented by x6; the object fluctuation factor is represented by x7; and non-quantified losses are represented by x8.

[0080] After the preprocessing is completed, the sample data is input into the evaluation model. The structure of the evaluation model in one embodiment is as follows: Figure 6 As shown, there are multiple decision trees. The structure of the decision tree is as follows Figure 7 As shown, new nodes are split according to leaf growth, as follows:

[0081] 1. Initialization: First, initialize a root node (x1,........x8) containing all samples.

[0082] 2. First split: Calculate all possible split points (for years, possible split points are 2.5, 7.5, 12.5, 17.5, 22), and find the split point that can minimize the loss function. Suppose the optimal split point we find is 32.5 years, we divide the data into two parts according to this split point, forming two new leaf nodes.

[0083] 3. Second split: We find a node among all leaf nodes that can minimize the loss function and split it. Assuming that the optimal node we find is the part with age greater than 12.5, we find the optimal split point in this part of the data.

[0084] 4. Subsequent splitting: Repeat the above process, each time finding a node among all leaf nodes that can minimize the loss function for splitting, until the preset maximum number of leaf nodes is reached or the loss function cannot be further reduced.

[0085] Each time, find the leaf with the largest splitting gain from all the current leaves, and then split it, and repeat this cycle. With the same number of splits, more errors can be reduced and better accuracy can be obtained.

[0086] The structure of the residual network is as follows Figure 8 As shown in the figure, its function is to add a "shortcut" connection so that information can be passed directly from the previous layer to the next layer. In the model structure, the output is Tree(x) and the input is x. In the residual module, the actual output becomes Tree(x)+x, where H(x)=Tree(x)-x is the residual. This module solves the problems of gradient vanishing and gradient exploding in deep networks. Due to the existence of shortcut connections, gradients can be back-propagated more directly, making it easier to train deep networks and enabling the network to learn identity mappings more easily, that is, when F(x)=0, the output is equal to the input, which increases the flexibility and robustness of the network to a certain extent.

[0087] After the evaluation model is built, the algorithm of the maintenance strategy cost estimation model built based on LightGBM is trained using the prepared data. The model parameters are continuously adjusted to improve the accuracy and generalization of the model.

[0088] After the evaluation model training is completed, the trained model is evaluated using the test set. The mean square error (MSE) is used as the evaluation indicator, and the model with the smallest error is selected as the optimal model for cost evaluation of faulty equipment maintenance.

[0089] After the model training is completed, the trained evaluation model can be used to predict the cost of the maintenance strategy of industrial equipment.

[0090] The machine learning-based method of this embodiment can make full use of the information in historical data, provide a more accurate and reliable basis for the maintenance cost evaluation of industrial equipment, and help enterprises make more informed decisions.

[0091] The method of this application achieves cost optimization by accurately evaluating and avoiding unnecessary expenses. It improves equipment reliability, selects appropriate maintenance strategies, reduces equipment failures and downtime, and improves production efficiency. At the same time, resources are reasonably allocated to make more effective use of human, material, and financial resources. This method can also enhance the scientific nature of decision-making, provide management with reliable data support, and make more informed strategic decisions.

[0092] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0093] Based on the same inventive concept, the embodiment of the present application also provides an industrial equipment maintenance strategy evaluation device for implementing the above-mentioned industrial equipment maintenance strategy evaluation method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in the embodiments of the maintenance strategy evaluation device for one or more industrial equipment provided below can refer to the limitations of the maintenance strategy evaluation method for industrial equipment above, and will not be repeated here.

[0094] In one embodiment, Fig. 9 As shown, a maintenance strategy evaluation device for industrial equipment is provided, comprising:

[0095] The information acquisition module 902 is used to acquire information of the industrial equipment to be maintained; the information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss.

[0096] The strategy determination module 904 is used to determine at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment; the maintenance strategy to be evaluated includes the estimated downtime, replaced parts and maintenance personnel information.

[0097] The prediction module 906 is used to input the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and output the predicted cost of the maintenance strategy to be evaluated through the evaluation model.

[0098] The evaluation module 908 is used to obtain an evaluation result according to the maintenance strategy to be evaluated and the predicted cost.

[0099] In another embodiment, the evaluation module is used to sort at least one of the maintenance strategies to be evaluated according to the predicted cost, and obtain an evaluation result according to the sorting result and the predicted cost of each maintenance strategy to be evaluated.

[0100] In another embodiment, it also includes a display module for displaying a maintenance strategy analysis page; the maintenance strategy analysis page includes an industrial equipment information area and a strategy evaluation area; the industrial equipment information area is used to display the information of the industrial equipment to be maintained; the strategy evaluation area includes a maintenance strategy filter bar, each filter bar is used to set at least one dimension of maintenance strategy information.

[0101] The strategy determination module 904 is used to display a maintenance strategy recommendation page in response to a trigger operation in any filter bar; recommend at least one candidate maintenance strategy for the industrial equipment based on the information of the industrial equipment, and display the candidate maintenance strategy on the maintenance strategy recommendation page; obtain at least one maintenance strategy to be evaluated selected from the at least one candidate maintenance strategy, or obtain the maintenance strategy to be evaluated input through the filter bar.

[0102] In another embodiment, the strategy determination module 904 is used to screen out similar industrial equipment according to the information of the industrial equipment; and recommend at least one candidate maintenance strategy for the industrial equipment to be maintained according to the historically executed maintenance strategies of the similar industrial equipment.

[0103] In another embodiment, the strategy determination module 904 displays the similar industrial equipment and the candidate maintenance strategy corresponding to each similar industrial equipment on the maintenance strategy recommendation page according to the descending order of similarity between the similar industrial equipment and the industrial equipment to be maintained.

[0104] In another embodiment, the information acquisition module is used to determine that the industrial equipment is a device to be maintained when it is detected that the industrial equipment has reached the daily maintenance time; or, when fault information of the industrial equipment is detected, determine that the industrial equipment is a device to be maintained.

[0105] In another embodiment, a training module is used to obtain a sample set, each sample of the sample set includes information and maintenance strategies of industrial equipment, and the industrial equipment and information include risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object volatility factor and non-quantified loss, and actual maintenance cost; the samples of the sample set are input into the evaluation model to be trained; the evaluation model is constructed based on LightGBM; wherein the evaluation model includes multiple decision trees, and feature processing is performed on each node of the decision tree of the evaluation model to obtain a predicted cost; wherein a root node is initialized by the evaluation model, and the root node includes all samples; all possible splitting points are calculated, and a splitting point that can minimize the loss function is found, and the data is divided into two parts at the splitting point to form two new leaf nodes; repeatedly executing among all leaf nodes of the current level, a node that can minimize the loss function is found for splitting, and the data is divided into two parts at the splitting point to form two new leaf nodes of the next level, until the preset maximum number of leaf nodes is reached or the loss function cannot be further reduced.

[0106] Each module in the above-mentioned maintenance strategy evaluation device for industrial equipment can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0107] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a maintenance strategy evaluation method for industrial equipment is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0108] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the maintenance strategy evaluation method for industrial equipment in the above-mentioned embodiments when executing the computer program.

[0110] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the maintenance strategy evaluation method for industrial equipment in the above-mentioned embodiments are implemented.

[0111] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the maintenance strategy evaluation method for industrial equipment of the above-mentioned embodiments.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0113] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A maintenance strategy evaluation method for industrial equipment, characterized in that: include: Obtain information about industrial equipment to be maintained; The information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss; Based on the information of the industrial equipment, determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained; the maintenance strategy to be evaluated includes an estimated downtime, replaced parts, and maintenance personnel information; Inputting the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and outputting the predicted cost of the maintenance strategy to be evaluated through the evaluation model; An evaluation result is obtained according to the maintenance strategy to be evaluated and the predicted cost.

2. The method according to claim 1, characterized in that The obtaining of an evaluation result according to the maintenance strategy to be evaluated and the predicted cost includes: At least one of the maintenance strategies to be evaluated is sorted according to the predicted cost, and an evaluation result is obtained according to the sorting result and the predicted cost of each maintenance strategy to be evaluated.

3. The method according to claim 1, characterized in that The method further comprises: Displaying a maintenance strategy analysis page; the maintenance strategy analysis page includes an industrial equipment information area and a strategy evaluation area; the industrial equipment information area is used to display the information of the industrial equipment to be maintained; the strategy evaluation area includes a maintenance strategy filter bar, each filter bar is used to set at least one dimension of maintenance strategy information; The step of determining at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment includes: In response to a trigger operation on any filter bar, displaying a maintenance strategy recommendation page; Recommending at least one candidate maintenance strategy for the industrial equipment based on the information of the industrial equipment, and displaying the candidate maintenance strategy on the maintenance strategy recommendation page; obtaining at least one maintenance strategy to be evaluated selected from the at least one candidate maintenance strategy, or The maintenance strategies to be evaluated inputted through the filter bar are obtained.

4. The method according to claim 3, characterized in that The step of recommending at least one candidate maintenance strategy for the industrial equipment according to the information of the industrial equipment includes: Filter out similar industrial equipment according to the information of the industrial equipment; At least one candidate maintenance strategy is recommended for the industrial equipment to be maintained according to the maintenance strategies that have been executed historically for the similar industrial equipment.

5. The method according to claim 4, characterized in that The displaying of the candidate maintenance strategies on the maintenance strategy recommendation page includes: On the maintenance strategy recommendation page, the similar industrial equipment and the candidate maintenance strategy corresponding to each similar industrial equipment are displayed in descending order of similarity between the similar industrial equipment and the industrial equipment to be maintained.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: When it is detected that the industrial equipment has reached the daily maintenance time, the industrial equipment is determined to be equipment to be maintained; or, When fault information of the industrial equipment is detected, the industrial equipment is determined to be equipment to be maintained.

7. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining a sample set, each sample in the sample set includes information and maintenance strategies of industrial equipment, the industrial equipment and information including risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss, and actual maintenance cost; Input samples of the sample set into the evaluation model to be trained; the evaluation model is constructed based on LightGBM; wherein the evaluation model includes multiple decision trees, and feature processing is performed on each node of the decision tree of the evaluation model to obtain a prediction cost; Wherein, a root node is initialized through the evaluation model, and the root node includes all samples; Calculate all possible split points and find the split point that can minimize the loss function. At the split point, divide the data into two parts to form two new leaf nodes. Repeat the process among all leaf nodes of the current level to find a node that can minimize the loss function and split it. At the split point, the data is divided into two parts to form two new leaf nodes of the next level until the preset maximum number of leaf nodes is reached or the loss function cannot be further reduced.

8. A maintenance strategy evaluation device for industrial equipment, characterized in that: The device comprises: An information acquisition module, used to acquire information of the industrial equipment to be maintained; the information of the industrial equipment includes at least one of risk information, basic information, historical maintenance information, production plan, economic value related to the production plan, object fluctuation factor and non-quantified loss; A strategy determination module, configured to determine at least one maintenance strategy to be evaluated for the industrial equipment to be maintained based on the information of the industrial equipment; the maintenance strategy to be evaluated includes an estimated downtime, parts to be replaced, and maintenance personnel information; A prediction module, used for inputting the information of the industrial equipment and the maintenance strategy to be evaluated into a pre-trained evaluation model, and outputting the predicted cost of the maintenance strategy to be evaluated through the evaluation model; An evaluation module is used to obtain an evaluation result according to the maintenance strategy to be evaluated and the predicted cost.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images