Equipment maintenance prediction system and method applied to part machining

Abstract

The invention discloses an equipment maintenance prediction system and method applied to part processing, and relates to the technical field of equipment maintenance, and the system comprises an equipment maintenance prediction module, an initial maintenance determination module, an initial maintenance effect analysis module, a reconfiguration maintenance determination module, a setting equipment maintenance prediction module and an initial maintenance determination module. The maintenance of the equipment can be regularly predicted and analyzed, the operation data of the equipment is combined with a deep learning model, whether the equipment needs to be maintained in the next maintenance prediction period or not is accurately predicted, the initial maintenance content of the equipment is synchronously determined, and an initial maintenance effect analysis module and a reconfiguration maintenance determination module are arranged. According to the method, the maintenance effect of each initially determined maintenance content of the equipment can be subjected to deep simulation analysis, and the maintenance effect of each initially determined maintenance content is accurately predicted, so that the maintenance content needing to be maintained of the equipment in the next maintenance prediction period is rapidly and accurately determined.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and more specifically, to an equipment maintenance prediction system and method applied to parts processing. Background Art

[0002] In the current industrial manufacturing environment, the performance and stability of parts processing equipment are crucial to ensuring production efficiency and product quality. However, as the equipment is used for a longer time, its performance will decline, and it may even fail, which will affect production progress and product quality. Therefore, regular maintenance and care of the equipment, and timely repair or replacement of severely worn parts are the key to ensuring long-term stable operation of the equipment.

[0003] Traditional equipment maintenance methods mostly rely on experience judgment or fixed maintenance cycles, which have obvious limitations. On the one hand, experience judgment is often subjective and it is difficult to accurately predict the actual maintenance needs of the equipment; on the other hand, fixed maintenance cycles may lead to insufficient or excessive maintenance due to different actual equipment usage conditions, resulting in a waste of resources.

[0004] In recent years, with the rapid development of technologies such as big data and artificial intelligence, equipment maintenance prediction technology has emerged. However, most of the existing equipment maintenance prediction systems only stay at the level of predicting whether the equipment needs maintenance, and there is still a lack of effective solutions for specific maintenance content, maintenance effects, and allocation of maintenance resources. Summary of the invention

[0005] In view of the deficiencies in the prior art, the object of the present invention is to provide an equipment maintenance prediction system and method for parts processing.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An equipment maintenance prediction system applied to parts processing, comprising an equipment maintenance prediction module, a preliminary maintenance determination module, a preliminary maintenance effect analysis module, and a re-determined maintenance determination module;

[0008] The equipment maintenance prediction module is used to determine the maintenance prediction cycle. When the equipment processes parts, each time a maintenance prediction cycle is experienced, the equipment maintenance value of the equipment is obtained, and based on the comparison result between the equipment maintenance value and the equipment maintenance threshold, it is predicted whether the equipment needs maintenance in the next maintenance prediction cycle;

[0009] The initial maintenance determination module determines the initial maintenance content of the equipment after predicting that the equipment needs maintenance in the next maintenance prediction cycle;

[0010] After determining the initial maintenance content of the equipment, the initial maintenance effect analysis module constructs maintenance simulation processing models of various initial maintenance contents, performs simulation processing of a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtains the maintenance effect value of each initial maintenance content;

[0011] The re-scheduled maintenance determination module determines the re-scheduled maintenance content of the equipment based on the comparison result of the maintenance effect value of the initial maintenance content and the maintenance effect threshold, and then performs maintenance processing on the equipment according to the re-scheduled maintenance content in the next maintenance prediction cycle.

[0012] Furthermore, the equipment maintenance value of the equipment is obtained as follows: obtain the maintenance prediction value of the equipment for various maintenance contents, sum and average the maintenance prediction values ​​of all maintenance contents to obtain the maintenance prediction mean FRts, match all maintenance contents in pairs, calculate the difference between the maintenance prediction values ​​of the two matched maintenance contents and take the absolute value to obtain the maintenance prediction gap value, sum and average all maintenance prediction gap values ​​to obtain the maintenance prediction gap mean HDM, and use the formula The equipment maintenance value Zwa of the equipment is obtained, where qa is the maintenance prediction mean coefficient and qb is the maintenance prediction gap mean coefficient.

[0013] Furthermore, the initial maintenance content of the equipment is determined, specifically: obtaining the maintenance prediction value of the equipment for various maintenance contents, setting the maintenance prediction standard value, and when the maintenance prediction value of the maintenance content is greater than or equal to the maintenance prediction standard value, marking the maintenance content as the initial maintenance content; when the maintenance prediction value of the maintenance content is less than the maintenance prediction standard value, no further processing is performed.

[0014] Furthermore, maintenance prediction values ​​of the equipment for various maintenance contents are obtained, specifically: all operating data of the equipment within the maintenance prediction period are collected, all operating data are preprocessed and combined into an operating data set, maintenance prediction models for various maintenance contents are obtained, and the operating data sets are respectively input into the maintenance prediction models for various maintenance contents. The maintenance prediction model for each maintenance content outputs a maintenance prediction value, thereby obtaining the maintenance prediction values ​​of the equipment for various maintenance contents.

[0015] Furthermore, the maintenance effect value of the initial maintenance content is obtained as follows: when the maintenance simulation processing model of the initial maintenance content is simulated, G maintenance effect time periods of equal length are divided within the maintenance prediction cycle, and the maintenance effect time period value BCgd of each maintenance effect time period is obtained, g = 1, 2, ..., G, g is the serial number of the maintenance effect time period, and the maintenance effect time period coefficient is set to Ztd, and the maintenance effect turbulence value Vopb is obtained. The formula The maintenance effect value Mak of the initial maintenance content is obtained.

[0016] Furthermore, the maintenance effect turbulence value Vopb is obtained as follows: all maintenance effect period values ​​are sorted in order of the maintenance effect periods, the difference between two adjacent maintenance effect period values ​​after sorting is calculated and the absolute value is taken to obtain the maintenance effect turbulence value, all maintenance effect turbulence values ​​are summed and the average is taken to obtain the maintenance effect turbulence value Vopb.

[0017] Furthermore, the maintenance effect period value of the maintenance effect period is obtained as follows: all parts processing data within the maintenance effect period are collected, all parts processing data are preprocessed and combined into a processing data set, a processing evaluation model is obtained, the processing data set is input into the processing evaluation model, and the processing evaluation model outputs the maintenance effect period value of the maintenance effect period.

[0018] Furthermore, a maintenance effect threshold is set. When the maintenance effect value of the initially determined maintenance content is greater than or equal to the maintenance effect threshold, the initially determined maintenance content is marked as a revised maintenance content. When the maintenance effect value of the initially determined maintenance content is less than the maintenance effect threshold, no further processing is performed. After determining the revised maintenance content of the equipment, the equipment is maintained according to the revised maintenance content in the next maintenance prediction cycle.

[0019] Furthermore, a method for predicting equipment maintenance applied to parts processing includes the following steps:

[0020] Step 1: Determine the maintenance prediction cycle. When the equipment processes parts, each time a maintenance prediction cycle is experienced, obtain the equipment maintenance value of the equipment. Based on the comparison result between the equipment maintenance value and the equipment maintenance threshold, predict whether the equipment needs maintenance in the next maintenance prediction cycle.

[0021] Step 2: After predicting that the equipment needs maintenance in the next maintenance forecast cycle, determine the initial maintenance content of the equipment;

[0022] Step 3: After determining the initial maintenance content of the equipment, build maintenance simulation processing models for various initial maintenance contents, perform simulation processing for a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtain the maintenance effect value of each initial maintenance content;

[0023] Step 4: Based on the comparison result between the maintenance effect value of the initial maintenance content and the maintenance effect threshold, determine the revised maintenance content of the equipment, and then perform maintenance processing on the equipment according to the revised maintenance content in the next maintenance forecast cycle.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. The method of the present invention can quickly and accurately determine the maintenance content that needs to be maintained for the equipment in the next maintenance forecast cycle, and then reasonably allocate the maintenance resources of the equipment, avoid invalid maintenance operations of the equipment, and reduce the waste of maintenance resources;

[0026] 2. Set up the equipment maintenance prediction module and the initial maintenance determination module to regularly perform predictive analysis on the equipment maintenance, combine the equipment operation data with the deep learning model, accurately predict whether the equipment needs maintenance in the next maintenance prediction cycle, and simultaneously determine the initial maintenance content of the equipment. Set up the initial maintenance effect analysis module and the revised maintenance determination module to perform in-depth simulation analysis on the maintenance effect of each initial maintenance content of the equipment, and accurately predict the maintenance effect of each initial maintenance content. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A method flow chart of a method for predicting equipment maintenance applied to parts processing;

[0028] Figure 2 A prediction flow chart for predicting whether the equipment needs maintenance in the next maintenance prediction cycle;

[0029] Figure 3 This is a system module diagram of an equipment maintenance prediction system used in parts processing. DETAILED DESCRIPTION

[0030] Example 1: Reference Figure 1 , a method for predicting equipment maintenance applied to parts processing, comprising the following steps:

[0031] Step 1: Determine the maintenance prediction cycle. When the equipment processes parts, each time a maintenance prediction cycle is experienced, obtain the equipment maintenance value of the equipment. Based on the comparison result between the equipment maintenance value and the equipment maintenance threshold, predict whether the equipment needs maintenance in the next maintenance prediction cycle.

[0032] Step 2: After predicting that the equipment needs maintenance in the next maintenance forecast cycle, determine the initial maintenance content of the equipment;

[0033] Step 3: After determining the initial maintenance content of the equipment, build maintenance simulation processing models for various initial maintenance contents, perform simulation processing for a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtain the maintenance effect value of each initial maintenance content;

[0034] Step 4: Based on the comparison result between the maintenance effect value of the initial maintenance content and the maintenance effect threshold, determine the revised maintenance content of the equipment, and then perform maintenance processing on the equipment according to the revised maintenance content in the next maintenance forecast cycle.

[0035] The above method can quickly and accurately determine the maintenance content that the equipment needs to perform in the next maintenance forecast cycle, and then reasonably allocate the maintenance resources of the equipment, avoid invalid maintenance operations on the equipment, and reduce the waste of maintenance resources.

[0036] Example 2: Reference Figures 2 to 3 , an equipment maintenance prediction system applied to parts processing, including an equipment maintenance prediction module, a preliminary maintenance determination module, a preliminary maintenance effect analysis module, and a re-determined maintenance determination module.

[0037] Equipment maintenance prediction module: Determine the maintenance prediction cycle (the maintenance prediction cycle is a time period, the length of which is set according to the equipment processing requirements). When the equipment processes parts, it obtains the equipment maintenance value of the equipment and sets the equipment maintenance threshold (the equipment maintenance threshold is a preset value, and the preset value size is custom set) after each maintenance prediction cycle. When the equipment maintenance value of the equipment is greater than or equal to the equipment maintenance threshold, it is predicted that the equipment needs maintenance in the next maintenance prediction cycle. When the equipment maintenance value of the equipment is less than the equipment maintenance threshold, no further processing is performed.

[0038] The equipment maintenance value of the equipment is obtained as follows: obtain the maintenance prediction value of the equipment for various maintenance contents, sum and average the maintenance prediction values ​​of all maintenance contents to obtain the maintenance prediction mean FRts, match all maintenance contents in pairs, calculate the difference between the maintenance prediction values ​​of the two matched maintenance contents and take the absolute value to obtain the maintenance prediction gap value, sum and average all maintenance prediction gap values ​​to obtain the maintenance prediction gap mean HDM, and use the formula The equipment maintenance value Zwa of the equipment is obtained, where qa is the maintenance prediction mean coefficient, qb is the maintenance prediction gap mean coefficient, the value of qa is 0.92, and the value of qb is 1.58.

[0039] Obtain maintenance prediction values ​​for various maintenance contents of the equipment, specifically: collect all operating data of the equipment within the maintenance prediction period (operating data includes but is not limited to power data, current and voltage data, operating time data, temperature data, pressure data, and energy consumption data), preprocess all operating data and combine them into an operating data set, obtain maintenance prediction models for various maintenance contents (maintenance contents include but are not limited to replacement of wearing parts, equipment lubrication, equipment tightening, and all maintenance contents of the equipment in daily use), input the operating data sets into the maintenance prediction models of various maintenance contents respectively, and the maintenance prediction model of each maintenance content outputs a maintenance prediction value, thereby obtaining the maintenance prediction values ​​of the equipment for various maintenance contents.

[0040] All operation data are preprocessed and combined into an operation data set. Specifically, all operation data of the equipment are cleaned and converted, and the cleaned and converted operation data are integrated into a unified data set to obtain the operation data set.

[0041] Each maintenance content has different judgment criteria, so different maintenance contents correspond to different maintenance prediction models. Each maintenance prediction model is constructed by a deep learning model. This embodiment takes equipment cleaning as an example to disclose the construction method of the maintenance prediction model: collect k groups of operation data sets, build a deep learning model, use the operation data sets as training data for the deep learning model, and assign a maintenance prediction value to each training data. The range of the maintenance prediction value is (1.1 to 3.9). The closer the maintenance prediction value is to 3.9, the more it is predicted that the equipment needs to be cleaned in the next maintenance prediction cycle, and the higher the maintenance prediction value is. The closer the value is to 1.1, the less likely the equipment needs to be cleaned in the next maintenance prediction cycle (if a maintenance prediction model for replacement of wearing parts is constructed, the closer the maintenance prediction value is to 3.9, the more likely the equipment needs to be replaced in the next maintenance prediction cycle; the closer the maintenance prediction value is to 1.1, the less likely the equipment needs to be replaced in the next maintenance prediction cycle). The training data is divided into a training set, a validation set, and a test set in a ratio of 2:1:1. The training set, validation set, and test set are trained. After the training, a maintenance prediction model for equipment cleaning is constructed.

[0042] Initial maintenance determination module: after predicting that the equipment needs maintenance in the next maintenance forecast cycle, determine the initial maintenance content of the equipment.

[0043] Determine the initial maintenance content of the equipment, specifically: obtain the maintenance prediction value of the equipment for various maintenance contents, set the maintenance prediction standard value (the maintenance prediction standard value is a preset value, and the preset value size is custom set). When the maintenance prediction value of the maintenance content is greater than or equal to the maintenance prediction standard value, the maintenance content is marked as the initial maintenance content. When the maintenance prediction value of the maintenance content is less than the maintenance prediction standard value, no further processing is performed.

[0044] By setting up an equipment maintenance prediction module and a preliminary maintenance determination module, you can regularly perform predictive analysis on equipment maintenance, combine the equipment's operating data with the deep learning model, accurately predict whether the equipment needs maintenance in the next maintenance prediction cycle, and simultaneously determine the equipment's preliminary maintenance content.

[0045] Initial maintenance effect analysis module: After determining the initial maintenance content of the equipment, build maintenance simulation processing models for various initial maintenance contents, perform simulation processing for a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtain the maintenance effect value of each initial maintenance content.

[0046] The maintenance simulation processing model of the initial maintenance content is constructed as follows: specifically: determine an initial maintenance content, obtain the current processing parameters of the equipment and the historical processing data (the processing parameters of the equipment include but are not limited to the processing path, cutting speed, spindle speed, feed rate, and the historical processing data include but are not limited to the number of processed parts and the type of processed parts), and construct a maintenance simulation processing model based on the determined initial maintenance content, the processing parameters of the equipment and the historical processing data.

[0047] This embodiment takes equipment lubrication as the initial maintenance content and discloses a method for constructing a maintenance simulation processing model for equipment lubrication: select equipment simulation software (equipment simulation software such as SolidWorks Simulation and ANSYS can be selected), create a new model in the equipment simulation software, add equipment entities and component entities to the model according to the processing parameters of the equipment and historical processing data, set appropriate parameters for the equipment entity and the component entity, such as the cutting speed, feed speed, material of the component, size of the component, etc. of the equipment, and adjust the friction coefficient of the equipment entity to the minimum (that is, ensure that there is no equipment lubrication problem during the processing of the equipment. If equipment tightening is taken as the initial maintenance content, the vibration coefficient of the equipment entity is adjusted to the minimum), thereby completing the construction of the maintenance simulation processing model for equipment lubrication.

[0048] The maintenance effect value of the initial maintenance content is obtained as follows: when the maintenance simulation processing model of the initial maintenance content is simulated, the maintenance prediction period is divided into G maintenance effect periods of equal length, and the maintenance effect period value BCgd of each maintenance effect period is obtained, g = 1, 2, ..., G, g is the serial number of the maintenance effect period, and the maintenance effect period coefficient is set to Ztd, d = 1, 2, ..., d, Zt1 < Zt2 < Zt3 < ... < Ztd, and each maintenance effect period coefficient is set to correspond to a range of maintenance effect period values, where , the range of maintenance effect period value includes (0, BCg1], (BCg1, BCg2], …, (BCgd-1, BCgd], when BCgd∈(0, BCg1], the maintenance effect period coefficient is Zt1, all maintenance effect period values ​​are sorted in the order of maintenance effect period, the difference between the two adjacent maintenance effect period values ​​after sorting is calculated and the absolute value is taken to obtain the maintenance effect turbulence value, all maintenance effect turbulence values ​​are summed and averaged to obtain the maintenance effect turbulence value Vopb, using the formula The maintenance effect value Mak of the initial maintenance content is obtained.

[0049] The maintenance effect period value of the maintenance effect period is obtained as follows: collect all parts processing data within the maintenance effect period (parts processing data includes but is not limited to processing accuracy data, processing efficiency data, and material utilization rate data), pre-process all parts processing data and combine them into a processing data set, obtain a processing evaluation model, input the processing data set into the processing evaluation model, and the processing evaluation model outputs the maintenance effect period value of the maintenance effect period.

[0050] The construction method of the processing evaluation model is as follows: collect group b processing data sets, build a deep learning model, use the processing data sets as training data for the deep learning model, assign a maintenance effect period value to each training data, and the value range of the maintenance effect period value is (0.1~0.9). The closer the maintenance effect period value is to 0.9, the better the processing effect of the equipment on the parts in the maintenance effect period value. The closer the maintenance effect period value is to 0.1, the worse the processing effect of the equipment on the parts in the maintenance effect period value. The training data is divided into training set, validation set and test set in a ratio of 3:2:1, and the training set, validation set and test set are trained. After the training, the processing evaluation model is constructed.

[0051] Re-determined maintenance determination module: Set the maintenance effect threshold (the maintenance effect threshold is a preset value, and the preset value size is custom set). When the maintenance effect value of the initial maintenance content is greater than or equal to the maintenance effect threshold, the initial maintenance content is marked as re-determined maintenance content. When the maintenance effect value of the initial maintenance content is less than the maintenance effect threshold, no further processing is performed. After determining the re-determined maintenance content of the equipment, the equipment is maintained according to the re-determined maintenance content in the next maintenance forecast cycle.

[0052] By setting up an initial maintenance effect analysis module and a revised maintenance determination module, the maintenance effect of each initial maintenance content of the equipment can be deeply simulated and analyzed, and the maintenance effect of each initial maintenance content can be accurately predicted, so as to quickly and accurately determine the maintenance content that needs to be maintained in the next maintenance prediction cycle, and then reasonably allocate the maintenance resources of the equipment, avoid invalid maintenance operations on the equipment, and reduce the waste of maintenance resources.

[0053] The above formulas are all dimensionless and numerical calculations are performed, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0054] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0055] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0057] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0059] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0060] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An equipment maintenance prediction system applied to parts processing, characterized in that: It includes equipment maintenance prediction module, initial maintenance determination module, initial maintenance effect analysis module, and re-determined maintenance determination module; The equipment maintenance prediction module is used to determine the maintenance prediction cycle. When the equipment processes parts, each time a maintenance prediction cycle is experienced, the equipment maintenance value of the equipment is obtained, and based on the comparison result between the equipment maintenance value and the equipment maintenance threshold, it is predicted whether the equipment needs maintenance in the next maintenance prediction cycle; The initial maintenance determination module determines the initial maintenance content of the equipment after predicting that the equipment needs maintenance in the next maintenance prediction cycle; After determining the initial maintenance content of the equipment, the initial maintenance effect analysis module constructs maintenance simulation processing models of various initial maintenance contents, performs simulation processing of a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtains the maintenance effect value of each initial maintenance content; The re-scheduled maintenance determination module determines the re-scheduled maintenance content of the equipment based on the comparison result of the maintenance effect value of the initial maintenance content and the maintenance effect threshold, and then performs maintenance processing on the equipment according to the re-scheduled maintenance content in the next maintenance prediction cycle.

2. The equipment maintenance prediction system for parts processing according to claim 1 is characterized in that: The equipment maintenance value of the equipment is obtained as follows: obtain the maintenance prediction value of the equipment for various maintenance contents, sum and average the maintenance prediction values ​​of all maintenance contents to obtain the maintenance prediction mean FRts, match all maintenance contents in pairs, calculate the difference between the maintenance prediction values ​​of the two matched maintenance contents and take the absolute value to obtain the maintenance prediction gap value, sum and average all maintenance prediction gap values ​​to obtain the maintenance prediction gap mean HDM, and use the formula The equipment maintenance value Zwa of the equipment is obtained, where qa is the maintenance prediction mean coefficient and qb is the maintenance prediction gap mean coefficient.

3. The equipment maintenance prediction system for parts processing according to claim 1 is characterized in that: Determine the initial maintenance content of the equipment, specifically: obtain the maintenance prediction value of the equipment for various maintenance contents, set the maintenance prediction standard value, when the maintenance prediction value of the maintenance content is greater than or equal to the maintenance prediction standard value, mark the maintenance content as the initial maintenance content, when the maintenance prediction value of the maintenance content is less than the maintenance prediction standard value, no further processing is performed.

4. The equipment maintenance prediction system for parts processing according to claim 2 is characterized in that: Obtain the maintenance prediction value of the equipment for various maintenance contents, specifically: collect all operation data of the equipment within the maintenance prediction period, preprocess all operation data and combine them into an operation data set, obtain maintenance prediction models for various maintenance contents, input the operation data sets into the maintenance prediction models of various maintenance contents respectively, and the maintenance prediction model of each maintenance content outputs a maintenance prediction value, thereby obtaining the maintenance prediction value of the equipment for various maintenance contents.

5. The equipment maintenance prediction system for parts processing according to claim 1 is characterized in that: The maintenance effect value of the initial maintenance content is obtained as follows: When the maintenance simulation processing model of the initial maintenance content is simulated, G maintenance effect periods of equal length are divided within the maintenance prediction cycle, and the maintenance effect period value BCgd of each maintenance effect period is obtained, g = 1, 2, ..., G, g is the serial number of the maintenance effect period, and the maintenance effect period coefficient is set to Ztd. The maintenance effect turbulence value Vopb is obtained, and the formula is used The maintenance effect value Mak of the initial maintenance content is obtained.

6. The equipment maintenance prediction system for parts processing according to claim 5 is characterized in that: The maintenance effect turbulence value Vopb is obtained as follows: all maintenance effect period values ​​are sorted in the order of the maintenance effect periods, the difference between the two adjacent maintenance effect period values ​​after sorting is calculated and the absolute value is taken to obtain the maintenance effect turbulence value, all maintenance effect turbulence values ​​are summed up and the average is taken to obtain the maintenance effect turbulence value Vopb.

7. The equipment maintenance prediction system for parts processing according to claim 5 is characterized in that: The maintenance effect period value of the maintenance effect period is obtained as follows: collect all parts processing data within the maintenance effect period, preprocess all parts processing data and combine them into a processing data set, obtain a processing evaluation model, input the processing data set into the processing evaluation model, and the processing evaluation model outputs the maintenance effect period value of the maintenance effect period.

8. The equipment maintenance prediction system for parts processing according to claim 1 is characterized in that: Set a maintenance effect threshold. When the maintenance effect value of the initially determined maintenance content is greater than or equal to the maintenance effect threshold, the initially determined maintenance content is marked as a revised maintenance content. When the maintenance effect value of the initially determined maintenance content is less than the maintenance effect threshold, no further processing is performed. After determining the revised maintenance content of the equipment, the equipment is maintained according to the revised maintenance content in the next maintenance forecast cycle.

9. A method for predicting equipment maintenance applied to parts processing, applied to a system for predicting equipment maintenance applied to parts processing as claimed in any one of claims 1 to 8, characterized in that: The steps include: Step 1: Determine the maintenance prediction cycle. When the equipment processes parts, each time a maintenance prediction cycle is experienced, obtain the equipment maintenance value of the equipment. Based on the comparison result between the equipment maintenance value and the equipment maintenance threshold, predict whether the equipment needs maintenance in the next maintenance prediction cycle. Step 2: After predicting that the equipment needs maintenance in the next maintenance forecast cycle, determine the initial maintenance content of the equipment; Step 3: After determining the initial maintenance content of the equipment, build maintenance simulation processing models for various initial maintenance contents, perform simulation processing for a maintenance prediction cycle on the maintenance simulation processing model of each initial maintenance content, and obtain the maintenance effect value of each initial maintenance content; Step 4: Based on the comparison result between the maintenance effect value of the initial maintenance content and the maintenance effect threshold, determine the revised maintenance content of the equipment, and then perform maintenance processing on the equipment according to the revised maintenance content in the next maintenance forecast cycle.

Images