A method and device for repairing electromechanical equipment

By comprehensively considering the full life cycle cost and maintenance methods of electromechanical equipment, and optimizing the maintenance plan, the problem of high maintenance costs in the existing technology is solved, and a cost-effective maintenance plan is achieved, and production efficiency is improved.

CN118469411BActive Publication Date: 2024-11-15ZHEJIANG EXPRESSWAY INFO ENG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410941410.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-15
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

The existing mechanical and electrical equipment maintenance methods lack the optimization of maintenance costs, resulting in waste of maintenance resources and high emergency maintenance costs, affecting production continuity and economic benefits.

Method used

By obtaining the quality evaluation information, historical inspection data and maintenance records of electromechanical equipment, the full life cycle cost of the equipment is determined, and the most economical maintenance time and method are calculated based on the current value of the equipment and the estimated cost of different maintenance methods. Technology such as the Holt-Winters model, improved Gaussian functions and generative adversarial networks perform data preprocessing and optimize maintenance plans.

Benefits of technology

It achieves the minimization of maintenance costs while ensuring the operating efficiency and safety of equipment, improves economic benefits, and avoids the waste of maintenance resources and the high costs brought by emergency repairs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118469411B_ABST
    Figure CN118469411B_ABST
Patent Text Reader

Abstract

The present invention is applicable to the field of equipment maintenance, and provides a method and device for the maintenance of electromechanical equipment. In this embodiment, the quality score curve of the electromechanical equipment is first determined through the quality evaluation information, historical inspection data and maintenance records of the electromechanical equipment. Then, the full life cycle cost and the total cost curve of the electromechanical equipment are determined through the purchase cost, operating cost, estimated maintenance cost and the present value of the electromechanical equipment. Then, the target maintenance time and maintenance method with the highest economic benefit are determined based on the quality score curve, the total cost curve and the present value of the electromechanical equipment. This achieves the goal of minimizing maintenance costs and improving economic benefits while ensuring the operating efficiency and safety of the equipment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of equipment maintenance, and in particular to a method and device for repairing electromechanical equipment. Background Art

[0002] With the development of industrial automation and intelligence, electromechanical equipment plays an increasingly important role in the production process. However, electromechanical equipment will inevitably suffer from wear and aging during use, which not only affects the operating efficiency of the equipment, but may also lead to production interruptions and safety accidents. Therefore, effective repair and maintenance of electromechanical equipment is the key to ensuring production continuity and safe operation of equipment.

[0003] At present, the maintenance methods of electromechanical equipment mainly rely on two modes: regular inspection and post-fault maintenance. Although the regular inspection mode can prevent the occurrence of some faults, it often leads to waste of maintenance resources or inaccurate maintenance timing due to the lack of real-time monitoring and accurate evaluation of equipment status. Although the post-fault maintenance mode can cope with sudden equipment failures, this passive maintenance method is often accompanied by high emergency maintenance costs and production losses.

[0004] In order to solve the above problems, technicians in this field have proposed a predictive maintenance method based on equipment condition monitoring. This method collects the operating data of the equipment, uses statistical analysis or machine learning and other technologies to predict possible equipment failures, and arranges maintenance plans accordingly. However, most of the existing predictive maintenance methods focus on the prediction of failures, while ignoring the optimization of maintenance costs. In actual operation, the control of maintenance costs is equally important because it is directly related to the economic benefits of the enterprise. Summary of the invention

[0005] In view of this, the present application provides a method and device for repairing electromechanical equipment, which can not only accurately predict the time point of equipment failure, but also comprehensively consider the equipment present value, operating cost, maintenance cost and the estimated cost of different repair methods, so as to calculate the most economical repair date. Through this method, enterprises can minimize maintenance costs and improve economic benefits while ensuring the efficiency and safety of equipment operation.

[0006] The first aspect of the present application provides a method for repairing electromechanical equipment, the method comprising:

[0007] Acquire quality evaluation information, historical inspection data and maintenance records of target electromechanical equipment, and determine a quality score curve of the target electromechanical equipment, wherein the quality evaluation information includes several different types of evaluation indicators;

[0008] Determine the purchase cost CI, operation cost COM, estimated maintenance cost CF and equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment based on the purchase cost, operation cost, estimated maintenance cost and equipment present value, and determine the equipment present value curve of the target electromechanical equipment based on the full life cycle cost;

[0009] A cost difference curve is determined according to the total cost curve and the equipment present value of the target electromechanical equipment, a date corresponding to the minimum absolute value of the cost difference on the cost difference curve is determined as the target maintenance time of the target electromechanical equipment, a maintenance method corresponding to the target maintenance time is determined through the quality score curve, and maintenance is performed using the maintenance method when the target maintenance time is reached.

[0010] Optionally, after repairing the target electromechanical equipment when the target repair time is reached, the method further includes:

[0011] The quality score curve of the target electromechanical equipment after maintenance is updated, and the maintenance time of the target electromechanical equipment is determined again according to the updated quality score curve and the equipment present value curve.

[0012] Optionally, before determining the life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the method further includes:

[0013] Performing anomaly detection on the purchase cost, the operating cost, the estimated maintenance cost, and the equipment present value by using a time series anomaly detection method based on the Holt-Winters model to generate first preprocessed data;

[0014] Detecting and eliminating the first preprocessed data by an outlier detection method based on an improved Gaussian function to generate second preprocessed data;

[0015] The second preprocessed data is subjected to data standardization processing based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data;

[0016] The full life cycle cost of the target electromechanical equipment is determined using the target data.

[0017] Optionally, obtaining quality evaluation information of the target electromechanical equipment includes:

[0018] The initial scores of different types of evaluation indicators are obtained, the weight values ​​of different types of evaluation indicators are determined by the hierarchical analysis method, the final scores of each evaluation indicator are determined by the product of the scores and the weight values, and the quality evaluation information is determined by the final scores.

[0019] Optionally, determining the weight values ​​of different types of evaluation indicators by using the hierarchical analysis method includes:

[0020] Compare each evaluation index in pairs to determine the judgment matrix of the evaluation index ;

[0021] Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax;

[0022] The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.

[0023] A second aspect of the present application provides a mechanical and electrical equipment maintenance device, the device comprising:

[0024] A first curve determination unit is used to obtain quality evaluation information, historical inspection data and maintenance records of the target electromechanical equipment, and determine the quality score curve of the target electromechanical equipment, wherein the quality evaluation information includes several different types of evaluation indicators;

[0025] a second curve determination unit, configured to determine the purchase cost CI, the operating cost COM, the estimated maintenance cost CF and the equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the equipment present value, and determine the equipment present value curve of the target electromechanical equipment according to the full life cycle cost;

[0026] A maintenance time determination unit is used to determine a cost difference curve according to the total cost curve and the equipment present value of the target electromechanical equipment, determine the date corresponding to the minimum absolute value of the cost difference on the cost difference curve as the target maintenance time of the target electromechanical equipment, determine the maintenance method corresponding to the target maintenance time through the quality score curve, and perform maintenance through the maintenance method when the target maintenance time is reached.

[0027] Optionally, after repairing the target electromechanical equipment when the target repair time is reached, the device further includes:

[0028] The maintenance time updating unit is used to update the quality score curve of the target electromechanical equipment after maintenance, and to determine the maintenance time of the target electromechanical equipment again through the updated quality score curve and the equipment present value curve.

[0029] Optionally, before determining the life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the device further includes:

[0030] A data preprocessing unit, configured to perform anomaly detection on the purchase cost, the operating cost, the estimated maintenance cost and the equipment present value by using a time series anomaly detection method based on a Holt-Winters model, and generate first preprocessed data;

[0031] Detecting and eliminating the first preprocessed data by an outlier detection method based on an improved Gaussian function to generate second preprocessed data;

[0032] The second preprocessed data is subjected to data standardization processing based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data;

[0033] The full life cycle cost of the target electromechanical equipment is determined using the target data.

[0034] Optionally, the obtaining of quality evaluation information of the target electromechanical equipment in the first curve determining unit includes:

[0035] The initial scores of different types of evaluation indicators are obtained, the weight values ​​of different types of evaluation indicators are determined by the hierarchical analysis method, the final scores of each evaluation indicator are determined by the product of the scores and the weight values, and the quality evaluation information is determined by the final scores.

[0036] Optionally, the determining of the weight values ​​of different types of evaluation indicators by the hierarchical analysis method in the first curve determining unit includes:

[0037] Compare each evaluation index in pairs to determine the judgment matrix of the evaluation index ;

[0038] Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax;

[0039] The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.

[0040] In the embodiment provided in the present application, the quality score curve of the electromechanical equipment is first determined through the quality evaluation information, historical inspection data and maintenance records of the electromechanical equipment. The full life cycle cost and the total cost curve of the electromechanical equipment are then determined through the purchase cost, operating cost, estimated maintenance cost and the present value of the equipment. Then, the target maintenance time and maintenance method with the highest economic benefits are determined based on the quality score curve, the total cost curve and the present value of the electromechanical equipment. This achieves the goal of minimizing maintenance costs and improving economic benefits while ensuring the operating efficiency and safety of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of the method provided in the embodiment of the present application;

[0042] Figure 2 A graph provided for an embodiment of the present application;

[0043] Figure 3 A graph provided for another embodiment of the present application;

[0044] Figure 4 A graph provided for another embodiment of the present application;

[0045] Figure 5 A graph provided for another embodiment of the present application;

[0046] Figure 6 A graph provided for another embodiment of the present application;

[0047] Figure 7 This is a diagram of the device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0049] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0050] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0051] The present application provides a method and device for repairing electromechanical equipment to ensure the operating efficiency and safety of the electromechanical equipment while minimizing the repair cost and improving economic benefits.

[0052] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0053] like Figure 1 As shown, it is a flow chart of a method for repairing electromechanical equipment provided by the present application, and the process may include the following steps:

[0054] Step S101, obtaining quality evaluation information, historical inspection data and maintenance records of target electromechanical equipment, and determining a quality score curve of the target electromechanical equipment.

[0055] In this embodiment, the above-mentioned quality evaluation information includes several different types of evaluation indicators. When selecting different types of evaluation indicators, it is possible to use the survey of transportation industry experts, operating managers, engineers and the reference of relevant national standards to determine that the evaluation of the operating status of electromechanical equipment should be based on the operating status of electromechanical equipment, equipment maintenance management and equipment failure conditions. The evaluation indicator system should be established, and then specific evaluation indicators are selected. After determining the evaluation indicators, the specific indicator values ​​of each indicator are determined. For different types of evaluation indicators, the method of determining the indicator value is also different. For example, for quantitative indicator evaluation, such as voltage, current, failure rate, etc., a quantitative evaluation method should be adopted, and the data measured on site should be extrapolated, and then processed in combination with relevant national standards. For qualitative indicator evaluation, the expert group can conduct qualitative evaluation in combination with relevant national standards and personal experience, and give a reasonable scoring range for the indicators to be evaluated based on on-site observation and query of historical operation records. When implementing the measurement and evaluation of qualitative indicators, the indicator scoring adopts the set value statistical method, and the expert group scores its status based on on-site observation. Taking the evaluation indicator as output voltage as an example, the quality evaluation information obtained is shown in the following table:

[0056] Rating Measured output voltage (V) Rating range 1 [217.8,222.2] [90,100] 2 [213.4,217.8) or(222.2,226.6] [80,90) 3 [209,213.4) or (226.6,231] [60,80) 4 [198,209) or (231,242] [30,60)

[0057] The above table records the scores for different index values ​​of output voltage, thus providing a basis for determining the quality score of the electromechanical equipment.

[0058] The historical inspection data and maintenance records can be obtained from the historical data of the target electromechanical equipment. Combined with the quality evaluation information, the quality score curve of the target electromechanical equipment is calibrated, where the ordinate is the quality score of the target electromechanical equipment and the abscissa is time. The life status of the electromechanical equipment can be recorded through this curve. Taking UPS uninterruptible power supply as an example, the quality score curve is as follows: Figure 2 shown.

[0059] In another embodiment, obtaining quality evaluation information of the target electromechanical device includes:

[0060] The initial scores of different types of evaluation indicators are obtained, the weight values ​​of different types of evaluation indicators are determined by the hierarchical analysis method, the final scores of each evaluation indicator are determined by the product of the scores and the weight values, and the quality evaluation information is determined by the final scores.

[0061] In this embodiment, corresponding weight values ​​are assigned to different evaluation indicators according to their importance. To give a simple example, taking UPS equipment as an example, through the expert scoring table of UPS equipment, experts combine their personal experience and score the importance of the next-level indicators for the previous-level indicators to determine the indicator weights. Finally, the average value of all experts' scores on a certain indicator is taken as the weight of the indicator, and the weights of each indicator are obtained as follows. A=[B1, B2, B3]=[0.78, 0.11, 0.11], A is a set of evaluation indicators, B1, B2, B3 are evaluation indicators of different types. B1=[C11, C12, C13, C14, C15]=[0.17, 0.17, 0.18, 0.34, 0.13], B2=[C21]=[1], B3=[C31]=[1]. According to the membership function, the membership of each indicator at each level of the measured value on 2022 / 2 / 16 can be obtained, and the fuzzy matrix is ​​obtained as follows: , R2=[C21]=[1 0 0 0 0], R3=[C31]=[0.50.5 0 0 0], the first-level fuzzy result is U1=B1*R1=[0.85,0.15,0,0,0]. U2=[1,0,0,0,0],U3=[0.5,0.5,0,0,0]. The second-level fuzzy result is U=A*R=[0.83,0.17,0,0,0]. Then determine the quality score distinction point set V={100,90,80,60,30}, through G=U*V T =[0.83,0.17,0,0,0]* =98.3, the quality score of the UPS device on 2022 / 2 / 16 is 98.3. Through the above method, the quality score of the target electromechanical equipment at each time can be determined, thereby determining the corresponding quality score curve.

[0062] In another embodiment, determining the weight values ​​of different types of evaluation indicators by using the hierarchical analysis method includes:

[0063] Compare each evaluation index in pairs to determine the judgment matrix A of the evaluation index;

[0064] Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax;

[0065] The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.

[0066] In this embodiment, the characteristic vector ωi is normalized by the formula Wi=(ωi / Σωi), (i=1…n), so that the sum of the determined weight value vector Wi is 1, thereby determining the weight value of each evaluation index.

[0067] Step S102, determine the purchase cost CI, operating cost COM, estimated maintenance cost CF and equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment based on the purchase cost, operating cost, estimated maintenance cost and equipment present value, and determine the equipment present value curve of the target electromechanical equipment based on the full life cycle cost.

[0068] In this embodiment, the cost input of the whole life cycle of the equipment mainly includes four parts: the first is the purchase cost CI of the equipment; the second is the operating cost of the equipment, which includes the running cost and maintenance cost, which is generally called the operating cost COM, involving related energy consumption costs and personnel costs such as inspections; the third is the maintenance cost CF of the equipment. In addition to the maintenance cost, the cost of updating the equipment involved in the scrapping and updating stage of the equipment is used as the estimated maintenance cost of the scrapping stage; the fourth is the present value CR of the equipment, that is, the residual value of the equipment. The equipment cost does not involve the cost of dismantling the equipment. The whole life cycle cost of the target electromechanical equipment is determined by the formula LCC=CI+COM+CF-CR, where LCC represents the whole life cycle cost.

[0069] In the process of determining LCC according to different times, the total cost curve of the equipment is calculated by combining the quality scores of the target electromechanical equipment at different times, such as Figure 3 shown.

[0070] In another embodiment, before determining the life cycle cost of the target electromechanical equipment based on the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the method further includes:

[0071] The above purchase cost, operating cost, estimated maintenance cost and equipment present value are preprocessed to remove invalid values. The specific method is as follows:

[0072] Performing anomaly detection on the purchase cost, the operating cost, the estimated maintenance cost, and the equipment present value by using a time series anomaly detection method based on the Holt-Winters model to generate first preprocessed data;

[0073] Detecting and eliminating the first preprocessed data by an outlier detection method based on an improved Gaussian function to generate second preprocessed data;

[0074] The second preprocessed data is subjected to data standardization processing based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data;

[0075] The full life cycle cost of the target electromechanical equipment is determined using the target data.

[0076] Step S103, determining a cost difference curve according to the total cost curve and the equipment present value of the target electromechanical equipment, determining the date corresponding to the minimum absolute value of the cost difference on the cost difference curve as the target maintenance time of the target electromechanical equipment, determining the maintenance method corresponding to the target maintenance time through the quality score curve, and performing maintenance through the maintenance method when the target maintenance time is reached.

[0077] In this embodiment, through the one-to-one correspondence between the quality score and the preset maintenance suggestion, the cost of performing different types of maintenance at different time points corresponding to different quality scores is determined by the above-mentioned quality score curve, and the optimal solution is selected by comparing various solutions.

[0078] Taking UPS as an example, the estimated maintenance costs for different maintenance operations of this equipment are shown in the following table:

[0079] Quality score 90-100 80-90 60-80 30-60 0-30 Repair suggestions Inspection and maintenance Minor repair Intermediate revision Overhaul scrapped Estimated repair costs 0 Original value of equipment*3% Original value of equipment*10% Original value of equipment*35% 12000

[0080] Calculate the time point corresponding to the median of each score segment, and then find the equipment present value, operating cost and maintenance cost at the corresponding time point through the total cost curve, and then determine the estimated cost of different maintenance methods, and finally calculate the total cost. Then subtract the sum of operating cost, maintenance cost and repair cost from the equipment present value, and determine the cost difference curve as follows: Figure 4 As shown. Figure 4When the value is greater than 0, the residual value of the equipment is lower than the cost of operating and maintaining the equipment. Therefore, the day before this is the most economical maintenance point, and the date when the cost difference is 0 is 1864 days. In other words, the economic benefit of repairing the electromechanical equipment is the highest when it is used for 1864 days. From the quality score curve, it is determined that the quality score at 1864 days is between 60 and 80 points. According to the above estimated maintenance cost table, it is determined that medium maintenance is required, and the cost is the original value of the equipment * 10%.

[0081] In another embodiment, after the target electromechanical device is repaired when the target repair time is reached, the method further includes:

[0082] The quality score curve of the target electromechanical equipment after maintenance is updated, and the maintenance time of the target electromechanical equipment is determined again according to the updated quality score curve and the total cost curve.

[0083] In this embodiment, taking the UPS uninterruptible power supply as an example, after the maintenance on the 1864th day, the quality score is improved. At this time, the quality score curve re-determined by the above method is as follows: Figure 5 The cost difference curve determined by the re-determined quality fraction curve is shown in Figure 6 As shown. Figure 6 It can be seen that the time required for further maintenance is 2092 days.

[0084] So far, completed Figure 1 The process shown.

[0085] In the embodiment of the present application, the quality score curve of the electromechanical equipment is first determined through the quality evaluation information, historical inspection data and maintenance records of the electromechanical equipment. Then, the full life cycle cost and the total cost curve of the electromechanical equipment are determined through the purchase cost, operating cost, estimated maintenance cost and the present value of the equipment. Then, the target maintenance time and maintenance method with the highest economic benefit are determined based on the quality score curve, the total cost curve and the present value of the electromechanical equipment. This achieves the goal of minimizing maintenance costs and improving economic benefits while ensuring the operating efficiency and safety of the equipment.

[0086] like Figure 7 As shown, the present application also provides a mechanical and electrical equipment maintenance device, the device comprising:

[0087] The first curve determination unit 701 is used to obtain quality evaluation information, historical inspection data and maintenance records of the target electromechanical equipment, and determine the quality score curve of the target electromechanical equipment, wherein the quality evaluation information includes several different types of evaluation indicators;

[0088] The second curve determination unit 702 is used to determine the purchase cost CI, the operating cost COM, the estimated maintenance cost CF and the equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the equipment present value, and determine the equipment present value curve of the target electromechanical equipment according to the full life cycle cost;

[0089] The maintenance time determination unit 703 is used to determine the total cost curve of the target electromechanical equipment through the equipment present value curve and the quality score curve, and determine the date corresponding to the minimum absolute value of the cost difference on the total cost curve as the target maintenance time of the target electromechanical equipment, and repair the target electromechanical equipment when the target maintenance time is reached.

[0090] In another embodiment, after the target electromechanical equipment is repaired when the target repair time is reached, the apparatus further comprises:

[0091] The maintenance time updating unit 704 is used to update the quality score curve of the target electromechanical equipment after maintenance, and re-determine the maintenance time of the target electromechanical equipment through the updated quality score curve and the equipment present value curve.

[0092] In another embodiment, before determining the life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the device further includes:

[0093] The data preprocessing unit 705 is used to perform anomaly detection on the purchase cost, operating cost, estimated maintenance cost and equipment present value by using a time series anomaly detection method based on the Holt-Winters model to generate first preprocessed data;

[0094] Detecting and eliminating the first preprocessed data by an outlier detection method based on an improved Gaussian function to generate second preprocessed data;

[0095] The second preprocessed data is subjected to data standardization processing based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data;

[0096] The full life cycle cost of the target electromechanical equipment is determined using the target data.

[0097] In another embodiment, obtaining the quality evaluation information of the target electromechanical device in the first curve determination unit includes:

[0098] The initial scores of different types of evaluation indicators are obtained, the weight values ​​of different types of evaluation indicators are determined by the hierarchical analysis method, the final scores of each evaluation indicator are determined by the product of the scores and the weight values, and the quality evaluation information is determined by the final scores.

[0099] In another embodiment, the determining of the weight values ​​of different types of evaluation indicators by the hierarchical analysis method in the first curve determining unit includes:

[0100] Compare each evaluation index in pairs to determine the judgment matrix of the evaluation index;

[0101] Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax;

[0102] The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.

[0103] The above embodiment of the present invention provides a method for repairing electromechanical equipment, and based on the method, provides a device for repairing electromechanical equipment. Through the above method and device, the present application can solve the problems of traditional soil health assessment methods being time-consuming, labor-intensive, costly, poor in data interpretability, and lacking in dynamic monitoring.

[0104] This embodiment also discloses a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement any of the above-mentioned regional soil health assessment methods based on machine learning.

[0105] In addition, in the implementation of the regional soil health assessment device based on machine learning, the logical division of each program module is only an example. In actual applications, the above functions can be assigned to different program modules as needed, for example, for the convenience of corresponding hardware configuration requirements or software implementation. That is, the internal structure of the regional soil health assessment device based on machine learning is divided into different program modules to complete all or part of the functions described above.

[0106] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for repairing electromechanical equipment, It is characterized in that The method comprises: Acquire quality evaluation information, historical inspection data and maintenance records of the target electromechanical equipment, determine the quality score of the target electromechanical equipment at each time, so as to obtain a quality score curve of the target electromechanical equipment, wherein the quality evaluation information includes several different types of evaluation indicators; Determine the purchase cost CI, operating cost COM, estimated maintenance cost CF and equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment based on the purchase cost, operating cost, estimated maintenance cost and equipment present value, and determine the total cost curve of the target electromechanical equipment based on the full life cycle cost; A cost difference curve is determined according to the total cost curve, the quality score curve, the preset estimated maintenance cost and the equipment present value of the target electromechanical equipment, the date corresponding to the minimum absolute value of the cost difference on the cost difference curve is determined as the target maintenance time of the target electromechanical equipment, the maintenance method corresponding to the target maintenance time is determined by the quality score curve, and maintenance is performed by the maintenance method when the target maintenance time is reached.

2. The method according to claim 1, It is characterized in that After the target electromechanical equipment is repaired when the target repair time is reached, the method further includes: The quality score curve of the target electromechanical equipment after maintenance is updated, and the maintenance time of the target electromechanical equipment is re-determined through the updated quality score curve, the total cost curve, the preset estimated maintenance cost and the equipment present value of the target electromechanical equipment.

3. The method according to claim 1, It is characterized in that Before determining the life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the method further includes: Performing anomaly detection on the purchase cost, the operating cost, the estimated maintenance cost, and the equipment present value by using a time series anomaly detection method based on the Holt-Winters model to generate first preprocessed data; Detecting and eliminating the first preprocessed data by using an outlier detection method based on an improved Gaussian function to generate second preprocessed data; The second preprocessed data is subjected to a data standardization process based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data; The full life cycle cost of the target electromechanical equipment is determined using the target data.

4. The method according to claim 1, It is characterized in that The obtaining of quality evaluation information of the target electromechanical equipment includes: Obtain the initial scores of different types of evaluation indicators, determine the weight values ​​of different types of evaluation indicators through hierarchical analysis, determine the final scores of each evaluation indicator through the product of the initial scores and the weight values, and determine the quality evaluation information through the final scores.

5. The method according to claim 4, It is characterized in that Determining the weight values ​​of different types of evaluation indicators by the hierarchical analysis method includes: Compare each evaluation index in pairs to determine the judgment matrix of the evaluation index ; Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax; The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.

6. A mechanical and electrical equipment maintenance device, It is characterized in that The device comprises: A first curve determination unit is used to obtain quality evaluation information, historical inspection data and maintenance records of the target electromechanical equipment, determine the quality score of the target electromechanical equipment at each time, so as to obtain a quality score curve of the target electromechanical equipment, wherein the quality evaluation information includes a plurality of different types of evaluation indicators; a second curve determination unit, configured to determine the purchase cost CI, the operating cost COM, the estimated maintenance cost CF and the equipment present value CR of the target electromechanical equipment, and determine the full life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the equipment present value, and determine the total cost curve of the target electromechanical equipment according to the full life cycle cost; A maintenance time determination unit is used to determine a cost difference curve according to the total cost curve, the quality score curve, a preset estimated maintenance cost and the equipment present value of the target electromechanical equipment, determine the date corresponding to the minimum absolute value of the cost difference on the cost difference curve as the target maintenance time of the target electromechanical equipment, determine the maintenance method corresponding to the target maintenance time through the quality score curve, and perform maintenance through the maintenance method when the target maintenance time is reached.

7. The device according to claim 6, It is characterized in that After the target electromechanical equipment is repaired when the target repair time is reached, the device further comprises: The maintenance time updating unit is used to update the quality score curve of the target electromechanical equipment after maintenance, and re-determine the maintenance time of the target electromechanical equipment through the updated quality score curve, the total cost curve, the preset estimated maintenance cost and the equipment present value of the target electromechanical equipment.

8. The device according to claim 6, It is characterized in that Before determining the life cycle cost of the target electromechanical equipment according to the purchase cost, the operating cost, the estimated maintenance cost and the present value of the equipment, the device further includes: A data preprocessing unit, configured to perform anomaly detection on the purchase cost, the operating cost, the estimated maintenance cost and the equipment present value by using a time series anomaly detection method based on a Holt-Winters model, and generate first preprocessed data; Detecting and eliminating the first preprocessed data by using an outlier detection method based on an improved Gaussian function to generate second preprocessed data; The second preprocessed data is subjected to a data standardization process based on Min-Max, and the processed data is subjected to missing value completion based on a generative adversarial network to obtain target data; The full life cycle cost of the target electromechanical equipment is determined using the target data.

9. The device according to claim 6, It is characterized in that The first curve determination unit acquires the quality evaluation information of the target electromechanical equipment, including: Obtain the initial scores of different types of evaluation indicators, determine the weight values ​​of different types of evaluation indicators through hierarchical analysis, determine the final scores of each evaluation indicator through the product of the initial scores and the weight values, and determine the quality evaluation information through the final scores.

10. The device according to claim 9, It is characterized in that The step of determining the weight values ​​of different types of evaluation indicators by using the hierarchical analysis method in the first curve determination unit includes: Compare each evaluation index in pairs to determine the judgment matrix of the evaluation index ; Through the characteristic equation |λi- |=0 determines the maximum eigenvalue λmax of the judgment matrix, and calculates the eigenvector ωi corresponding to the λmax; The characteristic vector ωi is normalized to obtain an indicator weight value vector Wi, and the weight value of each evaluation indicator is determined according to the indicator weight value vector Wi.