Data processing method and device for maintenance interval optimization

Abstract

The invention discloses a data processing method and device for maintenance interval optimization. The method comprises the steps that to-be-processed data are acquired, and the to-be-processed data comprise related data used for representing the service life of a sample equipment part; reliability feature extraction processing is carried out on the to-be-processed data to obtain reliability feature data, and the reliability feature data is feature data used for representing the reliability of the equipment component; constructing a multi-target maintenance interval optimization model according to the reliability characteristic data; and solving the multi-target maintenance interval optimization model based on a maintenance interval optimization algorithm to obtain target maintenance interval data. According to the method, the multi-target optimal maintenance interval solution is obtained by performing solution processing based on the maintenance interval optimization algorithm on the constructed multi-target maintenance interval optimization model, so that the problem of relatively low accuracy of equipment maintenance interval decision in the prior art is solved, and the accuracy of the maintenance interval decision is improved.

Description

Technical Field

[0001] The present application relates to the field of equipment maintenance and support, and in particular, to a data processing method and device for optimizing maintenance intervals. Background Art

[0002] With the continuous development of manufacturing technology, equipment is gradually developing towards automation, multifunctionality and complex structure. In order to ensure the reliability and safety of equipment, more and more people are paying attention to the operating performance of the system. During the use of equipment, equipment aging, wear and failure will occur, resulting in a decrease in the reliability of the equipment. However, through appropriate maintenance means, the performance of the equipment can be restored to a certain extent, so that it can continue to operate in a qualified state. Maintenance and guarantee decision-making ability is one of the important means for the equipment market to test the effectiveness of equipment. For equipment with high reliability requirements, the current maintenance and guarantee mode is preventive maintenance, with scheduled maintenance as the main mode. For equipment with low reliability requirements, the current maintenance and guarantee mode is mainly post-maintenance, that is, post-failure maintenance. The realization of these two maintenance and guarantee modes is inseparable from the determination of maintenance intervals. Reasonable maintenance intervals can effectively ensure the reliability of equipment and continuously maintain the operating performance of equipment, but scheduled maintenance and post-maintenance have caused a waste of resources to a certain extent. Therefore.

[0003] By using computer simulation to optimize equipment maintenance intervals, the cost of improving equipment maintenance support can be effectively reduced. In the prior art, an equipment maintenance interval decision optimization method is constructed based on an analytical mathematical model. Since equipment is usually composed of multiple complex subsystems and components, the equipment maintenance interval decision needs to take into account multiple systems. The construction of an equipment maintenance support decision optimization method based on an analytical mathematical model requires a lot of calculations and analysis, which is computationally intensive, time-consuming, and wastes a lot of resources. Moreover, this method usually only considers part of the constraints and cannot well reflect the complexity and diversity of the actual maintenance process.

[0004] Therefore, the equipment maintenance interval decision in the prior art has the problem of low accuracy. Summary of the invention

[0005] The main purpose of this application is to provide a data processing method and device for maintenance interval optimization, so as to solve the technical problem of low accuracy of equipment maintenance interval decision-making in the prior art, and achieve the technical effect of improving the accuracy of equipment maintenance interval decision-making.

[0006] In order to achieve the above-mentioned purpose, in a first aspect of the present application, a data processing method for optimizing maintenance intervals is proposed, which is applied to an equipment maintenance decision system to optimize the maintenance intervals of equipment components. The method comprises:

[0007] Acquiring data to be processed, wherein the data to be processed includes relevant data for indicating the life of sample equipment components;

[0008] Performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data used to represent the reliability of equipment components;

[0009] Constructing a multi-objective maintenance interval optimization model according to the reliability characteristic data;

[0010] The multi-objective maintenance interval optimization model is solved based on a maintenance interval optimization algorithm to obtain target maintenance interval data.

[0011] Further, the data to be processed is subjected to reliability feature extraction processing to obtain reliability feature data, the reliability feature data including first reliability feature data and second reliability feature data, including:

[0012] Performing component life recognition processing on the data to be processed to obtain sample life data, wherein the sample life data is data used to represent the life of sample equipment components;

[0013] Performing reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data;

[0014] Constructing a reliability model according to the first reliability parameter data to obtain a first reliability model;

[0015] Performing life characteristic extraction processing based on the first reliability model on the data to be processed to obtain reliable life characteristic data, wherein the reliable life characteristic data is data used to represent life characteristics of sample equipment components;

[0016] The first reliability characteristic data is determined according to the first reliability model and the reliable life characteristic data.

[0017] Further, determining the first reliability characteristic data according to the first reliability model and the reliable life characteristic data includes:

[0018] Performing a reliability threshold calculation process on the first reliability model to obtain reliability threshold data;

[0019] constructing an availability model according to the first reliability model and the reliable life characteristic data to obtain an availability model, wherein the availability model is a model for representing the degree of use of computing equipment components;

[0020] Constructing a cost rate model according to the data to be processed to obtain a cost rate model, wherein the cost rate model is a model for representing the cost rate of the calculated equipment;

[0021] The first reliability characteristic data is obtained according to the availability model, the cost rate model and the reliability threshold data.

[0022] Further, the data to be processed is subjected to reliability feature extraction processing to obtain reliability feature data, the reliability feature data including first reliability feature data and second reliability feature data, including:

[0023] Performing component category-based identification processing on the data to be processed to obtain component category feature data, wherein the component category feature data is feature data used to represent the component category of the sample equipment;

[0024] Matching a reliable life analysis model corresponding to the component category characteristic data to obtain a second reliability model;

[0025] The data to be processed is subjected to reliable life characteristic analysis processing based on a second reliability model to obtain the second reliability characteristic data, wherein the second reliability characteristic data is data for representing reliable life interval characteristics of sample equipment components.

[0026] Furthermore, the multi-objective maintenance interval optimization model is solved based on a maintenance interval optimization algorithm to obtain target maintenance interval data including:

[0027] Initializing the multi-objective maintenance interval optimization model to obtain initialization overall data;

[0028] Performing individual characteristic data updating processing based on a preset multi-objective optimization algorithm on each individual in the initialized overall data to obtain updated individual characteristic data;

[0029] The updated individual characteristic data is subjected to judgment processing based on a preset convergence rule to obtain the target maintenance interval data,

[0030] If the updated individual characteristic data satisfies the preset convergence rule, obtaining the target maintenance interval data, wherein the target maintenance interval data includes the updated individual characteristic data;

[0031] If the updated individual feature data does not satisfy the preset convergence rule, the updated individual feature data is iteratively processed based on the preset multi-objective optimization algorithm until the preset convergence rule is satisfied to obtain the target maintenance interval data.

[0032] Furthermore, the individual characteristic data of each individual in the initialized overall data is updated based on a preset multi-objective optimization algorithm to obtain updated individual characteristic data including:

[0033] Performing screening processing on the initialized overall data based on individual position characteristics to obtain optimal overall data;

[0034] Performing an update process based on position characteristics on each individual in the optimal overall data to obtain the updated individual characteristic data.

[0035] According to a second aspect of the present application, a data processing device for optimizing maintenance intervals is proposed, which is applied to an equipment maintenance decision system to optimize maintenance intervals of equipment components. The device comprises:

[0036] A data acquisition module, used to acquire data to be processed, wherein the data to be processed includes relevant data for indicating the life of sample equipment components;

[0037] A reliability feature extraction module, used for performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data used to represent the reliability of equipment components;

[0038] A model building module, used to build a multi-objective maintenance interval optimization model according to the reliability characteristic data;

[0039] The solution module is used to perform a solution process on the multi-objective maintenance interval optimization model based on a maintenance interval optimization algorithm to obtain target maintenance interval data.

[0040] Furthermore, the reliability feature extraction module includes:

[0041] An identification module, used for performing identification processing of component life on the data to be processed to obtain sample life data, wherein the sample life data is data used to represent the life of sample equipment components;

[0042] A first reliability evaluation module, used for performing reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data;

[0043] A first reliability model module, used to construct a reliability model according to the first reliability parameter data to obtain a first reliability model;

[0044] A life characteristic extraction module, used for performing life characteristic extraction processing on the data to be processed based on the first reliability model to obtain reliable life characteristic data, wherein the reliable life characteristic data is data used to represent the life characteristics of sample equipment components;

[0045] The first reliability feature extraction module is used to determine the first reliability feature data according to the first reliability model and the reliable life feature data.

[0046] According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data processing method for optimizing maintenance intervals.

[0047] According to a fourth aspect of the present application, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the above-mentioned data processing method for optimizing maintenance intervals.

[0048] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0049] In the present application, by obtaining data to be processed, wherein the data to be processed includes relevant data for representing the life of sample equipment components; performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data for representing the reliability of equipment components; constructing a multi-objective maintenance interval optimization model based on the reliability feature data; performing a solution processing based on the maintenance interval optimization algorithm on the multi-objective maintenance interval optimization model to obtain target maintenance interval data. By performing a solution processing based on the maintenance interval optimization algorithm on the constructed multi-objective maintenance interval optimization model to obtain a multi-objective optimal maintenance interval solution, the problem of low accuracy of equipment maintenance interval decision-making in the prior art is solved, and the accuracy of maintenance interval decision-making is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0051] Figure 1 A flow chart of a data processing method for optimizing maintenance intervals provided in this application;

[0052] Figure 2 A flow chart of a data processing method for optimizing maintenance intervals provided in this application;

[0053] Figure 3A schematic diagram of a multi-objective maintenance interval optimization process provided for this application;

[0054] Figure 4 A flow chart of a data processing method for optimizing maintenance intervals provided in this application;

[0055] Figure 5 A schematic diagram of a maintenance interval optimization algorithm process provided in this application;

[0056] Figure 6 A flow chart of a data processing method for optimizing maintenance intervals provided in this application;

[0057] Figure 7 A schematic diagram of a data processing device for optimizing maintenance intervals provided in the present application;

[0058] Figure 8 A schematic diagram of another data processing device for optimizing maintenance intervals provided in the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0060] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0062] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0063] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] In the prior art, equipment maintenance and support decision optimization methods are usually based on analytical mathematical models, which require a lot of calculations and analysis, so the amount of calculations is large, time-consuming, and wastes a lot of resources. Moreover, this method usually only considers part of the constraints and cannot well reflect the complexity and diversity of the actual maintenance process. In response to the above problems, this application is proposed.

[0065] In an optional embodiment of the present application, a data processing method for optimizing maintenance intervals is proposed, which is applied to an equipment maintenance decision system to optimize the maintenance intervals of equipment components. Figure 1 A flowchart of a data processing method for optimizing maintenance intervals provided in this application, such as Figure 1 As shown, the method comprises the following steps:

[0066] S101: Obtaining data to be processed;

[0067] The data to be processed include relevant data for representing the life of sample equipment components. In the equipment maintenance decision system, when optimizing the maintenance interval of equipment components, relevant data on the life of sample equipment components are obtained. The sample equipment components are equipment components whose maintenance intervals are to be optimized, including obtaining historical life data of unified components on multiple identical equipment, constructing an optimization model corresponding to the maintenance interval of the equipment component based on the sample historical life data of the equipment component, and optimizing the maintenance interval of the equipment component through the optimization model corresponding to the maintenance interval of the equipment component.

[0068] S102: performing reliability feature extraction processing on the data to be processed to obtain reliability feature data;

[0069] The reliability characteristic data is characteristic data used to represent the reliability of equipment components, and the reliability characteristic data includes first reliability characteristic data and second reliability characteristic data.

[0070] In another optional embodiment of the present application, a data processing method for optimizing maintenance intervals is proposed. Figure 2 A flowchart of a data processing method for optimizing maintenance intervals provided in this application, such as Figure 2 As shown, the method comprises the following steps:

[0071] S201: performing component life recognition processing on the data to be processed to obtain sample life data;

[0072] The sample life data is data for indicating the life of sample equipment components.

[0073] S202: performing reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data;

[0074] The sample life data includes life data of multiple samples. The data distribution in the sample life data sets is different. The sample life data sets are subjected to parameter estimation processing based on a preset parameter estimation algorithm to obtain parameter data, wherein the parameter data is used to construct a multi-objective maintenance interval optimization model for the sample life equipment.

[0075] In an embodiment of the present application, reliability assessment processing is performed on the sample life data based on a preset parameter estimation algorithm, including: performing GM parameter estimation processing on the sample life data to obtain a first characteristic parameter, and after the GM parameter estimation, performing support vector regression (SVR) parameter estimation processing to obtain a second characteristic parameter, wherein the first reliability parameter data includes the first characteristic parameter and the second characteristic parameter.

[0076] S203: constructing a reliability model according to the first reliability parameter data to obtain a first reliability model;

[0077] Identify the first characteristic parameter and the second characteristic parameter in the first reliability parameter data, wherein the second characteristic parameter is a position parameter used to represent the reliability model to be constructed, and the second characteristic parameter includes a shape parameter and a scale parameter of the reliability model to be constructed, and a reliability function is obtained based on the density function according to the above parameters.

[0078] S204: performing life feature extraction processing on the data to be processed based on the first reliability model to obtain reliable life feature data;

[0079] The reliable life characteristic data is data used to represent the life characteristics of the sample equipment components. The reliable life of each individual in the sample equipment component life data is calculated according to the reliability function constructed as described above to obtain the first reliable life characteristic data. The average life of the sample equipment component life data is processed to obtain the second reliable life characteristic data. The reliable life characteristic data includes the first reliable life characteristic data and the second reliable life characteristic data.

[0080] S205: Determine first reliability characteristic data according to the first reliability model and the reliable life characteristic data.

[0081] Figure 3 This is a schematic diagram of a multi-objective maintenance interval optimization process provided by the present application. In another optional embodiment of the present application, a data processing method for maintenance interval optimization is proposed, including:

[0082] The reliability threshold value of the first reliability model is calculated and processed to obtain the reliability threshold value data; the availability model is constructed according to the first reliability model and the reliable life characteristic data to obtain the availability model, wherein the availability model is a model used to represent the degree of use of the computing equipment components, and the availability calculation formula is:

[0083]

[0084] Among them, T p is the preventive maintenance time, T f is the repair time after failure, T is the maintenance interval, and R(T) is the above reliability function.

[0085] A cost rate model is constructed according to the data to be processed to obtain a cost rate model, wherein the cost rate model is a model used to represent the cost rate of equipment, and the cost rate C(T) calculation formula is:

[0086]

[0087] Among them, C(T) is the unit time cost; E I Long averaging period; E C is the expected loss in a single cycle.

[0088] The first reliability characteristic data is obtained according to the availability model, the cost rate model and the reliability threshold data.

[0089] In an embodiment of the present application, by combining the availability model and the cost rate model, in the process of multi-objective equipment maintenance interval optimization, the cost rate and availability are simultaneously used as optimization objectives, a multi-objective maintenance interval optimization model is constructed, and the optimal maintenance interval of components under multi-objective conditions is obtained, thereby improving the accuracy of component maintenance intervals.

[0090] In another optional embodiment of the present application, a data processing method for optimizing maintenance intervals is proposed. Figure 4 A flowchart of a data processing method for optimizing maintenance intervals provided in this application, such as Figure 4 As shown, the method comprises the following steps:

[0091] S301: performing component category-based identification processing on the data to be processed to obtain component category feature data;

[0092] The component category characteristic data is characteristic data for indicating the category of the sample equipment component.

[0093] S302: matching a reliable life analysis model corresponding to the component category feature data to obtain a second reliability model;

[0094] Equipment component categories correspond to different reliable life analysis models. The reliable life analysis equation is used to analyze the impact of faults on reliable life. Different components correspond to different fault analyses. A plurality of reliable life analysis models are stored in the preset equipment maintenance decision system database. The corresponding reliable life analysis model is matched in the preset system database by component category so that the reliable life analysis model can analyze the historical life data of equipment components to obtain second reliability characteristic data.

[0095] S303: Perform reliable life characteristic analysis on the data to be processed based on the second reliability model to obtain second reliability characteristic data.

[0096] The second reliability characteristic data is data used to represent the reliable life interval characteristics of sample equipment components. The historical life data of the equipment components is analyzed through the above-mentioned reliable life analysis model corresponding to the component category to obtain the reliable life interval data of the equipment components and the second reliability characteristic data.

[0097] S103: constructing a multi-objective maintenance interval optimization model according to the reliability characteristic data;

[0098] According to the above reliability characteristic data, a multi-objective maintenance interval optimization model is established with reliability threshold as constraint and maximum availability and minimum cost rate as optimization objectives.

[0099] S104: performing a solution process based on a maintenance interval optimization algorithm on the multi-objective maintenance interval optimization model to obtain target maintenance interval data.

[0100] like Figure 5 As shown, Figure 5 A schematic diagram of a maintenance interval optimization algorithm process provided in the present application, the maintenance interval optimization algorithm is an algorithm processing based on the improvement of the multi-objective Coati optimization algorithm, and the maintenance interval optimization algorithm obtained by improving the multi-objective Coati optimization algorithm realizes the multi-objective maintenance interval optimization model and obtains the optimal maintenance interval data under multi-objective conditions. In the embodiment of the present application, by improving the multi-objective Coati optimization algorithm as described above, the algorithm performance is improved, and the efficiency of equipment maintenance interval optimization is improved.

[0101] In another optional embodiment of the present application, a data processing method for optimizing maintenance intervals is proposed. Figure 6 A flowchart of a data processing method for optimizing maintenance intervals provided in this application, such as Figure 6 As shown, the method comprises the following steps:

[0102] S401: Initializing the multi-objective maintenance interval optimization model to obtain initialization overall data;

[0103] S402: performing individual characteristic data updating processing based on a preset multi-objective optimization algorithm on each individual in the initialized overall data to obtain updated individual characteristic data;

[0104] In another optional embodiment of the present application, a data processing method for optimizing maintenance intervals is proposed, comprising:

[0105] The initialized overall data is screened based on individual position features to obtain optimal overall data; each individual in the optimal overall data is updated based on position features to obtain updated individual feature data.

[0106] Initialize the population, set the number of algorithm iterations, inertia weight, population size, external archive size, learning factor, position limit, speed limit, and initialize the speed and position of the population; calculate the fitness value of the position of each individual in the population; use the quick sort method to obtain the non-dominated solution set; update and select the best historical position of each individual in the population; implement the position learning strategy for each individual in the elite population; update the external archive, control the archive size based on the crowding distance, calculate the crowding distance of the position of each individual in the population in the external archive, sort the crowding distance in descending order, and delete the redundant individuals at the end; update the position of each individual in the global optimal population, randomly select the position of each individual in a preset number of populations in the external archive as the position of each individual in the global optimal population, to guide the iterative update of the next generation; update the speed and position of each individual in the population according to the speed and position update formula of the position of the individual in the population.

[0107] In an optional embodiment of the present application, the crowding distance determines the diversity of the position group of each individual in the population by the density around a solution. In the process of updating the above individual feature data, the fitness value is calculated by the fitness function, and the position of each individual in the top-ranked population is stored in an external archive by the quick sorting method. Then, the average distance of the position of each individual in the two populations around the position of each individual in each population is calculated. This average distance is the crowding distance of the position of each individual in the population. The position of each individual in the population is reordered by the size of the calculated crowding distance. In the external archive, the position of each individual in the population with a large crowding distance is replaced by the position of each individual in the population with a small crowding distance. The calculation formula of the above crowding distance is as follows:

[0108]

[0109] The maximum target value is set as max, the minimum target value is kept as min, and the crowding distances of these two extreme points are set to inf, i.e., infinity. i represents the i-th particle, f m (·) represents the fitness function.

[0110] At the same time, the external archive needs to be reordered to ensure that the number of Pareto solutions stored in the external archive does not exceed the maximum number of Pareto solutions stored in the external archive. When the number of Pareto solutions stored in the external archive has reached the maximum, the position of each individual in the new population is added to the external archive, and the Pareto solutions that exceed the number of Pareto solutions stored in the external archive need to be deleted to avoid the storage of non-dominated solutions in the external archive, thereby ensuring that the number of Pareto solutions stored in the external archive does not exceed the maximum number of Pareto solutions stored in the external archive. The above-mentioned external storage archive deletion processing method includes the following steps:

[0111] Calculate the crowding distance of each individual position in all populations in the external archive, and sort the crowding distances of each individual position in all populations from large to small;

[0112] According to the above sorting, the crowding distance relationship of the position of each individual in the population is obtained. If the minimum crowding distance value appears repeatedly, the position of each individual in one or more populations exceeding the maximum storage number is randomly selected and removed from the external storage archive;

[0113] Check whether the storage quantity of the external storage archive after removing the position of each individual in the population exceeds the maximum value. If it exceeds, repeat the above sorting and removal steps; if it does not exceed, end the external archive deletion operation.

[0114] In an optional embodiment of the present application, in the process of performing the position learning strategy of each individual in the elite population, Cauchy mutation is used to increase the diversity of the position of the individual in the population. The specific idea of ​​the position learning strategy of each individual in the elite population based on Cauchy mutation is to first copy the position of each individual in each population in the archive A into the position of each individual in a new population, and then perform a Cauchy mutation on the randomly selected variable on the dth dimension, and the formula is as follows:

[0115]

[0116] Where Cauchy(α,γ) is the Cauchy distribution with parameters α and γ. is the d-th dimension component of position i of each individual in the population, α is the location parameter that defines the peak position of the distribution, and γ is the scale parameter of the half width at half the maximum value, also known as the "elite learning rate", which decreases linearly with the number of iterations. max and γ min are the upper and lower bounds of γ, where the above γ max and γ min Can be set to, max =1.0 and γ min =0.1.

[0117] S403: Performing judgment processing on the updated individual characteristic data based on a preset convergence rule to obtain target maintenance interval data.

[0118] If the updated individual characteristic data satisfies the preset convergence rules, the target maintenance interval data is obtained, wherein the target maintenance interval data includes the updated individual characteristic data; if the updated individual characteristic data does not satisfy the preset convergence rules, the updated individual characteristic data is iteratively processed based on the preset multi-objective optimization algorithm until the preset convergence rules are satisfied, thereby obtaining the target maintenance interval data.

[0119] In another optional embodiment of the present application, a data processing method for maintenance interval optimization is proposed. After solving the multi-objective maintenance interval optimization model based on the maintenance interval optimization algorithm to obtain the target maintenance interval data, the method further includes:

[0120] The evaluation of the maintenance interval optimization algorithm includes: extracting algorithm evaluation feature data, including Spacing (SP), Inverted Generational Distance (IGD), and Hyper volume (HV), and evaluating the algorithm performance based on the above algorithm evaluation feature data, wherein the smaller the IGD value, the better the overall performance of the algorithm, including convergence and distribution. The smaller the Spacing value, the more uniform the distribution of the solution set. The larger the HV value, the better the overall performance of the algorithm.

[0121] In another optional embodiment of the present application, a data processing device for optimizing maintenance intervals is proposed. Figure 7 A schematic diagram of a data processing device for optimizing maintenance intervals provided in this application, such as Figure 7 As shown, the device comprises:

[0122] A data acquisition module 51 is used to acquire data to be processed, wherein the data to be processed includes relevant data for indicating the life of sample equipment components;

[0123] A reliability feature extraction module 52 is used to perform reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data used to represent the reliability of equipment components;

[0124] A model building module 53, used to build a multi-objective maintenance interval optimization model according to the reliability characteristic data;

[0125] The solution module 54 is used to perform a solution process on the multi-objective maintenance interval optimization model based on the maintenance interval optimization algorithm to obtain target maintenance interval data.

[0126] In another optional embodiment of the present application, a data processing device for optimizing maintenance intervals is proposed. Figure 8 A schematic diagram of another data processing device for optimizing maintenance intervals provided in this application, such as Figure 8 As shown, the device comprises:

[0127] An identification module 61 is used to perform identification processing on the component life of the data to be processed to obtain sample life data, wherein the sample life data is data used to represent the life of the sample equipment component;

[0128] A first reliability evaluation module 62, used to perform reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data;

[0129] A first reliability model module 63, used to construct a reliability model according to the first reliability parameter data to obtain a first reliability model;

[0130] The life characteristic extraction module 64 is used to perform life characteristic extraction processing on the data to be processed based on the first reliability model to obtain reliable life characteristic data, wherein the reliable life characteristic data is data used to represent the life characteristics of the sample equipment component;

[0131] The first reliability feature extraction module 65 is used to determine first reliability feature data according to the first reliability model and the reliable life feature data.

[0132] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0133] In summary, in the present application, by obtaining data to be processed, wherein the data to be processed includes relevant data for representing the life of sample equipment components; performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data for representing the reliability of equipment components; constructing a multi-objective maintenance interval optimization model based on the reliability feature data; performing a solution processing based on the maintenance interval optimization algorithm on the multi-objective maintenance interval optimization model to obtain target maintenance interval data. By performing a solution processing based on the maintenance interval optimization algorithm on the constructed multi-objective maintenance interval optimization model to obtain a multi-objective optimal maintenance interval solution, the problem of low accuracy of equipment maintenance interval decision-making in the prior art is solved, and the accuracy of maintenance interval decision-making is improved.

[0134] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0135] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0136] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for optimizing maintenance intervals, characterized in that: Applied in an equipment maintenance decision system to optimize the maintenance interval of equipment components, the method includes: Acquiring data to be processed, wherein the data to be processed includes relevant data for indicating the life of sample equipment components; Performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data used to represent the reliability of equipment components; Constructing a multi-objective maintenance interval optimization model according to the reliability characteristic data; The multi-objective maintenance interval optimization model is solved based on a maintenance interval optimization algorithm to obtain target maintenance interval data.

2. The data processing method according to claim 1, characterized in that: Performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, the reliability feature data including first reliability feature data and second reliability feature data, including: Performing component life recognition processing on the data to be processed to obtain sample life data, wherein the sample life data is data used to represent the life of sample equipment components; Performing reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data; Constructing a reliability model according to the first reliability parameter data to obtain a first reliability model; Performing life characteristic extraction processing based on the first reliability model on the data to be processed to obtain reliable life characteristic data, wherein the reliable life characteristic data is data used to represent life characteristics of sample equipment components; The first reliability characteristic data is determined according to the first reliability model and the reliable life characteristic data.

3. The data processing method according to claim 2, characterized in that: Determining the first reliability characteristic data according to the first reliability model and the reliable life characteristic data includes: Performing a reliability threshold calculation process on the first reliability model to obtain reliability threshold data; constructing an availability model according to the first reliability model and the reliable life characteristic data to obtain an availability model, wherein the availability model is a model for representing the degree of use of computing equipment components; Constructing a cost rate model according to the data to be processed to obtain a cost rate model, wherein the cost rate model is a model for representing the cost rate of the calculated equipment; The first reliability characteristic data is obtained according to the availability model, the cost rate model and the reliability threshold data.

4. The data processing method according to claim 1, characterized in that: Performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, the reliability feature data including first reliability feature data and second reliability feature data, including: Performing component category-based identification processing on the data to be processed to obtain component category feature data, wherein the component category feature data is feature data used to represent the component category of the sample equipment; Matching a reliable life analysis model corresponding to the component category characteristic data to obtain a second reliability model; The data to be processed is subjected to reliable life characteristic analysis processing based on a second reliability model to obtain the second reliability characteristic data, wherein the second reliability characteristic data is data for representing reliable life interval characteristics of sample equipment components.

5. The data processing method according to claim 1, characterized in that: The multi-objective maintenance interval optimization model is solved based on the maintenance interval optimization algorithm to obtain target maintenance interval data including: Initializing the multi-objective maintenance interval optimization model to obtain initialization overall data; Performing individual characteristic data updating processing based on a preset multi-objective optimization algorithm on each individual in the initialized overall data to obtain updated individual characteristic data; The updated individual characteristic data is subjected to judgment processing based on a preset convergence rule to obtain the target maintenance interval data, If the updated individual characteristic data satisfies the preset convergence rule, obtaining the target maintenance interval data, wherein the target maintenance interval data includes the updated individual characteristic data; If the updated individual feature data does not satisfy the preset convergence rule, the updated individual feature data is iteratively processed based on the preset multi-objective optimization algorithm until the preset convergence rule is satisfied to obtain the target maintenance interval data.

6. The data processing method according to claim 5, characterized in that: Performing individual characteristic data updating processing based on a preset multi-objective optimization algorithm on each individual in the initialized overall data, and obtaining updated individual characteristic data includes: Performing screening processing on the initialized overall data based on individual position characteristics to obtain optimal overall data; Performing an update process based on position characteristics on each individual in the optimal overall data to obtain the updated individual characteristic data.

7. A data processing device for optimizing maintenance intervals, characterized in that: Applied in an equipment maintenance decision system to optimize the maintenance interval of equipment components, the device comprises: A data acquisition module, used to acquire data to be processed, wherein the data to be processed includes relevant data for indicating the life of sample equipment components; A reliability feature extraction module, used for performing reliability feature extraction processing on the data to be processed to obtain reliability feature data, wherein the reliability feature data is feature data used to represent the reliability of equipment components; A model building module, used to build a multi-objective maintenance interval optimization model according to the reliability characteristic data; The solution module is used to perform a solution process on the multi-objective maintenance interval optimization model based on a maintenance interval optimization algorithm to obtain target maintenance interval data.

8. The data processing device according to claim 7, characterized in that: Reliability feature extraction module, including: An identification module, used for performing identification processing of component life on the data to be processed to obtain sample life data, wherein the sample life data is data used to represent the life of sample equipment components; A first reliability evaluation module, used for performing reliability evaluation processing on the sample life data based on a preset parameter estimation algorithm to obtain first reliability parameter data; A first reliability model module, used to construct a reliability model according to the first reliability parameter data to obtain a first reliability model; A life characteristic extraction module, used for performing life characteristic extraction processing on the data to be processed based on the first reliability model to obtain reliable life characteristic data, wherein the reliable life characteristic data is data used to represent the life characteristics of sample equipment components; The first reliability feature extraction module is used to determine the first reliability feature data according to the first reliability model and the reliable life feature data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data processing method for optimizing maintenance intervals according to any one of claims 1 to 6.

10. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the data processing method for maintenance interval optimization according to any one of claims 1 to 6.

Images