Method for dynamically adjusting inspection path under intelligent perception of working state

Abstract

The invention discloses an inspection path dynamic adjustment method under intelligent perception of a working state, and relates to the related technical field of inspection path optimization, and the method comprises the steps: obtaining equipment basic information of an inspection region; performing equipment fault probability analysis according to the equipment working state, the equipment model information and the equipment service duration to obtain an equipment fault probability; constructing a path repetition length fitness function and an equipment inspection sorting fitness function; constructing a comprehensive fitness function; performing routing inspection path optimization based on the equipment fault probability according to the comprehensive fitness function to obtain a recommended routing inspection path; and sending the recommended inspection path to the inspection mobile terminal. The technical problems of low inspection efficiency and unreasonable resource allocation caused by weak working state perception mobility and incapability of dynamically adapting to equipment working state change by inspection path planning in the prior art are solved, and the technical effects of improving the inspection efficiency, reducing the equipment fault risk and optimizing the resource utilization rate are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to inspection path optimization, and in particular to a method for dynamically adjusting inspection paths under intelligent perception of working status. Background Art

[0002] With the increasing requirements for industrial equipment maintenance and management, the planning and optimization of inspection paths has gradually become a key research area. However, traditional inspection path planning methods are usually based on fixed equipment distribution and static inspection strategies, lacking the ability to dynamically adjust. Especially when there are many types of equipment and complex and changeable working conditions, traditional inspection solutions are often difficult to adapt to actual needs, thus affecting inspection efficiency and equipment reliability. In addition, the mobility of equipment working status perception is weak, making it difficult to effectively apply it to inspection path adjustment and optimization, thus affecting inspection work efficiency.

[0003] Therefore, in the current relevant technologies, there are technical problems such as weak working status perception mobility and inability of inspection route planning to dynamically adapt to changes in equipment working status, resulting in low inspection efficiency and unreasonable resource allocation. Summary of the invention

[0004] This application solves the technical problems in the prior art that the working status perception has weak mobility and the inspection path planning cannot dynamically adapt to changes in the working status of equipment, resulting in low inspection efficiency and unreasonable resource allocation by providing a method for dynamically adjusting the inspection path under intelligent perception of the working status. This achieves the technical effect of improving inspection efficiency, reducing the risk of equipment failure and optimizing resource utilization.

[0005] The present application provides a method for dynamically adjusting an inspection path under intelligent perception of working status, including: obtaining basic information of equipment in an inspection area, wherein the basic information of the equipment includes equipment working status, equipment model information, equipment service time and equipment distribution location; performing equipment failure probability analysis according to the equipment working status, the equipment model information and the equipment service time to obtain equipment failure probability; constructing a path repetition length fitness function and an equipment inspection sorting fitness function, wherein the path repetition length fitness function is a function for evaluating the proportion of repeated sections in an inspection path, and the equipment inspection sorting fitness function is a function for evaluating whether the priority of inspection equipment is reasonable; configuring a first weight for the path repetition length fitness function, configuring a second weight for the equipment inspection sorting fitness function, and constructing a comprehensive fitness function; according to the comprehensive fitness function, optimizing the inspection path based on the equipment failure probability to obtain a recommended inspection path; and sending the recommended inspection path to an inspection mobile terminal.

[0006] In a possible implementation, an equipment failure probability analysis is performed based on the equipment working status, the equipment model information, and the equipment service time to obtain the equipment failure probability, and the following processing is performed: a fixed constraint condition is constructed based on the equipment service time and the equipment model information; a device working status attribute deviation threshold is obtained; a dynamic constraint condition is configured based on the device working status attribute deviation threshold; equipment operation samples are collected based on the fixed constraint conditions and the dynamic constraint conditions to obtain the proportion of the number of failure samples, which is set as the equipment failure probability.

[0007] In a possible implementation, equipment operation samples are collected according to the fixed constraints and the dynamic constraints, and a proportion of the number of faulty samples is obtained, which is set as the equipment failure probability. The following processing is also performed: according to the fixed constraints and the dynamic constraints, equipment operation samples are collected once to obtain a single equipment operation sample; the single sample fixed constraints and the single sample dynamic constraints of the single equipment operation sample are configured; according to the single sample fixed constraints and the single sample dynamic constraints, equipment operation samples are collected twice to obtain a secondary equipment operation sample; until the equipment operation samples are collected five times according to the four sample fixed constraints and the four sample dynamic constraints to obtain five equipment operation samples; the proportion of the number of faulty samples of the single equipment operation sample, the secondary equipment operation sample, and the fifth equipment operation sample is counted and set as the equipment failure probability.

[0008] In a possible implementation, statistics are given on the percentage of the number of faulty samples among the first device operation samples, the second device operation samples, and up to the fifth device operation samples, and the following processing is also performed: the five device operation samples are grouped according to the fourth device operation samples to obtain multiple groups of five device operation samples; until the second device operation samples are grouped according to the first device operation samples to obtain multiple groups of secondary device operation samples; recursive fault sample statistics are performed on the multiple groups of five device operation samples until the multiple groups of secondary device operation samples and the first device operation samples to obtain the percentage of the number of faulty samples.

[0009] In a possible implementation, recursive fault sample statistics are performed on the multiple groups of five device operation samples until the multiple groups of secondary device operation samples and the primary device operation samples to obtain the proportion of the number of fault samples, and the following processing is also performed: a primary sample aggregation weight, a secondary sample aggregation weight, and a fifth sample aggregation weight are configured, wherein the sum of the primary sample aggregation weight, the secondary sample aggregation weight, and the fifth sample aggregation weight is equal to 1; fault sample statistics are performed on the multiple groups of five device operation samples to obtain the proportion of the number of five fitting fault samples; recursively statistics are performed downward from the proportion of the number of five fitting fault samples until fault sample statistics are performed on the multiple groups of secondary device operation samples to obtain the proportion of the number of secondary fitting fault samples; the proportion of the number of primary fault samples of the primary device operation samples is counted; and according to the primary sample aggregation weight, the secondary sample aggregation weight, and the fifth sample aggregation weight, weighted mean statistics are performed on the proportion of the number of five fitting fault samples, the proportion of the number of secondary fitting fault samples, and the proportion of the number of primary fault samples to obtain the proportion of the number of fault samples.

[0010] In a possible implementation, fault sample statistics are performed on the multiple groups of five equipment operation samples to obtain the proportions of the number of five fitting fault samples, and the following processing is also performed: fault sample statistics are performed on the multiple groups of five equipment operation samples respectively to obtain the proportions of the number of multiple five fault samples; the numbers of multiple five equipment operation samples of the multiple groups of five equipment operation samples are calculated; the ratios of the numbers of the multiple five equipment operation samples to the total number of five equipment operation samples are calculated respectively to obtain the fitting weights of multiple five equipment operation samples, and weighted mean statistics are performed on the proportions of the multiple five fault samples to obtain the proportions of the number of five fitting fault samples.

[0011] In a possible implementation, a path repetition length fitness function and a device inspection sorting fitness function are constructed, and the following processing is performed: the path repetition length fitness function is used to count the length of the covered path of the inspection mobile terminal twice or more; based on the device failure probability, the device distribution positions are sorted to obtain the device distribution position sorting result; the device inspection sorting fitness function is used to calculate the inverse of the Hamming distance between the actual inspection position sequence and the device distribution position sorting result.

[0012] In a possible implementation, the recommended inspection path is sent to the inspection mobile terminal, and the following processing is performed: the intersection equipment distribution position of the inspected path and the recommended inspection path is obtained; the intersection equipment distribution position is deleted from the recommended inspection path, and an updated inspection path is obtained and sent to the inspection mobile terminal.

[0013] Through the method of dynamic adjustment of inspection paths under intelligent perception of working status proposed in this application, it is planned to obtain basic equipment information in the inspection area; analyze the probability of equipment failure according to the working status of the equipment, equipment model information, and equipment service time to obtain the probability of equipment failure; construct a path repetition length fitness function and an equipment inspection sorting fitness function; configure a first weight for the path repetition length fitness function, and configure a second weight for the equipment inspection sorting fitness function to construct a comprehensive fitness function; according to the comprehensive fitness function, optimize the inspection path based on the probability of equipment failure to obtain a recommended inspection path; send the recommended inspection path to the inspection mobile terminal. It solves the technical problems existing in the prior art that the working status perception has weak mobility and the inspection path planning cannot dynamically adapt to the changes in the working status of the equipment, resulting in low inspection efficiency and unreasonable resource allocation, and achieves the technical effect of improving inspection efficiency, reducing the risk of equipment failure, and optimizing resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A flow chart of a method for dynamically adjusting an inspection path under intelligent perception of a working status provided in an embodiment of the present application; Figure 2 A flow chart of obtaining the probability of equipment failure in the method for dynamically adjusting the inspection path under intelligent perception of the working status provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0019] The present application embodiment provides a method for dynamically adjusting the inspection path under intelligent perception of the working status, such as Figure 1 As shown, the method includes: Step S100, obtaining basic information of equipment in the inspection area, wherein the basic information of equipment includes equipment working status, equipment model information, equipment service time and equipment distribution location.

[0020] Preferably, obtaining basic information about the equipment in the inspection area refers to collecting data related to the basic properties and operating conditions of the equipment in the inspection area, mainly including the equipment working status, equipment model information, equipment service time and equipment distribution location. Specifically, the equipment working status refers to the current operating status of the equipment, including whether the equipment is in normal operation, standby, shutdown, overload or abnormal state, etc. The equipment working status may be obtained through sensor monitoring data (such as temperature, vibration, pressure, etc.) or real-time status information provided by the equipment control system, which is used to determine whether the equipment needs special attention or emergency inspection; equipment model information refers to the model and category information of the equipment, such as the brand, specifications, functional characteristics and applicable scenarios of the equipment, which are usually stored in Stored in the equipment management system or product technical documents, according to the different characteristics of the equipment (such as high-precision equipment or heavy-load equipment), adjust the inspection strategy or use special tools for inspection; equipment service life refers to the working time or service life of the equipment since it was put into use. It is estimated through the installation date or operation record of the equipment, combined with the service life curve of the equipment (such as wear and tear pattern or aging trend), evaluate the possible failure probability of the equipment, and include the equipment with longer service time in the priority inspection scope; equipment distribution location refers to the specific physical location of the equipment in the inspection area, including floor, area number, coordinate location, etc., usually obtained through GIS (geographic information system) data or equipment layout diagram, providing a geographical basis for inspection route planning. Through the basic information of the equipment, the inspection route can be dynamically optimized, the path duplication can be reduced, the key equipment can be inspected in time, the situation of missed inspection and repeated inspection can be reduced, and the inspection efficiency can be improved.

[0021] Step S200, performing equipment failure probability analysis based on the equipment working status, the equipment model information, and the equipment service time to obtain equipment failure probability.

[0022] Preferably, equipment failure probability analysis refers to evaluating and quantifying the possibility of equipment failure based on the acquired equipment working status, equipment model information and equipment service time to obtain the equipment failure probability. Specifically, the equipment status indicators (such as temperature, pressure, vibration, etc.) are collected through sensor data, and compared with the predetermined thresholds or standard models for analysis to evaluate the stability and failure risk of the equipment. The failure probability of equipment in normal status is low, and the failure probability of equipment in abnormal status (such as overload, overheating, excessive vibration, etc.) is significantly increased; different models of equipment have different design characteristics, performance differences and durability, and the failure probability varies depending on the equipment model. An association model between equipment model and historical failure records is established. Statistical analysis is performed based on historical data of equipment of the same model (such as average failure rate and main failure mode) to predict the possible failure probability of the current equipment. The longer the equipment is used, the more likely its components will age and wear out. The failure probability increases with the service time. For example, some equipment needs to be overhauled or have core components replaced after a certain period of service. Otherwise, the risk of failure will increase significantly. Based on the equipment life curve (such as the bathtub curve model), combined with the maintenance records and operation history of the specific equipment, the current remaining life and the possibility of failure are estimated. The equipment failure probability is then obtained. Through high failure probability warnings, the equipment can be set as an inspection focus and maintained or replaced in time to avoid production accidents.

[0023] Further, such as Figure 2 As shown, step S200 also includes step S210, constructing a fixed constraint condition based on the service time of the equipment and the equipment model information; step S220, obtaining a deviation threshold of the equipment working status attribute; step S230, configuring a dynamic constraint condition based on the deviation threshold of the equipment working status attribute; step S240, collecting equipment operation samples according to the fixed constraint condition and the dynamic constraint condition, obtaining the proportion of the number of fault samples, and setting it as the equipment failure probability.

[0024] Preferably, fixed constraints are constructed based on the service time of the equipment (the time or cumulative operating hours of the equipment since it was put into use) and the equipment model information (specifications, brand and design characteristics of the equipment), which means setting constraints based on the inherent attributes of the equipment (such as service time and model information). Specifically, based on the historical failure data of the equipment and the statistical model, a failure risk threshold is set for each model of equipment in different service time periods, and then the equipment working state attribute deviation threshold is obtained. The equipment working state attribute deviation refers to the degree to which the current operating parameters of the equipment (such as temperature, vibration, pressure, etc.) deviate from the normal range, that is, an allowable deviation range is set for each operating parameter as the deviation threshold, and exceeding this range is an abnormal state; then dynamic constraints are configured based on the equipment working state attribute deviation threshold, that is, the equipment is configured in real time. The operating conditions change with the change of equipment status. For example, the key parameter values ​​of the equipment during operation are collected and compared with the normal values ​​to determine whether they exceed the deviation threshold. The deviation degrees of different parameters have different weights, and the severity of the abnormal equipment operation status is comprehensively evaluated. Equipment operation sample collection based on fixed constraints and dynamic constraints refers to the real-time collection of equipment operation data through sensors, control systems, etc., including key parameter values ​​(such as temperature, pressure, speed, etc.), obtaining fault samples (equipment whose operating parameters exceed the set deviation threshold) and calculating the proportion of fault samples, that is, the ratio of the number of equipment fault samples to the total number of equipment operation samples, setting it as the failure probability, and then optimizing the inspection and maintenance strategies, reasonably adjusting the inspection frequency and maintenance resource allocation, and improving the reliability and safety of equipment operation.

[0025] Further, step S240 also includes step S241, collecting equipment operation samples once according to the fixed constraints and the dynamic constraints to obtain a single equipment operation sample; step S242, configuring the single sample fixed constraints and the single sample dynamic constraints of the single equipment operation sample; step S243, collecting equipment operation samples twice according to the single sample fixed constraints and the single sample dynamic constraints to obtain a secondary equipment operation sample; step S244, until collecting equipment operation samples five times according to four sample fixed constraints and four sample dynamic constraints to obtain five equipment operation samples; step S245, counting the proportion of the number of fault samples of the single equipment operation sample, the secondary equipment operation sample, and the fifth equipment operation sample, and setting it as the equipment failure probability.

[0026] Preferably, by collecting equipment operation samples multiple times and dynamically adjusting the constraints, the reliability and accuracy of the data are gradually improved, and the probability of equipment failure is finally obtained. Specifically, under the initial conditions, according to the fixed constraints (such as equipment model and service time) and the dynamic constraints (such as the attribute deviation threshold of the real-time operation status), the first sample collection is carried out, including the key parameters of the equipment operation (such as temperature, vibration, pressure, etc.) and whether they exceed the fixed and dynamic constraints, to obtain preliminary equipment operation sample data, and then according to the operation sample data collected once, the fixed constraints of the sample and the dynamic constraints of the sample are adjusted, that is, in combination with the results of the first sampling, the risk standards based on the service time and model of the equipment are refined or modified, and according to the distribution of the real-time parameters, the risk standards are readjusted. Deviation threshold is set to further improve the accuracy of samples; then, the equipment operation samples are collected again according to the fixed constraint conditions of the first sample and the dynamic constraint conditions of the first sample to obtain the secondary equipment operation samples; then, the constraint conditions are reconfigured after each sampling, the sampling parameters are gradually optimized, and the equipment operation samples are collected again. Each sampling is based on the constraint conditions adjusted for the previous time to ensure that the new sampling data can more accurately reflect the equipment operation status and failure risks. Through five progressive samplings, each time based on dynamic adjustment of fixed and dynamic constraints, a more comprehensive and accurate data set is finally formed. Finally, the number of failure samples of the first equipment operation sample, the second equipment operation sample, and the fifth equipment operation sample is counted, and the proportion of the number of failure samples is calculated and set as the equipment failure probability, which improves the reliability and scientificity of the failure probability.

[0027] Further, step S245 also includes step S2451, grouping the five equipment operation samples according to the four equipment operation samples to obtain multiple groups of five equipment operation samples; step S2452, until the secondary equipment operation samples are grouped according to the primary equipment operation samples to obtain multiple groups of secondary equipment operation samples; step S2453, recursively performing fault sample statistics on the multiple groups of five equipment operation samples until the multiple groups of secondary equipment operation samples and the primary equipment operation samples to obtain the proportion of the number of fault samples.

[0028] Preferably, five equipment operation samples are grouped according to four equipment operation samples to obtain multiple groups of five equipment operation samples, for example, divided into equipment type group 1, high priority equipment (such as key equipment), equipment type group 2, low priority equipment (such as secondary equipment). Similarly, the secondary equipment operation samples are grouped according to the primary equipment operation samples to obtain multiple groups of secondary equipment operation samples, until all equipment operation samples are grouped. In a hierarchical recursive manner, from the lowest level (such as the primary sample) to the highest level (such as the fifth sample), the number and proportion of faulty samples in each group are counted layer by layer, and finally the fault proportion of each group of samples is accumulated to obtain the proportion of the number of faulty samples. Multi-layer recursive analysis can capture the complex changing trend of equipment failure probability, improve prediction accuracy, and thus improve the level of intelligence of equipment operation and maintenance.

[0029] Further, step S2453 also includes step S2453a, configuring the first sample aggregation weight, the second sample aggregation weight, and up to the fifth sample aggregation weight, wherein the sum of the first sample aggregation weight, the second sample aggregation weight, and up to the five sample aggregation weights is equal to 1; step S2453b, performing fault sample statistics on the multiple groups of five equipment operation samples to obtain the proportion of the number of five fitting fault samples; step S2453c, recursively counting downward from the proportion of the number of five fitting fault samples until the fault sample statistics are performed on the multiple groups of secondary equipment operation samples to obtain the proportion of the number of secondary fitting fault samples; step S2453d, counting the proportion of the number of first fault samples of the first equipment operation sample; step S2453e, performing weighted mean statistics on the proportion of the number of five fitting fault samples, up to the proportion of the number of secondary fitting fault samples, and the proportion of the number of first fault samples according to the first sample aggregation weight, the second sample aggregation weight, and up to the five sample aggregation weights, to obtain the proportion of the number of fault samples.

[0030] Preferably, by assigning weights to equipment operation samples at different levels, the failure proportions of samples at each level are weighted and aggregated, and finally the comprehensive failure probability of the equipment is calculated. Specifically, the aggregation weights of the first sample, the second sample, and the fifth sample are configured. The aggregation weight of each sampling sample represents the importance of the sampling sample in the overall failure probability calculation. The sum of the weights of all levels is equal to 1, ensuring the normalization of the weighted mean statistics. For example, the configuration weights are 0.1 for the first sample, 0.15 for the second sample, 0.2 for the third sample, 0.25 for the fourth sample, and 0.3 for the fifth sample. The total weight satisfies that the sum of the aggregation weights is equal to 1. Then, the grouped equipment operation samples in each sampling are counted, and the proportion of the number of failure samples in each group is calculated. Then, the proportion results of each group are fitted to obtain the overall proportion of the number of failure samples at this level, and the proportion of the number of five fitted failure samples is obtained, which refers to the fitting result of the failure proportion of all groups at the fifth sample level.

[0031] Preferably, similarly, recursively perform downward from five sample fittings to two sample fittings, gradually aggregate the proportion of faulty samples, and then count the proportion of the number of faulty samples of the equipment operation sample once, that is, the proportion of the number of faulty samples directly counted by all grouped data at the level of the equipment operation sample once, and finally perform weighted calculation on the proportion of the number of faulty samples of samples at different levels through the five sample aggregation weights to obtain the proportion of the number of comprehensive faulty samples (that is, the probability of equipment failure). By configuring weights and performing weighted calculations, the deviation of single-layer data can be avoided, the accuracy of the overall assessment can be improved, and the failure risk of the equipment can be fully reflected.

[0032] Furthermore, step S2453b also includes step S2453b1, respectively performing fault sample statistics on the multiple groups of five equipment operation samples to obtain the proportion of the number of multiple five fault samples; step S2453b2 calculating the number of multiple five equipment operation samples of the multiple groups of five equipment operation samples; step S2453b3 respectively calculating the ratio of the number of multiple five equipment operation samples to the total number of five equipment operation samples to obtain the fitting weights of multiple five equipment operation samples, performing weighted mean statistics on the proportion of the number of multiple five fault samples to obtain the proportion of the five fitting fault samples.

[0033] Preferably, by performing fault statistics on each group of data respectively, and using the proportion of the number of samples in each group to the total number of samples as a weight, weighted mean statistics are performed on the grouping results, so as to obtain the proportion of the number of fitting fault samples at the five sampling levels. Specifically, the five sampling equipment operation samples are grouped according to specific rules (such as model, state or area), and the proportion of the number of fault samples of each group of samples is counted respectively to obtain multiple proportions of the number of five fault samples. The fault proportion of each group of samples reflects the failure probability of the group of equipment under specific conditions. The multiple five-time equipment operation proportions of multiple groups of five-time equipment operation samples are calculated. The number of equipment operation samples is calculated, and then the ratios of multiple five-time equipment operation samples and the total number of five-time equipment operation samples are calculated respectively. The ratio of the number of samples in each group to the total number of five sampling samples is used as the weight, that is, the fitting weights of multiple five-time equipment operation samples are obtained to reflect the contribution of each group of samples in the overall data. Finally, according to the ratio of the number of samples in each group, the proportion of faulty samples in each group is weightedly calculated to obtain the overall proportion of faulty samples at the five-sampling level, that is, the proportion of the number of five fitting faulty samples, to avoid the error caused by simple averaging, thereby effectively improving the scientificity and accuracy of fault probability assessment.

[0034] Step S300, constructing a path repetition length fitness function and a device inspection sorting fitness function, wherein the path repetition length fitness function is a function for evaluating the proportion of repeated sections in the inspection path, and the device inspection sorting fitness function is a function for evaluating whether the inspection device priority is reasonable.

[0035] Preferably, a path repetition length fitness function and an equipment inspection sorting fitness function are constructed to use mathematical models to quantify and evaluate the advantages and disadvantages of different inspection paths in the inspection path optimization process, so as to find the optimal path and solve the problems of repeated paths and inspection priority sorting in path planning respectively. Specifically, the geographical location information of the equipment in the inspection area is obtained, and the inspection path is initially generated, including each node (equipment location) and path. The inspection path is divided into several segments (such as from device A to device B as a segment), and then the movement trajectory data of the inspection personnel or the automated equipment is recorded, and the number of times each path is repeated is counted, and a threshold is set (such as more than 1 time is considered as a repetition), and then the path repetition length fitness function formula is designed as follows: ,in, Indicates the path repetition length fitness value (range 0~1, the closer to 1 the better), represents the total length of the repeated path, It represents the total length of the inspection path. The path repetition length fitness function is used to measure the degree of repeated passing through the same area or node in the inspection path. The purpose is to minimize the path repetition rate and improve the inspection efficiency. That is, assuming that the inspection path contains multiple nodes (equipment locations), the path repetition length is the cumulative length of passing through the same node or path segment multiple times during the inspection process. The path repetition rate is associated with the optimization target through a mathematical expression. The smaller the path repetition length fitness value, the better the inspection path. Minimizing the path repetition length fitness value means reducing unnecessary path repetitions, reducing inspection time and energy consumption, improving inspection efficiency, and ensuring that inspection personnel can cover more key equipment within a limited time.

[0036] Preferably, the equipment inspection ranking fitness function is used to evaluate the rationality of the equipment inspection sequence, with the purpose of giving priority to checking equipment with high failure probability or high importance, that is, assigning a priority to each device according to factors such as the importance and failure probability of the equipment, and calculating the fitness value according to whether the inspection sequence of the equipment conforms to the priority arrangement. Specifically, the basic information of the equipment is obtained, including the equipment failure probability, importance level, service time, and real-time working status. The failure probability or inspection priority score is evaluated based on the historical failure data and real-time status analysis of the equipment, and then the weight of the equipment is determined according to the criticality of the equipment to the system. Assuming that the equipment inspection sequence is , design fitness function ;in, Indicates The weight of each device (determined by importance or priority); It is The failure probability or inspection priority score of each device; the optimization goal is to maximize The equipment inspection sorting fitness function ensures that inspection resources are allocated preferentially to equipment with high failure probability or high importance, reducing the hidden dangers of failure of high-risk equipment due to delayed inspection.

[0037] Furthermore, step S300 also includes step S310, wherein the path repetition length fitness function is used to count the coverage path length of the inspection mobile terminal twice or more; step S320, based on the equipment failure probability, the equipment distribution positions are sorted to obtain the equipment distribution position sorting result; step S330, the equipment inspection sorting fitness function is used to calculate the inverse of the Hamming distance between the actual inspection position sequence and the equipment distribution position sorting result.

[0038] Preferably, the path repetition length fitness function is used to count the length of the covered path twice or more by the patrol mobile terminal, aiming to measure the efficiency of path planning and aiming to reduce repeated paths, wherein the covered path length refers to the actual path length of the patrol mobile terminal along the established route, and the repeated path refers to the same area or path segment passed by the patrol mobile terminal twice or more in a patrol task. The path repetition length fitness function counts the total length of the repeated covered path and minimizes the path repetition length; based on the failure probability of the equipment, the distribution location of the equipment is prioritized, that is, it is sorted from high to low according to the failure probability of the equipment, and at the same time combined with the physical distribution location of the equipment to form a reasonable inspection priority. The equipment inspection sorting fitness function calculates the degree of deviation between the actual inspection path and the equipment priority sorting, and uses the inverse of the Hamming distance as an evaluation indicator to measure the consistency between the inspection path and the priority sorting. The Hamming distance refers to the distance between the actual inspection position sequence and the equipment distribution position sorting result, indicating the degree of difference between the two. The calculation of the Hamming distance is to calculate the number of inconsistent elements in the corresponding positions for two sequences of equal length. The inverse of the Hamming distance is used to measure the matching degree between the actual inspection path and the priority sorting. The smaller the Hamming distance, the higher the equipment inspection sorting fitness value, thereby improving the accuracy of the inspection work and reducing the risk of sudden equipment failure.

[0039] Step S400: configuring a first weight for the path repetition length fitness function, configuring a second weight for the equipment inspection sorting fitness function, and constructing a comprehensive fitness function.

[0040] Preferably, a first weight is configured for the path repetition length fitness function, including setting a larger weight to reduce repeated paths when the inspection area has dense equipment and frequent path intersections, or increasing its weight (priority) when the path planning time is limited or repeated paths bring high costs, wherein the first weight of the path repetition length fitness function represents the priority of reducing repeated paths in the comprehensive optimization goal, and the larger the weight value, the more important the goal of reducing repeated paths; a second weight is configured for the equipment inspection sorting fitness function, including setting a larger weight to ensure that high-risk equipment is inspected first in scenarios with high probability of failure or more critical equipment, Or when the path length requirement is loose but the inspection equipment is important, the sorting weight is increased. The weight of the equipment inspection sorting fitness function indicates the priority of high-risk equipment in the comprehensive optimization goal. The larger the weight value, the more important the inspection sorting goal is. Then, the path repetition length fitness and the equipment inspection sorting fitness are weightedly combined according to the first weight and the second weight to obtain a comprehensive fitness function, which is used to simultaneously optimize the path efficiency and the inspection effect. That is, by adjusting the first weight and the second weight, a balance is achieved between reducing path repetition and optimizing the inspection order, thereby taking into account both the inspection work efficiency and the equipment inspection effect, and improving the intelligence and practicality of equipment inspection.

[0041] Step S500: optimizing the inspection path based on the comprehensive fitness function and the equipment failure probability to obtain a recommended inspection path.

[0042] Preferably, according to the comprehensive fitness function, the failure probability of the equipment is used as the core basis for the inspection priority, and the inspection path is globally optimized through an intelligent algorithm to generate the optimal inspection route. Specifically, the goal of the inspection path optimization is to minimize path duplication and optimize the inspection order while meeting the inspection efficiency, to ensure that the equipment with high failure risk is inspected first, and to construct a global optimization goal by combining the path duplication length and the equipment inspection priority. The advantages and disadvantages of the path are evaluated by maximizing the function to generate a recommended inspection path. For example, the inspection area is modeled as a graph structure, the node represents the location of the equipment, the edge represents the path between the equipment, and the edge weight can represent the path length or the inspection time cost. The comprehensive fitness function (combined with the path repetition rate and the inspection priority) is used to assign a score to each possible inspection path. According to the score of the comprehensive fitness function, the path optimization algorithm (such as genetic algorithm, ant colony algorithm, etc.) is used to iteratively optimize the inspection path to find the path with the highest score, and the path with the highest score is used as the recommended inspection path to achieve the optimal allocation of inspection resources and improve the scientificity and accuracy of the inspection work.

[0043] Step S600: sending the recommended inspection path to the inspection mobile terminal.

[0044] Preferably, the inspection path data generated based on the optimization model is transmitted to the inspection personnel's inspection mobile terminal (such as a smart phone, tablet computer or dedicated inspection equipment) through data transmission (such as wireless communication, Bluetooth or local area network, etc.), so that the inspection personnel can perform efficient inspection operations according to the recommended inspection path, thereby ensuring that the optimization results are truly implemented and improving the efficiency, transparency and controllability of the inspection work.

[0045] Furthermore, step S600 also includes step S610, obtaining the intersection device distribution position of the inspected path and the recommended inspection path; step S620, deleting the intersection device distribution position from the recommended inspection path, obtaining an updated inspection path and sending it to the inspection mobile terminal.

[0046] Preferably, a list of inspected equipment locations is obtained through the inspection mobile terminal, and a list of currently planned inspection equipment locations is obtained from the recommended path, thereby obtaining the intersection equipment distribution locations (equipment overlapping parts) of the inspected path and the recommended inspection path, that is, the equipment distribution locations that have been inspected in the recommended inspection path, to avoid repeated inspections, and then the intersection equipment distribution locations (inspected equipment locations) are deleted from the recommended inspection path, and the equipment locations and their sequence of unfinished tasks are obtained as updated inspection paths, and the updated inspection paths are transmitted to the inspection personnel's mobile devices, so as to obtain the latest inspection task information in real time to improve the inspection work efficiency, making the inspection tasks more efficient, accurate and scientific.

[0047] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for dynamically adjusting inspection paths under intelligent perception of working status, characterized in that: include: Obtain basic information about the equipment in the inspection area, wherein the basic information includes equipment working status, equipment model information, equipment service time, and equipment distribution location; Perform equipment failure probability analysis according to the equipment working status, the equipment model information, and the service time of the equipment to obtain the equipment failure probability; Construct a path repetition length fitness function and a device inspection sorting fitness function, wherein the path repetition length fitness function is a function for evaluating the proportion of repeated sections in the inspection path, and the device inspection sorting fitness function is a function for evaluating whether the inspection device priority sequence is reasonable; Configuring a first weight for the path repetition length fitness function, configuring a second weight for the equipment inspection sorting fitness function, and constructing a comprehensive fitness function; According to the comprehensive fitness function, based on the equipment failure probability, an inspection path is optimized to obtain a recommended inspection path; Sending the recommended inspection path to the inspection mobile terminal; Among them, constructing a path repetition length fitness function and a device inspection sorting fitness function includes: the path repetition length fitness function is used to count the length of the covered path of the inspection mobile terminal twice or more; Based on the equipment failure probability, sorting the equipment distribution positions to obtain the equipment distribution position sorting result; The equipment inspection sorting fitness function is used to calculate the inverse of the Hamming distance between the actual inspection position sequence and the equipment distribution position sorting result.

2. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 1, characterized in that: Performing equipment failure probability analysis according to the equipment working status, the equipment model information, and the equipment service time to obtain the equipment failure probability includes: Constructing fixed constraints based on the service life of the equipment and the equipment model information; Obtaining a device working status attribute deviation threshold; Configuring dynamic constraint conditions based on the device working state attribute deviation threshold; Equipment operation samples are collected according to the fixed constraint conditions and the dynamic constraint conditions to obtain a proportion of the number of fault samples, which is set as the equipment failure probability.

3. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 2, characterized in that: Collecting equipment operation samples according to the fixed constraint condition and the dynamic constraint condition to obtain a proportion of the number of fault samples is set as the equipment failure probability, including: Collecting a device operation sample once according to the fixed constraint condition and the dynamic constraint condition to obtain a device operation sample; configuring a fixed constraint condition for a single sample and a dynamic constraint condition for a single sample of the single device operation sample; Performing secondary collection of equipment operation samples according to the fixed constraint condition of the primary sample and the dynamic constraint condition of the primary sample to obtain secondary equipment operation samples; Until the equipment operation samples are collected five times according to the four sample fixed constraint conditions and the four sample dynamic constraint conditions, and five equipment operation samples are obtained; The proportion of the number of failure samples of the first device operation sample, the second device operation sample, and up to the fifth device operation sample is counted and set as the device failure probability.

4. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 3 is characterized in that: Counting the proportion of the number of fault samples of the first device operation sample, the second device operation sample, and up to the fifth device operation sample, includes: According to the four equipment operation samples, the five equipment operation samples are grouped to obtain multiple groups of five equipment operation samples; Until the secondary equipment operation samples are grouped according to the primary equipment operation samples to obtain multiple groups of secondary equipment operation samples; Recursive fault sample statistics are performed on the multiple groups of five device operation samples until the multiple groups of secondary device operation samples and the primary device operation samples to obtain the proportion of the number of fault samples.

5. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 4 is characterized in that: Recursively performing fault sample statistics on the multiple groups of five device operation samples until the multiple groups of secondary device operation samples and the primary device operation samples to obtain the proportion of the number of fault samples, including: Configure a primary sample aggregation weight, a secondary sample aggregation weight, and up to a fifth sample aggregation weight, wherein the sum of the primary sample aggregation weight, the secondary sample aggregation weight, and up to the fifth sample aggregation weight is equal to 1; Performing fault sample statistics on the multiple groups of five equipment operation samples to obtain the proportion of the number of five fitting fault samples; Recursively counting the proportion of the number of fault samples of the five fittings downwards until the fault sample statistics are performed on the multiple groups of secondary equipment operation samples to obtain the proportion of the number of fault samples of the second fitting; Count the percentage of the number of primary failure samples in the primary equipment operation samples; According to the first sample aggregation weight, the second sample aggregation weight, and up to the fifth sample aggregation weight, weighted mean statistics are performed on the proportion of the number of five fitting fault samples, up to the proportion of the number of second fitting fault samples, and the proportion of the number of first fault samples to obtain the proportion of the number of fault samples.

6. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 5, characterized in that: Perform fault sample statistics on the multiple groups of five equipment operation samples to obtain the proportion of the number of five fitting fault samples, including: Performing fault sample statistics on the multiple groups of five equipment operation samples respectively to obtain a number ratio of multiple five fault samples; Calculating a plurality of five device operation sample quantities for the plurality of groups of five device operation samples; The ratios of the multiple five equipment operation sample quantities to the total five equipment operation sample quantities are calculated respectively to obtain multiple five equipment operation sample fitting weights, and weighted mean statistics are performed on the multiple five fault sample quantity proportions to obtain the five fitting fault sample quantity proportions.

7. The method for dynamically adjusting the inspection path under intelligent perception of working status according to claim 1, characterized in that: Sending the recommended inspection path to the inspection mobile terminal includes: Obtaining the distribution location of the equipment at the intersection of the inspected path and the recommended inspection path; The intersection device distribution position is deleted from the recommended inspection path, and an updated inspection path is obtained and sent to the inspection mobile terminal.

Images