Highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence

Abstract

The present invention relates to the field of highway electromechanical equipment operation and maintenance evaluation, and in particular to a highway electromechanical equipment operation and maintenance decision evaluation system based on artificial intelligence, comprising collecting data information of highway electromechanical equipment, cleaning and preprocessing the collected data, scoring the highway electromechanical equipment, and classifying the highway electromechanical equipment according to the scores; establishing a neural network model for electromechanical equipment fault analysis based on the preprocessed highway electromechanical equipment data information, and analyzing the fault conditions of the highway electromechanical equipment; optimizing the inspection and maintenance frequency based on the output result of the obtained neural network model for electromechanical equipment fault analysis, and calculating the inspection and maintenance frequency correction parameter; establishing an operation and maintenance decision evaluation model based on the corrected inspection and maintenance frequency and in combination with the highway electromechanical equipment data information, and making an operation and maintenance decision suitable for the actual situation.

Description

Technical Field

[0001] The present invention relates to the field of highway equipment operation and maintenance evaluation, and in particular to a highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence. Background Art

[0002] The electromechanical equipment of highways includes but is not limited to street lights, road signs, signal lights, surveillance cameras, toll collection equipment, tunnel ventilation equipment, etc. The operation and maintenance process of electromechanical equipment of highways is directly related to the safety, smoothness and service level of roads. Therefore, the normal operation of electromechanical equipment of highways is crucial to ensure the safe and efficient operation of highways. At the same time, operation and maintenance decisions refer to the decisions made during the operation and maintenance process based on various factors such as the operating status of the equipment, maintenance requirements, and cost-benefit analysis.

[0003] At present, with the continuous development of technologies such as artificial intelligence and machine learning, the operation and maintenance decisions of highway electromechanical equipment have been greatly helped. However, in practical applications, the existing technologies still have the following problems: it is impossible to determine the operation and maintenance plan according to the actual situation of different highway electromechanical equipment, resulting in unreasonable resource allocation, waste of manpower, financial resources and other costs; there is no accurate analysis of past historical data, so it is impossible to provide data support for management personnel, and there is a lack of strong and sustainable decision-making; there is no further optimization and adjustment of the acquired data parameters, which makes the operation and maintenance decision evaluation results have a certain gap with the actual situation, forming an unreliable and unstable operation and maintenance decision plan; for the operation and maintenance decision evaluation process, there is a lack of consideration of actual applications, and there is a lack of help in improving the operating efficiency and performance of highway electromechanical equipment.

[0004] Therefore, an artificial intelligence-based highway electromechanical equipment operation and maintenance decision-making evaluation system is needed. Summary of the invention

[0005] The artificial intelligence-based highway electromechanical equipment operation and maintenance decision-making evaluation system provided by the present invention aims to provide intelligent decision-making support for operation and maintenance managers based on equipment status, operating conditions and historical data, to help them formulate reasonable maintenance plans, repair strategies and equipment update plans, and optimize the operation and maintenance decision-making process; at the same time, the operation and maintenance decision-making evaluation system can continuously learn and optimize, improve the intelligence level of the system, and gradually improve and optimize the equipment operation and maintenance strategy to adapt to the ever-changing operation and maintenance environment.

[0006] The technical solution of the present invention is specifically as follows:

[0007] The highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence includes the following contents:

[0008] Information acquisition and processing module, highway electromechanical equipment scoring module, electromechanical equipment fault analysis module, inspection and maintenance frequency correction module, coefficient optimization module, electromechanical equipment operation and maintenance decision evaluation module;

[0009] The information acquisition and processing module is used to acquire various data information of highway electromechanical equipment through sensors, monitoring systems, and maintenance recording methods, and perform data preprocessing;

[0010] The highway electromechanical equipment scoring module scores the highway electromechanical equipment according to the preprocessed highway electromechanical equipment data, and classifies the highway electromechanical equipment according to the scores;

[0011] The electromechanical equipment failure analysis module is used to establish an electromechanical equipment failure pre-analysis model by learning historical data and output the results of the electromechanical equipment failure analysis on the expressway;

[0012] The overhaul and maintenance frequency correction module corrects the overhaul and maintenance frequency according to the output result of the electromechanical equipment fault analysis module, providing data support for making reliable decisions;

[0013] The coefficient optimization module is used to compare the correction parameter of the inspection and maintenance frequency with the preset correction parameter, and optimize the inspection and maintenance frequency according to the comparison result;

[0014] The electromechanical equipment operation and maintenance decision evaluation module is used to calculate the evaluation index of the operation and maintenance decision according to the revised inspection and maintenance frequency to evaluate the operation and maintenance decision of the electromechanical equipment of the expressway, so as to provide a scientific decision-making basis for the management personnel.

[0015] The highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence includes the following steps:

[0016] Step S1. Collect data information of highway electromechanical equipment, clean and preprocess the collected data, score the highway electromechanical equipment, and classify the highway electromechanical equipment according to the score;

[0017] Step S2. Based on the pre-processed highway electromechanical equipment data information, a neural network model for electromechanical equipment fault analysis is established to analyze the fault conditions of the highway electromechanical equipment;

[0018] Step S3. Optimize the inspection and maintenance frequency according to the output result of the electromechanical equipment fault analysis neural network model, and calculate the inspection and maintenance frequency correction parameter;

[0019] Step S4. Based on the optimized and corrected inspection and maintenance frequency and combined with the highway electromechanical equipment data information, an operation and maintenance decision evaluation model is established to provide a decision basis for management personnel.

[0020] Further, step S1 specifically includes:

[0021] According to the classification of highway electromechanical equipment, the inspection and maintenance frequency is set. The comprehensive score of highway electromechanical equipment is: , and set the scoring thresholds to , ;

[0022] if , it means that the level of the highway electromechanical equipment is A, which means that the highway electromechanical equipment is generally in good condition; then the maintenance frequency is set to ;

[0023] if , it means that the level of the highway electromechanical equipment is B, which means that the highway electromechanical equipment has experienced some years and failures, but is still in normal condition, so the maintenance frequency is set to ;

[0024] if , it means that the level of the highway electromechanical equipment is C, indicating that the overall condition of the highway electromechanical equipment is poor; then the maintenance frequency is set to ;

[0025] in, , , represents a tuning parameter that controls the rate of change of the probability; and .

[0026] Further, step S2 specifically includes:

[0027] The electromechanical equipment fault analysis neural network model includes an input layer, an abnormality identification layer, a fault analysis layer, and an output layer;

[0028] The highway electromechanical equipment related data information is used as the input of the electromechanical equipment fault analysis neural network model. Represents any piece of electromechanical equipment information. The input layer will Passed to the exception layer, the transmission process is as follows:

[0029] in, Represents the input of the anomaly recognition layer; Represents the connection weight between the input layer and the anomaly recognition layer; Represents the output of the input layer; Represents the bias of the anomaly identification layer.

[0030] Further, step S2 detects abnormal situations or unusual patterns in the input data in the abnormality identification layer, and the specific process is as follows:

[0031] in, Represents the output of the anomaly recognition layer; represents the convergence coefficient; Standard cases that represent different types of abnormal label information; Indicates The actual characteristic information of the class attributes; Influencing parameters that represent abnormal feature information.

[0032] Further, step S3 specifically includes:

[0033] According to the output results of the neural network model for mechanical and electrical equipment fault analysis, the correction coefficient of the maintenance frequency is calculated. The specific process is as follows:

[0034] in, Indicates the correction factor for the inspection and maintenance frequency; , Represents the adjustment coefficient, which is used to control the stability of the calculation process; Indicates the upper limit of load that electromechanical equipment can withstand; Represents the output of the neural network model for electromechanical equipment fault analysis; represents a constant coefficient; represents the impact factor; Indicates the operating time of electromechanical equipment; Indicates that the device is Energy consumption; Indicates the energy required for normal operation of the equipment; Indicates the basic cost of operation and maintenance under ideal conditions.

[0035] Further, step S3 specifically includes:

[0036] Compare the correction coefficient of the maintenance frequency with the preset correction parameters, and optimize the maintenance frequency based on the comparison results;

[0037] if , then the maintenance frequency is optimized and corrected to , ;if , then the maintenance frequency is optimized and corrected to , ;if , then the maintenance frequency is optimized and corrected to , ; represents the first correction comparison parameter, represents the second modified contrast parameter, and .

[0038] Further, step S4 specifically includes:

[0039] According to the cost-benefit ratio of highway electromechanical equipment operation and maintenance, the operation and maintenance decision-making process of highway electromechanical equipment operation and maintenance is dynamically improved, and the evaluation indicators of operation and maintenance decisions are calculated to evaluate the operation and maintenance decisions of highway electromechanical equipment.

[0040] Beneficial effects: 1. By scoring and grading highway electromechanical equipment, the present invention enables operation and maintenance personnel to more accurately identify the status and needs of equipment, thereby formulating more refined operation and maintenance strategies and decisions; rationally allocating maintenance resources according to the status and level of the equipment, ensuring priority treatment of equipment that requires more urgent attention, and at the same time, formulating effective maintenance plans to extend the service life of equipment, reduce the frequency of equipment replacement, and save costs; and laying the foundation for improving the reliability and stability of equipment.

[0041] 2. The present invention provides maintenance personnel with more accurate fault diagnosis information by establishing a neural network model for mechanical and electrical equipment fault analysis, saving maintenance time and costs; through accurate fault analysis, it can reduce downtime and increase in maintenance costs caused by faults, reduce maintenance costs, and improve equipment utilization and work efficiency; it can also provide suggestions and measures for continuous improvement of equipment performance, helping the equipment to operate more stably and efficiently. Decision makers can provide data support for subsequent processes based on the analysis results generated by the model, thereby improving the effectiveness of operation and maintenance decisions.

[0042] 3. The present invention can accurately adjust the inspection and maintenance frequency by optimizing the inspection and maintenance frequency, better prevent equipment failures, improve equipment reliability and stability, reduce unnecessary maintenance interventions, extend the service life of equipment, and reduce equipment loss and wear. Optimizing the inspection and maintenance frequency can enable operation and maintenance personnel to perform maintenance work more specifically, improve operation and maintenance efficiency, and reduce manpower and time costs. The inspection and maintenance frequency correction parameters obtained by calculation can scientifically allocate maintenance resources, avoid resource waste, improve resource utilization efficiency, and help continuously improve maintenance strategies and gradually improve the efficiency of equipment operation.

[0043] 4. The present invention establishes an operation and maintenance decision-making evaluation model, combines the revised inspection and maintenance frequency and equipment data information, formulates more accurate and effective operation and maintenance strategies and decisions, and improves the reliability and performance of the equipment; the operation and maintenance decision-making evaluation model can continuously learn and optimize, adjust the operation and maintenance strategy according to actual conditions, continuously improve the equipment operation efficiency and performance, and ensure that the equipment is in the best state. The operation and maintenance decision-making evaluation model established based on the revised inspection and maintenance frequency and equipment data information provides a scientific decision-making basis for the operation and maintenance team, making the decision more reliable and more accurate for the operation and maintenance decision-making evaluation process of highway electromechanical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a module diagram of the highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence of the present invention;

[0045] Figure 2 The present invention is a flowchart of the highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence. DETAILED DESCRIPTION

[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] Refer to the attached Figure 2 , this embodiment provides a highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence, comprising the following steps:

[0048] S1. Collect data information of highway electromechanical equipment through different sensors, monitoring systems and monitoring equipment, including highway electromechanical equipment operation data, highway electromechanical equipment maintenance history, environmental data, fault records, maintenance plans, highway electromechanical equipment usage, etc.

[0049] In this embodiment, the operation data of highway electromechanical equipment includes but is not limited to key parameters such as operation status, operation time, workload, temperature, pressure, voltage, current, etc.; the maintenance history of highway electromechanical equipment includes but is not limited to information such as maintenance type, frequency, maintenance time, replacement of parts, etc.; the environmental data of highway electromechanical equipment includes but is not limited to information such as temperature, humidity, wind speed, etc.; the fault record includes but is not limited to the type of fault, occurrence time, repair measures, etc. of highway electromechanical equipment; the maintenance plan includes but is not limited to regular inspection, maintenance, replacement of parts, etc.; the use of highway electromechanical equipment includes but is not limited to main information such as operators, frequency of use, workload, etc. For example, for the lane controller in the toll collection system, its CPU usage, memory occupancy, network connection status, etc. data are collected.

[0050] Clean the collected data to remove invalid data, such as abnormally high or low data values ​​due to sensor failure). Standardize the data to convert different types of data into the same dimension for subsequent analysis. The process of preprocessing the acquired data is a mature prior art and will not be described in detail in this invention.

[0051] Scoring highway electromechanical equipment, classifying highway electromechanical equipment according to the scores, and setting inspection and maintenance frequencies according to the grades;

[0052] According to the received historical data information of the highway electromechanical equipment, the highway historical data information is represented as ,in, Indicates The first highway electromechanical equipment Attribute data, Indicated in The major attribute data Small category attribute data; when scoring highway electromechanical equipment, it is assumed that rating factors.

[0053] In the embodiment of the present invention, the type of highway electromechanical equipment, the service life of highway electromechanical equipment, the current operating status of highway electromechanical equipment, and the safety requirements of highway electromechanical equipment are defined as scoring elements, and the weights are respectively , , , , then the comprehensive score of the electromechanical equipment of the highway The specific process is as follows:

[0054] in, A scoring function representing the type of electromechanical equipment on a highway; A scoring function representing the service life of electromechanical equipment on highways; A scoring function representing the current operating status of the electromechanical equipment of the highway; A scoring function representing the safety requirements of electromechanical equipment on highways.

[0055] Because the scoring range of each factor must be considered, and the scoring function can reflect the continuous change of factor values, for example, the scoring function for the type of electromechanical equipment on a highway ,in, represents the slope coefficient, represents the intercept coefficient, Indicates the type of electromechanical equipment for highways, for example: Level 1 is indispensable, including safety equipment, communication equipment, control equipment, and lighting equipment; Level 2 can be used as an auxiliary, including power supply equipment, traffic management equipment, environmental monitoring equipment, and water conservancy equipment; Level 3 is an additional function, including highway beautification equipment, humanistic care equipment, etc.; For the scoring function of the service life of electromechanical equipment for highways ,in, , , are polynomial coefficients, Indicates the service life of highway electromechanical equipment, for example: Level 1 is new equipment that has been put into use for a short time, Level 2 is mid-term equipment that has been put into use for a period of time, and Level 3 is aging equipment that has been used for many years; for the current operating status scoring function of highway electromechanical equipment ,in, represents the amplitude, represents the mean, represents the standard deviation, Indicates the current operating status of the equipment, for example: Level 1 is normal operating equipment, Level 2 is partially faulty equipment, and Level 3 is out of service equipment; for the safety requirement scoring function of highway electromechanical equipment ,in, , A coefficient that represents the safety requirements for electromechanical equipment, It represents the characteristic indicators of safety requirements for electromechanical equipment of highways. For example, level one is high-safety-requirement equipment, which requires special attention and high-frequency inspections; level two is medium-safety-requirement equipment, which needs to be maintained in accordance with relevant specifications; level three is low-safety-requirement equipment, and it only needs to ensure the normal operation of the equipment.

[0056] In order to ensure that the sum of the weights is 1 and to avoid the scoring results being affected by the size of the weights, the weights are normalized: ,in, Represents the normalized weights, Indicates all weight Sum, From 1 to .

[0057] Therefore, the overall score .

[0058] According to previous statistical data, the scoring thresholds are pre-set. , The specific judgment process is as follows:

[0059] if , it means that the level of highway electromechanical equipment is A, which means that highway electromechanical equipment usually has high performance and stability, which is very important to ensure the safety of highway operation; then the maintenance frequency is set to ;

[0060] if , it means that the level of the highway electromechanical equipment is B, which means that the highway electromechanical equipment has experienced some years and failures, but is still in normal condition, so the maintenance frequency is set to ;

[0061] if , it means that the level of the highway electromechanical equipment is C, which means that the highway electromechanical equipment needs to be replaced or upgraded to improve the safety and reliability of the equipment; then the maintenance frequency is set to ;

[0062] in, , , represents a tuning parameter that controls the rate of change of the probability; and .

[0063] By scoring and grading highway electromechanical equipment, the present invention enables operation and maintenance personnel to more accurately identify the status and needs of equipment, thereby formulating more refined operation and maintenance strategies and decisions; reasonably allocating maintenance resources according to the status and level of the equipment, ensuring priority treatment of equipment that requires more urgent attention, and at the same time, formulating effective maintenance plans to extend the service life of equipment, reduce the frequency of equipment replacement, and save costs; and laying the foundation for improving the reliability and stability of equipment.

[0064] S2. According to the pre-processed data information related to the electromechanical equipment of the highway, a neural network model for electromechanical equipment fault analysis is established to analyze the fault conditions of the electromechanical equipment of the highway.

[0065] In the embodiment of the present invention, a neural network model for electromechanical equipment fault analysis is established through deep learning, and the data information related to the electromechanical equipment of the highway is used as a training sample, that is, the input value of the neural network model for electromechanical equipment fault analysis. express, , Indicates shared Any piece of information related to electromechanical equipment can be used Indicates that The neural network model for electromechanical equipment fault analysis includes an input layer, an abnormality recognition layer, a fault analysis layer, and an output layer.

[0066] The input layer will Passed to the exception layer, the transmission process is as follows:

[0067] in, Represents the input of the anomaly recognition layer; Represents the connection weight between the input layer and the anomaly recognition layer; Represents the output of the input layer; Represents the bias of the anomaly identification layer.

[0068] The anomaly recognition layer detects anomalies or unusual patterns in the input data. The specific process is as follows:

[0069] in, represents the output of the anomaly recognition layer; represents the convergence coefficient; Standard cases that represent different types of abnormal label information; Indicates The actual feature information of the class attributes; Influence parameters that represent abnormal feature information. By combining sine and cosine functions, the characteristics of the abnormal part can be better captured.

[0070] The fault analysis layer receives the output from the anomaly identification layer and further analyzes these anomalies. The specific process is as follows:

[0071] in, Represents the output of the fault analysis layer; Indicates fault maintenance record data information; Indicates the influence coefficient between different maintenance records; represents the correction factor; Indicated in Environmental parameter information during the time period, including temperature, humidity, air pressure, etc. when the electromechanical equipment of the highway is running. ; Indicates the balance parameters when a fault occurs in the electromechanical equipment; represents the adjustment parameters of the fault analysis layer; represents the analysis density in the fault analysis layer; represents the exponential parameter for adjusting the analysis density; The vertical coordinate data representing the abnormal information; The horizontal axis data represents the abnormal information.

[0072] Finally, the final result of the model is generated in the output layer to help highway electromechanical equipment managers take quick action to solve the problem. The specific process is as follows:

[0073] in, Represents the output result of the output layer; Represents the connection weight between the fault analysis layer and the output layer; Represents the bias of the output layer.

[0074] The present invention provides maintenance personnel with more accurate fault diagnosis information by establishing a neural network model for mechanical and electrical equipment fault analysis, saving maintenance time and costs; through accurate fault analysis, it can reduce downtime and increase in maintenance costs caused by faults, reduce maintenance costs, and improve equipment utilization and work efficiency; it can also provide suggestions and measures for continuous improvement of equipment performance, helping the equipment to operate more stably and efficiently. Decision makers can provide data support for subsequent processes based on the analysis results generated by the model to improve the effectiveness of operation and maintenance decision-making.

[0075] S3. Optimize the inspection and maintenance frequency according to the output results of the electromechanical equipment fault analysis neural network model.

[0076] According to the output results of the neural network model for mechanical and electrical equipment fault analysis, the correction coefficient of the maintenance frequency is calculated. The specific process is as follows:

[0077] in, Indicates the correction factor for the inspection and maintenance frequency; , Represents the adjustment coefficient, which is used to control the stability of the calculation process; Indicates the maximum load that electromechanical equipment can withstand; Represents the output of the neural network model for electromechanical equipment fault analysis; represents a constant coefficient; represents the impact factor; Indicates the operating time of electromechanical equipment; Indicates that the device is Energy consumption; Indicates the energy required for normal operation of the equipment; Indicates the basic cost of operation and maintenance under ideal conditions.

[0078] In the embodiment of the present invention, a first correction comparison parameter is set , the second correction comparison parameter ,and , the maintenance frequency correction factor Compare the parameters with the first correction , the second correction comparison parameter Make a comparison and optimize the inspection and maintenance frequency according to the comparison results; the specific process is as follows:

[0079] if , then the maintenance frequency is optimized and corrected to , ;

[0080] if , then the maintenance frequency is optimized and corrected to , ;

[0081] if , then the maintenance frequency is optimized and corrected to , .

[0082] By optimizing the inspection and maintenance frequency, the present invention can accurately adjust the inspection and maintenance frequency, better prevent equipment failures, improve equipment reliability and stability, reduce unnecessary maintenance interventions, extend the service life of equipment, and reduce equipment loss and wear. Optimizing the inspection and maintenance frequency can enable operation and maintenance personnel to perform maintenance work more targeted, improve operation and maintenance efficiency, and reduce manpower and time costs. Through the calculated inspection and maintenance frequency correction parameters, maintenance resources can be scientifically allocated, resource waste can be avoided, resource utilization efficiency can be improved, and maintenance strategies can be continuously improved to gradually improve the efficiency of equipment operation.

[0083] S4. Based on the optimized and corrected inspection and maintenance frequency and combined with the relevant data information of highway electromechanical equipment, an operation and maintenance decision-making evaluation model is established to provide strong data support for highway electromechanical equipment managers and help them make operation and maintenance decisions based on data and actual conditions.

[0084] In the embodiment of the present invention, the operation and maintenance decision process of the electromechanical equipment of the highway is dynamically enhanced. First, the cost-effectiveness ratio of the operation and maintenance of the electromechanical equipment of the highway is calculated. , the specific process is as follows:

[0085] in, Indicates the selected period; Indicates the total number of cycles; represents the total operation and maintenance cost; Represents the total benefit, , It indicates the benefit of improving equipment reliability; Indicates the benefit of reduced downtime; Indicates safety improvement benefits.

[0086] The specific process of dynamically improving the operation and maintenance decision-making process: in, represents the dynamic adjustment factor; Indicates the target benefit to be obtained in the next cycle; Indicates the benefits obtained in the current cycle; Indicates the cost-effectiveness ratio in the current cycle.

[0087] in, It represents the evaluation index of operation and maintenance decision, that is, the effectiveness of operation and maintenance decision; represents the evaluation coefficient; Indicates the target benefits expected to be achieved in the next cycle; Indicates the loss caused by wrong decision; Indicates the inspection and maintenance frequency after optimization and correction; Indicates the improvement factor of operation and maintenance decision; Represents the update rate of the decision plan.

[0088] The present invention establishes an operation and maintenance decision-making evaluation model, combines the revised inspection and maintenance frequency and equipment data information, formulates more accurate and effective operation and maintenance strategies and decisions, and improves the reliability and performance of the equipment; the operation and maintenance decision-making evaluation model can continuously learn and optimize, adjust the operation and maintenance strategy according to actual conditions, continuously improve the equipment operation efficiency and performance, and ensure that the equipment is in the best state. The operation and maintenance decision-making evaluation model established based on the revised inspection and maintenance frequency and equipment data information provides a scientific decision-making basis for the operation and maintenance team, making the decision more reliable and more accurate for the operation and maintenance decision-making evaluation process of highway electromechanical equipment.

[0089] Refer to the attached Figure 1 This embodiment provides a highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence, including the following contents:

[0090] Information acquisition and processing module, highway electromechanical equipment scoring module, electromechanical equipment fault analysis module, inspection and maintenance frequency correction module, coefficient optimization module, electromechanical equipment operation and maintenance decision evaluation module;

[0091] The information acquisition and processing module is used to obtain various data information of highway electromechanical equipment through sensors, monitoring systems, maintenance records, etc., and perform data preprocessing;

[0092] The highway electromechanical equipment scoring module scores the highway electromechanical equipment based on the preprocessed highway electromechanical equipment data, and classifies the highway electromechanical equipment according to the scores;

[0093] The electromechanical equipment failure analysis module is used to establish an electromechanical equipment failure pre-analysis model by learning historical data and output the results of highway electromechanical equipment failure analysis;

[0094] The maintenance frequency correction module corrects the maintenance frequency according to the output results of the electromechanical equipment fault analysis module, providing data support for making reliable decisions;

[0095] A coefficient optimization module is used to compare the correction parameters of the inspection and maintenance frequency with the preset correction parameters, and optimize the inspection and maintenance frequency according to the comparison results;

[0096] The electromechanical equipment operation and maintenance decision evaluation module is used to calculate the evaluation indicators of the operation and maintenance decision according to the revised inspection and maintenance frequency, evaluate the operation and maintenance decision of the electromechanical equipment on the highway, and provide scientific decision-making basis for managers.

[0097] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0100] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0101] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. The highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence is characterized by: Includes the following: Information acquisition and processing module, highway electromechanical equipment scoring module, electromechanical equipment fault analysis module, inspection and maintenance frequency correction module, coefficient optimization module, electromechanical equipment operation and maintenance decision evaluation module; The information acquisition and processing module is used to acquire various data information of highway electromechanical equipment through sensors, monitoring systems, and maintenance recording methods, and perform data preprocessing; The highway electromechanical equipment scoring module scores the highway electromechanical equipment according to the preprocessed highway electromechanical equipment data, and classifies the highway electromechanical equipment according to the scores; The electromechanical equipment failure analysis module is used to establish an electromechanical equipment failure pre-analysis model by learning historical data and output the results of the highway electromechanical equipment failure analysis; The overhaul and maintenance frequency correction module corrects the overhaul and maintenance frequency according to the output result of the electromechanical equipment fault analysis module, providing data support for making reliable decisions; Calculate the correction factor for the maintenance frequency. The specific process is as follows: in, Indicates the correction factor for the inspection and maintenance frequency; , Represents the adjustment coefficient, which is used to control the stability of the calculation process; Indicates the upper limit of load that electromechanical equipment can withstand; Represents the output of the neural network model for electromechanical equipment fault analysis; represents a constant coefficient; represents the impact factor; Indicates the operating time of electromechanical equipment; Indicates that the device is Energy consumption; Indicates the energy required for normal operation of the equipment; Indicates the basic cost of operation and maintenance under ideal conditions; The coefficient optimization module is used to compare the correction parameter of the inspection and maintenance frequency with the preset correction parameter, and optimize the inspection and maintenance frequency according to the comparison result; Compare the correction coefficient of the maintenance frequency with the preset correction parameters, and optimize the maintenance frequency based on the comparison results; if , then the maintenance frequency is optimized and corrected to , ;if , then the maintenance frequency is optimized and corrected to , ;if , then the maintenance frequency is optimized and corrected to , ; represents the first correction comparison parameter, represents the second modified contrast parameter, and ; The electromechanical equipment operation and maintenance decision evaluation module is used to calculate the evaluation index of the operation and maintenance decision according to the revised inspection and maintenance frequency to evaluate the operation and maintenance decision of the electromechanical equipment of the highway, so as to provide a scientific decision-making basis for the management personnel; According to the cost-benefit ratio of highway electromechanical equipment operation and maintenance, the operation and maintenance decision-making process of highway electromechanical equipment operation and maintenance is dynamically improved, and the evaluation indicators of operation and maintenance decisions are calculated to evaluate the operation and maintenance decisions of highway electromechanical equipment.

2. The highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence is applied to the highway electromechanical equipment operation and maintenance decision-making evaluation system based on artificial intelligence as claimed in claim 1, characterized in that: The following steps are involved: Step S1. Collect data information of highway electromechanical equipment, clean and preprocess the collected data, score the highway electromechanical equipment, and classify the highway electromechanical equipment according to the score; Step S2. Based on the pre-processed highway electromechanical equipment data information, a neural network model for electromechanical equipment fault analysis is established to analyze the fault conditions of the highway electromechanical equipment; Step S3. Optimize the inspection and maintenance frequency according to the output result of the electromechanical equipment fault analysis neural network model, and calculate the inspection and maintenance frequency correction parameter; Step S4. Based on the optimized and corrected inspection and maintenance frequency and combined with the highway electromechanical equipment data information, an operation and maintenance decision evaluation model is established to provide a decision basis for management personnel.

3. The highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence according to claim 2 is characterized in that: The step S1 specifically includes: According to the classification of highway electromechanical equipment, the inspection and maintenance frequency is set. The comprehensive score of highway electromechanical equipment is: , and set the scoring thresholds to , ; if , it means that the level of the electromechanical equipment of the expressway is , indicating that the electromechanical equipment of the highway is generally in good condition; then the maintenance frequency is set to ; if , it means that the level of the electromechanical equipment of the expressway is , indicating that the electromechanical equipment of the highway has experienced some age and failures, but is still in normal condition, then the maintenance frequency is set to ; if , it means that the level of the electromechanical equipment of the expressway is , indicating that the overall condition of the electromechanical equipment of the highway is poor; then the maintenance frequency is set to ; in, , , represents a tuning parameter that controls the rate of change of the probability; and .

4. The highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence according to claim 2 is characterized in that: The step S2 specifically includes: The electromechanical equipment fault analysis neural network model includes an input layer, an abnormality identification layer, a fault analysis layer, and an output layer; The highway electromechanical equipment related data information is used as the input of the electromechanical equipment fault analysis neural network model. Represents any piece of electromechanical equipment information. The input layer will Passed to the exception layer, the transmission process is as follows: in, Represents the input of the anomaly recognition layer; Represents the connection weight between the input layer and the anomaly recognition layer; Represents the output of the input layer; Represents the bias of the anomaly identification layer.

5. The highway electromechanical equipment operation and maintenance decision-making evaluation method based on artificial intelligence according to claim 4 is characterized in that: The step S2 detects abnormal situations or unusual patterns in the input data in the abnormality identification layer. The specific process is as follows: in, Represents the output of the anomaly recognition layer; represents the convergence coefficient; Standard cases that represent different types of abnormal label information; Indicates The actual characteristic information of the class attributes; Influencing parameters that represent abnormal feature information.

Images