Intelligent inspection system and method for intelligent station building
Through the intelligent inspection system of smart station buildings, digital twins and AR technology are used for real-time monitoring and fault prediction, combined with improved slime mold optimization algorithm to optimize inspection paths, the existing problems of low inspection efficiency and poor accuracy are solved, and the existing inspection is achieved. Efficiency, safety monitoring and early warning of distribution station buildings.
Patent Information
- Application Number
- CN202411292197.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2024-12-27
AI Technical Summary
The inspection efficiency of existing distribution station buildings is low, the accuracy rate is low, and the timeliness is poor. The detection data linkage capability of ordinary inspection systems is insufficient, and there is a lack of effective inspection and scheduling mechanisms and means.
Adopt smart station building intelligent patrol system, including data acquisition module, intelligent patrol module, remote monitoring module and intelligent control module, and use digital twin technology and AR technology to build a three-dimensional model to perform real-time monitoring, fault prediction and intelligent scheduling, combined with Improved slime mold optimization algorithm optimizes patrol paths and frequency.
It improves the efficiency and accuracy of station building inspections, realizes timely warnings of potential dangers, and enhances the safety of station building operation and the convenience of system.
Smart Images
Figure CN119209901A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of safety management technology, and in particular to an intelligent inspection system and method for a smart station building. Background Art
[0002] Currently, the duty of power distribution stations is carried out through manual inspections, but manual inspections not only require a large number of manpower reserves, but also fail to detect the status of each device in the station in a timely manner, and fail to predict potential dangers in the station, resulting in low inspection efficiency, low accuracy, and poor timeliness. The ordinary inspection system is not capable of linking detection data and lacks effective inspection scheduling mechanisms and means.
[0003] In order to solve the above problems, the present invention proposes an intelligent inspection system and method for a smart station building. Summary of the invention
[0004] The purpose of the present invention is to propose a smart station intelligent inspection system and method to solve the problems raised in the background technology: Existing manual inspections are inefficient, inaccurate, and timelier; ordinary inspection systems lack the ability to link detection data and lack effective inspection scheduling mechanisms and means.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A smart station house intelligent inspection system, comprising: Data collection module: used to collect status data and equipment status data in the smart station room; Intelligent inspection module: used to conduct regular inspections in the smart station based on inspection equipment; Remote monitoring module: used to perform remote monitoring based on the data updated by the remote communication module, and generate corresponding control instructions based on the monitoring results; Intelligent control module: used for remote intelligent control of the smart station and internal equipment; Remote communication module: used to realize remote communication between the intelligent inspection module, the remote monitoring module and the intelligent control module; The remote monitoring module includes a model building module, an analysis and prediction module, an intelligent control module and an intelligent scheduling module; The model building module builds a three-dimensional model of the smart station building based on the digital twin technology, and dynamically updates it based on the data updated by the intelligent inspection module; The analysis and prediction module performs analysis and fault prediction based on the data updated by the model building module; The intelligent control module generates an intelligent control scheme based on the analysis and prediction results of the analysis and prediction module; The intelligent scheduling module performs intelligent scheduling of inspection equipment based on the analysis and prediction results of the analysis and prediction module.
[0006] Preferably, the model building module projects the constructed three-dimensional model of the smart station building into the real scene based on AR technology, so as to realize the virtual display and real-time monitoring of the smart station building and its internal equipment.
[0007] A smart inspection method for a smart station house comprises the following steps: S1: Build a remote monitoring platform for information exchange with inspection equipment; S2: Real-time monitoring and data collection of equipment status in the smart station based on inspection equipment docking sensors; S3: The collected data is transmitted to the remote monitoring platform via wireless or wired communication, and the remote monitoring platform performs preliminary preprocessing and storage management on the data; S4: The remote monitoring platform also performs real-time status analysis of the smart station, equipment importance judgment and fault prediction based on the pre-processed data, and performs intelligent scheduling and inspection of inspection equipment based on the prediction results, executes preventive maintenance tasks, and performs remote control or automatic repair.
[0008] Preferably, in S4, the remote monitoring platform builds a three-dimensional smart station based on the digital twin algorithm, and projects the constructed three-dimensional model of the smart station into the real scene based on AR technology, so as to realize virtual display and real-time monitoring of the smart station and its internal equipment.
[0009] Preferably, in S4, inspection tasks corresponding to different frequencies are generated based on real-time status analysis, equipment importance judgment and fault prediction results. The remote monitoring platform also generates inspection routes and intelligent control plans according to the inspection task optimization, and then sends them to the inspection equipment and intelligent control equipment for corresponding inspection and control, and generates corresponding early warning signals.
[0010] Preferably, the inspection tasks corresponding to different times and frequencies generated based on real-time status analysis, equipment importance judgment and fault prediction results are specifically as follows: The corresponding weights are generated for the three indicators of real-time status, equipment importance and fault prediction based on the improved slime mold optimization algorithm. The improved slime mold optimization algorithm is optimized with the comprehensive safety of the smart station as the goal to generate a comprehensive evaluation value, and the inspection priority and inspection frequency are divided according to the comprehensive evaluation value; Encode the inspection tasks of the inspection points in the smart station house, as follows: Generated based on remote control platform analysis Individual inspection tasks:
[0011] in, Indicates Inspection tasks; according to Each priority generates different levels of inspection tasks:
[0012] in, Indicates The first priority Individual inspection tasks; With the goal of minimizing the time consumption, the execution order and inspection path of sub-inspection tasks at different levels are optimized based on the improved slime mold optimization algorithm. The inspection paths corresponding to the inspection tasks are merged, sorted in descending order of time consumption and summarized into the inspection task set, and the inspection task set is sorted in order from the lowest priority to the highest priority. Define a chromosome, and encode it on the genes of the chromosome in the sorting order. After the encoding is completed, decode the chromosome and reverse the sequence information of the chromosome. The improved slime mold optimization is specifically as follows: Phase 1: The slime mold approaches the food according to the smell in the air. The slime mold is the sub-inspection task or inspection path to be optimized, and the food is the sub-inspection task sequence or inspection path with the shortest consumption time. The shorter the sub-inspection task sequence or the shortest consumption time of the inspection path, the higher the degree of optimization of the sub-inspection task or inspection path. On the contrary, the degree of optimization of the sub-inspection task or inspection path is reduced, and the optimization turns to other sub-inspection tasks or inspection paths to be optimized.
[0013] in, Indicates the current iteration number; Indicates the location of the sub-inspection task or inspection path to be optimized; Indicates The sub-inspection task or inspection path to be optimized in the next iteration In the The location of the dimension; Indicates the dominant sub-inspection task or inspection path position selected according to the preferred matrix, where: for Integer within ; Indicates The sub-inspection task or inspection path to be optimized in the first iteration is The location of the dimension; Indicates The sub-inspection task or inspection path to be optimized is randomly selected in the first iteration. The location of the dimension; Simulate the interaction process of the inspection task or inspection path concentrated information in the sub-inspection task or inspection path to be optimized, , obey Uniform distribution of Simulate the process of sub-inspection tasks or inspection paths to be optimized to preserve themselves. ,obey Uniform distribution of express Random numbers within Indicates the scale of the inspection task or inspection path set; Indicates The fitness value of the sub-inspection task or inspection path to be optimized; Indicates the fitness value of the global optimal sub-inspection task or inspection path to be optimized;
[0014] in, represents the rounding function; Indicates the maximum number of iterations; the improved The value range is , and obey Uniform distribution of
[0015] in, is a mathematical constant; Phase 2: The sub-inspection task or inspection path to be optimized connects multiple sub-inspection task sequences or inspection path sets with the shortest consumption time, and establishes a connection network with different connection degrees between the sub-inspection task sequences or inspection path sets with the shortest consumption time. When the connection line is close to the sub-inspection task sequence or inspection path set with the shortest consumption time, the signal emitted by the sub-inspection task or inspection path to be optimized stimulates the connection line oscillator to generate a propagation wave, thereby promoting the optimization process. The shorter the time of the sub-inspection task sequence or inspection path to be optimized, the lower the degree of optimization, the stronger the wave signal generated, the faster the optimization process, and the higher the degree of connection. Otherwise, the lower the degree of connection:
[0016] in, and Respectively represent the upper and lower bounds of the search space; and Both said Random numbers within represents the transition probability; represents the weight factor of the random individuals of slime mold; Indicates Iteration slime mold individuals In the The location of the dimension; Phase 3: The connection line oscillator generates propagation waves, changes the order of sub-inspection tasks or the optimization process of the inspection path, through , and Simulate the oscillation frequency and connection degree of the connection line. The sub-inspection task sequence or inspection path to be optimized slowly approaches the shortest consumption time during the optimization process. When the shortest consumption time is found, it approaches and replaces the position corresponding to the sub-inspection task sequence or inspection path with the shortest consumption time more quickly.
[0017] in, and They represent the optimal fitness value and the worst fitness value of the sub-inspection task sequence or inspection path in the current generation respectively; express Uniform random numbers within .
[0018] Preferably, in S4, one inspection point corresponds to a plurality of inspection tasks, and each inspection task corresponds to a different priority.
[0019] Preferably, in S4, the inspection route is optimized based on an improved slime mold optimization algorithm with the goal of minimizing the inspection path.
[0020] Compared with the prior art, the present invention provides a smart station intelligent inspection system and method, which has the following beneficial effects: The present invention realizes status monitoring of the smart station house and internal equipment based on a remote monitoring platform, thereby improving the inspection efficiency of the station house, and combines AR technology to improve the visualization of the monitoring results, thereby improving the convenience and practicality of the inspection system; and generates an effective inspection scheduling mechanism based on a comprehensive linkage analysis of multiple data, and flexibly changes the inspection frequency based on the analysis results to improve the inspection efficiency, and can also realize timely early warning of the status in the station house, thereby improving the safety of the station house operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 This is a system block diagram mentioned in Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method mentioned in Example 2 of the present invention; Figure 3 This is a schematic diagram of the chromosome encoding mentioned in Example 3 of the present invention. DETAILED DESCRIPTION
[0022] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.
[0023] The present invention realizes the status monitoring of the smart station house and internal equipment based on the remote monitoring platform, improves the inspection efficiency of the station house, and combines AR technology to improve the visualization of the monitoring results, improves the convenience and practicality of the inspection system; and generates an effective inspection scheduling mechanism based on the comprehensive linkage analysis of multiple data, and flexibly changes the inspection frequency based on the analysis results to improve the inspection efficiency, and can also realize timely early warning of the status in the station house, and improve the safety of the station house operation. Specifically include the following contents.
[0024] Embodiment 1: See also Figure 1 The present invention provides an intelligent inspection system for a smart station house, comprising: Data collection module 100: used to collect status data and equipment status data in the smart station room; Intelligent inspection module 200: used to perform regular inspections in the smart station house based on inspection equipment; Remote monitoring module 300: used to perform remote monitoring based on the data updated by the remote communication module 500, and generate corresponding control instructions based on the monitoring results; The remote monitoring module 300 includes a model building module 310, an analysis and prediction module 320, an intelligent control module 330 and an intelligent scheduling module 340; The model building module 310 builds a three-dimensional model of the smart station building based on the digital twin technology, and dynamically updates it based on the data updated by the intelligent inspection module 200; The analysis and prediction module 320 performs analysis and fault prediction based on the data updated by the model building module 310; The intelligent control module 330 generates an intelligent control scheme based on the analysis and prediction results of the analysis and prediction module 320; The intelligent scheduling module 340 performs intelligent scheduling of inspection equipment based on the analysis and prediction results of the analysis and prediction module 320 .
[0025] The model building module 310 projects the constructed three-dimensional model of the smart station house into the real scene based on AR technology, realizing the virtual display and real-time monitoring of the smart station house and its internal equipment. Then the inspection equipment, such as the patrol robot, can be intelligently equipped with AR smart glasses, and the operation and maintenance personnel can view the equipment information, maintenance records, etc. in real time through the interface displayed by the AR smart glasses, providing visual operation instructions and data display. The patrol robot is also equipped with cameras and sensors to patrol the station house equipment in real time and transmit the data to the digital twin model. The operation and maintenance personnel can also conduct real-time patrol, anomaly detection and fault diagnosis of the equipment through the remote AR interface displayed by the remote monitoring module 300, and make quick responses and decisions. In this technical application, the digital twin model, as a virtual simulation platform, is combined with AR technology and intelligent patrol robots to realize the digital presentation, intelligent auxiliary operation and remote monitoring and maintenance of the equipment. This comprehensive application improves the efficiency and accuracy of station house equipment management, reduces maintenance costs and risks, and improves work efficiency and user experience.
[0026] Intelligent control module 400: used for remote intelligent control of the smart station and internal equipment; Remote communication module 500: used to realize remote communication between the intelligent inspection module 200, the remote monitoring module 300 and the intelligent control module 400; Embodiment 2: Please refer to FIG. 2 , a method for intelligent inspection of a smart station house according to the present invention comprises the following steps: S1: Build a remote monitoring platform for information exchange with inspection equipment; details are as follows: First, you need to determine the scope of equipment to be monitored and the monitoring indicators, and select appropriate sensors or monitoring equipment to collect real-time information such as equipment status and operating parameters. These devices can be temperature sensors, pressure sensors, vibration sensors, etc. Select appropriate collection equipment based on the characteristics of specific equipment and monitoring requirements.
[0027] The collected equipment information needs to be transmitted to the remote monitoring platform through the network. Therefore, it is possible to consider using Internet of Things technology, sensor network technology or other communication technologies to transmit data to the remote monitoring platform.
[0028] It is also necessary to establish a database to store the collected equipment information data and establish a corresponding data processing system to clean, analyze and process the data for subsequent monitoring and decision-making.
[0029] Design and develop a visual interface for the remote monitoring platform, which intuitively displays equipment information data in the form of charts, dashboards, etc., so that users can clearly understand the operating status and health of the equipment.
[0030] By implementing remote monitoring function on the monitoring platform, you can view device information anytime and anywhere, set corresponding alarm thresholds and alarm mechanisms, detect device anomalies in time and take corresponding measures.
[0031] By using technologies such as data analysis and machine learning to analyze and mine equipment information data, we can realize functions such as equipment status prediction and fault diagnosis, detect potential problems in advance and perform preventive maintenance.
[0032] When establishing a remote monitoring platform, issues such as data security and permission management are also considered to ensure the security and privacy of device information.
[0033] Through the above steps, a remote monitoring platform that communicates with inspection equipment can be established to achieve real-time monitoring, prediction and management of equipment status.
[0034] S2: Based on the inspection equipment docking sensor, the equipment status in the smart station is monitored in real time and data is collected; the details are as follows: Ensure that the inspection equipment has the ability to connect to sensors, such as having interfaces or communication protocols that are compatible with sensors. Select appropriate sensors for installation according to the type and parameters of the equipment to be monitored. For example, temperature sensors can monitor temperature changes of equipment, and pressure sensors can monitor pressure changes of equipment. Connect the sensors to the inspection equipment to ensure that the sensor data can be read by the inspection equipment. Set monitoring tasks on the inspection equipment, including the monitored equipment, monitored parameters, and monitoring frequency. In this way, the inspection equipment will collect data according to the set tasks. The inspection equipment will monitor the sensors in real time according to the set tasks and collect corresponding data. These data can be viewed and analyzed in real time through the display screen of the inspection equipment or transmitted to the monitoring center. By processing and analyzing the collected data, you can understand the status and performance of the equipment, find abnormalities and problems in time, and perform corresponding processing and maintenance. The connection between the inspection equipment and the sensor can realize real-time monitoring and data collection of the equipment status in the smart station room, providing strong support for equipment maintenance and management.
[0035] S3: The collected data is transmitted to the remote monitoring platform via wireless or wired communication, and the remote monitoring platform performs preliminary preprocessing and storage management on the data; the details are as follows: Choose appropriate communication methods according to actual conditions, such as Wi-Fi, Ethernet, cellular networks such as 4G / 5G, LoRaWAN, etc. Consider factors such as station environment, communication distance, data volume and security. Ensure that appropriate data transmission protocols are adopted to ensure secure and reliable data transmission. Common protocols include MQTT, HTTP(S), CoAP, etc. Choose appropriate transmission equipment according to the communication method, such as wireless modules, Ethernet interfaces, data concentrators, etc. Build or select a suitable remote monitoring platform to ensure that the platform has the functions of data reception, processing, storage and management. The platform can be a self-built server system or a platform provided by a cloud service provider. The remote monitoring platform can perform preliminary preprocessing on the received data, such as data parsing, denoising, anomaly detection, etc., to ensure the accuracy and availability of the data. The remote monitoring platform needs to provide data storage and management functions, including data storage structure design, storage medium selection, data backup and recovery strategies, etc. Ensure the security of data during transmission and storage, and take appropriate encryption, authentication and access control measures to prevent data leakage and tampering.
[0036] Through the above steps, the collected data can be transmitted to the remote monitoring platform through wireless or wired communication, and preliminary preprocessing and storage management can be performed on the platform to provide support for remote monitoring and management.
[0037] S4: The remote monitoring platform also performs real-time status analysis of the smart station, equipment importance judgment and fault prediction based on the pre-processed data, and performs intelligent scheduling and inspection of inspection equipment based on the prediction results, performs preventive maintenance tasks, and performs remote control or automatic repair. The details are as follows: The remote monitoring platform can use the collected data to perform real-time status analysis, monitor the operating status of the equipment, parameter changes, etc. Through data visualization technology, the real-time status is displayed in the form of charts, curves, etc., to help operation and maintenance personnel to understand the operation status of the station equipment in a timely manner. By analyzing the equipment operation data, the importance level of the equipment can be determined. The operating status of important equipment may have a significant impact on the operation of the entire station, so it needs to be given higher attention and priority. Using machine learning, data mining and other technologies, the equipment operation data is analyzed and modeled to discover the possible fault characteristics and trends of the equipment. Based on these characteristics and trends, fault prediction can be carried out, maintenance measures can be taken in advance, and equipment downtime and maintenance costs can be reduced. When an abnormal state of the equipment is detected or a possible fault is predicted, the remote monitoring platform can trigger an alarm mechanism and notify relevant personnel in time to handle it. This can be achieved through SMS, email, APP push, etc. The monitoring platform can continuously optimize and improve based on the collected data and operation experience, improve the accuracy and timeliness of fault prediction, and improve the operation efficiency and reliability of the smart station. Through the above methods, the remote monitoring platform can perform real-time status analysis, equipment importance judgment and fault prediction of the smart station based on the preprocessed data, thereby improving the safety and stability of the station operation.
[0038] The remote monitoring platform generates inspection tasks with different frequencies based on real-time status analysis, equipment importance judgment and fault prediction results, as follows: For the three indicators of real-time status, equipment importance and fault prediction, corresponding weights are generated respectively based on the improved slime mold optimization algorithm. Among them, the improved slime mold optimization algorithm is optimized with the comprehensive safety of the smart station as the goal to generate a comprehensive evaluation value, and the inspection priority and inspection frequency are divided according to the comprehensive evaluation value; among them, one inspection point can correspond to one or more inspection tasks, and different inspection frequencies can be generated according to the analysis results. Multiple inspection tasks of a point to be inspected correspond to different priorities to achieve the time coverage of the inspection.
[0039] Encode the inspection tasks of the inspection points in the smart station house, as follows: Generated based on remote control platform analysis Individual inspection tasks:
[0040] in, Indicates Inspection tasks; according to Each priority generates different levels of inspection tasks:
[0041] in, Indicates The first priority Individual inspection tasks; With the goal of minimizing the time consumption, the execution order and inspection path of sub-inspection tasks at different levels are optimized based on the improved slime mold optimization algorithm. The inspection paths corresponding to the inspection tasks are merged, sorted in descending order of time consumption and summarized into the inspection task set, and the inspection task set is sorted in order from the lowest priority to the highest priority. Define a chromosome, and encode it on the genes of the chromosome in the sorting order. After the encoding is completed, decode the chromosome and reverse the sequence information of the chromosome. Improved slime mold optimization is as follows: Phase 1: The slime mold approaches the food according to the smell in the air. The slime mold is the sub-inspection task or inspection path to be optimized, and the food is the sub-inspection task sequence or inspection path with the shortest consumption time. The shorter the sub-inspection task sequence or the shortest consumption time of the inspection path, the higher the degree of optimization of the sub-inspection task or inspection path. On the contrary, the degree of optimization of the sub-inspection task or inspection path is reduced, and the optimization turns to other sub-inspection tasks or inspection paths to be optimized.
[0042] in, Indicates the current iteration number; Indicates the location of the sub-inspection task or inspection path to be optimized; Indicates The sub-inspection task or inspection path to be optimized in the next iteration In the The location of the dimension; Indicates the dominant sub-inspection task or inspection path position selected according to the preferred matrix, where: for Integer within ; Indicates The sub-inspection task or inspection path to be optimized in the first iteration is The location of the dimension; Indicates The sub-inspection task or inspection path to be optimized is randomly selected in the first iteration. The location of the dimension; Simulate the interaction process of the inspection task or inspection path concentrated information in the sub-inspection task or inspection path to be optimized, , obey Uniform distribution of Simulate the process of sub-inspection tasks or inspection paths to be optimized to preserve themselves. ,obey Uniform distribution of express Random numbers within Indicates the scale of the inspection task or inspection path set; Indicates The fitness value of the sub-inspection task or inspection path to be optimized; Indicates the fitness value of the global optimal sub-inspection task or inspection path to be optimized;
[0043] in, represents the rounding function; Indicates the maximum number of iterations; the improved The value range is , and obey Uniform distribution of
[0044] in, is a mathematical constant; Phase 2: The sub-inspection task or inspection path to be optimized connects multiple sub-inspection task sequences or inspection path sets with the shortest consumption time, and establishes a connection network with different connection degrees between the sub-inspection task sequences or inspection path sets with the shortest consumption time. When the connection line is close to the sub-inspection task sequence or inspection path set with the shortest consumption time, the signal emitted by the sub-inspection task or inspection path to be optimized stimulates the connection line oscillator to generate a propagation wave, thereby promoting the optimization process. The shorter the time of the sub-inspection task sequence or inspection path to be optimized, the lower the degree of optimization, the stronger the wave signal generated, the faster the optimization process, and the higher the degree of connection. Otherwise, the lower the degree of connection:
[0045] in, and Respectively represent the upper and lower bounds of the search space; and Both said Random numbers within represents the transition probability; represents the weight factor of the random individuals of slime mold; Indicates Iteration slime mold individuals In the The location of the dimension; Phase 3: The connection line oscillator generates propagation waves, changes the order of sub-inspection tasks or the optimization process of the inspection path, through , and Simulate the oscillation frequency and connection degree of the connection line. The sub-inspection task sequence or inspection path to be optimized slowly approaches the shortest consumption time during the optimization process. When the shortest consumption time is found, it approaches and replaces the position corresponding to the sub-inspection task sequence or inspection path with the shortest consumption time more quickly.
[0046] in, and They represent the optimal fitness value and the worst fitness value of the sub-inspection task sequence or inspection path in the current generation respectively; express Uniform random numbers within .
[0047] In the improved slime mold optimization algorithm, the algorithm shifts from global search to local mining based on the improved convergence factor, so that the algorithm can quickly converge to the optimal solution in the early stage of iteration and slightly approach the optimal solution in the later stage of iteration, accelerating convergence and improving convergence accuracy, so as to further improve the analysis speed of the remote monitoring platform and improve inspection efficiency.
[0048] The remote monitoring platform also generates inspection routes and intelligent control plans based on the inspection task optimization. The inspection route is based on the improved slime mold optimization algorithm, and is optimized with the shortest inspection path as the goal. The intelligent control plan generates control instructions for the station environment parameters, such as temperature, humidity, and light, based on the analysis results of the smart station and its internal equipment; or generates relevant control instructions for internal equipment, which are then sent to the inspection equipment and intelligent control equipment for corresponding inspection and control.
[0049] In the field of equipment management, inspection is part of routine processing, and its purpose is to ensure the normal operation of equipment, prevent failures, and promptly discover and solve potential problems. By taking into account factors such as predicted fault level, equipment importance and real-time status, and dynamically adjusting the inspection frequency based on these factors, resources can be allocated more effectively, and the pertinence and effectiveness of inspections can be improved, thereby further optimizing the equipment management process; improving efficiency, reducing costs, and ensuring quality and safety.
[0050] Embodiment 3: Reference Figure 3 , A, B, C, D, E, and F correspond to priorities from high to low, and numbers 1 to 5 correspond to inspection tasks of different priorities. The remote monitoring platform analyzes the data in the smart station room and generates the corresponding inspection task set as follows: A1, A3, A5, A4, A2; B3, B5, B2, B1, B4; C1, C2, C5, C4, C3; D1, D2, D5, D4, D3; E5, E3, E2, E4, E1; F1, F2, F3, F4, F5; The order of the above task sets is the order in which they need to be executed. The priorities of the above tasks are arranged in reverse order, as follows: F1, F2, F3, F4, F5; E5, E3, E2, E4, E1; D1, D2, D5, D4, D3; C1, C2, C5, C4, C3; B3, B5, B2, B1, B4; A1, A3, A5, A4, A2; Then arrange the sub-inspection tasks in each priority level in reverse order: F5, F4, F3, F2, F1; E1, E4, E2, E3, E5; D3, D4, D5, D2, D1; B4, B1, B2, B5, B6; A2, A4, A5, A3, A1; This is how chromosomes are encoded, see Figure 3 After the chromosome encoding is completed, the reverse decoding operation can correspond to the correct inspection order.
[0051] The performance of the improved slime mold optimization algorithm is compared with that of the ordinary slime mold optimization algorithm based on different benchmark functions. For details, please refer to Table 1: Table 1 Performance comparison of slime mold optimization algorithm before and after improvement
[0052] It can be seen from Table 1 that the slime mold optimization algorithm has certain optimization performance before and after the improvement, but the improved slime mold optimization algorithm has better performance and faster optimization speed, and is more suitable for the inspection process of smart station houses.
[0053] Based on the improved slime mold optimization algorithm, the path generated based on the inspection task is optimized, and some inspection path nodes are intercepted for detection. For details, please refer to Table 2: Table 2 Comparison of inspection paths before and after optimization based on the improved slime mold optimization algorithm
[0054] In the table, LX represents the path node. The optimized path based on the improved slime mold optimization algorithm reduces unnecessary inspection path nodes, saves inspection time, and improves inspection efficiency.
[0055] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A smart station intelligent inspection system, characterized in that: include: Data collection module (100): used to collect status data and equipment status data in the smart station room; Intelligent inspection module (200): used for performing regular inspection in the smart station house based on inspection equipment; A remote monitoring module (300): used to perform remote monitoring based on data updated by the remote communication module (500), and to generate corresponding control instructions based on monitoring results; Intelligent control module (400): used for remote intelligent control of the smart station and internal equipment; A remote communication module (500): used to realize remote communication between the intelligent inspection module (200), the remote monitoring module (300) and the intelligent control module (400); The remote monitoring module (300) comprises a model building module (310), an analysis and prediction module (320), an intelligent control module (330) and an intelligent scheduling module (340); The model building module (310) builds a three-dimensional model of a smart station building based on digital twin technology, and dynamically updates it based on the data updated by the intelligent inspection module (200); The analysis and prediction module (320) performs analysis and fault prediction based on the data updated by the model building module (310); The intelligent control module (330) generates an intelligent control scheme based on the analysis and prediction results of the analysis and prediction module (320); The intelligent scheduling module (340) performs intelligent scheduling of inspection equipment based on the analysis and prediction results of the analysis and prediction module (320).
2. According to claim 1, the intelligent inspection system for smart station buildings is characterized in that: The model building module (310) projects the built three-dimensional model of the smart station building into a real scene based on AR technology, thereby realizing virtual display and real-time monitoring of the smart station building and its internal equipment.
3. A smart station intelligent inspection method according to any one of claims 1 to 2, characterized in that: The steps include: S1: Build a remote monitoring platform for information exchange with inspection equipment; S2: Real-time monitoring and data collection of equipment status in the smart station based on inspection equipment docking sensors; S3: The collected data is transmitted to the remote monitoring platform via wireless or wired communication, and the remote monitoring platform performs preliminary preprocessing and storage management on the data; S4: The remote monitoring platform also performs real-time status analysis of the smart station, equipment importance judgment and fault prediction based on the pre-processed data, and performs intelligent scheduling and inspection of inspection equipment based on the prediction results, executes preventive maintenance tasks, and performs remote control or automatic repair.
4. According to claim 3, a smart station intelligent inspection method is characterized in that: In S4, the remote monitoring platform builds a three-dimensional smart station based on the digital twin algorithm, and projects the built three-dimensional model of the smart station into the real scene based on AR technology, so as to realize virtual display and real-time monitoring of the smart station and its internal equipment.
5. According to claim 4, a smart station intelligent inspection method is characterized in that: In S4, inspection tasks corresponding to different frequencies are generated based on real-time status analysis, equipment importance judgment and fault prediction results. The remote monitoring platform also generates inspection routes and intelligent control plans based on the inspection task optimization, and then sends them to the inspection equipment and intelligent control equipment for corresponding inspection and control, and generates corresponding early warning signals.
6. According to claim 5, a smart station intelligent inspection method is characterized in that: The inspection tasks corresponding to different times and frequencies generated based on real-time status analysis, equipment importance judgment and fault prediction results are as follows: The corresponding weights are generated for the three indicators of real-time status, equipment importance and fault prediction based on the improved slime mold optimization algorithm. The improved slime mold optimization algorithm is optimized with the comprehensive safety of the smart station as the goal to generate a comprehensive evaluation value, and the inspection priority and inspection frequency are divided according to the comprehensive evaluation value; Encode the inspection tasks of the inspection points in the smart station house, as follows: Generated based on remote control platform analysis Individual inspection tasks: in, Indicates Inspection tasks; according to Each priority generates different levels of inspection tasks: in, Indicates The first priority Individual inspection tasks; With the goal of minimizing the time consumption, the execution order and inspection path of sub-inspection tasks at different levels are optimized based on the improved slime mold optimization algorithm. The inspection paths corresponding to the inspection tasks are merged, sorted in descending order of time consumption and summarized into the inspection task set, and the inspection task set is sorted in order from the lowest priority to the highest priority. Define a chromosome, and encode it on the genes of the chromosome in the sorting order. After the encoding is completed, decode the chromosome and reverse the sequence information of the chromosome. The improved slime mold optimization is specifically as follows: Phase 1: The slime mold approaches the food according to the smell in the air. The slime mold is the sub-inspection task or inspection path to be optimized, and the food is the sub-inspection task sequence or inspection path with the shortest consumption time. The shorter the sub-inspection task sequence or the shortest consumption time of the inspection path, the higher the degree of optimization of the sub-inspection task or inspection path. On the contrary, the degree of optimization of the sub-inspection task or inspection path is reduced, and the optimization turns to other sub-inspection tasks or inspection paths to be optimized. in, Indicates the current iteration number; Indicates the location of the sub-inspection task or inspection path to be optimized; Indicates The sub-inspection task or inspection path to be optimized in the next iteration In the The location of the dimension; Indicates the dominant sub-inspection task or inspection path position selected according to the preferred matrix, where: for Integer within ; Indicates The sub-inspection task or inspection path to be optimized in the first iteration is The location of the dimension; Indicates The sub-inspection task or inspection path to be optimized is randomly selected in the first iteration. The location of the dimension; Simulate the interaction process of the inspection task or inspection path concentrated information in the sub-inspection task or inspection path to be optimized, , obey Uniform distribution of Simulate the process of sub-inspection tasks or inspection paths to be optimized to preserve themselves. ,obey Uniform distribution of express Random numbers within Indicates the scale of the inspection task or inspection path set; Indicates The fitness value of the sub-inspection task or inspection path to be optimized; Indicates the fitness value of the global optimal sub-inspection task or inspection path to be optimized; in, represents the rounding function; Indicates the maximum number of iterations; the improved The value range is , and obey Uniform distribution of in, is a mathematical constant; Phase 2: The sub-inspection task or inspection path to be optimized connects multiple sub-inspection task sequences or inspection path sets with the shortest consumption time, and establishes a connection network with different connection degrees between the sub-inspection task sequences or inspection path sets with the shortest consumption time. When the connection line is close to the sub-inspection task sequence or inspection path set with the shortest consumption time, the signal emitted by the sub-inspection task or inspection path to be optimized stimulates the connection line oscillator to generate a propagation wave, thereby promoting the optimization process. The shorter the time of the sub-inspection task sequence or inspection path to be optimized, the lower the degree of optimization, the stronger the wave signal generated, the faster the optimization process, and the higher the degree of connection. Otherwise, the lower the degree of connection: in, and Respectively represent the upper and lower bounds of the search space; and Both said Random numbers within represents the transition probability; represents the weight factor of the random individuals of slime mold; Indicates Iteration slime mold individuals In the The location of the dimension; Phase 3: The connection line oscillator generates propagation waves, changes the order of sub-inspection tasks or the optimization process of the inspection path, through , and Simulate the oscillation frequency and connection degree of the connection line. The sub-inspection task sequence or inspection path to be optimized slowly approaches the shortest consumption time during the optimization process. When the shortest consumption time is found, it approaches and replaces the position corresponding to the sub-inspection task sequence or inspection path with the shortest consumption time more quickly. in, and They represent the optimal fitness value and the worst fitness value of the sub-inspection task sequence or inspection path in the current generation respectively; express Uniform random numbers within .
7. The intelligent inspection method for a smart station building according to claim 6 is characterized in that: In S4, one inspection point corresponds to a plurality of inspection tasks, and each inspection task corresponds to a different priority.
8. The intelligent inspection method for a smart station building according to claim 6 is characterized in that: In S4, the inspection route is optimized based on an improved slime mold optimization algorithm with the goal of minimizing the inspection path.