Intelligent operation and maintenance method and system for expressway energy facilities and medium

Abstract

The invention discloses an intelligent operation and maintenance method and system for highway energy facilities, and a medium, mainly relates to the technical field of intelligent operation and maintenance, and is used for solving the problems that the manual inspection coverage rate is low and lags behind, the rule threshold alarm false alarm rate is high, and maintenance resource distribution depends on artificial experience in the existing scheme. Comprising the following steps: inputting operation parameters and environment parameters into a preset trained neural network algorithm to obtain an initial fault judgment result; based on the initial fault judgment result, determining energy facilities with potential safety hazards and obtaining maintenance time corresponding to the potential safety hazards; generating a maintenance task corresponding to the current hidden danger; wherein the maintenance task comprises the position of the energy facility with the potential safety hazard, the maintenance time and the initial fault judgment result; obtaining an initial maintenance terminal whose position distance to the energy facility is less than a preset distance; and broadcasting the maintenance task to all the initial maintenance terminals, and determining the initial maintenance terminal which returns the receiving information for the first time as a final maintenance terminal.

Description

Technical Field

[0001] The present application relates to the field of facility operation and maintenance technology, and in particular to a method, system and medium for intelligent operation and maintenance of highway energy facilities. Background Art

[0002] Currently, the operation and maintenance of highway energy facilities (such as lighting and monitoring power supplies) primarily relies on regular manual inspections and post-fault reporting. Traditionally, maintenance personnel are required to record equipment operating status (such as voltage and temperature) on-site, or collect limited data from basic sensors and then manually analyze it. Some systems have adopted SCADA (Supervisory Control and Data Acquisition) for remote monitoring, but fault diagnosis still relies on empirical rules or simple threshold alarms. Maintenance tasks must be manually assigned to designated teams, limiting response efficiency due to labor scheduling and communication delays.

[0003] This approach suffers from the following drawbacks: First, manual inspection coverage is low and delayed, making it impossible to detect sudden potential hazards (such as cable overheating) in real time. Second, rule-based threshold alarms have a high false alarm rate, making it difficult to distinguish complex fault modes (such as intermittent short circuits). Third, maintenance resource allocation relies on manual experience, which can lead to long-distance scheduling and overlapping tasks, resulting in response timeouts. Furthermore, task dispatch relies on single-point communication, which can lead to missed inspections if the terminal is offline, compromising highway operational safety. Summary of the Invention

[0004] The present application provides a method, system and medium for intelligent operation and maintenance of highway energy facilities to solve the problems of existing solutions such as low and delayed manual inspection coverage, high false alarm rate of rule threshold alarms, and dependence of maintenance resource allocation on manual experience.

[0005] In a first aspect, the present application provides a method for intelligent operation and maintenance of highway energy facilities, the method comprising: Based on energy facilities and sensors preset in energy facilities, collect operating parameters and environmental parameters of energy facilities; Input the operating parameters and environmental parameters into the preset trained neural network algorithm to obtain the initial fault judgment result; Based on the initial fault diagnosis results, identify energy facilities with potential safety hazards and obtain the corresponding maintenance time for the potential safety hazards; Generate maintenance tasks corresponding to current hidden dangers; the maintenance tasks include the location of the energy facility with safety hazards, maintenance time, and initial fault judgment results; Acquire an initial maintenance terminal that is less than a preset distance from the energy facility location; The maintenance task is broadcast to all initial maintenance terminals, and the initial maintenance terminal that first returns a receipt message is determined as the final maintenance terminal.

[0006] In one implementation of the present application, based on energy facilities and sensors preset in the energy facilities, the operating parameters and environmental parameters of the energy facilities are collected, specifically including: Establishing communication connections between energy facilities, sensors preset in energy facilities, and preset edge gateways; Uploading the initial operating parameters of the energy facility and the initial environmental parameters of the sensors preset in the energy facility to a preset edge gateway, unifying the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unifying the initial environmental parameters into a preset second format to obtain environmental parameters; Upload the operating parameters and environmental parameters to the server through the preset edge gateway.

[0007] In one implementation of the present application, before inputting the operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result, the method further includes: Obtain operating data within a historical period; extract operating parameters, environmental parameters, and fault judgment results from the operating data as training samples; The training samples are used to train the initial neural network algorithm to obtain a trained neural network algorithm.

[0008] In one implementation of the present application, the maintenance task is broadcast to all initial maintenance terminals, and the initial maintenance terminal that first returns a receipt message is determined as the final maintenance terminal, specifically including: S1. Broadcast a maintenance task instruction package in JSON format to all registered initial maintenance terminals via the MQTT protocol; the maintenance task instruction package contains the task ID, timeout parameter, and maintenance task; S2. After receiving the command, each initial maintenance terminal will immediately return a confirmation frame containing the device MAC address and current load status; S3. Create an independent FIFO queue for each initial maintenance terminal and buffer the response packets in the order of arrival. S4. During each preset time period, check the header data packet in the FIFO queue; if only one response packet is received, it is directly determined to be the first response; if multiple response packets are received, they are re-sorted by TCP sequence number + hardware timestamp to determine the first response; S5. Confirm the initial maintenance terminal corresponding to the first response as the final maintenance terminal; S6. When no response packet is received within the time period corresponding to the timeout parameter, return to S1.

[0009] In one implementation of the present application, after broadcasting the maintenance task to all initial maintenance terminals and determining that the first initial maintenance terminal that returns a receipt message is the final maintenance terminal, the method further includes: Start the supervision countdown mechanism, and when the preset supervision countdown time period is reached, send a progress acquisition instruction to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

[0010] In a second aspect, the present application provides an intelligent operation and maintenance system for highway energy facilities, the system comprising: A collection module, used for collecting operating parameters and environmental parameters of energy facilities based on energy facilities and sensors preset in energy facilities; An acquisition module is used to input operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result; A determination module is used to determine energy facilities with potential safety hazards based on the initial fault judgment results and obtain maintenance time corresponding to the potential safety hazards; An acquisition module is used to generate a maintenance task corresponding to the current hidden danger; wherein the maintenance task includes the location of the energy facility with the safety hazard, the maintenance time, and the initial fault judgment result; and obtain an initial maintenance terminal that is less than a preset distance from the energy facility location; The terminal module is used to broadcast the maintenance task to all initial maintenance terminals and determine the initial maintenance terminal that first returns the reception information as the final maintenance terminal.

[0011] In one implementation of the present application, the acquisition module includes an acquisition unit, Used to establish a communication connection between energy facilities, sensors preset in energy facilities and preset edge gateways; Uploading the initial operating parameters of the energy facility and the initial environmental parameters of the sensors preset in the energy facility to a preset edge gateway, unifying the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unifying the initial environmental parameters into a preset second format to obtain environmental parameters; Upload the operating parameters and environmental parameters to the server through the preset edge gateway.

[0012] In one implementation of the present application, the acquisition module includes a training unit, Used to obtain operating data within a historical period; extract operating parameters, environmental parameters, and fault judgment results from the operating data as training samples; The training samples are used to train the initial neural network algorithm to obtain a trained neural network algorithm.

[0013] In one implementation of the present application, the system further includes a supervision module. It is used to start the supervision countdown mechanism. When the preset supervision countdown time period is reached, a progress acquisition instruction is sent to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

[0014] In a third aspect, the present application provides a non-volatile computer storage medium on which computer instructions are stored. When the computer instructions are executed, they implement a method for intelligent operation and maintenance of highway energy facilities as described above.

[0015] It can be seen from the above technical solutions that this application has the following advantages: To improve inspection coverage, this application utilizes pre-installed sensors in energy facilities to enable distributed, 24 / 7 data collection, addressing the issues of long inspection intervals and numerous blind spots associated with manual inspections. The system monitors key parameters such as cable temperature and current fluctuations in real time, responding to sudden anomalies within seconds and avoiding the lag inherent in manual inspections. Furthermore, a pre-configured sensor layout strategy ensures full coverage of key equipment.

[0016] To address the high false alarm rate, this application uses a neural network for multi-parameter correlation analysis. Compared to traditional single-threshold alarm mechanisms, this application can integrate multiple characteristic dimensions, such as voltage, temperature, and harmonics, to identify the true fault mode. Especially for complex faults such as intermittent short circuits, the neural network's temporal feature analysis improves identification accuracy and reduces unnecessary on-site inspections.

[0017] To optimize resource allocation, this application establishes a dynamic scheduling mechanism based on geolocation services. By automatically matching the fault point with the nearest available maintenance terminal, this avoids empirical errors in manual scheduling. A broadcast-based task dispatching design ensures task accessibility even in unstable communication situations. A "first responder" mechanism ensures the optimal allocation of maintenance resources, shortening the emergency response window.

[0018] This application achieves standardized and intelligent operations and maintenance through process reengineering. Automating the entire process, from data collection and analysis to task dispatch, not only reduces the risk of human error but also establishes a traceable and optimizable closed-loop management system. This model provides a new technical path to ensure the reliable operation of highway energy facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of a method for intelligent operation and maintenance of highway energy facilities provided in an embodiment of the present application.

[0021] Figure 2This is a schematic diagram of the internal structure of an intelligent operation and maintenance system for highway energy facilities provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] It should be understood by those skilled in the art that the embodiments described below are merely preferred embodiments of the present disclosure and do not imply that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely intended to explain the technical principles of the present disclosure and are not intended to limit the scope of protection of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present disclosure.

[0024] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0025] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0026] The embodiment provides a method for intelligent operation and maintenance of highway energy facilities, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Based on the energy facility and sensors preset in the energy facility, collect the operating parameters and environmental parameters of the energy facility.

[0027] In some embodiments, the energy facility and its pre-set sensors are used to collect the operating parameters and environmental parameters of the energy facility, including: Establishing communication connections between energy facilities, sensors preset in energy facilities, and preset edge gateways; Uploading the initial operating parameters of the energy facility and the initial environmental parameters of the sensors preset in the energy facility to a preset edge gateway, unifying the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unifying the initial environmental parameters into a preset second format to obtain environmental parameters; Upload the operating parameters and environmental parameters to the server through the preset edge gateway.

[0028] Those skilled in the art will appreciate that this step utilizes the edge gateway's format unification module to convert initial parameters from various sources into a pre-defined format, eliminating data heterogeneity and ensuring compatibility and accuracy for subsequent analysis. Establishing a stable communication connection between facilities, sensors, and the edge gateway enables real-time upload of operating parameters (such as energy consumption and device status) and environmental parameters (such as temperature and humidity), providing a data foundation for dynamic control. The edge gateway preprocesses and standardizes the data before uploading it to the server, reducing redundant transmission, lowering cloud processing load, and improving overall system response efficiency.

[0029] Step 120: Input the operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result.

[0030] Before inputting the operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result, the method may further include: Obtain operating data within a historical time period; extract operating parameters, environmental parameters, and fault judgment results from the operating data as training samples; use the training samples to train an initial neural network algorithm to obtain a trained neural network algorithm.

[0031] Those skilled in the art will appreciate that the neural network model trained in this step can extract nonlinear features from multi-dimensional parameters (such as voltage fluctuations, temperature gradients, and vibration frequencies). Compared to traditional threshold alarm mechanisms, it can identify complex failure modes (such as equipment aging combined with environmental anomalies). Models trained using historical data are targeted to specific facilities, reducing the risk of false positives.

[0032] This step utilizes a dual-loop mechanism of "historical data training + real-time data iteration." The initial training phase establishes a baseline model using massive historical samples (including full-condition data for both normal and faulty conditions). During the operational phase, the online learning module automatically adds newly generated fault cases to the training set, enabling the model to adapt to dynamic changes such as equipment performance degradation and new fault types.

[0033] This step, from data collection and format conversion to fault determination, requires no human intervention, making it particularly suitable for unmanned scenarios such as distributed energy stations. The algorithm's structured output (such as failure probability and severity level) can directly trigger the maintenance work order system, upgrading the traditional "post-fault maintenance" model to "predictive maintenance" and shortening the mean fault response time.

[0034] Step 130: Based on the initial fault judgment result, determine the energy facilities with potential safety hazards and obtain the maintenance time corresponding to the potential safety hazards.

[0035] Those skilled in the art will appreciate that this step uses the algorithm's initial fault determination to quickly identify specific energy facilities (such as transformers and photovoltaic inverters) with potential safety hazards, avoiding the waste of resources associated with a comprehensive investigation. By combining the equipment's real-time status with historical maintenance records, optimal maintenance windows (such as during low-load periods) are automatically generated, ensuring timely fault resolution while minimizing the impact on normal operations. Linking maintenance time with the work order system creates an automated closed-loop "diagnosis-decision-execution" process, improving the efficiency of addressing safety hazards.

[0036] ‌Specific implementation example‌: The system has a pre-set maintenance policy library, which contains response timelines for different fault levels (e.g., a Level 1 fault must be addressed within 2 hours). Once the neural network outputs a fault diagnosis, it automatically matches the policy library to generate a maintenance time recommendation. It also draws on equipment inventory data, links maintenance team schedules with spare parts inventory status, and ultimately outputs a prioritized maintenance schedule that is pushed to the O&M terminal.

[0037] Step 140: Generate a maintenance task corresponding to the current hidden danger; and obtain an initial maintenance terminal whose distance from the energy facility is less than a preset distance.

[0038] Among them, maintenance tasks include the location of energy facilities with safety hazards, maintenance time, and initial fault judgment results.

[0039] In some embodiments, broadcasting the maintenance task to all initial maintenance terminals and determining the initial maintenance terminal that first returns a receipt message as the final maintenance terminal specifically includes: S1. Broadcast a maintenance task instruction package in JSON format to all registered initial maintenance terminals via the MQTT protocol; the maintenance task instruction package contains the task ID, timeout parameter, and maintenance task; S2. After receiving the command, each initial maintenance terminal will immediately return a confirmation frame containing the device MAC address and current load status; S3. Create an independent FIFO queue for each initial maintenance terminal and buffer the response packets in the order of arrival. S4. During each preset time period, check the header data packet in the FIFO queue; if only one response packet is received, it is directly determined to be the first response; if multiple response packets are received, they are re-sorted by TCP sequence number + hardware timestamp to determine the first response; S5. Confirm the initial maintenance terminal corresponding to the first response as the final maintenance terminal; S6. When no response packet is received within the time period corresponding to the timeout parameter, return to S1.

[0040] Those skilled in the art will appreciate that this step, by screening the nearest terminal and combining dual verification of MAC address and load status, ensures optimal terminal selection to address potential vulnerabilities and reduces response latency (theoretically reducing latency by over 40%). A two-level sorting method using TCP sequence numbers and hardware timestamps effectively addresses contention issues associated with simultaneous responses from multiple terminals, avoiding the resource waste associated with traditional polling mechanisms. A timeout retransmission mechanism, combined with independent FIFO queue management, automatically triggers task reallocation in the event of network fluctuations or terminal offline, improving system availability.

[0041] Step 150: broadcast the maintenance task to all initial maintenance terminals, and determine the initial maintenance terminal that first returns a reception message as the final maintenance terminal.

[0042] After broadcasting the maintenance task to all initial maintenance terminals and determining the initial maintenance terminal that first returns a receipt message as the final maintenance terminal, the method further includes: Start the supervision countdown mechanism, and when the preset supervision countdown time period is reached, send a progress acquisition instruction to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

[0043] Those skilled in the art will appreciate that this step eliminates the latency of traditional centralized scheduling through broadcast-based task distribution. All terminals meeting geofencing requirements receive instructions simultaneously, achieving zero-wait transmission for task releases. A hardware-level first-responder determination mechanism (MAC address + timing stamp) ensures the optimal terminal is identified within milliseconds, improving efficiency compared to manual dispatch. A monitoring countdown mechanism creates a mandatory progress reporting node to prevent tasks from entering a "zombie state" and ensure a traceable execution path for each maintenance task. Progress acquisition instructions utilize a two-way verification protocol that not only collects terminal reporting data but also simultaneously verifies the device's online status, effectively identifying false completions. An intelligent adjustment function for the preset time window automatically extends or shortens the monitoring interval based on task complexity, balancing monitoring intensity and communication overhead. A first-responder failure protection mechanism automatically triggers task rebroadcast if there is no feedback from the terminal, resolving process interruptions caused by sudden device offline. Digitally signed logs are maintained for all interactions, meeting audit requirements and providing data support for subsequent optimization.

[0044] In addition, this application Figure 2 This application provides an intelligent operation and maintenance system for highway energy facilities. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The collection module 210 is used to collect the operating parameters and environmental parameters of the energy facility based on the energy facility and the sensors preset in the energy facility.

[0045] The acquisition module 210 includes an acquisition unit, which is used to establish a communication connection between the energy facility, the preset sensor of the energy facility and the preset edge gateway; upload the initial operating parameters of the energy facility and the initial environmental parameters of the preset sensor of the energy facility to the preset edge gateway, and unify the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unify the initial environmental parameters into a preset second format to obtain environmental parameters; and upload the operating parameters and environmental parameters to the server through the preset edge gateway.

[0046] Those skilled in the art will appreciate that the acquisition module 210, through the edge gateway's format unification module, converts initial parameters from various sources into a pre-set format, eliminating data heterogeneity and ensuring compatibility and accuracy for subsequent analysis. A stable communication connection is established between facilities, sensors, and the edge gateway, enabling real-time upload of operating parameters (such as energy consumption and device status) and environmental parameters (such as temperature and humidity), providing a data foundation for dynamic control. The edge gateway preprocesses and standardizes the data before uploading it to the server, reducing redundant transmission, lowering cloud processing load, and improving overall system response efficiency.

[0047] The acquisition module 220 is used to input the operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result.

[0048] The acquisition module 220 includes a training unit for acquiring operation data within a historical time period; extracting operation parameters, environmental parameters, and fault judgment results from the operation data as training samples; and using the training samples to train an initial neural network algorithm to obtain a trained neural network algorithm.

[0049] Those skilled in the art will appreciate that the neural network model trained by acquisition module 220 can extract nonlinear features from multi-dimensional parameters (such as voltage fluctuations, temperature gradients, and vibration frequencies). Compared to traditional threshold alarm mechanisms, it can identify complex failure modes (such as equipment aging combined with environmental anomalies). Models trained using historical data are targeted to specific facilities, reducing the risk of false positives.

[0050] The acquisition module 210 utilizes a dual-loop mechanism of "historical data training + real-time data iteration." During the initial training phase, a baseline model is established using massive historical samples (including full-condition data for both normal and faulty conditions). During the operational phase, the online learning module automatically adds newly generated fault cases to the training set, enabling the model to adapt to dynamic changes such as equipment performance degradation and new fault types.

[0051] The acquisition module 210 eliminates the need for human intervention throughout the entire process, from data collection and format conversion to fault diagnosis, making it particularly suitable for unmanned scenarios such as distributed energy stations. The structured results (such as failure probability and severity level) output by the algorithm can directly trigger the operation and maintenance work order system, upgrading the traditional "post-fault maintenance" model to "predictive maintenance" and shortening the mean fault response time.

[0052] The determination module 230 is used to determine the energy facilities with potential safety hazards and obtain the maintenance time corresponding to the potential safety hazards based on the initial fault judgment result.

[0053] Those skilled in the art will appreciate that the algorithmic determination module 230 uses to quickly identify specific energy facilities (such as transformers and photovoltaic inverters) posing safety hazards based on the initial fault result, avoiding the waste of resources associated with a comprehensive investigation. By combining the real-time status of the equipment with historical maintenance records, it automatically generates optimal maintenance windows (such as during low-load periods), ensuring timely fault resolution while minimizing the impact on normal operations. Linking maintenance time with the work order system creates an automated closed-loop "diagnosis-decision-execution" process, improving the efficiency of addressing safety hazards.

[0054] ‌Specific implementation example‌: The system has a pre-set maintenance policy library, which contains response timelines for different fault levels (e.g., a Level 1 fault must be addressed within 2 hours). Once the neural network outputs a fault diagnosis, it automatically matches the policy library to generate a maintenance time recommendation. It also draws on equipment inventory data, links maintenance team schedules with spare parts inventory status, and ultimately outputs a prioritized maintenance schedule that is pushed to the O&M terminal.

[0055] The acquisition module 240 is used to generate a maintenance task corresponding to the current hidden danger; wherein the maintenance task includes the location of the energy facility with the safety hazard, the maintenance time, and the initial fault judgment result; obtain the initial maintenance terminal whose distance from the energy facility location is less than a preset distance; the terminal module is used to broadcast the maintenance task to all initial maintenance terminals, and determine that the first initial maintenance terminal that returns the received information is the final maintenance terminal.

[0056] Those skilled in the art will appreciate that Acquisition Module 240 selects the most recent terminal and combines dual verification of MAC address and load status to ensure optimal terminal selection for addressing potential risks and reduce response latency (theoretical latency reduction of over 40%). A two-level sorting method using TCP sequence numbers and hardware timestamps effectively resolves contention issues when multiple terminals respond simultaneously, avoiding the resource waste associated with traditional polling mechanisms. A timeout retransmission mechanism, combined with independent FIFO queue management, automatically triggers task reallocation in the event of network fluctuations or terminal offline, improving system availability. Acquisition Module 240 eliminates the latency associated with traditional centralized scheduling through broadcast-based task distribution. All terminals meeting geofence requirements receive instructions synchronously, achieving zero-wait transmission for task releases. A hardware-based first-responder determination mechanism (MAC address + timing stamp) ensures optimal terminal selection within milliseconds, improving efficiency compared to manual dispatching. An intelligent adjustment function for preset time windows automatically extends or shortens the monitoring interval based on task complexity, balancing monitoring intensity and communication overhead. The first-response failure protection mechanism automatically triggers task rebroadcast when there is no feedback from the terminal, resolving process interruptions caused by sudden device offline; digitally signed logs are retained for all interaction processes, meeting audit requirements and providing data support for subsequent optimization.

[0057] The system also includes a supervision module, It is used to start the supervision countdown mechanism. When the preset supervision countdown time period is reached, a progress acquisition instruction is sent to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

[0058] In addition, an embodiment of the present application further provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a method for intelligent operation and maintenance of highway energy facilities as described above is implemented.

[0059] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent operation and maintenance of highway energy facilities, characterized in that: The method comprises: Based on energy facilities and sensors preset in energy facilities, collect operating parameters and environmental parameters of energy facilities; Input the operating parameters and environmental parameters into the preset trained neural network algorithm to obtain the initial fault judgment result; Based on the initial fault diagnosis results, identify energy facilities with potential safety hazards and obtain the corresponding maintenance time for the potential safety hazards; Generate maintenance tasks corresponding to current hidden dangers; the maintenance tasks include the location of the energy facility with safety hazards, maintenance time, and initial fault judgment results; Acquire an initial maintenance terminal that is less than a preset distance from the energy facility location; The maintenance task is broadcast to all initial maintenance terminals, and the initial maintenance terminal that first returns a receipt message is determined as the final maintenance terminal.

2. The intelligent operation and maintenance method for highway energy facilities according to claim 1 is characterized in that: Based on energy facilities and their preset sensors, the operating and environmental parameters of energy facilities are collected, including: Establishing communication connections between energy facilities, sensors preset in energy facilities, and preset edge gateways; Uploading the initial operating parameters of the energy facility and the initial environmental parameters of the sensors preset in the energy facility to a preset edge gateway, unifying the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unifying the initial environmental parameters into a preset second format to obtain environmental parameters; Upload the operating parameters and environmental parameters to the server through the preset edge gateway.

3. The intelligent operation and maintenance method for highway energy facilities according to claim 1 is characterized in that: Before inputting the operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result, the method further includes: Obtain operating data within a historical period; extract operating parameters, environmental parameters, and fault judgment results from the operating data as training samples; The training samples are used to train the initial neural network algorithm to obtain a trained neural network algorithm.

4. The intelligent operation and maintenance method for highway energy facilities according to claim 1 is characterized in that: Broadcast the maintenance task to all initial maintenance terminals and determine the first initial maintenance terminal that returns a receipt message as the final maintenance terminal. Specifically, the following steps are performed: S1. Broadcast a maintenance task instruction package in JSON format to all registered initial maintenance terminals via the MQTT protocol; the maintenance task instruction package contains the task ID, timeout parameter, and maintenance task; S2. After receiving the command, each initial maintenance terminal will immediately return a confirmation frame containing the device MAC address and current load status; S3. Create an independent FIFO queue for each initial maintenance terminal and buffer the response packets in the order of arrival. S4. During each preset time period, check the header data packet in the FIFO queue; if only one response packet is received, it is directly determined to be the first response; if multiple response packets are received, they are re-sorted by TCP sequence number + hardware timestamp to determine the first response; S5. Confirm the initial maintenance terminal corresponding to the first response as the final maintenance terminal; S6. When no response packet is received within the time period corresponding to the timeout parameter, return to S1.

5. The intelligent operation and maintenance method for highway energy facilities according to claim 1 is characterized in that: After broadcasting the maintenance task to all initial maintenance terminals and determining the initial maintenance terminal that first returns a receipt message as the final maintenance terminal, the method further includes: Start the supervision countdown mechanism, and when the preset supervision countdown time period is reached, send a progress acquisition instruction to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

6. An intelligent operation and maintenance system for highway energy facilities, characterized in that: The system comprises: A collection module, used for collecting operating parameters and environmental parameters of energy facilities based on energy facilities and sensors preset in energy facilities; An acquisition module is used to input operating parameters and environmental parameters into a preset trained neural network algorithm to obtain an initial fault judgment result; A determination module is used to determine energy facilities with potential safety hazards based on the initial fault judgment results and obtain maintenance time corresponding to the potential safety hazards; An acquisition module is used to generate a maintenance task corresponding to the current hidden danger; wherein the maintenance task includes the location of the energy facility with the safety hazard, the maintenance time, and the initial fault judgment result; and obtain an initial maintenance terminal that is less than a preset distance from the energy facility location; The terminal module is used to broadcast the maintenance task to all initial maintenance terminals and determine the initial maintenance terminal that first returns the reception information as the final maintenance terminal.

7. The intelligent operation and maintenance system for highway energy facilities according to claim 6 is characterized in that: The acquisition module includes an acquisition unit, Used to establish a communication connection between energy facilities, sensors preset in energy facilities and preset edge gateways; Uploading the initial operating parameters of the energy facility and the initial environmental parameters of the sensors preset in the energy facility to a preset edge gateway, unifying the initial operating parameters into a preset first format through a preset format unification module in the preset edge gateway to obtain operating parameters; unifying the initial environmental parameters into a preset second format to obtain environmental parameters; Upload the operating parameters and environmental parameters to the server through the preset edge gateway.

8. The intelligent operation and maintenance system for highway energy facilities according to claim 6 is characterized in that: The acquisition module includes training units, Used to obtain operating data within a historical period; extract operating parameters, environmental parameters, and fault judgment results from the operating data as training samples; The training samples are used to train the initial neural network algorithm to obtain a trained neural network algorithm.

9. The intelligent operation and maintenance system for highway energy facilities according to claim 6 is characterized in that: The system further comprises a supervisory module, It is used to start the supervision countdown mechanism. When the preset supervision countdown time period is reached, a progress acquisition instruction is sent to the final maintenance terminal to obtain the task progress information returned by the final maintenance terminal.

10. A non-volatile computer storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, they implement a method for intelligent operation and maintenance of highway energy facilities as described in any one of claims 1 to 5.

Images