Traffic supplementary lighting equipment operation and maintenance management method and platform based on LoRa transmission

Abstract

The present invention discloses a method and platform for operation and maintenance management of traffic fill light equipment based on LoRa transmission, which relates to the technical field related to data communication transmission. The method includes: deploying a LoRa wireless communication module to collect real-time data from target traffic fill light equipment; performing dynamic analysis based on the fill light operation data set, determining anomalies based on the dynamic analysis results, and generating abnormality alarm information; transmitting the information to the operation and maintenance management platform to trigger remote maintenance instructions; issuing control parameter adjustment instructions to the target traffic fill light equipment; and performing real-time operation and maintenance management optimization on the target traffic fill light equipment in combination with the control parameter adjustment instructions. This method solves the technical problems existing in the prior art, such as the widespread distribution of traffic fill light equipment, the difficulty of timely fault detection during manual inspections, and the susceptibility of the equipment to environmental interference, which in turn lead to inaccurate abnormality alarm information and poor operation and maintenance efficiency and reliability of traffic fill light equipment, thereby achieving the technical effect of improving equipment operation and maintenance efficiency and reliability.

Description

Technical Field

[0001] The present application relates to the technical field related to data communication transmission, and specifically to an operation and maintenance management method and platform for traffic supplementary lighting equipment based on LoRa transmission. Background Art

[0002] The stable operation of traffic supplementary lighting equipment ensures that traffic monitoring systems can clearly capture key information such as vehicles and pedestrians under various lighting conditions, playing a key role in maintaining traffic order and preventing and handling accidents. However, the operation and maintenance of traditional traffic supplementary lighting equipment is difficult. In terms of distribution, it is widely distributed in urban streets and alleys, highways, bridges and tunnels, and other places. Manual inspection methods are inefficient and cannot detect equipment failures in a timely manner, often causing faulty equipment to malfunction for a long time, seriously affecting the effectiveness of traffic monitoring. In terms of the operating environment, traffic supplementary lighting equipment is easily interfered with by complex environmental factors such as severe weather, large fluctuations in temperature and humidity, and electromagnetic interference. This greatly increases the probability of equipment experiencing problems such as bulb damage, power failure, and control circuit anomalies, further exacerbating the complexity of traffic supplementary lighting equipment operation and maintenance, affecting the efficiency and reliability of traffic supplementary lighting equipment operation and management.

[0003] Therefore, in the current relevant technologies, there are technical problems such as the wide distribution of traffic lighting equipment, difficulty in timely detection of faults during manual inspections, and susceptibility of equipment to environmental interference, which in turn leads to inaccurate abnormal alarm information and poor operation and maintenance efficiency and reliability of traffic lighting equipment. Summary of the Invention

[0004] This application provides a LoRa-based traffic lighting equipment operation and maintenance management method and platform, which solves the technical problems in the prior art that traffic lighting equipment is widely distributed, manual inspections are difficult to detect faults in a timely manner, and the equipment is susceptible to environmental interference, which in turn leads to inaccurate abnormal alarm information and poor operation and maintenance efficiency and reliability of traffic lighting equipment. The application achieves the technical effect of improving the operation and maintenance efficiency and reliability of equipment.

[0005] The present application provides a method for operation and maintenance management of traffic fill light equipment based on LoRa transmission, the method comprising: deploying a LoRa wireless communication module, performing real-time data collection of a target traffic fill light device through the LoRa wireless communication module, and obtaining a fill light operation data set; performing dynamic analysis based on the fill light operation data set, making an abnormality judgment based on the dynamic analysis result, and generating abnormality alarm information; transmitting the abnormality alarm information to an operation and maintenance management platform to trigger a remote maintenance instruction; issuing a control parameter adjustment instruction to the target traffic fill light device through the LoRa wireless communication module; and performing real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction in combination with the control parameter adjustment instruction.

[0006] In a possible implementation, the LoRa transmission-based traffic fill light equipment operation and maintenance management method also performs the following processing: deploying a LoRa wireless communication module on the road traffic monitoring fill light equipment; collecting real-time parameters of the target traffic fill light equipment at fixed intervals through the LoRa wireless communication module to determine the equipment cycle data group; classifying and cleaning the equipment cycle data group according to the data type to generate a standardized data set; encapsulating the standardized data set into a LoRa protocol frame through the LoRa wireless communication module to determine the fill light operation data set.

[0007] In a possible implementation, the LoRa transmission-based traffic fill light equipment operation and maintenance management method also performs the following processing: sending the fill light operation data set to the operation and maintenance management platform through a dynamic channel allocation mechanism for data classification and storage, and determining multiple operation storage data information; retrieving historical operation data for training and constructing a random forest model; dividing the multiple operation storage data information through the random forest model to determine multiple fault status data; performing cluster analysis on the target traffic fill light equipment under different environmental scenarios and setting an adaptive threshold; judging the multiple fault status data according to the adaptive threshold, generating a composite judgment rule, and performing real-time judgment update according to the composite judgment rule to obtain the dynamic analysis result.

[0008] In a possible implementation, the operation and maintenance management method of traffic fill light equipment based on LoRa transmission also performs the following processing: monitoring the channel of the LoRa wireless communication module to obtain a signal quality index; setting a signal expectation threshold, and when the signal quality index is lower than the signal expectation threshold, switching the channel of the LoRa wireless communication module to a backup channel to obtain a channel switching record; dynamically adjusting the data sending interval of the fill light operation data set according to the channel switching record to obtain a signal status log; activating the dynamic channel allocation mechanism according to the signal status log to synchronize the fill light operation data set to the operation and maintenance management platform.

[0009] In a possible implementation, the LoRa transmission-based traffic supplementary lighting equipment operation and maintenance management method further performs the following processing: retrieving the operating data of the target traffic supplementary lighting equipment under different meteorological conditions during a historical period to construct a multidimensional training data set; performing time series analysis on the multidimensional training data set, and extracting periodic features based on the time series analysis results; cross-validating the multidimensional training data set with actual equipment fault records according to the periodic features, and adjusting the model hyperparameters based on the validation results to obtain the random forest model.

[0010] In a possible implementation, the LoRa transmission-based traffic supplementary lighting equipment operation and maintenance management method further performs the following processing: constructing a dynamic topology map according to the physical deployment location of the target traffic supplementary lighting equipment; traversing the dynamic topology map according to the dynamic analysis results to perform layout identification and determine multiple node identification results; performing abnormal judgment extraction based on the multiple node identification results, determining multiple abnormal device nodes, and correlating and analyzing the multiple abnormal device nodes with historical alarm records to generate the abnormal alarm information.

[0011] In a possible implementation, the operation and maintenance management method of the traffic supplementary lighting equipment based on LoRa transmission also performs the following processing: analyzing the historical alarm records and historical maintenance records to extract high-frequency fault modes and fault resolution strategies; verifying the effectiveness of the fault resolution strategies through simulation tests according to the high-frequency fault modes to generate strategy priority scores; integrating the fault resolution strategies with strategy priority scores higher than the preset scores to construct a maintenance strategy library; parsing based on the abnormal alarm information to determine the abnormality type, matching the abnormality type with the maintenance strategy library, and determining the control parameter adjustment instructions according to the matching results.

[0012] In a possible implementation, the LoRa transmission-based traffic fill light equipment operation and maintenance management method further performs the following processing: integrating the remote maintenance instruction and the control parameter adjustment instruction according to the abnormality type, executing the integrated instruction to determine the execution status data; judging whether the fill light operation data set has recovered to the normal threshold range based on the execution status data, and triggering an optimization signal if the fill light operation data set has not recovered to the normal threshold range; adaptively optimizing the integrated instruction through the optimization signal to generate a fill light equipment health report; and performing operation and maintenance management on the target traffic fill light equipment according to the fill light equipment health report.

[0013] In a possible implementation, the LoRa transmission-based traffic fill light equipment operation and maintenance management method further performs the following processing: dynamically adjusting the integrated instruction based on the optimization signal to determine the equipment operation and maintenance optimization log; performing operation and maintenance analysis according to the equipment operation and maintenance optimization log and the fill light operation data set to generate a health score matrix; and grading the target traffic fill light equipment based on the health score matrix to determine the fill light equipment health report.

[0014] The present application also provides a traffic fill light equipment operation and maintenance management platform based on LoRa transmission, including: an operation data set acquisition unit, used to deploy a LoRa wireless communication module, and perform real-time data collection of the target traffic fill light equipment through the LoRa wireless communication module to obtain a fill light operation data set; an abnormal alarm information generation unit, used to perform dynamic analysis based on the fill light operation data set, make abnormality judgments based on the dynamic analysis results, and generate abnormal alarm information; a remote maintenance instruction triggering unit, used to transmit the abnormal alarm information to the operation and maintenance management platform, and trigger remote maintenance instructions; a control parameter adjustment instruction issuing unit, used to issue control parameter adjustment instructions to the target traffic fill light equipment through the LoRa wireless communication module; an operation and maintenance management optimization unit, used to perform real-time operation and maintenance management optimization on the target traffic fill light equipment according to the remote maintenance instructions in combination with the control parameter adjustment instructions.

[0015] This application proposes a LoRa-based traffic fill light equipment operation and maintenance management method and platform. This method deploys LoRa wireless communication modules to collect data from target traffic fill light equipment in real time. Dynamic analysis is performed based on the fill light operation data set, and abnormality determinations are made based on the dynamic analysis results, generating abnormality alarm information. This information is transmitted to the operation and maintenance management platform, triggering remote maintenance instructions. Control parameter adjustment instructions are issued to the target traffic fill light equipment. In conjunction with the control parameter adjustment instructions, real-time operation and maintenance management optimization is performed on the target traffic fill light equipment. This method solves the existing technical problems of widespread distribution of traffic fill light equipment, difficulty in timely detection of faults during manual inspections, and susceptibility of equipment to environmental interference, which in turn lead to inaccurate abnormality alarm information and poor operation and maintenance efficiency and reliability of traffic fill light equipment. This method achieves the technical effect of improving equipment operation and maintenance efficiency and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the platform according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. On the contrary, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of the operation and maintenance management method for traffic supplementary lighting equipment based on LoRa transmission provided in an embodiment of the present application.

[0018] Figure 2 Schematic diagram of the structure of the traffic supplementary lighting equipment operation and maintenance management platform based on LoRa transmission provided in the embodiment of the present application.

[0019] Explanation of the reference numerals: operating data set obtaining unit 10 , abnormal alarm information generating unit 20 , remote maintenance instruction triggering unit 30 , control parameter adjustment instruction issuing unit 40 , operation and maintenance management optimization unit 50 . DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms “first\second” involved are merely to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions, for example, a process, method, platform, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0023] The embodiment of the present application provides a method for operation and maintenance management of traffic light supplementary equipment based on LoRa transmission, such as Figure 1 As shown, the method includes:

[0024] Step S100: deploy a LoRa wireless communication module, collect data from the target traffic fill light device in real time through the LoRa wireless communication module, and obtain a fill light operation data set.

[0025] Preferably, a LoRa wireless communication module is deployed on the road traffic monitoring fill light device, and the module is used to collect real-time data of the target traffic fill light device to obtain a fill light operation data set. Among them, the traffic fill light device is an important auxiliary equipment in the traffic monitoring system, mainly used to provide additional lighting for the monitoring camera under insufficient light conditions to ensure clear image and video acquisition effects. The traffic fill light generally uses a high-brightness LED (light-emitting diode) as a light source. The fill light drives the LED to emit light through a control circuit. According to different working modes (constant light, strobe or flash), the control circuit will provide current to the LED according to the corresponding frequency and duty cycle, so that it emits light of different intensities and frequencies; LoRa is an ultra-long-distance wireless transmission solution based on spread spectrum technology. It belongs to the low-power wide area network (LPWAN) wireless communication technology and is widely used in the field of Internet of Things. It has the characteristics of long distance, low power consumption, multiple nodes and low cost.

[0026] Preferably, deploying a LoRa wireless communication module on a road traffic monitoring fill light device means integrating the module into the control system of the traffic fill light device. The traffic fill light device uses LoRa technology to communicate wirelessly with other devices (such as gateways, operation and maintenance management platforms) to upload data and receive control instructions. Specifically, through the deployed LoRa wireless communication module, various operating parameters of the target traffic fill light device (including power, temperature, health status and trigger times, etc.) are collected in real time to form a fill light operation data set, where power is the electrical power consumed by the fill light during operation. If the power suddenly increases, it may indicate that the fill light is Problems such as short circuits and aging of components inside the lamp will lead to additional energy consumption. Too low power may mean that the bulb is damaged or the power supply is insufficient, which will affect the fill light effect. By real-time monitoring of power data, potential faults of the fill light can be discovered in time and maintenance can be carried out in advance; temperature is the internal temperature or surface temperature of the fill light when it is working; continuous high temperature may cause the filament of the bulb to age faster, the performance of electronic components to deteriorate or even be damaged. By monitoring temperature data, it can be monitored that if the temperature exceeds the normal range, it may be necessary to check whether the heat dissipation device is working properly, or whether the working environment of the fill light is not conducive to heat dissipation, and timely measures can be taken to prevent the equipment from being damaged by overheating.

[0027] Preferably, the health status is used to comprehensively assess the overall operating status of the fill light. This may be based on multiple parameters (such as power, temperature, and flashing frequency) as well as the device's historical operating data. This intuitively reflects whether the fill light is operating normally. For example, if the health status displays "abnormal," it indicates a possible fault or potential problem with the fill light, requiring further analysis and repair. Trigger count refers to the number of times a traffic fill light device is triggered to illuminate within a certain period of time. In road traffic monitoring, fill lights typically illuminate in response to trigger signals from monitoring devices (such as cameras) to provide sufficient light for filming. Trigger counts reflect the fill light's usage frequency and workload. An abnormally high trigger count indicates increased traffic volume on that road section or a problem with the monitoring device's trigger settings. A low trigger count indicates a monitoring device failure or a problem with the fill light's trigger mechanism. By analyzing trigger count data, fill light usage strategies can be optimized, trigger parameters can be adjusted appropriately, and the device's service life can be extended. By collecting real-time operating data from fill light devices, potential problems can be promptly identified and resolved, thereby improving the efficiency, reliability, and stability of traffic fill light device operation and maintenance management.

[0028] Furthermore, step S100 also includes step S110, deploying a LoRa wireless communication module on the road traffic monitoring fill light device; step S120, collecting real-time parameters of the target traffic fill light device at fixed intervals through the LoRa wireless communication module to determine the device cycle data group; step S130, classifying and cleaning the device cycle data group according to data type to generate a standardized data set; step S140, encapsulating the standardized data set into a LoRa protocol frame through the LoRa wireless communication module to determine the fill light operation data set.

[0029] Preferably, a LoRa wireless communication module is deployed on the road traffic monitoring fill light device, that is, the module is integrated into the traffic fill light device, so that it has wireless communication capabilities and can exchange data with other devices (such as gateways, servers, etc.); then the LoRa wireless communication module is used to collect the real-time parameters of the target traffic fill light device at fixed intervals. Specifically, fixed interval collection refers to setting a time interval, for example, every 5 minutes, 10 minutes, etc. The LoRa wireless communication module collects the real-time parameters of the target traffic fill light device according to the set time interval. The real-time parameters include but are not limited to the power, temperature, health status (such as whether it is working normally, whether there are any faults, etc.), number of triggers, etc. of the fill light, reflecting the operating status and performance of the fill light; all real-time parameters in each collection cycle are combined into a data set, that is, a device cycle data group. For example, collection is performed once every 10 minutes, and each time parameters such as power, temperature, and number of triggers are collected, it is a device cycle data group.

[0030] Preferably, the data in the device cycle data group are classified according to the nature and type of the collected data, for example, power data is classified into one category, temperature data is classified into one category, trigger number data is classified into one category, etc., and then the classified data are cleaned to remove noise data, error data, duplicate data, etc. For example, due to sensor failure or interference, some obviously unreasonable temperature values may be collected, and these data are cleaned. After the data cleaning is completed, all types of data are organized according to a unified format and standard to generate a standardized data set; LoRa communication has its own specific protocol format. In order to be able to accurately and efficiently communicate in the LoRa network, To reliably transmit standardized data sets, they need to be encapsulated according to the requirements of the LoRa protocol to form LoRa protocol frames. The encapsulation process includes adding information such as protocol headers and check bits to ensure the integrity and accuracy of the data during transmission. The data contained in the encapsulated LoRa protocol frame is the fill light operation data set, which can be sent to the designated receiving end (such as a gateway, server, etc.) through the LoRa wireless communication module for subsequent data analysis, anomaly monitoring, operation and maintenance management, etc. The entire process realizes the collection and processing of the operating parameters of the road traffic monitoring fill light equipment, thereby improving the accuracy and reliability of equipment operation and maintenance management.

[0031] Step S200: Perform dynamic analysis based on the fill light operation data set, perform abnormality determination according to the dynamic analysis result, and generate abnormality alarm information.

[0032] Preferably, a dynamic analysis is performed on the fill light operation data set, that is, the changes in the fill light operation data over time are studied. Specifically, the changing trends of various parameters over time are observed. For example, whether the fill light power shows a gradual upward or downward trend is analyzed. If the power continues to rise, it may mean that there is an internal fault in the fill light, such as component aging causing resistance changes, which in turn increases power consumption; the correlation between different parameters is studied. For example, there is usually a certain correlation between temperature and power. When the power increases, the temperature tends to increase. By analyzing this correlation, a more comprehensive understanding of the operating status of the fill light can be obtained. If it is found that the power increases but the temperature does not change accordingly, it may indicate that there is a problem with the heat dissipation system of the fill light; the current operating data is compared with historical data or preset standard data. For example, the current fill light temperature is compared with the average temperature of the same time period in the past. If the current temperature exceeds the normal range, it indicates that there is a problem.

[0033] Preferably, after completing the dynamic analysis, it is necessary to determine whether there is any abnormality in the fill light based on the analysis results. Specifically, a reasonable threshold range is set for each parameter. When the value of a parameter exceeds the threshold range, it is determined to be abnormal. For example, the normal power range of the fill light is set to 50-100 watts. If the real-time monitored power is greater than 100 watts or less than 50 watts, the power parameter is considered abnormal. The judgment is made based on the change pattern of the data. For example, the number of triggering times of the fill light is usually less during the day and more at night. If abnormally frequent triggering occurs during the day, it can be determined to be abnormal even if the number of triggering times does not exceed the threshold. If it is determined that the fill light is abnormal, a corresponding abnormal alarm message is generated to promptly notify the operation and maintenance personnel for processing. The abnormal alarm message should include a detailed description of the abnormal situation, such as the time when the abnormality occurred, the name of the abnormal parameter (such as power, temperature, etc.), the specific abnormal value, and the difference from the normal range. In this way, abnormal situations of the traffic fill light equipment can be discovered in a timely manner and corresponding measures can be taken to deal with them, thereby ensuring the normal operation of the traffic monitoring equipment.

[0034] Furthermore, step S200 also includes step S210, sending the fill light operation data set to the operation and maintenance management platform for data classification and storage through a dynamic channel allocation mechanism, and determining multiple operation storage data information; step S220, retrieving historical operation data for training, and constructing a random forest model; step S230, dividing the multiple operation storage data information through the random forest model, and determining multiple fault status data; step S240, performing cluster analysis on the target traffic fill light equipment under different environmental scenarios, and setting an adaptive threshold; step S250, judging the multiple fault status data according to the adaptive threshold, generating a composite judgment rule, and performing real-time judgment update according to the composite judgment rule to obtain the dynamic analysis result.

[0035] Preferably, in wireless communications, channel resources are limited. A dynamic channel allocation mechanism can dynamically select appropriate communication channels for fill-light devices based on factors such as current network conditions, signal strength, and interference, thereby avoiding channel congestion and improving data transmission reliability and efficiency. For example, when a channel experiences significant interference, the system automatically switches to a channel with less interference for data transmission. After the fill-light operation data set is sent to the operation and maintenance management platform, the data is categorized and stored according to dimensions such as data type, time, and device number. For example, power data, temperature data, and trigger count data are stored in separate database tables and sorted chronologically. Through data classification and storage, each data category forms an independent data set, thereby forming multiple operational storage data information. For example, the stored information for power data includes the power value, acquisition time, and the corresponding fill-light device number.

[0036] Preferably, the historical operating data of the fill light device is retrieved, including normal operating data and data when a fault occurs, and a random forest model is constructed. By training the historical operating data, the relationship between the monitoring parameters and the operating status of the fill light device is learned, so that the operating status of the fill light device is predicted based on the collected real-time operating data, wherein the random forest includes multiple decision trees and the prediction results are integrated; the multiple decision trees of the random forest model are used to analyze and judge the multiple operating stored data information, specifically, the operating data of the fill light device is divided into different categories, including normal operating status and various fault statuses. For example, based on the combination of parameters such as power and temperature, it is judged whether the fill light device has fault status such as bulb damage, power failure, etc., thereby obtaining fault status data, which includes various parameter information when the fault occurs.

[0037] Preferably, cluster analysis is performed on target traffic light devices in different environmental scenarios (such as daytime, nighttime, sunny days, rainy days, etc.). Specifically, target traffic fill light devices are divided into different categories based on the similarity of the data. For example, fill light devices that operate during the day are classified into one category, and fill light devices that operate at night are classified into another category. According to the cluster analysis results, different thresholds (such as power thresholds and temperature thresholds) are set for each category, and adaptive adjustments can be made according to changes in environmental scenarios. For example, during the day, due to the strong ambient light, the power threshold of the fill light may be set lower, while at night, due to the weak ambient light, the power threshold of the fill light may be set lower. , the power threshold may be set higher; finally, the fault status data is compared and judged with the adaptive threshold, and multiple parameters and conditions are comprehensively considered to generate a composite judgment rule. Then, during the operation of the fill light equipment, the new operation data is continuously compared with the composite judgment rule, and the judgment result is updated in real time. If it is found that the new data meets the fault judgment conditions, an alarm information is issued in time. If the data returns to normal, it is updated to the normal state; through real-time judgment and update, the dynamic analysis results of the operation status of the fill light equipment are finally obtained, which helps operation and maintenance personnel to promptly discover equipment faults and abnormal conditions and take corresponding measures to deal with them.

[0038] Furthermore, step S210 also includes step S211, monitoring the channel of the LoRa wireless communication module to obtain a signal quality index; step S212, setting a signal expectation threshold, and when the signal quality index is lower than the signal expectation threshold, switching the channel of the LoRa wireless communication module to a backup channel to obtain a channel switching record; step S213, dynamically adjusting the data sending interval of the fill light operation data set according to the channel switching record to obtain a signal status log; step S214, activating the dynamic channel allocation mechanism according to the signal status log to synchronize the fill light operation data set to the operation and maintenance management platform.

[0039] Preferably, a detection device (such as a spectrum analyzer) is used to continuously monitor the channel of the LoRa wireless communication module to obtain various interferences that the channel may be subject to in a complex communication environment, such as signal interference from other wireless devices, electromagnetic interference in the natural environment, etc. Through monitoring, multiple indicators reflecting the channel signal quality can be obtained, such as the received signal strength indicator (RSSI), signal-to-noise ratio (SNR), etc. RSSI indicates the strength of the received signal. A larger value usually indicates a stronger signal. SNR reflects the ratio of signal strength to noise strength. A higher ratio indicates a clearer signal and less noise interference. According to actual communication needs and historical experience, the expected threshold of signal quality is pre-set to ensure L The oRa wireless communication module can stably and reliably transmit the fill light operation data set. For example, the expected RSSI threshold can be set to -100dBm, and the expected SNR threshold can be set to 5dB. When the monitored signal quality index is lower than the set expected threshold, it means that the communication quality of the current channel is poor, which may cause data transmission errors or loss. The channel of the LoRa wireless communication module is automatically switched to the backup channel. The backup channel is pre-planned and has relatively good signal quality. It can provide a more stable environment for data transmission. When switching channels, the relevant information of the switching is recorded, including the switching time, the original channel number, the number of the backup channel switched to, etc., to form a channel switching record.

[0040] Preferably, the channel switching record reflects the stability and communication quality of the channel. According to the channel switching record, the data sending interval of the fill light operation data set is dynamically adjusted. Specifically, if the channel switches frequently, it means that the current communication environment is poor. In order to reduce the probability of data errors during transmission, the data sending interval can be appropriately increased and the frequency of data transmission can be reduced. On the contrary, if the channel is relatively stable and the signal quality is good, the data sending interval can be appropriately reduced to improve the real-time performance of data transmission. In the process of adjusting the data sending interval, the relevant information of each adjustment is recorded, such as the time of adjustment, the data sending interval before and after adjustment, the signal quality index at that time, etc., to form a signal status log to fully reflect the LoRa wireless The signal status and data transmission status of the communication module; finally, the dynamic channel allocation mechanism takes into account multiple factors such as the signal quality, idle status, interference status of the channel according to the signal status log (including the current channel status and communication requirements), and automatically selects the most suitable channel for the LoRa wireless communication module for data transmission; according to the information recorded in the signal status log, when it is found that the current channel is not suitable for data transmission, the dynamic channel allocation mechanism is activated to re-allocate a better channel for the LoRa wireless communication module, and use this newly allocated channel to synchronize the fill light operation data set to the operation and maintenance management platform to ensure that the operation and maintenance management platform can obtain the fill light operation data in a timely and accurate manner, thereby improving the overall operation and maintenance management efficiency of the traffic fill light equipment.

[0041] Furthermore, step S220 also includes step S221, retrieving the operating data of the target traffic supplementary lighting equipment under different meteorological conditions during a historical period to construct a multidimensional training data set; step S222, performing time series analysis on the multidimensional training data set, and extracting periodic features based on the time series analysis results; step S223, cross-validating the multidimensional training data set with actual equipment fault records according to the periodic features, adjusting the model hyperparameters based on the validation results, and obtaining the random forest model.

[0042] Preferably, the operating data of the target traffic fill light device in the past period of time is retrieved from the relevant database, including not only the operating parameters of the device itself, such as the brightness, current, voltage, etc. of the fill light, but also different meteorological conditions information, such as temperature, humidity, light intensity, whether it is raining, whether there is fog, etc. The collected data is sorted and constructed into a multidimensional training data set. Specifically, each data record contains information of multiple dimensions such as the device operating parameters and the corresponding meteorological conditions. For example, a record can be represented as a vector form such as [brightness, current, voltage, temperature, humidity, light intensity, weather conditions (rainy / sunny, etc.)], and multiple such records constitute a multidimensional training data set.

[0043] Preferably, a time series analysis is performed on the multidimensional training dataset. Specifically, the temporal variations of various operating data of the target traffic supplemental lighting equipment under different meteorological conditions are studied. For example, time series analysis techniques such as moving average, exponential smoothing, autoregressive model (AR), autoregressive moving average model (ARMA), and seasonal decomposition are used to conduct an in-depth analysis of the temporal variation patterns of each variable in the dataset (e.g., operating parameters such as the power, temperature, and on / off state of the supplemental lighting, as well as meteorological parameters such as temperature, humidity, and light intensity). Periodic features are then extracted based on the analysis results. Traffic supplemental lighting equipment may exhibit various periodicities, such as daily cycles (different operating states during the day and night), weekly cycles (differences in usage between weekdays and weekends), and seasonal cycles (the impact of seasonal meteorological changes on equipment operation). For example, analysis revealed that the power of the supplemental lighting equipment increases significantly in the evening (peak traffic period) and then gradually decreases late at night, or that the equipment failure rate is relatively high during the hot summer months, exhibiting a seasonal cyclical pattern.

[0044] Preferably, the multidimensional training data set is reasonably divided according to the extracted periodic features. For example, the data set is divided into four subsets of spring, summer, autumn and winter according to the season, or divided into two subsets of day and night according to the time period of each day, etc., and then the divided data set subsets are compared and verified with the actual fault records of the equipment, that is, the relationship between the operating data of the equipment in the period and the actual faults that occurred is checked. For example, in the summer data set subset, the operating parameters and meteorological conditions when the equipment fails are statistically analyzed to see whether there are certain specific patterns or regularities. Through cross-validation, the prediction ability of the model for equipment failures under different periodic conditions is evaluated; according to the results of cross-validation, such as If it is found that the model's prediction results under certain periodic conditions deviate significantly from the actual fault records, it is necessary to adjust the hyperparameters (such as the number of decision trees, the maximum depth of the tree, the minimum number of sample splits, etc.). For example, if the model has a low accuracy rate when predicting equipment failures in the summer, you may try increasing the number of decision trees or adjusting the maximum depth of the tree to improve the model's ability to fit complex data patterns. By continuously adjusting the random forest hyperparameters and performing cross-validation, the model is gradually optimized until the model can achieve good prediction performance under different periodic conditions. Finally, a random forest model is obtained, which can use the equipment's operating data and periodic characteristics to more accurately predict possible equipment failures. For example, Table 1 gives an example of adjusting the hyperparameters of the random forest model:

[0045]

[0046] Furthermore, step S200 also includes step S260, constructing a dynamic topology map according to the physical deployment location of the target traffic fill lighting equipment; step S270, traversing the dynamic topology map according to the dynamic analysis results to perform layout identification and determine multiple node identification results; step S280, performing abnormal judgment extraction based on the multiple node identification results, determining multiple abnormal device nodes, and correlating and analyzing the multiple abnormal device nodes with historical alarm records to generate the abnormal alarm information.

[0047] Preferably, accurate physical deployment location information of the target traffic fill light equipment is obtained through geographic information system (GIS) technology, equipment installation records or on-site surveys. For example, each traffic fill light device has its own specific latitude and longitude coordinates, as well as the specific location where it is installed on the road (such as an intersection, the middle of a road section, etc.). Then, each traffic fill light device is used as a node, and the communication connection or physical proximity relationship between the devices is used as an edge to construct a dynamic topology map reflecting the spatial relationship and connection status between the devices. For example, if a communication module of a device fails and the connection with other devices is interrupted, the dynamic topology map will be updated accordingly to display this change; the nodes in the dynamic topology map (i.e., traffic fill light devices) are traversed one by one, and the layout of each device in the topology map is identified according to the dynamic analysis results corresponding to each device. For example, if the dynamic analysis result of a device shows normal operation, its node may be identified as green; if it shows an abnormality, it is identified as red; for devices with potential faults, they are identified as yellow, so that the operating status of each device can be intuitively seen on the topology map, and multiple node identification results are determined.

[0048] Preferably, based on the node identification results, those device nodes (i.e., abnormal device nodes) that are identified as abnormal (such as red marks) are extracted from the dynamic topology map, and then the abnormal device nodes are associated with historical alarm records (containing detailed information when the equipment failed or abnormal in the past, such as the fault type, occurrence time, treatment measures, etc.) to find out whether these abnormal device nodes have also experienced similar abnormal situations in history, or whether they are associated with failures of other devices. For example, if a device has the same type of abnormality multiple times, or multiple adjacent devices have abnormalities at the same time, there may be some common causes, such as power supply problems or communication interference in a certain area; based on the results of the correlation analysis, detailed abnormal alarm information is generated, which not only includes the basic information of the abnormal device node (such as device number, location, etc.), but also explains the type of abnormality, possible causes (obtained through correlation analysis) and correlation with historical alarm records, etc., so as to provide comprehensive and accurate information for operation and maintenance personnel and improve the efficiency of operation and maintenance management.

[0049] Step S300: Transmit the abnormal alarm information to the operation and maintenance management platform to trigger a remote maintenance instruction.

[0050] Preferably, the generated abnormal alarm information is sent using the LoRa wireless communication module, and the information is ensured to be reliably transmitted to the operation and maintenance management platform under different environments and distances. For example, for traffic fill light equipment distributed in different areas of the city, the LoRa wireless communication module can rely on its long-distance communication capability to transmit the alarm information to the operation and maintenance management platform located in the city monitoring center. The operation and maintenance management platform is used to centrally manage and monitor traffic fill light equipment, and has the function of receiving and processing various equipment information. When the abnormal alarm information is transmitted, the platform will receive, parse and store it. After receiving the abnormal alarm information, the operation and maintenance management platform determines whether it is necessary to trigger a remote maintenance instruction based on preset rules and strategies. The rules may include the severity of the abnormality, the importance of the equipment, etc. For example, if the abnormal alarm information shows that the equipment has a serious fault, a remote maintenance instruction may be triggered immediately; for some minor abnormalities, further monitoring and analysis may be carried out before deciding whether to trigger the instruction; remote maintenance instructions refer to operation and maintenance operation instructions sent to the abnormal equipment through the network, which are used to remotely troubleshoot, adjust parameters or repair the system of the equipment. For example, if there is a problem with the parameter setting of the equipment, the remote maintenance instruction may be to modify the relevant parameters of the equipment; if the communication module of the equipment fails, the instruction may be to try to restart the communication module or reconfigure the communication parameters; after receiving the remote maintenance instruction, the abnormal equipment will perform the corresponding operation according to the requirements of the instruction. The control system inside the equipment will parse the instruction content and execute the corresponding action to realize remote maintenance of the equipment, thereby achieving rapid response and remote fault handling of the traffic fill light equipment, and improving the maintenance efficiency and reliability of the equipment.

[0051] Step S400: Send a control parameter adjustment instruction to the target traffic fill light device through the LoRa wireless communication module.

[0052] Step S400 further includes step S410, analyzing the historical alarm records and historical maintenance records to extract high-frequency fault modes and fault resolution strategies; step S420, verifying the effectiveness of the fault resolution strategies through simulation tests according to the high-frequency fault modes to generate strategy priority scores; step S430, integrating the fault resolution strategies whose strategy priority scores are higher than the preset scores to construct a maintenance strategy library; step S440, parsing based on the abnormal alarm information to determine the abnormality type, matching the abnormality type with the maintenance strategy library, and determining the control parameter adjustment instructions according to the matching results.

[0053] Preferably, historical alarm records and historical maintenance records generated by traffic fill light equipment are collected, which include various fault information that occurred during the past operation of the equipment, as well as maintenance measures taken for these faults. Data mining and statistical analysis are used to conduct in-depth analysis on the large amount of historical records collected to find out the fault modes that occur more frequently. For example, it is found that frequent faults such as bulb damage and power module overheating of the fill light are more common, that is, they belong to high-frequency fault modes. At the same time, the solution strategies adopted for different faults are extracted from the historical maintenance records. For example, when encountering a bulb damage fault, the strategy adopted is to replace the bulb; for the problem of power module overheating, the strategy adopted is to add a heat dissipation device or adjust the power parameters.

[0054] Preferably, for the extracted high-frequency fault modes, a corresponding simulation environment is constructed to simulate the conditions and scenarios of fault occurrence, and then different fault resolution strategies are applied respectively to observe the operating status of the equipment and the fault resolution effect. Specifically, through simulation testing, the effectiveness of each fault resolution strategy in resolving the corresponding fault is evaluated. For example, it is determined whether the strategy of replacing a light bulb can truly solve the problem of light bulb damage, whether the strategy of adjusting power parameters can effectively reduce the temperature of the power module, etc. According to the results of the simulation test, a priority score is generated for each fault resolution strategy based on the success rate of the strategy, the time and cost required to resolve the fault, etc. For example, if a strategy can resolve the fault quickly, at low cost and efficiently, then its priority score will be higher; then a preset score is set as the screening criterion, and the fault resolution strategies with a strategy priority score higher than the preset score are screened out and integrated into a maintenance strategy library, that is, a database that centrally stores and manages effective fault resolution strategies.

[0055] Preferably, the currently received abnormal alarm information is analyzed in detail, and the specific type of abnormality is determined based on the equipment operating parameters, fault characteristics and other information contained therein. For example, by analyzing the power abnormality, high temperature and other data in the alarm information, it is determined whether it is a power supply failure or a bulb failure, and then the determined abnormality type is matched with the fault resolution strategy in the maintenance strategy library, and the most effective resolution strategy corresponding to the abnormality type in the maintenance strategy library is found; then, based on the matched fault resolution strategy, the control parameter adjustment instruction that needs to be issued to the target traffic fill light device is determined, which may include adjusting the corresponding power value or switching the working mode. For example, if the matched strategy is to adjust the power supply parameters to solve the power supply failure, then the control parameter adjustment instruction may be to adjust the output voltage or current of the power supply to a specified value; finally, the determined control parameter adjustment instruction is sent to the target traffic fill light device through the LoRa wireless communication module. After receiving the instruction, the device makes corresponding parameter adjustments to solve the abnormal problem of the device, thereby improving the overall operation and maintenance management efficiency of the traffic fill light device.

[0056] Step S500: Execute real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction combined with the control parameter adjustment instruction.

[0057] Preferably, when an abnormality occurs in the traffic fill light device, remote maintenance instructions (device ID, abnormality type and environmental parameters in the abnormality alarm information) and control parameter adjustment instructions (power adjustment value of the device, working mode switching instruction and priority score of effectiveness) are comprehensively utilized to perform real-time operation and maintenance management optimization of the target traffic fill light device to restore the normal operation of the device and improve its performance. Specifically, the execution order and method of the instructions are reasonably arranged according to the actual situation of the device and the characteristics of the abnormal problem. For example, the device diagnosis operation in the remote maintenance instruction is first executed to determine the specific fault point of the device, and then the corresponding control parameter adjustment instruction is executed according to the fault type. The integrated instruction is sent to the target traffic fill light device in real time through communication means such as the LoRa wireless communication module. After receiving the instruction, the device immediately operates according to the requirements of the instruction. By executing the remote maintenance instruction and the control parameter adjustment instruction, the fault of the device is repaired and it is restored to normal operation, achieving efficient and accurate maintenance of the device. At the same time, the operating parameters of the device are optimized and adjusted to improve the performance and stability of the device, improve the reliability and operating efficiency of the device, and ensure the normal operation of the road traffic monitoring system.

[0058] Furthermore, step S500 also includes step S510, integrating the remote maintenance instruction and the control parameter adjustment instruction according to the abnormality type, and executing the integrated instruction to determine the execution status data; step S520, judging whether the fill light operation data set has recovered to the normal threshold range based on the execution status data, and triggering the optimization signal if the fill light operation data set has not recovered to the normal threshold range; step S530, adaptively optimizing the integrated instruction through the optimization signal, and generating a fill light device health report; step S540, performing operation and maintenance management on the target traffic fill light device according to the fill light device health report.

[0059] Preferably, when an abnormality occurs in a traffic fill light device, remote maintenance instructions (such as remote operation instructions such as restarting the device and updating software) and control parameter adjustment instructions (instructions for device operating parameters, such as adjusting brightness, power, and other parameters) are generated. These two types of instructions are integrated together according to the type of abnormality. For example, if the abnormality is abnormal brightness of the fill light, the control parameter adjustment instructions related to brightness adjustment and the remote maintenance instructions that may help solve the problem (such as instructions for restarting the relevant control module) are integrated. The integrated instructions are sent to the device for execution. During the execution process, the device will feedback various information, such as whether the instructions were received, the start time of execution, the status of key steps in the execution process, etc. This information forms execution status data. With the help of the execution status data, it is checked whether the various parameters in the fill light operation data set have returned to the normal threshold range. For example, under normal circumstances, the fill light power is between 50-80 watts. If the power parameter is still below 50 watts or above 80 watts after executing the integrated instructions, it means that the fill light operation data set has not returned to the normal threshold range. The normal threshold range is a pre-set parameter range used to measure whether the fill light is operating normally.

[0060] Preferably, if it is determined that the fill light operation data set has not returned to normal, an optimization signal is triggered to optimize the integrated instructions, that is, according to the execution status data, abnormal conditions of the fill light operation data set, etc., the execution order of the instructions, parameter settings, etc. are readjusted. For example, an attempt may be made to change the amplitude of the control parameter adjustment, or adjust the execution timing of certain operations in the remote maintenance instructions. Then, a comprehensive review of the current operating status of the fill light equipment is conducted, including the current operating parameters of the equipment, whether there are still potential risks, and which aspects have been improved after optimization, etc., and a fill light equipment health report is generated to present the health status of the equipment in detail; finally, the operation and maintenance personnel take corresponding operation and maintenance management measures according to the content of the fill light equipment health report to ensure the efficiency of operation and maintenance management and ensure the continuous and stable operation of the fill light equipment.

[0061] Furthermore, step S530 also includes step S531, dynamically adjusting the integration instruction based on the optimization signal to determine the equipment operation and maintenance optimization log; step S532, performing operation and maintenance analysis according to the equipment operation and maintenance optimization log and the fill light operation data set to generate a health score matrix; step S533, grading the target traffic fill light equipment based on the health score matrix to determine the fill light equipment health report.

[0062] Preferably, when an optimization signal is received indicating that the integrated instruction (including the remote maintenance instruction and the control parameter adjustment instruction) fails to restore the fill light operation data set to the normal threshold range, the integrated instruction is dynamically adjusted based on the historical fault data of the device, the specific manifestation of the current abnormality, the instruction execution effect fed back by the execution status data, etc. For example, if it is found that the control parameter adjustment instruction for adjusting the fill light power is not effective, the adjustment amplitude and direction of the power parameter may be recalculated and adjusted; if the restart operation in the remote maintenance instruction does not solve the communication problem, other remote operation instructions related to communication recovery may be tried, such as reconfiguring the communication protocol parameters; then a large amount of equipment operation and maintenance related data during the dynamic adjustment and re-execution process is recorded to form an equipment operation and maintenance optimization log, which may include but is not limited to alarm count (the number of times each traffic fill light device triggers an abnormal alarm within a specified time period), average response time calculation (the average value of the time interval from the device triggering the alarm to the start of executing the corresponding maintenance instruction), and maintenance success rate evaluation (the proportion of the number of times the device successfully restored to normal operating status to the total number of maintenance attempts).

[0063] Preferably, the data such as the number of alarms, average response time, and maintenance success rate in the equipment operation and maintenance optimization log are combined with the fill light operation data set for comprehensive analysis, that is, by comparing the data of different devices in different time periods, the relationship between the operating status of the equipment and the operation and maintenance effect is deeply understood, and based on the results of the operation and maintenance analysis, a health score matrix is generated for each traffic fill light device. The elements in the matrix may include scores for various key operating indicators and operation and maintenance indicators of the equipment. For example, for power parameters, corresponding scores are given according to the degree of deviation from the normal threshold; for the number of alarms, they are converted into scores according to certain rules, and the fewer the number of alarms, the higher the score; by comprehensively considering the indicator scores of multiple dimensions, a matrix that comprehensively reflects the health status of the equipment is formed.

[0064] Preferably, the target traffic fill light equipment is graded according to the generated health score matrix. Specifically, different health levels can be set, such as high, medium, low, or A, B, C, etc. The classification is based on the comprehensive score of the equipment in the health score matrix. For example, a device with a score of 80 points or more (out of 100 points) is classified as a high health level (A level), indicating that the equipment is in good operating condition and rarely has abnormalities; a device with a score between 60-80 points is classified as a medium health level (B level), indicating that the equipment has certain potential problems but is still operating normally; a device with a score below 60 points is classified as a low health level. (Grade C): This type of equipment may have many faults or unstable operation and requires special attention and maintenance; the generated fill light equipment health report contains the equipment classification information and a detailed health status analysis of each device, and is presented in a visual way. For example, charts (bar charts, line charts, pie charts, etc.) are used to intuitively display the number distribution of equipment at different health levels, statistical data of various operating indicators, etc. At the same time, the report is pushed to the operation and maintenance terminal, which is convenient for operation and maintenance personnel to view it anytime and anywhere, quickly understand the health status of the entire traffic fill light equipment system, take targeted operation and maintenance measures for equipment of different levels, and improve the overall operation and maintenance management efficiency.

[0065] In the above, refer to Figure 1 The operation and maintenance management method of traffic light supplement equipment based on LoRa transmission according to an embodiment of the present invention is described in detail. Figure 2 The present invention describes an operation and maintenance management platform for traffic supplementary lighting equipment based on LoRa transmission according to an embodiment of the present invention.

[0066] The LoRa transmission-based traffic light equipment operation and maintenance management platform according to the embodiment of the present invention is used to solve the technical problems in the prior art, such as the wide distribution of traffic light equipment, the difficulty of timely detection of faults during manual inspections, and the susceptibility of equipment to environmental interference, which in turn leads to inaccurate abnormal alarm information and poor operation and maintenance efficiency and reliability of traffic light equipment, thereby achieving the technical effect of improving equipment operation and maintenance efficiency and reliability. Figure 2 As shown, the traffic supplementary lighting equipment operation and maintenance management platform based on LoRa transmission includes: an operation data set acquisition unit 10, an abnormal alarm information generation unit 20, a remote maintenance instruction triggering unit 30, a control parameter adjustment instruction issuing unit 40, and an operation and maintenance management optimization unit 50.

[0067] An operation data set acquisition unit 10 is used to deploy a LoRa wireless communication module, and to collect data in real time from the target traffic fill light device through the LoRa wireless communication module to obtain a fill light operation data set; an abnormal alarm information generation unit 20 is used to perform dynamic analysis based on the fill light operation data set, make abnormality judgments based on the dynamic analysis results, and generate abnormal alarm information; a remote maintenance instruction triggering unit 30 is used to transmit the abnormal alarm information to the operation and maintenance management platform to trigger a remote maintenance instruction; a control parameter adjustment instruction issuing unit 40 is used to issue a control parameter adjustment instruction to the target traffic fill light device through the LoRa wireless communication module; an operation and maintenance management optimization unit 50 is used to perform real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction combined with the control parameter adjustment instruction.

[0068] The specific configuration of the operation data set acquisition unit 10 will be described in detail below. The operation data set acquisition unit 10 further includes: deploying a LoRa wireless communication module on the road traffic monitoring fill light device; using the LoRa wireless communication module to collect real-time parameters of the target traffic fill light device at regular intervals to determine a device cycle data set; classifying and cleaning the device cycle data set according to data type to generate a standardized data set; and encapsulating the standardized data set into LoRa protocol frames using the LoRa wireless communication module to determine the fill light operation data set.

[0069] The specific configuration of the abnormal alarm information generation unit 20 will be described in detail below. The abnormal alarm information generation unit 20 further includes: sending the fill light operation data set to the operation and maintenance management platform for data classification and storage through a dynamic channel allocation mechanism, determining multiple pieces of operation and storage data; retrieving historical operation data for training and constructing a random forest model; dividing the multiple pieces of operation and storage data using the random forest model to determine multiple pieces of fault status data; performing cluster analysis on the target traffic fill light equipment in different environmental scenarios and setting adaptive thresholds; judging the multiple pieces of fault status data according to the adaptive thresholds to generate a composite judgment rule, and performing real-time judgment updates according to the composite judgment rule to obtain the dynamic analysis results.

[0070] The specific configuration of the abnormal alarm information generation unit 20 will be described in detail below. The abnormal alarm information generation unit 20 further includes: monitoring the channel of the LoRa wireless communication module to obtain a signal quality indicator; setting a signal expectation threshold, and when the signal quality indicator is lower than the signal expectation threshold, switching the channel of the LoRa wireless communication module to a backup channel and obtaining a channel switching record; dynamically adjusting the data transmission interval of the fill light operation data set based on the channel switching record to obtain a signal status log; and activating a dynamic channel allocation mechanism according to the signal status log to synchronize the fill light operation data set to the operation and maintenance management platform.

[0071] The specific configuration of abnormal alarm information generation unit 20 will be described in detail below. Abnormal alarm information generation unit 20 further includes: retrieving historical operating data of target traffic supplementary lighting equipment under different meteorological conditions to construct a multidimensional training dataset; performing time series analysis on the multidimensional training dataset and extracting periodic features based on the time series analysis results; cross-validating the multidimensional training dataset with actual equipment failure records based on the periodic features, and adjusting model hyperparameters based on the validation results to obtain the random forest model.

[0072] The specific configuration of the abnormality alarm information generation unit 20 will be described in detail below. The abnormality alarm information generation unit 20 further includes: constructing a dynamic topology map based on the physical deployment location of the target traffic supplementary lighting device; traversing the dynamic topology map to identify the layout according to the dynamic analysis results, and determining multiple node identification results; performing abnormality determination and extraction based on the multiple node identification results, identifying multiple abnormal device nodes, and correlating and analyzing the multiple abnormal device nodes with historical alarm records to generate the abnormality alarm information.

[0073] The specific configuration of the control parameter adjustment instruction issuing unit 40 will be described in detail below. The control parameter adjustment instruction issuing unit 40 further includes: analyzing the historical alarm records and historical maintenance records to extract high-frequency fault modes and fault resolution strategies; verifying the effectiveness of the fault resolution strategies through simulation tests based on the high-frequency fault modes to generate a strategy priority score; integrating the fault resolution strategies with strategy priority scores higher than a preset score to construct a maintenance strategy library; parsing the abnormal alarm information to determine the abnormality type, matching the abnormality type with the maintenance strategy library, and determining the control parameter adjustment instruction based on the matching result.

[0074] The specific configuration of the operation and maintenance management optimization unit 50 will be described in detail below. The operation and maintenance management optimization unit 50 further includes: integrating the remote maintenance instruction and the control parameter adjustment instruction according to the abnormality type, executing the integrated instruction to determine execution status data; determining whether the fill light operation data set has recovered to a normal threshold range based on the execution status data, and triggering an optimization signal if the fill light operation data set has not recovered to the normal threshold range; adaptively optimizing the integrated instruction using the optimization signal to generate a fill light device health report; and performing operation and maintenance management on the target traffic fill light device according to the fill light device health report.

[0075] The specific configuration of the operation and maintenance management optimization unit 50 will be described in detail below. The operation and maintenance management optimization unit 50 further includes: dynamically adjusting the integration instruction based on the optimization signal to determine the device operation and maintenance optimization log; performing operation and maintenance analysis based on the device operation and maintenance optimization log and the fill light operation data set to generate a health score matrix; and grading the target traffic fill light equipment based on the health score matrix to determine the fill light equipment health report.

[0076] The LoRa transmission-based traffic supplementary lighting equipment operation and maintenance management platform provided in the embodiment of the present invention can execute the LoRa transmission-based traffic supplementary lighting equipment operation and maintenance management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0077] Although this application makes various references to certain modules in the platform according to the embodiments of this application, any number of different modules can be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0078] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission is characterized in that: The method comprises: Deploy the LoRa wireless communication module to collect data on the target traffic fill light equipment in real time and obtain the fill light operation data set; Performing dynamic analysis based on the fill light operation data set, determining abnormalities based on the dynamic analysis results, and generating abnormality alarm information; Transmitting the abnormal alarm information to the operation and maintenance management platform to trigger remote maintenance instructions; Send control parameter adjustment instructions to the target traffic light device through the LoRa wireless communication module; Performing real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction combined with the control parameter adjustment instruction; Performing dynamic analysis based on the fill light operation data set, the method includes: Sending the fill light operation data set to the operation and maintenance management platform through a dynamic channel allocation mechanism for data classification and storage, and determining multiple operation and storage data information; Retrieve historical operation data for training and build a random forest model; Dividing the plurality of running stored data information by the random forest model to determine a plurality of fault status data; Conduct cluster analysis on target traffic fill lighting equipment in different environmental scenarios and set adaptive thresholds; Determine the plurality of fault status data according to the adaptive threshold value, generate a composite determination rule, and perform real-time determination and update according to the composite determination rule to obtain the dynamic analysis result; Based on the dynamic analysis results, abnormality determination is performed and abnormality alarm information is generated. The method includes: Build a dynamic topology map based on the physical deployment location of the target traffic fill lighting equipment; Traversing the dynamic topology graph according to the dynamic analysis result to perform layout identification and determine multiple node identification results; Anomaly determination and extraction are performed based on the multiple node identification results to determine multiple abnormal device nodes, and the multiple abnormal device nodes are associated with historical alarm records for analysis to generate the abnormal alarm information.

2. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 1, characterized in that: Deploy the LoRa wireless communication module to collect data on the target traffic fill light device in real time through the LoRa wireless communication module to obtain the fill light operation data set. The method includes: Deploy LoRa wireless communication modules on road traffic monitoring supplementary lighting equipment; The LoRa wireless communication module collects the real-time parameters of the target traffic light device at fixed intervals to determine the device cycle data group; Classifying and cleaning the equipment cycle data group according to data type to generate a standardized data set; The standardized data set is encapsulated into a LoRa protocol frame through a LoRa wireless communication module to determine the fill light operation data set.

3. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 1, characterized in that: The method of sending the fill light operation data set to the operation and maintenance management platform through a dynamic channel allocation mechanism includes: Monitor the channel of the LoRa wireless communication module and obtain signal quality indicators; Setting a signal expectation threshold, when the signal quality index is lower than the signal expectation threshold, switching the channel of the LoRa wireless communication module to a backup channel, and obtaining a channel switching record; Dynamically adjust the data transmission interval of the fill light operation data set according to the channel switching record to obtain a signal status log; According to the signal status log, a dynamic channel allocation mechanism is activated to synchronize the fill light operation data set to the operation and maintenance management platform.

4. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 1, characterized in that: Retrieve historical operation data for training and build a random forest model. The methods include: Retrieve the operating data of target traffic supplementary lighting equipment under different meteorological conditions during the historical period to construct a multi-dimensional training data set; Performing time series analysis on the multidimensional training data set and extracting periodic features according to the time series analysis results; The multidimensional training data set is cross-validated with actual equipment failure records according to the periodic characteristics, and the model hyperparameters are adjusted according to the validation results to obtain the random forest model.

5. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 1, characterized in that: The method of sending control parameter adjustment instructions to the target traffic fill light device through the LoRa wireless communication module includes: Analyze the historical alarm records and historical maintenance records to extract high-frequency failure modes and failure resolution strategies; Verify the effectiveness of the fault resolution strategy through simulation testing according to the high-frequency fault mode and generate a strategy priority score; Integrate the fault resolution strategies with strategy priority scores higher than a preset score to build a maintenance strategy library; The abnormality alarm information is parsed to determine the abnormality type, the abnormality type is matched with the maintenance strategy library, and the control parameter adjustment instruction is determined according to the matching result.

6. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 5, characterized in that: The method includes performing real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction combined with the control parameter adjustment instruction, comprising: Integrating the remote maintenance instruction and the control parameter adjustment instruction according to the abnormality type, and executing the integration instruction to determine execution status data; determining whether the fill light operation data set is restored to a normal threshold range based on the execution status data, and triggering an optimization signal if the fill light operation data set is not restored to the normal threshold range; Adaptively optimizing the integrated instruction using the optimization signal to generate a health report for the fill light device; Perform operation and maintenance management on the target traffic fill light equipment according to the fill light equipment health report.

7. The operation and maintenance management method of traffic supplementary lighting equipment based on LoRa transmission according to claim 6, characterized in that: Adaptively optimizing the integrated instruction using the optimization signal to generate a health report of the fill light device includes: Dynamically adjusting the integration instruction based on the optimization signal to determine a device operation and maintenance optimization log; Performing operation and maintenance analysis based on the equipment operation and maintenance optimization log and the fill light operation data set to generate a health score matrix; The target traffic fill light equipment is graded based on the health score matrix to determine the health report of the fill light equipment.

8. Traffic supplementary lighting equipment operation and maintenance management platform based on LoRa transmission, characterized by: The platform is used to implement the LoRa transmission-based traffic supplementary lighting equipment operation and maintenance management method according to any one of claims 1 to 7, and the platform includes: The operation data set acquisition unit is used to deploy the LoRa wireless communication module to collect data in real time from the target traffic fill light equipment and obtain the fill light operation data set; an abnormality alarm information generating unit, configured to perform dynamic analysis based on the fill light operation data set, perform abnormality determination based on the dynamic analysis result, and generate abnormality alarm information; A remote maintenance instruction triggering unit, configured to transmit the abnormal alarm information to the operation and maintenance management platform to trigger a remote maintenance instruction; A control parameter adjustment instruction sending unit is used to send a control parameter adjustment instruction to a target traffic fill light device through a LoRa wireless communication module; The operation and maintenance management optimization unit is used to perform real-time operation and maintenance management optimization on the target traffic fill light device according to the remote maintenance instruction combined with the control parameter adjustment instruction.

Images