A street lamp brightness self-adaptive adjusting system based on light sensing feedback

Abstract

The application belongs to the technical field of adaptive adjustment, and discloses a street lamp brightness adaptive adjustment system based on light feedback; the system comprises an adaptive street lamp brightness adjustment module, a brightness adjustment knowledge deep learning module, a real-time health degree evaluation early warning module and a preventive maintenance brightness adjustment scheme optimization module, obtains a street lamp brightness adjustment instruction report, stores multiple version models, supports processing of an optimization request of the adaptive street lamp brightness adjustment module, and processes the models in multiple ways to obtain a health degree evaluation early warning report, corrects a life prediction model based on the health degree evaluation early warning report, establishes a target function to optimize a brightness adjustment scheme, and obtains a strategy optimization report; in general, the application has the remarkable advantages of strong effectiveness of basic data use, great adaptive optimization effect of street lamp brightness and good applicable effect of management strategy.

Description

Technical Field

[0001] This invention relates to the field of adaptive adjustment technology, and more specifically, to a street light brightness adaptive adjustment system based on light-sensing feedback. Background Technology

[0002] The adaptive brightness adjustment method for streetlights is a core technology for achieving energy conservation and intelligent control in road lighting. By matching environmental changes with lighting demands, it can reduce public lighting energy consumption and improve traffic safety, demonstrating significant application value. The core of this method is a closed loop of "environmental perception - data processing - brightness control," where multi-source data fusion is the key link connecting perception and control, directly determining the accuracy and reliability of the adjustment method and serving as its core performance indicator.

[0003] However, traditional adaptive regulation systems suffer from several shortcomings during use. First, they rely on multiple data sources as their foundation, but these sources are independent and lack temporal and spatial alignment, making it difficult to obtain a complete data view of a single streetlight under full brightness regulation. Second, traditional systems often use theoretically derived fixed values ​​for streetlight brightness regulation, leading to significant fluctuations in actual brightness adjustment and hindering the high consistency required for high-performance streetlights. Third, traditional systems often use fixed time periods or simple mileage triggers for brightness regulation line maintenance and streetlight replacement, lacking consideration for actual brightness regulation quality and equipment health, potentially resulting in resource waste and unexpected downtime. Therefore, effectively addressing the issues of independent multi-source information, fixed streetlight brightness regulation, and rigid management methods in traditional systems has become a key challenge for current adaptive regulation systems.

[0004] In view of this, the present invention proposes a street light brightness adaptive adjustment system based on light-sensing feedback to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution, including:

[0006] The multi-source heterogeneous data acquisition and fusion module is used to acquire multi-source data in real time based on multiple data sources and perform preprocessing to obtain the original preprocessed dataset;

[0007] Furthermore, the steps for real-time acquisition and preprocessing of multi-source data based on multiple data sources include:

[0008] S1.1: Real-time acquisition of multi-source data based on multiple data sources to obtain the raw dataset. The multiple data sources include visual inspection system, MES system, IoT sensor and RFID reader;

[0009] S1.2: Based on the system's internal time, and according to the collection data stamps of all data items in the original dataset, time alignment processing is performed to obtain a time-aligned dataset;

[0010] S1.3: Perform data validation based on the time-aligned dataset, and remove data items that fail the validation to obtain the cleaned dataset;

[0011] S1.4: Arrange the data items in the data cleaning dataset according to the time order to obtain the original preprocessed dataset;

[0012] S1.5: Store the original preprocessed dataset in the database and output it to the digital twin construction module of the brightness adjustment process;

[0013] The brightness adjustment process digital twin construction module is used to update the digital twin based on the original preprocessed dataset, perform real-time calculation of multiple indicators, and obtain a twin status report.

[0014] Furthermore, the steps of updating the digital twin based on the original preprocessed dataset and performing real-time calculation of multiple metrics include:

[0015] S2.1: Create an initial digital twin template based on the original preprocessed dataset. The initial digital twin template includes the street light device ID, street light device model, tolerance design range, and standard street light brightness.

[0016] S2.2: Based on the initial digital twin template, and by obtaining the latest original preprocessed dataset in real time from the database, the initial digital twin template is updated according to the event types of the original preprocessed dataset to obtain the digital twin model.

[0017] S2.3: Calculate multiple indicator values ​​of street light equipment in real time based on digital twin model and obtain multiple indicator reports;

[0018] S2.4: Package the digital twin model and multiple indicator reports to obtain the twin status report, and store the twin status report in the database according to the time series;

[0019] S2.5: Output the twin status report to the adaptive street light brightness adjustment module;

[0020] The adaptive street light brightness adjustment module is used to process the twin status report and retrieve the process optimization model for further processing to obtain the street light brightness adjustment instruction report.

[0021] Furthermore, the steps of processing based on the twin status report and retrieving the process optimization model include:

[0022] S3.1: Feature extraction is performed based on the twin's state report to obtain the key parameter feature vector;

[0023] S3.2: Determine whether the current brightness adjustment state meets the optimization conditions based on the key parameter feature vector. If the determination result is yes, proceed to step S3.3. If the determination result is no, terminate the system process.

[0024] S3.3: Send a model inference request to the brightness adjustment knowledge deep learning module and receive the optimization parameters returned by the brightness adjustment knowledge deep learning module;

[0025] S3.4: Verify the feasibility of the scheme based on the optimized parameters and obtain a street light brightness adjustment instruction report;

[0026] S3.5: Output the street light brightness adjustment command report to the intelligent scheduling and coordination module;

[0027] The brightness adjustment knowledge deep learning module is used to store multiple versions of the model and supports the processing of optimization requests from the adaptive street light brightness adjustment module, as well as various processing of the model.

[0028] Furthermore, the system stores multiple versions of the model and supports processing optimization requests from the adaptive streetlight brightness adjustment module, as well as various processing steps for the model, including:

[0029] S4.1: Retrieve multiple versions of the model from the database, load the corresponding model according to the optimization request, input the optimization request into the corresponding model, and output the optimization parameters.

[0030] S4.2: Based on the historical twin status reports retrieved from the database as a sample set, and updated and trained multiple versions of the model according to the preset model training cycle or the update instructions input by the staff;

[0031] S4.3: Based on the validation set in the sample set, calculate the performance metrics of the multiple versions of the model and obtain a performance metric report;

[0032] S4.4: When the overall performance index in the performance index report is greater than the model performance threshold, generate a new version of the model and replace the corresponding old version of the model. When the overall performance index in the performance index report is less than the model performance threshold, keep the current version of the model and support model version rollback.

[0033] The real-time health assessment and early warning module is used to calculate the health status and predict the probability of failure based on the twin status report, and obtain a health assessment and early warning report.

[0034] Furthermore, the steps of calculating health status and predicting failure risk probability based on twin status reports include:

[0035] S5.1: Based on the database, obtain the latest twin status report in real time. When the time type changes to brightness adjustment complete, obtain the complete brightness adjustment data and get the final brightness adjustment data report.

[0036] S5.2: Extract feature vectors based on the final brightness adjustment data report to obtain a health feature vector;

[0037] S5.3: Retrieve the latest version of the health assessment model from the database, input the health feature vector, and output the comprehensive health score;

[0038] S5.4: Retrieve the latest version of the fault prediction model from the database, input the health feature vector, and output the predicted risk probability value;

[0039] S5.5: Based on the comprehensive health score and the predicted risk probability, a warning logic judgment is made to obtain a health assessment warning report;

[0040] S5.6: Store health assessment and early warning reports in the database;

[0041] The preventive maintenance brightness adjustment scheme optimization module is used to correct the life prediction model based on the health assessment early warning report, and to establish an objective function to optimize the brightness adjustment scheme, thereby obtaining a strategy optimization report.

[0042] Furthermore, the steps of revising the lifespan prediction model based on the health assessment and early warning report, and establishing an objective function to optimize the brightness adjustment scheme include:

[0043] S6.1: Obtain a pre-set batch of health assessment and early warning reports based on the database, and obtain the corresponding street light usage data based on the MES system to obtain a street light usage report;

[0044] S6.2: Based on the street light usage report, the predicted lifespan is corrected to obtain the corrected predicted lifespan value. The specific calculation formula for the correction is as follows:

[0045] ;

[0046] Obtain the corrected predicted lifetime value ,in, To predict lifetime values, The number of correction factors, For the first One correction factor;

[0047] S6.3: Establish an optimization model for the brightness adjustment scheme with the goal of minimizing the total cost. The specific expression of the brightness adjustment scheme optimization model is as follows:

[0048] ;

[0049] in, Total number of maintenance events The cost of downtime per unit of time. For the first Total downtime of this maintenance event For the cost of a single new street light, For the first The number of streetlights replaced in this maintenance event;

[0050] S6.4: Calculate the impact of brightness adjustment parameters on lifespan using multiple regression, and calculate the contribution of each factor to obtain the lifespan variable and factor contribution sequences. The specific formula set for the calculation is as follows:

[0051] ;

[0052] Obtain lifespan variables and factor contribution sequence ,in, For the regression intercept term, , and For regression coefficients, To ensure the interference fits the actual value, For the standard deviation of pressing force, This represents the effective value of vibration acceleration. For error terms, For the first One regression coefficient, For the first The standard deviation of each regression coefficient The number of regression coefficients;

[0053] S6.5: Generate a strategy optimization report based on the corrected predicted lifetime value, brightness adjustment scheme optimization model, lifetime variables and factor contribution sequences;

[0054] S6.6: Output the strategy optimization report to the intelligent scheduling and coordination module;

[0055] The intelligent scheduling and coordination module provides support for monitoring, verifying, processing, and outputting system data.

[0056] Furthermore, the steps to support the monitoring, verification, processing, and output of system data include:

[0057] S7.1: Verify the street light brightness adjustment command report. If the verification result is successful, proceed to step S7.2. If the verification result is unsuccessful, stop the system process and generate a verification failure report to be output to the staff receiving end.

[0058] S7.2: Convert the street light brightness adjustment instruction report verified in step S7.1 into a format executable by the device, and output it to the corresponding execution system respectively;

[0059] S7.3: Parse the strategy optimization report. When the parsing result is yes, generate a retraining task and output it to the brightness adjustment knowledge deep learning module.

[0060] S7.4: Collect heartbeat signals from all modules in real time, calculate system health based on heartbeat signals, and obtain a system status monitoring report;

[0061] S7.5: Monitor the execution status of commands. When an execution error occurs, initiate a rollback mechanism and feed back the abnormal execution result to the adaptive street light brightness adjustment module.

[0062] Furthermore, a street light brightness adaptive adjustment system based on light-sensing feedback includes:

[0063] S1: Collect multi-source data in real time based on multiple data sources, and perform preprocessing to obtain the original preprocessed dataset;

[0064] S2: Update the digital twin based on the original preprocessed dataset and perform real-time calculation of multiple indicators to obtain a twin status report;

[0065] S3: Process the data based on the twin status report and retrieve the process optimization model for further processing to obtain the street light brightness adjustment instruction report;

[0066] S4: Stores multiple versions of the model and supports processing optimization requests for the adaptive street light brightness adjustment module, as well as performing various processing on the model;

[0067] S5: Based on the twin status report, calculate the health status and predict the failure risk probability to obtain a health status assessment and early warning report;

[0068] S6: Based on the health assessment and early warning report, the lifespan prediction model is corrected, and an objective function is established to optimize the brightness adjustment scheme, resulting in a strategy optimization report;

[0069] S7: Provides support for monitoring, verifying, processing, and outputting system data.

[0070] The technical effects and advantages of the street light brightness adaptive adjustment system based on light-sensing feedback of the present invention are as follows:

[0071] This invention collects multi-source data in real time from multiple data sources, performs preprocessing to obtain a raw preprocessed dataset, updates the digital twin based on the raw preprocessed dataset, and calculates multiple indicators in real time to obtain a twin status report. The twin status report is then processed, and a process optimization model is invoked for further processing to obtain a streetlight brightness adjustment instruction report. Multiple versions of the model are stored, and the invention supports processing optimization requests from the adaptive streetlight brightness adjustment module and performing various model processing operations. Based on the twin status report, health status is calculated and fault risk probability is predicted to obtain a health assessment and early warning report. Based on the health assessment and early warning report, the lifespan prediction model is corrected, and an objective function is established to optimize the brightness adjustment scheme, resulting in a strategy optimization report. This invention provides support for monitoring, verifying, processing, and outputting system data, enabling the system to construct a digital twin of the brightness adjustment process through a multi-source heterogeneous data acquisition and fusion module. This module integrates and maps multi-source heterogeneous data into a digital twin in real time, fundamentally solving the data independence problem in traditional systems and effectively addressing the slow response of traditional systems to abnormal operating conditions. Furthermore, through an adaptive streetlight brightness adjustment module, a deep learning module for brightness adjustment knowledge, and an intelligent scheduling and coordination module, this invention minimizes the large fluctuations in brightness adjustment quality found in traditional systems, significantly improving the consistency of streetlight performance. Finally, through a real-time health assessment and early warning module and a preventative maintenance brightness adjustment scheme optimization module, the management strategy of the traditional system is changed from being based on fixed triggering conditions to being triggered based on equipment status, thereby reducing the probability of downtime due to unexpected situations and effectively extending the lifespan of streetlights, thus significantly improving the economic benefits for enterprises. Overall, this invention has significant advantages such as strong effectiveness in using basic data, significant adaptive optimization of streetlight brightness, and good applicability of management strategies. Attached Figure Description

[0072] Figure 1 This is a system architecture diagram of a street light brightness adaptive adjustment system based on light-sensing feedback, according to Embodiment 1 of the present invention.

[0073] Figure 2 This is a schematic diagram of a street light brightness adaptive adjustment system based on light-sensing feedback, according to Embodiment 2 of the present invention. Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0076] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0077] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0078] In practice, the server-side equipment deployed in a light-sensing feedback-based adaptive streetlight brightness adjustment system may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing light-sensing feedback-based adaptive streetlight brightness adjustment to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage each user terminal. Or, it can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more devices configured to provide light-sensing feedback-based adaptive streetlight brightness adjustment to various user terminals.

[0079] In terms of implementation, the adaptive street light brightness adjustment system based on light-sensing feedback and the user terminal are mutually compatible. That is, if the adaptive street light brightness adjustment system based on light-sensing feedback is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the adaptive street light brightness adjustment system based on light-sensing feedback is implemented as a website, then the user terminal is implemented as a webpage; or if the adaptive street light brightness adjustment system based on light-sensing feedback is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0080] like Figure 1 The figure shown is a system architecture diagram of a street light brightness adaptive adjustment system based on light-sensing feedback provided in an embodiment of the present invention.

[0081] The photosensitive feedback-based adaptive street light brightness adjustment system of this invention can be installed on a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server or server cluster), or it can be developed into a website. Depending on the functions implemented, the photosensitive feedback-based adaptive street light brightness adjustment system may include a multi-source heterogeneous data acquisition and fusion module, a digital twin construction module for the brightness adjustment process, an adaptive street light brightness adjustment module, a deep learning module for brightness adjustment knowledge, a real-time health assessment and early warning module, a preventative maintenance brightness adjustment scheme optimization module, and an intelligent scheduling and coordination module. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0082] In this embodiment of the invention, in the photosensitive feedback-based adaptive street light brightness adjustment system, each of the above modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the intelligent scheduling and coordination module can call the same information acquisition module to obtain information collected by that module. Based on the above characteristics, in the photosensitive feedback-based adaptive street light brightness adjustment system provided in this embodiment of the invention, without modifying the program code, the applicable scope of the photosensitive feedback-based adaptive street light brightness adjustment system architecture can be adjusted by adding modules and directly calling them, achieving cluster-style horizontal expansion to quickly and flexibly expand the photosensitive feedback-based adaptive street light brightness adjustment system. In practical applications, the above modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0083] Example 1

[0084] Please see Figure 1As shown in this embodiment, a street light brightness adaptive adjustment system based on light-sensing feedback is described. The system includes:

[0085] The multi-source heterogeneous data acquisition and fusion module is used to acquire multi-source data in real time based on multiple data sources and perform preprocessing to obtain the original preprocessed dataset.

[0086] Furthermore, the steps for real-time acquisition and preprocessing of multi-source data based on multiple data sources include:

[0087] S1.1: Real-time acquisition of multi-source data based on multiple data sources to obtain the raw dataset. The multiple data sources include visual inspection system, MES system, IoT sensor and RFID reader;

[0088] It needs to be explained that, taking a visual inspection system as an example, the information collected includes images of the street light itself, the light pole, the wiring, and surrounding facilities captured by the camera, and the identification of visible faults such as damaged lamps, cracked lampshades, tilted or fallen light poles, exposed wiring, and hanging foreign objects. Taking an MES system as an example, the work order type data collected includes, but is not limited to, the batch number, model, and planned quantity of the street light equipment. Taking an IoT sensor as an example, it collects electrical and physical operating data such as street light voltage, current, power, temperature and humidity, tilt, lighting status, battery power (for photovoltaic street lights), and line leakage current. Taking an RFID reader as an example, the logistics type data collected includes, but is not limited to, component ID, workstation ID, and logistics timestamp.

[0089] S1.2: Based on the system's internal time, and according to the collection data stamps of all data items in the original dataset, time alignment processing is performed to obtain a time-aligned dataset;

[0090] S1.3: Perform data validation based on the time-aligned dataset, and remove data items that fail the validation to obtain the cleaned dataset;

[0091] It needs to be explained that data validation means, taking temperature as an example, when the temperature exceeds the temperature threshold range, the temperature data item in the time-aligned dataset will be judged as a failure result;

[0092] S1.4: Arrange the data items in the data cleaning dataset according to the time order to obtain the original preprocessed dataset;

[0093] S1.5: Store the original preprocessed dataset in the database and output it to the digital twin construction module of the brightness adjustment process;

[0094] The brightness adjustment process digital twin construction module is used to update the digital twin based on the original preprocessed dataset, and to perform real-time calculation of multiple indicators to obtain a twin status report.

[0095] Furthermore, the steps of updating the digital twin based on the original preprocessed dataset and performing real-time calculations of multiple metrics include:

[0096] S2.1: Create an initial digital twin template based on the original preprocessed dataset. The initial digital twin template includes the street light device ID, street light device model, tolerance design range, and standard street light brightness.

[0097] S2.2: Based on the initial digital twin template, and by obtaining the latest original preprocessed dataset in real time from the database, the initial digital twin template is updated according to the event types of the original preprocessed dataset to obtain the digital twin model.

[0098] It should be explained that the update in step S2.2 refers to, for example, updating the current pressing depth of the initial digital twin template when the event type of the original preprocessed dataset is a pressing event, and updating the torque sequence of the initial digital twin template when the event type of the original preprocessed dataset is a tightening event.

[0099] S2.3: Calculate multiple indicator values ​​of street light equipment in real time based on digital twin model and obtain multiple indicator reports;

[0100] S2.4: Package the digital twin model and multiple indicator reports to obtain the twin status report, and store the twin status report in the database according to the time series;

[0101] S2.5: Output the twin status report to the adaptive street light brightness adjustment module;

[0102] The adaptive street light brightness adjustment module is used to process the twin status report and retrieve the process optimization model for processing to obtain the street light brightness adjustment instruction report.

[0103] Furthermore, the steps of processing based on the twin status report and retrieving the process optimization model include:

[0104] S3.1: Feature extraction is performed based on the twin's state report to obtain the key parameter feature vector;

[0105] S3.2: Determine whether the current brightness adjustment state meets the optimization conditions based on the key parameter feature vector. If the determination result is yes, proceed to step S3.3. If the determination result is no, terminate the system process.

[0106] It should be explained that the judgment in step S3.2 refers to the following conditions: Condition 1: When the actual value of the interference fit is within the interference threshold range and not within the standard interference threshold range, the judgment result is yes; Condition 2: When the brightness adjustment stability is less than the stability threshold, the judgment result is yes; Condition 3: When conditions 1 and 2 are not met, the judgment result is no. Here, the interference threshold range, the standard interference threshold range, and the stability threshold are all manually set and input into the system.

[0107] S3.3: Send a model inference request to the brightness adjustment knowledge deep learning module and receive the optimization parameters returned by the brightness adjustment knowledge deep learning module;

[0108] It should be explained that, taking the pressing event as an example, the model inference request includes the street light device ID and key parameter feature vectors, and the optimization parameters include the optimization pressing force, optimization pressing speed, optimization torque, and brightness adjustment sequence number.

[0109] S3.4: Verify the feasibility of the scheme based on the optimized parameters and obtain a street light brightness adjustment instruction report;

[0110] It needs to be explained that feasibility verification refers to conducting safety checks on the data items in the optimization parameters. Taking the optimization of pressing force as an example, it checks whether the value of the optimization pressing force is within the safe threshold range of pressing force. When the check result is yes, the optimization parameter is converted into a street light brightness adjustment command to obtain an optimization plan report. When the check result is no, an optimization failure report is generated and output to the staff receiving end.

[0111] S3.5: Output the street light brightness adjustment command report to the intelligent scheduling and coordination module;

[0112] The brightness adjustment knowledge deep learning module is used to store multiple versions of the model, and supports processing optimization requests from the adaptive street light brightness adjustment module, as well as performing various processing on the model.

[0113] Furthermore, it stores multiple versions of the model and supports processing optimization requests from the adaptive streetlight brightness adjustment module, as well as various processing steps for the model, including:

[0114] S4.1: Retrieve multiple versions of the model from the database, load the corresponding model according to the optimization request, input the optimization request into the corresponding model, and output the optimization parameters.

[0115] It should be explained that multiple versions of the model include, but are not limited to, different versions of process optimization models, health assessment models, life prediction models, and failure prediction models.

[0116] S4.2: Based on the historical twin status reports retrieved from the database as a sample set, and updated and trained multiple versions of the model according to the preset model training cycle or the update instructions input by the staff;

[0117] It should be explained that the model training cycle is manually set and input into the system; for example, the model training cycle is every ten days.

[0118] S4.3: Based on the validation set in the sample set, calculate the performance metrics of the multiple versions of the model and obtain a performance metric report;

[0119] S4.4: When the overall performance index in the performance index report is greater than the model performance threshold, generate a new version of the model and replace the corresponding old version of the model. When the overall performance index in the performance index report is less than the model performance threshold, keep the current version of the model and support model version rollback.

[0120] It should be noted that the model performance thresholds were manually set and input into the system.

[0121] The real-time health assessment and early warning module is used to calculate the health status and predict the probability of failure based on the twin status report, and obtain a health assessment and early warning report.

[0122] Furthermore, the steps for calculating health status and predicting failure risk probability based on twin status reports include:

[0123] S5.1: Based on the database, obtain the latest twin status report in real time. When the time type changes to brightness adjustment complete, obtain the complete brightness adjustment data and get the final brightness adjustment data report.

[0124] S5.2: Extract feature vectors based on the final brightness adjustment data report to obtain a health feature vector;

[0125] S5.3: Retrieve the latest version of the health assessment model from the database, input the health feature vector, and output the comprehensive health score;

[0126] It should be explained that the overall health score is a value from 0 to 100, and the higher the value, the better the health.

[0127] S5.4: Retrieve the latest version of the fault prediction model from the database, input the health feature vector, and output the predicted risk probability value;

[0128] It should be explained that the risk probability prediction value is a value between 0 and 1, and the higher the value, the higher the risk probability.

[0129] S5.5: Based on the comprehensive health score and the predicted risk probability, a warning logic judgment is made to obtain a health assessment warning report;

[0130] It should be explained that the warning logic judgment in step S5.5 means, for example, that when the overall health score is less than 60 or the risk probability prediction value is greater than 0.7, a red warning report is generated; when the overall health score is greater than or equal to 60 and less than 80 or the risk probability prediction value is greater than 0.3 and less than or equal to 0.7, a yellow warning report is generated; and when the above warning report generation conditions are not met, a green warning report is generated.

[0131] S5.6: Store health assessment and early warning reports in the database;

[0132] The preventive maintenance brightness adjustment scheme optimization module is used to correct the life prediction model based on the health assessment and early warning report, and to establish an objective function to optimize the brightness adjustment scheme, thereby obtaining a strategy optimization report.

[0133] Furthermore, the steps of revising the lifespan prediction model based on the health assessment and early warning report, and establishing an objective function to optimize the brightness adjustment scheme include:

[0134] S6.1: Obtain a pre-set batch of health assessment and early warning reports based on the database, and obtain the corresponding street light usage data based on the MES system to obtain a street light usage report;

[0135] S6.2: Based on the street light usage report, the predicted lifespan is corrected to obtain the corrected predicted lifespan value. The specific calculation formula for the correction is as follows:

[0136] ;

[0137] Obtain the corrected predicted lifetime value ,in, To predict lifetime values, The number of correction factors, For the first One correction factor;

[0138] It should be explained that the correction factors include, but are not limited to, geological condition correction factors, load correction factors, and rotational speed correction factors;

[0139] S6.3: Establish an optimization model for the brightness adjustment scheme with the goal of minimizing the total cost. The specific expression of the brightness adjustment scheme optimization model is as follows:

[0140] ;

[0141] in, Total number of maintenance events The cost of downtime per unit of time. For the first Total downtime of this maintenance event For the cost of a single new street light, For the first The number of streetlights replaced in this maintenance event;

[0142] It should be explained that the constraints of the brightness adjustment scheme optimization model are that each street light must be replaced before the end of its lifespan, the number of street lights to be replaced must be less than the maximum number of maintenance personnel, and the time interval between street light replacements must be greater than the minimum maintenance time window.

[0143] S6.4: Calculate the impact of brightness adjustment parameters on lifespan using multiple regression, and calculate the contribution of each factor to obtain the lifespan variable and factor contribution sequences. The specific formula set for the calculation is as follows:

[0144] ;

[0145] Obtain lifespan variables and factor contribution sequence ,in, For the regression intercept term, , and For regression coefficients, To ensure the interference fits the actual value, For the standard deviation of pressing force, This represents the effective value of vibration acceleration. For error terms, For the first One regression coefficient, For the first The standard deviation of each regression coefficient The number of regression coefficients;

[0146] S6.5: Generate a strategy optimization report based on the corrected predicted lifetime value, brightness adjustment scheme optimization model, lifetime variables and factor contribution sequences;

[0147] It should be explained that the strategy optimization report is a report generated based on the corrected predicted lifetime value, the brightness adjustment scheme optimization model, lifetime variables and factor contribution sequences, which has the function of optimizing the brightness adjustment scheme and analyzing the correlation between brightness adjustment process and lifetime.

[0148] S6.6: Output the strategy optimization report to the intelligent scheduling and coordination module;

[0149] The intelligent scheduling and coordination module is used to provide support for monitoring, verifying, processing and outputting system data;

[0150] Further steps to support the monitoring, verification, processing, and output of system data include:

[0151] S7.1: Verify the street light brightness adjustment command report. If the verification result is successful, proceed to step S7.2. If the verification result is unsuccessful, stop the system process and generate a verification failure report to be output to the staff receiving end.

[0152] It should be explained that the verification in step S7.1 includes, but is not limited to, permission verification, data integrity verification, and security scope verification;

[0153] S7.2: Convert the street light brightness adjustment instruction report verified in step S7.1 into a format executable by the device, and output it to the corresponding execution system respectively;

[0154] S7.3: Parse the strategy optimization report. When the parsing result is yes, generate a retraining task and output it to the brightness adjustment knowledge deep learning module.

[0155] It should be explained that the analysis in step S7.3 refers to, for example, the existence of new key influencing factors;

[0156] S7.4: Collect heartbeat signals from all modules in real time, calculate system health based on heartbeat signals, and obtain a system status monitoring report;

[0157] S7.5: Monitor the execution status of commands. When an execution error occurs, initiate a rollback mechanism and feed back the abnormal execution result to the adaptive street light brightness adjustment module.

[0158] The beneficial effects of this embodiment are as follows: Multi-source data is collected in real time from multiple data sources and preprocessed to obtain an original preprocessed dataset. The digital twin is updated based on this dataset, and multiple indicators are calculated in real time to obtain a twin status report. This twin status report is then processed, and a process optimization model is invoked for further processing to obtain a streetlight brightness adjustment instruction report. Multiple versions of the model are stored, and the system supports processing optimization requests from the adaptive streetlight brightness adjustment module, as well as performing various processing on the model. Based on the twin status report, health status is calculated and fault risk probability is predicted to obtain a health assessment and early warning report. Based on this report, the lifespan prediction model is corrected, and an objective function is established to optimize the brightness adjustment scheme, resulting in a strategy optimization report. This provides support for monitoring, verifying, processing, and outputting system data, enabling the system to utilize a multi-source heterogeneous data acquisition and fusion module and a digital twin for the brightness adjustment process. The digital twin construction module integrates and maps multi-source heterogeneous data into a digital twin in real time, fundamentally solving the data independence problem in traditional systems and effectively addressing the slow response of traditional systems to abnormal operating conditions. Furthermore, this embodiment utilizes an adaptive streetlight brightness adjustment module, a deep learning module for brightness adjustment knowledge, and an intelligent scheduling and coordination module to minimize the large fluctuations in brightness adjustment quality found in traditional systems, significantly improving the consistency of streetlight performance. Finally, through a real-time health assessment and early warning module and a preventative maintenance brightness adjustment scheme optimization module, the management strategy of the traditional system is changed from being based on fixed triggering conditions to being triggered based on equipment status, thereby reducing the probability of downtime due to unexpected situations and effectively extending the lifespan of streetlights, thus significantly improving the economic benefits for enterprises. Overall, this embodiment has significant advantages such as strong effectiveness in using basic data, a large adaptive optimization effect for streetlight brightness, and good applicability of management strategies.

[0159] Example 2

[0160] Please see Figure 2 As shown, the parts not described in detail in this embodiment are described in Embodiment 1. A street light brightness adaptive adjustment system based on light feedback is provided. The method includes: S1: Real-time acquisition of multi-source data based on multiple data sources and preprocessing to obtain the original preprocessed dataset;

[0161] S2: Update the digital twin based on the original preprocessed dataset and perform real-time calculation of multiple indicators to obtain a twin status report;

[0162] S3: Process the data based on the twin status report and retrieve the process optimization model for further processing to obtain the street light brightness adjustment instruction report;

[0163] S4: Stores multiple versions of the model and supports processing optimization requests for the adaptive street light brightness adjustment module, as well as performing various processing on the model;

[0164] S5: Based on the twin status report, calculate the health status and predict the failure risk probability to obtain a health status assessment and early warning report;

[0165] S6: Based on the health assessment and early warning report, the lifespan prediction model is corrected, and an objective function is established to optimize the brightness adjustment scheme, resulting in a strategy optimization report;

[0166] S7: Provides support for monitoring, verifying, processing, and outputting system data.

[0167] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the present invention.

Claims

1. A street light brightness adaptive adjustment system based on light-sensing feedback, characterized in that, The system includes: an adaptive street light brightness adjustment module, a brightness adjustment knowledge deep learning module, a real-time health assessment and early warning module, and a preventive maintenance brightness adjustment scheme optimization module, wherein: The adaptive street light brightness adjustment module is used to process the twin status report and retrieve the process optimization model for processing to obtain the street light brightness adjustment instruction report. The brightness adjustment knowledge deep learning module is used to store multiple versions of the model, and supports processing optimization requests from the adaptive street light brightness adjustment module, as well as performing various processing on the model. The real-time health assessment and early warning module is used to calculate the health status and predict the probability of failure based on the twin status report, and obtain a health assessment and early warning report. The preventive maintenance brightness adjustment scheme optimization module is used to correct the life prediction model based on the health assessment and early warning report, and to establish an objective function to optimize the brightness adjustment scheme, thereby obtaining a strategy optimization report.

2. The street light brightness adaptive adjustment system based on light-sensing feedback according to claim 1, characterized in that, The system also includes: a multi-source heterogeneous data acquisition and fusion module, a digital twin construction module for the brightness adjustment process, and an intelligent scheduling and coordination module, wherein: The multi-source heterogeneous data acquisition and fusion module is used to acquire multi-source data in real time based on multiple data sources and perform preprocessing to obtain the original preprocessed dataset. The brightness adjustment process digital twin construction module is used to update the digital twin based on the original preprocessed dataset, and to perform real-time calculation of multiple indicators to obtain a twin status report. The intelligent scheduling and coordination module is used to provide support for monitoring, verifying, processing and outputting system data.

3. The street light brightness adaptive adjustment system based on light-sensing feedback according to claim 2, characterized in that, The steps for real-time acquisition and preprocessing of multi-source data include: S1.1: Real-time acquisition of multi-source data based on multiple data sources to obtain the raw dataset. The multiple data sources include visual inspection system, MES system, IoT sensor and RFID reader; S1.2: Based on the system's internal time, and according to the collection data stamps of all data items in the original dataset, time alignment processing is performed to obtain a time-aligned dataset; S1.3: Perform data validation based on the time-aligned dataset, and remove data items that fail the validation to obtain the cleaned dataset; S1.4: Arrange the data items in the data cleaning dataset according to the time order to obtain the original preprocessed dataset; S1.5: Store the original preprocessed dataset in the database and output it to the digital twin building module of the brightness adjustment process.

4. The street light brightness adaptive adjustment system based on light-sensing feedback according to claim 3, characterized in that, The steps for updating the digital twin based on the original preprocessed dataset and performing real-time calculations of multiple metrics include: S2.1: Create an initial digital twin template based on the original preprocessed dataset. The initial digital twin template includes the street light device ID, street light device model, tolerance design range, and standard street light brightness. S2.2: Based on the initial digital twin template, and by obtaining the latest original preprocessed dataset in real time from the database, the initial digital twin template is updated according to the event types of the original preprocessed dataset to obtain the digital twin model. S2.3: Calculate multiple indicator values ​​of street light equipment in real time based on digital twin model and obtain multiple indicator reports; S2.4: Package the digital twin model and multiple indicator reports to obtain the twin status report, and store the twin status report in the database according to the time series; S2.5: Output the twin status report to the adaptive street light brightness adjustment module.

5. The street light brightness adaptive adjustment system based on light-sensing feedback according to claim 4, characterized in that, The steps for processing based on twin status reports and retrieving process optimization models include: S3.1: Feature extraction is performed based on the twin's state report to obtain the key parameter feature vector; S3.2: Determine whether the current brightness adjustment state meets the optimization conditions based on the key parameter feature vector. If the determination result is yes, proceed to step S3.

3. If the determination result is no, terminate the system process. S3.3: Send a model inference request to the brightness adjustment knowledge deep learning module and receive the optimization parameters returned by the brightness adjustment knowledge deep learning module; S3.4: Verify the feasibility of the scheme based on the optimized parameters and obtain a street light brightness adjustment instruction report; S3.5: Output the street light brightness adjustment command report to the intelligent scheduling and coordination module.

6. The street light brightness adaptive adjustment system based on photosensitive feedback according to claim 3, characterized in that, It stores multiple versions of the model and supports processing optimization requests from the adaptive street light brightness adjustment module, as well as various processing steps for the model, including: S4.1: Retrieve multiple versions of the model from the database, load the corresponding model according to the optimization request, input the optimization request into the corresponding model, and output the optimization parameters. S4.2: Based on the historical twin status reports retrieved from the database as a sample set, and updated and trained multiple versions of the model according to the preset model training cycle or the update instructions input by the staff; S4.3: Based on the validation set in the sample set, calculate the performance metrics of the multiple versions of the model and obtain a performance metric report; S4.4: When the overall performance index in the performance index report is greater than the model performance threshold, a new version of the model is generated and the corresponding old version of the model is replaced. When the overall performance index in the performance index report is less than the model performance threshold, the current version of the model is maintained, and model version rollback is supported.

7. The street light brightness adaptive adjustment system based on light-sensing feedback according to claim 3, characterized in that, The steps for calculating health status and predicting failure risk probability based on twin status reports include: S5.1: Based on the database, obtain the latest twin status report in real time. When the time type changes to brightness adjustment complete, obtain the complete brightness adjustment data and get the final brightness adjustment data report. S5.2: Extract feature vectors based on the final brightness adjustment data report to obtain a health feature vector; S5.3: Retrieve the latest version of the health assessment model from the database, input the health feature vector, and output the comprehensive health score; S5.4: Retrieve the latest version of the fault prediction model from the database, input the health feature vector, and output the predicted risk probability value; S5.5: Based on the comprehensive health score and the predicted risk probability, a warning logic judgment is made to obtain a health assessment warning report; S5.6: Store health assessment and early warning reports in the database.

8. A street light brightness adaptive adjustment system based on light-sensing feedback according to claim 3, characterized in that, The steps for revising the lifespan prediction model based on the health assessment and early warning report, and for establishing an objective function to optimize the brightness adjustment scheme, include: S6.1: Obtain a pre-set batch of health assessment and early warning reports based on the database, and obtain the corresponding street light usage data based on the MES system to obtain a street light usage report; S6.2: Based on the street light usage condition report, the predicted lifespan is corrected to obtain the corrected predicted lifespan value; S6.3: Establish an optimization model for brightness adjustment schemes with the goal of minimizing total cost; S6.4: Calculate the impact of brightness adjustment parameters on lifespan using multiple regression, and calculate the contribution of each factor to obtain the lifespan variable and factor contribution sequence; S6.5: Generate a strategy optimization report based on the corrected predicted lifetime value, brightness adjustment scheme optimization model, lifetime variables and factor contribution sequences; S6.6: Output the strategy optimization report to the intelligent scheduling and coordination module.

9. A street light brightness adaptive adjustment system based on photosensitive feedback according to claim 5, characterized in that, The steps to support the monitoring, verification, processing, and output of system data include: S7.1: Verify the street light brightness adjustment command report. If the verification result is successful, proceed to step S7.

2. If the verification result is unsuccessful, stop the system process and generate a verification failure report to be output to the staff receiving end. S7.2: Convert the street light brightness adjustment instruction report verified in step S7.1 into a format executable by the device, and output it to the corresponding execution system respectively; S7.3: Parse the strategy optimization report. When the parsing result is yes, generate a retraining task and output it to the brightness adjustment knowledge deep learning module. S7.4: Collect heartbeat signals from all modules in real time, calculate system health based on heartbeat signals, and obtain a system status monitoring report; S7.5: Monitor the execution status of commands. When an execution error occurs, initiate a rollback mechanism and feed back the abnormal execution result to the adaptive street light brightness adjustment module.

10. A street light brightness adaptive adjustment system based on light-sensing feedback according to any one of claims 1-9, characterized in that, The work includes the following steps: S1: Collect multi-source data in real time based on multiple data sources, and perform preprocessing to obtain the original preprocessed dataset; S2: Update the digital twin based on the original preprocessed dataset and perform real-time calculation of multiple indicators to obtain a twin status report; S3: Process the data based on the twin status report and retrieve the process optimization model for further processing to obtain the street light brightness adjustment instruction report; S4: Stores multiple versions of the model and supports processing optimization requests for the adaptive street light brightness adjustment module, as well as performing various processing on the model; S5: Based on the twin status report, calculate the health status and predict the failure risk probability to obtain a health status assessment and early warning report; S6: Based on the health assessment and early warning report, the lifespan prediction model is corrected, and an objective function is established to optimize the brightness adjustment scheme, resulting in a strategy optimization report; S7: Provides support for monitoring, verifying, processing, and outputting system data.

Images