Intelligent street lamp illumination data quality control system
By collecting and processing the lighting intensity, lamp status and energy consumption data of smart street lights in real time, establishing a state classification model, generating and responding decisions, the data accuracy and timeliness in smart street light systems are solved, and the system's operating efficiency and the stability of urban lighting are improved.
Patent Information
- Application Number
- CN202510623588.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-15
- Publication Date
- 2025-08-19
AI Technical Summary
In the smart street light system, there are data accuracy, completeness and timeliness in the collection, transmission and processing of lighting data, which affects the efficient operation and function of the system.
The data acquisition module is used to collect light intensity, lamp working status and energy consumption data in real time. After data cleaning and denoising processing, the state reference value is generated using weight calculation, a state classification model is established, street light status classification is performed, and the response decision results are generated through the early warning feedback module, and the user interaction module displays the analysis results.
It improves the processing capacity of lighting data, reduces the work burden of managers, improves work efficiency, and ensures the reliable operation of street light systems and the stability of urban lighting.
Smart Images
Figure CN120508940A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a smart street lamp lighting data quality control system. Background Art
[0002] With the rapid development of smart cities, smart streetlights, as a crucial component of smart city construction, undertake multiple functions, including lighting, as well as data collection, transmission, and analysis. The large amount of lighting data generated by smart streetlight systems is crucial for optimizing streetlight management, improving energy efficiency, and ensuring the quality of urban lighting.
[0003] However, the current collection, transmission, and processing of smart street lighting data often face challenges with accuracy, completeness, and timeliness. Traditional data processing methods struggle to effectively address the impact of complex and changing environmental factors on lighting data, resulting in inconsistent data quality and hindering the efficient operation and functionality of smart street lighting systems. For example, inclement weather can affect the accuracy of sensor data, while network fluctuations can cause data loss or delays, making it difficult to provide a reliable basis for intelligent control and scientific management of street lights.
[0004] In view of this, the present invention proposes a smart street lamp lighting data quality control system to solve the above problems. Summary of the Invention
[0005] In order to overcome the deficiencies of the prior art, the present invention is proposed.
[0006] In order to solve the above technical problems, the basic technical solutions proposed by the present invention are: A smart street lighting data quality control system, comprising: A data acquisition module is used to collect and pre-process various data sets related to smart street lighting. The lighting data sets include light intensity data, lamp operating status data, and energy consumption data; A data processing module is used to process the lighting data set to obtain a state reference value, and to classify the data to obtain a street lamp state classification result; An early warning feedback module is used to process the street light status classification result to obtain a response decision result; The user interaction module is used to display normal operation prompt information through the display terminal, analyze the lighting data set, and obtain and display the analysis results.
[0007] The preferred method of collecting smart street lighting data sets includes: installing light sensors to collect the light intensity values of the surrounding environment in real time to obtain light intensity data; Use smart meters to monitor the power consumption of street lights and obtain energy consumption data; Obtain the working status data of the lamp through the information fed back by the lamp controller; Preprocessing methods include data cleaning and data denoising.
[0008] Preferably, the steps of processing the lighting data set are as follows: obtaining a lighting state reference value by substituting into the calculation formula: Z = α × G + β × H + γ × N, where G is the light intensity data, H is the lamp working state data, N is the energy consumption data, and α, β, and γ are corresponding weight factors respectively; Collect K groups of historical feature vectors as the sample set, and divide the sample set into a training set of 70%K, a test set of 15%K, and a validation set of 15%K; Establish a state classification model based on the sample set, obtain the historical feature vectors in the training set, preset the normal data cluster L1, alarm data cluster L2 and warning data cluster L3, and randomly select three data points in the training set as the center of the first cluster, representing the higher normal data cluster L1, alarm data cluster L2 and warning data cluster L3 respectively; By substituting the calculation formula: d=∑i=1n(xi−yi)2, the distance between the data items is obtained. The distance between the data items in the training set and the higher data cluster P1, the normal data cluster P2, and the lower data cluster P3 is calculated respectively, and the data items are assigned to the data clusters closest to them. Three new data clusters are obtained as the second cluster centers, where xi and yi are the coordinate values of the data points, xi and yi are the values of the two data points on n sub-data items respectively, and n is the number of sub-data items; Calculate the means of the three new data clusters in the second cluster center respectively, and use them as the new first cluster center for recalculation; Repeat the above steps until the preset number of iterations is reached to obtain a street light status classification model; The feature vector is input into the street light state classification model, and the state reference value is output.
[0009] Preferably, the classification method includes: presetting the street light status threshold interval (E1, E2), generating a normal operation signal when the status reference value is less than E1, generating an abnormal operation signal when the status reference value is greater than E1 and less than E2, generating a serious fault signal when the status reference value is greater than E2, the normal operation signal includes a group of fields representing that the street light is in good working condition, the abnormal operation signal includes a group of fields representing that the street light working condition is abnormal but can still maintain basic operation, the serious fault signal includes a group of fields representing that the street light working condition is seriously abnormal and requires immediate maintenance, and the normal operation signal, abnormal operation signal and serious fault signal are packaged to obtain the street light status classification result.
[0010] Preferably, the specific method for processing the street light status classification result is as follows: When the streetlight status classification result is a normal operating signal, a normal operating prompt message is sent to the monitoring end through the communication unit, indicating that the streetlight is currently in good working condition and can be inspected and maintained according to the regular plan; When the streetlight status classification result is an abnormal operation signal, an abnormal maintenance prompt message is sent to the maintenance personnel receiving end through the communication unit, indicating that the streetlight status is abnormal and requiring the maintenance personnel to check the streetlight lighting data set as soon as possible. Based on the inspection results, maintenance measures such as adjusting lamp parameters, replacing some parts, or conducting circuit inspections are implemented on the streetlight. When the streetlight status classification result is a serious fault signal, an emergency maintenance notice is sent to the maintenance personnel receiving end through the communication unit, indicating that there is a serious abnormality in the streetlight status, requiring maintenance personnel to immediately go to the site to carry out emergency repairs, adopt temporary lighting protection measures and formulate a detailed maintenance plan; Package normal operation prompt information, abnormal maintenance prompt information and emergency maintenance notifications to obtain response decision results.
[0011] Preferably, the lighting data set is analyzed as follows: displaying normal operation prompt information through the display terminal, analyzing the collected lighting data set, and obtaining and displaying the analysis results; The lighting data set analysis method includes: presetting a data standard threshold interval group, substituting the light intensity data, lamp working status data, energy consumption data, etc. into the corresponding data standard threshold interval for comparison, and outputting the normal state, abnormal state or fault state; When all lighting data sets are normal results, the normal state is output; when there is one or more abnormal results and the rest are normal results, the abnormal state is output; when there is one or more fault results and the rest are normal results or abnormal results, the fault state is output; the normal state, abnormal state and fault state are packaged to obtain analysis results, and the analysis results are intuitively presented through the display terminal, which allows managers to quickly understand the overall operating status of the street lighting system.
[0012] The beneficial effects of the present invention are: The present invention processes the smart street lamp lighting data set to obtain a state reference value that can directly reflect the current working state of the street lamp, greatly reducing the workload of managers caused by analyzing and calculating large amounts of lighting data and improving work efficiency.
[0013] By processing the street light status classification results, the response decision results obtained can assist maintenance personnel to quickly take highly targeted response measures according to the different working conditions of street lights, effectively reducing the adverse effects of street light failures and ensuring the stability of urban lighting.
[0014] By analyzing the smart streetlight lighting dataset, the resulting analysis results can assist management personnel in quickly screening individual streetlight operating data, preventing more serious failures caused by untimely processing of single data anomalies and ensuring the reliable operation of the smart streetlight system. Overall, this invention offers significant advantages in terms of strong lighting data processing capabilities, high decision-making support, and timely lighting data feedback. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 This is a system flow chart of a smart street lighting data quality control system of the present invention. DETAILED DESCRIPTION
[0016] The following will be combined with the Figure 1 The technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.
[0017] A smart street lighting data quality control system, comprising: The data acquisition module is used to collect and pre-process various data sets related to smart street lighting. The lighting data set includes light intensity data, lamp operating status data, and energy consumption data. The smart street lighting data set is collected by installing a light sensor to collect the light intensity value of the surrounding environment in real time to obtain light intensity data. Use smart meters to monitor the power consumption of street lights and obtain energy consumption data; Obtain the working status data of the lamp through the information fed back by the lamp controller; Preprocessing methods include data cleaning and data denoising.
[0018] For example, by installing light sensors, real-time data on the ambient light intensity around streetlights can be collected. Light intensity values are quantified in lux (lx) based on actual lighting conditions. For example, when light intensity falls below a certain threshold (e.g., 50lx), it indicates dimming and the streetlight should be turned on or brighter. Smart meters are also used to monitor streetlight power consumption. Energy consumption data is collected in real time via the meters, recording the streetlight's power consumption over a specific time interval in kilowatt-hours (kWh). Information fed back by the lighting controllers provides information on the lighting's operating status, such as whether it's on or off (1 = on, 0 = off), and the brightness adjustment level (ranging from 1 to 5, with 1 being the lowest brightness and 5 being the highest).
[0019] Perform data preprocessing and use data cleaning algorithms to remove obvious erroneous values in the collected data, such as negative light intensity or values far beyond the reasonable range; use data denoising technology, such as wavelet denoising algorithm, to eliminate noise data generated by factors such as electromagnetic interference, to ensure the accuracy and reliability of the collected data.
[0020] The data processing module is used to process the lighting data set to obtain a state reference value, and perform classification to obtain a street lamp state classification result. The steps of processing the lighting data set are as follows: the lighting state reference value is obtained by substituting into the calculation formula: Z = α × G + β × H + γ × N, where G is the light intensity data, H is the lamp working state data, N is the energy consumption data, and α, β, and γ are corresponding weight factors respectively. Collect K groups of historical feature vectors as the sample set, and divide the sample set into a training set of 70%K, a test set of 15%K, and a validation set of 15%K; Establish a state classification model based on the sample set, obtain the historical feature vectors in the training set, preset the normal data cluster L1, alarm data cluster L2 and warning data cluster L3, and randomly select three data points in the training set as the center of the first cluster, representing the higher normal data cluster L1, alarm data cluster L2 and warning data cluster L3 respectively; By substituting the calculation formula: d=∑i=1n(xi−yi)2, the distance between the data items is obtained. The distance between the data items in the training set and the higher data cluster P1, the normal data cluster P2, and the lower data cluster P3 is calculated respectively, and the data items are assigned to the data clusters closest to them. Three new data clusters are obtained as the second cluster centers, where xi and yi are the coordinate values of the data points, xi and yi are the values of the two data points on n sub-data items respectively, and n is the number of sub-data items; Calculate the means of the three new data clusters in the second cluster center respectively, and use them as the new first cluster center for recalculation; Repeat the above steps until the preset number of iterations is reached to obtain a street light status classification model; The feature vector is input into the street light state classification model, and the state reference value is output.
[0021] The classification method includes: presetting the street light status threshold interval (E1, E2), when the status reference value is less than E1, generating a normal operation signal, when the status reference value is greater than E1 and less than E2, generating an abnormal operation signal, when the status reference value is greater than E2, generating a serious fault signal, the normal operation signal includes a group of fields representing that the street light is in good working condition, the abnormal operation signal includes a group of fields representing that the street light working condition is abnormal but can still maintain basic operation, the serious fault signal includes a group of fields representing that the street light working condition is seriously abnormal and requires immediate maintenance, and the normal operation signal, abnormal operation signal and serious fault signal are packaged to obtain the street light status classification result.
[0022] For example, through analysis of a large amount of historical data and evaluation of actual street lamp operation, the weight of light intensity data is determined to be α = 0.4, the weight of lamp working status data is determined to be β = 0.3, and the weight of energy consumption data is determined to be γ = 0.3.
[0023] Collect K = 1000 groups of historical feature vectors as the sample set. Divide the sample set into a training set of 700 groups (70% * 1000 = 700), a test set of 150 groups (15% * 1000 = 150), and a validation set of 15% * 1000 = 150.
[0024] A state classification model is established based on the sample set. Three data points are randomly selected in the training set as the first cluster center, representing the higher normal data cluster L1, the alarm data cluster L2 and the warning data cluster L3 respectively.
[0025] Using the distance calculation formula d=∑i=1n(xi−yi) 2 Calculate the distance between each data item in the training set and the center of each cluster. For example, for a feature vector containing three sub-data items (light intensity, lamp operating status, and energy consumption), with n = 3, calculate the distance between it and the center of each cluster for each of these three sub-data items.
[0026] Assign the data items to the closest clusters, obtaining three new clusters as the second cluster centers. Calculate the mean of the three new clusters within the second cluster centers and use them as the new first cluster centers for further calculation. Repeat this process for 50 iterations to obtain a streetlight status classification model.
[0027] The collected feature vectors are input into the streetlight status classification model, and the output is a status reference value. Preset streetlight status thresholds (E1 = 0.5, E2 = 0.8) generate a normal operation signal when the status reference value is less than 0.5; an abnormal operation signal when the status reference value is greater than 0.5 and less than 0.8; and a serious fault signal when the status reference value is greater than 0.8.
[0028] The early warning feedback module is used to process the street light status classification results to obtain a response decision result; the specific method of processing the street light status classification results is as follows: When the streetlight status classification result is a normal operating signal, a normal operating prompt message is sent to the monitoring end through the communication unit, indicating that the streetlight is currently in good working condition and can be inspected and maintained according to the regular plan; When the streetlight status classification result is an abnormal operation signal, an abnormal maintenance prompt message is sent to the maintenance personnel receiving end through the communication unit, indicating that the streetlight status is abnormal and requiring the maintenance personnel to check the streetlight lighting data set as soon as possible. Based on the inspection results, maintenance measures such as adjusting lamp parameters, replacing some parts, or conducting circuit inspections are implemented on the streetlight. When the streetlight status classification result is a serious fault signal, an emergency maintenance notice is sent to the maintenance personnel receiving end through the communication unit, indicating that there is a serious abnormality in the streetlight status, requiring maintenance personnel to immediately go to the site to carry out emergency repairs, adopt temporary lighting protection measures and formulate a detailed maintenance plan; Package normal operation prompt information, abnormal maintenance prompt information and emergency maintenance notifications to obtain response decision results.
[0029] The user interaction module is configured to display the normal operation prompt information on a display terminal (such as a large screen in a monitoring center or a management software interface), analyze the lighting dataset, and obtain and display the analysis results. The lighting dataset is analyzed as follows: the normal operation prompt information is displayed on the display terminal, the collected lighting dataset is analyzed, and the analysis results are obtained and displayed; The lighting data set analysis method includes: presetting a data standard threshold interval group, substituting the light intensity data, lamp working status data, energy consumption data, etc. into the corresponding data standard threshold interval for comparison, and outputting the normal state, abnormal state or fault state; When all lighting data sets are normal results, the normal state is output; when there is one or more abnormal results and the rest are normal results, the abnormal state is output; when there is one or more fault results and the rest are normal results or abnormal results, the fault state is output; the normal state, abnormal state and fault state are packaged to obtain analysis results, and the analysis results are intuitively presented through the display terminal, which allows managers to quickly understand the overall operating status of the street lighting system.
[0030] Based on the disclosure and teachings of the above description, those skilled in the art may also make changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and modifications and variations of the present invention should also fall within the scope of protection of the claims of the present invention. In addition, although certain specific terms are used in this description, these terms are only for convenience of description and do not constitute any limitation to the present invention.
Claims
1. A smart street lighting data quality control system, characterized in that: include: A data acquisition module is used to collect and pre-process various data sets related to smart street lighting. The lighting data sets include light intensity data, lamp operating status data, and energy consumption data; A data processing module is used to process the lighting data set to obtain a state reference value, and to classify the data to obtain a street lamp state classification result; An early warning feedback module is used to process the street light status classification result to obtain a response decision result; The user interaction module is used to display normal operation prompt information through the display terminal, analyze the lighting data set, and obtain and display the analysis results.
2. The intelligent street lighting data quality control system according to claim 1, characterized in that: Methods for collecting smart street lighting data sets include: installing light sensors to collect real-time light intensity values of the surrounding environment to obtain light intensity data; Use smart meters to monitor the power consumption of street lights and obtain energy consumption data; Obtain the working status data of the lamp through the information fed back by the lamp controller; Preprocessing methods include data cleaning and data denoising.
3. The intelligent street lighting data quality control system according to claim 1, characterized in that: The steps of processing the lighting data set are as follows: obtaining a lighting state reference value by substituting into the calculation formula: Z = α × G + β × H + γ × N, where G is the light intensity data, H is the lamp working state data, N is the energy consumption data, and α, β, and γ are corresponding weight factors respectively; Collect K groups of historical feature vectors as the sample set, and divide the sample set into a training set of 70%K, a test set of 15%K, and a validation set of 15%K; Establish a state classification model based on the sample set, obtain the historical feature vectors in the training set, preset the normal data cluster L1, alarm data cluster L2 and warning data cluster L3, and randomly select three data points in the training set as the center of the first cluster, representing the higher normal data cluster L1, alarm data cluster L2 and warning data cluster L3 respectively; By substituting the calculation formula: d=∑i=1n(xi−yi)2, the distance between the data items is obtained. The distance between the data items in the training set and the higher data cluster P1, the normal data cluster P2, and the lower data cluster P3 is calculated respectively, and the data items are assigned to the data clusters closest to them. Three new data clusters are obtained as the second cluster centers, where xi and yi are the coordinate values of the data points, xi and yi are the values of the two data points on n sub-data items respectively, and n is the number of sub-data items; Calculate the means of the three new data clusters in the second cluster center respectively, and use them as the new first cluster center for recalculation; Repeat the above steps until the preset number of iterations is reached to obtain a street light status classification model; The feature vector is input into the street light state classification model, and the state reference value is output.
4. The intelligent street lighting data quality control system according to claim 3, characterized in that: The classification method includes: presetting the street light status threshold interval (E1, E2), when the status reference value is less than E1, generating a normal operation signal, when the status reference value is greater than E1 and less than E2, generating an abnormal operation signal, when the status reference value is greater than E2, generating a serious fault signal, the normal operation signal includes a group of fields representing that the street light is in good working condition, the abnormal operation signal includes a group of fields representing that the street light working condition is abnormal but can still maintain basic operation, the serious fault signal includes a group of fields representing that the street light working condition is seriously abnormal and requires immediate maintenance, and the normal operation signal, abnormal operation signal and serious fault signal are packaged to obtain the street light status classification result.
5. The intelligent street lighting data quality control system according to claim 1, characterized in that: The specific method for processing the street light status classification result is as follows: When the streetlight status classification result is a normal operating signal, a normal operating prompt message is sent to the monitoring end through the communication unit, indicating that the streetlight is currently in good working condition and can be inspected and maintained according to the regular plan; When the streetlight status classification result is an abnormal operation signal, an abnormal maintenance prompt message is sent to the maintenance personnel receiving end through the communication unit, indicating that the streetlight status is abnormal and requiring the maintenance personnel to check the streetlight lighting data set as soon as possible. Based on the inspection results, maintenance measures such as adjusting lamp parameters, replacing some parts, or conducting circuit inspections are implemented on the streetlight. When the streetlight status classification result is a serious fault signal, an emergency maintenance notice is sent to the maintenance personnel receiving end through the communication unit, indicating that there is a serious abnormality in the streetlight status, requiring maintenance personnel to immediately go to the site to carry out emergency repairs, adopt temporary lighting protection measures and formulate a detailed maintenance plan; Package normal operation prompt information, abnormal maintenance prompt information and emergency maintenance notifications to obtain response decision results.
6. The intelligent street lighting data quality control system according to claim 1, characterized in that: The lighting data set is analyzed as follows: the normal operation prompt information is displayed on the display terminal, the collected lighting data set is analyzed, and the analysis results are obtained and displayed; The lighting data set analysis method includes: presetting a data standard threshold interval group, substituting the light intensity data, lamp working status data, energy consumption data, etc. into the corresponding data standard threshold interval for comparison, and outputting the normal state, abnormal state or fault state; When all lighting data sets are normal results, the normal state is output; when there is one or more abnormal results and the rest are normal results, the abnormal state is output; when there is one or more fault results and the rest are normal results or abnormal results, the fault state is output; the normal state, abnormal state and fault state are packaged to obtain analysis results, and the analysis results are intuitively presented through the display terminal, which allows managers to quickly understand the overall operating status of the street lighting system.