Street lamp intelligent operation and maintenance optimization management platform based on big data analysis

Abstract

The invention discloses a street lamp intelligent operation and maintenance optimization management platform based on big data analysis, and the platform comprises an obtaining module which is used for obtaining the target data of an intelligent street lamp in a preset time period; the extraction module is used for performing feature extraction on the target data to obtain target features; the evaluation module is used for inputting the target features into a pre-trained big data analysis model for evaluation, and determining an operation and maintenance evaluation value of the intelligent street lamp; the determining module is used for comparing the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold value, and when it is determined that the operation and maintenance evaluation value is smaller than or equal to the preset operation and maintenance evaluation threshold value, the intelligent street lamp serves as an intelligent street lamp to be optimized; the optimization module is used for querying a target optimization strategy of the to-be-optimized smart street lamp and optimizing the to-be-optimized smart street lamp based on the target optimization strategy; the data processing and analysis capability in the street lamp operation and maintenance process is improved, a scientific evaluation system is established, and the operation and maintenance efficiency is improved based on an accurate optimization strategy.

Description

Technical Field

[0001] The present invention relates to the field of intelligent energy-saving street lamp lighting, and in particular to a smart operation and maintenance optimization management platform for street lamps based on big data analysis. Background Art

[0002] With the acceleration of the urbanization process, the scale of the urban lighting system is constantly expanding. As an important part of the urban lighting system, smart street lamps are gradually popularized and widely used in every corner of the city. Intelligent energy-saving street lamps not only have the traditional lighting function, but also integrate a variety of sensors and communication devices, which can realize multiple functions such as intelligent lighting control, environmental monitoring, video monitoring, etc., providing strong support for the intelligent management of the city.

[0003] However, the operation and maintenance management of current intelligent energy-saving street lamps still faces many challenges:

[0004] During the operation of intelligent energy-saving street lamps, a large amount of target data will be generated, such as light intensity, current voltage, fault alarm information, etc. These data contain rich information, but due to the lack of effective data processing and analysis means, most of the data have not been fully utilized. The existing management methods often can only simply store and display the data, and cannot deeply explore the potential problems behind the data, resulting in the inability to timely discover the potential faults and performance degradation trends of street lamps.

[0005] In the traditional operation and maintenance management of street lamps, the evaluation of intelligent energy-saving street lamps mainly relies on manual experience and simple index judgment, lacking a scientific and comprehensive evaluation system. This evaluation method is highly subjective and prone to inaccurate evaluation, and cannot accurately reflect the actual operation status and performance level of smart street lamps. For example, only judging whether a street lamp is working properly based on whether it is lit, while ignoring important indicators such as light intensity and energy consumption, may cause some potential problems to be ignored, affecting the service life and lighting effect of the street lamp.

[0006] Due to the lack of effective data support and scientific evaluation system, the existing operation and maintenance management of street lamps often adopts the methods of regular inspection and after-fact repair. This method not only consumes a large amount of manpower, material resources and time, but also cannot timely discover and solve the fault problems of street lamps, resulting in the inability to timely repair street lamp faults, affecting the urban lighting quality and traffic safety. In addition, for different types of street lamp faults, there is a lack of targeted optimization strategies, and accurate operation and maintenance cannot be achieved, further reducing the operation and maintenance efficiency.

[0007] During the operation and maintenance management of street lights, when problems are found in street lights, a unified processing method is often adopted, lacking personalized optimization strategies for different street lights and different types of faults. This "one-size-fits-all" optimization method cannot fully consider the actual situation and operating environment of street lights, which may lead to poor optimization effects and even new problems. For example, for some street light failures caused by environmental factors, if the impact of environmental factors is not considered and only street light components are replaced, the problem may not be fundamentally solved, and the operation and maintenance costs will increase.

[0008] In summary, the existing intelligent street light operation and maintenance management methods have problems such as insufficient data processing and analysis capabilities, lack of a scientific evaluation system, low operation and maintenance efficiency, and inaccurate optimization strategies, and cannot meet the needs of intelligent and efficient management of urban lighting systems. Therefore, there is an urgent need for a street light intelligent operation and maintenance optimization management platform based on big data analysis to improve the operation and maintenance management level of intelligent street lights and ensure the stable operation of urban lighting systems. Summary of the Invention

[0009] The present invention aims to solve at least one of the technical problems in the above technologies to some extent. For this reason, the object of the present invention is to propose a street light intelligent operation and maintenance optimization management platform based on big data analysis, which can improve the data processing and analysis capabilities during the operation and maintenance of street lights, establish a scientific evaluation system, and improve the operation and maintenance efficiency based on accurate optimization strategies.

[0010] To achieve the above object, an embodiment of the present invention proposes a street light intelligent operation and maintenance optimization management platform based on big data analysis, including:

[0011] An acquisition module, configured to acquire target data of intelligent street lights within a preset time period;

[0012] An extraction module, configured to extract features from the target data to obtain target features;

[0013] An evaluation module, configured to input the target features into a pre-trained big data analysis model for evaluation to determine the operation and maintenance evaluation value of the intelligent street lights;

[0014] A determination module, configured to compare the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold, and when it is determined that the operation and maintenance evaluation value is less than or equal to the preset operation and maintenance evaluation threshold, regard the intelligent street light as a street light to be optimized;

[0015] An optimization module, configured to query the target optimization strategy of the street light to be optimized, and optimize the street light to be optimized based on the target optimization strategy.

[0016] Preferably, the acquisition module includes:

[0017] The first acquisition sub-module is used to acquire the operation data of the intelligent street lamp within a preset time period to obtain the first data;

[0018] The second acquisition sub-module is used to acquire the monitoring image data of the intelligent street lamp within a preset time period to obtain the second data;

[0019] The first determination sub-module is used to use the first data and the second data as the target data of the intelligent street lamp.

[0020] Preferably, it further includes a preprocessing module, which is used to preprocess the target data to obtain preprocessed target data before the extraction module extracts features from the target data to obtain target features.

[0021] Preferably, the preprocessing module includes:

[0022] The data cleaning sub-module is used to clean the first data to obtain the first data after data cleaning;

[0023] The noise reduction sub-module is used to perform image noise reduction on the second data to obtain the second data after noise reduction;

[0024] The second determination sub-module is used to use the first data after data cleaning and the second data after noise reduction as the preprocessed target data.

[0025] Preferably, the data cleaning sub-module includes:

[0026] The segmentation unit is used to:

[0027] Arbitrarily select a type of data in the first data as the target category data;

[0028] Divide the data in the target category data into several target category sub-data evenly based on the time series order;

[0029] The first calculation unit is used to:

[0030] Arbitrarily select a target category sub-data as the first target category sub-data;

[0031] Calculate the anomaly evaluation value corresponding to the first target category sub-data;

[0032] The first determination unit is used to:

[0033] Compare the anomaly evaluation value with a preset evaluation threshold, and when it is determined that the anomaly evaluation value is greater than or equal to the preset evaluation threshold, use the first target category sub-data as the second target category sub-data;

[0034] Traverse all the target category sub-data to obtain several second target category sub-data;

[0035] The second calculation unit is used for:

[0036] Arbitrarily select a second target category sub - data;

[0037] Based on the first preset algorithm, calculate the local fluctuation index of each data point in the second target category sub - data;

[0038] The second determination unit is used for:

[0039] Compare the local fluctuation index of each data point with a preset fluctuation threshold, and take the data points whose local fluctuation index is greater than or equal to the preset fluctuation threshold as abnormal data points;

[0040] Traverse all the second target category sub - data to obtain several abnormal data points;

[0041] The data cleaning unit is used for:

[0042] Delete several abnormal data points to obtain the target category data after data cleaning;

[0043] Traverse all category data in the first data to obtain the first data after data cleaning.

[0044] Preferably, the first calculation unit includes:

[0045] An acquisition subunit for arbitrarily selecting a target category sub - data as the first target category sub - data;

[0046] The first calculation subunit is used for calculating the mean value of the data values corresponding to all data points in the first target category sub - data to obtain the first mean value;

[0047] The second calculation subunit is used for:

[0048] Obtain the target category sub - data adjacent to the first target category sub - data, and calculate the mean value of the data values corresponding to all data points in the first target category sub - data and the target category sub - data adjacent to the first target category sub - data to obtain the second mean value;

[0049] The third calculation subunit is used for:

[0050] Calculate the absolute value of the difference between the first mean value and the second mean value to obtain the first difference value;

[0051] Calculate the range of the data values corresponding to all data points in the first target category sub - data and the target category sub - data adjacent to the first target category sub - data to obtain the second difference value;

[0052] The determination subunit is used for determining the abnormal evaluation value of the first target category sub - data based on the first difference value and the second difference value.

[0053] Preferably, the noise reduction sub-module includes:

[0054] An acquisition unit for:

[0055] Arbitrarily select a monitoring image of a smart street lamp from the second data and perform grayscale processing;

[0056] Divide the monitored image of the smart street lamp after grayscale processing into several sub-images;

[0057] Perform clustering processing on the several sub-images to obtain several sub-image sets;

[0058] Arbitrarily select one sub-image set as the target sub-image set;

[0059] Arbitrarily select one sub-image from the target sub-image set as the target sub-image;

[0060] Arbitrarily select one pixel point from the target sub-image as the first pixel point;

[0061] A third calculation unit for respectively calculating the brightness value and the blurriness value of the first pixel point;

[0062] A comparison unit for comparing the brightness value of the first pixel point with a preset brightness threshold and comparing the blurriness value of the first pixel point with a preset blurriness threshold;

[0063] A third determination unit for:

[0064] When it is determined that the brightness value of the first pixel point is less than the preset brightness threshold and the blurriness value of the first pixel point is greater than the preset blurriness threshold, take the first pixel point as the pixel point to be noise-reduced;

[0065] Traverse all pixel points to obtain several pixel points to be noise-reduced;

[0066] A noise reduction unit for:

[0067] Perform noise reduction on the several pixel points to be noise-reduced based on a filtering algorithm to obtain a noise-reduced target sub-image;

[0068] Based on the target sub-image and the noise-reduced target sub-image, determine the noise reduction amplitude of each pixel point to be noise-reduced in the target sub-image;

[0069] Perform noise reduction on other sub-images in the target sub-image set based on the noise reduction amplitude of each pixel point to be noise-reduced;

[0070] Traverse all sub-image sets to obtain a monitored image of the smart street lamp after noise reduction;

[0071] Traverse all monitored images of smart street lamps in the second data to obtain the second data after noise reduction.

[0072] Preferably, the third calculation unit includes:

[0073] A brightness calculation subunit, configured to:

[0074] Determine a target area centered on the first pixel point with a preset distance as the radius;

[0075] Calculate the grayscale mean value of each pixel point in the target area as the brightness value of the first pixel point;

[0076] A blurriness calculation subunit, configured to:

[0077] Calculate the sum value of the squares of the grayscale differences between the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum value;

[0078] Obtain the total number of other pixel points except the first pixel point in the target area to obtain a target value;

[0079] Take the ratio of the target sum value to the target value as the blurriness value of the first pixel point.

[0080] Preferably, the method for constructing a big data analysis model includes:

[0081] Obtain a big data analysis training data set;

[0082] Train a neural network model based on the big data analysis training data set to obtain an initial big data analysis model;

[0083] Obtain a big data analysis test data set;

[0084] Test the initial big data analysis model based on the big data analysis test data set, and when the test result is qualified, obtain a trained big data analysis model.

[0085] Preferably, the optimization module includes:

[0086] A query sub-module, configured to query a smart operation and maintenance optimization database based on the target features of the smart street lamp to be optimized, and determine the target optimization strategy of the smart street lamp to be optimized;

[0087] An optimization sub-module, configured to optimize the smart street lamp to be optimized based on the target optimization strategy.

[0088] The present invention discloses an intelligent operation and maintenance optimization management platform for street lamps based on big data analysis, which acquires the target data of intelligent street lamps within a preset time period, providing a rich data basis for comprehensively grasping the operation status of street lamps; extracting features from these target data can refine key information from a large amount of data to obtain target features; inputting the target features into a pre-trained big data analysis model for evaluation to determine the evaluation value of the intelligent street lamp; evaluating the target features through the big data analysis model avoids the subjectivity and limitations of traditional evaluation methods that mainly rely on manual experience and simple index judgment; using the powerful analysis ability of the big data analysis model can timely detect potential faults and performance degradation trends of street lamps. For example, by analyzing the energy consumption data of street lamps, it can be found in advance whether there are abnormal energy consumption situations in street lamps, and measures can be taken in a timely manner to avoid the further deterioration of problems; comparing the evaluation value with a preset evaluation threshold can accurately identify the street lamps to be optimized. This accurate identification method avoids the blindness of regular inspections and post-event repairs in traditional operation and maintenance methods, can timely detect the fault problems of street lamps, and improves the timeliness of operation and maintenance. At the same time, querying the target optimization strategy for the street lamps to be optimized can take personalized optimization measures according to the actual conditions and fault types of different street lamps, realizing precise operation and maintenance and improving the operation and maintenance efficiency.

[0089] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification, or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0090] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0091] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification, and are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0092] Figure 1 is a block diagram of an intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to an embodiment of the present invention;

[0093] Figure 2 is a block diagram of an acquisition module according to an embodiment of the present invention;

[0094] Figure 3 is a block diagram of a preprocessing module according to an embodiment of the present invention. Detailed Embodiments

[0095] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0096] Embodiment 1

[0097] As Figure 1 shown, a smart operation and maintenance optimization management platform for street lights based on big data analysis includes:

[0098] An acquisition module, configured to acquire target data of smart street lights within a preset time period;

[0099] An extraction module, configured to extract features from the target data to obtain target features;

[0100] An evaluation module, configured to input the target features into a pre-trained big data analysis model for evaluation to determine the operation and maintenance evaluation value of the smart street lights;

[0101] A determination module, configured to compare the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold, and when it is determined that the operation and maintenance evaluation value is less than or equal to the preset operation and maintenance evaluation threshold, regard the smart street light as a smart street light to be optimized;

[0102] An optimization module, configured to query the target optimization strategy of the smart street light to be optimized, and optimize the smart street light to be optimized based on the target optimization strategy.

[0103] In this embodiment, the target data includes the operation data of the smart street lights and the monitoring image data of the smart street lights.

[0104] In this embodiment, the target features include electrical performance-related features, lighting effect-related features, fault and abnormality-related features, and environment-related features.

[0105] In this embodiment, the big data analysis model is a pre-trained evaluation model.

[0106] The working principle and beneficial effects of the above technical solution are as follows: obtaining the target data of smart street lamps within a preset time period provides a rich data basis for comprehensively grasping the operating status of street lamps; extracting features from these target data can refine key information from a large amount of data to obtain target features; inputting the target features into a pre-trained big data analysis model for evaluation to determine the evaluation value of the smart street lamps; evaluating the target features through the big data analysis model avoids the subjectivity and limitations of traditional evaluation methods that mainly rely on manual experience and simple index judgments; using the powerful analysis ability of the big data analysis model can timely detect potential faults and performance degradation trends of street lamps. For example, by analyzing the energy consumption data of street lamps, it can be determined in advance whether there are abnormal energy consumption situations in the street lamps, and measures can be taken in a timely manner to avoid further deterioration of the problem; comparing the evaluation value with a preset evaluation threshold can accurately identify the smart street lamps to be optimized. This accurate identification method avoids the blindness of regular inspections and post-facto repairs in traditional operation and maintenance methods, can timely detect the fault problems of street lamps, and improves the timeliness of operation and maintenance. At the same time, querying the target optimization strategy for the smart street lamps to be optimized can take personalized optimization measures according to the actual conditions and fault types of different street lamps, realizing precise operation and maintenance and improving the operation and maintenance efficiency.

[0107] Embodiment 2

[0108] As Figure 2 shown, the acquisition module includes:

[0109] The first acquisition sub-module is used to acquire the operation data of the smart street lamps within a preset time period to obtain the first data;

[0110] The second acquisition sub-module is used to acquire the monitoring image data of the smart street lamps within a preset time period to obtain the second data;

[0111] The first determination sub-module is used to use the first data and the second data as the target data of the smart street lamps.

[0112] In this embodiment, the operation data includes the electrical operation data of the street lamps, lighting-related data, street lamp equipment status data, street lamp surrounding environment perception data, etc.

[0113] The beneficial effects of the above technical solution are as follows: through the collaborative work of the first acquisition sub-module and the second acquisition sub-module, it is possible to achieve a comprehensive monitoring of the operating conditions of smart street lamps and the surrounding environment, ensuring the normal operation of the street lamp system and public safety; the integrated target data set of smart street lamps provides rich data support for urban managers, helping them make more scientific and reasonable decisions and improving the efficiency and scientific nature of urban management; by comprehensively acquiring and analyzing the operation data and monitoring image data of smart street lamps, it provides rich data support for urban managers, helping to achieve more scientific and efficient urban management.

[0114] Example 3

[0115] It further includes a preprocessing module, which is used to preprocess the target data to obtain preprocessed target data before the extraction module extracts features from the target data to obtain target features.

[0116] Example 4

[0117] As Figure 3 shown, the preprocessing module includes:

[0118] A data cleaning sub-module, which is used to clean the first data to obtain the first data after data cleaning;

[0119] A noise reduction sub-module, which is used to perform image noise reduction on the second data to obtain the second data after noise reduction;

[0120] A second determination sub-module, which is used to use the first data after data cleaning and the second data after noise reduction as the preprocessed target data.

[0121] The beneficial effects of the above technical solutions are as follows: Through data cleaning and noise reduction processing, the quality of the operation data of smart street lights and the monitoring image data is effectively improved, providing more accurate and reliable data support for subsequent data analysis and decision-making; integrating data cleaning and noise reduction processing into the preprocessing module realizes the fast and efficient processing of raw data and optimizes the data processing process; the preprocessed target data is more accurate and complete, which helps to improve the overall performance of the smart street light system and improve the efficiency and scientificity of urban management; through the collaborative work of each sub-module in the preprocessing module, the comprehensive and efficient preprocessing of raw data is realized, providing a solid foundation for subsequent data analysis and decision-making.

[0122] Example 5

[0123] The data cleaning sub-module includes:

[0124] A segmentation unit, which is used to:

[0125] Arbitrarily select a type of data in the first data as the target category data;

[0126] Evenly divide the data in the target category data into several target category sub-data based on the time series order;

[0127] A first calculation unit, which is used to:

[0128] Arbitrarily select a target category sub-data as the first target category sub-data;

[0129] Calculate the abnormal evaluation value corresponding to the first target category sub-data;

[0130] The first determination unit is configured to:

[0131] Compare the abnormal evaluation value with a preset evaluation threshold, and when it is determined that the abnormal evaluation value is greater than or equal to the preset evaluation threshold, use the first target category sub-data as the second target category sub-data;

[0132] Traverse all the target category sub-data to obtain a number of second target category sub-data;

[0133] The second calculation unit is configured to:

[0134] Arbitrarily select one second target category sub-data;

[0135] Based on a first preset algorithm, calculate the local fluctuation index of each data point in the second target category sub-data;

[0136] The second determination unit is configured to:

[0137] Compare the local fluctuation index of each data point with a preset fluctuation threshold, and use the data points whose local fluctuation index is greater than or equal to the preset fluctuation threshold as abnormal data points;

[0138] Traverse all the second target category sub-data to obtain a number of abnormal data points;

[0139] The data cleaning unit is configured to:

[0140] Delete a number of abnormal data points to obtain the target category data after data cleaning;

[0141] Traverse all the class data in the first data to obtain the first data after data cleaning.

[0142] In this embodiment, the first preset algorithm includes:

[0143]

[0144] Wherein, A b,c represents the local fluctuation index of the c-th data point in the b-th second target category sub-data; Y b,c represents the data value of the c-th data point in the b-th second target category sub-data; Y b,c,x represents the data value of the x-th data point within the neighborhood range of the c-th data point in the b-th second target category sub-data; d b,c,x represents the distance between the c-th data point and the x-th data point within the neighborhood range of the c-th data point in the b-th second target category sub-data; V represents the total number of data points within the neighborhood range of the c-th data point; σ represents a parameter for controlling weight decay; norm() represents a normalization function; exp() represents an exponential function with the natural constant as the base.

[0145] The working principle of the above technical solution is as follows: Arbitrarily select a type of target category data from the first data, and evenly divide the target category data into several target category sub-data based on the time sequence. At this time, the several sub-data also have a sequence order; Arbitrarily select a sub-data as the first target category sub-data, and calculate the anomaly evaluation value of the first target category sub-data. In fact, it is to divide the data into several data blocks, and first judge the anomaly degree between the data blocks, so as to reduce the calculation amount of the overall data cleaning; When it is determined that the anomaly evaluation value is greater than or equal to the preset evaluation threshold, the first target category sub-data is used as the second target category sub-data; Traverse all the target category sub-data to obtain several second target category sub-data; At this time, the screening of the first target category sub-data is completed, and several second target category sub-data are obtained; Identify the abnormal data points in the data of each second target category sub-data, and calculate the local fluctuation index of each data point in each second target category sub-data. Because the data value fluctuation degree of the data points in the continuous operation data is relatively large, the possibility of anomaly is very high, and several abnormal data points are obtained; Delete the several abnormal data points to obtain the target category data after data cleaning; Traverse all types of data in the first data to obtain the first data after data cleaning.

[0146] The beneficial effects of the above technical solution are as follows: The target category data is evenly segmented based on the time series order by the segmentation unit, which helps the subsequent steps to analyze the data in detail. This segmentation method can ensure the uniformity and continuity of the data in the time dimension, providing a solid foundation for calculating the anomaly evaluation value in the subsequent steps; The combined use of the first calculation unit and the second determination unit can accurately identify the target category sub-data with a higher anomaly evaluation value; The second calculation unit further calculates the local fluctuation index of each data point in the second target category sub-data and compares it with the preset fluctuation threshold, so as to accurately identify the abnormal data points; The data cleaning unit obtains the target category data after data cleaning by deleting several abnormal data points. This process not only removes the noise and outliers in the data, but also retains the integrity and coherence of the data, providing a more accurate and reliable data basis for subsequent data analysis and decision-making. Traverse all types of data in the first data to ensure that the entire data set has been effectively cleaned, improving the overall data quality.

[0147] Embodiment 6

[0148] The first calculation unit includes:

[0149] An acquisition subunit, configured to arbitrarily select a target category sub-data as the first target category sub-data;

[0150] The first calculation subunit is configured to calculate the mean value of the data values corresponding to all data points in the first target category sub-data to obtain a first mean value;

[0151] The second calculation subunit is configured to:

[0152] Obtain the target category sub-data adjacent to the first target category sub-data, and calculate the mean value of the data values corresponding to all data points in the first target category sub-data and the target category sub-data adjacent to the first target category sub-data to obtain a second mean value;

[0153] The third calculation subunit is configured to:

[0154] Calculate the absolute value of the difference between the first mean value and the second mean value to obtain a first difference value;

[0155] Calculate the range of the data values corresponding to all data points in the first target category sub-data and the target category sub-data adjacent to the first target category sub-data to obtain a second difference value;

[0156] The determination subunit is configured to determine the anomaly evaluation value of the first target category sub-data based on the first difference value and the second difference value.

[0157] In this embodiment, the anomaly evaluation value of the first target category sub-data includes:

[0158] T = e w + e q

[0159] Wherein, T represents the anomaly evaluation value of the first target category sub-data; e represents the natural constant; w represents the first difference value; q represents the second difference value.

[0160] The working principle of the above technical solution is as follows: The acquisition subunit randomly selects a target category sub-data from the data set as the first target category sub-data. This step is the starting point of data processing and provides the basic data for subsequent calculations; The first calculation subunit calculates the mean value of the data values corresponding to all data points in the first target category sub-data to obtain the first mean value. The mean value is an important indicator to measure the central tendency of the data set and helps to understand the overall distribution of the data; The second calculation subunit further obtains the target category sub-data adjacent to the first target category sub-data and calculates the mean value of the data values corresponding to all data points in these two parts of data to obtain the second mean value. This step considers the continuity of the data in the time series or spatial distribution and helps to capture the changing trend of the data; The third calculation subunit performs two key calculations: one is to calculate the absolute value of the difference between the first mean value and the second mean value to obtain the first difference value; the other is to calculate the range of the data values corresponding to all data points in the first target category sub-data and its adjacent sub-data to obtain the second difference value. The first difference value reflects the degree of change in the mean value of the data, while the second difference value reflects the fluctuation range of the data at the extreme values; The determination subunit comprehensively evaluates the abnormality degree of the first target category sub-data based on the first difference value and the second difference value and gives an abnormality evaluation value. This step is the core of anomaly detection. By comparing the difference value with a preset threshold or standard, it can be determined whether there is an anomaly in the data.

[0161] The beneficial effects of the above technical solution are as follows: By calculating the mean value of the first target category sub-data and the difference between its mean value and that of the adjacent sub-data, the subtle changes in the data in the time series or spatial distribution can be captured. This difference analysis based on the mean value helps to accurately identify the abnormal fluctuations of the data; At the same time, calculating the range further enhances the sensitivity of anomaly detection; The range reflects the difference between the maximum value and the minimum value in the data set and is an important indicator to measure the fluctuation range of the data; Combining the first difference value and the second difference value, the determination subunit can more comprehensively evaluate the abnormality degree of the data; Through parallel computing or pipeline processing, the first calculation unit can efficiently process large-scale data sets; The data transfer and calculation processes between each subunit can be optimized to reduce the calculation time and resource consumption; Accurate anomaly detection helps to timely discover and correct errors or abnormal values in the data, thereby improving the quality and reliability of the data. This is crucial for subsequent data analysis and decision-making processes; The design of the first calculation unit provides strong support for the data anomaly detection task by improving the accuracy of anomaly detection, enhancing the flexibility of data processing, increasing the data processing efficiency, promoting the improvement of data quality, and supporting various application scenarios. This design not only improves the efficiency and accuracy of data processing but also provides a reliable basis for subsequent data analysis and decision-making.

[0162] Embodiment 7

[0163] The noise reduction sub-module includes:

[0164] An acquisition unit for:

[0165] Arbitrarily select a monitoring image of a smart street lamp from the second data and perform grayscale processing;

[0166] Divide the monitoring image of the smart street lamp after grayscale processing into several sub-images;

[0167] Perform clustering processing on the several sub-images to obtain several sub-image sets;

[0168] Arbitrarily select a sub-image set as the target sub-image set;

[0169] Arbitrarily select a sub-image from the target sub-image set as the target sub-image;

[0170] Arbitrarily select a pixel point from the target sub-image as the first pixel point;

[0171] A third calculation unit for respectively calculating the brightness value and the blurriness value of the first pixel point;

[0172] A comparison unit for comparing the brightness value of the first pixel point with a preset brightness threshold and comparing the blurriness value of the first pixel point with a preset blurriness threshold;

[0173] A third determination unit for:

[0174] When it is determined that the brightness value of the first pixel point is less than the preset brightness threshold and the blurriness value of the first pixel point is greater than the preset blurriness threshold, take the first pixel point as the pixel point to be denoised;

[0175] Traverse all pixel points to obtain several pixel points to be denoised;

[0176] A denoising unit for:

[0177] Perform denoising on the several pixel points to be denoised based on a filtering algorithm to obtain a denoised target sub-image;

[0178] Based on the target sub-image and the denoised target sub-image, determine the denoising amplitude of each pixel point to be denoised in the target sub-image;

[0179] Perform denoising on other sub-images in the target sub-image set based on the denoising amplitude of each pixel point to be denoised;

[0180] Traverse all sub-image sets to obtain a denoised monitoring image of the smart street lamp;

[0181] Traverse all monitoring images of smart street lamps in the second data to obtain denoised second data.

[0182] In this embodiment, the filtering algorithm includes, but is not limited to, the median filtering algorithm and the mean filtering algorithm.

[0183] The working principle of the above technical solution is as follows: Arbitrarily select a monitoring image of a smart street lamp from the second data and perform grayscale processing; divide the monitoring image of the smart street lamp after grayscale processing into several sub-images; perform clustering processing on the several sub-images to obtain several sub-image sets; the purpose of clustering is to divide the parts with similar content in the monitoring image into one category to obtain several sub-image sets. By denoising one sub-image in the set, a denoising coefficient is obtained, and the same denoising processing is performed on other sub-images in the same set based on the denoising coefficient; the third calculation unit screens the first pixel point by calculating the brightness value and the blurriness value of the first pixel point to obtain several pixel points to be denoised; denoise the pixel points to be denoised based on the filtering algorithm.

[0184] The beneficial effects of the above technical solution are as follows: Through grayscale processing, sub-image division, and clustering processing, this module can efficiently process a large number of monitoring images of smart street lamps; this processing method not only reduces the computational complexity but also improves the efficiency of image processing; by calculating the brightness value and the blurriness value of the pixel points and comparing them with the preset threshold, this module can accurately identify the pixel points that need to be denoised. This method avoids blindly denoising all pixel points, thereby improving the pertinence and effect of denoising; by denoising the identified pixel points to be denoised based on the filtering algorithm, this module can intelligently remove the noise in the image. At the same time, by determining the denoising amplitude and denoising other sub-images, this module can ensure that the denoising effects of the entire target sub-image set are consistent, improving the overall quality of the image.

[0185] Embodiment 8

[0186] The third calculation unit includes:

[0187] The brightness calculation sub-unit is used for:

[0188] Taking the first pixel point as the center, determining a target area with a preset distance as the radius;

[0189] Calculating the grayscale mean value of each pixel point in the target area as the brightness value of the first pixel point;

[0190] The blurriness calculation sub-unit is used for:

[0191] Calculating the sum value of the squares of the grayscale differences between the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum value;

[0192] Obtaining the total number of other pixel points except the first pixel point in the target area to obtain a target value;

[0193] Take the ratio of the target sum and value to the target numerical value as the blur value of the first pixel point.

[0194] The beneficial effects of the above technical solution are as follows: The brightness calculation subunit determines a target area with the first pixel point as the center and a preset distance as the radius, and calculates the grayscale average value of all pixel points in this area as the brightness value of the first pixel point; this method can more accurately reflect the average brightness situation around the first pixel point and avoid the error that may be brought by the brightness value of a single pixel point; the blur calculation subunit obtains the blur value of the first pixel point by calculating the sum of the squares of the grayscale differences between the first pixel point and other pixel points except the first pixel point in the target area, and then dividing it by the total number of pixel points except the first pixel point in the target area; this calculation method can quantify the degree of grayscale difference between the first pixel point and its surrounding pixel points, thereby effectively evaluating the blur degree of the image; through accurate brightness calculation and effective blur evaluation, this technical solution can more accurately identify the pixel points that need noise reduction. This helps to improve the accuracy of noise reduction processing, avoid overprocessing clear pixel points, and ensure that blurred pixel points are fully processed for noise reduction.

[0195] Embodiment 9

[0196] A method for constructing a big data analysis model includes:

[0197] Obtain a big data analysis training data set;

[0198] Train a neural network model based on the big data analysis training data set to obtain an initial big data analysis model;

[0199] Obtain a big data analysis test data set;

[0200] Test the initial big data analysis model based on the big data analysis test data set, and when the test result is qualified, obtain a trained big data analysis model.

[0201] In this embodiment,

[0202]

[0203] where φ i represents the first evaluation value of the intelligent street lamp at the i-th moment; U i represents the voltage value at both ends of the intelligent street lamp at the i-th moment; I i represents the current value at both ends of the intelligent street lamp at the i-th moment; R i represents the internal resistance value of the intelligent street lamp at the i-th moment; t1 represents the time value that the intelligent street lamp has been used, t2 represents the ideal use time of the intelligent street lamp; α represents the aging coefficient of the intelligent street lamp; represents the theoretical remaining service life of the intelligent street lamp; δ represents the number of failures of the intelligent street lamp;

[0204] Obtain the output power and rated power of the smart street lamp;

[0205] Take the ratio of the output power to the rated power as the lighting output index of the smart street lamp;

[0206] Arbitrarily select a monitoring image of the smart street lamp, and obtain the moving speed of the moving objects in each lane of the monitoring image; Determine the moving distance of the moving objects in each lane based on the moving speed of the moving objects in each lane and the unit time; Divide each lane with the moving distance of the moving objects as the length and the width of the corresponding lane as the width to determine the target area corresponding to each lane;

[0207] Calculate the lighting demand index of each lane based on a preset algorithm;

[0208]

[0209] where, C i,a represents the lighting demand index of the ath lane in the monitoring image of the smart street lamp corresponding to the ith moment; v represents the moving speed of the moving objects in the ath lane; θ represents the direction of the line connecting the center point of the current moving object and the center point in the current target area, and the included angle between this line direction and the driving direction of the moving object; l represents the distance between the center point of the current moving object and the center point in the current target area; b represents the natural constant;

[0210] Take the average value of the lighting demand indexes of all lanes as the lighting demand index of the smart street lamp;

[0211] Take the ratio of the lighting demand index of the smart street lamp to the lighting output index of the smart street lamp as the second evaluation value of the smart street lamp;

[0212] Obtain the preset weight value;

[0213] Determine the operation and maintenance evaluation value of the smart street lamp based on the first evaluation value, the second evaluation value and the preset weight value of the smart street lamp;

[0214]

[0215] where, P represents the operation and maintenance evaluation value of the smart street lamp; φ i represents the first evaluation value of the smart street lamp at the ith moment; β1 represents the first preset weight; n represents the total number of moments in the target data; C i,a represents the lighting demand index of the ath lane in the monitoring image of the smart street lamp corresponding to the ith moment; m represents the total number of lanes in the monitoring image; β2 represents the second preset weight, and β1 + β2 = 1.

[0216] The beneficial effects of the above technical solution are as follows: The construction method of the big data analysis model improves the accuracy of the operation and maintenance evaluation value of the intelligent street lamp through multiple aspects such as targeted training, accurate performance evaluation, improvement of generalization ability, optimization of business processes, and promotion of a data-driven decision-making culture.

[0217] Embodiment 10

[0218] The optimization module includes:

[0219] A query sub-module for querying the intelligent operation and maintenance optimization database based on the target features of the intelligent street lamp to be optimized, and determining the target optimization strategy for the intelligent street lamp to be optimized;

[0220] An optimization sub-module for optimizing the intelligent street lamp to be optimized based on the target optimization strategy.

[0221] The beneficial effects of the above technical solution are as follows: The query sub-module can quickly query and determine the target optimization strategy in the intelligent operation and maintenance optimization database based on the target features of the intelligent street lamp to be optimized; this process avoids the cumbersome process of manually analyzing and judging the optimization strategy in the traditional method, and significantly improves the optimization efficiency; with the support of the intelligent operation and maintenance optimization database, the query sub-module can obtain the optimization strategy that matches the target features of the intelligent street lamp to be optimized.

[0222] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A smart operation and maintenance optimization management platform for street lights based on big data analysis, characterized in that, Including: An acquisition module, configured to acquire target data of smart street lights within a preset time period; An extraction module, configured to extract features from the target data to obtain target features; An evaluation module, configured to input the target features into a pre-trained big data analysis model for evaluation to determine the operation and maintenance evaluation value of the smart street lights; A determination module, configured to compare the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold, and when it is determined that the operation and maintenance evaluation value is less than or equal to the preset operation and maintenance evaluation threshold, use the smart street lights as the smart street lights to be optimized; An optimization module, configured to query the target optimization strategy of the smart street lights to be optimized, and optimize the smart street lights to be optimized based on the target optimization strategy.

2. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 1, characterized in that, The acquisition module includes: A first acquisition sub-module, configured to acquire the operation data of the smart street lights within a preset time period to obtain first data; A second acquisition sub-module, configured to acquire the monitoring image data of the smart street lights within a preset time period to obtain second data; A first determination sub-module, configured to use the first data and the second data as the target data of the smart street lights.

3. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 2, characterized in that, It further includes a preprocessing module, configured to preprocess the target data to obtain preprocessed target data before the extraction module extracts features from the target data to obtain target features.

4. The intelligent operation and maintenance optimization management platform for street lights based on big data analysis according to claim 3, wherein The preprocessing module includes: A data cleaning sub-module, configured to clean the first data to obtain the first data after data cleaning; A noise reduction sub-module, configured to perform image noise reduction on the second data to obtain the second data after noise reduction; A second determination sub-module, configured to use the first data after data cleaning and the second data after noise reduction as the preprocessed target data.

5. The intelligent operation and maintenance optimization management platform for street lights based on big data analysis according to claim 4, characterized in that The data cleaning sub-module includes: A segmentation unit, configured to: Arbitrarily select a type of data in the first data as target category data; Evenly divide the data in the target category data into several target category sub-data based on the time series order; A first calculation unit, configured to: Arbitrarily select a target category sub-data as the first target category sub-data; Calculate the anomaly evaluation value corresponding to the first target category sub-data; A first determination unit, configured to: Compare the anomaly evaluation value with a preset evaluation threshold, and when it is determined that the anomaly evaluation value is greater than or equal to the preset evaluation threshold, use the first target category sub-data as the second target category sub-data; Traverse all the target category sub-data to obtain several second target category sub-data; A second calculation unit, configured to: Arbitrarily select a second target category sub-data; Calculate the local fluctuation index of each data point in the second target category sub-data based on a first preset algorithm; A second determination unit, configured to: Compare the local fluctuation index of each data point with a preset fluctuation threshold, and use the data points whose local fluctuation index is greater than or equal to the preset fluctuation threshold as anomaly data points; Traverse all the second target category sub-data to obtain several anomaly data points; A data cleaning unit, configured to: Delete the several anomaly data points to obtain the target category data after data cleaning; Traverse all types of data in the first data to obtain the first data after data cleaning.

6. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 5, characterized in that The first calculation unit includes: An obtaining subunit, configured to arbitrarily select a target category sub-data as the first target category sub-data; A first calculation subunit, configured to calculate the mean value of the data values corresponding to all data points in the first target category sub-data to obtain a first mean value; A second calculation subunit, configured to: Obtain the target category sub-data adjacent to the first target category sub-data, and calculate the mean value of the data values corresponding to all data points in the first target category sub-data and the target category sub-data adjacent to the first target category sub-data to obtain a second mean value; A third calculation subunit, configured to: Calculate the absolute value of the difference between the first mean value and the second mean value to obtain a first difference value; Calculate the range of the data values corresponding to all data points in the first target category sub-data and the target category sub-data adjacent to the first target category sub-data to obtain a second difference value; A determination subunit, configured to determine the anomaly evaluation value of the first target category sub-data based on the first difference value and the second difference value.

7. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 4, characterized in that A noise reduction sub-module, including: An obtaining unit, configured to: Arbitrarily select a monitoring image of a smart street lamp in the second data and perform grayscale processing; Divide the monitoring image of the smart street lamp after grayscale processing into several sub-images; Perform clustering processing on the several sub-images to obtain several sub-image sets; Arbitrarily select a sub-image set as the target sub-image set; Arbitrarily select a sub-image in the target sub-image set as the target sub-image; Arbitrarily select a pixel point in the target sub-image as the first pixel point; A third calculation unit, configured to calculate the brightness value and the blurriness value of the first pixel point respectively; A comparison unit, configured to compare the brightness value of the first pixel point with a preset brightness threshold and compare the blurriness value of the first pixel point with a preset blurriness threshold; A third determination unit, configured to: When it is determined that the brightness value of the first pixel point is less than the preset brightness threshold and the blurriness value of the first pixel point is greater than the preset blurriness threshold, use the first pixel point as the pixel point to be noise-reduced; Traverse all pixel points to obtain several pixel points to be noise-reduced; A noise reduction unit, configured to: Perform noise reduction on the several pixel points to be noise-reduced based on a filtering algorithm to obtain a noise-reduced target sub-image; Determine the noise reduction amplitude of each pixel point to be noise-reduced in the target sub-image based on the target sub-image and the noise-reduced target sub-image; Perform noise reduction on other sub-images in the target sub-image set based on the noise reduction amplitude of each pixel point to be noise-reduced; Traverse all sub-image sets to obtain a noise-reduced monitoring image of the smart street lamp; Traverse all monitoring images of the smart street lamp in the second data to obtain a noise-reduced second data.

8. The intelligent operation and maintenance optimization management platform for street lights based on big data analysis according to claim 7, characterized in that, A third calculation unit, including: A brightness calculation subunit, configured to: With the first pixel point as the center, determine a target area with a preset distance as the radius; Calculate the grayscale mean value of each pixel point in the target area as the brightness value of the first pixel point; A blurriness calculation subunit, configured to: Calculate the sum value of the squares of the grayscale differences between the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum value; Obtain the total number of other pixel points except the first pixel point in the target area to obtain a target value; Use the ratio of the target sum value to the target value as the blurriness value of the first pixel point.

9. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 1, characterized in that Method for constructing big data analysis model, including: Obtain big data analysis training data set; Train a neural network model based on the big data analysis training data set to obtain an initial big data analysis model; Obtain big data analysis test data set; Test the initial big data analysis model based on the big data analysis test data set. When the test result is qualified, obtain the trained big data analysis model.

10. The intelligent operation and maintenance optimization management platform for street lamps based on big data analysis according to claim 1, characterized in that Optimization module, including: Query sub-module, used to query the intelligent operation and maintenance optimization database based on the target features of the intelligent street lamp to be optimized, and determine the target optimization strategy of the intelligent street lamp to be optimized; Optimization sub-module, used to optimize the intelligent street lamp to be optimized based on the target optimization strategy.

Images