Digital LED lighting quality assessment method and system

Abstract

The present invention relates to the technical field of lighting quality detection, and in particular to a digital LED lighting quality assessment method and system, which can more comprehensively and objectively assess the LED lighting quality, improve the lighting quality, ensure visual health and enhance energy efficiency; the method comprises: acquiring detection data and lighting environment data in a historical LED device detection process, wherein the detection data and the lighting environment data correspond one to one; the detection data comprises an LED device lighting quality assessment result and LED device lighting data; extracting parameter features affecting the lighting quality from the LED device lighting data, and obtaining an LED device lighting feature set, wherein the LED device lighting feature set comprises luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation and dimming performance; extracting environmental features affecting the lighting quality from the lighting environment data, and obtaining a lighting environment impact feature set.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting quality detection, and in particular to a digital LED lighting quality evaluation method and system. Background Art

[0002] Lighting quality assessment is an important research topic in the field of lighting engineering. It is of great significance to improve people's quality of life, ensure visual health and improve energy efficiency. Traditional lighting quality assessment methods are mainly based on manual detection and experience judgment, which have limitations such as strong subjectivity and low efficiency. With the development of digital and intelligent technology, digital LED lighting systems have been widely used in urban lighting, indoor lighting and other fields, and the demand for automatic assessment of digital LED lighting quality is becoming increasingly urgent.

[0003] Existing digital LED lighting quality assessment methods are mainly based on statistics and pattern recognition technology, and quality assessment is performed by extracting simple parameters such as brightness and color temperature of LED devices. However, this method ignores the impact of the lighting environment on lighting quality and is difficult to fully reflect the true situation of lighting quality. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a digital LED lighting quality evaluation method which can more comprehensively and objectively evaluate the LED lighting quality, improve the lighting quality, ensure visual health and enhance energy utilization efficiency.

[0005] In a first aspect, the present invention provides a method for evaluating the quality of digital LED lighting, the method comprising:

[0006] Acquire the detection data and lighting environment data in the historical LED device detection process, wherein the detection data and lighting environment data correspond to each other one by one; the detection data includes the LED device lighting quality assessment result and the LED device lighting data;

[0007] Extracting parameter features that affect lighting quality from the LED device lighting data to obtain a set of LED device lighting features, wherein the set of LED device lighting features includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation, and dimming performance;

[0008] Extracting environmental features that affect lighting quality from the lighting environment data to obtain a lighting environment impact feature set, wherein the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particulate matter concentration;

[0009] Combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space to obtain lighting quality assessment factor features;

[0010] The lighting quality assessment factor features and the corresponding LED equipment lighting quality assessment results are associated and used as training data sets for deep learning training to build an LED equipment lighting quality assessment model.

[0011] The lighting quality assessment factor characteristics of the LED device to be evaluated are obtained in real time, and the lighting quality assessment factor characteristics obtained in real time are input into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be evaluated.

[0012] Furthermore, the LED device is provided with sensors, including light sensors, color sensors, temperature sensors, photometers, radiometers, spectroradiometers, humidity sensors and particle counters.

[0013] Furthermore, the LED device lighting feature set extraction method includes:

[0014] Calculate the change trend of luminous flux from the historical lighting data of LED equipment through time series data;

[0015] Use the color sensor inside the LED device to obtain the color temperature value;

[0016] Use the color sensor inside the LED device to measure the color of different areas and calculate the color uniformity index;

[0017] Record the color data of LED lighting under different conditions, analyze its consistency with the real color, and obtain color reproducibility;

[0018] The wavelength spectrum distribution was recorded using a spectroradiometer on the LED device;

[0019] Get beam angle information from LED device specifications;

[0020] Analyze the luminous flux data in the historical records of LED equipment and calculate the light attenuation ratio;

[0021] The dimming data recorded by the LED device is used to analyze its performance at different brightness levels and obtain the dimming performance of the LED device.

[0022] Furthermore, the lighting environment impact feature set extraction method includes:

[0023] Use the LED device's external temperature sensor to measure the ambient temperature in real time and match it with the LED device's lighting data;

[0024] Use a photometer to measure the ambient illumination and record the lighting data of the corresponding LED equipment;

[0025] Use the LED device's external humidity sensor to monitor the ambient humidity in real time and match it with the LED device's lighting data;

[0026] The concentration of suspended particulate matter in the environment is monitored in real time through a particle counter, which corresponds to the lighting data of the LED device.

[0027] Furthermore, the method for acquiring characteristics of lighting quality assessment factors includes:

[0028] Perform data alignment on the LED device lighting feature set and the lighting environment impact feature set;

[0029] Through feature splicing technology, the LED device lighting feature set and the lighting environment impact feature set are combined;

[0030] Normalize the combined data;

[0031] Remove redundant and irrelevant features from the combined data and perform feature selection;

[0032] The integrated feature set is regarded as the lighting quality assessment factor feature.

[0033] Furthermore, the method for constructing the LED equipment lighting quality assessment model includes:

[0034] Acquire lighting quality assessment factor characteristics and corresponding LED device lighting quality assessment results, associate the lighting quality assessment factor characteristics with the corresponding LED device lighting quality assessment results, and obtain a model training data set;

[0035] Clean the training data, handle missing values ​​and outliers, and standardize and normalize the data;

[0036] Based on the complexity of the task, the characteristics of the data, and the expected output, a recurrent neural network was chosen as the basis for the deep learning model;

[0037] Use the training data set to train the selected deep learning model and continuously optimize the model parameters through the back-propagation algorithm;

[0038] Adjust the model's hyperparameters through cross-validation techniques to improve the model's performance and generalization capabilities;

[0039] Choose to use loss function and optimizer to minimize the error during training and accelerate model convergence;

[0040] Use the validation set to evaluate the model’s performance on unseen data and make further adjustments to the model.

[0041] After training, the model is deployed in practical applications to perform real-time evaluation of the lighting quality of the LED devices to be evaluated.

[0042] Furthermore, the method for obtaining the lighting quality evaluation result of the LED device to be evaluated includes:

[0043] Use LED device sensors to obtain real-time detection data and lighting environment data of the LED device to be evaluated;

[0044] Extract parameter features that affect lighting quality from real-time LED device lighting data to obtain a real-time LED device lighting feature set;

[0045] Extract environmental features that affect lighting quality from real-time lighting environment data to obtain a real-time lighting environment influencing feature set;

[0046] Combine the real-time LED equipment lighting feature set with the real-time lighting environment impact feature set in the same time and space to obtain the real-time lighting quality assessment factor features;

[0047] The real-time lighting quality assessment factor characteristics are input into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be evaluated.

[0048] On the other hand, the present application also provides a digital LED lighting quality assessment system, the system comprising:

[0049] Historical data acquisition module: used to obtain the detection data and lighting environment data in the historical LED equipment detection process, and the detection data and lighting environment data correspond one to one; the detection data includes the LED equipment lighting quality evaluation results and LED equipment lighting data, and is sent;

[0050] Lighting feature extraction module: used to receive LED device lighting data, extract parameter features that affect lighting quality from the LED device lighting data, obtain a set of LED device lighting features, and send the set; the LED device lighting feature set includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation and dimming performance;

[0051] Environmental feature extraction module: used to receive lighting environment data, extract environmental features that affect lighting quality from the lighting environment data, obtain a lighting environment impact feature set, and send it; the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particle concentration;

[0052] Data combining module: used for receiving the LED device lighting feature set and the lighting environment impact feature set, combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space, obtaining the lighting quality assessment factor features, and sending them;

[0053] Deep learning training module: used to receive the lighting quality assessment factor features and the LED equipment lighting quality assessment results, associate the lighting quality assessment factor features with the corresponding LED equipment lighting quality assessment results, use them as training data sets for deep learning training, build an LED equipment lighting quality assessment model, and send it;

[0054] Real-time data acquisition module: used to acquire the lighting quality assessment factor characteristics of the LED device to be assessed in real time and send them;

[0055] The real-time evaluation module is used to receive the LED device lighting quality evaluation model and the lighting quality evaluation factor characteristics of the LED device to be evaluated in real time, input the lighting quality evaluation factor characteristics obtained in real time into the LED device lighting quality evaluation model, and obtain the lighting quality evaluation result of the LED device to be evaluated.

[0056] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0057] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0058] Compared with the prior art, the present invention has the following beneficial effects: the method combines the LED device lighting data and the lighting environment data, obtains data from multiple aspects, and extracts multiple parameter features that affect the lighting quality, thereby improving the comprehensiveness of the evaluation; by combining the LED device lighting features and the lighting environment impact features as lighting quality evaluation factor features, then associating these factors with the LED device lighting quality evaluation results and using them for deep learning training, an LED device lighting quality evaluation model is established, which can more effectively utilize data and improve the accuracy and reliability of the evaluation model;

[0059] The method allows the real-time acquisition of the lighting quality assessment factor features of the LED device to be evaluated, and these features are input into the evaluation model in real time, so as to obtain the lighting quality evaluation results of the LED device to be evaluated, and can timely detect and adjust the working state of the LED lighting system, thereby improving the application flexibility of the system; the method utilizes more objective data and deep learning models, can more accurately evaluate the LED lighting quality, and avoids the deviation caused by subjective judgment; the method is applicable to various LED lighting scenarios, provides scalability for future technological development, and can add new features and data as needed to improve the accuracy and comprehensiveness of the evaluation;

[0060] In summary, this method overcomes the limitations of traditional methods and can more comprehensively and objectively evaluate the quality of LED lighting, improve lighting quality, ensure visual health, and improve energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flow chart of the present invention;

[0062] Figure 2 is a flow chart of a method for constructing a lighting quality assessment model for LED equipment;

[0063] Figure 3 It is a structural diagram of a digital LED lighting quality evaluation system. DETAILED DESCRIPTION

[0064] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0065] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0066] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0067] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0068] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0069] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0070] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0071] The present application is described below in conjunction with the drawings in the present application.

[0072] Embodiment 1: Figure 1 to Figure 2 As shown, the digital LED lighting quality evaluation method of the present invention specifically includes the following steps:

[0073] S1. Acquire the detection data and lighting environment data in the historical LED device detection process, wherein the detection data and lighting environment data correspond to each other one by one; the detection data includes the LED device lighting quality assessment result and the LED device lighting data;

[0074] The LED device is provided with a sensor inside, and the sensor includes:

[0075] A light sensor is deployed inside the LED device and is used to measure light intensity, thereby obtaining luminous flux information of the LED device;

[0076] A color sensor is deployed inside the LED device and is used to measure the color information of the LED device, including color temperature, color uniformity, and color reproducibility;

[0077] A temperature sensor is integrated in the LED device to monitor the temperature of the LED when it is working;

[0078] The LED device is provided with a detection device outside, and the LED device external detection device is connected to the LED lamp through a communication protocol, and the LED device external detection device includes:

[0079] photometers and radiometers, which measure the intensity, wavelength, and distribution of light;

[0080] spectroradiometers, which analyze the wavelength and spectral characteristics of light;

[0081] Based on the communication interface, the LED device transmits real-time data to the central data acquisition system; using the Internet of Things technology, the LED device is connected to the cloud platform through the Internet to transmit the LED device lighting data in real time; using the database to store the LED device lighting data to ensure the security and accessibility of the data;

[0082] The lighting environment data collection method comprises:

[0083] S11. Using an external sensor to collect data of the lighting environment, the sensor comprising:

[0084] Light sensor, used to measure the light intensity in the environment;

[0085] Temperature sensor, used to monitor ambient temperature;

[0086] Humidity sensor, used to detect the ambient humidity level;

[0087] Particle counters, used to measure the concentration of suspended particles in the air;

[0088] S12. Establish an environmental monitoring system, integrate multiple sensors to monitor lighting environment data in real time, and continuously collect, store and analyze environmental data;

[0089] S13. Use a data logger to regularly record environmental data and obtain more comprehensive environmental data;

[0090] S14. Based on Internet technology, environmental data is monitored in real time through remote data transmission, allowing remote access and real-time data analysis to achieve timely monitoring and management of the lighting environment.

[0091] In this step, the combination of internal sensors and external detection devices of LED equipment can provide multi-dimensional data, which is helpful for comprehensive evaluation of LED lighting quality. Through the collection and analysis of these data, the performance of LED equipment can be evaluated more accurately. LED equipment transmits real-time data to the central data acquisition system through the communication interface, which can monitor the operating status of LED equipment in real time. At the same time, various sensors of the lighting environment can also monitor environmental data in real time, and regularly record environmental data through data loggers to ensure the integrity and accuracy of the data.

[0092] Establish an environmental monitoring system and continuously collect data to enable long-term tracking of the performance of LED equipment and the status of the lighting environment; by analyzing historical data, potential problems and improvement points can be discovered, and targeted improvement measures can be implemented to improve the efficiency and performance of the LED lighting system;

[0093] Based on Internet technology, remote access and real-time analysis of LED equipment lighting data and lighting environment data are realized, which is conducive to remote management and decision-making; users can monitor and analyze the operating status of the lighting system anytime and anywhere, find problems in time and take corresponding measures; real-time data transmission and storage through cloud platforms and databases can ensure the security and accessibility of LED equipment lighting data and environmental data; thus, potential safety hazards can be found in time, and necessary safety and reliability maintenance can be carried out on the system;

[0094] In summary, this step can provide more comprehensive and accurate data support for the evaluation, monitoring and management of LED lighting systems, thereby promoting the improvement of lighting quality and energy efficiency.

[0095] S2. Extracting parameter features that affect lighting quality from the LED device lighting data to obtain a set of LED device lighting features, wherein the set of LED device lighting features includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation, and dimming performance;

[0096] The purpose of step S2 is to extract parameter features that affect lighting quality from the lighting data of the LED device to form a set of LED device lighting features. These features are key factors in evaluating the quality of LED lighting. By conducting in-depth analysis of these features, the performance and behavior of the LED device under different conditions can be accurately reflected. The method for extracting the set of LED device lighting features includes:

[0097] S21. Luminous flux is the total amount of light emitted by an LED device, measured in lumens. The trend of luminous flux is calculated from the historical lighting data of the LED device using time series data.

[0098] S22. Color temperature describes the color of light and affects the overall feeling of the lighting environment. Extracting color temperature characteristics helps to understand the color performance of LED devices. Use the color sensor inside the LED device to obtain the color temperature value.

[0099] S23. Color uniformity refers to the uniformity of the color distribution of the light emitted by the LED device within the lighting area. Extracting the color uniformity feature helps to understand the color consistency of LED lighting in different areas. Use the color sensor inside the LED device to measure the color of different areas and calculate the color uniformity index.

[0100] S24. Color reproducibility is used to evaluate the ability of LED devices to reproduce true colors under different conditions; record the color data of LED devices lighting under different conditions and analyze its consistency with the true color;

[0101] S25, wavelength spectrum distribution describes the light intensity distribution of the LED light source at different wavelengths, which is used for realism and color quality; the wavelength spectrum distribution is recorded using a spectroradiometer outside the LED device;

[0102] S26. The beam angle indicates the range of light divergence, which will affect the layout of the lighting area and the lighting effect; the beam angle information is obtained from the LED equipment specifications;

[0103] S27. Light attenuation measures the degree of reduction in the luminous flux of LED equipment during use. Extracting light attenuation characteristics helps to understand the lifespan and performance stability of LED equipment; analyzing the luminous flux data in the historical records of LED equipment and calculating the attenuation ratio;

[0104] S28. Dimming performance is used to evaluate the performance of LED devices at different dimming levels. Extracting dimming performance characteristics helps to understand the performance of LED devices when flexibly adjusting brightness; using the dimming data recorded by LED devices, analyze their performance at different brightness levels.

[0105] In this step, by extracting multiple features, the evaluation model is no longer limited to simple parameters, but can comprehensively consider the performance of LED devices in different aspects; while considering the characteristics of the lighting environment, these features extracted in this step make the evaluation closer to the actual usage scenario;

[0106] Using time series data to calculate the trend of luminous flux and analyze color temperature changes in historical data can help understand the evolution of LED device performance over time, thereby predicting possible problems in advance and providing more effective means for maintenance and management;

[0107] Taking into account the light attenuation characteristics, we can better understand the stability and life of the luminous flux of LED devices during long-term use, and improve the accuracy of the evaluation; by quantitatively extracting various features, we can free the lighting quality from subjective manual detection and empirical judgment, and achieve a more objective and quantifiable LED lighting quality evaluation; these extracted feature sets will serve as inputs to the deep learning model, which will help build a more complex and intelligent LED device lighting quality evaluation model, and further improve the accuracy and generalization of the evaluation;

[0108] In summary, step S2 makes the LED equipment lighting quality assessment more comprehensive and accurate through multi-faceted feature extraction, and provides a rich data basis for subsequent steps, realizing the automatic evaluation of digital LED lighting systems, improving people's quality of life, ensuring visual health, and promoting the improvement of energy efficiency.

[0109] S3. Extracting environmental features that affect lighting quality from the lighting environment data to obtain a lighting environment impact feature set, wherein the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particulate matter concentration;

[0110] In step S3, the lighting environment impact features are extracted to fully consider the impact of the external environment on the performance of LED equipment when evaluating the lighting quality; the lighting environment impact feature set extraction method includes:

[0111] S31. Ambient temperature will affect the luminous efficiency and stability of LED light sources. Higher ambient temperature will reduce LED power and accelerate light attenuation. Use an external temperature sensor on the LED device to measure the ambient temperature in real time and match it with the lighting data of the LED device.

[0112] S32. Ambient illumination will directly affect the lighting effect of LED lamps. Under different lighting requirements, changes in illumination levels will lead to changes in LED brightness and color performance. Use a photometer to measure ambient illumination and record the lighting data of the corresponding LED equipment.

[0113] S33. Ambient humidity will affect the heat dissipation and dustproof performance of LED devices, thus affecting their performance and lifespan. Use an external humidity sensor on the LED device to monitor the ambient humidity in real time and match it with the lighting data of the LED device.

[0114] S34. The concentration of suspended particles in the environment will affect the propagation of light, causing light attenuation, scattering and absorption, which in turn affects the brightness and clarity of LED lighting. The concentration of suspended particles in the environment is monitored in real time through a particle counter, which corresponds to the lighting data of the LED equipment.

[0115] In this step, multiple environmental factors such as ambient temperature, ambient illumination, ambient humidity and ambient suspended particulate matter concentration are taken into account, making the LED equipment lighting quality assessment more comprehensive and able to more truly reflect the performance of LEDs in actual use environments;

[0116] By using external sensors, it is possible to monitor changes in environmental parameters in real time and match these real-time data with the lighting data of LED equipment; this helps capture instantaneous environmental changes and makes LED lighting quality assessment more accurate and reliable;

[0117] By extracting features such as ambient temperature, ambient illumination, ambient humidity, and ambient suspended particulate matter concentration, a quantitative set of lighting environment impact features is formed; this helps to establish objective evaluation standards so that the performance of LED devices under different environmental conditions can be quantitatively compared and analyzed;

[0118] In summary, step S3 builds a more comprehensive, accurate, and real-time LED lighting quality assessment model to improve the performance and adaptability of LED lighting systems in actual use;

[0119] S4, combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space to obtain lighting quality assessment factor features;

[0120] Step S4 is to combine the lighting characteristics of the LED device with the influencing characteristics of the lighting environment to form a comprehensive lighting quality evaluation factor characteristic, in order to more comprehensively consider various factors of the LED lighting system in the actual use environment, so as to more accurately evaluate the lighting quality;

[0121] The method for acquiring characteristics of lighting quality assessment factors comprises:

[0122] S41, aligning the LED device lighting feature set and the lighting environment impact feature set to ensure that the LED device lighting feature set and the lighting environment impact feature set correspond in time and space, thereby ensuring effective comparison and analysis of the data;

[0123] S42, combining the LED device lighting feature set and the lighting environment impact feature set through feature splicing technology;

[0124] S43, normalizing the combined data to ensure that the value ranges of different features are similar, to prevent the large value ranges of some features from having too great an impact on the training of the model;

[0125] S44. Remove redundant and irrelevant features according to actual needs, perform feature selection, and improve the generalization ability and efficiency of the model;

[0126] S45. The integrated feature set is regarded as a lighting quality assessment factor feature.

[0127] In this step, the time-space alignment of the LED device lighting characteristics and the lighting environment impact characteristics ensures that the data correspond at the same time and space, so that the LED device lighting characteristics and environmental impact characteristics can be effectively compared and analyzed; time-space alignment helps to avoid data confusion, ensure that the evaluation is based on the same conditions and environmental parameters, and improve the reliability and consistency of the evaluation; through feature splicing technology, the lighting characteristics of the LED device and the lighting environment impact characteristics are combined to achieve multi-dimensional information fusion; multi-dimensional information fusion helps to deeply understand the performance of the LED lighting system under different conditions and improve the comprehensive evaluation of lighting quality;

[0128] The combined data is normalized to ensure that the value ranges of different features are similar; this can prevent the value range of some features from being too large and have too much impact on the training of the model, and improve the stability and convergence speed of the model; redundant and irrelevant features are removed according to actual needs, and feature selection is performed to improve the generalization ability and efficiency of the model, reduce the risk of overfitting, and ensure the model's prediction ability for unknown data; the integrated feature set is regarded as a lighting quality assessment factor, which will provide a more comprehensive and comprehensive input for the establishment of an LED equipment lighting quality assessment model, and help the model to more accurately understand the performance of the LED lighting system in the actual environment;

[0129] In summary, the beneficial effect of this step is that it provides a more comprehensive, accurate and robust feature set for LED lighting quality assessment, thereby enhancing the performance and reliability of the assessment model.

[0130] S5. Associating the lighting quality assessment factor features with the corresponding LED device lighting quality assessment results, and using them as training data sets for deep learning training to build an LED device lighting quality assessment model;

[0131] Step S5: In order to construct an LED device lighting quality assessment model, the model can automatically assess the quality of the LED lighting system. In the field of lighting quality detection, deep learning has been widely used to process complex data sets and extract features from them;

[0132] The methods for constructing LED equipment lighting quality assessment model include:

[0133] S51, obtaining lighting quality assessment factor characteristics and corresponding LED device lighting quality assessment results, associating the lighting quality assessment factor characteristics with the corresponding LED device lighting quality assessment results, and obtaining a model training data set;

[0134] S52. Clean the training data, process missing values ​​and outliers, and standardize and normalize the data to ensure the stability and reliability of the model during the training process;

[0135] S53. Based on the complexity of the task, the characteristics of the data, and the expected output, a recurrent neural network was selected as the basis for the deep learning model.

[0136] S54, using the training data set to train the selected deep learning model, and continuously optimizing the model parameters through the back propagation algorithm so that the model can accurately predict the LED lighting quality;

[0137] S55. Adjust the model's hyperparameters through cross-validation technology to improve the model's performance and generalization ability;

[0138] S56. Select the loss function and optimizer to minimize the error during training and accelerate model convergence;

[0139] S57. Use the validation set to evaluate the performance of the model on unseen data to prevent overfitting and make further adjustments to the model.

[0140] S58. After the training is completed, the model is deployed to actual applications to perform real-time evaluation of the lighting quality of the LED device to be evaluated.

[0141] In this step, the lighting quality assessment factor features are associated with the LED equipment lighting quality assessment results, and a labeled training data set is constructed, which enables the model to learn the complex relationship between specific lighting quality factors and assessment results; cleaning and processing the training data helps to eliminate problems such as outliers and missing values, and ensure the quality of the training data; standardization and normalization can make the numerical ranges of different features relatively consistent, which helps to improve the convergence speed and stability of the model;

[0142] Based on the complexity of the task and the selection of data features, the use of recurrent neural networks can effectively process time series data; by using the back propagation algorithm for training, the model can gradually learn the complex patterns of LED lighting quality evaluation factors; the adjustment of hyperparameters, the selection of appropriate loss functions and optimizers can help improve the performance of the model and make it better adapt to the training data; using the validation set to evaluate the performance of the model can check the generalization ability of the model on unseen data and avoid overfitting; based on the validation results, the structure or hyperparameters of the model can be further adjusted to improve the accuracy of the model;

[0143] After training, the model is deployed to actual applications, enabling real-time evaluation of new LED equipment; the automated evaluation system can improve efficiency, reduce manual intervention, and more promptly identify and resolve quality issues in LED lighting systems;

[0144] In summary, step S5 effectively utilizes the characteristics of lighting quality factors through deep learning technology to achieve automatic evaluation of LED lighting system quality, providing strong support for improving the accuracy and efficiency of lighting quality detection;

[0145] S6. Acquire the lighting quality assessment factor characteristics of the LED device to be evaluated in real time, and input the lighting quality assessment factor characteristics acquired in real time into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be evaluated.

[0146] In step S6, the lighting quality assessment factor characteristics of the LED device to be evaluated are obtained in real time, and these characteristics are input into the previously constructed LED device lighting quality assessment model for prediction, so as to obtain the lighting quality assessment result of the LED device to be evaluated; the method for obtaining the lighting quality assessment result of the LED device to be evaluated includes:

[0147] S61, using LED device sensors to obtain detection data and lighting environment data of the LED device to be evaluated in real time;

[0148] S62, extracting parameter features that affect lighting quality from the real-time LED device lighting data, and obtaining a real-time LED device lighting feature set;

[0149] S63, extracting environmental features that affect lighting quality from the real-time lighting environment data to obtain a real-time lighting environment influencing feature set;

[0150] S64, combining the real-time LED device lighting feature set with the real-time lighting environment impact feature set in the same time and space to obtain real-time lighting quality assessment factor features;

[0151] S65. Input the real-time lighting quality assessment factor characteristics into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be assessed.

[0152] In this step, by using LED device sensors to obtain the detection data of LED devices and lighting environment data in real time, the system can quickly capture changes in LED devices and the environment; making the lighting quality assessment more real-time and accurate, helping to promptly discover and respond to any lighting quality issues;

[0153] Extract parameter features that affect lighting quality from real-time LED device lighting data and real-time lighting environment data, making lighting quality assessment more comprehensive and better reflecting the combined impact of LED devices and their surrounding environment;

[0154] The real-time LED device lighting feature set is combined with the real-time lighting environment impact feature set, taking into account the joint impact of LED devices and lighting environment under the same time and space conditions; it can more accurately characterize the interaction between the working state of LED devices and the environment, and improve the accuracy of the evaluation model;

[0155] Input the real-time lighting quality assessment factor characteristics into the LED equipment lighting quality assessment model to obtain the lighting quality assessment results of the LED equipment to be assessed; enable the system to have the ability of intelligent decision support, automatically assess the LED equipment, and provide targeted suggestions for subsequent maintenance and adjustment, thereby improving the overall performance of the LED lighting system;

[0156] In summary, the steps of S6 can improve the real-time, comprehensive and intelligent performance of the LED lighting system, and bring positive effects in improving lighting quality, reducing energy consumption and enhancing user experience.

[0157] Embodiment 2: Figure 3 As shown, the digital LED lighting quality evaluation system of the present invention specifically includes the following modules:

[0158] Historical data acquisition module: used to obtain the detection data and lighting environment data in the historical LED equipment detection process, and the detection data and lighting environment data correspond one to one; the detection data includes the LED equipment lighting quality evaluation results and LED equipment lighting data, and is sent;

[0159] Lighting feature extraction module: used to receive LED device lighting data, extract parameter features that affect lighting quality from the LED device lighting data, obtain a set of LED device lighting features, and send the set; the LED device lighting feature set includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation and dimming performance;

[0160] Environmental feature extraction module: used to receive lighting environment data, extract environmental features that affect lighting quality from the lighting environment data, obtain a lighting environment impact feature set, and send it; the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particle concentration;

[0161] Data combining module: used for receiving the LED device lighting feature set and the lighting environment impact feature set, combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space, obtaining the lighting quality assessment factor features, and sending them;

[0162] Deep learning training module: used to receive the lighting quality assessment factor features and the LED equipment lighting quality assessment results, associate the lighting quality assessment factor features with the corresponding LED equipment lighting quality assessment results, use them as training data sets for deep learning training, build an LED equipment lighting quality assessment model, and send it;

[0163] Real-time data acquisition module: used to acquire the lighting quality assessment factor characteristics of the LED device to be assessed in real time and send them;

[0164] The real-time evaluation module is used to receive the LED device lighting quality evaluation model and the lighting quality evaluation factor characteristics of the LED device to be evaluated in real time, input the lighting quality evaluation factor characteristics obtained in real time into the LED device lighting quality evaluation model, and obtain the lighting quality evaluation result of the LED device to be evaluated.

[0165] The system obtains detailed data during the LED equipment detection process through the historical data acquisition module, which can fully reflect the actual situation of LED lighting quality and avoid the problem of ignoring the impact of the lighting environment in traditional methods; the lighting feature extraction module and the environmental feature extraction module can accurately extract the parameter features that affect the lighting quality, ensuring that the system accurately captures the features of the LED equipment and the environment, thereby improving the accuracy of the evaluation; the data combination module combines the lighting features of the LED equipment with the features of the lighting environment to form the features of the lighting quality evaluation factors, providing more comprehensive input data for deep learning training, which helps to build a more accurate LED equipment lighting quality evaluation model;

[0166] The real-time data acquisition module and the real-time evaluation module enable the system to have real-time evaluation capabilities; they can instantly obtain the characteristics of the lighting quality evaluation factors of the LED equipment to be evaluated, and obtain the lighting quality evaluation results in real time through the deep learning model, meeting the requirements of the digital LED lighting system for automation and real-time performance; through the deep learning training module, the system realizes the intelligent evaluation of the lighting quality of LED equipment; the application of digital and intelligent technologies makes the system more adaptable to the needs of urban lighting, indoor lighting and other fields, and improves the efficiency and reliability of lighting projects;

[0167] In summary, the system comprehensively utilizes key technologies such as historical data, feature extraction, data combination and deep learning to reduce the limitations of lighting quality assessment methods and provide a comprehensive, accurate and real-time solution for the quality assessment of digital LED lighting systems.

[0168] The various variations and specific embodiments of the digital LED lighting quality assessment method in the aforementioned embodiment 1 are also applicable to the digital LED lighting quality assessment system of this embodiment. Through the aforementioned detailed description of the digital LED lighting quality assessment method, those skilled in the art can clearly understand the implementation method of the digital LED lighting quality assessment system of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0169] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0170] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A digital LED lighting quality assessment method, characterized in that: The method comprises: Acquire the detection data and lighting environment data in the historical LED device detection process, wherein the detection data and lighting environment data correspond to each other one by one; the detection data includes the LED device lighting quality assessment result and the LED device lighting data; Extracting parameter features that affect lighting quality from the LED device lighting data to obtain a set of LED device lighting features, wherein the set of LED device lighting features includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation, and dimming performance; Extracting environmental features that affect lighting quality from the lighting environment data to obtain a lighting environment impact feature set, wherein the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particulate matter concentration; Combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space to obtain lighting quality assessment factor features; The lighting quality assessment factor features and the corresponding LED equipment lighting quality assessment results are associated and used as training data sets for deep learning training to build an LED equipment lighting quality assessment model. Acquire the lighting quality assessment factor characteristics of the LED device to be evaluated in real time, and input the lighting quality assessment factor characteristics acquired in real time into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be evaluated; The method for acquiring characteristics of lighting quality assessment factors comprises: Perform data alignment on the LED device lighting feature set and the lighting environment impact feature set; Through feature splicing technology, the LED device lighting feature set and the lighting environment impact feature set are combined; Normalize the combined data; Remove redundant and irrelevant features from the combined data and perform feature selection; The integrated feature set is regarded as the lighting quality assessment factor feature.

2. The digital LED lighting quality evaluation method according to claim 1, characterized in that: The LED device is provided with sensors, which include a light sensor, a color sensor, a temperature sensor, a photometer, a radiometer, a spectroradiometer, a humidity sensor and a particle counter.

3. The digital LED lighting quality evaluation method according to claim 2, characterized in that: The LED device lighting feature set extraction method comprises: Calculate the change trend of luminous flux from the historical lighting data of LED equipment through time series data; Use the color sensor inside the LED device to obtain the color temperature value; Use the color sensor inside the LED device to measure the color of different areas and calculate the color uniformity index; Record the color data of LED lighting under different conditions, analyze its consistency with the real color, and obtain color reproducibility; The wavelength spectrum distribution was recorded using a spectroradiometer on the LED device; Get beam angle information from LED device specifications; Analyze the luminous flux data in the historical records of LED equipment and calculate the light attenuation ratio; The dimming data recorded by the LED device is used to analyze its performance at different brightness levels and obtain the dimming performance of the LED device.

4. The digital LED lighting quality evaluation method according to claim 2, characterized in that: The lighting environment impact feature set extraction method comprises: Use the LED device's external temperature sensor to measure the ambient temperature in real time and match it with the LED device's lighting data; Use a photometer to measure the ambient illumination and record the lighting data of the corresponding LED equipment; Use the LED device's external humidity sensor to monitor the ambient humidity in real time and match it with the LED device's lighting data; The concentration of suspended particulate matter in the environment is monitored in real time through a particle counter, which corresponds to the lighting data of the LED device.

5. The digital LED lighting quality evaluation method according to claim 1, characterized in that: The methods for constructing LED equipment lighting quality assessment model include: Acquire lighting quality assessment factor characteristics and corresponding LED device lighting quality assessment results, associate the lighting quality assessment factor characteristics with the corresponding LED device lighting quality assessment results, and obtain a model training data set; Clean the training data, handle missing values ​​and outliers, and standardize and normalize the data; Based on the complexity of the task, the characteristics of the data, and the expected output, a recurrent neural network was chosen as the basis for the deep learning model; Use the training data set to train the selected deep learning model and continuously optimize the model parameters through the back-propagation algorithm; Adjust the model's hyperparameters through cross-validation techniques to improve the model's performance and generalization capabilities; Choose to use loss function and optimizer to minimize the error during training and accelerate model convergence; Use the validation set to evaluate the model’s performance on unseen data and make further adjustments to the model. After training, the model is deployed in practical applications to perform real-time evaluation of the lighting quality of the LED devices to be evaluated.

6. The digital LED lighting quality evaluation method according to claim 5, characterized in that: The method for obtaining the lighting quality evaluation result of the LED device to be evaluated comprises: Use LED device sensors to obtain real-time detection data and lighting environment data of the LED device to be evaluated; Extract parameter features that affect lighting quality from real-time LED device lighting data to obtain a real-time LED device lighting feature set; Extract environmental features that affect lighting quality from real-time lighting environment data to obtain a real-time lighting environment influencing feature set; Combine the real-time LED equipment lighting feature set with the real-time lighting environment impact feature set in the same time and space to obtain the real-time lighting quality assessment factor features; The real-time lighting quality assessment factor characteristics are input into the LED device lighting quality assessment model to obtain the lighting quality assessment result of the LED device to be evaluated.

7. A digital LED lighting quality assessment system, characterized in that: The system is applied to the digital LED lighting quality assessment method according to claim 1, and the system comprises: Historical data acquisition module: used to obtain the detection data and lighting environment data in the historical LED equipment detection process, and the detection data and lighting environment data correspond one to one; the detection data includes the LED equipment lighting quality evaluation results and LED equipment lighting data, and is sent; Lighting feature extraction module: used to receive LED device lighting data, extract parameter features that affect lighting quality from the LED device lighting data, obtain a set of LED device lighting features, and send the set; the LED device lighting feature set includes luminous flux, color temperature, color uniformity, color reproducibility, wavelength spectrum distribution, beam angle, light attenuation and dimming performance; Environmental feature extraction module: used to receive lighting environment data, extract environmental features that affect lighting quality from the lighting environment data, obtain a lighting environment impact feature set, and send it; the lighting environment impact feature set includes ambient temperature, ambient illumination, ambient humidity, and ambient suspended particle concentration; Data combining module: used for receiving the LED device lighting feature set and the lighting environment impact feature set, combining the LED device lighting feature set with the lighting environment impact feature set at the same time and space, obtaining the lighting quality assessment factor features, and sending them; Deep learning training module: used to receive the lighting quality assessment factor features and the LED equipment lighting quality assessment results, associate the lighting quality assessment factor features with the corresponding LED equipment lighting quality assessment results, use them as training data sets for deep learning training, build an LED equipment lighting quality assessment model, and send it; Real-time data acquisition module: used to acquire the lighting quality evaluation factor characteristics of the LED device to be evaluated in real time and send them; The real-time evaluation module is used to receive the LED device lighting quality evaluation model and the lighting quality evaluation factor characteristics of the LED device to be evaluated in real time, input the lighting quality evaluation factor characteristics obtained in real time into the LED device lighting quality evaluation model, and obtain the lighting quality evaluation result of the LED device to be evaluated.

8. An electronic device for a digital LED lighting quality evaluation method, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images