Digital twin illumination optimization method, system and device and storage medium

Abstract

The invention discloses a digital twin illumination optimization method, system and device and a computer readable storage medium, and the method comprises the steps: collecting multi-modal original data containing illumination information, environment information, scene information and device information, and carrying out the space-time alignment processing and edge calculation preprocessing of the multi-modal original data; performing illumination simulation optimization on the processed data through preset illumination design twinning, cloud data processing and real-time scene modeling; and regulating and controlling the current lighting state and / or equipment state in combination with the lighting simulation optimization result, and carrying out lighting operation and maintenance resource optimization through a preset three-party dynamic game model. According to the invention, an intelligent lighting design optimization and operation and maintenance management scheme based on the digital twinning technology is realized, the lighting design efficiency and accuracy are improved, the personalized requirements of users are met, the operation and maintenance management level of a lighting system is improved, and the technical innovation and development of the lighting design industry are promoted.

Description

Technical Field

[0001] The present invention relates to the field of lighting technology, and in particular to a digital twin lighting optimization method, system, device and computer-readable storage medium. Background Art

[0002] At present, traditional lighting design has serious defects in data collection. The data is easily affected by external interference, the accuracy is difficult to guarantee, and it is impossible to fully obtain various types of data in complex scenes, making it difficult to meet diverse lighting needs. Specifically, it is reflected in: First, the use of a single light intensity sensor cannot obtain key parameters such as material reflectivity and spatial topology; second, the three-dimensional modeling process relies on manual measurement, with a high error rate and a long time consumption; third, the existing optimization algorithm converges slowly in complex scenes, and the optimal solution cannot be obtained even after more than 200 iterations, affecting the verification and optimization of the design solution; fourth, equipment maintenance relies on regular inspections, and resource allocation is unreasonable, resulting in high operation and maintenance costs and low efficiency.

[0003] Therefore, how to effectively improve the efficiency and accuracy of lighting design, meet the personalized needs of users, enhance the operation and maintenance management level of lighting systems, and promote technological innovation and development in the lighting design industry has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the deficiencies in the prior art, the purpose of the present invention is to provide a solution to the problems that the current lighting design has low efficiency and accuracy, cannot meet the personalized needs of users, and the level of operation and maintenance management of the lighting system needs to be improved.

[0005] The present invention proposes a digital twin lighting optimization method, which includes:

[0006] Collecting multimodal raw data including lighting information, environmental information, scene information, and device information, and performing spatiotemporal alignment processing and edge computing preprocessing on the multimodal raw data;

[0007] Perform lighting simulation optimization on the processed data through preset lighting design twins, cloud data processing, and real-time scene modeling;

[0008] In combination with the lighting simulation optimization result, the current lighting status and / or equipment status is regulated, and the lighting operation and maintenance resources are optimized through a preset three-party dynamic game model.

[0009] Optionally, the performing spatiotemporal alignment processing and edge computing preprocessing on the multimodal raw data specifically includes:

[0010] Deploy the iterative closest point algorithm and acrylic model;

[0011] Match the 3D point cloud data and 2D image data in the multi-modal raw data through the Iterative Closest Point algorithm, and calibrate the spatial coordinate origin positioning of each data through the acrylic model, so that the multi-source heterogeneous data is consistent in space and time.

[0012] Optionally, the spatio-temporal alignment processing and edge computing preprocessing of the multi-modal raw data specifically include:

[0013] Deploy an anomaly data filtering algorithm accelerated by a field-programmable gate array;

[0014] Preliminarily process the multi-modal raw data through the anomaly data filtering algorithm and filter out outliers.

[0015] Optionally, the illumination simulation optimization of the processed data through the preset illumination design twin, cloud data processing, and real-time scene modeling specifically includes:

[0016] Construct a virtual scene corresponding to the real illumination environment;

[0017] Regulate the acquisition action of the multi-modal raw data through the virtual scene.

[0018] Optionally, the illumination simulation optimization of the processed data through the preset illumination design twin, cloud data processing, and real-time scene modeling specifically includes:

[0019] Analyze the processed data through big data processing algorithms and artificial intelligence algorithms;

[0020] Combine the real-time dynamic grid and the multi-level of detail algorithm to perform real-time scene modeling on the analyzed data, and adjust the level of detail of the real-time scene model according to the viewing distance;

[0021] Perform illumination simulation optimization through ray tracing, optimization algorithms, the real-time scene model, and the preset illumination design software.

[0022] Optionally, the analysis of the processed data through big data processing algorithms and artificial intelligence algorithms specifically includes:

[0023] Deploy a data import and integration algorithm;

[0024] Standardize the processed data and user requirements through the data import and integration algorithm, extract the key information of unstructured data using the preset image recognition algorithm, fuse it with the structured data, and perform two-way data circulation and integration with the illumination design software through a unified interface protocol.

[0025] Optionally, by combining the real-time dynamic grid with the level-of-detail algorithm, a real-time scene model is built for the analyzed data, and the level of detail of the real-time scene model is adjusted according to the viewing distance, which specifically includes:

[0026] Deploy the simulation and analysis algorithm;

[0027] Through the simulation and analysis algorithm, simulate the lighting design scheme in the lighting design software, and combine the real-time scene and environmental data of the digital twin, use the Monte Carlo ray tracing algorithm to calculate the light intensity distribution, and analyze the color temperature index and color rendering index parameters by combining the preset color model algorithm.

[0028] Optionally, through ray tracing, optimization algorithms, the real-time scene model, and the preset lighting design software, lighting simulation optimization is performed, which specifically includes:

[0029] Deploy the optimization algorithm;

[0030] Through the optimization algorithm, the preset quantum annealing algorithm, and the traditional genetic algorithm, construct a quantum hybrid optimizer, encode the lighting parameters as the superposition of quantum bit states, construct a fitness function by combining the dynamic game theory, transform the lighting parameter optimization problem into the form of quadratic unconstrained binary optimization for solution, and perform optimization through quantum bit mapping to obtain an optimization scheme.

[0031] Optionally, through ray tracing, optimization algorithms, the real-time scene model, and the preset lighting design software, lighting simulation optimization is performed, which specifically includes:

[0032] Deploy the feedback and adjustment algorithm;

[0033] Through the feedback and adjustment algorithm, place the optimization scheme into the preset digital twin system, compare the simulation results of the virtual scene with the actual monitoring data, calculate the error and / or adjust the optimization scheme.

[0034] The present invention also proposes a digital twin lighting optimization system, which includes:

[0035] The data acquisition layer is used to collect raw data through multi-modal sensors and perform spatio-temporal alignment and edge computing preprocessing on the raw data;

[0036] The transmission layer is used to receive the processed data sent by the data acquisition layer and transmit the data to the digital twin system layer through the preset mobile network, private network, and positioning network;

[0037] The digital twin system layer is used to perform lighting simulation optimization on the data through the preset intelligent lighting design twin, cloud data processing, and real-time high-precision scene modeling;

[0038] The application layer is used for controlling and managing the lighting state and device state, and optimizing the operation and maintenance resource allocation through a preset three-party dynamic game resource allocator.

[0039] The present invention also provides a digital twin lighting optimization device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it realizes the steps of the digital twin lighting optimization method described in any one of the above.

[0040] The present invention also provides a computer-readable storage medium, on which a digital twin lighting optimization program is stored. When the digital twin lighting optimization program is executed by a processor, it realizes the steps of the digital twin lighting optimization method described in any one of the above.

[0041] Implementing the digital twin lighting optimization method, device, and computer-readable storage medium of the present invention, by collecting multi-modal raw data including lighting information, environmental information, scene information, and device information, and performing spatio-temporal alignment processing and edge computing preprocessing on the multi-modal raw data; performing lighting simulation optimization on the processed data through a preset lighting design twin, cloud data processing, and real-time scene modeling; combining the results of the lighting simulation optimization, regulating the current lighting state and / or device state, and optimizing the lighting operation and maintenance resources through a preset three-party dynamic game model. An intelligent lighting design optimization and operation and maintenance management solution based on digital twin technology is realized, which improves the lighting design efficiency and accuracy, meets the personalized needs of users, enhances the operation and maintenance management level of the lighting system, and promotes the technological innovation and development of the lighting design industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below in conjunction with the drawings and embodiments. In the drawings:

[0043] Figure 1 is the first flowchart of the digital twin lighting optimization method of the present invention;

[0044] Figure 2 is the second flowchart of the digital twin lighting optimization method of the present invention;

[0045] Figure 3 is the third flowchart of the digital twin lighting optimization method of the present invention;

[0046] Figure 4 is the fourth flowchart of the digital twin lighting optimization method of the present invention;

[0047] Figure 5 is the fifth flowchart of the digital twin lighting optimization method of the present invention;

[0048] Figure 6 It is the sixth flowchart of the digital twin lighting optimization method of the present invention;

[0049] Figure 7 It is the seventh flowchart of the digital twin lighting optimization method of the present invention;

[0050] Figure 8 It is the eighth flowchart of the digital twin lighting optimization method of the present invention;

[0051] Figure 9 It is the ninth flowchart of the digital twin lighting optimization method of the present invention;

[0052] Figure 10 It is the first working principle diagram of the digital twin lighting optimization method of the present invention;

[0053] Figure 11 It is the data acquisition working principle diagram of the digital twin lighting optimization method of the present invention;

[0054] Figure 12 It is the data transmission working principle diagram of the digital twin lighting optimization method of the present invention;

[0055] Figure 13 It is the digital twin working principle diagram of the digital twin lighting optimization method of the present invention;

[0056] Figure 14 It is the simulation and algorithm principle diagram of the digital twin lighting optimization method of the present invention;

[0057] Figure 15 It is the operation and maintenance working principle diagram of the digital twin lighting optimization method of the present invention;

[0058] Figure 16 It is the second working principle diagram of the digital twin lighting optimization method of the present invention;

[0059] Figure 17 It is the module block diagram of the digital twin lighting optimization system of the present invention. Detailed implementation manners

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0061] In the following description, suffixes such as "module", "component", or "unit" used to represent elements are only for the convenience of describing the present invention, and they have no specific meaning themselves. Therefore, "module", "component", or "unit" can be used interchangeably.

[0062] Figure 1 It is the first flowchart of the digital twin lighting optimization method of the present invention. In this embodiment, a digital twin lighting optimization method is proposed, and the method includes:

[0063] S1. Collect multi-modal raw data including lighting information, environmental information, scene information, and device information, and perform spatio-temporal alignment processing and edge computing preprocessing on the multi-modal raw data;

[0064] S2. Optimize the processed data through pre-set lighting design digital twin, cloud data processing, and real-time scene modeling for lighting simulation;

[0065] S3. Combine the results of the lighting simulation optimization, regulate the current lighting state and / or device state, and optimize lighting operation and maintenance resources through a pre-set tripartite dynamic game model.

[0066] In this embodiment, please refer to Figure 10 , the digital twin lighting optimization method of the present invention is applied to a digital twin lighting optimization system, which includes a data acquisition layer, a transmission layer, a digital twin system layer, and an application layer. Among them, the data acquisition layer includes a multi-modal sensor, a spatio-temporal alignment module, and an edge computing preprocessing module; the transmission layer includes a 5G network module, a private network module, and a Beidou positioning module; the digital twin system layer includes an intelligent lighting design digital twin system, a cloud data processing center real-time scene modeling module, a lighting simulation optimization module, and a blockchain evidence storage module; the application layer includes an intelligent control module, a device management module, and a dynamic game allocation module.

[0067] In the data acquisition layer of this embodiment, multi-modal sensor fusion acquisition is performed. Specifically: a variety of high-precision professional sensors are used. For example, light data is accurately measured through a wire-wound electroplated thermopile sensor, environmental temperature and humidity data are obtained through a temperature and humidity composite sensor, dynamic scene data is collected through a 3D lidar, and device status data is monitored through a current harmonic detection module, etc., to comprehensively collect multi-faceted information such as lighting, environment, scene, and device status; in the data acquisition layer of this embodiment, multi-modal spatio-temporal alignment is performed. Specifically: an improved ICP (Iterative Closest Point) algorithm is used, combined with acrylic model calibration, to calibrate the spatial coordinate origin positioning of each data, so as to achieve millimeter-level precise matching of 3D point cloud data and two-dimensional image data, ensuring the spatio-temporal consistency of multi-source heterogeneous data and providing a reliable data basis for subsequent analysis and application; in the data acquisition layer of this embodiment, edge computing preprocessing is performed. Specifically: an abnormal data filtering algorithm based on FPGA (Field Programmable Gate Array) acceleration is deployed to perform preliminary processing on the data at the data acquisition source, filter out abnormal values, reduce the cloud transmission pressure, improve the data processing efficiency, and ensure the data quality.

[0068] In the transport layer of this embodiment, a high-speed and stable 5G mobile network, a secure and reliable private network, and a Beidou positioning network for precise positioning are deployed. Thus, high-speed data transmission is achieved through the 5G network, the private network is provided to ensure data transmission security, and the Beidou positioning network is provided to offer precise positioning services, ensuring the efficient and secure transmission of data from the acquisition layer to the digital twin system layer.

[0069] In the digital twin system layer of this embodiment, an intelligent lighting design twin system is deployed, where: a virtual scene highly consistent with the real lighting environment is constructed through modeling technology to achieve accurate data collection and simulation, providing an intuitive and efficient platform for lighting design optimization; in the digital twin system layer of this embodiment, a cloud data processing center is deployed, where: a large amount of collected data is deeply analyzed using big data processing and artificial intelligence algorithms to mine data value, providing a precise decision-making basis for lighting simulation and scheme design; in the digital twin system layer of this embodiment, a real-time high-precision scene model is deployed, where: combining real-time dynamic mesh technology with LOD (Levels of Detail) technology, the model detail level is automatically adjusted according to the viewing distance, while ensuring modeling accuracy, reducing VRAM (Video Random Access Memory) occupancy, and improving calculation efficiency, and, through frustum culling technology, rapid switching of the detail level is achieved to further optimize modeling performance; in the digital twin system layer of this embodiment, lighting simulation and scheme design are carried out, where: advanced ray tracing and intelligent optimization algorithms are adopted to work in cooperation with professional lighting design software such as dialux, and lighting design optimization is achieved through innovative algorithms.

[0070] In the application layer of this embodiment, intelligent lighting control management is carried out, where: precise intelligent control of lighting devices is realized, providing personalized and adaptive lighting effects according to different scenarios and requirements; in the application layer of this embodiment, precise control management of device status is carried out, where: the device status is monitored in real time, device failures are detected and processed in a timely manner to ensure the stable operation of the lighting system; in the application layer of this embodiment, a dynamic game resource allocator is deployed, where: a three-party game model of operation and maintenance personnel / equipment / users is established, and Nash equilibrium is achieved through Q-learning to optimize the operation and maintenance resource allocation, improve the operation and maintenance efficiency, and reduce the operation and maintenance cost.

[0071] It is not difficult to see that in this embodiment, first, by applying multi-modal sensor fusion technology and combining with an innovative spatio-temporal alignment method, the problem of multi-source heterogeneous data collection is broken through, comprehensive and accurate data collection is achieved, the spatio-temporal synchronization problem of data is solved, and a reliable data foundation is provided for lighting design and operation and maintenance management. Second, a dynamic adaptive digital twin modeling technology is proposed, which combines real-time dynamic grid technology and LOD (Level of Detail) technology to balance modeling accuracy and computational efficiency, reduce system resource consumption, and create an efficient virtual model for lighting design and operation and maintenance. Third, an innovative hybrid optimization algorithm is developed, which integrates the quantum annealing algorithm and the traditional genetic algorithm, incorporates concepts such as quantum bit mapping, greatly improves the optimization efficiency and quality of lighting schemes, and quickly generates lighting schemes that meet different requirements. Fourth, blockchain technology is introduced, and a digital identity chain of devices is constructed based on Hyperledger Fabric to achieve device authentication and data traceability, ensure the credibility of data collection devices, and guarantee the security and reliability of data. Fifth, a new ray tracing acceleration structure is developed, which integrates various optimization strategies, significantly improves the simulation speed, accelerates the verification and optimization process of lighting design schemes, and improves the design efficiency. Sixth, a dynamic game resource allocation model is constructed, which combines reinforcement learning and game theory to optimize the allocation of operation and maintenance resources, reduce operation and maintenance costs, and improve system stability and operation and maintenance efficiency.

[0072] The beneficial effects of this embodiment are as follows: by collecting multi-modal raw data including lighting information, environmental information, scene information, and device information, and performing spatio-temporal alignment processing and edge computing preprocessing on the multi-modal raw data; through pre-set lighting design twins, cloud data processing, and real-time scene modeling, lighting simulation optimization is performed on the processed data; combined with the results of the lighting simulation optimization, the current lighting state and / or device state are regulated, and lighting operation and maintenance resource optimization is performed through a pre-set three-party dynamic game model. An intelligent lighting design optimization and operation and maintenance management solution based on digital twin technology is realized, which improves the lighting design efficiency and accuracy, meets the personalized needs of users, enhances the operation and maintenance management level of the lighting system, and promotes the technological innovation and development of the lighting design industry.

[0073] Figure 2 This is the second flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the spatio-temporal alignment processing and edge computing preprocessing of the multi-modal raw data specifically include:

[0074] S11. Deploy the iterative closest point algorithm and the acrylic model;

[0075] S12. Match the three-dimensional point cloud data and two-dimensional image data in the multi-modal raw data through the iterative closest point algorithm and the acrylic model, so that the multi-source heterogeneous data is consistent in space and time.

[0076] In this embodiment, please refer toFigure 11 , the applied sensor array includes a wire-wound electroplated thermopile sensor, a temperature and humidity composite sensor, a 3D lidar, and a current harmonic detection module, which are respectively used to accurately measure light data, obtain ambient temperature and humidity data, collect dynamic scene data, and monitor equipment status data.

[0077] In this embodiment, the above data is input into the spatio-temporal alignment module. On the one hand, spatio-temporal alignment processing is performed, and on the other hand, edge computing processing is performed. Specifically, the iterative closest point algorithm and the acrylic model are deployed, and the three-dimensional point cloud data and two-dimensional image data in the multi-modal raw data are matched through the iterative closest point algorithm and the acrylic model, so that multi-source heterogeneous data is consistent in space and time, providing a reliable data basis for subsequent analysis and application.

[0078] The beneficial effect of this embodiment is that by deploying the iterative closest point algorithm and the acrylic model; the three-dimensional point cloud data and two-dimensional image data in the multi-modal raw data are matched through the iterative closest point algorithm and the acrylic model, so that multi-source heterogeneous data is consistent in space and time.

[0079] Figure 3 is the third flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the spatio-temporal alignment processing and edge computing preprocessing of the multi-modal raw data specifically include:

[0080] S13. Deploy an anomaly data filtering algorithm accelerated by a field-programmable gate array;

[0081] S14. Perform preliminary processing on the multi-modal raw data through the anomaly data filtering algorithm and filter out outliers.

[0082] In this embodiment, please refer to Figure 11 , through edge computing preprocessing, deploy an anomaly data filtering algorithm accelerated by FPGA (field-programmable gate array), perform preliminary processing on the data at the data acquisition source, and filter out outliers.

[0083] In this embodiment, please refer to Figure 12 , the transport layer consists of a high-speed and stable 5G mobile network, a secure and reliable private network, and a precisely positioned Beidou positioning network.

[0084] In this embodiment, the 5G network realizes high-speed data transmission, the private network ensures data transmission security, and the Beidou positioning network provides precise positioning services to ensure the efficient and secure transmission of data from the acquisition layer to the digital twin system layer.

[0085] The beneficial effect of this embodiment is that an abnormal data filtering algorithm accelerated by a field-programmable gate array is deployed; the multi-modal raw data is preliminarily processed by the abnormal data filtering algorithm, and abnormal values are filtered. Thereby reducing the cloud transmission pressure, improving the data processing efficiency, and ensuring the data quality.

[0086] Figure 4 It is the fourth flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the processed data is subjected to lighting simulation optimization through preset lighting design twin, cloud data processing, and real-time scene modeling, specifically including:

[0087] S21. Construct a virtual scene corresponding to the real lighting environment;

[0088] S22. Regulate the acquisition action of the multi-modal raw data through the virtual scene.

[0089] In this embodiment, please refer to Figure 13 , the digital twin core includes dynamic network modeling, physical property binding, and material mapping. Substitute the above three into the real-time rendering engine and provide a preset scene interface. The data is processed by the simulation optimization module, and the data processing includes three aspects. One is data cleaning, the second is machine learning analysis, and the third is time series prediction.

[0090] In this embodiment, after the above data processing, it is substituted into a quantum optimizer for optimization to obtain the final solution; and, in this process, the certificate verification of the final solution is stored through the blockchain.

[0091] In this embodiment, the intelligent lighting design twin system uses modeling technology to construct a virtual scene highly consistent with the real lighting environment to achieve accurate data collection and simulation.

[0092] The beneficial effect of this embodiment is that a virtual scene corresponding to the real lighting environment is constructed; the acquisition action of the multi-modal raw data is regulated through the virtual scene. Thereby providing an intuitive and efficient platform for lighting design optimization.

[0093] Figure 5 It is the fifth flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the processed data is subjected to lighting simulation optimization through preset lighting design twin, cloud data processing, and real-time scene modeling, specifically including:

[0094] S23. Analyze the processed data through big data processing algorithms and artificial intelligence algorithms;

[0095] S24. Combine the real-time dynamic grid with the level of detail algorithm to perform real-time scene modeling on the analyzed data, and adjust the level of detail of the real-time scene model according to the viewing distance;

[0096] S25. Perform lighting simulation optimization through ray tracing, optimization algorithms, the real-time scene model, and a preset lighting design software.

[0097] In this embodiment, a cloud data processing center is deployed, and big data processing and artificial intelligence algorithms are used to deeply analyze the massive collected data, mine the data value, and provide accurate decision-making basis for lighting simulation and scheme design.

[0098] In this embodiment, real-time high-precision scene modeling is performed, thus combining the real-time dynamic grid technology with the LOD (Levels of Detail) technology, and automatically adjusting the model level of detail according to the viewing distance. While ensuring the modeling accuracy, it reduces the VRAM (Video Random Access Memory) occupancy and improves the calculation efficiency. Optionally, the rapid switching of the level of detail is achieved through frustum culling technology to further optimize the modeling performance.

[0099] In this embodiment, lighting simulation and scheme design are performed. Among them, advanced ray tracing and intelligent optimization algorithms are adopted, which work in cooperation with professional lighting design software such as dialux, and lighting design optimization is achieved through innovative algorithms.

[0100] The beneficial effect of this embodiment is that the processed data is analyzed through big data processing algorithms and artificial intelligence algorithms; the real-time dynamic grid is combined with the level of detail algorithm to perform real-time scene modeling on the analyzed data, and the level of detail of the real-time scene model is adjusted according to the viewing distance; lighting simulation optimization is performed through ray tracing, optimization algorithms, the real-time scene model, and a preset lighting design software. Thus, it provides an intuitive and efficient platform for lighting design optimization and improves the innovation ability of lighting design optimization algorithms.

[0101] Figure 6 It is the sixth flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the analysis of the processed data through big data processing algorithms and artificial intelligence algorithms specifically includes:

[0102] S231. Deploy data import and integration algorithms;

[0103] S232. Standardize the processed data and user requirements through the data import and integration algorithms, extract the key information of unstructured data using a preset image recognition algorithm, fuse it with structured data, and perform two-way data flow and integration with the lighting design software through a unified interface protocol.

[0104] In this embodiment, the collected data and user requirements are standardized, and key information of unstructured data is extracted using advanced image recognition technology and integrated with structured data. Moreover, two-way data flow and deep integration with the lighting design software are achieved through a unified interface protocol.

[0105] The beneficial effect of this embodiment is that by deploying a data import and integration algorithm, the processed data and user requirements are standardized through the data import and integration algorithm, and key information of unstructured data is extracted using a preset image recognition algorithm and integrated with structured data. Data two-way flow and integration are carried out with the lighting design software through a unified interface protocol, providing more accurate and efficient data input for subsequent simulation and analysis.

[0106] Figure 7 It is the seventh flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, the combined real-time dynamic grid and multi-level of detail algorithm is used to perform real-time scene modeling on the analyzed data, and the level of detail of the real-time scene model is adjusted according to the viewing distance, specifically including:

[0107] S241. Deploy a simulation and analysis algorithm;

[0108] S242. Through the simulation and analysis algorithm, simulate the lighting design scheme in the lighting design software, and combine the real-time scene and environmental data of the digital twin, use the Monte Carlo ray tracing algorithm to calculate the light intensity distribution, and analyze the color temperature index and color rendering index parameters in combination with a preset color model algorithm.

[0109] In this embodiment, the lighting design scheme is simulated in the dialux software, combined with the real-time scene and environmental data of the digital twin system, the Monte Carlo ray tracing algorithm is used to accurately calculate the light intensity distribution, and the CIELAB color model algorithm is used to deeply analyze parameters such as color temperature and color rendering index, continuously optimizing the lighting design scheme.

[0110] The beneficial effect of this embodiment is that by deploying a simulation and analysis algorithm; through the simulation and analysis algorithm, simulate the lighting design scheme in the lighting design software, and combine the real-time scene and environmental data of the digital twin, use the Monte Carlo ray tracing algorithm to calculate the light intensity distribution, and analyze the color temperature index and color rendering index parameters in combination with a preset color model algorithm. Thereby further optimizing the lighting design scheme.

[0111] Figure 8 It is the eighth flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, lighting simulation optimization is carried out through ray tracing, an optimization algorithm, the real-time scene model, and a preset lighting design software, specifically including:

[0112] S251. Deploy the optimization algorithm;

[0113] S252. Through the optimization algorithm, the preset quantum annealing algorithm, and the traditional genetic algorithm, construct a quantum hybrid optimizer, encode the lighting parameters as a superposition of quantum bit states, construct a fitness function in combination with the dynamic game theory, transform the lighting parameter optimization problem into the form of quadratic unconstrained binary optimization for solution, and perform optimization through quantum bit mapping to obtain an optimization scheme.

[0114] In this embodiment, the quantum annealing algorithm and the traditional genetic algorithm are innovatively integrated to construct a quantum hybrid optimizer. The lighting parameters are encoded as a superposition of quantum bit states, the dynamic game theory is introduced to construct a fitness function, the lighting parameter optimization problem is transformed into the form of QUBO (quadratic unconstrained binary optimization) for solution, and efficient optimization is achieved through quantum bit mapping (such as color temperature - brightness matrix encoding).

[0115] The beneficial effect of this embodiment is that by deploying the optimization algorithm; through the optimization algorithm, the preset quantum annealing algorithm, and the traditional genetic algorithm, construct a quantum hybrid optimizer, encode the lighting parameters as a superposition of quantum bit states, construct a fitness function in combination with the dynamic game theory, transform the lighting parameter optimization problem into the form of quadratic unconstrained binary optimization for solution, and perform optimization through quantum bit mapping to obtain an optimization scheme. Thereby improving the optimization efficiency and quality of the lighting scheme.

[0116] Figure 9 This is the ninth flowchart of the digital twin lighting optimization method of the present invention. Based on the above embodiment, through ray tracing, the optimization algorithm, the real - time scene model, and the preset lighting design software, lighting simulation optimization is performed, specifically including:

[0117] S253. Deploy the feedback and adjustment algorithm;

[0118] S254. Through the feedback and adjustment algorithm, place the optimization scheme into the preset digital twin system, compare the simulation results of the virtual scene with the actual monitoring data, calculate the error and / or adjust the optimization scheme.

[0119] In this embodiment, the optimized scheme is placed into the digital twin system, and the simulation results of the virtual scene are compared with the actual monitoring data to accurately calculate the error.

[0120] In this embodiment, please refer to Figure 14, the processes of the above simulations and algorithms successively include: data import, data standardization, scenario analysis, Monte Carlo ray tracing, CIELAB color analysis, quantum hybrid optimization, genetic algorithm iteration, virtual scenario verification, error analysis, parameter adjustment, and solution output. Among them, quantum hybrid optimization specifically includes quantum annealing optimization, quantum bit mapping, QUBO matrix construction, and optimization solution.

[0121] The beneficial effect of this embodiment lies in deploying a feedback and adjustment algorithm; putting the optimization solution into a preset digital twin system through the feedback and adjustment algorithm, comparing the simulation results of the virtual scenario with the actual monitoring data, calculating the error and / or adjusting the optimization solution. Thus, by adjusting the solution in a timely manner, it is ensured that the lighting effect highly coincides with the expectation.

[0122] In this embodiment, please refer to Figure 15 , for operation and maintenance status monitoring and operation and maintenance management, the specific solution includes: equipment alarm, AI diagnosis, fault location, dynamic game, personnel dispatch, on-site repair, function test, and blockchain evidence storage; among them, dynamic game specifically includes: determining personnel location, equipment status, and user needs through digital twin mapping, thus establishing a game model based on the above three, and then performing Q-leanning optimization to generate a scheduling solution.

[0123] In this embodiment, for fault early warning and diagnosis, data analysis and artificial intelligence algorithms (such as decision tree algorithms) are used to monitor the operation data of equipment in real time, construct a decision tree model based on historical data, and accurately predict equipment faults in advance and locate the fault location.

[0124] In this embodiment, for maintenance plan formulation, based on time series analysis methods, data such as the historical operation time of equipment and the fault occurrence time are analyzed, and a regular maintenance plan is intelligently formulated to remind operation and maintenance personnel to conduct inspections and maintenance in a timely manner.

[0125] In this embodiment, for resource management, a dynamic game resource allocation model is established, combining reinforcement learning and game theory to construct a three-party game model of operation and maintenance personnel - equipment - user. Optionally, Beidou positioning network is used to obtain the location information of personnel and equipment, combined with mobile trajectory prediction technology, using the state of wireless charging equipment, etc. as game parameters, and Nash equilibrium is achieved through Q-learning to optimize the efficiency of operation and maintenance resource allocation.

[0126] In this embodiment, for data analysis and reporting, association rule algorithms are used to deeply analyze the correlation relationship of operation and maintenance data, and a detailed operation and maintenance report is sorted out and generated to provide a scientific reference for management decisions and assist subsequent procurement and operation and maintenance management.

[0127] In this embodiment, for the blockchain evidence storage module, a digital identity chain for devices is constructed based on Hyperledger Fabric. Lightweight Merkle proofs are used for certificate issuance. Remote authentication based on TEE (Trusted Execution Environment) is used for anomaly detection. Smart contracts automatically execute certificate revocation to achieve data traceability and ensure the credibility of data collection devices.

[0128] In this embodiment, please refer to Figure 16 , after the project starts, an operation and maintenance plan is generated through the twin system, and then operation and maintenance twins are carried out until the end of the life cycle. The above twin system is an illumination design twin system, which specifically includes a data collection layer, a transmission layer, a digital twin system layer, an application layer, and an illumination device layer.

[0129] In this embodiment, the above data collection layer includes one or more of the following data collections: illumination data collection, environmental data collection, scenario data collection, vehicle operation status data collection, and road surface data collection, as well as the acquisition of one or more of the following states: the state of illumination devices, the state of sensing devices, the state of video recording devices, and the state of detection devices.

[0130] It is not difficult to see that the innovations of this embodiment are as follows: First, multi-modal data collection and spatio-temporal synchronization; second, dynamic adaptive digital twin modeling; third, quantum hybrid optimization algorithm; fourth, blockchain device authentication; fifth, ray tracing acceleration structure; sixth, dynamic game resource allocation. Specifically, the advantages of data collection in this embodiment are as follows: The multi-modal sensor fusion technology combined with an innovative spatio-temporal alignment method effectively solves the problem of spatio-temporal synchronization of multi-source heterogeneous data, significantly improves the comprehensiveness and accuracy of data collection, and provides a solid and reliable data basis for illumination design and operation and maintenance management; the advantages of digital twin modeling in this embodiment are as follows: The dynamic adaptive digital twin modeling technology successfully balances the modeling accuracy and computational efficiency, reduces system resource consumption, provides an efficient and accurate virtual model support for illumination design and operation and maintenance, and improves the overall performance of the system; the advantages of the optimization algorithm in this embodiment are as follows: The innovative quantum hybrid optimization algorithm greatly improves the optimization efficiency and quality of illumination schemes, can quickly generate high-quality illumination schemes that meet different requirements, and saves design time and costs; the advantages of device authentication in this embodiment are as follows: The device authentication system constructed by blockchain technology ensures the credibility of data collection devices, guarantees the security and reliability of data, effectively prevents data tampering and forgery, and improves the overall security of the system; the advantages of ray tracing in this embodiment are as follows: The new ray tracing acceleration structure integrates a variety of optimization strategies, significantly improves the simulation speed, accelerates the verification and optimization process of illumination design schemes, and improves the design efficiency; the advantages of operation and maintenance resource allocation in this embodiment are as follows: The dynamic game resource allocation model optimizes the operation and maintenance resource configuration, reduces the operation and maintenance costs, improves the system stability and operation and maintenance efficiency, and ensures the continuous and reliable operation of the illumination system.

[0131] In this embodiment, the above-mentioned transport layer includes a mobile network, a private network, and a positioning network.

[0132] In this embodiment, the above-mentioned digital twin system layer includes a cloud data processing center, real-time scene modeling, lighting simulation and solution design, visual input and output, and operation and maintenance status.

[0133] In this embodiment, the above-mentioned application layer includes lighting control management and device status control management.

[0134] In this embodiment, the above-mentioned lighting device layer includes lighting devices.

[0135] Specifically, in this embodiment, a large commercial complex is taken as an example for illustration.

[0136] First, data collection and deployment are carried out: In the commercial complex, various high-precision sensors are comprehensively deployed. In the store area, high-resolution spectral sensors are installed in jewelry stores to accurately collect the reflection spectral data of jewelry under different lighting conditions, providing data support for accurately simulating the luster of jewelry; texture perception sensors are installed in clothing stores to obtain clothing material texture information and assist in optimizing lighting to highlight the texture of clothing. Panoramic cameras and high-precision position sensors are installed in public areas to capture the movement trajectories and gathering areas of people in real time. All sensor data is preliminarily denoised and de-duplicated by the edge computing preprocessing unit, and the multi-modal spatio-temporal alignment module ensures the spatio-temporal consistency of the data. The processed data is transmitted to the data collection terminal.

[0137] Second, data transmission and digital twin scene construction are carried out: The data of the collection terminal is uploaded to the cloud server through a high-speed network, and a virtual scene that is exactly the same as the commercial complex is constructed using digital twin technology. The virtual scene not only includes static information such as building structures and store layouts, but also can reflect the dynamic changes of people and equipment in real time. For example, when a customer picks up a product in a store, the corresponding position and product status in the virtual scene are updated synchronously. An LOD dynamic grid is constructed through real-time point cloud data, and the model details are automatically adjusted according to the perspective of the person. For example, when a person approaches the store window, the model details of the products displayed in the window are automatically enriched. At the same time, material mapping is carried out to accurately simulate the optical characteristics of various materials, as well as physical property binding, including properties such as lamp heat dissipation and lighting range, to achieve a high degree of restoration of the real scene.

[0138] Thirdly, the design and optimization of lighting solutions based on digital twins. On the one hand, for intelligent dimming and scene simulation: Taking the atrium of a shopping mall as an example, intelligent dimming is carried out according to time, season and personnel activities. During peak holiday hours, the digital twin system simulates the lighting effects under different dimming schemes, combines the feedback data on personnel comfort, and uses the quantum hybrid optimization algorithm to quickly determine the best dimming strategy, such as increasing the overall brightness and adjusting the color temperature to a warm tone to create a lively atmosphere. The light propagation is quickly simulated through the ray tracing acceleration structure, and the lighting uniformity and shadow conditions under different lamp layouts and brightness settings are analyzed to avoid lighting dead spots. On the other hand, for personalized lighting customization in stores: In a beauty store, based on the digital twin scene, a lighting solution is designed according to the product display requirements and the store decoration style. The digital twin system is used to simulate the product display effects under different light angles, colors and intensities, and communicate with the brand side to determine the lighting solution that can best highlight the product features. For example, for the lipstick display area, different spectral lighting effects are simulated, and lighting parameters that can truly present the color of the lipstick and enhance visual attraction are selected. When the store decoration is adjusted, the lighting effects under the new layout are simulated in advance in the digital twin scene, and the positions and types of lamps are optimized according to the simulation results, reducing the actual decoration cost and time.

[0139] Fourthly, the operation and maintenance management based on digital twins. On the one hand, for equipment fault warning and remote maintenance: The digital twin system is used to monitor the status of lighting equipment in real time, such as parameters like lamp temperature and current. When the temperature of a certain lamp rises abnormally, the system combines historical data and the equipment model, and uses machine learning algorithms to predict possible faults and notify the operation and maintenance personnel in advance. The operation and maintenance personnel can remotely view the surrounding environment and connection lines of the equipment through the digital twin scene and formulate a maintenance plan. Some simple faults can be remotely repaired by sending instructions through the digital twin system. On the other hand, for optimizing the maintenance plan: Based on the equipment operation data recorded by the digital twin system, the influence of equipment usage frequency and environmental factors on equipment life is analyzed to formulate a personalized maintenance plan. For example, for the lamps frequently used at the entrance of a shopping mall, the maintenance cycle is shortened; for the lamps in the underground parking lot in a humid environment, the moisture-proof inspection is strengthened. The digital twin system is used to simulate the operation status of the equipment under different maintenance plans, evaluate the maintenance effect, continuously optimize the maintenance plan, reduce the equipment failure rate, and improve the reliability of the lighting system.

[0140] Taking the urban road lighting system as an example for illustration.

[0141] First, conduct data collection and deployment: Install sensors with multiple functions on street light poles along urban roads. In addition to basic illuminance and color temperature sensors, vehicle flow monitoring radars, pedestrian thermal sensors, road surface condition imagers, etc. are also installed. The sensors collect road lighting data, vehicle and pedestrian dynamic data, and road surface condition data in real time. The data is preprocessed in the edge computing unit to remove outliers, and the multi-modal spatio-temporal alignment module ensures data synchronization. The data is transmitted to the cloud through 5G and Beidou networks.

[0142] Second, conduct data transmission and digital twin scenario construction: The cloud server uses digital twin technology to construct a virtual scenario of urban road lighting, accurately restoring the positions and shapes of roads, street lights, and surrounding buildings. The road surface condition is dynamically updated according to real-time point cloud data, such as simulating the impact of road waterlogging and snow accumulation on light reflection. Combining meteorological data, simulating the lighting environment under different weather conditions, such as the light scattering effect in foggy and rainy days. Through the LOD dynamic grid technology, the model accuracy is automatically adjusted when users view different areas. For example, when viewing accident-prone sections, the model details of this area are improved.

[0143] Third, conduct lighting scheme design and optimization based on digital twins. On the one hand, for intelligent dimming and traffic safety optimization: According to the real-time dynamics of vehicles and pedestrians in the digital twin scenario, adjust the brightness and color temperature of street lights. When there are few vehicles at night but pedestrians are crossing the road, automatically increase the brightness of street lights in the zebra crossing area and adjust the color temperature to cold white to enhance recognition. Use ray tracing acceleration structures to simulate the lighting effects under different dimming schemes and analyze the impact on drivers' vision to ensure that the lighting scheme meets both traffic safety requirements and energy conservation. Through the digital twin system, simulate the lighting requirements in different seasons and at different times of the day, and optimize the street light switching time and dimming strategy. For example, in winter, the daylight hours are short, so the street light turning-on time is appropriately extended; in summer, night activities are frequent, and the lighting brightness is increased in densely populated areas. On the other hand, for lighting system upgrade planning: In areas where urban roads are widened or newly built, use the digital twin system to plan the lighting layout in advance. Input road planning drawings and surrounding environment information, and simulate the lighting effects under different street light spacings, lamp types, and installation heights. By comparing and analyzing the simulation results and combining traffic flow prediction data, determine the best lighting scheme to avoid insufficient lighting or waste in actual construction. In the renovation project of old street lights, evaluate the effects of different renovation schemes through the digital twin system, such as replacing new energy-saving lamps and adjusting the positions of street lights, providing a scientific basis for decision-making and reducing the renovation cost.

[0144] Fourth, operation and maintenance management based on digital twins. On the one hand, for rapid fault location and repair: When a street lamp fails, the digital twin system quickly locates the fault location and cause based on sensor data and device models. For example, when the brightness of a certain street lamp decreases abnormally, the system analyzes the current, voltage data, and the status of surrounding street lamps to determine whether it is a bulb damage or a line fault. The operation and maintenance personnel can intuitively view the terrain and traffic conditions around the faulty street lamp through the digital twin scenario and plan the best repair route. Using augmented reality (AR) technology, project the device information and repair guide in the digital twin scenario onto the real scenario during on-site maintenance to assist the repair personnel in quickly repairing the fault. On the other hand, for resource scheduling and cost control: Based on the data analysis of the digital twin system, reasonably schedule operation and maintenance resources. Allocate corresponding repair personnel and tools according to the failure rate and repair difficulty of street lamps in different regions. Optimize resource allocation, improve operation and maintenance efficiency, and reduce operation and maintenance costs by simulating the repair efficiency and cost under different resource scheduling schemes. For example, reserve repair materials in advance in high-fault areas to reduce the material transportation time; reasonably allocate repair tasks according to the skill level and workload of repair personnel to ensure the efficient completion of each repair task.

[0145] Please refer to Figure 17 , based on the above embodiments, the present invention also proposes a digital twin lighting optimization system, which includes:

[0146] The data acquisition layer 10 is used to collect raw data through multi-modal sensors and perform spatio-temporal alignment and edge computing preprocessing on the raw data;

[0147] The transmission layer 20 is used to receive the processed data sent by the data acquisition layer and transmit the data to the digital twin system layer 30 through a preset mobile network, private network, and positioning network;

[0148] The digital twin system layer 30 is used to perform lighting simulation optimization on the data through preset intelligent lighting design twins, cloud data processing, and real-time high-precision scene modeling;

[0149] The application layer 40 is used to control and manage the lighting state and device state, and optimize the operation and maintenance resource configuration through a preset three-party dynamic game resource allocator.

[0150] It should be noted that the above system embodiments and method embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments, and the technical features in the method embodiments are all applicable to the system embodiments correspondingly, and will not be elaborated here.

[0151] Based on the above embodiments, the present invention further provides a digital twin lighting optimization device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the digital twin lighting optimization method described in any one of the above are implemented.

[0152] It should be noted that the above device embodiment and method embodiment belong to the same concept. The specific implementation process is described in detail in the method embodiment, and the technical features in the method embodiment are correspondingly applicable to the device embodiment, so they will not be repeated here.

[0153] Based on the above embodiments, the present invention further provides a computer-readable storage medium, on which a digital twin lighting optimization program is stored. When the digital twin lighting optimization program is executed by a processor, the steps of the digital twin lighting optimization method described in any one of the above are implemented.

[0154] It should be noted that the above medium embodiment and method embodiment belong to the same concept. The specific implementation process is described in detail in the method embodiment, and the technical features in the method embodiment are correspondingly applicable to the medium embodiment, so they will not be repeated here.

[0155] Implementing the digital twin lighting optimization method, device and computer-readable storage medium of the present invention, by collecting multi-modal raw data including lighting information, environmental information, scene information and device information, and performing spatio-temporal alignment processing and edge computing preprocessing on the multi-modal raw data; performing lighting simulation optimization on the processed data through preset lighting design twins, cloud data processing and real-time scene modeling; combining the results of the lighting simulation optimization, adjusting the current lighting state and / or device state, and optimizing lighting operation and maintenance resources through a preset tripartite dynamic game model. An intelligent lighting design optimization and operation and maintenance management solution based on digital twin technology is realized, which improves the efficiency and accuracy of lighting design, meets the personalized needs of users, improves the operation and maintenance management level of the lighting system, and promotes the technological innovation and development of the lighting design industry.

[0156] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0157] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element.

[0158] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A digital twin lighting optimization method, characterized in that, The method includes: Collecting multi-modal raw data including lighting information, environmental information, scene information, and device information, and performing spatio-temporal alignment processing and edge computing preprocessing on the multi-modal raw data; Performing lighting simulation optimization on the processed data through a preset lighting design twin, cloud data processing, and real-time scene modeling; Combining the results of the lighting simulation optimization, regulating the current lighting state and / or device state, and optimizing lighting operation and maintenance resources through a preset three-party dynamic game model.

2. The digital twin lighting optimization method according to claim 1, wherein The spatio-temporal alignment processing and edge computing preprocessing of the multi-modal raw data specifically include: Deploying the iterative closest point algorithm and the acrylic model; Matching the 3D point cloud data and 2D image data in the multi-modal raw data through the iterative closest point algorithm, and calibrating the spatial coordinate origin positioning of each data through the acrylic model to make the multi-source heterogeneous data consistent in space and time.

3. The digital twin lighting optimization method according to claim 1, wherein The spatio-temporal alignment processing and edge computing preprocessing of the multi-modal raw data specifically include: Deploying a field-programmable gate array-accelerated abnormal data filtering algorithm; Performing preliminary processing on the multi-modal raw data through the abnormal data filtering algorithm and filtering out abnormal values.

4. The digital twin lighting optimization method according to claim 1, characterized in that, The performing lighting simulation optimization on the processed data through a preset lighting design twin, cloud data processing, and real-time scene modeling specifically includes: Constructing a virtual scene corresponding to the real lighting environment; Regulating the acquisition actions of the multi-modal raw data through the virtual scene.

5. The digital twin lighting optimization method according to claim 1, wherein The performing lighting simulation optimization on the processed data through a preset lighting design twin, cloud data processing, and real-time scene modeling specifically includes: Analyzing the processed data through big data processing algorithms and artificial intelligence algorithms; Combining the real-time dynamic grid and the multi-level of detail algorithm to perform real-time scene modeling on the analyzed data, and adjusting the level of detail of the real-time scene model according to the viewing distance; Performing lighting simulation optimization through ray tracing, optimization algorithms, the real-time scene model, and a preset lighting design software.

6. The digital twin lighting optimization method according to claim 5, wherein The analyzing the processed data through big data processing algorithms and artificial intelligence algorithms specifically includes: Deploying a data import and integration algorithm; Performing standardized processing on the processed data and user requirements through the data import and integration algorithm, extracting key information of unstructured data using a preset image recognition algorithm, fusing it with structured data, and performing two-way data circulation and integration with the lighting design software through a unified interface protocol.

7. The digital twin lighting optimization method according to claim 5, characterized in that The combining the real-time dynamic grid and the multi-level of detail algorithm to perform real-time scene modeling on the analyzed data, and adjusting the level of detail of the real-time scene model according to the viewing distance specifically includes: Deploying a simulation and analysis algorithm; Through the simulation and analysis algorithm, simulating the lighting design scheme in the lighting design software, combining the real-time scene and environmental data of the digital twin, calculating the light intensity distribution using the Monte Carlo ray tracing algorithm, and analyzing the color temperature index and color rendering index parameters by combining a preset color model algorithm.

8. The digital twin lighting optimization method according to claim 5, wherein Performing lighting simulation optimization through ray tracing, an optimization algorithm, the real-time scene model, and a preset lighting design software, specifically including: Deploying the optimization algorithm; Constructing a quantum hybrid optimizer through the optimization algorithm, a preset quantum annealing algorithm, and a traditional genetic algorithm, encoding lighting parameters as a superposition of qubit states, constructing a fitness function in combination with dynamic game theory, transforming the lighting parameter optimization problem into a form of quadratic unconstrained binary optimization for solution, and performing optimization through qubit mapping to obtain an optimization scheme.

9. The digital twin lighting optimization method according to claim 8, wherein Performing lighting simulation optimization through ray tracing, an optimization algorithm, the real-time scene model, and a preset lighting design software, specifically including: Deploying a feedback and adjustment algorithm; Putting the optimization scheme into a preset digital twin system through the feedback and adjustment algorithm, comparing the simulation results of the virtual scene with the actual monitoring data, and calculating the error and / or adjusting the optimization scheme.

10. A digital twin lighting optimization system, characterized in that, The system includes: A data acquisition layer for collecting raw data through multi-modal sensors and performing spatio-temporal alignment and edge computing preprocessing on the raw data; A transmission layer for receiving the processed data sent by the data acquisition layer and transmitting the data to the digital twin system layer through a preset mobile network, private network, and positioning network; A digital twin system layer for performing lighting simulation optimization on the data through a preset intelligent lighting design twin, cloud data processing, and real-time high-precision scene modeling; An application layer for controlling and managing lighting states and device states, and optimizing the allocation of operation and maintenance resources through a preset three-party dynamic game resource allocator.

11. A digital twin lighting optimization device, characterized in that, The device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the digital twin lighting optimization method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that, A digital twin lighting optimization program is stored on the computer-readable storage medium. When the digital twin lighting optimization program is executed by the processor, the steps of the digital twin lighting optimization method according to any one of claims 1 to 9 are implemented.

Images