Intelligent lighting energy-saving control system based on multi-sensor linkage

The intelligent lighting energy-saving control system, which uses multiple sensors to determine and adjust the stability and data quality of the fusion algorithm, solves the problem of insufficient multi-sensor linkage in existing systems and achieves more stable and accurate lighting control.

CN123124173APending Publication Date: 2026-11-17GUANGZHOU YINGBANG INTELLIGENT TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202611323719.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-28
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing smart lighting systems lack multi-sensor linkage mechanisms, resulting in insufficient robustness of fusion algorithms and an inability to achieve precise dimming and high-efficiency energy saving.

Method used

By setting up a data processing module, an energy-saving control module, a fusion judgment module, a fluctuation adjustment module, and a timing adjustment module, the operational stability of the fusion algorithm is determined, and the fusion fluctuation rejection ratio and timing scale adjustment amount are adjusted to improve the stability and robustness of multi-sensor data fusion.

Benefits of technology

It improves the stability and robustness of multi-sensor fusion, reduces the anomaly rate and duration of anomalies in environmental fusion results, enhances the accuracy of characterizing ambient lighting conditions, and ensures the validity of operational data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123124173A_ABST
    Figure CN123124173A_ABST
Patent Text Reader

Abstract

This invention relates to the field of lighting technology, and more particularly to an intelligent lighting energy-saving control system based on multi-sensor linkage, comprising: a data processing module, which collects and preprocesses lighting operation data of an office area through several sensors to output lighting optimization data; an energy-saving control module, which fuses the lighting optimization data and environmental conditions using a fusion algorithm to output an environmental fusion result, and determines a lighting energy-saving scheme based on the environmental fusion result; a fusion judgment module, which determines the operational stability of the fusion algorithm based on the anomaly rate of the environmental fusion result; a fluctuation adjustment module, which determines the fusion fluctuation elimination ratio of the lighting operation data based on the proportion of abrupt changes in the lighting optimization data per unit time; and a time-series adjustment module, which determines the time-series scale adjustment amount of abnormal lighting operation data based on the distortion rate of the lighting operation data. This invention improves the robustness of the fusion algorithm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of lighting technology, and in particular to an intelligent lighting energy-saving control system based on multi-sensor linkage. Background Technology

[0002] In existing technologies, traditional intelligent lighting systems often use single light sensors or human body sensors for simple on / off switching and segmented control. This results in insufficient sensing dimensions and rigid control logic, making it difficult to achieve precise dimming and high energy efficiency. Some multi-sensor solutions are not optimized for complex indoor environments, leading to distorted data, difficulty in distinguishing noise from valid signals, and consequently, lighting misjudgments, excessive brightness, or frequent flickering. Furthermore, existing systems generally lack multi-sensor collaborative fusion mechanisms, often relying on independent individual sensor control, which fails to achieve regional linkage and global energy consumption optimization, resulting in insufficient robustness of the fusion algorithm.

[0003] Chinese Patent Publication No. CN120426538A discloses an intelligent AI mining lamp system and control method based on multimodal fusion. The system includes a multimodal data acquisition module, an energy-saving control module, a holographic projection unit, and a blockchain storage module. The multimodal data acquisition module comprises a miniature pinhole camera, a four-in-one gas sensor, a variable wavelength optical array, and a vital signs monitoring unit for multi-source data acquisition. The energy-saving control module includes an environmental adaptive engine, a MEMS beam adjustment system, and an edge computing unit for data analysis and control. The holographic projection unit uses an LCOS laser projection module to achieve three-dimensional information visualization. The blockchain storage module uses a blockchain platform for tamper-proof data storage. However, this intelligent AI mining lamp system and control method based on multimodal fusion suffers from insufficient robustness of the fusion algorithm due to the lack of an effective multi-sensor linkage mechanism and global lighting coordination scheduling, despite the multimodal acquisition module containing various heterogeneous sensors. Summary of the Invention

[0004] To address this, the present invention provides an intelligent lighting energy-saving control system based on multi-sensor linkage, which overcomes the problem in the prior art where, although the multi-modal acquisition module contains a variety of heterogeneous sensors, it lacks an effective multi-sensor linkage mechanism and global lighting collaborative scheduling, resulting in insufficient robustness of the fusion algorithm.

[0005] To achieve the above objectives, the present invention provides an intelligent lighting energy-saving control system based on multi-sensor linkage, comprising: The data processing module includes an acquisition unit for collecting lighting operation data of the office area through several sensors, and a preprocessing unit connected to the acquisition unit for preprocessing the lighting operation data to output lighting optimization data. An energy-saving control module, which is connected to the data processing module, includes a fusion unit for fusing the lighting optimization data and environmental status through a fusion algorithm to output an environmental fusion result, and an energy-saving control unit connected to the fusion unit for determining a lighting energy-saving scheme based on the environmental fusion result. The fusion determination module, which is connected to the energy-saving control module, is used to determine whether the operational stability of the fusion algorithm meets the requirements based on the anomaly rate of the environmental fusion results. A fluctuation adjustment module, which is connected to the fusion determination module, is used to determine the fusion fluctuation elimination ratio of the lighting operation data based on the proportion of sudden change points in the lighting optimization data per unit time when the running stability of the fusion algorithm does not meet the requirements. The timing adjustment module, which is connected to the fluctuation adjustment module, is used to determine the timing scale adjustment amount of abnormal lighting operation data based on the distortion rate of the lighting operation data.

[0006] Furthermore, the fusion determination module responds to the anomaly rate of the environmental fusion results to determine whether the operational stability of the fusion algorithm meets the requirements.

[0007] Furthermore, if the anomaly rate of the fusion determination module in response to the environmental fusion result is less than or equal to a preset anomaly rate, the stability of the fusion algorithm is determined to meet the requirements. The fusion determination module determines that the stability of the fusion algorithm does not meet the requirements if the anomaly rate of the environmental fusion result is greater than the preset anomaly rate.

[0008] Furthermore, in response to the condition that the operational stability of the fusion algorithm does not meet the requirements, the fluctuation adjustment module determines whether the effectiveness of the preprocessing meets the requirements based on the proportion of abrupt changes in the lighting optimization data per unit time.

[0009] Furthermore, if the fluctuation adjustment module responds to the fact that the percentage of abrupt changes in the lighting optimization data within the unit time is less than or equal to a preset first percentage, it determines that the effectiveness of the preprocessing meets the requirements. The fluctuation adjustment module determines that the effectiveness of preprocessing does not meet the requirements when the percentage of abrupt changes in the lighting optimization data within the unit time is greater than the preset first percentage.

[0010] Furthermore, the fluctuation adjustment module responds to the fact that the proportion of abrupt changes in the lighting optimization data within the unit time is greater than the preset first proportion and less than the preset second proportion, thereby increasing the fusion fluctuation elimination ratio of the lighting operation data. The fluctuation adjustment module responds when the percentage of abrupt changes in the lighting optimization data within a unit time is greater than or equal to the preset second percentage, and preliminarily determines that the validity of the lighting operation data collection does not meet the requirements. It then determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

[0011] Furthermore, the increase in the fusion fluctuation elimination ratio of the lighting operation data is determined by the difference between the percentage of mutation points in the lighting optimization data per unit time and the preset first percentage.

[0012] Furthermore, in response to the condition that the proportion of abrupt changes in the lighting optimization data within the unit time is greater than or equal to the preset second proportion, the timing adjustment module determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

[0013] Furthermore, the timing adjustment module determines that the validity of the lighting operation data collection meets the requirements when the distortion rate of the lighting operation data is less than or equal to the preset distortion rate. The timing adjustment module responds when the distortion rate of the lighting operation data is greater than the preset distortion rate, determines that the acquisition validity of the lighting operation data does not meet the requirements, and increases the timing scale adjustment amount of the abnormal lighting operation data.

[0014] Furthermore, the increase in the time-scale adjustment amount of the abnormal lighting operation data is determined by the difference between the distortion rate of the lighting operation data and the preset distortion rate.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: The system of this invention, by setting up a data processing module, an energy-saving control module, a fusion judgment module, a fluctuation adjustment module, and a timing adjustment module, judges the operational stability of the fusion algorithm based on the anomaly rate of the environmental fusion results. Because the preprocessing's ability to denoise the operational data is insufficient, the output standardized operational data still contains significant noise interference, failing to accurately reflect environmental state information. This causes the fusion algorithm to calculate based on distorted data during multi-sensor data fusion, resulting in improper weight settings and distorted multi-sensor fusion results. By judging the operational stability of the fusion algorithm, problems such as unreasonable weight allocation or insufficient anomaly handling can be detected in a timely manner, reducing the anomaly rate and duration of anomalies in the environmental fusion results, and improving the stability of multi-sensor fusion. The system also adjusts the fusion fluctuation removal ratio of the lighting operational data based on the proportion of abrupt changes in the lighting optimization data per unit time. Since the collected data contains a lot of interference data, it cannot accurately represent the actual environmental state, making it difficult for the preprocessing process to effectively distinguish between noise and effective data. The data, which leads to insufficient denoising capabilities, can be addressed by increasing the proportion of fluctuation removal during the fusion of lighting operation data. This enhances the screening intensity of abnormal fluctuation data during preprocessing, reduces the impact of interfering data on standardized operation data, lowers the proportion of abrupt changes in standardized operation data per unit time, and improves the preprocessing's ability to distinguish between noise and valid data. This provides stable data input for subsequent multi-sensor data fusion. The temporal scale adjustment of abnormal lighting operation data is adjusted based on the distortion rate of the lighting operation data. Since light sensors installed on desktops or other obstructed locations cannot collect raw operation data that accurately reflects the office environment's lighting level, the lighting operation data becomes distorted. Increasing the temporal scale adjustment of abnormal lighting operation data effectively stretches or compresses the influence range of distorted data on the time axis, reducing the weight of single-point or short-term distorted data within the fusion window. This suppresses the interference of outliers on the overall fusion result, improves the accuracy of the operation data in representing the true lighting state of the environment, and ultimately satisfies the requirement for effective operation data collection.

[0016] Furthermore, the system described in this invention determines the operational stability of the fusion algorithm by setting a preset anomaly rate. Due to insufficient noise reduction capability of preprocessing for operational data, the output standardized operational data still contains significant noise interference and cannot truly reflect environmental state information. This causes the fusion algorithm to perform calculations based on distorted data when fusing multi-sensor data, resulting in improper weight settings and distortion of multi-sensor fusion results. By determining the operational stability of the fusion algorithm, problems such as unreasonable weight allocation or insufficient anomaly handling can be detected in a timely manner, reducing the anomaly rate and duration of anomalies in the environmental fusion results, improving the stability of multi-sensor fusion, and further enhancing the robustness of the fusion algorithm.

[0017] Furthermore, the system of the present invention adjusts the fusion fluctuation rejection ratio of lighting operation data by setting a preset first ratio and a preset second ratio. Since the collected data contains a lot of interference data, it cannot accurately represent the actual environmental state, making it difficult for the preprocessing process to effectively distinguish between noise and valid data, resulting in insufficient denoising capability. By increasing the fusion fluctuation rejection ratio of lighting operation data, the screening intensity of abnormal fluctuation data in the preprocessing process can be improved, the impact of interference data on standardized operation data can be reduced, the proportion of mutation points in standardized operation data per unit time can be reduced, the preprocessing can distinguish between noise and valid data can be improved, and a stable data input can be provided for subsequent multi-sensor data fusion, further improving the robustness of the fusion algorithm.

[0018] Furthermore, the system described in this invention adjusts the temporal scale of abnormal lighting operation data by setting a preset distortion rate. Since the light sensor cannot collect original operation data that truly reflects the office environment's lighting level when it is installed on a desktop or other obstructed location, the lighting operation data is distorted. By increasing the temporal scale adjustment of abnormal lighting operation data, the influence range of distorted data on the time axis can be effectively stretched or compressed, reducing the weight ratio of single-point or short-term distorted data within the fusion window. This suppresses the interference of outliers on the overall fusion result, improves the accuracy of the operation data in representing the true lighting state of the environment, and thus satisfies the validity of operation data collection, further improving the robustness of the fusion algorithm. Attached Figure Description

[0019] Figure 1 This is an overall structural block diagram of the intelligent lighting energy-saving control system based on multi-sensor linkage according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the operational stability process of the fusion algorithm for determining the operation of an intelligent lighting energy-saving control system based on multi-sensor linkage, according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating the process of determining the fusion fluctuation elimination ratio of lighting operation data in an intelligent lighting energy-saving control system based on multi-sensor linkage according to an embodiment of the present invention. Figure 4 This is a logic flowchart illustrating the process of determining the time-scale adjustment amount of abnormal lighting operation data in an intelligent lighting energy-saving control system based on multi-sensor linkage, according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0021] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] Please see Figure 1 As shown, it is an overall structural block diagram of the intelligent lighting energy-saving control system based on multi-sensor linkage according to an embodiment of the present invention.

[0023] An embodiment of the present invention provides an intelligent lighting energy-saving control system based on multi-sensor linkage, comprising: The data processing module includes an acquisition unit for collecting lighting operation data of the office area through several sensors, and a preprocessing unit connected to the acquisition unit for preprocessing the lighting operation data to output lighting optimization data. An energy-saving control module, which is connected to the data processing module, includes a fusion unit for fusing the lighting optimization data and environmental status through a fusion algorithm to output an environmental fusion result, and an energy-saving control unit connected to the fusion unit for determining a lighting energy-saving scheme based on the environmental fusion result. The fusion determination module, which is connected to the energy-saving control module, is used to determine whether the operational stability of the fusion algorithm meets the requirements based on the anomaly rate of the environmental fusion results. A fluctuation adjustment module, which is connected to the fusion determination module, is used to determine the fusion fluctuation elimination ratio of the lighting operation data based on the proportion of sudden change points in the lighting optimization data per unit time when the running stability of the fusion algorithm does not meet the requirements. The timing adjustment module, which is connected to the fluctuation adjustment module, is used to determine the timing scale adjustment amount of abnormal lighting operation data based on the distortion rate of the lighting operation data.

[0024] Specifically, the sensors include human infrared sensors, illuminance sensors, and power sensors.

[0025] Specifically, lighting operation data includes the frequency of human activity, real-time illuminance, and real-time power of luminaires.

[0026] Specifically, preprocessing includes data cleaning, noise reduction, and filling in missing values.

[0027] Specifically, the lighting optimization data includes the frequency of human activity after data cleaning, the real-time illuminance value after noise reduction, and the real-time power of the luminaires after supplementing missing values.

[0028] Specifically, the process of fusing lighting optimization data and environmental conditions through a fusion algorithm to output an environmental fusion result involves combining lighting optimization data with current environmental condition information, using an adaptive weighted fusion method to allocate weights to each sensor data, eliminating redundant and contradictory features between data, fitting a unified environmental representation information that comprehensively reflects the actual lighting needs, and finally forming an environmental fusion result.

[0029] Specifically, the fusion algorithm is used to comprehensively calculate and integrate the features of lighting optimization data and environmental conditions. Through data weighting, time-series matching and anomaly removal, it generates an environmental fusion result that reflects the current environmental conditions.

[0030] Specifically, environmental conditions include lighting conditions, the presence and activity of people, and time conditions.

[0031] Specifically, the environmental integration results include population estimates, lighting adjustment directions, and lighting demand levels.

[0032] Specifically, the process of determining a lighting energy-saving scheme based on the environmental integration results involves analyzing the environmental integration results, calculating the corresponding lighting control parameters, and generating a lighting energy-saving scheme that matches the current environment.

[0033] Specifically, lighting energy-saving solutions include lighting switch status, lighting brightness control, and adjustment methods.

[0034] Specifically, the fusion fluctuation elimination ratio of lighting operation data is a proportional parameter used to eliminate lighting operation data to be fused based on the fluctuation amplitude.

[0035] Specifically, the time-series scale adjustment amount of abnormal lighting operation data is an adjustable amplitude value used to stretch or compress the time-series scale of abnormal lighting operation data in order to reduce the weight ratio of distorted data in the data fusion process.

[0036] In implementation, the system of this invention sets up a data processing module, an energy-saving control module, a fusion judgment module, a fluctuation adjustment module, and a timing adjustment module. It judges the operational stability of the fusion algorithm based on the anomaly rate of the environmental fusion results. Due to insufficient denoising capability of preprocessing for operational data, the output standardized operational data still contains significant noise interference and cannot truly reflect environmental state information. This causes the fusion algorithm to calculate based on distorted data when performing multi-sensor data fusion, resulting in improper weight settings and distortion of multi-sensor fusion results. By judging the operational stability of the fusion algorithm, problems such as unreasonable weight allocation or insufficient anomaly handling can be detected in a timely manner, reducing the anomaly rate and duration of anomalies in the environmental fusion results, and improving the stability of multi-sensor fusion. The system adjusts the fusion fluctuation removal ratio of lighting operational data based on the proportion of abrupt change points in lighting optimization data per unit time. Because the collected data contains a lot of interference data, it cannot accurately represent the actual environmental state, making it difficult for the preprocessing process to effectively distinguish between noise and valid data, thus causing denoising issues. To address insufficient capabilities, increasing the proportion of fluctuation removal during the fusion of lighting operation data can enhance the screening intensity of abnormal fluctuation data during preprocessing, reduce the impact of interfering data on standardized operation data, lower the proportion of abrupt changes in standardized operation data per unit time, improve the preprocessing's ability to distinguish between noise and valid data, and provide stable data input for subsequent multi-sensor data fusion. The temporal scale adjustment of abnormal lighting operation data can be adjusted based on the distortion rate of the lighting operation data. Since light sensors installed on desktops or other obstructed locations cannot collect raw operation data that accurately reflects the office environment's lighting level, the lighting operation data becomes distorted. Increasing the temporal scale adjustment of abnormal lighting operation data can effectively stretch or compress the influence range of distorted data on the time axis, reducing the weight of single-point or short-term distorted data within the fusion window, thereby suppressing the interference of outliers on the overall fusion result, improving the accuracy of the operation data in representing the true lighting state of the environment, and ultimately ensuring the effectiveness of operation data collection.

[0037] Please see Figure 2 The diagram shown is a logical flowchart illustrating the process of determining whether the operational stability of the fusion algorithm meets the requirements according to an embodiment of the present invention. In this embodiment, the operational stability of the fusion algorithm is quantified based on the anomaly rate of the environmental fusion results. The anomaly rate of the environmental fusion results is determined based on the ratio of the number of abnormal environmental fusion results to the total number of environmental fusion results. An anomaly is that the resulting environmental fusion is inconsistent with the actual lighting, people, temperature, etc.

[0038] Specifically, the fusion determination module responds to the anomaly rate of the environmental fusion results to determine whether the operational stability of the fusion algorithm meets the requirements.

[0039] Specifically, if the anomaly rate of the fusion determination module in response to the environmental fusion result is less than or equal to a preset anomaly rate, the stability of the fusion algorithm is determined to meet the requirements. The fusion determination module determines that the stability of the fusion algorithm does not meet the requirements if the anomaly rate of the environmental fusion result is greater than the preset anomaly rate.

[0040] It is understandable that the preset anomaly rate is based on the statistical distribution of historical statistical samples by those skilled in the art. Preferably, the anomaly rate of the environmental fusion results is negatively correlated with the stable operation of the fusion algorithm, wherein... The preset anomaly rate is based on the number of historical statistical samples. When the anomaly rate of the environmental fusion result is less than or equal to this value, it indicates that the environmental fusion result output by the current fusion algorithm has a high consistency with the actual environmental state. The fusion algorithm can effectively integrate multi-source sensor data, accurately capture environmental features such as changes in light intensity, human activity, and temperature fluctuations, and provide a stable and reliable fusion output of the overall office environmental state. Therefore, the operational stability of the fusion algorithm is deemed to meet the requirements. When the anomaly rate of the environmental fusion result is greater than this value, it indicates that there is a large deviation between the environmental fusion result output by the current fusion algorithm and the actual environmental state. The reliability of the fusion result is reduced. Therefore, the operational stability of the fusion algorithm is deemed to not meet the requirements.

[0041] Regarding the magnitude of the preset anomaly rate, those skilled in the art can determine the base number based on the number of historical statistical samples, and can set it according to the actual situation, which will not be elaborated here.

[0042] In implementation, the system of the present invention determines the operational stability of the fusion algorithm by setting a preset anomaly rate. Due to insufficient noise reduction capability of preprocessing for operational data, the output standardized operational data still contains significant noise interference and cannot truly reflect environmental state information. This causes the fusion algorithm to perform calculations based on distorted data when fusing multi-sensor data, resulting in improper weight settings and distortion of multi-sensor fusion results. By determining the operational stability of the fusion algorithm, problems such as unreasonable weight allocation or insufficient anomaly handling can be detected in a timely manner, reducing the anomaly rate and duration of anomalies in the environmental fusion results, improving the stability of multi-sensor fusion, and further enhancing the robustness of the fusion algorithm.

[0043] Please see Figure 3 As shown, it is a logical flowchart of the process for determining the fusion fluctuation elimination ratio of lighting operation data according to an embodiment of the present invention. In this embodiment, the effectiveness of preprocessing is quantified based on the proportion of mutation points in standardized operation data per unit time. The percentage of abrupt changes in lighting optimization data per unit time is determined by the ratio of the number of abrupt changes in lighting optimization data per unit time to the total number of sampling points; A mutation point is a sampling point where the data change gradient deviates significantly from the normal slow change pattern.

[0044] Specifically, in response to the condition that the operational stability of the fusion algorithm does not meet the requirements, the fluctuation adjustment module determines whether the effectiveness of the preprocessing meets the requirements based on the proportion of mutation points in the lighting optimization data per unit time.

[0045] Specifically, if the fluctuation adjustment module responds to the fact that the percentage of abrupt changes in the lighting optimization data per unit time is less than or equal to a preset first percentage, the effectiveness of the preprocessing is determined to meet the requirements. The fluctuation adjustment module determines that the effectiveness of preprocessing does not meet the requirements when the percentage of abrupt changes in the lighting optimization data within the unit time is greater than the preset first percentage.

[0046] Specifically, the fluctuation adjustment module responds to the fact that the percentage of abrupt changes in the lighting optimization data within the unit time is greater than the preset first percentage and less than the preset second percentage, thereby increasing the fusion fluctuation elimination ratio of the lighting operation data. The fluctuation adjustment module responds when the percentage of abrupt changes in the lighting optimization data within a unit time is greater than or equal to the preset second percentage, and preliminarily determines that the validity of the lighting operation data collection does not meet the requirements. It then determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

[0047] In this embodiment, the preset first proportion is less than the preset second proportion, wherein... If the percentage of abrupt changes in the lighting optimization data per unit time is less than or equal to the preset first percentage, the corresponding situation is to determine the effectiveness of the preprocessing. If the percentage of abrupt changes in the lighting optimization data per unit time is greater than the first preset percentage and less than the second preset percentage, the corresponding situation is that the collected data contains a lot of interference data, which cannot accurately represent the actual environmental state, making it difficult for the preprocessing process to effectively distinguish noise from valid data, resulting in insufficient noise reduction capability. If the percentage of abrupt changes in the lighting optimization data per unit time is greater than or equal to the preset second percentage, the corresponding situation is that when the light sensor is installed in a position where it is blocked by clutter such as a desktop, it is impossible to collect the original operating data that can truly reflect the lighting level of the office environment, resulting in distorted lighting operating data.

[0048] It is understood that the preset first proportion and preset second proportion are values ​​determined by those skilled in the art based on the statistical distribution of historical statistical samples and in conjunction with the preprocessing effectiveness corresponding to different proportions. Preferably, the proportion of abrupt changes in lighting optimization data per unit time is negatively correlated with preprocessing effectiveness, wherein, The first preset proportion is the proportion of mutation points corresponding to the inflection point where the abnormality rate of the environmental fusion results in the historical statistical distribution begins to rise as the proportion of mutation points increases. When the proportion of mutation points is less than or equal to this value, the abnormality rate of the environmental fusion results remains at a low level, indicating that the preprocessing process can effectively filter out sensor noise and random fluctuations, and the accuracy of the representation of the actual environmental state by the lighting optimization data meets the input requirements of the subsequent fusion algorithm, and the effectiveness of the preprocessing meets the requirements. The rising inflection point is determined based on the paired data of the abnormal rate and the proportion of mutation points in the environmental fusion results recorded in historical synchronous records. It is determined by statistically analyzing the rising trend of the abnormal rate of environmental fusion results with the change of the proportion of mutation points, and identifying the node where the rate of increase of the abnormal rate of environmental fusion results first increases significantly. The baseline for setting the abnormality rate of the environmental fusion result is a standard reference value pre-set by those skilled in the art based on the application requirements of the lighting control system, the maximum allowable input error range of the fusion algorithm, and the average level of the abnormality rate of the environmental fusion result under historical stable operating conditions.

[0049] The second preset proportion is the proportion of mutation points corresponding to the points where the abnormality rate of the environmental fusion results rises sharply in the historical statistical distribution. When the proportion of mutation points is greater than or equal to this value, it indicates that there are still a large number of mutation points in the preprocessed lighting optimization data, the data fluctuates violently, and it can no longer accurately reflect the real lighting change trend. This leads to a large deviation between the environmental fusion results output by the fusion algorithm and the actual environmental state. The noise reduction and smoothing capabilities of the preprocessing stage for the original running data are seriously insufficient. The severe rise point is determined based on the paired data of the abnormal rate and the proportion of mutation points in the environmental fusion results recorded in historical synchronous records. It is determined by statistically analyzing the upward trend of the abnormal rate of environmental fusion results with the change of the proportion of mutation points, and identifying the critical node where the abnormal rate of environmental fusion results rises rapidly. Specifically, the process of determining a severe increase point based on the paired data of the abnormal rate of the environmental fusion results and the proportion of mutation points recorded in historical synchronous records is as follows: the historical data are sorted in ascending order of the proportion of mutation points, and the increase rate of the abnormal rate of the environmental fusion results is statistically analyzed segment by segment. When the rate of increase of the abnormal rate of the environmental fusion results significantly increases after a certain mutation point proportion node and exceeds the preset abnormal rate increase rate benchmark, then the node is determined as a severe increase point.

[0050] The size of the preset first proportion and the preset second proportion depends on the number of historical statistical samples and the baseline set by those skilled in the art for the stable operation of the fusion algorithm. They can be set according to the actual situation, and will not be elaborated here.

[0051] Specifically, the increase in the fusion fluctuation elimination ratio of the lighting operation data is determined by the difference between the percentage of mutation points in the lighting optimization data per unit time and the preset first percentage.

[0052] Specifically, the increase in the fusion fluctuation elimination ratio of the lighting operation data is calculated by obtaining the percentage of mutation points in the lighting optimization data per unit time and the preset first percentage, calculating the difference, and using the difference as the benchmark for the increase in the fusion fluctuation elimination ratio. If the difference is greater than 0, it indicates that the percentage of mutation points in the current preprocessed lighting optimization data has deviated from the preset standard, and there is a risk of insufficient noise reduction capability. The fusion fluctuation elimination ratio of the lighting operation data is increased according to the magnitude corresponding to the difference. The larger the difference value, the higher the increase in the fusion fluctuation elimination ratio. If the difference is equal to or less than 0, it indicates that the current preprocessing effectiveness meets the preset standard, and the fusion fluctuation elimination ratio is not increased, maintaining the original fusion fluctuation elimination ratio unchanged.

[0053] Specifically, the method of increasing the fusion fluctuation elimination ratio of lighting operation data according to the amplitude corresponding to the difference is based on the difference between the preset first ratio and the percentage of sudden change points in the lighting optimization data per unit time as the basic amplitude benchmark. A mapping rule between the difference value and the increase of the fusion fluctuation elimination ratio is established in advance. The obtained difference value is substituted into the mapping relationship to match and obtain the unique corresponding increase of the fusion fluctuation elimination ratio.

[0054] In implementation, the system of the present invention adjusts the fusion fluctuation rejection ratio of lighting operation data by setting a preset first ratio and a preset second ratio. Since the collected data contains a lot of interference data, it cannot accurately represent the actual environmental state, making it difficult for the preprocessing process to effectively distinguish between noise and valid data, resulting in insufficient denoising capability. By increasing the fusion fluctuation rejection ratio of lighting operation data, the screening intensity of abnormal fluctuation data in the preprocessing process can be improved, the impact of interference data on standardized operation data can be reduced, the proportion of mutation points in standardized operation data per unit time can be reduced, the preprocessing can distinguish between noise and valid data can be improved, and a stable data input can be provided for subsequent multi-sensor data fusion, further improving the robustness of the fusion algorithm.

[0055] Please see Figure 4 The diagram shown is a logical flowchart illustrating the process of determining the time-series scale adjustment amount for abnormal lighting operation data according to an embodiment of the present invention. In this embodiment, the distortion rate of the lighting operation data is used to quantify the effectiveness of the lighting operation data collection. The distortion rate of lighting operation data is determined based on the ratio of the number of distorted lighting operation data points to the total number of lighting operation data points. Distortion refers to the phenomenon where the lighting operation data collected by the sensor shows sudden changes, shifts, jumps, or continuous deviations from the actual ambient light, personnel, and temperature conditions, and fails to reflect the actual office environment.

[0056] Specifically, the timing adjustment module, in response to a condition where the percentage of abrupt changes in the lighting optimization data per unit time is greater than or equal to the preset second percentage, determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

[0057] Specifically, the timing adjustment module determines that the validity of the lighting operation data collection meets the requirements when the distortion rate of the lighting operation data is less than or equal to the preset distortion rate. The timing adjustment module responds when the distortion rate of the lighting operation data is greater than the preset distortion rate, determines that the acquisition validity of the lighting operation data does not meet the requirements, and increases the timing scale adjustment amount of the abnormal lighting operation data.

[0058] It is understood that the preset distortion rate is a value determined by those skilled in the art based on the statistical distribution of distortion rates in effective preprocessing of lighting operation data, combined with the effective acquisition status of lighting operation data corresponding to different distortion rates. Preferably, the distortion rate of lighting operation data is negatively correlated with the effective acquisition status of lighting operation data. The preset distortion rate is the distortion rate corresponding to the inflection point where the effectiveness of preprocessing begins to decrease as the distortion rate of lighting operation data increases in the historical statistical distribution. When the distortion rate of lighting operation data is less than or equal to this value, the effectiveness of preprocessing remains at a high level, indicating that the deviation between the lighting operation data collected by the sensor and the real environment is within an acceptable range, the sensor measurement accuracy meets the requirements, the effective acquisition of lighting operation data is good, the preprocessing stage can complete noise reduction and smoothing based on reliable raw data, and the acquisition effectiveness of lighting operation data meets the input requirements of subsequent fusion algorithms. The inflection point is determined based on the paired data of the preprocessing effectiveness index and the distortion rate of the lighting operation data recorded in history. It is determined by statistically analyzing the downward trend of the preprocessing effectiveness index with the change of distortion rate and identifying the node where the rate of decrease of the preprocessing effectiveness index first increases significantly. The baseline for setting the preprocessing effectiveness index is a standard reference value pre-set by those skilled in the art, taking into account the requirements of the lighting control system for data acquisition stability, the maximum data deviation tolerance range allowed by the fusion algorithm, and the average level of the preprocessing effectiveness index under historical stable operating conditions.

[0059] The preset distortion rate depends on the number of historical samples and the effective data collection baseline for lighting operation data by those skilled in the art. It can be set according to the actual situation and will not be elaborated here.

[0060] Specifically, the increase in the time-scale adjustment of the abnormal lighting operation data is determined by the difference between the distortion rate of the lighting operation data and the preset distortion rate.

[0061] Specifically, the increase in the time-series scale adjustment amount of the abnormal lighting operation data is achieved by obtaining the distortion rate of the lighting operation data and the preset distortion rate, calculating the difference between the distortion rate of the lighting operation data and the preset distortion rate, and using the difference as the benchmark for increasing the time-series scale adjustment amount. If the difference is greater than 0, it indicates that the distortion rate of the current lighting operation data has exceeded the preset allowable range, and there is a risk that the sensor-collected data is seriously deviating from the real environmental state. It is necessary to effectively stretch or compress the influence range of the distorted data on the time axis to suppress the interference of outliers on the fusion results. Then, the time-series scale adjustment amount of the abnormal lighting operation data is increased according to the magnitude corresponding to the difference. The larger the difference value, the higher the degree of distortion of the lighting operation data, and the stronger the demand for time-series scale adjustment. Therefore, the increase in the time-series scale adjustment amount is larger. If the difference is equal to or less than 0, it indicates that the distortion rate of the current lighting operation data is within the preset allowable range, and the effectiveness of the lighting operation data collection meets the requirements. The time-series scale adjustment amount is not increased and remains unchanged.

[0062] Specifically, the step of increasing the temporal scale adjustment amount of abnormal lighting operation data according to the amplitude corresponding to the difference is to use the difference between the distortion rate of the lighting operation data and the preset distortion rate as the basic adjustment amplitude benchmark, pre-establish a mapping rule between the distortion rate difference and the increase in the temporal scale adjustment amount, substitute the obtained difference into the mapping relationship, match to obtain a unique corresponding temporal scale adjustment amount adjustment value, and increase the temporal scale adjustment amount of abnormal lighting operation data based on the adjustment value. This enables the fusion algorithm to improve its ability to stretch or compress distorted data in the time dimension during the processing of lighting optimization data, reduce the weight ratio of single-point or short-term distorted data in the fusion window, suppress the interference of abnormal data on the overall fusion result, and improve the accuracy of the fusion algorithm in representing the real state of the environment.

[0063] In implementation, the system of this invention adjusts the temporal scale of abnormal lighting operation data by setting a preset distortion rate. When the light sensor is installed in a position where it is obstructed by clutter such as a desktop, it is impossible to collect the original operation data that can truly reflect the lighting level of the office environment, resulting in distorted lighting operation data. By increasing the temporal scale adjustment of abnormal lighting operation data, the influence range of distorted data on the time axis can be effectively stretched or compressed, reducing the weight ratio of single-point or short-term distorted data in the fusion window, thereby suppressing the interference of outliers on the overall fusion result, improving the accuracy of the operation data in representing the true lighting state of the environment, and thus satisfying the validity of operation data collection, further improving the robustness of the fusion algorithm.

[0064] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A multi-sensor linkage based intelligent lighting energy saving control system, characterized in that, include: The data processing module includes an acquisition unit for collecting lighting operation data of the office area through several sensors, and a preprocessing unit connected to the acquisition unit for preprocessing the lighting operation data to output lighting optimization data. An energy-saving control module, which is connected to the data processing module, includes a fusion unit for fusing the lighting optimization data and environmental status through a fusion algorithm to output an environmental fusion result, and an energy-saving control unit connected to the fusion unit for determining a lighting energy-saving scheme based on the environmental fusion result. The fusion determination module, which is connected to the energy-saving control module, is used to determine whether the operational stability of the fusion algorithm meets the requirements based on the anomaly rate of the environmental fusion results. A fluctuation adjustment module, which is connected to the fusion determination module, is used to determine the fusion fluctuation elimination ratio of the lighting operation data based on the proportion of sudden change points in the lighting optimization data per unit time when the running stability of the fusion algorithm does not meet the requirements. The timing adjustment module, which is connected to the fluctuation adjustment module, is used to determine the timing scale adjustment amount of abnormal lighting operation data based on the distortion rate of the lighting operation data.

2. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 1, wherein, The fusion determination module responds to the anomaly rate of the environmental fusion results to determine whether the operational stability of the fusion algorithm meets the requirements.

3. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 2, wherein, If the fusion determination module responds to the environment fusion result and the abnormality rate is less than or equal to the preset abnormality rate, the fusion algorithm's operational stability is deemed to meet the requirements. The fusion determination module determines that the stability of the fusion algorithm does not meet the requirements if the anomaly rate of the environmental fusion result is greater than the preset anomaly rate.

4. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 3, wherein, In response to the condition that the operational stability of the fusion algorithm does not meet the requirements, the fluctuation adjustment module determines whether the effectiveness of the preprocessing meets the requirements based on the proportion of mutation points in the lighting optimization data per unit time.

5. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 4, wherein, The fluctuation adjustment module responds when the percentage of abrupt changes in the lighting optimization data per unit time is less than or equal to a preset first percentage, and determines that the effectiveness of the preprocessing meets the requirements. The fluctuation adjustment module responds when the percentage of abrupt changes in the lighting optimization data per unit time exceeds the preset first percentage, and determines that the effectiveness of the preprocessing does not meet the requirements.

6. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 5, wherein, The fluctuation adjustment module responds to the fact that the percentage of abrupt changes in the lighting optimization data per unit time is greater than the preset first percentage and less than the preset second percentage, and increases the fusion fluctuation elimination ratio of the lighting operation data. The fluctuation adjustment module responds when the percentage of abrupt changes in the lighting optimization data within a unit time is greater than or equal to the preset second percentage, and preliminarily determines that the validity of the lighting operation data collection does not meet the requirements. It then determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

7. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 6, wherein, The increase in the fusion fluctuation elimination ratio of the lighting operation data is determined by the difference between the percentage of mutation points in the lighting optimization data per unit time and the preset first percentage.

8. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 7, wherein, The timing adjustment module, in response to a condition where the percentage of abrupt changes in the lighting optimization data within a unit time is greater than or equal to the preset second percentage, determines whether the validity of the lighting operation data collection meets the requirements based on the distortion rate of the lighting operation data.

9. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 8, wherein, The timing adjustment module determines that the validity of the lighting operation data collection meets the requirements when the distortion rate of the lighting operation data is less than or equal to the preset distortion rate. The timing adjustment module responds when the distortion rate of the lighting operation data is greater than the preset distortion rate, determines that the acquisition validity of the lighting operation data does not meet the requirements, and increases the timing scale adjustment amount of the abnormal lighting operation data.

10. The multi-sensor linkage based intelligent lighting energy saving control system according to claim 9, wherein, The increase in the time-scale adjustment of the abnormal lighting operation data is determined by the difference between the distortion rate of the lighting operation data and the preset distortion rate.

Citation Information

Patent Citations

  • Intelligent AI miner lamp system based on multi-modal fusion and control method

    CN120426538A