Intelligent illumination control method for severe environment based on multi-sensor fusion

Through multi-sensor fusion technology, combining entropy weight model and fuzzy logic control, lighting demand characteristics are extracted and lighting demand is predicted, and the problems of insufficient data fusion and dissatisfaction of user demand in intelligent lighting control in harsh environments in the existing technology are solved, achieving high efficiency , flexible lighting management.

CN118973017AActive Publication Date: 2024-11-15JIANGSU ZHENHUA INTELLIGENT TECH CO LTD

Patent Information

Application Number
CN202411421225.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-12
Publication Date
2024-11-15
Estimated Expiration
2044-10-12

AI Technical Summary

Technical Problem

The existing intelligent lighting control technology is simple to process data fusion in harsh environments, and fails to make full use of multimodal sensor network information, resulting in insufficient environmental perception accuracy and robustness, and fails to dynamically adjust the sensor data weight, which cannot meet users. Personalized lighting needs.

Method used

Using multi-sensor fusion method, data is collected through multi-modal sensor networks, entropy weight model is used to analyze the importance of sensor data and weight allocation, combined with fuzzy logic control and machine learning model, lighting demand characteristics are extracted, lighting demand is predicted, lighting demand is dynamically adjusted Strategy to meet different environments and user needs.

Benefits of technology

It significantly improves the performance of intelligent lighting systems in harsh environments, provides a more comfortable, energy-saving and safe lighting environment, ensures the stability and flexibility of the lighting system, meets diverse needs, and reduces energy consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118973017A_ABST
    Figure CN118973017A_ABST
Patent Text Reader

Abstract

The invention relates to the field of electric lighting control, and discloses a severe environment intelligent lighting control method based on multi-sensor fusion, which is used for improving the performance of an intelligent lighting system in a severe environment. And the device can be applied to complex and severe working environments such as underground mining. Through arrangement of the multi-mode sensor network, various environmental parameters such as illumination intensity, temperature, pressure, vibration and corrosive substances can be monitored and fused in real time. By means of the data, the actual state of the current environment can be evaluated more accurately, the future change trend can be predicted, the importance of sensor data is analyzed through an entropy weight model, fuzzy logic control is combined, and the system can output an optimized illumination control result. Besides, through kernel density estimation and a GBM gradient elevator model, distribution of future severe environment illumination demands can be predicted and a severe environment illumination demand value can be quantified so that a more accurate severe environment intelligent illumination control strategy can be formulated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electric lighting control, and in particular to a harsh environment intelligent lighting control method based on multi-sensor fusion. Background Art

[0002] With the rapid development of science and technology and the continuous improvement of people's quality of life, intelligent lighting systems play an increasingly important role in modern buildings and home environments. Especially in harsh environments, such as extreme weather, complex working scenes or emergency situations, the stability and intelligence level of intelligent lighting systems are particularly important. These systems not only need to be able to automatically adapt to changes in the external environment, but also meet the personalized lighting needs of users, while ensuring efficient use of energy.

[0003] However, existing intelligent lighting control technologies still have many shortcomings when facing harsh environments. First, most systems are relatively simple in data fusion processing and fail to fully utilize the information redundancy and complementarity of multimodal sensor networks, resulting in insufficient accuracy and robustness in environmental perception. Second, existing technologies often ignore the importance of sensor data and weight distribution issues when formulating lighting control strategies, and are unable to make dynamic adjustments based on the reliability and effectiveness of different sensors in harsh environments. In addition, existing systems do not fully consider users' personalized lighting needs, lack flexibility and adaptability, and are difficult to meet users' diverse lighting needs.

[0004] In order to solve the above problems, this study proposes a harsh environment intelligent lighting control method based on multi-sensor fusion, which can significantly improve the performance of intelligent lighting systems in harsh environments and provide users with a more comfortable, energy-saving and safe lighting environment. Summary of the invention

[0005] The present invention provides a harsh environment intelligent lighting control method based on multi-sensor fusion, which is used to improve the performance of the intelligent lighting system in harsh environments and provide users with a more comfortable, energy-saving and safe lighting environment.

[0006] The first aspect of the present invention provides a method for intelligent lighting control in a harsh environment based on multi-sensor fusion, and the method comprises: collecting input control harsh environment information according to a multi-modal sensor network, acquiring and fusing the input control harsh environment information in the multi-modal sensor network data, including light intensity, color, image, vibration, temperature, pressure and corrosive substance monitoring data, to obtain harsh environment fusion state information; using a preset entropy weight model, combined with the harsh environment fusion state information, analyzing the importance of data of different sensors in the multi-modal sensor network, and assigning weights according to their reliability and effectiveness in harsh environments, to obtain the weight and reading of each sensor data; using Fuzzy logic control, taking the reading of each sensor data as an input variable, using the weight of each sensor data to adjust the input membership function, and obtaining the output result of the harsh environment lighting control system; extracting lighting demand related features based on the harsh environment fusion state information, including: based on the light sensor data, combined with time, light contrast factors inside and outside the working environment, and special lighting conditions in the harsh environment, the special lighting conditions in the harsh environment include the dimness of the underground mining environment and uneven lighting, predicting the most suitable light intensity through a machine learning model, and obtaining the first lighting demand related features; using color sensor and camera data to analyze the environmental color, human activities, and the characteristics of the harsh environment on color and color temperature. The special requirements of the harsh environment on color and color temperature include the requirements for the anti-corrosion performance of equipment in corrosive environments. Pattern recognition technology is used to determine the combination of color and color temperature to obtain the second lighting demand related characteristics; combined with human movement detection data, historical behavior patterns and the impact of harsh environments on human movement and lighting needs, the impact of harsh environments on human movement and lighting needs includes the restricted flow of people in high temperature and high pressure environments. Time series analysis or machine learning algorithms are used to predict the changing trend of lighting needs in the future, including the flow path of people and the conversion of work areas, to obtain the third lighting demand related characteristics; the first lighting demand related characteristics, the second lighting demand related characteristics and the third lighting demand related characteristics are analyzed and analyzed. The data is annotated to mark the changes in lighting demand under special events and user preference patterns; data enhancement technology is used, including synthetic data generation and time series expansion, to enrich the data set and improve the generalization ability of the model; a historical data set of harsh environment is constructed based on the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features; a probability density function of the historical data set of harsh environment is estimated based on a preset kernel density estimation, and a distribution estimate of future harsh environment lighting demand is obtained by selecting a kernel function and a bandwidth parameter; a quantified harsh environment lighting demand value is obtained based on the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features combined with a preset GBM gradient boosting machine model;According to the output results of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting demand and the quantified harsh environment lighting demand value, a harsh environment intelligent lighting control strategy is obtained. ;

[0007] Optionally, in a first implementation method of the first aspect of the present invention, the multimodal sensor network includes a light sensor, a temperature sensor, a pressure sensor, a vibration sensor and a corrosion monitoring sensor, and utilizes the heat and electrical signals generated by each sensor itself as additional resources to obtain an additional resource data set, each sensor collects environmental data at a preset sampling frequency, and packages the data, and the aggregation node in the sensor network collects data from each sensor to form a multimodal input control environment sensor data set; a dynamic sensor activation strategy is preset to dynamically select and activate the most relevant sensors according to current environmental conditions and lighting requirements, and reduce or turn off the sampling frequency of the light intensity sensor when there is sufficient light during the day, and increase the sampling frequency at night or when the light is dim; the sensor data is fused at different time scales, including seconds, minutes, and hours, to capture the environmental change characteristics of different time scales and obtain fusion status information of harsh environments.

[0008] Optionally, in a second implementation method of the first aspect of the present invention, the weight distribution of the entropy weight model is combined with an online learning algorithm to update the weight distribution in real time; a multi-level fuzzy logic control is designed, in which each level is responsible for processing sensor data and lighting control tasks of different granularities, the low-level controller is responsible for basic brightness adjustment, and the high-level controller is responsible for more complex scene recognition and lighting strategy adjustment; using the fuzzy reasoning mechanism, fuzzy reasoning is performed based on the adjusted membership function and fuzzy rule base to obtain the output result of the harsh environment lighting control system.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, a multidimensional kernel density estimation method is used, including a Copula-based multidimensional kernel density estimation, to more accurately capture the joint distribution between features and obtain respective probability density functions; the probability density function of the harsh environment historical data set is used to estimate the distribution of future harsh environment lighting requirements using a sliding window method: in, Is the future harsh environment lighting demand x t+1 The conditional probability of is the indicator function, N is the number of sliding windows in the harsh environment historical data set, is the lighting demand sequence in the harsh environment historical data set; the distribution estimate of future harsh environment lighting demand is obtained.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the output results of the harsh environment lighting control system are evaluated, and by comparing the actual output of the lighting system with the preset lighting standards or user expectations, it is determined whether the current lighting system meets the lighting needs, and whether there are problems of too bright, too dark, or uneven light distribution, combined with quantifying the harsh environment lighting demand value; forming an environment-demand-response data set; and conducting an in-depth analysis of the environment-demand-response data set to identify the changing trend, abnormal values, and periodic laws of the lighting demand, and obtain an intelligent lighting control strategy for harsh environments.

[0011] Optionally, in a sixth implementation manner of the first aspect of the present invention, it also includes: setting a baseline lighting control strategy based on a historical data set of harsh environments and user preferences, including default light intensity, color temperature, and dynamic adjustment rules; formulating a dynamic adjustment strategy based on an estimated distribution of future harsh environment lighting needs, and when it is predicted that future harsh environment lighting needs will increase, adjusting the light intensity or color temperature in advance to meet user needs; collecting feedback data from the lighting control system in real time, including actual light intensity, color temperature, and energy consumption, and comparing them with expected values, and making timely adjustments when deviations are found; regularly evaluating and optimizing control strategies, and continuously adjusting and improving control strategies based on user feedback, environmental changes, and technological advances, so as to improve the intelligence level of lighting control and user satisfaction.

[0012] The second aspect of the present invention provides an intelligent lighting control device for harsh environments based on multi-sensor fusion, and the intelligent lighting control device for harsh environments based on multi-sensor fusion includes: an acquisition module, which is used to collect input control harsh environment information based on a multi-modal sensor network, acquire and fuse the input control harsh environment information in the multi-modal sensor network data, including light intensity, temperature, pressure, vibration and corrosive substance monitoring data, to obtain harsh environment fusion state information; a processing module, which is used to use a preset entropy weight model, combined with the harsh environment fusion state information, to analyze the importance of data of different sensors in the multi-modal sensor network, and to assign weights according to their reliability and effectiveness in harsh environments, to obtain the weight and reading of each sensor data; adopt fuzzy logic control, take the reading of each sensor data as an input variable, and use the weight of each sensor data to adjust the input membership function to obtain the output result of the harsh environment lighting control system; an extraction module, used to extract lighting demand-related features according to the harsh environment fusion state information to obtain first lighting demand-related features, second lighting demand-related features, and third lighting demand-related features, and to construct a harsh environment historical data set according to the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features; a quantization module, used to estimate the probability density function of the harsh environment historical data set according to a preset kernel density estimation, obtain a distribution estimate of future harsh environment lighting demand by selecting a kernel function and a bandwidth parameter, and obtain a quantized harsh environment lighting demand value according to the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features combined with a preset GBM gradient boosting machine model; an allocation module, used to obtain a harsh environment intelligent lighting control strategy according to the output result of the harsh environment lighting control system, the distribution estimate of future harsh environment lighting demand, and the quantized harsh environment lighting demand value.

[0013] The third aspect of the present invention provides an intelligent lighting control device for harsh environments based on multi-sensor fusion, comprising: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory so that the intelligent lighting control device for harsh environments based on multi-sensor fusion executes the above-mentioned intelligent lighting control method for harsh environments based on multi-sensor fusion.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned intelligent lighting control method for harsh environments based on multi-sensor fusion.

[0015] In the technical solution provided by the present invention, environmental information is collected through a multimodal sensor network, and a Kalman filter is used for data fusion to obtain fusion state information of harsh environment. Then, the importance of sensor data is analyzed in combination with the entropy weight model to provide adjustment basis for fuzzy logic control. By extracting the relevant features of lighting demand and constructing a historical data set of harsh environment, the kernel density estimation and GBM gradient boosting machine models are used to predict the distribution of future harsh environment lighting demand and quantify the harsh environment lighting demand value. Finally, the above information is combined to formulate an intelligent lighting control strategy to achieve intelligent and precise control of the lighting system.

[0016] Through multi-sensor fusion technology, the present invention can more comprehensively perceive environmental changes, adjust lighting parameters in real time, and meet lighting needs in different scenarios.

[0017] This technology takes into special consideration the impact of harsh environmental factors and ensures the reliable operation of the lighting system under harsh conditions by formulating emergency lighting control strategies.

[0018] The present invention avoids unnecessary lighting waste and effectively reduces energy consumption by accurately predicting and adjusting lighting needs, thereby achieving a green and environmentally friendly lighting solution.

[0019] In summary, the present invention combines a variety of advanced algorithms and models, can self-learn, self-optimize, and continuously adapt to environmental changes and changes in user needs, thereby improving the intelligence level of the lighting system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of an embodiment of a method for intelligent lighting control in a harsh environment based on multi-sensor fusion in an embodiment of the present invention; Figure 2 It is a schematic diagram of another embodiment of the harsh environment intelligent lighting control method based on multi-sensor fusion in an embodiment of the present invention; Figure 3 A schematic diagram of an embodiment of a harsh environment intelligent lighting control device based on multi-sensor fusion in an embodiment of the present invention; Figure 4 It is a schematic diagram of an embodiment of a harsh environment intelligent lighting control device based on multi-sensor fusion in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The embodiment of the present invention provides a harsh environment intelligent lighting control method based on multi-sensor fusion, which is used to improve the performance of the intelligent lighting system in harsh environments and provide users with a more comfortable, energy-saving and safe lighting environment. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present invention and the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0022] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the harsh environment intelligent lighting control method based on multi-sensor fusion in the embodiment of the present invention includes: 101. Collect input control harsh environment information based on the multimodal sensor network, obtain and fuse the input control harsh environment information in the multimodal sensor network data, including light intensity, temperature, pressure, vibration and corrosive material monitoring data, and obtain harsh environment fusion state information; It is understandable that the execution subject of the present invention may be a harsh environment intelligent lighting control device based on multi-sensor fusion, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0023] It should be noted that considering an underground mining environment, lighting control is crucial, not only related to work efficiency, but also directly affects the safety of workers. Due to the harsh underground environment, there are challenges such as high temperature, high pressure, vibration and corrosion, so it is necessary to build an intelligent lighting control system that can cope with these challenges.

[0024] First, a multimodal sensor network is deployed in key areas of the underground mining environment (such as working faces, channel intersections, etc.). These sensors include but are not limited to light sensors, temperature sensors, pressure sensors, vibration sensors, and corrosion monitoring sensors. Each sensor is optimized for the specific challenges of the underground environment to ensure reliable operation under harsh conditions. Light sensor: used to monitor the ambient light intensity in real time and provide direct input control signals for the lighting system. Temperature sensor: Able to withstand high temperature environments, such as using platinum-based sensors, its operating range can cover -70°C to 500°C to monitor underground temperature changes. Pressure sensor: used to monitor changes in underground air or water pressure to ensure the safe operation of the lighting system in a high-pressure environment. Vibration sensor: Able to detect and quantify underground vibration levels and provide stability feedback for the lighting system. Corrosion monitoring sensor: Monitors corrosive substances that may be present in the environment to protect lighting equipment and sensor networks from damage.

[0025] Data collection and preprocessing: Each sensor continuously collects environmental data at a set frequency (such as every second or every minute). The collected raw data first undergoes preprocessing steps, including signal amplification, analog-to-digital conversion, noise filtering, and interference compensation to ensure the accuracy and reliability of the data.

[0026] Multimodal input control environment sensor data fusion processing: The pre-processed multimodal sensor data is transmitted to the central control unit for data fusion processing. A variety of data fusion methods can be used here, such as Kalman filtering or Bayesian estimation, to integrate the information of each sensor and obtain the fusion state information of the harsh environment. Taking the Kalman filtering method as an example, this method can recursively determine the estimated value of the fused data so that the estimated value is optimal in a statistical sense. By fusing the data of multiple sensors, the system can more accurately estimate the actual state of the current environment (such as light intensity, temperature, pressure, etc.) and predict future changes.

[0027] Harsh environment fusion status information application and lighting control, based on the fusion of environmental status information, the intelligent lighting control system can adjust the brightness, color temperature and other parameters of the lamps in real time to provide the best lighting effect and ensure the safety of workers. For example, when the ambient light intensity is detected to be too low, the system will automatically increase the brightness of the lamps; when the temperature is too high, the working state of the lamps can be adjusted to reduce heat generation.

[0028] Data example: At a certain moment, the light sensor detected that the ambient light intensity was 50 lux (lx), the temperature sensor showed that the current temperature was 45°C, the pressure sensor read 1.2 atmospheres (atm), the vibration sensor detected slight vibrations (amplitude <0.5mm), and the corrosion monitoring sensor did not detect corrosive substances. After the data was fused and processed, the system determined that the current environment needed to increase the lighting brightness appropriately to ensure that workers could clearly see the situation in the work area. Therefore, the system automatically increased the brightness of the lamps to 100 lux (lx) and adjusted the color temperature to a warmer tone to reduce visual fatigue.

[0029] 102. Using the preset entropy weight model, combined with the harsh environment fusion state information, analyze the importance of data from different sensors in the multimodal sensor network, and assign weights according to their reliability and effectiveness in harsh environments, obtain the weight and reading of each sensor data, adopt fuzzy logic control, take the reading of each sensor data as the input variable, and use the weight of each sensor data to adjust the input membership function to obtain the output result of the harsh environment lighting control system; It should be noted that in the weight distribution and fuzzy logic control of the intelligent lighting control system in the underground mining environment, the harsh environment fusion state information and entropy weight model are as follows: First, the environmental information is obtained and fused through the multimodal sensor network described earlier to obtain the harsh environment fusion state information. This information includes multiple dimensions such as light intensity, temperature, pressure, vibration, etc.

[0030] Next, we use the preset entropy weight model to analyze the importance of these sensor data. The entropy weight method is a method to determine the objective weight according to the magnitude of the indicator variability. Here, we evaluate the importance of sensor data based on its historical variability and stability in the current environment.

[0031] For example, we have the following set of sensor readings (just an example, the actual data may change in real time depending on the downhole environment): Light sensor reading: 80 lx Temperature sensor reading: 40°C Pressure sensor reading: 1.5 atm Vibration sensor reading: 0.3 mm / s Through entropy weight model analysis, we can get the preliminary weight of each sensor data: Light sensor weight: 0.4 Temperature sensor weight: 0.3 Pressure sensor weight: 0.2 Vibration sensor weight: 0.1 Weight allocation and adjustment,Based on the preliminary weights obtained by the entropy weight model,,we can further adjust them according to the real-time and historical,performance of the sensors.,For example, if a sensor has shown a high failure rate or unstable data,in the recent period, its weight may be appropriately reduced.

[0032] After adjustment, we get the final weights for each sensor data, which will be used in subsequent fuzzy logic control.

[0033] Fuzzy logic control implementation, in fuzzy logic control, we take the reading of each sensor as the input variable. At the same time, the weight of each sensor data is used to adjust the membership function of these inputs. The membership function is a function used in fuzzy logic to describe the degree to which the input variable belongs to a fuzzy set. For the light sensor, its reading is 80 lx. We can define a fuzzy set "suitable light" and calculate the degree to which the reading belongs to the "suitable light" set based on its weight and the preset membership function. Similarly, similar calculations are performed for other sensors. Finally, through fuzzy reasoning and defuzzification steps, we get the output result of the harsh environment lighting control system. This output result may be a specific lighting brightness value, color temperature value or other control instructions, which are used to adjust the underground lighting equipment to meet the lighting needs and safety requirements in the current environment.

[0034] 103. Extract lighting demand-related features based on the harsh environment fusion state information to obtain first lighting demand-related features, second lighting demand-related features, and third lighting demand-related features, and construct a harsh environment historical data set based on the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features; It should be noted that the acquisition of fusion state information in harsh environment: First, the multi-dimensional information of the underground environment is acquired and fused through the multimodal sensor network described above, including but not limited to light intensity, temperature, pressure, vibration, etc. This information constitutes the fusion state information of harsh environment, which provides the basis for the subsequent extraction of lighting demand features.

[0035] Based on the fusion state information of the harsh environment, we can extract features that are closely related to lighting requirements. These features reflect the actual requirements of the underground environment for the lighting system and help to achieve refined lighting control.

[0036] The first lighting demand-related feature: light intensity demand, extraction method: based on the light intensity data in the harsh environment fusion status information, combined with the lighting demand standards of the underground working surface (such as the minimum illumination value specified by the national safety production standards), calculate the required light intensity in the current environment.

[0037] Specific data: At a certain moment, the actual illumination intensity of the underground working surface is 100 lx, while the minimum illumination value specified by the standard is 200 lx. Therefore, the extracted illumination intensity requirement characteristic value is 200 lx.

[0038] The second lighting demand-related feature: color temperature demand, extraction method: Determine the appropriate color temperature value in the current environment based on the temperature data in the harsh environment fusion status information and the human body's comfortable perception range of color temperature at different temperatures (such as preference for low color temperature in a warm environment and preference for high color temperature in a cold environment).

[0039] Specific data: The underground temperature is 30°C, which is a warm environment. According to the human body's comfortable perception range, the appropriate color temperature value is determined to be 4000K (warmer tone). Therefore, the extracted color temperature requirement feature value is 4000K.

[0040] The third lighting demand-related feature: stability demand, extraction method: evaluate the stability of the underground environment based on the vibration and pressure data in the harsh environment fusion state information. In areas with frequent vibration or large pressure changes, the stability requirements of the lighting system are higher.

[0041] Specific data: The reading of the vibration sensor in a certain area is 0.5 mm / s (mild vibration), and the reading of the pressure sensor is 1.2 atm (relatively stable). Based on these data, the stability requirement of this area is assessed to be medium. Therefore, the extracted stability requirement characteristic value can be quantified as a value between 0 and 1, such as 0.6 (indicating medium stability requirement).

[0042] Construct a historical data set for harsh environments, organize and store the first lighting demand-related features (light intensity requirements), the second lighting demand-related features (color temperature requirements), and the third lighting demand-related features (stability requirements) extracted above in a time series to form a historical data set for harsh environments. These data sets can be used to train and optimize the algorithm model of the intelligent lighting control system to improve the system's adaptability and accuracy in future operations.

[0043] 104. Estimating the probability density function of the harsh environment historical data set according to the preset kernel density estimation, obtaining the distribution estimation of the future harsh environment lighting demand by selecting the kernel function and the bandwidth parameter, and obtaining the quantified harsh environment lighting demand value according to the first lighting demand related feature, the second lighting demand related feature, and the third lighting demand related feature combined with the preset GBM gradient boosting machine model; It should be noted that the intelligent lighting demand prediction and quantification of the underground mining environment, the environmental parameters of the area are as follows: average temperature: 45°C; average pressure: 1.5 atm; vibration frequency: 0.4 mm / s; corrosive gas concentration: low; these environmental parameters are continuously monitored through a multimodal sensor network to form a historical data set of harsh environments.

[0044] Preparation of historical dataset for harsh environment,Based on the data of the past month, we constructed a historical dataset for,harsh environment with the following features: First lighting demand related characteristics: light intensity requirement (unit: lx) Example data: [150, 160, 170, 180, ...] Second lighting requirement related characteristics: color temperature requirement (unit: K) Example data: [4200, 4300, 4100, 4250, ...] Third lighting demand-related characteristics: stability demand (value between 0-1) Example data: [0.7, 0.75, 0.65, 0.72, ...] Kernel density estimation (KDE) implementation, kernel function selection: We choose Gaussian kernel function as the kernel function of KDE. Determine bandwidth parameter: Through cross-validation method, the optimal bandwidth parameter is determined to be 0.1. Probability density function estimation: KDE is used to estimate the probability density function of the light intensity demand in the harsh environment historical data set to obtain the distribution estimate of the future harsh environment light demand. Estimation results: The light intensity demand is mainly distributed between 150-200 lx, and the peak occurs near 170 lx.

[0045] GBM gradient boosting machine model application, feature input: the first, second, and third lighting demand related features are used as the input of the GBM model. Model training: the GBM model is trained using the harsh environment historical data set to optimize the model parameters. Quantitative harsh environment lighting demand value prediction: the trained GBM model is applied, combined with the current harsh environment fusion state information, to predict the future quantitative harsh environment lighting demand value.

[0046] Prediction results: The current harsh environment fusion status information shows that the light intensity requirement is 165 lx, the color temperature requirement is 4200 K, and the stability requirement is 0.7. Based on these inputs, the GBM model predicts that the future quantitative harsh environment lighting requirement value is 172 lx (indicating that the system should be adjusted to this light intensity while meeting safety and work efficiency).

[0047] Based on the output results of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting demand and the quantified harsh environment lighting demand value, the harsh environment intelligent lighting control strategy is obtained; It should be noted that in underground mining environments, lighting is critical to work efficiency and worker safety. Considering the harsh conditions such as high temperature, high pressure, vibration and corrosion, we need to build an intelligent lighting control system that can optimize lighting strategies based on multi-sensor fusion technology.

[0048] The current output results of the lighting control system show: current light intensity: 200 lx; ​​current color temperature: 4000 K; The distribution estimation of future harsh environment lighting demand is carried out by kernel density estimation method: Estimated results: In the future, the demand for lighting in harsh environments will mainly be distributed between 150-250 lx, among which the demand in the range of 180-220 lx is the most concentrated.

[0049] Quantify the lighting demand value for harsh environments. The quantify lighting demand value for harsh environments predicted by the GBM gradient boosting machine model: Prediction results: The quantify lighting demand value for harsh environments is 210 lx.

[0050] The intelligent lighting control strategy is formulated by comparing the output results of the harsh environment lighting control system with the future harsh environment lighting demand distribution: the current light intensity is 200 lx, while the future harsh environment lighting demand is mainly distributed in 150-250lx, and the predicted demand value is 210 lx.

[0051] Adjustment strategy: Since the current light intensity is slightly lower than the predicted demand value, the control system should gradually adjust the light intensity to about 210 lx to meet the future harsh environment lighting needs. At the same time, considering work efficiency and workers' visual comfort, the color temperature should be maintained between 4000-4500 K.

[0052] Implementation details: The lighting system should gradually increase the light intensity to avoid sudden changes that may cause visual shock to workers. The light intensity and color temperature can be adjusted by adjusting the power and color ratio of LED lamps. The monitoring system should detect environmental parameters and lighting effects in real time to ensure the effectiveness of the lighting strategy.

[0053] Specific data: Before adjustment: light intensity 200 lx, color temperature 4000 K After adjustment: Light intensity 210 lx, color temperature 4200 K (fine-tuned according to actual needs) Through the above embodiments, we have demonstrated how to formulate intelligent lighting control strategies for harsh environments based on the output results of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting requirements, and the quantified harsh environment lighting requirements. These strategies can ensure that the lighting in the underground mining environment meets both work efficiency requirements and worker safety.

[0054] In the embodiments of the present invention, in harsh environments such as underground mining, appropriate lighting is a key factor in ensuring the safety of workers. The present invention can ensure that workers can obtain sufficient lighting in any environment by real-time monitoring of environmental parameters and adjusting lighting strategies, thereby reducing safety accidents caused by insufficient lighting; suitable lighting conditions not only help workers to perform their work tasks better, but also reduce visual fatigue and improve work efficiency. The present invention creates a comfortable and efficient working environment for workers by intelligently adjusting the brightness and color temperature of lighting; by accurately controlling the brightness and color temperature of the lighting system, the present invention can avoid unnecessary energy waste and achieve the goal of energy conservation and environmental protection. While meeting lighting needs, energy consumption is reduced; the present invention realizes intelligent management of lighting, and by automatically adjusting the lighting strategy, the need for manual intervention is reduced, thereby improving management efficiency. At the same time, through continuous monitoring and data analysis, the system can continuously optimize the lighting strategy to adapt to changing environmental conditions; multi-sensor fusion technology improves the stability and reliability of the lighting control system. Even in harsh environments, the system can accurately perceive environmental changes and make corresponding adjustments to ensure the stability and continuity of lighting.

[0055] See also Figure 2 Another embodiment of the harsh environment intelligent lighting control method based on multi-sensor fusion in the embodiment of the present invention includes: 201. Collecting input control harsh environment information based on the multimodal sensor network, obtaining and fusing the input control harsh environment information in the multimodal sensor network data, including light intensity, temperature, pressure, vibration and corrosive material monitoring data, to obtain harsh environment fusion state information; Specifically, harsh environment information is collected and inputted by a multimodal sensor network. The multimodal sensor network includes a light intensity sensor, a human motion sensor, a temperature and humidity sensor, and a sound sensor. The heat and electrical signals generated by each sensor are used as additional resources to obtain an additional resource data set. Each sensor collects environmental data at a preset sampling frequency and packages the data. The aggregation node in the sensor network collects data from each sensor to form a multimodal input control environment sensor data set. A dynamic sensor activation strategy is preset to dynamically select and activate the most relevant sensor according to current environmental conditions and lighting requirements. When there is sufficient light during the day, the sampling frequency of the light intensity sensor is reduced or turned off, and the sampling frequency is increased at night or when the light is dim. The state input control environment sensor data set is cleaned, noise and outliers are removed, and normalized to make the data of different sensors comparable and consistent; a Kalman filter model is constructed for each sensor, and the estimated value at the previous moment and the observed value at the current moment are used to update the state estimate. According to the characteristics of the sensor and the requirements of lighting control, the initial state, state transfer equation, observation equation and noise covariance matrix parameters of the Kalman filter are set, and at least two sets of multimodal input control environment sensor data are input into the Kalman filter for data fusion processing. The Kalman filter iteratively updates the state estimate and the error covariance matrix according to the preset model parameters and input data, and sets an initial state of the Kalman filter for each sensor, including the initial state estimate value. And the initial error covariance matrix P0, set the state transfer equation to F, then: in, It is the current state prediction based on the previous estimated value; The observation matrix is ​​H and the observation equation is: Among them, z k is the observed value at the current moment, x k is the real state at the current moment, v k is the observation noise; The process noise covariance matrix is ​​Q, and the observation noise covariance matrix is ​​R; The recursive update process of the Kalman filter includes two steps: prediction and update: Forecast error covariance matrix: Update steps: Calculate the Kalman gain: Update the state estimate: Update the error covariance matrix: Among them, K k It is a key parameter in the Kalman filter, which determines how to integrate the observation information into the state estimation. Its calculation depends on the prediction error covariance matrix P k∣k−1, the observation matrix H and the observation noise covariance matrix R. Specifically, K k It is obtained by solving an optimization problem, the purpose of which is to minimize the mean square error of the state estimate. k The role of K can be regarded as a weight factor, which balances the contribution of the predicted value and the observed value in updating the state estimate. When the observation noise is large, K k will be smaller, which means that the predicted value dominates the update; when the prediction error is large, K k will be larger, which means that the observation value dominates the update; through data fusion processing, the harsh environment fusion state information containing multiple sensor information is obtained; and / or the sensor data is fused at different time scales, including seconds, minutes, and hours, to capture the environmental change characteristics at different time scales and obtain the harsh environment fusion state information.

[0056] It should be noted that considering the working environment underground in coal mines, the characteristics include high humidity, high dust, poor ventilation, possible presence of harmful gases such as gas, and extremely insufficient light. Intelligent lighting control systems are essential to ensure the safety of miners and improve work efficiency.

[0057] Implementation steps: Multimodal sensor network data collection: deploy light intensity sensor, human motion sensor, temperature and humidity sensor, sound sensor. Set sampling frequency: light intensity sensor (1Hz), human motion sensor (0.5Hz), temperature and humidity sensor (0.2Hz), sound sensor (2Hz).

[0058] Specific data: Light intensity sensor: initial reading 50 Lux (the light in the well is very weak); human motion sensor: reading 0 when there is no movement, reading 1 when there is movement; temperature and humidity sensor: temperature 28°C, humidity 80%RH; sound sensor: initial reading 40 dB (background noise); dynamic sensor activation strategy, due to the extremely weak light in the well, keep the light intensity sensor sampling frequency high. When the human motion sensor detects movement, temporarily increase the sampling frequency of the sound sensor to capture possible abnormal sounds.

[0059] Clean the collected data to remove outliers caused by equipment failure or temporary interference. Normalization: Normalize the temperature and humidity data to the [0,1] interval to facilitate subsequent data processing. Specific data (after normalization): Temperature: 28°C Normalized to (28 - (-40)) / (85 - (-40)) ≈ 0.73 Humidity: 80%RH normalized to 80 / 100 = 0.8 Kalman filter model construction and data fusion, build a Kalman filter model for each sensor, set the initial state, error covariance matrix, state transfer equation and other parameters.

[0060] Data fusion using a Kalman filter combines readings from multiple sensors to produce a more accurate estimate of the state of the environment.

[0061] Specific parameters (taking the light intensity sensor as an example): Initial state estimate =50 Lux; initial error covariance matrix P0=25 (assuming the initial estimate has an error of ±5 Lux) State transition equation F=1 (assuming that the light does not change much in a short period of time) Observation matrix H=1 Process noise covariance matrix Q=4 (represents uncertainty in the state transition process) The observation noise covariance matrix R=9 (represents the uncertainty in the observation process) Data fusion results: Through iterative updates of the Kalman filter and combining data from multiple sensors, the system obtains a more accurate and comprehensive estimate of the underground environment status, including information such as light intensity, temperature and humidity, human movement, and sound intensity. This information is used to intelligently adjust the brightness and working mode of the lighting system to ensure the safety of miners and improve work efficiency.

[0062] Multi-time scale data fusion fuses sensor data at different time scales such as seconds, minutes, and hours to capture the long-term and short-term characteristics of environmental changes. Adjust the lighting strategy based on the fusion results, such as reducing the lighting intensity to save energy when there is no human activity for a long time.

[0063] 202. Using the preset entropy weight model and combining the harsh environment fusion state information, the importance of the data of different sensors in the multimodal sensor network is analyzed, and the weights are assigned according to their reliability and effectiveness in the harsh environment, and the weight and reading of each sensor data are obtained. Fuzzy logic control is adopted, and the reading of each sensor data is used as an input variable. The input membership function is adjusted using the weight of each sensor data to obtain the output result of the harsh environment lighting control system; Specifically, based on the fusion state information of the harsh environment, an evaluation matrix containing different sensor data in the multimodal sensor network is constructed. Each row of the evaluation matrix represents a sensor, and each column represents the reading of the sensor at different times or conditions. The evaluation matrix is ​​set to R, then: R is an m×n matrix, where m is the number of sensors, n is the reading at different times or conditions, and r ij represents the reading of the i-th sensor at the j-th time or condition; The entropy value of each sensor is calculated according to the evaluation matrix input entropy weight model. The lower the entropy value, the more reliable and effective the information provided by the sensor is. The weight of each sensor is calculated according to the entropy value. The weight is inversely proportional to the entropy value, that is, the smaller the entropy value, the greater the weight. The entropy value is set to e i ,but: Among them, p ij is the normalized sensor reading; k is a constant, So that 0≤e i ≤1; w i is the weight of the ith sensor; an online learning algorithm is introduced, which includes incremental learning and online gradient descent, so that the entropy weight model can be dynamically updated according to real-time environmental data and lighting effect feedback; a membership function is constructed for each sensor, and the sensor readings in the harsh environment fusion state information are mapped to the input domain of the fuzzy logic control. The membership function is adjusted in combination with the weight of each sensor data, and the weight is used as the coefficient of the membership function, or the weight is multiplied by the output of the membership function to obtain the adjusted membership function; the fuzzy logic control includes a fuzzy rule base and a fuzzy reasoning mechanism; a fuzzy rule base is designed, and the rule base contains corresponding lighting control strategies under different sensor reading combinations; and / or a multi-level fuzzy logic control is designed, in which each level is responsible for processing sensor data and lighting control tasks of different granularities, the low-level controller is responsible for basic brightness adjustment, and the high-level controller is responsible for more complex scene recognition and lighting strategy adjustment; the fuzzy reasoning mechanism is used to perform fuzzy reasoning based on the adjusted membership function and the fuzzy rule base to obtain the output result of the harsh environment lighting control system.

[0064] It should be noted that in a harsh environment intelligent lighting control system based on multi-sensor fusion, we use four sensors: light intensity sensor (S1), human motion sensor (S2), temperature and humidity sensor (S3) and sound sensor (S4). These sensors collect data at different times and environmental conditions. Based on the readings of the four sensors at five different time points (T1, T2, T3, T4, T5), the evaluation matrix R is constructed: Each row of the matrix represents the evaluation data of a sensor, specifically: the first row (S1) represents the evaluation data of light intensity; the second row (S2) represents the evaluation data of human movement (represented by 0 and 1, which may be some kind of binary detection result); the third row (S3) represents the evaluation data of temperature; the fourth row (S4) represents the evaluation data of sound intensity; here, m=4 (number of sensors), n=5 (number of time points). The entropy value e of each sensor is calculated using the entropy weight model i and weight w i:Set the calculated weights to: w1=0.4, w2=0.2, w3=0.1, w4=0.3. As new data arrives, use incremental learning and online gradient descent methods to update the parameters in the entropy weight model to adapt to environmental changes. Build a membership function for each sensor and adjust it according to the weight. For example, for the light intensity sensor S1, a triangular membership function can be built to represent the fuzzy concept of "moderate brightness", and its weight w1 is used as the coefficient.

[0065] Design a fuzzy rule base, for example: if S1 (light intensity) is low and S2 (human movement) is active, increase the brightness. If S3 (temperature) is high and S4 (sound intensity) is high, adjust to cool lighting. Design a two-level fuzzy logic controller: the low-level controller adjusts the base brightness based on the readings of S1 and S2; the high-level controller adjusts the lighting strategy and scene based on the readings of S3 and S4.

[0066] The fuzzy inference mechanism is used to combine the adjusted membership function and fuzzy rule base to perform reasoning and obtain the output results of the harsh environment lighting control system. For example, at a certain point in time, based on the sensor readings and fuzzy rules, the system decides to increase the brightness and adjust to warm lighting to provide a more comfortable environment.

[0067] 203. Extract lighting demand related features according to the harsh environment fusion state information to obtain first lighting demand related features, second lighting demand related features, and third lighting demand related features, and construct a harsh environment historical data set according to the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features; Specifically, according to the needs of lighting control, three main feature dimensions are defined: the first lighting demand-related feature is the light intensity requirement, the second lighting demand-related feature is the color and color temperature requirement, and the third lighting demand-related feature is the dynamic adjustment requirement; based on light sensor data, combined with time, light contrast factors inside and outside the working environment, and special lighting conditions in harsh environments, the special lighting conditions in harsh environments include dim conditions and uneven lighting in underground mining environments, and the most suitable light intensity is predicted through a machine learning model to obtain the first lighting demand-related feature; using color sensor and camera data, analyze the environmental color, human activities, and special requirements of harsh environments for color and color temperature, including the requirements for equipment anti-corrosion performance in corrosive environments, and use pattern recognition technology to determine the color and color temperature combination to obtain the second lighting demand-related feature; combined with human movement detection data, historical behavior patterns, and harsh environments Impact on human movement and lighting needs. The impact of the harsh environment on human movement and lighting needs includes restricted personnel flow in high temperature and high pressure environments. Time series analysis or machine learning algorithms are used to predict the changing trend of lighting needs in the future, including personnel flow paths and work area conversions, to obtain third lighting demand-related features; a comprehensive data table containing timestamps, environmental parameters, lighting settings, and user feedback is designed to collect the first lighting demand-related features, second lighting demand-related features, and third lighting demand-related features extracted in the above steps in real time, as well as the corresponding lighting control results and user feedback; the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features are labeled to mark changes in lighting needs under special events, as well as user preference patterns; data enhancement techniques are used, including synthetic data generation and time series expansion, to enrich the data set and improve the generalization ability of the model; and a historical data set of harsh environments is obtained.

[0068] It should be noted that in the working environment of coal mines, in order to ensure the safety of miners and improve work efficiency, we implemented an intelligent lighting control method for harsh environments based on multi-sensor fusion. This method mainly realizes intelligent lighting control by defining and extracting three main feature dimensions.

[0069] First, the characteristics related to lighting requirements: Light intensity requirements: Data collection: Light intensity data of different areas in the mine are collected through light sensors, and the timestamp, the contrast between the light inside and outside the working environment, and the special lighting conditions of the underground mining environment (such as dim conditions, uneven lighting, etc.) are recorded. Feature extraction: Combined with time factors (such as day, night, dusk, etc.), the contrast between the light inside and outside the working environment, and the special lighting conditions of the underground mining environment, machine learning models (such as random forests, neural networks, etc.) are used to predict the most suitable light intensity.

[0070] Example data: Timestamp: 2024-09-24 12:00:00 Light intensity in working environment: 10 Lux Light intensity outside working environment: 5000 Lux Description of underground environment: dim, uneven lighting Predicted optimum light intensity: 500 Lux.

[0071] Second, the characteristics related to lighting requirements: Color and color temperature requirements: Data collection: Use color sensors and cameras to capture the color information of the underground environment and the activities of miners. Feature extraction: Use pattern recognition technology (such as support vector machines, deep learning models, etc.) to analyze the color of the environment, human activities, and the special requirements of harsh environments for color and color temperature (such as the requirements for equipment anti-corrosion performance in corrosive environments).

[0072] Example data: Main color of the environment: gray Miners' activities: At work Special requirements for harsh environments: In corrosive environments, equipment anti-corrosion needs to be considered.

[0073] Recommended color and color temperature combination: cool tones, 5000K color temperature.

[0074] Third, lighting demand-related features: Dynamically adjust demand: Data collection: Record miners' movement data through human movement detection sensors and analyze them in combination with historical behavior patterns. Feature extraction: Combine human movement detection data, historical behavior patterns, and the impact of harsh environments on human movement and lighting needs (such as limited personnel movement in high temperature and high pressure environments), and use time series analysis or machine learning algorithms to predict the changing trend of lighting demand in the future, including personnel flow paths, work area conversions, etc.

[0075] Example data: Current miner location: Area A Predicted location for the next time period: Area B Harsh environmental impact: high temperature environment, limited personnel movement Lighting adjustment strategy: gradually increase the lighting brightness in area B and reduce the lighting brightness in area A.

[0076] Furthermore, in harsh environments, intelligent lighting control systems need to comprehensively consider multiple factors to accurately extract features related to lighting needs. In addition to conventional environmental parameters (such as light intensity, temperature, pressure, and vibration), the addition of corrosive substance monitoring data is crucial for developing more accurate control strategies.

[0077] The light intensity requirement is not only affected by the current light intensity, time, and the contrast between the light inside and outside the working environment, but also by the possible damage to the lighting equipment caused by corrosive substances. In a highly corrosive environment, the lighting equipment may age or be damaged due to corrosion, resulting in a decrease in the actual light intensity. Therefore, when predicting the light intensity requirement, the concentration of corrosive substances and their impact on the equipment must be considered.

[0078] Data example analysis: Light sensor data: The current light intensity is 100 lx.

[0079] Time factor: 3 pm, the light outside the working environment is moderate.

[0080] Corrosive material data: Sulfuric acid mist concentration is 5 ppm (threshold is 10 ppm).

[0081] Light intensity demand forecast: Although the current light intensity is low, considering that the sulfuric acid mist concentration is low and does not exceed the threshold, the damage to the equipment is limited, so the light intensity demand is predicted to be 200 lx (standard demand). However, if the sulfuric acid mist concentration approaches or exceeds the threshold, the light intensity may need to be increased to compensate for potential equipment damage.

[0082] Second lighting demand related characteristics: color and color temperature requirements The color and color temperature requirements are not only related to the color of the environment and human activities, but also affected by corrosive substances. Certain corrosive gases may affect workers' perception of color and color temperature, so the color temperature needs to be adjusted according to the concentration of corrosive substances to reduce irritation to workers' eyes.

[0083] Data example analysis: Environmental color: mainly gray.

[0084] Human activities: Workers are performing delicate work.

[0085] Corrosive material data: Hydrogen chloride concentration is 3 ppm (threshold is 5 ppm).

[0086] Color and color temperature requirements: When performing fine work in a gray-tone environment, it is recommended to use cool colors (such as 6500K) to improve visual clarity. At the same time, considering that the concentration of hydrogen chloride is low and does not exceed the threshold, the current color temperature setting should reduce irritation to workers' eyes.

[0087] Third lighting demand-related characteristics: Dynamic adjustment of demand Dynamically adjusting demand involves predicting future trends in lighting demand, and must take into account changes in personnel flow, work area conversion, and corrosive substances. In particular, in the event of a sudden increase in the concentration of corrosive substances, the lighting strategy needs to be adjusted immediately to reduce potential hazards to workers.

[0088] Data example analysis: Worker flow data: Workers are expected to move from area A to area B in the next hour.

[0089] Work area conversion: Area B is a high-risk area for corrosive substances.

[0090] Corrosive substance data: Real-time monitoring showed that the concentration of nitric acid mist in area B rose rapidly from 2 ppm to 8 ppm (the threshold value is 10 ppm).

[0091] Dynamic adjustment strategy: In view of the rapid increase in the concentration of nitric acid mist in area B and its approach to the threshold, the protection level of the lighting equipment in area B should be increased immediately, and the lighting strategy should be adjusted to a low brightness, high color temperature mode. This can reduce the time workers are exposed to highly corrosive environments and improve visual alertness.

[0092] Design a comprehensive data table containing timestamps, environmental parameters, lighting settings, and user feedback to collect in real time the first lighting demand-related features, the second lighting demand-related features, the third lighting demand-related features extracted in the above steps, as well as the corresponding lighting control results and user feedback.

[0093] The data table fields include: Timestamp: record the specific time of data collection; Environmental parameters: light intensity, color, color temperature, special lighting conditions underground, corrosive environment, etc.; Lighting settings: setting values ​​of light intensity, color and color temperature; User feedback: feedback on miners' satisfaction with the current lighting settings Data annotation and enhancement: annotate the collected data to mark changes in lighting requirements and user preference patterns under special events. Use data enhancement techniques (such as synthetic data generation, time series expansion, etc.) to enrich the data set and improve the generalization ability of the model. For example, you can simulate underground environmental changes in different time periods to generate more diverse data samples.

[0094] Construct a historical dataset of harsh environments, integrate the annotated and enhanced data, and form a historical dataset of harsh environments containing the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features. This dataset will be used for subsequent model training and the formulation of intelligent lighting control strategies.

[0095] 204. Estimating the probability density function of the harsh environment historical data set according to the preset kernel density estimation, obtaining the distribution estimation of the future harsh environment lighting demand by selecting the kernel function and the bandwidth parameter, and obtaining the quantified harsh environment lighting demand value according to the first lighting demand related feature, the second lighting demand related feature, and the third lighting demand related feature combined with the preset GBM gradient boosting machine model; Specifically, in combination with the context recognition technology, the kernel function is dynamically selected according to the current context, the current context includes weather, season, and activity type, the kernel function includes Gaussian kernel and Epanechnikov kernel, and the bandwidth parameter is determined by cross-validation, interpolation method or empirical formula; kernel density estimation is performed on each feature dimension to obtain the respective probability density function; and / or a multidimensional kernel density estimation method is used, including a Copula-based multidimensional kernel density estimation, to more accurately capture the joint distribution between features and obtain the respective probability density functions; the probability density function of the harsh environment historical data set is used to estimate the distribution of future harsh environment lighting requirements by using the sliding window method: in, Is the future harsh environment lighting demand x t+1 The conditional probability of is the indicator function, N is the number of sliding windows in the harsh environment historical data set, is the lighting demand sequence in the harsh environment historical data set; obtain the distribution estimate of the future harsh environment lighting demand; preprocess the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features at the current moment, including data cleaning and normalization; construct a GBM gradient boosting machine model, select a loss function and a weak learner, the loss function uses square error, and the weak learners include decision trees and linear regression; train the GBM gradient boosting machine model based on the features in the harsh environment historical data set and the corresponding lighting demand values, and obtain the optimal model parameters through iterative optimization. For the square error loss function, use the following formula to update the model: Among them, F m (x) is the GBM gradient boosting machine model after the mth iteration, h m (x;a m ) is the weak learner of the mth iteration, βm is the weight of the weak learner, a m are the parameters of the weak learner; Input the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features at the current moment into the trained GBM gradient boosting machine model: in, is the predicted lighting demand value, F M (x') is the trained GBM gradient boosting machine model, and x' is the preprocessed feature value; the quantized lighting requirement value is obtained.

[0096] It should be noted that the working environment in coal mines is characterized by high humidity, dust, poor ventilation, and extremely insufficient light. To ensure the safety of miners and improve work efficiency, we implemented an intelligent lighting control method for harsh environments based on multi-sensor fusion. This embodiment will explain in detail how to dynamically select kernel functions in combination with context recognition technology and use the GBM gradient boosting machine model to predict lighting demand.

[0097] Context recognition and kernel function selection,Current context: Weather - cloudy, Season - autumn, Activity type - tunneling. Dynamic selection of kernel function: According to the current context, select Gaussian kernel for kernel density estimation.

[0098] Kernel density estimation,data: Use the features of light intensity, color and color temperature requirements,,dynamic adjustment requirements, etc. in the harsh environment historical data set.,Kernel density estimation: Perform Gaussian kernel density estimation on each feature dimension,and obtain their respective probability density functions.

[0099] Estimation of the distribution of lighting demand in future harsh environments, sliding window method: The sliding window method is used to estimate the distribution of lighting demand in future harsh environments. Parameter setting: Set the number of sliding windows N=100, and the length of the lighting demand sequence in the harsh environment historical data set is n=10. Result: The conditional probability distribution of lighting demand in future harsh environments is obtained.

[0100] Feature preprocessing, data cleaning: remove outliers and missing values. Normalization: normalize the first lighting demand related features (light intensity requirements), the second lighting demand related features (color and color temperature requirements), and the third lighting demand related features (dynamic adjustment requirements).

[0101] GBM gradient boosting machine model construction and training, model parameters: select square error as the loss function, and use decision tree as weak learner. Training data: Use the features in the harsh environment historical data set and the corresponding lighting demand values ​​for model training. Iterative optimization: Obtain the optimal model parameters through iterative optimization, including the weights and parameters of the weak learner.

[0102] Lighting demand prediction, input features: input the first, second, and third lighting demand related features after preprocessing at the current moment into the trained GBM model. Prediction results: get the quantified lighting demand value, such as the predicted light intensity is 600 Lux, the recommended color and color temperature combination is warm color, 4000K color temperature, and the dynamic adjustment strategy is to gradually increase the lighting brightness of the working area.

[0103] 205. Obtain a harsh environment intelligent lighting control strategy based on the output results of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting demand and the quantified harsh environment lighting demand value; Specifically, the output results of the harsh environment lighting control system, the distribution estimate of future harsh environment lighting demand and the quantified harsh environment lighting demand values ​​are integrated; the distribution estimate of future harsh environment lighting demand is used to predict the changing trend of lighting demand in the future by analyzing the probability density function, peak and valley information in the distribution estimate; the output results of the harsh environment lighting control system are evaluated, and the actual output of the lighting system is compared with the preset lighting standards or user expectations to determine whether the current lighting system meets the lighting demand, and whether there is a problem of too bright, too dark or uneven light distribution, combined with the quantified harsh environment lighting demand values; an environment-demand-response data set is formed; the environment-demand-response data set is deeply analyzed to identify the changing trend, abnormal values ​​and periodic laws of lighting demand, and obtain the intelligent lighting control strategy for harsh environments.

[0104] It should be noted that in the harsh environment of coal mines, the core task of the intelligent lighting control system is to ensure the safety of miners and improve work efficiency. This embodiment will explain how to specifically implement a multi-sensor fusion harsh environment intelligent lighting control method, including integrating system output results, estimating the distribution of future harsh environment lighting demand, and quantifying the harsh environment lighting demand value, and forming an environment-demand-response data set to formulate a control strategy.

[0105] Integrate the system output results with the lighting requirements. The system output results are: the current lighting system has a lighting intensity of 500 Lux, a color temperature of 4500 K, and a uniformity of 0.8. Estimation of the distribution of lighting requirements in harsh environments in the future: The peak value of lighting requirements in the future obtained by kernel density estimation is 600 Lux, and the valley value is 400 Lux. Quantify the lighting requirements in harsh environments: According to the GBM model prediction, the quantified lighting requirement value is 550 Lux.

[0106] Analysis of the future trend of harsh environment lighting demand changes, probability density function analysis: In the future, harsh environment lighting demand will mainly be distributed in the range of 450-650 Lux, with a high probability density. Peak and valley information: It is predicted that the harsh environment lighting demand will peak at around 600 Lux in the future and be at a low point at around 400 Lux. Change trend prediction: It is expected that the lighting demand will gradually increase in the future and then stabilize.

[0107] Evaluate the output results of the harsh environment lighting control system, preset lighting standards: light intensity 500-700 Lux, color temperature 4000-5000K, uniformity ≥ 0.7. Comparison of actual output and standard: The current system output meets the preset standard, but considering the rising trend of harsh environment lighting demand in the future, it may need to be adjusted appropriately. Problem identification: There is no problem of too bright, too dark or uneven light distribution.

[0108] Form an environment-demand-response data set. Environmental data: humidity 80%, dust concentration 0.5mg / m³, gas concentration 0.1%, temperature 25℃. Demand data: light intensity requirement 550 Lux, color temperature requirement 4500K, uniformity requirement ≥ 0.8. Response data: the actual system output light intensity 500 Lux, color temperature 4500K, uniformity 0.8; the future adjustment strategy is to gradually increase the light intensity to 550 Lux.

[0109] In-depth analysis of data sets and formulation of control strategies, identification of changing trends: Lighting demand fluctuates periodically with time and work activities. Outlier detection: No obvious outliers were found. Periodicity: Lighting demand is high from 10 a.m. to 2 p.m. every day, and low from 8 p.m. to 4 a.m. the next day. Control strategy formulation: According to the periodicity, formulate a time-based lighting adjustment strategy to meet the lighting demand in different time periods.

[0110] 206. Based on the historical data set of harsh environments and user preferences, set a baseline lighting control strategy, including default light intensity, color temperature, and dynamic adjustment rules; formulate a dynamic adjustment strategy based on the distribution estimate of future harsh environment lighting demand, and when it is predicted that the future harsh environment lighting demand will increase, adjust the light intensity or color temperature in advance to meet user needs; consider the impact of harsh environments and formulate emergency lighting control strategies to ensure the stability and safety of the lighting system in harsh environments; formulate personalized control strategies based on the user's personalized lighting needs, and adjust the light intensity and color temperature according to the user's activity habits and emotional state; collect feedback data from the lighting control system in real time, including actual light intensity, color temperature, and energy consumption, compare it with the expected value, and make timely adjustments when deviations are found; regularly evaluate and optimize the control strategy, and continuously adjust and improve the control strategy based on user feedback, environmental changes, and technological progress, so as to improve the intelligence level of lighting control and user satisfaction.

[0111] It should be noted that the working environment in coal mines is harsh, and an intelligent lighting control system is needed to ensure the safety of miners and improve work efficiency. This embodiment will specifically explain how to implement an intelligent lighting control method in a harsh environment based on multi-sensor fusion, including setting a baseline lighting control strategy, formulating a dynamic adjustment strategy, an emergency lighting control strategy, a personalized control strategy, and real-time feedback adjustment and strategy evaluation optimization.

[0112] Set the baseline lighting control strategy, default light intensity: according to historical data, set the default light intensity underground to 500 Lux. Default color temperature: considering the visual comfort of miners, set the default color temperature to 4500K. Dynamic adjustment rules: the light intensity is automatically adjusted every 30 minutes, and the adjustment range does not exceed ±10% each time.

[0113] Formulate dynamic adjustment strategies to estimate the distribution of lighting demand in harsh environments in the future: Sensor data predicts that lighting demand will increase to 600 Lux in the next 2 hours. Adjust in advance: The system starts to gradually increase the lighting intensity 15 minutes in advance to ensure that it reaches 600 Lux at the peak of demand.

[0114] Emergency lighting control strategy, harsh environment detection: When the sensor detects that the gas concentration exceeds 0.5%, the emergency lighting is triggered. Emergency lighting parameters: The light intensity is automatically increased to 800 Lux and the color temperature is adjusted to 5000K to increase alertness. Stability guarantee: In emergency lighting mode, the system automatically switches to the backup power supply to ensure continuous lighting for more than 6 hours.

[0115] Personalized control strategy, user activity habits: According to the miners' work shifts, the light intensity is set to 550 Lux during daytime work and reduced to 450 Lux during nighttime work. Emotional state adjustment: The emotional state is detected through the wearable devices worn by the miners. When fatigue is detected, the color temperature is automatically adjusted to a warmer 3500K.

[0116] Real-time feedback adjustment, actual light intensity and color temperature monitoring: The system monitors the current light intensity of 490 Lux and the color temperature of 4400 K in real time. Compared with the expected value, it is found that the actual light intensity is 500 Lux lower than the set value. Timely adjustment: The system automatically increases the power of the lighting equipment to restore the light intensity to the set value.

[0117] Strategy evaluation and optimization, user feedback collection: Regularly conduct lighting satisfaction surveys on miners to collect feedback. Environmental change monitoring: Continuously monitor changes in underground environmental parameters, such as humidity, dust concentration, etc. Technological progress integration: With the development of LED lighting technology, regularly update more efficient and stable lighting equipment. Strategy optimization implementation: Based on user feedback, environmental changes and technological progress, conduct a comprehensive evaluation and optimization of the control strategy every quarter.

[0118] In the embodiment of the present invention, by real-time monitoring of underground environmental parameters and miners' activities, the lighting system is intelligently adjusted to effectively avoid safety hazards caused by insufficient or excessive lighting, and ensure the safe operation of miners; the lighting brightness and color temperature are dynamically adjusted according to the miners' activity habits and emotional state to create a more comfortable working environment, thereby improving the miners' work efficiency and work quality; by accurately predicting and dynamically adjusting lighting needs, unnecessary energy waste is avoided and the goal of energy conservation and emission reduction is achieved. The lighting brightness is automatically reduced in areas where there is no human activity for a long time to reduce energy consumption; a variety of advanced algorithms and technical means (such as Kalman filtering, entropy weight model, GBM gradient boosting machine, etc.) are used to improve the intelligence level and adaptive ability of the system to ensure that the system can operate stably under different environments and requirements; by collecting miners' feedback on the lighting system in real time and optimizing strategies based on the feedback, the miners' satisfaction and acceptance of the lighting system are improved, and the miners' work enthusiasm and sense of belonging are enhanced.

[0119] In summary, the present invention can not only effectively cope with the challenges of harsh environments such as underground coal mines and improve the safety and work efficiency of miners, but also achieve multiple goals such as energy conservation and emission reduction and improve the level of system intelligence. It has significant beneficial effects and broad application prospects.

[0120] The above describes the harsh environment intelligent lighting control method based on multi-sensor fusion in the embodiment of the present invention. The following describes the harsh environment intelligent lighting control device based on multi-sensor fusion in the embodiment of the present invention. Figure 3In one embodiment of the present invention, an intelligent lighting control device for harsh environments based on multi-sensor fusion includes: an acquisition module 301, which is used to acquire input control harsh environment information, collect input control harsh environment information according to a multi-modal sensor network, obtain at least two groups of multi-modal input control environment sensor data, perform data fusion processing according to at least two groups of multi-modal input control environment sensor data, and obtain harsh environment fusion state information; a processing module 302, which is used to analyze the importance of data of different sensors in the multi-modal sensor network according to the harsh environment fusion state information combined with a preset entropy weight model, and perform weight allocation according to their reliability and effectiveness in harsh environments, so as to obtain the weight of each sensor data and the reading of each sensor, the input variable of the fuzzy logic control is the reading of each sensor, and the weight of each sensor data is used as a membership function to adjust these inputs to obtain the output result of the harsh environment lighting control system; extraction Module 303 is used to extract lighting demand related features based on the harsh environment fusion state information to obtain the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features, and to construct a harsh environment historical data set based on the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features; quantization module 304 is used to estimate the probability density function of the harsh environment historical data set based on the preset kernel density estimation, obtain the distribution estimate of future harsh environment lighting demand by selecting the kernel function and bandwidth parameters, and obtain the quantized harsh environment lighting demand value based on the first lighting demand related features, the second lighting demand related features, and the third lighting demand related features combined with the preset GBM gradient boosting machine model; allocation module 305 is used to obtain a harsh environment intelligent lighting control strategy based on the output result of the harsh environment lighting control system, the distribution estimate of future harsh environment lighting demand, and the quantized harsh environment lighting demand value.

[0121] In the embodiment of the present invention, through multi-sensor fusion technology, the device can fully perceive the environmental status and improve the accuracy and adaptability of lighting control. The application of the entropy weight model enables the device to automatically evaluate the importance of sensor data and effectively filter unreliable data, thereby enhancing the robustness of the system. Based on the historical data set of harsh environments and advanced algorithms, the device can predict the lighting requirements of harsh environments in the future and dynamically adjust the lighting strategy to meet the real-time changing lighting needs. Through accurate prediction and intelligent control, the device can effectively avoid unnecessary lighting waste, improve energy efficiency, and reduce energy consumption costs. The device can provide personalized lighting services based on user preferences and activity habits to improve user satisfaction and comfort.

[0122] above Figure 3The intelligent lighting control device for harsh environments based on multi-sensor fusion in an embodiment of the present invention is described in detail from the perspective of modular functional entities. The intelligent lighting control device for harsh environments based on multi-sensor fusion in an embodiment of the present invention is described in detail from the perspective of hardware processing.

[0123] Figure 4 It is a structural diagram of a harsh environment intelligent lighting control device based on multi-sensor fusion provided by an embodiment of the present invention. The harsh environment intelligent lighting control device 400 based on multi-sensor fusion may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 410 (for example, one or more processors) and a memory 420, and one or more storage media 430 (for example, one or more mass storage devices) storing application programs 433 or data 432. Among them, the memory 420 and the storage medium 430 can be short-term storage or permanent storage. The program stored in the storage medium 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the harsh environment intelligent lighting control device 400 based on multi-sensor fusion. Furthermore, the processor 410 can be configured to communicate with the storage medium 430 to execute a series of instruction operations in the storage medium 430 on the harsh environment intelligent lighting control device 400 based on multi-sensor fusion.

[0124] The harsh environment intelligent lighting control device 400 based on multi-sensor fusion may also include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input and output interfaces 460, and / or one or more operating systems 431, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Figure 4 The structure of the harsh environment intelligent lighting control device based on multi-sensor fusion shown does not constitute a limitation of the harsh environment intelligent lighting control device based on multi-sensor fusion, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0125] The present invention also provides an intelligent lighting control device for harsh environments based on multi-sensor fusion. The intelligent lighting control device for harsh environments based on multi-sensor fusion includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the intelligent lighting control method for harsh environments based on multi-sensor fusion in the above-mentioned embodiments.

[0126] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of a method for intelligent lighting control in harsh environments based on multi-sensor fusion.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the whole or part of the solution of the present invention, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0129] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent lighting control in harsh environments based on multi-sensor fusion, characterized in that: The harsh environment intelligent lighting control method based on multi-sensor fusion includes: According to the multimodal sensor network, the harsh environment information of the input control is collected and integrated in the multimodal sensor network data, including the light intensity, color, image, vibration, temperature, pressure and corrosive material monitoring data, to obtain the harsh environment fusion status information; Using the preset entropy weight model and combining the fusion state information of the harsh environment, the importance of the data of different sensors in the multimodal sensor network is analyzed, and the weights are assigned according to their reliability and effectiveness in the harsh environment to obtain the weight and reading of each sensor data; Fuzzy logic control is adopted, the reading of each sensor data is taken as the input variable, and the input membership function is adjusted by using the weight of each sensor data to obtain the output result of the harsh environment lighting control system; Extracting lighting demand-related features based on the harsh environment fusion state information includes: Based on the light sensor data, combined with the time, the contrast of light inside and outside the working environment, and the special light conditions in the harsh environment, the special light conditions in the harsh environment include the dimness and uneven light conditions in the underground mining environment, the most suitable light intensity is predicted through the machine learning model to obtain the first lighting demand related characteristics; Using color sensors and camera data, analyze the environmental color, human activities, and special requirements of harsh environments for color and color temperature, including the requirements for equipment anti-corrosion performance in corrosive environments, and use pattern recognition technology to determine the combination of color and color temperature to obtain the second lighting demand-related features; Combined with human movement detection data, historical behavior patterns, and the impact of harsh environments on human movement and lighting needs, including the restricted flow of people under high temperature and high pressure environments, time series analysis or machine learning algorithms are used to predict the changing trend of lighting needs in the future, including personnel flow paths and work area conversions, to obtain third lighting demand-related features; The first lighting demand-related feature, the second lighting demand-related feature, and the third lighting demand-related feature are marked to mark changes in lighting demand under special events and user preference modes; Use data enhancement techniques, including synthetic data generation and time series expansion, to enrich the dataset and improve the generalization ability of the model; Constructing a harsh environment historical data set according to the first lighting demand-related feature, the second lighting demand-related feature, and the third lighting demand-related feature; Perform probability density function estimation on the harsh environment historical data set according to a preset kernel density estimation, obtain a distribution estimate of future harsh environment lighting demand by selecting a kernel function and a bandwidth parameter, and obtain a quantified harsh environment lighting demand value according to the first lighting demand-related feature, the second lighting demand-related feature, and the third lighting demand-related feature combined with a preset GBM gradient boosting machine model; According to the output result of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting demand and the quantified harsh environment lighting demand value, a harsh environment intelligent lighting control strategy is obtained.

2. The method for intelligent lighting control in harsh environments based on multi-sensor fusion according to claim 1 is characterized in that: The multimodal sensor network includes a light sensor, a temperature sensor, a pressure sensor, a vibration sensor and a corrosion monitoring sensor. The heat and electrical signals generated by each sensor are used as additional resources to obtain an additional resource data set. Each sensor collects environmental data according to a preset sampling frequency and packages the data. The aggregation node in the sensor network collects data from each sensor to form a multimodal input control environment sensor data set. Preset dynamic sensor activation strategy to dynamically select and activate the most relevant sensors based on current environmental conditions and lighting requirements. When there is sufficient light during the day, the sampling frequency of the light intensity sensor is reduced or turned off, while the sampling frequency is increased at night or when the light is dim. The sensor data are fused at different time scales, including seconds, minutes, and hours, to capture the environmental change characteristics at different time scales and obtain the fusion status information of harsh environments.

3. The method for intelligent lighting control in harsh environments based on multi-sensor fusion according to claim 1 is characterized in that: The weight distribution of the entropy weight model is combined with an online learning algorithm to update the weight distribution in real time; Design multi-level fuzzy logic control, where each level is responsible for processing sensor data and lighting control tasks of different granularity, with low-level controllers responsible for basic brightness adjustment and high-level controllers responsible for more complex scene recognition and lighting strategy adjustment; By using the fuzzy reasoning mechanism, fuzzy reasoning is performed according to the adjusted membership function and fuzzy rule base to obtain the output result of the harsh environment lighting control system.

4. The method for intelligent lighting control in harsh environments based on multi-sensor fusion according to claim 1, characterized in that: Multidimensional kernel density estimation methods, including Copula-based multidimensional kernel density estimation, are used to more accurately capture the joint distribution between features and obtain their respective probability density functions; Using the probability density function of the harsh environment historical data set, the sliding window method is used to estimate the distribution of future harsh environment lighting requirements: in, Is the future harsh environment lighting demand x t+1 The conditional probability of is the indicator function, N is the number of sliding windows in the harsh environment historical data set, is the sequence of light demand in the harsh environment historical dataset; Obtain a distribution estimate of future harsh environment lighting requirements.

5. The method for intelligent lighting control in harsh environments based on multi-sensor fusion according to claim 1, characterized in that: Evaluate the output results of the harsh environment lighting control system, and judge whether the current lighting system meets the lighting needs by comparing the actual output of the lighting system with the preset lighting standards or user expectations, and whether there are problems such as too bright, too dark, or uneven light distribution, combined with quantifying the harsh environment lighting demand value; Forming environment-demand-response data sets; An in-depth analysis is conducted on the environment-demand-response data set to identify the changing trends, abnormal values, and periodic laws of lighting demand, and to obtain intelligent lighting control strategies for harsh environments.

6. The method for intelligent lighting control in harsh environments based on multi-sensor fusion according to claim 5 is characterized in that: Also includes: Set a baseline lighting control strategy based on the harsh environment historical data set and user preferences, including default light intensity, color temperature, and dynamic adjustment rules; Based on the estimated distribution of lighting demand in harsh environments in the future, a dynamic adjustment strategy is formulated. When it is predicted that lighting demand in harsh environments will increase in the future, the lighting intensity or color temperature is adjusted in advance to meet user needs; Collect feedback data from the lighting control system in real time, including actual light intensity, color temperature, and energy consumption, compare them with expected values, and make timely adjustments when deviations are found; Regularly evaluate and optimize control strategies, and continuously adjust and improve control strategies based on user feedback, environmental changes, and technological advances to improve the intelligence level of lighting control and user satisfaction.

7. An intelligent lighting control device for harsh environments based on multi-sensor fusion, characterized in that: The harsh environment intelligent lighting control device based on multi-sensor fusion includes: An acquisition module is used to collect input control harsh environment information based on the multimodal sensor network, acquire and fuse the input control harsh environment information in the multimodal sensor network data, including light intensity, temperature, pressure, vibration and corrosive substance monitoring data, and obtain harsh environment fusion state information; The processing module is used to use a preset entropy weight model, combined with the harsh environment fusion state information, to analyze the importance of data from different sensors in the multimodal sensor network, and to assign weights according to their reliability and effectiveness in the harsh environment, so as to obtain the weight and reading of each sensor data; fuzzy logic control is used, the reading of each sensor data is used as an input variable, and the input membership function is adjusted using the weight of each sensor data to obtain the output result of the harsh environment lighting control system; an extraction module, configured to extract lighting demand-related features according to the harsh environment fusion state information to obtain first lighting demand-related features, second lighting demand-related features, and third lighting demand-related features, and to construct a harsh environment historical data set according to the first lighting demand-related features, the second lighting demand-related features, and the third lighting demand-related features; A quantization module is used to perform a probability density function estimation on the harsh environment historical data set according to a preset kernel density estimation, obtain a distribution estimation of future harsh environment lighting demand by selecting a kernel function and a bandwidth parameter, and obtain a quantized harsh environment lighting demand value according to the first lighting demand-related feature, the second lighting demand-related feature, and the third lighting demand-related feature in combination with a preset GBM gradient boosting machine model; The allocation module is used to obtain a harsh environment intelligent lighting control strategy based on the output result of the harsh environment lighting control system, the distribution estimation of future harsh environment lighting demand and the quantified harsh environment lighting demand value.

8. A harsh environment intelligent lighting control device based on multi-sensor fusion, characterized in that: The harsh environment intelligent lighting control device based on multi-sensor fusion includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the harsh environment intelligent lighting control device based on multi-sensor fusion to execute the harsh environment intelligent lighting control method based on multi-sensor fusion as described in any one of claims 1-6.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the harsh environment intelligent lighting control method based on multi-sensor fusion as described in any one of claims 1-6 is implemented.

Citation Information

Patent Citations

  • Intelligent illumination control system and method based on wireless sensor network

    CN103338565A

  • LED display control method and system based on MCU controller

    CN117711309A

  • Intelligent illumination control method and system based on titanium material

    CN118741792A

Cited By

  • Intelligent landscape lighting control system based on data fusion of distributed optical sensors

    CN119383796A

  • Bullet train automatic light control system based on computer vision assistance

    CN119653554A

  • Ecological environment monitoring data processing method

    CN119808007A

  • Home energy management system and energy saving decision method thereof

    TWI938016B