Intelligent brightness adjustment control method and system for hydraulic power plant maintenance area

Abstract

The invention discloses an intelligent brightness adjustment control method and system for a hydraulic power plant maintenance area, and relates to the field of intelligent control of industrial lighting, and the method comprises the steps: determining the influence of the number of personnel, the equipment state and the ambient light intensity on the light brightness, predicting the potential safety risk in real time through a logistic regression model, and adjusting the brightness; in response to brightness adjustment, according to the personnel density and the ambient light intensity, the brightness is finely adjusted through a fuzzy logic control algorithm, and energy consumption optimization is carried out on the premise that the illumination requirement is met. According to the invention, the defects of incapability of dynamically responding to complex environment change, insufficient energy consumption optimization and lack of risk prediction capability in the prior art are overcome, and the intelligent degree, the safety and the energy-saving effect of illumination control are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control of industrial lighting, and in particular to an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant. Background Art

[0002] Common intelligent lighting systems use simple sensors (such as infrared sensors, timers, or ambient light sensors) to achieve automatic switching or basic brightness adjustment. For example, existing intelligent lighting systems mainly rely on infrared sensors to control the switching of lights based on the entry or exit of people. In addition, some systems use basic ambient light sensors to adjust the brightness of lights according to the intensity of ambient light. Such systems can save energy to a certain extent and provide basic lighting management functions. Infrared sensors or ultrasonic sensors are used in industrial scenarios to automatically turn lights on and off by sensing the presence of people. They mainly control lighting through direct sensing and rule triggering.

[0003] Although existing smart lighting systems have achieved some success in terms of energy saving and basic safety, they still have some significant drawbacks:

[0004] (1) Lack of dynamic adjustment capability: Existing technologies mostly use a single sensor or preset rules, which cannot be flexibly adjusted according to real-time changing environmental conditions, personnel activities and equipment status, resulting in the inability to achieve accurate brightness control in the complex maintenance environment of hydropower plants.

[0005] (2) Poor environmental adaptability: The existing system is based only on a single sensing signal (such as infrared or ambient light intensity) and cannot comprehensively consider the interactive effects of multiple factors. It is easy to cause false triggering or insufficient brightness, affecting operational safety.

[0006] (3) Limited energy-saving effects: Due to the lack of advanced energy consumption optimization algorithms, existing systems can usually only achieve basic energy-saving effects and cannot achieve optimal energy utilization efficiency.

[0007] (4) Lack of risk prediction function: Traditional systems lack the ability to comprehensively analyze the density of personnel activities and the operating status of equipment. They are unable to identify potential safety risks in advance, nor can they automatically enhance lighting in high-risk situations to ensure operational safety. Summary of the invention

[0008] In order to solve the above problems, the purpose of the present invention is to provide an intelligent brightness adjustment control technology for the maintenance area of ​​a hydropower plant, aiming to achieve efficient control of the lights in the maintenance area through intelligent perception, dynamic analysis and automatic adjustment.

[0009] In order to achieve the above technical objectives, the present application provides an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant, characterized in that it includes the following steps:

[0010] Determine the impact of the number of people, equipment status and ambient light intensity on light brightness, and use logistic regression models to predict potential safety risks in real time and adjust brightness;

[0011] In response to brightness adjustment, the brightness is finely adjusted according to the density of people and the ambient light intensity through the fuzzy logic control algorithm, and energy consumption is optimized while meeting the lighting needs.

[0012] Preferably, when analyzing the impact of light brightness, a random forest algorithm is used to perform multi-parameter association analysis to determine the weights of the impact of personnel density, equipment load and ambient light on brightness.

[0013] Preferably, when performing risk prediction, a Bayesian optimization + feedforward neural network algorithm is used to predict lighting needs and potential risks in real time, and dynamically adjust the hyperparameters of the neural network to optimize brightness adjustment.

[0014] Preferably, in the process of adjusting the brightness in detail, the fuzzy logic control algorithm further refines the lighting adjustment according to the predicted lighting brightness and risk level to achieve a balance between energy consumption and safety.

[0015] Preferably, in the process of refining the lighting adjustment, the input variables are fuzzified into three fuzzy sets; after reasoning according to a predefined fuzzy rule base, the fuzzy sets are converted into precise adjustment quantities using a centroid method.

[0016] Preferably, when optimizing energy consumption, a genetic algorithm is combined with a particle swarm optimization to perform multi-objective optimization on different brightness adjustment strategies, thereby minimizing energy consumption per unit time while meeting lighting requirements.

[0017] Preferably, when optimizing energy consumption, the fitness function is used to evaluate the quality of each brightness adjustment strategy and balance brightness accuracy and energy consumption, wherein the fitness function is expressed as:

[0018]

[0019] Among them, F(x) is the fitness value, x represents the parameters of the brightness adjustment strategy, is the target brightness of the ith region, y i (x) is the actual brightness of the ith region under strategy x, w is the weight, and n is the total number of regions.

[0020] Preferably, when optimizing energy consumption, the optimization of the regulation strategy is achieved by updating the particle positions based on the particle swarm optimization algorithm PSO, where PSO is expressed as:

[0021]

[0022] Among them, x i is the particle position, v i is the particle velocity, ω is the inertia weight, p i and g are the historical optimal and global optimal positions of the particle respectively, c1 and c2 are acceleration constants, and r1 and r2 are random numbers.

[0023] The present invention discloses an intelligent brightness adjustment control system for a maintenance area of ​​a hydropower plant, comprising:

[0024] The adjustment module is used to determine the impact of the number of people, equipment status and ambient light intensity on the light brightness. Through the logistic regression model, it predicts potential safety risks in real time and adjusts the brightness.

[0025] The corresponding module is used to respond to brightness adjustment. According to the density of people and the ambient light intensity, the brightness is adjusted in detail through the fuzzy logic control algorithm, and energy consumption is optimized while meeting the lighting needs.

[0026] The present invention discloses the following technical effects:

[0027] The present invention controls the lighting brightness at different time periods through simple sensing and preset schedules, so as to save energy and improve operation safety;

[0028] The present invention realizes dynamic and precise lighting control of the maintenance area through multi-sensor fusion, deep learning analysis and advanced optimization algorithms;

[0029] The present invention overcomes the defects of the prior art, such as the inability to dynamically respond to complex environmental changes, insufficient energy consumption optimization and lack of risk prediction capabilities, and improves the intelligence, safety and energy-saving effects of lighting control. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0032] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0033] like Figure 1 As shown, the present invention provides an intelligent brightness adjustment control technology for the maintenance area of ​​a hydropower plant, which specifically includes the following contents:

[0034] By deploying intelligent sensing equipment in the maintenance area of ​​the hydropower plant, including illumination sensors, human body sensors and other environmental perception modules, the operating environment information is collected in real time. The system automatically adjusts the switch status and brightness level of the lights according to the number of personnel, equipment operation status and ambient light changes, thereby meeting the lighting needs in different scenarios. The specific plan is as follows:

[0035] 1. Implementation principle:

[0036] (1) Lighting sensing module: The system monitors the ambient light intensity in real time through an illuminance sensor (range 0-1000 lux). When natural light is insufficient, the system automatically increases the light brightness; when natural light intensity is sufficient, the system automatically reduces or turns off the light to achieve energy saving.

[0037] (2) Human sensing module: The human body sensor detects the activities and number of people in the area. When a person is detected entering, the system will automatically turn on the light; when the person leaves for a period of time, the system will automatically turn off the light to avoid unnecessary energy consumption.

[0038] (3) Equipment status analysis module: The IoT sensor obtains the real-time operating status of the maintenance equipment, such as equipment load (0%-100%), maintenance status, maintenance time, etc., to determine the urgency of equipment operation and light requirements. If the equipment is in a high-load operation state, the system will increase the light brightness to ensure operation safety.

[0039] (4) Intelligent brightness adjustment module: Through a variety of algorithms, including multi-parameter correlation analysis, risk prediction algorithm, fuzzy logic control and energy consumption optimization algorithm, the system can dynamically analyze input data and make the best brightness adjustment decision. Specifically:

[0040] 1) Multi-parameter association analysis algorithm: used to determine the weight of the impact of the number of people, equipment status and ambient light intensity on light brightness.

[0041] 2) Risk prediction algorithm: Through the logistic regression model, the potential safety risk level is calculated in real time and the brightness is adjusted.

[0042] 3) Fuzzy logic control algorithm: According to the input personnel density and ambient light intensity, the brightness can be adjusted in detail.

[0043] 4) Energy consumption optimization algorithm: Minimize the energy consumption per unit time while meeting the lighting needs.

[0044] 2. Methods and steps:

[0045] (1) Data collection: Illumination sensors, computer vision modules, and equipment status detectors collect data on ambient light, number of people, and equipment status in real time; the data is integrated and analyzed by the central control unit.

[0046] (2) Data analysis and processing: Preprocess the collected data, including denoising, normalization, and outlier filtering, to ensure data accuracy. The original data set is represented by X, where x = [x1 x2, … x n ], where X1 is the ambient light intensity, X2 is the equipment load, and X3 is the maintenance status. This variable can be added according to actual needs. The output variable of the present invention is y.

[0047] Normalize the input data and scale all variables to the range [0,1] to ensure that the features are on the same scale:

[0048]

[0049] Among them, x is the original data, X is the normalized data, and x min and x max is the minimum and maximum value of the feature. Secondly, handle outliers and missing values, and ensure data integrity by interpolation, mean filling or deleting outliers.

[0050] (3) Intelligent brightness control: Based on the random forest algorithm, Bayesian optimization neural network and fuzzy logic control algorithm, the system evaluates lighting needs in real time and dynamically adjusts the light brightness according to personnel activities, ambient light and equipment status, as follows:

[0051] 1) Multi-parameter association analysis algorithm based on random forest:

[0052] The random forest algorithm is used to perform multi-parameter correlation analysis, study the correlation between multiple factors, analyze the impact of different parameters on light brightness, and determine the weight of the impact of personnel density, equipment load and ambient light on brightness. The specific steps are as follows:

[0053] Random forest algorithm construction process:

[0054] Randomly select feature subsets: A decision tree randomly selects a feature subset from the input feature set for node splitting. Let the total number of features be d, and the number of randomly selected features be m (usually ).

[0055]

[0056] Node splitting condition: At each node, random forest selects the best feature for splitting based on variance reduction.

[0057]

[0058] Among them, Var(Y) is the sample variance of the parent node, Var(Y L ) and Var(Y R ) are the sample variances of the left and right child nodes, respectively, N L and N R are the number of samples of the left and right child nodes respectively, and N represents the total number of nodes.

[0059] Construction and output of decision tree: Repeat the feature selection and node splitting process until the termination condition is met (such as reaching the maximum depth, the number of leaf node samples is less than the minimum threshold, etc.). The output of each decision tree is the predicted value of light brightness h. t (X), t is the index of the tree.

[0060] Random forest ensemble: A random forest consists of T decision trees. The overall performance of the model is improved by integrating the prediction results of each tree. The output of the ensemble model is the average of the prediction results of all decision trees.

[0061]

[0062] in, is the predicted value of light brightness, h t (X) is the prediction result of the t-th decision tree for input X.

[0063] Materiality Assessment:

[0064] Weigh the importance of different features for the output based on the reduction of impurity:

[0065]

[0066] Among them, ΔVarn (X j ) indicates a decrease in variance. I(X j )=[I(X1),I(X2),...,I(X n )], which represents the importance weight of the j-th feature.

[0067] 2) Risk prediction algorithm:

[0068] The Bayesian optimization + feedforward neural network algorithm is used to predict lighting needs and potential risks in real time, and dynamically adjust the hyperparameters of the neural network to optimize brightness adjustment. The input of the model is X, and the output of the light brightness prediction is:

[0069]

[0070] in, is the predicted brightness, Δy is the prediction deviation;

[0071] Based on the predicted light intensity, the Softmax activation function is used to calculate the probability distribution of its corresponding risk level:

[0072]

[0073] in, is the predicted probability of the jth risk, C is the number of risk level categories (such as normal, low, medium, and high), and also represents different levels of brightness, h (1) represents the output of the hidden layer, Indicates bias, Represents weight.

[0074] Afterwards, use Bayesian optimization to solve the overall goal:

[0075]

[0076] Among them, L y and L r They are the regression loss of light brightness and the classification loss of risk level, respectively. α and β are the weight coefficients of the loss function.

[0077] 3) Fuzzy logic control algorithm: Based on the predicted light brightness output above and risk level Fuzzy logic control algorithm is used to further refine lighting adjustment to achieve a balance between energy consumption and safety, as follows:

[0078] Input: Light brightness deviation The difference between the predicted brightness and the target brightness y target represents the target temperature, Indicates predicted temperature; risk level Predicted risk level.

[0079] Output: Brightness adjustment amount (Δy): Final brightness after adjustment.

[0080] Fuzzy processing and reasoning:

[0081] The input variable ( and ) is fuzzified into three fuzzy sets; secondly, reasoning is performed based on a predefined fuzzy rule base, which can be customized according to requirements. Example rules are as follows:

[0082] if is "high deviation" and If it is "high risk", the "adjustment amount" should be "substantially increased".

[0083] if is "low bias" and If it is "low risk", the "adjustment amount" should be "increased slightly".

[0084] Defuzzification:

[0085] Use the centroid method to convert fuzzy sets into precise modulated quantities:

[0086]

[0087] In the formula, y i is the current brightness adjustment strategy; y target is the target brightness; E(y i ) is the energy consumption corresponding to the brightness strategy.

[0088] Final brightness adjustment:

[0089]

[0090] (4) Optimization and feedback:

[0091] By combining genetic algorithm with particle swarm optimization, the system performs multi-objective optimization on different brightness adjustment strategies to minimize energy consumption per unit time while meeting lighting requirements. The main steps are as follows:

[0092] Fitness evaluation:

[0093] The fitness function is used to evaluate the quality of each brightness adjustment strategy and balance brightness accuracy and energy consumption:

[0094]

[0095] Among them, F(x) is the fitness value, x represents the parameters of the brightness adjustment strategy, is the target brightness of the ith region, yi (x) is the actual brightness of the ith region under strategy x, w is the weight, and n is the total number of regions.

[0096] Particle Swarm Optimization (PSO) position update:

[0097] PSO optimizes the regulation strategy by updating the particle positions:

[0098]

[0099] Among them, x i is the particle position (brightness adjustment strategy), v i is the particle velocity, ω is the inertia weight, p i and g are the historical optimal and global optimal positions of the particle respectively, c1 and c2 are acceleration constants, and r1 and r2 are random numbers.

[0100] Final adjustment strategy and feedback:

[0101] Combining the results of genetic algorithm and PSO, the optimal brightness adjustment strategy is obtained:

[0102] y optimal =argmin y (|yy target |+E(y)) (13)

[0103] Among them, y is the current brightness adjustment strategy; y target is the target brightness; E(y) is the energy consumption corresponding to the brightness strategy.

[0104] At the same time, the energy consumption data is uploaded to the central control system in real time and historical records are formed to facilitate analysis and optimization of regulation strategies.

[0105] (5) Abnormal warning and handling:

[0106] When the density of people is too high, the equipment load is too large, or the ambient light is extremely insufficient, the system will trigger the early warning mechanism and notify the management personnel through sound and light prompts or mobile devices; the system can also automatically adjust the light to the maximum brightness to ensure the safety of operations in emergency situations. Its parameter settings are as follows:

[0107] 1) The perception range of ambient light intensity: 0-1000 lux, the adjustment range is 10%-100%.

[0108] 2) The detection range of personnel density is 0-20 people, and the adjustment threshold is 0-10 levels.

[0109] 3) Equipment load monitoring range: 0%-100%, with three adjustment levels (low, medium, and high).

[0110] The present invention has achieved remarkable results in improving the intelligent level, safety and energy saving of lighting control. The main advantages are as follows:

[0111] (1) Intelligent perception and adjustment: The system can dynamically adjust the area lighting according to changes in the actual working environment, realizing humanized and intelligent lighting control.

[0112] (2) Significant energy-saving effect: Through the comprehensive application of multiple algorithms, the system can significantly reduce lighting energy consumption and improve energy utilization efficiency while ensuring operational safety.

[0113] (3) Efficient safety assurance: The system can quickly respond to changes in personnel activities and equipment status, ensuring adequate lighting in emergency situations and improving operational safety in the maintenance area of ​​the hydropower plant.

[0114] (4) Wide adaptability: This method and device are applicable to hydropower plants and similar industrial sites, especially to various combinations of ambient light intensity, personnel density and equipment load. It can provide managers with intuitive lighting control and energy consumption analysis, and has good adaptability and broad application prospects.

[0115] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0117] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant, characterized in that: The following steps are involved: Determine the impact of the number of people, equipment status and ambient light intensity on light brightness, and use logistic regression models to predict potential safety risks in real time and adjust brightness; In response to brightness adjustment, the brightness is finely adjusted according to the density of people and the ambient light intensity through the fuzzy logic control algorithm, and energy consumption is optimized while meeting the lighting needs.

2. According to claim 1, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: When analyzing the impact of light brightness, the random forest algorithm is used to perform multi-parameter correlation analysis to determine the weights of the impact of personnel density, equipment load and ambient light on brightness.

3. According to claim 2, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: When making risk predictions, the Bayesian optimization + feedforward neural network algorithm is used to predict lighting needs and potential risks in real time, and dynamically adjust the hyperparameters of the neural network to optimize brightness adjustment.

4. According to claim 3, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: In the process of detailed brightness adjustment, the fuzzy logic control algorithm further refines the lighting adjustment based on the predicted light brightness and risk level to achieve a balance between energy consumption and safety.

5. According to claim 4, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: In the process of refining the lighting adjustment, the input variables are fuzzified into three fuzzy sets; after reasoning based on the predefined fuzzy rule base, the centroid method is used to convert the fuzzy sets into precise adjustment quantities.

6. According to claim 5, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: When optimizing energy consumption, a combination of genetic algorithm and particle swarm optimization is used to perform multi-objective optimization on different brightness adjustment strategies to minimize energy consumption per unit time while meeting lighting needs.

7. According to claim 6, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: When optimizing energy consumption, the fitness function is used to evaluate the quality of each brightness adjustment strategy and balance brightness accuracy and energy consumption. The fitness function is expressed as: Among them, F(x) is the fitness value, x represents the parameters of the brightness adjustment strategy, is the target brightness of the ith region, y i (x) is the actual brightness of the ith region under strategy x, w is the weight, and n is the total number of regions.

8. According to claim 7, an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant is characterized by: When optimizing energy consumption, the particle swarm optimization algorithm PSO is used to optimize the regulation strategy by updating the particle positions. PSO is expressed as: Among them, x i is the particle position, v i is the particle velocity, ω is the inertia weight, p i and g are the historical optimal and global optimal positions of the particle respectively, c1 and c2 are acceleration constants, and r1 and r2 are random numbers.

9. An intelligent brightness adjustment control system for a maintenance area of ​​a hydropower plant, used to implement an intelligent brightness adjustment control method for a maintenance area of ​​a hydropower plant as claimed in any one of claims 1 to 8, characterized in that: include: The adjustment module is used to determine the impact of the number of people, equipment status and ambient light intensity on the light brightness. Through the logistic regression model, it predicts potential safety risks in real time and adjusts the brightness. The corresponding module is used to respond to brightness adjustment. According to the density of people and the ambient light intensity, the brightness is adjusted in detail through the fuzzy logic control algorithm, and energy consumption is optimized while meeting the lighting needs.

Images