LED shell heat dissipation optimization system and method based on artificial intelligence

Abstract

The invention relates to the technical field of LED shells, and particularly discloses an LED shell heat dissipation optimization system and method based on artificial intelligence. A data acquisition and processing module; an artificial intelligence algorithm module; a control execution module; an interaction module; through cooperation of the temperature monitoring module, the data acquisition and processing module, the artificial intelligence algorithm module, the control execution module and the interaction module, the temperature monitoring module is used for monitoring temperature data of an LED chip and a shell in real time, and the data acquisition and processing module is used for preprocessing the acquired temperature data and external environment data; through accurate analysis and intelligent decision of the artificial intelligence algorithm module and accurate execution of the control execution module, a heat dissipation strategy can be automatically adjusted according to different working environments and LED working states, self-adaptive optimization is achieved, response can be made in time no matter environment temperature changes or LED load changes, and a good heat dissipation effect is kept.

Description

Technical Field

[0001] The present invention belongs to the technical field of LED housings, and particularly relates to an LED housing heat dissipation optimization system and method based on artificial intelligence. Background Art

[0002] An LED housing is an external structure used to encapsulate and protect an LED chip and related circuits, and at the same time undertakes the functions of heat dissipation, protection and assistance. Since a large amount of heat is generated when the LED chip is working, if the heat is not dissipated in time, the temperature of the LED chip will rise, resulting in low luminous efficiency of the LED chip and the phenomenon of color shift of the emitted light. Therefore, heat dissipation treatment needs to be carried out on the LED housing.

[0003] Currently, the common way to dissipate heat from an LED housing is to set a large number of heat dissipation fins on the LED housing to increase the heat dissipation area and improve the heat dissipation effect. For example, the patent document with the application number 202421376957.1 discloses an LED lamp heat dissipation housing, which includes a fixing plate, and a housing mechanism is arranged on the surface of the fixing plate. The housing mechanism includes a mounting plate and a connecting plate, and a heat dissipation mechanism is arranged in the middle of the connecting plate. The heat dissipation mechanism includes a heat dissipation fan blade, a heat dissipation plate and a filter plate. A cleaning mechanism is arranged on the surface of the fixed bin. The cleaning mechanism includes a rotating shaft and bristles; for this LED lamp heat dissipation housing, the lamp is installed on the wall through the mounting plate, and through the heat dissipation fan blade, the air inside the fixed bin and the outside air are made to flow to improve the heat dissipation efficiency of the LED lamp. Through the filter plate, the circulating air is filtered. Through the heat dissipation plate and heat dissipation scales, the LED lamp is cooled to improve the heat dissipation efficiency of the LED lamp. Through the rotating shaft, the bristles are driven to rotate to clean the filter plate to avoid dust clogging the filter plate and improve the air filtering effect of the filter plate.

[0004] However, using a large number of heat dissipation fins will increase the volume and weight of the product, and the shape and distribution of the fins are usually designed based on empirical values, making the heat dissipation method single and not facilitating automatic adjustment of the heat dissipation strategy according to different environments and the working state of the LED, thus affecting the heat dissipation efficiency. Therefore, we need to propose an LED housing heat dissipation optimization system and method based on artificial intelligence to solve the above existing problems, enabling it to automatically adjust the heat dissipation strategy according to different working environments and the working state of the LED, achieve adaptive optimization, and improve the heat dissipation effect. Summary of the Invention

[0005] The purpose of the present invention is to provide an LED housing heat dissipation optimization system and method based on artificial intelligence, which can automatically adjust the heat dissipation strategy according to different working environments and the working state of the LED, achieve adaptive optimization, and improve the heat dissipation effect, so as to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] An LED housing heat dissipation optimization system based on artificial intelligence, comprising: a temperature monitoring module, which collects temperature data of the LED chip and the housing in real time;

[0008] A data collection and processing module, which collects the temperature data monitored by the temperature monitoring module and external environment data, and preprocesses the temperature data and the environment data;

[0009] An artificial intelligence algorithm module, which analyzes and models the preprocessed temperature data and environment data through artificial intelligence algorithms, formulates an optimal heat dissipation strategy according to the analysis results, and generates an optimized control instruction according to the optimal heat dissipation strategy; at the same time, it also diagnoses and predicts the faults of the heat dissipation structure, confirms potential fault signs, and conducts preventive control on potential faults in advance;

[0010] A control execution module, which drives the heat dissipation structure to optimize heat dissipation according to the optimized control instruction output by the artificial intelligence algorithm module;

[0011] An interaction module, which provides an interaction interface between the user and the system, and is electrically connected to the temperature monitoring module, the data collection and processing module, the artificial intelligence algorithm module, and the control execution module respectively.

[0012] Preferably, the temperature monitoring module includes a plurality of temperature sensors, and the plurality of temperature sensors are evenly distributed at different positions of the LED housing, and a temperature sensor is also attached to the surface of the LED chip.

[0013] Preferably, the process of the temperature monitoring module for collecting temperature data is as follows:

[0014] A1. The temperature sensors sense and collect the temperatures of the LED chip and the housing at a sampling frequency of every 1 second interval;

[0015] A2. Convert the collected physical temperature signal into an analog electrical signal;

[0016] A3. Convert the analog electrical signal into a digital signal through an analog-to-digital converter, and then transmit the converted digital signal to the data collection and processing module.

[0017] Preferably, the data acquisition and processing module includes an environmental temperature sensor, a humidity sensor, and a data processor. The environmental temperature sensor, the humidity sensor, and the temperature sensor are all connected to the data processor. The external environmental data includes external environmental temperature data and environmental humidity data. The environmental temperature sensor and the humidity sensor collect the temperature data and humidity data of the external environment in real time according to their respective sampling frequencies, and convert the collected data into digital signals. The data processor is used to preprocess the external environmental data and temperature data.

[0018] Preferably, the process of the data processor preprocessing the collected temperature data and external environmental data is as follows:

[0019] B1. Clean the received external environmental data and temperature data, find the outliers in the data, and correct the outliers so that all data are within the normal range. Among them, the way to correct the outliers is to calculate the correction value using the linear interpolation formula according to the normal temperature values corresponding to two adjacent time points and then perform replacement correction. The linear interpolation formula is:

[0020] where t j is the time point at which the outlier appears, T j is the correction value of the outlier, t i and t i+1 are two adjacent time points, and T i and T i+1 are the normal data values corresponding to the two adjacent time points t i and t i+1 respectively;

[0021] B2. Use a low-pass filter to filter the cleaned data to make the data smoother;

[0022] B3. Extract features according to the filtered data, and then combine the extracted features to form a feature vector.

[0023] Preferably, in step B3, the extracted features include the data change rate, the data mean, and the variance. Calculate the average value of the data change rate according to the data change rate, and then arrange the average value of the data change rate, the data mean, and the variance in sequence to form a feature vector.

[0024] Preferably, the artificial intelligence algorithm adopts a multi-layer perceptron algorithm model. The process of generating the optimization control instruction is as follows:

[0025] C1. Divide the preprocessed feature vector into a training set and a test set, and perform normalization processing on the divided data to make different features have the same scale;

[0026] C2. Determine the network structure of the multi-layer perceptron algorithm model, where the network structure includes the number of neurons in the input layer, the number of hidden layers, the number of neurons in each hidden layer, and the number of neurons in the output layer;

[0027] C3. Initialize the parameters of the multi-layer perceptron algorithm model;

[0028] C4. Input the feature vectors in the training set into the multi-layer perceptron algorithm model for prediction to obtain the prediction results;

[0029] C5. Calculate the loss value between the prediction results and the true results, and use the stochastic gradient descent algorithm to update the parameters of the multi-layer perceptron algorithm model according to the loss value to minimize the loss function;

[0030] C6. Confirm whether the loss function has a significant decrease. If there is a significant decrease, repeat steps C4 - C5. If there is no significant decrease, the training of the multi-layer perceptron algorithm model is completed, and proceed to C7;

[0031] C7. Use the test set to evaluate the trained multi-layer perceptron algorithm model, and determine whether the performance of the multi-layer perceptron algorithm model meets the requirements. If the performance does not meet the requirements, adjust the parameters of the multi-layer perceptron algorithm model and repeat C4 - C6. If the performance meets the requirements, formulate the optimal heat dissipation strategy and proceed to C8;

[0032] C8. Input the currently collected and preprocessed feature vectors into the multi-layer perceptron algorithm model for predicting the heat dissipation demand, and formulate the optimal heat dissipation strategy according to the predicted heat dissipation demand;

[0033] C9. Convert the optimal heat dissipation strategy into specific control instructions and send them to the control execution module for heat dissipation optimization.

[0034] Preferably, the process for the artificial intelligence algorithm module to perform early prevention and control of potential faults is as follows:

[0035] C10. Use the trained multi-layer perceptron algorithm model to analyze the current feature vectors and predict whether there is fault type information and the probability of faults in the heat dissipation structure;

[0036] C11. Set a fault probability threshold, compare the predicted fault probability with the fault probability threshold, and confirm whether the predicted fault probability is greater than the fault probability threshold. If the predicted fault probability is greater than the fault probability threshold, it is determined that there is a potential fault, a fault alarm is issued, and proceed to C12. Otherwise, it is determined that there is no potential fault;

[0037] C12. Determine the specific fault type according to the predicted fault type information, and then determine the early prevention measures according to the fault type;

[0038] C13. Send a control instruction to the control execution module according to the determined preventive measures to perform preventive operations. At the same time, monitor the status of the heat dissipation structure, evaluate the effect of the preventive measures. If the failure probability is reduced to the safe range, stop the execution of the preventive measures. If the failure probability is not effectively controlled, further troubleshoot and repair the fault, and then repeat the execution of C12 - C13.

[0039] Preferably, the control execution module includes a PLC controller and a heat dissipation structure connected to the PLC controller. The heat dissipation structure includes heat sinks with adjustable heat dissipation angles and heat dissipation fans for accelerating the heat dissipation rate of the heat sinks. The heat dissipation fans are located on one side of the heat sinks, and the heat sinks are installed on the surface of the LED housing through an angle adjustment mechanism.

[0040] Based on the above-described AI-based LED housing heat dissipation optimization system, the present invention also provides an AI-based LED housing heat dissipation optimization method, including the following steps:

[0041] S1. Real-time collect the temperature data of the LED chip and the housing through the temperature monitoring module, and at the same time, the data collection and processing module collects external environment data;

[0042] S2. Preprocess the collected temperature data and environment data through the data collection and processing module;

[0043] S3. Use the artificial intelligence algorithm module to analyze and model the preprocessed temperature data and environment data, formulate the optimal heat dissipation strategy according to the analysis results, and generate an optimization control instruction according to the optimal heat dissipation strategy;

[0044] S4. The control execution module receives the optimization control instruction output by the artificial intelligence algorithm module and drives the corresponding actuator to achieve heat dissipation optimization;

[0045] S5. Display the temperature status of the LED and the working conditions of the heat dissipation structure through the interaction module, and send prompts and suggestions to the user;

[0046] S6. Repeat steps S1 - S5 to continuously monitor the temperature of the LED and the status of the heat dissipation structure, and continuously optimize the heat dissipation strategy according to the actual situation to adapt to different working environments and changes in the working status of the LED.

[0047] The AI-based LED housing heat dissipation optimization system and method proposed by the present invention have the following advantages compared with the prior art:

[0048] 1. Through the cooperation of the temperature monitoring module, data acquisition and processing module, artificial intelligence algorithm module, control execution module, and interaction module, the present invention utilizes the temperature monitoring module to monitor the temperature data of the LED chip and the housing in real time, the data acquisition and processing module to preprocess the collected temperature data and external environment data, the precise analysis and intelligent decision-making of the artificial intelligence algorithm module, and the accurate execution of the control execution module to achieve precise control of LED heat dissipation, ensure that the LED chip always operates within an appropriate temperature range, improve the luminous efficiency and stability, and can also automatically adjust the heat dissipation strategy according to different working environments and the working state of the LED to achieve adaptive optimization. Whether the ambient temperature changes or the LED load changes, it can respond in a timely manner and maintain a good heat dissipation effect.

[0049] 2. Through the fault diagnosis and prediction function of the artificial intelligence algorithm module, combined with the timely feedback and adjustment of the control execution module, the present invention can detect and solve potential problems in the heat dissipation system in advance, reduce the failure rate, extend the service life of the LED and the heat dissipation system, and improve the reliability and stability of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Shows a system block diagram of a heat dissipation optimization system according to an embodiment of the present invention;

[0051] Figure 2 Shows a flowchart of the data processor preprocessing the collected temperature data and external environment data according to an embodiment of the present invention;

[0052] Figure 3 Shows a flowchart of generating an optimized control instruction according to an embodiment of the present invention;

[0053] Figure 4 Shows a flowchart of the artificial intelligence algorithm module pre-emptively preventing and controlling potential failures according to an embodiment of the present invention;

[0054] Figure 5 Shows a flowchart of a heat dissipation optimization method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0056] The present invention provides as Figures 1-4The shown AI-based LED housing heat dissipation optimization system includes a temperature monitoring module, a data acquisition and processing module, an AI algorithm module, a control execution module, and an interaction module. The temperature monitoring module collects the temperature data of the LED chip and the housing in real time;

[0057] The temperature monitoring module includes multiple temperature sensors. The multiple temperature sensors are evenly distributed at different positions of the LED housing, and a temperature sensor is also attached to the surface of the LED chip. The temperature sensor is set as a thin-film thermocouple or a micro thermal resistor. By reasonably arranging the temperature sensors, the temperature data of the LED chip and the housing can be effectively collected, facilitating accurate heat dissipation optimization control.

[0058] The process of the temperature monitoring module collecting temperature data is as follows:

[0059] A1. The temperature sensors sense and collect the temperatures of the LED chip and the housing at a sampling frequency of every 1 second;

[0060] A2. Convert the collected physical temperature signal into an analog electrical signal. The analog electrical signal conversion formula is:

[0061] D = kT + b, where D is the analog electrical signal, k is the sensitivity coefficient of the temperature sensor, T is the actually measured temperature in °C, and b is the offset of the analog electrical signal when the temperature is 0;

[0062] A3. Convert the analog electrical signal into a digital signal through an analog-to-digital converter, and then transmit the converted digital signal to the data acquisition and processing module so that the data acquisition and processing module can process and store these data. The digital signal conversion formula is:

[0063] where S is the digital signal converted to an integer, the value range of S is [0, 2 n -1], D is the analog electrical signal input to the analog-to-digital converter, and D min ≤ D ≤ D max , D max and D min are respectively the maximum and minimum input analog electrical signal ranges of the analog-to-digital converter, and n is the resolution that determines the smallest voltage change that the analog-to-digital converter can distinguish;

[0064] The data acquisition and processing module collects the temperature data monitored by the temperature monitoring module and the external environment data, and preprocesses the temperature data and the environment data;

[0065] The data acquisition and processing module includes an environmental temperature sensor, a humidity sensor, and a data processor. The environmental temperature sensor, humidity sensor, and temperature sensor are all connected to the data processor. The external environmental data includes external environmental temperature data and environmental humidity data. The environmental temperature sensor and humidity sensor collect the temperature data and humidity data of the external environment in real time according to their respective sampling frequencies, and convert the collected data into digital signals. The data processor is used to preprocess the external environmental data and temperature data;

[0066] As Figure 2 shown, the process of the data processor preprocessing the collected temperature data and external environmental data is as follows:

[0067] B1. Clean the received external environmental data and temperature data, find the outliers in the data, and correct the outliers so that all data is within the normal range;

[0068] The way to correct outliers is to calculate the correction value using the linear interpolation formula according to the normal temperature values corresponding to two adjacent time points and then perform replacement correction. The linear interpolation formula is:

[0069] where, t j is the time point when the outlier appears, T j is the correction value of the outlier, t i and t i+1 are two adjacent time points, T i and T i+1 are the normal data values corresponding to the two adjacent time points t i and t i+1 respectively;

[0070] B2. Use a low-pass filter to filter the cleaned data to make the data smoother;

[0071] The formula expression of the low-pass filter is:

[0072] y(m) = ax(m) + (1 - a)y(m - 1), where y(m) is the filtered output data, a is the coefficient related to the cut-off frequency of the low-pass filter, with a value between 0 and 1, m is the discrete time point, and x(m) is the input cleaned data;

[0073] B3. Extract features from the filtered data, and then combine the extracted features to form a feature vector;

[0074] The extracted features include the data change rate, data mean, and variance. Calculate the average value of the data change rate according to the data change rate, and then form a feature vector by arranging the average value of the data change rate, data mean, and variance in sequence;

[0075] The calculation formula for the data change rate is as follows:

[0076] where Δt is the time interval between two adjacent time points t i and t i+1 , T i+1 and T i are the normal data values corresponding to two adjacent time points t i+1 and t i respectively, and ΔT is the data change rate;

[0077] The calculation formula for the data mean is as follows:

[0078] where is the data mean, p is the total number of data points, and T i is the data value at the i-th time point;

[0079] The variance calculation formula is as follows:

[0080] where σ is the data variance value, is the data mean, p is the total number of data points, and T i is the data value at the i-th time point;

[0081] Outliers are removed through data cleaning to ensure data accuracy; filtering operations eliminate noise interference to make the data smoother; feature extraction obtains key features related to heat dissipation, converting the original data into effective information available for analysis, providing high-quality data input for the artificial intelligence algorithm module.

[0082] The artificial intelligence algorithm module analyzes and models the preprocessed temperature data and environmental data through artificial intelligence algorithms, formulates the optimal heat dissipation strategy based on the analysis results, generates optimization control instructions according to the optimal heat dissipation strategy, and at the same time diagnoses and predicts the faults of the heat dissipation structure, identifies potential fault signs, and performs preventive control on potential faults in advance;

[0083] As Figure 3 shown, the artificial intelligence algorithm uses a multi-layer perceptron algorithm model, and the process of generating the optimization control instructions is as follows:

[0084] C1. Divide the preprocessed feature vectors into a training set and a test set, and perform normalization processing on the divided data to make different features have the same scale;

[0085] C2. Determine the network structure of the multi-layer perceptron algorithm model, where the network structure includes the number of neurons in the input layer, the number of hidden layers, the number of neurons in each hidden layer, and the number of neurons in the output layer;

[0086] C3. Initialize the parameters of the multi-layer perceptron algorithm model;

[0087] C4. Input the feature vectors in the training set into the multi-layer perceptron algorithm model for prediction to obtain the prediction results. In the multi-layer perceptron algorithm model, data enters from the input layer and passes through each hidden layer in turn. A linear transformation is performed in each hidden layer, and finally the prediction results are obtained in the output layer. The formula for the linear transformation is:

[0088] a l = f(w l a l-1 + b l ), where a l is the output data of the l-th layer, w l is the weight matrix of the l-th layer, a l-1 is the input data of the l-th layer, b l is the bias vector of the l-th layer, and l is the position of the hidden layer in the multi-layer perceptron algorithm model;

[0089] C5. Calculate the loss value between the prediction result and the true result, and use the stochastic gradient descent algorithm to update the parameters of the multi-layer perceptron algorithm model according to the loss value to minimize the loss function;

[0090] C6. Confirm whether the loss function has decreased significantly. If there is a significant decrease, repeat steps C4 - C5. If there is no significant decrease, the training of the multi-layer perceptron algorithm model is completed, and proceed to C7;

[0091] C7. Use the test set to evaluate the trained multi-layer perceptron algorithm model, and determine whether the performance of the multi-layer perceptron algorithm model meets the requirements. If the performance does not meet the requirements, adjust the parameters of the multi-layer perceptron algorithm model and repeat C4 - C6. If the performance meets the requirements, formulate the optimal heat dissipation strategy and proceed to C8; Among them, the performance of the multi-layer perceptron algorithm model can be calculated and evaluated using accuracy and mean square error;

[0092] C8. Input the currently collected and preprocessed feature vectors into the multi-layer perceptron algorithm model for predicting the heat dissipation requirements, and formulate the optimal heat dissipation strategy according to the predicted heat dissipation requirements;

[0093] When formulating the optimal heat dissipation strategy, first set the threshold range of the heat dissipation requirement index according to the usage environment of the LED lamp housing. The method for formulating the optimal heat dissipation strategy is as follows:

[0094] 1) When the predicted heat dissipation requirement index is less than the minimum value of the threshold range, maintain the current heat dissipation state, such as keeping the fan running at a low speed and maintaining the current heat dissipation area of the heat sink;

[0095] 2) When the heat dissipation requirement index is between the threshold ranges, increase the fan speed to the next gear or finely adjust the heat dissipation angle of the heat sink to increase the heat dissipation area, such as finely adjusting the heat dissipation angle of the heat sink in an increment of 1°;

[0096] 3) When the heat dissipation requirement index is greater than the maximum of the threshold range, increase the fan speed to the highest gear and at the same time deploy the heat sink to maximize the heat dissipation area;

[0097] C9. Convert the optimal heat dissipation strategy into specific control instructions and send them to the control execution module for heat dissipation optimization;

[0098] As Figure 4 shown, the process of the artificial intelligence algorithm module for early prevention and control of potential faults is as follows:

[0099] C10. Analyze the current feature vector using the trained multi-layer perceptron algorithm model to predict whether there is fault type information and the probability of faults in the heat dissipation structure;

[0100] C11. Set a fault probability threshold, compare the predicted fault probability with the fault probability threshold, and confirm whether the predicted fault probability is greater than the fault probability threshold. If the predicted fault probability is greater than the fault probability threshold, it is determined that there is a potential fault, a fault alarm is issued, and proceed to C12. Otherwise, it is determined that there is no potential fault;

[0101] C12. Determine the specific fault type according to the predicted fault type information, and then determine the early prevention measures according to the fault type;

[0102] The fault types include heat sink blockage faults and fan faults. The early prevention measures for heat sink blockage faults are to clean and inspect the heat sink every 5 - 10 minutes or reduce the working current of the LED chip to reduce the heat generated by the LED chip; the early prevention measures for fan faults are to switch to a standby fan or reduce the working power of the LED chip;

[0103] C13. Send control instructions to the control execution module according to the determined prevention measures to perform prevention operations, and at the same time monitor the status of the heat dissipation structure and evaluate the effect of the prevention measures. If the fault probability drops to the safe range, stop the execution of the prevention measures. If the fault probability is not effectively controlled, further troubleshoot and repair the fault, and then repeat C12 - C13.

[0104] The fault diagnosis and prediction function of the artificial intelligence algorithm module, combined with the timely feedback and adjustment of the control execution module, can detect and solve potential problems in the heat dissipation system in advance, reduce the fault occurrence rate, extend the service life of the LED and the heat dissipation system, and improve the reliability and stability of the entire system.

[0105] The control execution module drives the heat dissipation structure according to the optimized control instruction output by the artificial intelligence algorithm module to optimize heat dissipation, so as to achieve the purpose of real-time adjustment of the heat dissipation effect;

[0106] The control execution module includes a PLC controller and a heat dissipation structure connected to the PLC controller. The heat dissipation structure includes heat sinks with adjustable heat dissipation angles and heat dissipation fans for accelerating the heat dissipation rate of the heat sinks. The heat dissipation fans are located on one side of the heat sinks. The heat sinks are installed on the surface of the LED housing through an angle adjustment mechanism. The angle adjustment mechanism consists of a rack, a gear, a motor, and a fixed bracket. The rack is connected to the heat sink. The motor drives the gear to rotate, and the gear meshes with the rack, so that the rack drives the heat sink to move linearly, realizing the change of the heat sink angle. Specifically, after the motor is powered on, its rotating shaft drives the gear to rotate. Since the gear meshes with the rack, the rotational motion of the gear is converted into the linear motion of the rack. The rack is fixedly connected to the heat sink, so the linear motion of the rack drives the heat sink to rotate around its installation point, thereby adjusting the angle of the heat sink. The angle change of the heat sink is accurately controlled by controlling the forward and reverse rotation of the motor, and a large driving force can be provided.

[0107] The interaction module provides an interaction interface between the user and the system. The user can set system parameters, view the temperature status of the LED, the working conditions of the heat dissipation system, and fault alarm information through this interaction interface; at the same time, it also sends prompts and suggestions to the user through the interaction module to help the user better manage and maintain the LED heat dissipation structure. The interaction module is electrically connected to the temperature monitoring module, the data acquisition and processing module, the artificial intelligence algorithm module, and the control execution module respectively.

[0108] The interaction module presents a user interface on the display screen. The user interface visually displays the LED temperature status, the working conditions of the heat dissipation structure, and fault alarm information. At the same time, it receives the parameter setting instructions input by the user through the keyboard or touch screen, and then transmits the parameter instructions input by the user to the temperature monitoring module, the data acquisition and processing module, the artificial intelligence algorithm module, and the control execution module. At the same time, it receives the feedback information of the temperature monitoring module, the data acquisition and processing module, the artificial intelligence algorithm module, and the control execution module and updates the interface display. Finally, it sends prompt and suggestion information to the user according to the running status and fault diagnosis results of the system.

[0109] Through the cooperation of the temperature monitoring module, data acquisition and processing module, artificial intelligence algorithm module, control execution module and interaction module, the temperature monitoring module is used to monitor the temperature data of the LED chip and the housing in real time. The data acquisition and processing module preprocesses the collected temperature data and external environment data. The accurate analysis and intelligent decision-making of the artificial intelligence algorithm module and the accurate execution of the control execution module are used to achieve precise control of LED heat dissipation, ensure that the LED chip always works within an appropriate temperature range, improve the luminous efficiency and stability, and can also automatically adjust the heat dissipation strategy according to different working environments and the working state of the LED to achieve adaptive optimization. Whether the ambient temperature changes or the LED load changes, it can respond in a timely manner and maintain a good heat dissipation effect.

[0110] Based on the above-described artificial intelligence-based LED housing heat dissipation optimization system, the present invention also provides an artificial intelligence-based LED housing heat dissipation optimization method, as Figure 5 shown, including the following steps:

[0111] S1. Real-time collect the temperature data of the LED chip and the housing through the temperature monitoring module, and at the same time, the data acquisition and processing module collects external environment data;

[0112] S2. Preprocess the collected temperature data and environment data through the data acquisition and processing module;

[0113] S3. Use the artificial intelligence algorithm module to analyze and model the preprocessed temperature data and environment data, draw up the optimal heat dissipation strategy according to the analysis results, and generate an optimized control instruction according to the optimal heat dissipation strategy;

[0114] S4. The control execution module receives the optimized control instruction output by the artificial intelligence algorithm module and drives the corresponding actuator to achieve heat dissipation optimization;

[0115] S5. Display the temperature status of the LED and the working conditions of the heat dissipation structure through the interaction module, and send prompts and suggestions to the user;

[0116] S6. Repeat steps S1-S5 to continuously monitor the temperature of the LED and the status of the heat dissipation structure in real time, continuously optimize the heat dissipation strategy according to the actual situation to adapt to different working environments and changes in the working state of the LED, and ensure that the LED is always in a good heat dissipation state.

[0117] By using the temperature monitoring module to monitor the temperature data of the LED chip and the housing in real time, the data acquisition and processing module to preprocess the acquired temperature data and the external environment data, the precise analysis and intelligent decision-making of the artificial intelligence algorithm module, and the accurate execution of the control execution module, it is possible to automatically adjust the heat dissipation strategy according to different working environments and the working states of the LED, achieve adaptive optimization, and improve the heat dissipation effect of the LED housing.

[0118] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An LED housing heat dissipation optimization system based on artificial intelligence, characterized in that: Including: A temperature monitoring module that collects the temperature data of the LED chip and the housing in real time; A data acquisition and processing module that collects the temperature data monitored by the temperature monitoring module and the external environment data, and preprocesses the temperature data and the environment data; An artificial intelligence algorithm module that analyzes and models the preprocessed temperature data and environment data through artificial intelligence algorithms, formulates an optimal heat dissipation strategy according to the analysis results, and generates an optimized control instruction according to the optimal heat dissipation strategy; at the same time, it also diagnoses and predicts the faults of the heat dissipation structure, confirms potential fault signs, and performs preventive control on potential faults in advance; A control execution module that drives the heat dissipation structure to optimize heat dissipation according to the optimized control instruction output by the artificial intelligence algorithm module; An interaction module that provides an interaction interface between the user and the system, and the interaction module is electrically connected to the temperature monitoring module, the data acquisition and processing module, the artificial intelligence algorithm module, and the control execution module respectively.

2. The AI-based LED housing heat dissipation optimization system according to claim 1, wherein: The temperature monitoring module includes a plurality of temperature sensors, and the plurality of temperature sensors are evenly distributed at different positions of the LED housing, and a temperature sensor is also attached to the surface of the LED chip.

3. The AI-based LED housing heat dissipation optimization system according to claim 2, wherein: The process of the temperature monitoring module for collecting temperature data is as follows: A1. The temperature sensors sense and collect the temperatures of the LED chip and the housing at a sampling frequency of every 1 second; A2. Convert the collected physical temperature signal into an analog electrical signal; A3. Convert the analog electrical signal into a digital signal through an analog-to-digital converter, and then transmit the converted digital signal to the data acquisition and processing module.

4. The AI-based LED housing heat dissipation optimization system according to claim 1, wherein: The data acquisition and processing module includes an ambient temperature sensor, a humidity sensor, and a data processor. The ambient temperature sensor, the humidity sensor, and the temperature sensors are all connected to the data processor. The external environment data includes external ambient temperature data and environmental humidity data. The ambient temperature sensor and the humidity sensor collect the temperature data and humidity data of the external environment at their respective sampling frequencies in real time, and convert the collected data into digital signals. The data processor is used to preprocess the external environment data and the temperature data.

5. The AI-based LED housing heat dissipation optimization system according to claim 4, wherein: The process of the data processor for preprocessing the collected temperature data and external environment data is as follows: B1. Clean the received external environment data and temperature data, find out the outliers in the data, and correct the outliers so that all data are within the normal range. Among them, the way to correct the outliers is to calculate the correction value according to the normal temperature values corresponding to two adjacent time points using the linear interpolation formula and then perform replacement correction. The linear interpolation formula is: Among them, t j is the time point at which the outlier appears, and T j is the correction value of the outlier, t i and t i+1 are two adjacent time points, and T i and T i+1 are the normal data values corresponding to the two adjacent time points t i and t i+1 respectively; B2. Filter the cleaned data using a low-pass filter to make the data smoother; B3. Extract features according to the filtered data, and then combine the extracted features to form a feature vector.

6. The LED housing heat dissipation optimization system based on artificial intelligence according to claim 5, wherein: In step B3, the extracted features include the data change rate, data mean, and variance. Calculate the average value of the data change rate based on the data change rate, and then form a feature vector by arranging the average value of the data change rate, data mean, and variance in sequence.

7. The AI-based LED housing heat dissipation optimization system according to claim 6, characterized in that: The artificial intelligence algorithm adopts a multi-layer perceptron algorithm model, and the process of generating the optimization control instruction is as follows: C1. Divide the preprocessed feature vector into a training set and a test set, and perform normalization processing on the divided data to make different features have the same scale; C2. Determine the network structure of the multi-layer perceptron algorithm model, and the network structure includes the number of neurons in the input layer, the number of hidden layers, the number of neurons in each hidden layer, and the number of neurons in the output layer; C3. Initialize the parameters of the multi-layer perceptron algorithm model; C4. Input the feature vector in the training set into the multi-layer perceptron algorithm model for prediction to obtain a prediction result; C5. Calculate the loss value between the prediction result and the true result, and use the stochastic gradient descent algorithm to update the parameters of the multi-layer perceptron algorithm model according to the loss value to minimize the loss function; C6. Confirm whether the loss function has decreased significantly. If there is a significant decrease, repeat steps C4 - C5. If there is no significant decrease, the training of the multi-layer perceptron algorithm model is completed, and enter C7; C7. Use the test set to evaluate the trained multi-layer perceptron algorithm model, and judge whether the performance of the multi-layer perceptron algorithm model meets the requirements. If the performance does not meet the requirements, adjust the parameters of the multi-layer perceptron algorithm model and repeat C4 - C6. If the performance meets the requirements, formulate the optimal heat dissipation strategy and enter C8; C8. Input the currently collected and preprocessed feature vector into the multi-layer perceptron algorithm model for predicting the heat dissipation demand, and formulate the optimal heat dissipation strategy according to the predicted heat dissipation demand; C9. Convert the optimal heat dissipation strategy into specific control instructions and send them to the control execution module for heat dissipation optimization.

8. The AI-based LED housing heat dissipation optimization system according to claim 7, characterized in that: The process of the artificial intelligence algorithm module for early prevention and control of potential faults is as follows: C10. Use the trained multi-layer perceptron algorithm model to analyze the current feature vector and predict whether there is fault type information and the probability of a fault in the heat dissipation structure; C11. Set a fault probability threshold, compare the predicted fault probability with the fault probability threshold, and confirm whether the predicted fault probability is greater than the fault probability threshold. If the predicted fault probability is greater than the fault probability threshold, it is judged that there is a potential fault, and a fault alarm is issued, and enter C12. Otherwise, it is judged that there is no potential fault; C12. Determine the specific fault type according to the predicted fault type information, and then determine the early prevention measures according to the fault type; C13. Send control instructions to the control execution module according to the determined prevention measures to perform prevention operations, and at the same time monitor the state of the heat dissipation structure and evaluate the effect of the prevention measures. If the fault probability is reduced to the safe range, stop the execution of the prevention measures. If the fault probability is not effectively controlled, further troubleshoot and repair the fault, and then repeat C12 - C13.

9. The AI-based LED housing heat dissipation optimization system according to claim 1, wherein: The control execution module includes a PLC controller and a heat dissipation structure connected to the PLC controller. The heat dissipation structure includes heat sinks with adjustable heat dissipation angles and heat dissipation fans for accelerating the heat dissipation rate of the heat sinks. The heat dissipation fans are located on one side of the heat sinks, and the heat sinks are mounted on the surface of the LED housing through an angle adjustment mechanism.

10. The AI-based LED housing heat dissipation optimization method, the AI-based LED housing heat dissipation optimization system according to any one of claims 1-9, characterized in that: The steps are as follows: S1. The temperature data of the LED chip and the housing are collected in real time through the temperature monitoring module, and at the same time, the data acquisition and processing module collects external environment data; S2. The collected temperature data and environment data are preprocessed through the data acquisition and processing module; S3. The preprocessed temperature data and environment data are analyzed and modeled using the artificial intelligence algorithm module. An optimal heat dissipation strategy is formulated according to the analysis results, and an optimized control instruction is generated according to the optimal heat dissipation strategy; S4. The control execution module receives the optimized control instruction output by the artificial intelligence algorithm module and drives the corresponding actuator to achieve heat dissipation optimization; S5. The temperature status of the LED and the working conditions of the heat dissipation structure are displayed through the interaction module, and prompts and suggestions are sent to the user; S6. Steps S1 - S5 are repeatedly executed to monitor the temperature of the LED and the status of the heat dissipation structure in real time, and the heat dissipation strategy is continuously optimized according to the actual situation to adapt to different working environments and changes in the working status of the LED.

Images