Intelligent Adjustment Method and Device for the Intelligent Control System of a Cooling Fan Resistant to Dust and Sand Environments

Abstract

The present invention relates to the field of intelligent control technology, and discloses an intelligent adjustment method and device for a heat dissipation fan intelligent control system in a sand and dust environment. The method includes: collecting multi-condition data of the heat dissipation test platform of the heat dissipation fan to obtain a sand and dust environment sample library; quantitatively modeling and analyzing the dust accumulation dynamics characteristics and the formation mechanism of duct blockage based on the sand and dust environment sample library to obtain a thermal equivalent model; performing feature extraction and integration based on the thermal equivalent model to obtain a multi-dimensional sand and dust environment heat dissipation feature vector; inputting the multi-dimensional sand and dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan cooperative control parameters adapted to the sand and dust environment. The present invention comprehensively characterizes the working state of the heat dissipation system in the sand and dust environment, overcomes the problem of insufficient description of traditional features in the sand and dust environment, and thus improves the adaptability and reliability of the heat dissipation fan in the complex sand and dust environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and particularly to an intelligent adjustment method and device for a heat dissipation fan intelligent control system resistant to a sand-dust environment. Background Art

[0002] In an industrial environment with severe sand and dust, heat dissipation fans are key components for equipment cooling. However, dust accumulation and particulate blockage can lead to a significant decline in heat dissipation performance, increased energy consumption, and shortened equipment service life. Traditional heat dissipation control methods mainly use iterative search or simple temperature feedback mechanisms to determine fan control parameters. These methods can meet the requirements in normal environments, but in a sand-dust environment, there are problems such as low control success rate, long response time, and inability to cope with dust interference, making it difficult to meet the actual needs of industrial applications.

[0003] Existing heat dissipation control methods in the prior art usually lack an in-depth understanding of the dynamic characteristics of dust accumulation and the formation mechanism of duct blockage, and are unable to accurately predict the attenuation law of fan performance in a sand-dust environment, resulting in low control accuracy, high energy consumption, and short fan life. Especially in a multi-fan system, each fan usually works independently, lacking coordination and cooperation. The contradiction between dust protection and heat dissipation efficiency is more prominent, the overall performance of the system is difficult to guarantee, and it is difficult to make a timely and effective response in the case of sudden changes in dust concentration. Summary of the Invention

[0004] The present invention provides an intelligent adjustment method and device for a heat dissipation fan intelligent control system resistant to a sand-dust environment. The present invention comprehensively characterizes the working state of the heat dissipation system in a sand-dust environment, overcomes the problem of insufficient description of traditional features in a sand-dust environment, and thus improves the adaptability and reliability of the heat dissipation fan in a complex sand-dust environment.

[0005] In a first aspect, the present invention provides an intelligent adjustment method for a heat dissipation fan intelligent control system resistant to a sand-dust environment. The intelligent adjustment method for the heat dissipation fan intelligent control system resistant to a sand-dust environment includes:

[0006] Collecting multi-condition data of a heat dissipation test platform of a heat dissipation fan to obtain a sand-dust environment sample library;

[0007] Based on the sand-dust environment sample library, quantitatively modeling and analyzing the dynamic characteristics of dust accumulation and the formation mechanism of duct blockage to obtain a thermal equivalent model;

[0008] Based on the thermal equivalent model, extracting and integrating features to obtain a multi-dimensional sand-dust environment heat dissipation feature vector;

[0009] Inputting the multi-dimensional sand-dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan collaborative control parameters adapted to the sand-dust environment.

[0010] In a second aspect, the present invention provides an intelligent adjustment device for an intelligent control system of a heat dissipation fan in a sand and dust environment. The intelligent adjustment device for the intelligent control system of the heat dissipation fan in the sand and dust environment includes:

[0011] An acquisition module, configured to collect multi-condition data of a heat dissipation test platform of the heat dissipation fan to obtain a sand and dust environment sample library;

[0012] A modeling module, configured to perform quantitative modeling analysis on the dust accumulation kinetic characteristics and the formation mechanism of air duct blockage based on the sand and dust environment sample library to obtain a thermal equivalent model;

[0013] A feature extraction module, configured to perform feature extraction and integration based on the thermal equivalent model to obtain a multi-dimensional heat dissipation feature vector of the sand and dust environment;

[0014] A processing module, configured to input the multi-dimensional heat dissipation feature vector of the sand and dust environment into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan cooperative control parameters adapted to the sand and dust environment.

[0015] In the technical solution provided by the present invention, a comprehensive sand and dust environment sample library is established through accurate multi-condition data collection and processing. The dust accumulation kinetic characteristics and the air duct blockage formation mechanism model developed based on this library reveal the internal mechanism of the reduction of heat dissipation efficiency in the sand and dust environment. With the help of innovative features such as the sum of periodic temperature differences and the energy consumption fluctuation array, the working state of the heat dissipation system in the sand and dust environment is comprehensively characterized, overcoming the insufficient description of traditional features. The constructed gradient boosting learning model with a multi-attraction mechanism realizes the accurate prediction of the optimal control parameters, and has obtained a significant improvement in the generation of the fan control trajectory. The control strategy combining complementary fan control and dynamic scaling enables the multi-fan system to form a complementary effect against dust by reasonably setting the fan phase difference and dynamically adjusting the power distribution, and at the same time realizes an adaptive control parameter adjustment mechanism based on temperature, dust concentration, and system reliability index. Compared with the prior art, the control efficiency of the present invention in the sand and dust environment is improved by an order of magnitude, while reducing the system energy consumption and extending the service life of the fan, providing an economical and efficient solution for the heat dissipation of industrial equipment in the sand and dust environment. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1Schematic diagram of the steps of the intelligent adjustment method of the intelligent control system of the heat dissipation fan for anti-sandstorm environment in the embodiment of the present invention;

[0018] Figure 2 Schematic diagram of the structure of the intelligent adjustment device of the intelligent control system of the heat dissipation fan for anti-sandstorm environment in the embodiment of the present invention. Detailed implementation manners

[0019] The embodiment of the present invention provides an intelligent adjustment method and device for the intelligent control system of the heat dissipation fan for anti-sandstorm environment. The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order different from that shown or described herein. In addition, the terms "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] For the convenience of understanding, the specific process of the embodiment of the present invention will be described below. Please refer to Figure 1 One embodiment of the intelligent adjustment method of the intelligent control system of the heat dissipation fan for anti-sandstorm environment in the embodiment of the present invention includes:

[0021] Step S1: Collect multi-condition data of the heat dissipation test platform of the heat dissipation fan to obtain a sandstorm environment sample library;

[0022] 0 It can be understood that the execution subject of the present invention can be the intelligent adjustment device of the intelligent control system of the heat dissipation fan for anti-sandstorm environment, or a terminal or a server. Specifically, it is not limited here. The embodiment of the present invention takes the server as the execution subject as an example for illustration.

[0023] Specifically, a heat dissipation test platform for the cooling fan is built. The test platform includes a cooling fan system and is equipped with a series of sensing devices for collecting the environmental and equipment operating states, including a temperature sensor array, a dust concentration sensor, a fan speed measuring device, a power monitoring module, and a thermal imager. The temperature sensor array monitors the temperature distribution changes in the heat dissipation area in real time. The dust concentration sensor is used to measure the dust concentration level in the test environment. The fan speed measuring device records the fan speed data under different working conditions. The power monitoring module measures the power consumption performance of the fan system. The thermal imager can visually present the heat distribution of the cooling fan under different loads and environmental conditions. Configure the temperature sensor array so that it is evenly distributed at the key target positions in the heat dissipation area to avoid temperature data acquisition blind spots and errors caused by uneven sensor distribution. At the same time, set the sampling frequency of the sensors so that data collection can ensure real-time performance without causing data redundancy and system resource waste due to too high a sampling frequency. After completing the hardware configuration, set up multiple working conditions for the test environment and formulate a test matrix containing multi-dimensional parameters. This multi-dimensional test matrix includes M dust concentration levels, N environmental temperature ranges, and T heat load levels. Through the method of multi-dimensional combined testing, various dust environments and operating conditions faced by the cooling fan are covered, thus ensuring the representativeness and effectiveness of the test data. Monitor the single-fan mode and multi-fan mode based on the multi-dimensional test matrix, so as to be able to compare the heat dissipation effects and system performances under different fan configurations. During the test, temperature change data is obtained in real time through the temperature sensor array, the dust concentration sensor continuously records the dust accumulation data, the fan speed measuring device synchronously obtains the fan speed data under different loads, and the power monitoring module monitors the energy consumption changes of the fan system. Perform outlier detection and filtering on the temperature change data, dust accumulation data, fan speed data, and power consumption data. The outlier detection process combines statistical methods and machine learning models to effectively eliminate data anomalies caused by sensor errors, sudden environmental conditions, or equipment failures. For example, by setting a threshold range based on historical data and physical models, quickly screen out abnormal data points that deviate from the normal range, and combine filtering processing (such as Kalman filtering, mean filtering, etc.) to smooth the data curve and eliminate noise interference to obtain a denoised effective data set. Classify and label the denoised effective data set according to dust concentration, environmental temperature, and heat load. According to different dust concentration levels (for example, M concentration levels from low to high), different environmental temperature ranges (N temperature ranges, such as low temperature, medium temperature, and high temperature environments), and different heat load levels (T heat load levels, such as no load, partial load, and full load), all data is sorted, classified, and labeled in an orderly manner to obtain a dust environment sample library.

[0024] Step S2: Based on the dust environment sample library, quantitatively model and analyze the dust accumulation kinetics characteristics and the formation mechanism of air duct blockage to obtain a thermal equivalent model;

[0025] Specifically, conduct a correlation analysis on the dust accumulation data and the operating parameters of the cooling fan in the dust environment sample library. By analyzing the accumulation law of dust in the cooling fan system under different working conditions, construct a dust accumulation kinetics characteristics model. In this process, based on the dynamic characteristics of the accumulation amount changing with time, establish a mathematical model of dust accumulation. For example, describe the influence of factors such as dust concentration, wind speed, and temperature on the dust accumulation process through an accumulation rate function. Assume the dust accumulation amount changes with time and is affected by dust concentration , wind speed and ambient temperature . Establish a kinetic model as , where is the initial dust amount, is the accumulation rate function, which is obtained through fitting analysis of the sample library data, so as to accurately describe the dynamic process of dust accumulation on the fan blades and the air duct surface. To analyze the formation mechanism of air duct blockage, perform grid division on the heat dissipation area, divide the entire heat dissipation air duct and related heat conduction areas into several small grids, and obtain a refined thermal resistance distribution grid by calculating the thermal resistance of each grid point. Grid division can not only accurately locate the blocked area in the air duct in space, but also deduce the influence of the blockage on the overall air flow distribution and heat dissipation efficiency of the air duct through the thermal resistance calculation model. For example, at each grid point , the thermal resistance is obtained through comprehensive calculation of the material thermal conductivity, dust accumulation thickness, and wind speed, so as to construct a model of the formation principle of air duct blockage. The air duct blockage model is further quantified as , where is the initial thermal resistance, is the influence coefficient of dust accumulation on the increase of thermal resistance, and this model accurately reflects the dynamic influence of dust accumulation on the air duct resistance and air flow distribution of the cooling fan. And conduct a comparative analysis on the actual heat dissipation efficiency and the theoretical heat dissipation efficiency of the cooling fan under different working conditions to obtain a fan performance degradation model. During the experiment, the heat dissipation performance data of the fan are collected in real time through an infrared thermal imager, a power monitoring module, and a temperature sensor array. Compare the actually measured heat dissipation efficiency with the theoretical heat dissipation efficiency calculated under ideal working conditions, and find the situation of heat dissipation efficiency decline caused by dust accumulation and air duct blockage. Based on these data, construct a fan performance degradation model, for example, through an efficiency degradation coefficient To describe the effects of dust concentration, thermal resistance change, and fan speed change on heat dissipation performance. Perform parameter fitting analysis on the dust accumulation kinetics characteristic model, air duct blockage formation principle model, and fan performance decay model. Through optimization methods such as the least squares method, gradient descent method, or genetic algorithm, compare the experimental data with the model output, and adjust the parameters in the model to make the model reflect the actual situation to the greatest extent. For example, through the experimental data of variables such as dust accumulation amount, concentration, wind speed, and temperature, calculate the dust adhesion rate coefficient and the dust concentration influence coefficient and other parameters to make the dust accumulation model more accurate. Through the relationship between the change in thermal resistance and the dust accumulation amount in the air duct blockage model, fit the thermal resistance influence coefficient to more accurately predict the impact of air duct blockage on heat dissipation performance. Substitute the optimal parameter values obtained through fitting into the dust accumulation kinetics characteristic model, air duct blockage formation principle model, and fan performance decay model respectively. Through the combination of the models, form the final thermal equivalent model.

[0026] Step S3: Based on the thermal equivalent model, perform feature extraction and integration to obtain a multi-dimensional heat dissipation feature vector in a sandy dust environment;

[0027] Specifically, the data output by the thermal equivalent model is preliminarily screened to construct an original feature set. The thermal equivalent model provides the operating data of the cooling fan system in different dust environments, including instantaneous temperature values, temperature change rates, dust concentrations, fan speeds, and power consumption data. These data are collected in real time by sensors and stored in the dataset after preprocessing. By analyzing and screening these data, outliers and invalid data are removed, and the key features that effectively reflect the system state under normal operating conditions are retained to obtain the original feature set. The temperature data in the original feature set is segmented, and the entire temperature data time series is divided into several time windows of a fixed length (such as one window per minute or per hour). The difference between the maximum and minimum temperatures is calculated within each time window, and these differences are accumulated to obtain the sum of periodic temperature differences feature, which effectively captures the fluctuations in the heat dissipation capacity of the cooling fan at different time periods. This feature is also used to detect the temperature stability state of the cooling fan at night or under low-load conditions, thereby assisting in determining whether the system has entered a stable operating mode. At the same time, for the power data in the original feature set, continuous recording is used for analysis, and the standard deviation of the power data within each time period is calculated. These standard deviation values are arranged into a sequence to obtain the energy consumption fluctuation array feature. The standard deviation of the power data can quantify the fluctuation amplitude of the energy consumption of the fan system within a specific time period. When the fan is in a stable operating state, its power fluctuation is small, while when the system causes the fan to frequently adjust its speed due to dust blockage or drastic changes in load, the power fluctuation will increase significantly. Fourier transform analysis is performed on the fan speed data in the original feature set. By converting the time-domain signal into a frequency-domain signal, the energy distribution in the speed spectrum is calculated, and the ratio of the spectrum energy to the energy of the original speed signal is calculated to obtain the speed regularity feature, which reflects whether the fan maintains a certain operating rhythm during long-term operation. For example, under normal circumstances, the fan speed should show a certain regular fluctuation with changes in temperature or load, and when the fan speed frequently jumps due to dust blockage, the ratio of its spectrum energy will change significantly. During the analysis of the heat dissipation efficiency data, the number of times the direction of the heat dissipation efficiency change is reversed is counted through the difference and sign change detection method to obtain the heat dissipation efficiency change reversal count feature. This feature is used to capture the stability and response characteristics of the system's heat dissipation efficiency under different operating conditions. The original feature set, the sum of periodic temperature differences feature, the energy consumption fluctuation array feature, the speed regularity feature, and the heat dissipation efficiency change reversal count feature are combined to form an initial multi-dimensional feature vector, and feature dimensionality reduction is performed. For example, through methods such as principal component analysis, linear discriminant analysis, or autoencoders, the high-dimensional feature vector is projected into a low-dimensional space while trying to retain the effective information of the features. During the dimensionality reduction process, the key features that have a greater impact on the heat dissipation performance are automatically selected, and redundant and noise information is removed to obtain the multi-dimensional dust environment heat dissipation feature vector.

[0028] Step S4: Input the multi-dimensional dust environment heat dissipation feature vector into the gradient boosting learning model with a multi-attraction mechanism for processing to obtain the fan collaborative control parameters adapted to the dust environment.

[0029] Specifically, the multi-dimensional dust environment heat dissipation feature vector is input into a deep neural network for feature mapping to obtain the mapped feature space data. Through its multi-layer structure and non-linear activation function, the deep neural network performs multiple non-linear transformations on the feature data, enabling the feature vector to complete complex feature mapping in a high-dimensional space, thereby transforming the input features into higher-level feature representations with greater predictive value. In this process, the hidden layers of the network gradually extract the patterns and regularities in the data, making the mapped feature space data not only a simple transformation of the original data but also a deep reconstruction at the data abstraction level. The mapped feature space data is input into a gradient boosting learning model with a multi-attractor mechanism for predicting control parameters, obtaining a preliminary predicted value of the control parameters. The core module of the gradient boosting learning model consists of a gradient boosting decision module constructed by the XGBoost algorithm. XGBoost is an ensemble learning method based on decision trees that gradually fits the error of the data by constructing multiple weak classifiers (decision trees), enabling the model to continuously learn the non-linear relationship between features and the target output. In specific implementation, the model generates new decision trees by learning the gradient information of the error in each round of iteration to supplement and correct the prediction error of the previous round. This mechanism of gradually approaching the true value can effectively improve the prediction accuracy of the model. The regularization mechanism in the XGBoost model can also avoid overfitting of the model, enabling the preliminary predicted value of the predicted control parameters to maintain good generalization performance under various dust environments. Calculate the similarity between the multi-dimensional dust environment heat dissipation feature vector and the predefined K attractors to obtain the similarity values between the feature vector and each attractor. An attractor refers to a predefined feature pattern under different dust environments and working conditions, such as a specific attractor for a high dust concentration and low wind speed environment, or an attractor for a high temperature and high load working condition. These attractors are predefined through clustering analysis or expert experience and represent the control requirements of the heat dissipation system under typical environments. By calculating the similarity between the current feature vector and these attractors, the matching degree between the current working condition and historical typical working conditions is quantified. For example, the similarity value is calculated through methods such as cosine similarity, Euclidean distance, or dynamic time warping. Based on the similarity values between the feature vector and each attractor, perform normalization processing to obtain weight coefficients to ensure that the influence weights of different attractors are numerically stable and comparable. The normalization processing uses the softmax function or linear normalization method to convert all similarity values into a probability distribution between 0 and 1, making the sum of all weight coefficients equal to 1, effectively avoiding weight imbalance caused by individual similarity values being too large or too small, and thus making the control parameter prediction process more stable and reliable. According to the weight coefficients, perform weighted fusion calculation on the preliminary predicted values of the control parameters corresponding to each attractor to obtain the fan collaborative control parameters. Multiply the preliminary predicted value corresponding to each attractor by its weight coefficient, and then accumulate the weighted predicted values of all attractors to obtain the weighted fusion control parameters.

[0030] Perform cluster analysis on the historical optimized control strategy data to obtain the centers of K typical control strategies. These centers serve as K attractors, and each attractor represents an optimal control mode in the feature space. The cluster analysis method uses the K-means clustering algorithm, which iteratively divides the historical data into K clusters in the feature space, and the center of each cluster is an attractor. The historical optimized control strategy data includes the control parameters of the fan (such as rotation speed, power distribution ratio, response time threshold) and the corresponding system feedback (such as heat dissipation efficiency, energy consumption, temperature stability, etc.) under different dust environments and fan operating conditions. Through cluster analysis, these data are aggregated into K representative control modes, so that each attractor can reflect the optimal control strategy under specific working conditions. In the subsequent control process, when the actual feature vector has a high similarity with a certain attractor, it means that the current working condition highly matches the optimal control mode represented by this attractor, and the system preferentially refers to the control parameters of this mode. Normalize the multi-dimensional dust environment heat dissipation feature vector and the K attractors. Use the standardization method (z-score standardization) to map the feature data to a specific numerical range (such as between 0 and 1), so that the contribution of each dimension of the feature to the similarity calculation will not be biased due to different dimensions. For example, for features such as temperature, fan rotation speed, dust concentration, and power consumption, the problem of different original numerical ranges of these features is eliminated through normalization, so that the feature vector and the attractor can perform accurate distance calculations in the same standardized space. Calculate the Euclidean distance between the standardized feature vector and each standardized attractor to obtain K distance values, and quantitatively evaluate the similarity between the current feature vector and each attractor. The smaller the distance, the higher the similarity. Perform a Gaussian kernel function transformation on the distance values to obtain initial similarity values that are smoother and have a numerical upper bound of 1. The non-linear transformation can effectively avoid the problem that the similarity approaches 0 when the distance value is too large, thus maintaining the system's response ability to medium and long-distance attractors, and making the weight distribution of each attractor in the multi-attractor mechanism more smooth and continuous. Dynamically adjust the initial similarity values based on the dust concentration and load level to obtain the similarity values between the feature vector and each attractor. Dynamically adjust the priorities of different attractors according to the current environmental characteristics. For example, in an environment with a high dust concentration, the system is more inclined to select those attractors that perform well in a similar high-dust environment. By applying a weight adjustment function to the initial similarity values, the dust concentration is associated with the attractor preference degree. For example, re-weight the similarity values through a linear function or an exponential function, so that in a high-dust concentration environment, the similarity values of the high-dust environment attractors are amplified, while the similarity values of the low-dust environment attractors are moderately weakened. Similarly, when the load level is high, through a similar method, the system is more inclined to select those attractors that can maintain the balance of heat dissipation efficiency and energy consumption in a high-load environment, thus ensuring the rationality and safety of the fan control parameters.

[0031] In a multi-fan system, to ensure the coordinated operation of each fan and avoid air flow interference, a phase definition is carried out for each fan in the system to obtain the fan control phase parameters. In a multi-fan system, each fan is assigned a specific phase angle such that the phase difference between adjacent fans remains 2π / N (where N is the total number of fans). Through the setting of a uniformly distributed phase difference, the air flow generated by the fans during operation forms a periodic fluctuation, avoiding problems such as excessive concentration or disorder of the air flow caused by the synchronous operation of multiple fans, and achieving a more stable heat dissipation air flow distribution. Based on the defined fan control phase parameters, the basic rotational speeds of each fan are calculated by combining the rotational speed adjustment curve in the fan coordinated control parameters to obtain the rotational speed reference value. According to the current dust environment characteristics, dust concentration, temperature distribution, and load level, an intelligent control model is used to predict a rotational speed adjustment curve suitable for the current working conditions, and this curve defines the optimal rotational speed range of the fan under different time or temperature conditions. After obtaining the rotational speed reference value, the rotational speeds of each fan are sinusoidally modulated according to the fan control phase parameters, so that the fan rotational speeds can not only be maintained within the optimal adjustment curve, but also achieve an alternating operating state of each fan through the periodic characteristics of the sine function. Through this sinusoidal modulation method, a certain phase difference is always maintained among the fans during operation, thereby achieving an alternating output effect of the air flow, enhancing the uniformity of the heat dissipation air flow, and effectively reducing the mechanical stress and current impact caused by the synchronous start and stop of the fans, and prolonging the service life of the fans. To enable the fan system to dynamically adjust the power distribution ratio according to the actual heat dissipation requirements, the power distribution ratio in the fan coordinated control parameters is dynamically adjusted according to the temperature difference in the areas responsible for each fan to obtain a temperature-adaptive power distribution ratio. The temperature data around each fan is real-time monitored through temperature sensors, and these temperature data are compared with the actual heat dissipation effect of the fan. When the temperature in the area responsible for a certain fan is significantly higher than other areas, the system automatically increases the power distribution ratio of this fan, thereby enhancing the heat dissipation intensity in this area. At the same time, in a dusty environment, since dust accumulation will affect the heat dissipation efficiency and mechanical performance of the fans, based on the response time threshold in the fan coordinated control parameters and the dust accumulation amount of each fan, a dust-adaptive response time is calculated. The dust accumulation situation around each fan is real-time monitored through dust sensors. When the dust accumulation reaches a certain threshold, the response time of the fan is automatically shortened, the fan rotational speed is increased to enhance the self-cleaning ability, or the reverse air blowing mechanism is started to remove the dust attached to the fan blades, thereby delaying the attenuation rate of the fan performance. To cope with sudden changes in the dust concentration, the change rate of the dust concentration in the environment is real-time monitored. When a significant mutation in the dust concentration is detected, an emergency adjustment mechanism is immediately triggered to obtain a dust-proof optimized rotational speed curve.In this case, the system temporarily increases the rotation speeds of all fans to form a stronger air flow resistance, preventing dust from quickly entering the interior of the device. Meanwhile, it adjusts the operation mode of the fans according to the duct conditions, such as switching to the negative pressure mode to enhance the dust removal effect. The combined application of the temperature - adaptive power distribution ratio, the dust - adaptive response time, and the dust - proof - optimized rotation speed curve to the control of each fan results in a complementary fan control strategy. Under this strategy, each fan realizes the alternating output of air flow through dynamic phase regulation, ensures the long - term stable operation of the system in a complex dust - laden environment through the dual mechanisms of temperature adaptation and dust adaptation, and copes with extreme dust events through an emergency adjustment mechanism, thus achieving an intelligent, automated, and efficient fan control effect.

[0032] In the embodiment of the present invention, a comprehensive dust - laden environment sample library is established through precise multi - condition data acquisition and processing. The dust accumulation kinetic characteristic and duct blockage formation mechanism models developed based on this library reveal the internal mechanism of the reduction in heat dissipation efficiency in a dust - laden environment. With the help of innovative features such as the sum of periodic temperature differences and the energy consumption fluctuation array, the system comprehensively characterizes the working state of the heat dissipation system in a dust - laden environment, overcoming the deficiencies in the description of traditional features. The constructed multi - attraction mechanism gradient boosting learning model realizes the precise prediction of the optimal control parameters and achieves a significant improvement in the generation of the fan control trajectory. The control strategy combining complementary fan control and dynamic scaling forms a complementary effect of dust resistance for the multi - fan system by reasonably setting the fan phase difference and dynamically adjusting the power distribution, and at the same time realizes the adaptive control parameter adjustment mechanism based on temperature, dust concentration, and system reliability index. Compared with the prior art, the control efficiency of the present invention in a dust - laden environment is improved by an order of magnitude, while reducing the system energy consumption, extending the service life of the fan, and providing an economical and efficient solution for the heat dissipation of industrial equipment in a dust - laden environment.

[0033] In a specific embodiment, the process of executing step S1 may specifically include the following steps:

[0034] Build a heat dissipation test platform for the heat dissipation fan to obtain a test environment including a heat dissipation fan system, a temperature sensor array, a dust concentration sensor, a fan rotation speed measuring device, a power monitoring module, and a thermal imager;

[0035] Configure the temperature sensor array to be evenly distributed at the target positions in the heat dissipation area and set the sampling frequency of the sensors. At the same time, set the working conditions of the test environment to obtain a multi - dimensional test matrix including M dust concentration levels, N ambient temperature intervals, and T heat load levels;

[0036] Monitor the single - fan mode and the multi - fan mode based on the multi - dimensional test matrix to obtain temperature change data, dust accumulation data, fan rotation speed data, and power consumption data;

[0037] Perform outlier detection and filtering on temperature change data, dust accumulation data, fan speed data, and power consumption data to obtain a denoised effective data set, and classify and label the denoised effective data set according to dust concentration, ambient temperature, and thermal load to obtain a dust environment sample library.

[0038] Specifically, a complete test environment is designed. This test environment includes a cooling fan system and is equipped with a series of professional devices for monitoring environmental parameters and the operating status of the fan, including a temperature sensor array, a dust concentration sensor, a fan speed measurement device, a power monitoring module, and a thermal imager. During the construction of the test platform, a fan system suitable for the test space is selected. Its heat dissipation capacity, wind speed range, and speed adjustment ability should be able to cover the requirements under different working conditions. For example, a variable-speed, high-airflow, PWM (pulse width modulation)-controlled cooling fan is selected to ensure that the fan speed can be dynamically adjusted in a simulated dust environment to achieve the switching of multiple heat dissipation modes. The temperature sensor array is one of the core components in the test platform for monitoring temperature changes. These sensors need to be evenly distributed at the target positions in the heat dissipation area to ensure the comprehensiveness and accuracy of temperature data collection. When arranging the sensors, a grid method is adopted. The entire heat dissipation area is divided into several small areas, and one temperature sensor is arranged in each small area to form a two-dimensional or three-dimensional temperature monitoring grid. At the same time, an appropriate sampling frequency is set for the sensors. During the test, the dust concentration sensor is used to detect the change in dust concentration in the environment, the fan speed measurement device obtains the operating speed of the fan in real time, the power monitoring module is used to accurately calculate the power consumption performance of the fan system, and the thermal imager can provide an intuitive temperature distribution image. To make the test environment closer to the actual working conditions, multi-dimensional working condition settings are carried out, and a multi-dimensional test matrix including M dust concentration levels, N environmental temperature intervals, and T heat load levels is constructed. During the experiment, the system is monitored in both single-fan mode and multi-fan mode to compare the effects of different fan configurations on the heat dissipation performance. For example, in single-fan mode, by adjusting the fan speed and direction, observe the temperature changes and heat dissipation effects under different dust concentrations and heat loads. In multi-fan mode, by adjusting the phase difference and speed synchronization of the fans, analyze the differences in air flow distribution and heat dissipation efficiency when the fans work together. During the test, the temperature sensor array continuously records the temperature change data in the heat dissipation area, the dust concentration sensor monitors the dust accumulation in the environment in real time, the fan speed measurement device obtains the fan operating speed data, the power monitoring module records the power consumption data of the fan system, and the thermal imager provides a visual image of the temperature distribution. These data are stored in real time through the data acquisition system to form a preliminary data set. Outlier detection and filtering are performed on the temperature change data, dust accumulation data, fan speed data, and power consumption data to obtain a denoised effective data set. Outlier detection uses statistical methods, such as methods based on standard deviation or interquartile range, to identify outliers in the data and mark the data points outside the normal range as outliers. For example, for temperature data, if the temperature reading of a certain sensor exceeds three times the standard deviation of the average value, it is regarded as an outlier and removed from the data set.The filtering process adopts the method of Kalman filtering or moving average filtering. By smoothing the data curve, noise interference is eliminated. For example, for the fan speed data, the reading jitter caused by the instantaneous fluctuation of the fan is eliminated through moving average filtering, and a more stable speed data sequence is obtained. The denoised effective data set is classified and labeled according to the dust concentration, ambient temperature, and heat load to construct a dust environment sample library. Each record in the sample library includes original data such as temperature, dust, speed, and power consumption, and is accompanied by a clear description of the working conditions.

[0039] In a specific embodiment, the process of executing step S2 may specifically include the following steps:

[0040] Perform correlation analysis on the dust accumulation data and operating parameters in the dust environment sample library to obtain a dust accumulation kinetic characteristic model;

[0041] Perform grid division processing on the heat dissipation area to obtain a thermal resistance distribution grid, and calculate the thermal resistance of each grid point in the thermal resistance distribution grid to obtain a duct blockage formation principle model;

[0042] Perform comparative analysis on the actual heat dissipation efficiency and theoretical heat dissipation efficiency of the cooling fan under different working conditions to obtain a fan performance degradation model;

[0043] Perform parameter fitting analysis on the dust accumulation kinetic characteristic model, the duct blockage formation principle model, and the fan performance degradation model to obtain the optimal parameter values including the dust adhesion rate coefficient, the dust concentration influence coefficient, the dust direct influence coefficient, and the thermal resistance influence coefficient;

[0044] Substitute the optimal parameter values into the dust accumulation kinetic characteristic model, the duct blockage formation principle model, and the fan performance degradation model respectively for combination to obtain a thermal equivalent model.

[0045] Specifically, extract the dust accumulation data and related operating parameters from the dust environment sample library, including influencing factors such as fan speed, wind speed, dust concentration, temperature, and humidity. Through correlation analysis, reveal the dynamic relationship between these parameters and the dust accumulation characteristics. In the process of modeling the dust accumulation kinetic characteristics, by analyzing the law of dust accumulation changing with time, a dynamic model is constructed. This model not only considers the influence of dust concentration and wind speed on the dust deposition rate, but also introduces ambient temperature and humidity as correction factors. The dust accumulation kinetic model is expressed as:

[0046]

[0047] Among them, represents the dust accumulation at time the initial dust amount is is the dust concentration,​ is the wind speed, is the ambient temperature, is the humidity, and are the dust adhesion rate coefficient, the temperature influence coefficient, and the humidity attenuation coefficient, respectively. In this model, the first term reflects the direct influence of dust concentration and wind speed on the dust adhesion speed, while the second term describes the inhibitory effect of humidity on dust adhesion in the form of exponential decay. For example, in a high-humidity environment, dust is prone to caking and is not easily attached to the fan blades, thus reducing the accumulation rate. The heat dissipation area is divided into grids to construct a thermal resistance distribution grid, and by calculating the thermal resistance of each grid point, a model of the formation principle of air duct blockage is obtained. The entire heat dissipation air duct area is divided into small grids, and the thermal resistance value at each grid point is jointly determined by the dust accumulation amount and the air flow velocity. The thermal resistance calculation model is expressed as:

[0048]

[0049] where is the thermal resistance value of the th grid point, is the initial thermal resistance, is the dust accumulation amount at this grid point, is the air flow velocity, is the thermal resistance influence coefficient, is a small positive number to avoid a zero denominator. In this model, the increase in the dust accumulation amount will cause the thermal resistance to increase linearly, while the increase in the air flow velocity can effectively reduce the local thermal resistance. This model can reflect the dynamic process of dust accumulation on the blockage of the heat dissipation air duct and can also reveal the effect of wind speed optimization in improving the air duct resistance. To evaluate the heat dissipation performance of the fan under different working conditions, a comparative analysis of the actual heat dissipation efficiency and the theoretical heat dissipation efficiency is carried out to obtain a fan performance decay model. The actual heat dissipation efficiency is obtained through the temperature sensor and power monitoring module of the test platform, while the theoretical heat dissipation efficiency is calculated based on the ideal operating model of the fan. For example, under ideal conditions without dust blockage and without air duct interference, the heat dissipation power of the fan is expressed as:

[0050]

[0051] where is the specific heat capacity of air, is the air volume, is the temperature difference between the inlet and outlet. And the actual heat dissipation efficiency Due to the influence of dust accumulation and duct blockage, it will be lower than the theoretical value. Therefore, the fan performance degradation model is expressed as:

[0052]

[0053] Where, is the decay coefficient of heat dissipation efficiency, and are the direct dust influence coefficient and the thermal resistance influence coefficient respectively, and represent the overall dust accumulation amount and the average thermal resistance of the system respectively. In this model, by introducing the dual influence factors of dust accumulation and thermal resistance change, the decay of fan performance over time is more accurately evaluated. Parameter fitting analysis is carried out on the dust accumulation kinetic characteristic model, the duct blockage formation principle model and the fan performance degradation model. The optimal parameter values of the dust adhesion rate coefficient, the dust concentration influence coefficient, the direct dust influence coefficient and the thermal resistance influence coefficient are obtained through the least squares fitting of the experimental data. This process is achieved by minimizing the error between the model prediction value and the actual measured value. The specific objective function is expressed as:

[0054]

[0055] Where, is the experimentally measured decay value of heat dissipation efficiency, is the heat dissipation efficiency predicted by the model. By optimizing the model parameters (i = 1, 2, …, 6), the prediction result is made as close as possible to the experimental data, so as to ensure the accuracy and reliability of the model in practical applications. Substitute the optimal parameter values into the dust accumulation kinetic characteristic model, the duct blockage formation principle model and the fan performance degradation model respectively for combination to obtain the thermal equivalent model. This model comprehensively predicts the heat dissipation efficiency and operating state of the cooling fan in different dust environments. For example, when specific dust concentration, wind speed, temperature and humidity parameters are input, the thermal equivalent model can output the expected heat dissipation power, power consumption and the change trend of heat dissipation efficiency of the fan.

[0056] In a specific embodiment, the process of executing step S3 may specifically include the following steps:

[0057] Screen the instantaneous temperature value, temperature change rate, dust concentration, fan speed and power consumption data output by the thermal equivalent model to obtain the original feature set;

[0058] Perform segmented processing on the temperature data in the original feature set, calculate the cumulative sum of the difference between the maximum and minimum temperature values in each time window, and obtain the periodic temperature difference sum feature;

[0059] Continuously record the power data in the original feature set, calculate the sequence composed of the standard deviation of power in each time period, and obtain the energy consumption fluctuation array feature;

[0060] Perform Fourier transform analysis on the fan speed data in the original feature set, calculate the ratio of the rotational speed spectrum energy to the energy of the original rotational speed signal, and obtain the rotational speed regularity feature;

[0061] Perform difference and sign change detection on the heat dissipation efficiency data in the original feature set, and count the number of times the direction of change in heat dissipation efficiency reverses to obtain the heat dissipation efficiency change reversal number feature;

[0062] Combine and perform dimensionality reduction on the original feature set, the sum of periodic temperature differences feature, the energy consumption fluctuation array feature, the rotational speed regularity feature, and the heat dissipation efficiency change reversal number feature to obtain a multi-dimensional dust environment heat dissipation feature vector.

[0063] Specifically, among the various data output by the thermal equivalent model, use a preprocessing algorithm to screen the instantaneous temperature value, temperature change rate, dust concentration, fan speed, and power consumption data to obtain an original feature set. In this process, eliminate some noise data and outliers. For example, smooth the temperature and speed data by methods such as moving average filtering or Kalman filtering, and at the same time use the three-standard-deviation method (3σ criterion) to detect and eliminate outliers to ensure the data quality in the original feature set. When constructing the original feature set, all data points are timestamped to accurately locate the change trend of the data in the time dimension during the subsequent feature extraction process. After obtaining the original feature set, extract the sum of periodic temperature differences feature for the temperature data through a segmentation method. Segment the temperature data according to a fixed time window, and calculate the maximum value of the temperature in each time window and the minimum value , and then calculate the cumulative sum of these temperature differences:

[0064]

[0065] where, represents the sum of periodic temperature differences feature, is the number of time windows, and are respectively the The maximum and minimum temperatures within a time window. This feature can reflect the temperature fluctuations of the cooling system under different loads and environmental conditions. Based on this feature value, it is determined whether the current fan's cooling capacity matches the actual thermal load, so as to adjust the fan speed or power distribution when necessary. At the same time, for the power data in the original feature set, by calculating the standard deviation sequence of the power within each time period, the energy consumption fluctuation array feature is obtained. The power data is segmented according to the same time window, and the standard deviation of the power data is calculated within each time window , and then these standard deviation values are formed into a sequence: . Among them, is the energy consumption fluctuation array feature, represents the standard deviation of the power data within the th time window. This feature can quantify the fluctuation degree of the power consumption of the cooling fan under different working conditions. When analyzing the fan speed data, through Fourier transform, the frequency domain analysis of the speed signal is carried out to extract the speed regularity feature. The speed signal is Fourier-transformed to obtain the frequency spectrum , and then the ratio of the frequency spectrum energy to the original signal energy is calculated:

[0066]

[0067] Among them, represents the speed regularity feature, and are the system-set feature frequency ranges. The frequency spectrum energy within this range represents the regular changes of the fan at specific frequencies. For example, in the alternating speed regulation or periodic dust cleaning mode, there will be strong harmonic components in the speed signal at specific frequencies. By calculating this ratio, the periodicity and stability during the fan operation are quantified, so as to monitor in real time whether the fan is in the preset operation mode in the system. For the heat dissipation efficiency data, through the difference and sign change detection method, the number of times the direction of the heat dissipation efficiency change is reversed is counted to obtain the heat dissipation efficiency change reversal number feature. Calculate the difference sequence of the heat dissipation efficiency data :

[0068]

[0069] Then count the number of sign changes in the difference sequence, that is, the total number of times from positive to negative or from negative to positive, denoted as This feature reflects the stability of the heat dissipation efficiency. When the system is in a stable state, the change in the heat dissipation efficiency should be gentle and in the same direction. However, when the load changes frequently or the air duct is blocked, the heat dissipation efficiency will fluctuate violently, resulting in a significant increase in the number of sign changes. Combine the original feature set, the sum of periodic temperature differences feature, the energy consumption fluctuation array feature, the rotational speed regularity feature, and the number of reversals of the heat dissipation efficiency change feature to obtain an initial high-dimensional feature vector. Through a dimensionality reduction method, such as principal component analysis, reduce the high-dimensional feature vector to a more compact form, and finally obtain a multi-dimensional dust environment heat dissipation feature vector . Among them, is the feature dimension after dimensionality reduction, indicating each important feature component

[0070] In a specific embodiment, the process of executing step S4 may specifically include the following steps:

[0071] Input the multi-dimensional dust environment heat dissipation feature vector into a deep neural network for feature mapping to obtain mapped feature space data;

[0072] Input the mapped feature space data into a gradient boosting learning model with a multi-attraction mechanism for control parameter prediction to obtain a preliminary predicted value of the control parameter. The gradient boosting learning model with a multi-attraction mechanism includes a gradient boosting decision module constructed by the XGBoost algorithm;

[0073] Calculate the similarity between the multi-dimensional dust environment heat dissipation feature vector and K predefined attractors to obtain the similarity values between the feature vector and each attractor;

[0074] Perform normalization processing based on the similarity values between the feature vector and each attractor to obtain weight coefficients;

[0075] Perform weighted fusion calculation on the preliminary predicted values of the control parameters corresponding to each attractor according to the weight coefficients to obtain the fan collaborative control parameters. The collaborative control parameters include a rotational speed adjustment curve, a power distribution ratio, and a response time threshold.

[0076] Specifically, input the multi-dimensional dust environment heat dissipation feature vector into a trained deep neural network. Through multi-layer non-linear transformation, map the input feature vector to a high-dimensional feature space to obtain mapped feature space data During the feature mapping process, each layer of the deep neural network introduces non-linear characteristics through an activation function, enabling the model to capture the complex relationships in the feature vector. For example, calculate the mapped feature through the fully connected layer in the neural network:

[0077]

[0078] Among them, is the th mapping feature, is the weight coefficient, is the bias, is the activation function (such as ReLU or Sigmoid). Through the calculation of multiple layers of networks, the feature data after high-dimensional and non-linear transformation is obtained . The mapping feature space data is input into the gradient boosting learning model with a multi-attraction mechanism. The core of the model is the gradient boosting decision module constructed based on the XGBoost algorithm. XGBoost builds multiple decision tree models and uses the prediction error of the previous round for learning in each round of iteration, thereby gradually improving the prediction accuracy of the model. In this process, the output of each tree is the fitting of the prediction residual of the previous round, that is, the model parameters are optimized by minimizing the objective function:

[0079]

[0080] Among them, is the objective function, is the number of samples, is the loss function, representing the error between the actual value and the predicted value , is the number of decision trees, is the model complexity penalty term, is the th tree output. In practical applications, the XGBoost model generates a new decision tree in each round of iteration, and gradually corrects the prediction result through the additive model to obtain the preliminary predicted value of the control parameters. These predicted values include the preliminary estimates of the rotational speed adjustment curve, power distribution ratio, and response time threshold. After obtaining the preliminary predicted value of the control parameters, in order to introduce the multi-attraction mechanism, the multi-dimensional dust environment heat dissipation feature vector is calculated for similarity with the predefined attractors to obtain the similarity values of the feature vector and each attractor. The attractor represents the typical control mode under different dust environments and working conditions, and is predefined through clustering analysis or expert experience. For example, each attractor represents an optimal fan control strategy. In the similarity calculation, a similarity measurement method based on the Gaussian kernel function is adopted. For example, the Euclidean distance between the feature vector and each attractor is calculated, and the distance value is converted into a similarity value:

[0081]

[0082] Among them, is the similarity value between the feature vector and the th attractor, is the bandwidth parameter of the Gaussian kernel function, is the attractor in the -dimensional feature value. By this method, the distance between the feature vector and the attractor is mapped to a similarity value. The smaller the distance, the higher the similarity value. Normalize the similarity value to obtain the weight coefficient . The weight coefficient represents the contribution degree of each attractor in the final control parameter. The normalization process is achieved through the Softmax function:

[0083]

[0084] Among them, is the weight coefficient of the th attractor. The Softmax function can convert all similarity values into a probability distribution between 0 and 1, making the sum of all weight coefficients equal to 1, thus ensuring the numerical stability and interpretability of the weighted fusion calculation. According to these weight coefficients, the preliminary predicted values of the control parameters corresponding to each attractor are weighted and fused to obtain the fan collaborative control parameter. This process is achieved by calculating the weighted sum:

[0085]

[0086] Among them, represents the final fan collaborative control parameter, including the rotation speed adjustment curve, power distribution ratio, and response time threshold, is the preliminary predicted value of the control parameter corresponding to the th attractor. Through weighted fusion calculation, the predicted values of each attractor are integrated according to the similarity level. The final control parameter can reflect the actual situation of the current dust environment and inherit the optimal control experience in the historical working conditions, realizing dynamic and intelligent fan control.

[0087] In a specific embodiment, the process of performing the step of calculating the similarity between the multi-dimensional dust environment heat dissipation feature vector and the predefined K attractors to obtain the similarity values between the feature vector and each attractor may specifically include the following steps:

[0088] Perform cluster analysis on the historical optimized control strategy data to obtain K typical control strategy center points. The K typical control strategy center points are used as K attractors, and each attractor represents an optimal control mode in the feature space;

[0089] Normalize the multi-dimensional dust environment heat dissipation feature vector and K attractors to obtain the standardized feature vector and standardized attractors;

[0090] Calculate the Euclidean distance between the standardized feature vector and each standardized attractor to obtain K distance values, and perform Gaussian kernel function transformation on each distance value respectively to obtain the initial similarity values;

[0091] Dynamically adjust the initial similarity values based on the dust concentration and load level to obtain the similarity values between the feature vector and each attractor.

[0092] Specifically, extract the control parameters under all historical working conditions from the historical optimization control strategy data, including fan speed, power distribution ratio, response time threshold, and environment-related features (such as dust concentration, temperature, humidity, and load level, etc.). These data points are represented as a multi-dimensional vector set in the feature space , where is the number of samples of historical data, and each sample is a -dimensional feature vector. To identify representative control strategy patterns in these data, a clustering algorithm is used to divide the data into categories. The K-means clustering algorithm realizes the aggregation of data points by minimizing the squared distance from the samples to the cluster centers. The objective function of the K-means algorithm is:

[0093]

[0094] where, is the clustering objective function, is the center point (attractor) of the -th cluster, represents the Euclidean distance between the data point and the cluster center . Through iterative calculation, the K-means algorithm finally converges to the state where the distance from all data points to their respective cluster centers is minimized, and typical control strategy center points are obtained. These center points represent the typical control patterns in the historical data and serve as the attractors in the multi-attractor mechanism, providing a reference template for predicting the control parameters of the current system. Normalize the multi-dimensional dust environment heat dissipation feature vector and these attractors to ensure that the feature data and attractors are calculated for similarity within the same numerical scale, and eliminate the dimensional differences between each feature dimension. After completing the normalization process, calculate the Euclidean distance between the standardized feature vector and each standardized attractor to obtain distance values. The Euclidean distance calculation formula is:

[0095]

[0096] Among them, represents the distance between the normalized eigenvector and the th attractor, and are the normalized eigenvalues of the eigenvector and the attractor in the th dimension respectively, is the dimension of the eigenvector. The Euclidean distance can quantify the similarity between the current operating condition characteristics and the historical optimal control mode. The smaller the distance, the higher the matching degree between the current characteristics and the attractor. Perform a Gaussian kernel function transformation on the distance value to obtain the initial similarity value:

[0097]

[0098] Among them, is the initial similarity value of the th attractor, is the bandwidth parameter of the kernel function, which controls the smoothness of the Gaussian function. The Gaussian kernel function can map the distance value to a similarity value between 0 and 1. When the distance is small, the similarity value is close to 1. When the distance is large, the similarity value rapidly decays to close to 0. This non-linear mapping helps to highlight the attractor closest to the current characteristics, thereby improving the system's response ability to the optimal control mode.

[0099] In a specific embodiment, the intelligent adjustment method of the cooling fan intelligent control system for resisting the dust environment further includes the following steps:

[0100] Define the phases of the fans in the multi-fan system to obtain the fan control phase parameters, and the fan control phase parameters satisfy that the phase difference between adjacent fans is 2π divided by the total number of fans;

[0101] Based on the speed adjustment curve in the fan collaborative control parameters, calculate the basic speeds of the fans to obtain the speed reference values, and perform sinusoidal modulation on the speeds of the fans according to the fan control phase parameters, so that the fans form an alternating working state;

[0102] Dynamically adjust the power distribution ratio in the fan collaborative control parameters according to the temperature differences in the areas responsible for each fan to obtain the temperature-adaptive power distribution ratio;

[0103] Based on the response time threshold in the fan collaborative control parameters and the dust accumulation amounts of the fans, calculate to obtain the dust-adaptive response time;

[0104] Real-time monitor the change rate of the dust concentration in the environment, and trigger an emergency adjustment mechanism when a sudden change in the dust concentration is detected to obtain a dust-proof optimized speed curve;

[0105] The temperature-adaptive power allocation ratio, dust-adaptive response time and dust-optimized speed curve are combined and applied to the control of each fan to obtain a complementary fan control strategy.

[0106] Specifically, the phase of each fan in the multi-fan system is defined to obtain the fan control phase parameters, so that the phase difference between adjacent fans is ,in is the total number of fans, and the formula is as follows:

[0107]

[0108] Ensure that the phase difference between each fan is uniform, so that the working status of the fans changes alternately to maximize the heat dissipation efficiency. Based on the speed adjustment curve in the fan collaborative control parameters, calculate the basic speed of each fan Assume that the base speed of the fan is determined by the fan load , ambient temperature and fan performance parameters The basic speed is calculated as follows:

[0109]

[0110] in, For the The load of the fan, is the ambient temperature, is the fan performance parameter. Perform sinusoidal modulation on the fan speed to ensure that each fan works alternately. Set the actual fan speed to , then the modulation formula is:

[0111]

[0112] in, is the operating frequency of the system, is the time variable, For the Through this sinusoidal modulation, each fan will start and stop alternately to optimize the cooling effect and avoid interference between fans. , dynamically adjust the power distribution ratio to obtain the temperature-adaptive power distribution ratio . The formula is expressed as:

[0113]

[0114] in, For the The temperature difference of the area covered by each fan is is a proportional constant. Through this dynamic adjustment, the fan can be adaptively adjusted in different temperature zones to ensure that hotter areas receive more heat dissipation support. Considering the impact of dust accumulation on the fan, based on the amount of dust accumulation , calculate the response time adjustment. Assume the base response time is , the relationship between dust accumulation and response time is expressed as:

[0115]

[0116] in, As the basic response time, is the dust impact coefficient, For the The dust accumulation of each fan. As the dust accumulates, the response time will gradually increase to ensure that the fan can adjust in a longer time to avoid performance degradation. Exceeding the preset threshold When the system triggers the emergency adjustment mechanism, the fan speed curve will be adjusted. The speed curve after dust prevention optimization is:

[0117]

[0118] in, is the adjustment coefficient, The current dust concentration. When the dust concentration exceeds the threshold, the fan will be quickly adjusted through this mechanism to avoid performance degradation caused by dust. All control parameters, including the temperature-adaptive power allocation ratio , Dust adaptive response time And the speed curve after dust protection optimization , combined with the control applied to each fan, a complementary fan control strategy is obtained.

[0119] The above describes the intelligent adjustment method of the intelligent control system of the cooling fan in the dusty environment according to the embodiment of the present invention. The following describes the intelligent adjustment device of the intelligent control system of the cooling fan in the dusty environment according to the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an intelligent control system intelligent adjustment device for a heat dissipation fan in an anti-sand and dust environment includes:

[0120] The acquisition module is used to collect data from multiple working conditions on the heat dissipation test platform of the cooling fan to obtain a dust environment sample library;

[0121] A modeling module is used to quantitatively model and analyze the dust accumulation dynamics and air duct blockage formation mechanism based on a dust environment sample library to obtain a thermal equivalent model;

[0122] A feature extraction module, configured to perform feature extraction and integration based on a thermal equivalent model to obtain a multi-dimensional dust environment heat dissipation feature vector;

[0123] A processing module, configured to input the multi-dimensional dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan collaborative control parameters adapted to the dust environment.

[0124] Through the collaborative cooperation of the above-mentioned various components, a comprehensive dust environment sample library is established by accurately collecting and processing multi-condition data. The dust accumulation kinetic characteristics and duct blockage formation mechanism model developed based on this library reveals the internal mechanism of the reduction in heat dissipation efficiency in the dust environment. With the help of innovative features such as the sum of periodic temperature differences and the energy consumption fluctuation array, the working state of the heat dissipation system in the dust environment is comprehensively characterized, overcoming the deficiencies in the description of traditional features. The constructed gradient boosting learning model with a multi-attraction mechanism realizes the accurate prediction of the optimal control parameters, and has achieved significant improvement in the generation of the fan control trajectory. The control strategy combining complementary fan control and dynamic scaling enables the multi-fan system to form a complementary effect against dust by reasonably setting the fan phase difference and dynamically adjusting the power distribution, and at the same time realizes an adaptive control parameter adjustment mechanism based on temperature, dust concentration, and system reliability index. Compared with the prior art, the control efficiency of the present invention is improved by an order of magnitude in the dust environment, while reducing the system energy consumption and extending the service life of the fan, providing an economical and efficient solution for the heat dissipation of industrial equipment in the dust environment.

[0125] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0126] 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0127] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent adjustment method for the intelligent control system of a cooling fan resistant to a sand and dust environment, characterized in that, The method includes: Collecting multi-condition data of the heat dissipation test platform of the cooling fan to obtain a dust environment sample library; Based on the dust environment sample library, quantitatively modeling and analyzing the dust accumulation kinetic characteristics and the formation mechanism of duct blockage to obtain a thermal equivalent model; specifically including: performing correlation analysis on the dust accumulation data and operating parameters in the dust environment sample library to obtain a dust accumulation kinetic characteristic model; dividing the heat dissipation area into grids to obtain a thermal resistance distribution grid, and calculating the thermal resistance of each grid point of the thermal resistance distribution grid to obtain a duct blockage formation principle model; comparing and analyzing the actual heat dissipation efficiency and the theoretical heat dissipation efficiency of the cooling fan under different conditions to obtain a fan performance degradation model; performing parameter fitting analysis on the dust accumulation kinetic characteristic model, the duct blockage formation principle model, and the fan performance degradation model to obtain optimal parameter values including a dust adhesion rate coefficient, a dust concentration influence coefficient, a dust direct influence coefficient, and a thermal resistance influence coefficient; substituting the optimal parameter values into the dust accumulation kinetic characteristic model, the duct blockage formation principle model, and the fan performance degradation model respectively for combination to obtain a thermal equivalent model; Based on the thermal equivalent model, performing feature extraction and integration to obtain a multi-dimensional dust environment heat dissipation feature vector; Inputting the multi-dimensional dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan collaborative control parameters adapted to the dust environment.

2. The intelligent adjustment method of the heat dissipation fan intelligent control system for resisting sand and dust environment according to claim 1, wherein, The collecting multi-condition data of the heat dissipation test platform of the cooling fan to obtain a dust environment sample library includes: Building a heat dissipation test platform for the cooling fan to obtain a test environment including a cooling fan system, a temperature sensor array, a dust concentration sensor, a fan speed measurement device, a power monitoring module, and a thermal imager; Configuring the temperature sensor array to be evenly distributed at target positions in the heat dissipation area and setting the sampling frequency of the sensors. At the same time, setting the conditions of the test environment to obtain a multi-dimensional test matrix including M dust concentration levels, N environmental temperature intervals, and T heat load levels; Monitoring the single-fan mode and the multi-fan mode based on the multi-dimensional test matrix to obtain temperature change data, dust accumulation data, fan speed data, and power consumption data; Performing outlier detection and filtering on the temperature change data, the dust accumulation data, the fan speed data, and the power consumption data to obtain a denoised effective data set, and classifying and labeling the denoised effective data set according to dust concentration, environmental temperature, and heat load to obtain a dust environment sample library.

3. The intelligent adjustment method of the heat dissipation fan intelligent control system resistant to sand and dust environment according to claim 1, characterized in that, The inputting the multi-dimensional dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan collaborative control parameters adapted to the dust environment includes: Inputting the multi-dimensional dust environment heat dissipation feature vector into a deep neural network for feature mapping to obtain mapped feature space data; Input the mapped feature space data into a gradient boosting learning model with a multi-attraction mechanism for predicting control parameters, and obtain a preliminary predicted value of the control parameters. The gradient boosting learning model with a multi-attraction mechanism includes a gradient boosting decision module constructed by the XGBoost algorithm; Calculate the similarity between the multi-dimensional dust environment heat dissipation feature vector and the predefined K attractors to obtain the similarity values between the feature vector and each attractor; Perform normalization processing based on the similarity values between the feature vector and each attractor to obtain weight coefficients; Perform weighted fusion calculation on the preliminary predicted values of the control parameters corresponding to each attractor according to the weight coefficients to obtain the fan collaborative control parameters, where the fan collaborative control parameters include a speed adjustment curve, a power distribution ratio, and a response time threshold.

4. The intelligent adjustment method of the heat dissipation fan intelligent control system for anti-dust and sand environment according to claim 3, characterized in that, The step of calculating the similarity between the multi-dimensional dust environment heat dissipation feature vector and the predefined K attractors to obtain the similarity values between the feature vector and each attractor includes: Perform clustering analysis on the historical optimized control strategy data to obtain K typical control strategy center points, and use the K typical control strategy center points as K attractors, where each attractor represents an optimal control mode in the feature space; Perform normalization processing on the multi-dimensional dust environment heat dissipation feature vector and the K attractors to obtain a normalized feature vector and normalized attractors; Calculate the Euclidean distance between the normalized feature vector and each normalized attractor to obtain K distance values, and perform Gaussian kernel function transformation on each distance value respectively to obtain initial similarity values; Dynamically adjust the initial similarity values based on the dust concentration and load level to obtain the similarity values between the feature vector and each attractor.

5. The intelligent adjustment method of the heat dissipation fan intelligent control system for anti-dust storm environment according to claim 1, characterized in that, The intelligent adjustment method of the heat dissipation fan intelligent control system resistant to the dust environment further includes: Define the phases of the fans in the multi-fan system to obtain fan control phase parameters, where the fan control phase parameters satisfy that the phase difference between adjacent fans is 2π divided by the total number of fans; Calculate the basic speeds of the fans based on the speed adjustment curve in the fan collaborative control parameters to obtain speed reference values, and perform sinusoidal modulation on the speeds of the fans according to the fan control phase parameters so that the fans form an alternating working state; Dynamically adjust the power distribution ratio in the fan collaborative control parameters according to the temperature difference in the areas responsible for each fan to obtain a temperature-adaptive power distribution ratio; Calculate the dust-adaptive response time based on the response time threshold in the fan collaborative control parameters combined with the dust accumulation amount of each fan; Monitor the change rate of the dust concentration in the environment in real time, and trigger an emergency adjustment mechanism when a sudden change in the dust concentration is detected to obtain a dust-proof optimized speed curve; Apply the temperature-adaptive power distribution ratio, the dust-adaptive response time, and the dust-proof optimized speed curve in combination to the control of each fan to obtain a complementary fan control strategy.

6. An intelligent adjustment device for an intelligent control system of a cooling fan resistant to a dust and sand environment, characterized in that, An intelligent adjustment device for the heat dissipation fan intelligent control system resistant to the dust environment, which is used to execute the intelligent adjustment method of the heat dissipation fan intelligent control system resistant to the dust environment according to any one of claims 1-5, includes: The acquisition module is used to collect multi-condition data of the heat dissipation test platform of the cooling fan to obtain a dust environment sample library; The modeling module is used to quantitatively model and analyze the dust accumulation kinetic characteristics and the formation mechanism of duct blockage based on the dust environment sample library to obtain a thermal equivalent model; The feature extraction module is used to extract and integrate features based on the thermal equivalent model to obtain a multi-dimensional dust environment heat dissipation feature vector; The processing module is used to input the multi-dimensional dust environment heat dissipation feature vector into a gradient boosting learning model with a multi-attraction mechanism for processing to obtain fan cooperative control parameters adapted to the dust environment.

Images