Intelligent heat dissipation control method based on motor operation monitoring

Abstract

The invention provides an intelligent heat dissipation control method based on motor operation monitoring, and relates to the technical field of motor control, and the method comprises the steps: reading motor monitoring data, obtaining heat dissipation source feature data, carrying out motor temperature risk prediction, activating a motor heat dissipation decision model, generating a motor heat dissipation decision, carrying out heat dissipation verification, and generating a heat dissipation tuning instruction. And activating a heat dissipation optimization algorithm to carry out optimization adjustment, generating a heat dissipation optimization scheme, and finally carrying out heat dissipation control. According to the invention, the technical problem that the operation efficiency of the motor is further affected due to the poor heat dissipation effect caused by the fact that the heat dissipation control strategy cannot be dynamically adjusted according to reality in the prior art can be solved. By implementing the more accurate heat dissipation control method, the stability and the performance of the motor can be improved, and the service life of the motor is prolonged at the same time.

Description

Technical Field

[0001] This application relates to the field of motor control technology, and in particular to an intelligent heat dissipation control method based on motor operation monitoring. Background Technology

[0002] As motor structures become more complex and functions more powerful, the potential losses and impacts of motor failures are also increasing. Real-time measurement of motor operating parameters using signal processing technology can promptly detect early signs and trends reflecting fault characteristics, providing a basis for predictive maintenance and thus preventing failures and ensuring continuous and safe motor operation. Traditional cooling systems, such as fans and heat sinks, are often unable to meet the cooling requirements of different physical environments.

[0003] Currently, existing motor cooling control systems often employ fixed cooling strategies, which cannot be flexibly adjusted according to actual conditions. They typically rely on preset cooling modes, such as timed on / off switching of cooling fans, or control of the cooling equipment's operation based on simple temperature thresholds.

[0004] In summary, the existing technology suffers from poor heat dissipation due to its inability to dynamically adjust the heat dissipation control strategy according to actual conditions, which further affects the operating efficiency of the motor. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent heat dissipation control method based on motor operation monitoring, in order to solve the technical problem that the existing technology cannot dynamically adjust the heat dissipation control strategy according to the actual situation, resulting in poor heat dissipation effect and further affecting the operating efficiency of the motor.

[0006] In view of the above problems, this application provides an intelligent heat dissipation control method based on motor operation monitoring.

[0007] This application provides an intelligent heat dissipation control method based on motor operation monitoring. The method includes: reading motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data from a motor monitoring unit; extracting structural features and identifying material features of the motor's air-cooled heat dissipation unit to obtain heat source feature data; predicting motor temperature risk based on the motor temperature monitoring data to obtain a motor heat dissipation signal; activating a motor heat dissipation decision model based on the heat dissipation signal, and generating a motor heat dissipation decision by combining the motor temperature monitoring data and the heat source feature data; verifying the motor heat dissipation decision based on a heat dissipation prediction and evaluation unit and motor heat dissipation constraint rules to generate a heat dissipation optimization instruction; activating a heat dissipation optimization algorithm based on the heat dissipation optimization instruction, and optimizing and adjusting the motor heat dissipation decision by combining the motor temperature monitoring data, the motor operating condition monitoring data, the motor environmental monitoring data, and the motor heat dissipation constraint rules to generate a heat dissipation optimization scheme; and controlling the motor's heat dissipation based on the air-cooled heat dissipation unit and the heat dissipation optimization scheme.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By reading motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data from the motor monitoring unit, structural features are extracted and material features are identified in the motor's air-cooled heat dissipation unit to obtain heat dissipation source feature data. Motor temperature risk prediction is performed based on the motor temperature monitoring data to obtain motor heat dissipation signals. Based on these signals, a motor heat dissipation decision model is activated, and a motor heat dissipation decision is generated by combining the motor temperature monitoring data and the heat dissipation source feature data. The heat dissipation decision is then verified using a heat dissipation prediction and evaluation unit and motor heat dissipation constraint rules to generate heat dissipation optimization instructions. Based on these instructions, a heat dissipation optimization algorithm is activated, and the motor heat dissipation decision is optimized and adjusted using the motor temperature monitoring data, motor operating condition monitoring data, motor environmental monitoring data, and the heat dissipation constraint rules to generate a heat dissipation optimization scheme. Based on the air-cooled heat dissipation unit and the optimization scheme, the motor's heat dissipation is controlled. This effectively solves the technical problem in existing technologies where the inability to dynamically adjust heat dissipation control strategies according to actual conditions leads to poor heat dissipation and further affects motor operating efficiency. By implementing a more precise heat dissipation control method, the stability and performance of the motor can be improved, while extending its service life.

[0009] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating the intelligent heat dissipation control method based on motor operation monitoring according to this application; Figure 2 This is a schematic diagram of the process for generating motor heat dissipation signals in the intelligent heat dissipation control method based on motor operation monitoring in this application. Detailed Implementation

[0012] This application provides an intelligent heat dissipation control method based on motor operation monitoring, solving the technical problem in existing technologies where the inability to dynamically adjust heat dissipation control strategies according to actual conditions leads to poor heat dissipation and further affects motor operating efficiency. By implementing a more precise heat dissipation control method, the stability and performance of the motor can be improved, while extending its service life.

[0013] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0014] Example 1 Please see the appendix Figure 1 This application provides an intelligent heat dissipation control method based on motor operation monitoring, wherein the method specifically includes the following steps: S1: Based on the motor monitoring unit, read the motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data.

[0015] Specifically, suitable temperature sensors, such as thermocouples or thermistors, are installed on the motor. These sensors are connected to the motor monitoring unit's input interface, and a suitable sampling frequency is set to collect the motor's temperature data in real time. The collected temperature data is then processed, such as through filtering and noise reduction. Motor operating condition monitoring data includes parameters such as the motor's input voltage, current, and power. These parameters reflect the motor's operating status and performance. Measuring devices such as voltmeters and ammeters are used to monitor the motor's input voltage and current parameters in real time. Measuring devices are connected to the motor monitoring unit's input interface, and a suitable sampling frequency is set to collect the motor's operating condition data in real time. Stable data transmission and storage are also ensured. Motor environmental monitoring data includes parameters such as ambient temperature and humidity. Temperature and humidity sensors are placed in the motor's operating environment to monitor environmental parameters in real time. Environmental sensors are connected to the motor monitoring unit's input interface, and a suitable sampling frequency is set to collect environmental data in real time.

[0016] S2: Extract structural features and identify material features of the air-cooled heat dissipation unit of the motor to obtain heat dissipation source feature data.

[0017] Specifically, the air-cooled heat dissipation unit is scanned or measured using 3D scanning equipment or precise measuring tools to obtain its accurate 3D dimensions and shape data. A 3D model of the heat dissipation unit is then created in CAD software. By analyzing the 3D model, key structural parameters of the heat dissipation unit are identified, including the number, spacing, height, and thickness of the heat dissipation fins, the size of the fan, and the air inlet and outlet. Computational Fluid Dynamics (CFD) software is used to simulate and analyze the heat dissipation unit, identifying potential flow resistance and heat exchange bottlenecks through flow channel analysis. Material characteristic identification determines the materials used in the heat dissipation unit and their thermal properties. Material testing equipment, such as a spectrometer and thermal conductivity meter, is used to detect and analyze the materials of the heat dissipation unit. The composition, thermal conductivity, specific heat capacity, and other thermal properties of the materials are determined. Based on the detected material parameters, the heat dissipation performance of the materials is evaluated, including thermal conductivity and thermal stability. The heat dissipation performance of different materials is compared. These two sets of data are integrated to form heat dissipation source characteristic data. This data includes the structural parameters and material parameters of the heat dissipation unit, as well as the flow and heat exchange performance parameters obtained through simulation analysis.

[0018] S3: Based on the motor temperature monitoring data, predict the motor temperature risk and obtain the motor heat dissipation signal.

[0019] Specifically, the motor temperature is monitored in real time using temperature sensors. The collected temperature data is preprocessed to remove outliers, fill in missing values, and smooth the data. Based on historical data and machine learning algorithms such as support vector machines, random forests, or neural networks, a model capable of predicting motor temperature risk is built. Historical temperature monitoring data is used as a training set to train the model, and a validation set is used to validate the trained model. The preprocessed real-time temperature monitoring data is then input into the trained temperature risk prediction model. The model predicts the motor temperature over a future period based on current and past temperature data. When the predicted temperature exceeds a set risk threshold (which can be set by someone skilled in the art), a risk of motor overheating is determined. If an overheating risk is determined, a motor cooling signal is generated.

[0020] S4: Based on the motor heat dissipation signal, activate the motor heat dissipation decision model, and generate a motor heat dissipation decision by combining the motor temperature monitoring data and the heat dissipation source characteristic data.

[0021] Specifically, when a motor cooling signal is triggered, the motor cooling decision model immediately receives the signal and selects an appropriate cooling decision model based on the urgency of the signal. This can be a machine learning model. The model is initialized using current motor temperature monitoring data and heat source characteristic data. The motor temperature monitoring data and heat source characteristic data are then integrated to form a comprehensive dataset. Features relevant to cooling decisions, such as current temperature, temperature change trends, structural features of the heat dissipation unit, and material properties, are extracted from the integrated dataset. Using the activated cooling decision model and the extracted features, multiple cooling decision schemes are formulated. These schemes include increasing fan speed, turning on or off specific heat dissipation equipment, etc. Each cooling decision scheme is evaluated, and the optimal cooling decision scheme is selected based on the evaluation results.

[0022] S5: Perform heat dissipation verification on the motor heat dissipation decision based on the heat dissipation prediction and evaluation unit and the motor heat dissipation constraint rules, and generate heat dissipation optimization instructions.

[0023] Specifically, the heat dissipation prediction and evaluation unit is activated, and a pre-trained heat dissipation prediction model is loaded. This model can predict the motor's heat dissipation effect based on the current heat dissipation decision and determine the evaluation criteria for the heat dissipation effect, such as the expected rate of temperature drop of the motor and the energy consumption of the heat dissipation system. The motor's heat dissipation decision is input into the heat dissipation prediction and evaluation unit, and the heat dissipation prediction model is used to predict the motor's heat dissipation based on the input heat dissipation decision. The predicted heat dissipation is verified according to motor heat dissipation constraints, such as the motor temperature not exceeding a certain threshold and the energy consumption of the heat dissipation system not exceeding a certain upper limit. If the predicted heat dissipation meets all the constraints and reaches the expected evaluation criteria, the heat dissipation decision is considered effective. If the predicted heat dissipation does not meet the constraints or does not reach the evaluation criteria, optimization is required. Based on the analysis results of the heat dissipation prediction model, the heat dissipation strategy parts that need to be adjusted are determined, such as increasing the fan speed or changing the heat sink fin layout.

[0024] S6: According to the heat dissipation optimization instruction, activate the heat dissipation optimization algorithm, combine the motor temperature monitoring data, the motor operating condition monitoring data, the motor environment monitoring data, and the motor heat dissipation constraint rules to optimize and adjust the motor heat dissipation decision, and generate a heat dissipation optimization scheme.

[0025] Specifically, based on the complexity and characteristics of the problem, an optimization algorithm is selected, including genetic algorithms, particle swarm optimization, and simulated annealing. Initial parameters of the algorithm are set, such as population size, number of iterations, crossover rate, and mutation rate. Motor temperature monitoring data, motor operating condition monitoring data (such as voltage, current, and power), and motor environmental monitoring data (such as ambient temperature and humidity) are integrated. Preprocessing operations such as data cleaning and normalization are performed on the data. Based on the goal of heat dissipation optimization, an objective function is defined for the optimization problem, such as minimizing motor temperature or maximizing heat dissipation efficiency. Constraints are set for the optimization problem, such as the maximum temperature limit of the motor and the energy consumption limit of the heat dissipation system, in conjunction with motor heat dissipation constraints. The population or solution set is initialized, and new heat dissipation decision schemes are generated iteratively, with their performance evaluated. Based on the evaluation results of the objective function and constraints, excellent individuals are selected for evolutionary operations, such as crossover and mutation. Iteration stops when the preset number of iterations is reached or other termination conditions are met. The optimal heat dissipation decision scheme is extracted from the iterative optimization process.

[0026] S7: Perform heat dissipation control on the motor based on the air-cooled heat dissipation unit and the heat dissipation optimization scheme.

[0027] Specifically, based on the motor's power and heat dissipation requirements, ensure that the fan's airflow, air pressure, and other parameters meet the motor's heat dissipation requirements. Optimize the fan's installation position and, according to the heat dissipation optimization plan, optimize the shape, size, and spacing of the heat sink to improve heat dissipation area and heat exchange efficiency. Monitor the motor temperature in real time, and trigger the heat dissipation control mechanism when the temperature exceeds a set threshold. Dynamically adjust the fan speed based on the motor's real-time temperature and the heat dissipation optimization plan. Increase the fan speed to improve heat dissipation efficiency when the motor temperature is high; appropriately reduce the fan speed to save energy after the motor temperature decreases. Regularly check the operating status of the air-cooled heat dissipation unit, including whether the fan is operating normally and whether the heat sink is dusty. If any faults or abnormalities are found, handle them promptly to ensure the stability of the heat dissipation system. Adjust the heat dissipation control strategy according to the ambient temperature of the motor's environment. In high-temperature environments, increase the fan speed or increase the heat dissipation area of ​​the heat sink to cope with higher heat dissipation demands.

[0028] Furthermore, such as Figure 2 As shown, step S3 of this application further includes: Based on the motor temperature monitoring data, a motor temperature risk prediction is performed to obtain a motor temperature risk prediction index; it is then determined whether the motor temperature risk prediction index is greater than or equal to a motor temperature risk prediction threshold; if the motor temperature risk prediction index is greater than or equal to the motor temperature risk prediction threshold, a motor heat dissipation signal is generated.

[0029] Specifically, motor temperature monitoring data is continuously collected. Using this collected data, historical temperature monitoring data is used as a training set to train the model, and the trained model is validated using a validation set. Preprocessed real-time temperature monitoring data is then input into the trained temperature risk prediction model. The prediction model outputs a motor temperature risk prediction index, which represents the degree of risk of motor overheating. A motor temperature risk prediction threshold is set by someone skilled in the art, and the motor temperature risk prediction index is compared with this threshold. If the motor temperature risk prediction index is greater than or equal to the threshold, it indicates a risk of motor overheating. In this case, a motor cooling signal is immediately generated to trigger appropriate cooling measures to prevent motor overheating.

[0030] Furthermore, this application also includes: A motor temperature risk prediction unit is constructed, comprising S motor temperature risk prediction models, where S is a positive integer greater than 1. Motor temperature monitoring data is input into the motor temperature risk prediction unit to obtain S motor temperature risk prediction coefficients. The output accuracy parameters of the S motor temperature risk prediction models are collected to obtain S motor temperature risk prediction accuracies. It is determined whether the S motor temperature risk prediction accuracies meet the temperature risk prediction accuracy constraint, resulting in P superior temperature risk prediction accuracies that meet the constraint, where P is a positive integer and P is less than or equal to S. The proportions of the P superior temperature risk prediction accuracies are calculated to obtain P temperature risk prediction gain coefficients. The P superior temperature risk prediction accuracies are matched with the S motor temperature risk prediction coefficients to obtain P superior temperature risk prediction coefficients. The P superior temperature risk prediction coefficients are weighted and calculated based on the P temperature risk prediction gain coefficients to obtain the motor temperature risk prediction index.

[0031] Specifically, S different motor temperature risk prediction models are selected, and these models are based on machine learning and deep learning. These models are trained using historical motor temperature monitoring data, and real-time collected motor temperature monitoring data is input into each model in the motor temperature risk prediction unit. Each model outputs a motor temperature risk prediction coefficient, representing the current temperature risk of the motor. For each model, its output accuracy parameter on historical data is collected through cross-validation and test set evaluation. The accuracy parameter is converted into motor temperature risk prediction precision, used to measure the prediction performance of each model. A constraint condition for temperature risk prediction precision is set, for example, the prediction accuracy must be higher than a certain threshold. Which of the S models meet this precision constraint are determined, resulting in P winning temperature risk prediction precisions that satisfy the condition. Based on the proportion of the P winning temperature risk prediction precisions, a temperature risk prediction gain coefficient is calculated for each winning model. This gain coefficient reflects the relative importance of the model's prediction precision. From the S motor temperature risk prediction coefficients, P winning temperature risk prediction coefficients corresponding to the P winning temperature risk prediction precisions are selected. The P winning temperature risk prediction coefficients are then weighted using the P temperature risk prediction gain coefficients. The weighted calculation result is the motor temperature risk prediction index, which integrates the prediction results of multiple models.

[0032] Furthermore, step S5 of this application also includes: The heat dissipation prediction and evaluation unit includes a heat dissipation prediction platform and a heat dissipation evaluation model. It collects the material structure information of the motor, combines it with motor temperature monitoring data, motor operating condition monitoring data, motor environmental monitoring data, and heat source characteristic data, and models the model based on the heat dissipation prediction platform to generate a heat dissipation prediction model. Based on the heat dissipation prediction model, it performs simulated heat dissipation control according to the motor heat dissipation decision to obtain a simulated heat dissipation monitoring dataset. It inputs the simulated heat dissipation monitoring dataset into the heat dissipation evaluation model to obtain a heat dissipation evaluation result. It determines whether the heat dissipation evaluation result meets the motor heat dissipation constraint rules, wherein the motor heat dissipation constraint rules include multi-dimensional motor heat dissipation constraints. If the heat dissipation evaluation result does not meet the motor heat dissipation constraint rules, it obtains the heat dissipation optimization instruction.

[0033] Specifically, information on the motor's material structure is collected, including key parameters such as the motor's thermally conductive materials and heat dissipation structure design. This data is combined with motor temperature monitoring data, motor operating condition monitoring data, motor environmental monitoring data, and heat source characteristic data to form a comprehensive dataset. Using a heat dissipation prediction platform and this collected dataset, the heat dissipation process is modeled. By analyzing the motor's heat dissipation characteristics under various operating conditions and environments, a heat dissipation prediction model is generated. This model can predict the motor's heat dissipation performance under different conditions. Based on the heat dissipation prediction model, motor heat dissipation decisions are simulated, such as adjusting the cooling fan speed and changing the heat sink layout. During the simulated heat dissipation control process, key indicators such as motor temperature changes and heat dissipation efficiency are recorded, forming a simulated heat dissipation monitoring dataset. This simulated heat dissipation monitoring dataset is input into a heat dissipation evaluation model. The heat dissipation evaluation model evaluates the simulated heat dissipation effect according to preset evaluation criteria, such as heat dissipation efficiency and temperature stability, and outputs the heat dissipation evaluation results. The heat dissipation evaluation results are compared with motor heat dissipation constraint rules. These constraints include multi-dimensional constraints such as the motor's maximum allowable temperature, the energy consumption limit of the heat dissipation system, and the minimum requirement for heat dissipation efficiency. The system then determines whether the heat dissipation evaluation results meet these multi-dimensional motor heat dissipation constraint rules. If the heat dissipation evaluation results do not meet the motor heat dissipation constraints, it indicates that the current heat dissipation decision needs to be optimized. In this case, a heat dissipation tuning instruction is generated, triggering the subsequent heat dissipation tuning process.

[0034] Furthermore, this application also includes: The heat dissipation evaluation model includes a multivariate heat dissipation evaluation sub-model, which includes a heat dissipation efficiency evaluation sub-model, a heat dissipation balance evaluation sub-model, a heat dissipation noise evaluation sub-model, and a heat dissipation energy consumption evaluation sub-model. The simulated heat dissipation monitoring dataset is input into the multivariate heat dissipation evaluation sub-model to obtain the heat dissipation efficiency evaluation coefficient, the heat dissipation balance evaluation coefficient, the heat dissipation noise evaluation coefficient, and the heat dissipation energy consumption evaluation coefficient. The heat dissipation efficiency evaluation coefficient, the heat dissipation balance evaluation coefficient, the heat dissipation noise evaluation coefficient, and the heat dissipation energy consumption evaluation coefficient are added to the heat dissipation evaluation result.

[0035] Specifically, the heat dissipation evaluation model comprises multiple sub-models, each evaluating different aspects of heat dissipation performance. These include a heat dissipation efficiency evaluation sub-model, a heat dissipation uniformity evaluation sub-model, a heat dissipation noise evaluation sub-model, and a heat dissipation energy consumption evaluation sub-model. Simulated heat dissipation monitoring datasets obtained through simulated heat dissipation control are input into these multivariate heat dissipation evaluation sub-models. The datasets contain various parameter changes of the motor during the simulated heat dissipation process, such as temperature distribution, heat dissipation rate, noise level, and energy consumption data. The overall heat dissipation speed and capacity of the motor's heat dissipation system are evaluated, generating a heat dissipation efficiency evaluation coefficient. This coefficient reflects the system's ability to quickly remove heat from the motor. The temperature distribution of different parts of the motor is analyzed to assess the uniformity of heat dissipation, generating a heat dissipation uniformity evaluation coefficient. This coefficient reflects whether heat dissipation is uniform across the motor, avoiding hot spots. The noise level generated during heat dissipation is measured, generating a heat dissipation noise evaluation coefficient. This coefficient assesses whether the noise generated by the heat dissipation system during operation is within acceptable limits. The energy consumption of the heat dissipation system during operation is calculated, generating a heat dissipation energy consumption evaluation coefficient. This coefficient reflects the energy utilization efficiency of the heat dissipation system while achieving effective heat dissipation. The evaluation coefficients for heat dissipation efficiency, heat dissipation uniformity, heat dissipation noise, and heat dissipation energy consumption are integrated into the heat dissipation evaluation result. This comprehensive evaluation result provides a complete analysis of the motor's heat dissipation performance, taking into account not only the heat dissipation speed and effect, but also the uniformity of heat dissipation, noise, and energy consumption.

[0036] Furthermore, step S6 of this application also includes: Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environmental monitoring data, heat dissipation backtracking learning is performed to establish a heat dissipation optimization population, wherein the heat dissipation optimization population includes multiple heat dissipation optimization seeds. The first heat dissipation optimization seed is randomly extracted from the heat dissipation optimization population. The motor heat dissipation decision is adjusted according to the first heat dissipation optimization seed to obtain the first optimized heat dissipation decision; The first optimization heat dissipation decision is input into the heat dissipation prediction and evaluation unit to obtain the heat dissipation evaluation result of the first optimization decision; Determine whether the heat dissipation evaluation result of the first optimization decision satisfies the motor heat dissipation constraint rule; If the heat dissipation evaluation result of the first optimization decision satisfies the motor heat dissipation constraint rule, the first heat dissipation optimization decision is added to the heat dissipation optimization scheme.

[0037] Specifically, using motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data, a backtracking learning process is employed to analyze the correlation between heat dissipation effect and factors such as motor operating conditions and the environment. Based on the results of the backtracking learning, a heat dissipation optimization population is established. This population consists of multiple heat dissipation optimization seeds, each representing a possible heat dissipation optimization scheme or strategy. A heat dissipation optimization seed is randomly selected from the population; this seed contains a specific heat dissipation optimization strategy and will serve as the starting point for subsequent optimizations. Based on the strategy of the first heat dissipation optimization seed, the motor's heat dissipation decisions are adjusted to obtain the first optimized heat dissipation decision. This includes adjusting the fan speed, changing the heat sink layout, and selecting heat dissipation materials. The first optimized heat dissipation decision is input into a heat dissipation prediction and evaluation unit, which can predict and evaluate the impact of the new heat dissipation decision on the motor's heat dissipation effect. The heat dissipation prediction and evaluation unit outputs the evaluation result of the first optimized heat dissipation decision. This result reflects the motor's heat dissipation performance after adopting the decision. The heat dissipation evaluation result of the first optimized decision is compared with the motor's heat dissipation constraint rules. The constraint rules include the motor's maximum allowable temperature and the minimum requirement for heat dissipation efficiency. If the heat dissipation evaluation result of the first optimization decision meets the motor heat dissipation constraint rules, it means that the heat dissipation decision is effective. In this case, the first optimization heat dissipation decision is added to the heat dissipation optimization scheme.

[0038] Furthermore, this application also includes: Based on the air-cooled heat dissipation unit, the control element features are identified to obtain multi-dimensional attribute information and multi-dimensional interval information of the control element. Based on the multi-dimensional attribute information of the control elements, a basic matrix for heat dissipation control is constructed; Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environment monitoring data, a heat dissipation correlation backtracking is performed to obtain a heat dissipation correlation decision set; Based on the heat dissipation-related decision set, standardization processing and centralized interval calculation are performed to obtain the multidimensional heat dissipation control centralized interval; Calculate the intersection of the multidimensional attribute information of the control element and the multidimensional heat dissipation control set interval to obtain the heat dissipation control optimization domain; Based on the heat dissipation control optimization domain and the motor heat dissipation decision, a heat dissipation optimization amplitude analysis is performed to obtain the heat dissipation control optimization domain. Based on the heat dissipation control optimization domain, heat dissipation amplitude is set on the heat dissipation control basic matrix to obtain the heat dissipation optimization population, wherein each heat dissipation optimization seed in the heat dissipation optimization population includes a heat dissipation optimization matrix.

[0039] Specifically, the control element features of the air-cooled heat dissipation unit are identified to obtain multi-dimensional attribute information and multi-dimensional interval information of the control elements. This information describes the adjustable parameters in heat dissipation control and their possible value ranges. A basic heat dissipation control matrix is ​​constructed using the multi-dimensional attribute information of the control elements. This matrix forms the basis of the heat dissipation control strategy, representing the initial control state before optimization. Heat dissipation correlation backtracking analysis is performed by combining motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data. Through backtracking, it is found which heat dissipation control elements are most closely related to the motor's heat dissipation effect under different operating conditions and environmental conditions. Based on the heat dissipation correlation decision set, standardization and concentrated interval calculation are performed. A multi-dimensional heat dissipation control concentrated interval is obtained, reflecting the ideal range to which the heat dissipation control elements should be adjusted under various conditions. The intersection of the multi-dimensional attribute information of the control elements and the multi-dimensional heat dissipation control concentrated interval is calculated. This intersection is defined as the heat dissipation control optimization domain, which represents the optimal range for adjusting the heat dissipation control elements to achieve the best heat dissipation effect. Based on the heat dissipation control optimization domain and motor heat dissipation decisions, heat dissipation optimization magnitude analysis is performed. By analyzing the tuning amplitude, a cooling control tuning domain is derived. This tuning domain clarifies the specific adjustment range of each cooling control element within the optimization domain to achieve optimized cooling performance. Based on the cooling control tuning domain, the cooling amplitude is set on the cooling control base matrix. A cooling tuning population is constructed, where each cooling tuning seed contains an optimized cooling tuning matrix. These cooling tuning matrices represent different cooling optimization strategies.

[0040] Furthermore, this application also includes: Based on the motor, a backtracking retrieval target is set, wherein the backtracking retrieval target includes the motor and multiple motors of the same model as the motor; Based on the backtracking retrieval target, a heat dissipation record retrieval is performed to obtain multiple backtracking heat dissipation records; The first retrospective heat dissipation record is extracted by traversing the multiple retrospective heat dissipation records. The first retrospective heat dissipation record includes first historical motor temperature monitoring data, first historical motor operating condition monitoring data, first historical motor environmental monitoring data, and first historical motor heat dissipation decision. Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environment monitoring data, similarity identification is performed on the first historical motor temperature monitoring data, the first historical motor operating condition monitoring data, and the first historical motor environment monitoring data to obtain the first comprehensive heat dissipation correlation coefficient; If the first comprehensive heat dissipation correlation coefficient is greater than or equal to the comprehensive heat dissipation correlation threshold, the first historical motor heat dissipation decision is added to the heat dissipation correlation decision set.

[0041] Specifically, the target of the retrospective retrieval is determined, including the motor currently under study and multiple motors of the same model. Including motors of the same model in the search scope expands the data sample. Based on the defined retrospective retrieval target, relevant heat dissipation records are retrieved from the database. These records include motor temperature monitoring data, operating condition monitoring data, environmental monitoring data, and the heat dissipation decisions made at that time. Multiple retrieved retrospective heat dissipation records are traversed, and the first retrospective heat dissipation record is extracted. This record contains the first historical motor temperature monitoring data, the first historical motor operating condition monitoring data, the first historical motor environmental monitoring data, and the first historical motor heat dissipation decision. Similarity identification is performed using the current motor's temperature monitoring data, operating condition monitoring data, and environmental monitoring data against the corresponding data in the first retrospective heat dissipation record. By calculating the correlation and distance metrics between the data, a first comprehensive heat dissipation correlation coefficient is obtained. A comprehensive heat dissipation correlation threshold is set to determine if the similarity between the current motor state and the historical motor state is sufficiently high. If the first comprehensive heat dissipation correlation coefficient is greater than or equal to this threshold, it indicates that the current motor state is highly similar to the motor state in the first retrospective heat dissipation record. In this case, the first historical motor heat dissipation decision is added to the heat dissipation correlation decision set. The heat dissipation-related decision set is a collection used to store historical heat dissipation decisions similar to the current motor state.

[0042] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0043] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. An intelligent heat dissipation control method based on motor operation monitoring, characterized in that, The method includes: Based on the motor monitoring unit, read the motor temperature monitoring data, motor operating condition monitoring data, and motor environmental monitoring data; Structural features are extracted and material features are identified from the air-cooled heat dissipation unit of the motor to obtain heat dissipation source feature data; Based on the motor temperature monitoring data, motor temperature risk prediction is performed to obtain motor heat dissipation signals; Based on the motor heat dissipation signal, the motor heat dissipation decision model is activated, and a motor heat dissipation decision is generated by combining the motor temperature monitoring data and the heat dissipation source characteristic data. The heat dissipation decision of the motor is verified by the heat dissipation prediction and evaluation unit and the motor heat dissipation constraint rules, and a heat dissipation optimization instruction is generated. According to the heat dissipation optimization instruction, the heat dissipation optimization algorithm is activated, and the motor heat dissipation decision is optimized and adjusted by combining the motor temperature monitoring data, the motor operating condition monitoring data, the motor environment monitoring data, and the motor heat dissipation constraint rules to generate a heat dissipation optimization scheme. The motor is controlled for heat dissipation based on the air-cooled heat dissipation unit and the heat dissipation optimization scheme.

2. The method as described in claim 1, characterized in that, Based on the motor temperature monitoring data, motor temperature risk prediction is performed to obtain motor heat dissipation signals, including: Based on the motor temperature monitoring data, motor temperature risk prediction is performed to obtain a motor temperature risk prediction index. Determine whether the motor temperature risk prediction index is greater than or equal to the motor temperature risk prediction threshold. If the motor temperature risk prediction index is greater than or equal to the motor temperature risk prediction threshold, the motor heat dissipation signal is generated.

3. The method as described in claim 2, characterized in that, Based on the motor temperature monitoring data, a motor temperature risk prediction index is obtained, including: A motor temperature risk prediction unit is constructed, wherein the motor temperature risk prediction unit includes S motor temperature risk prediction models, where S is a positive integer greater than 1; The motor temperature monitoring data is input into the motor temperature risk prediction unit to obtain S motor temperature risk prediction coefficients. Collect the output accuracy parameters of the S motor temperature risk prediction models to obtain the prediction accuracy of the S motor temperature risks. Determine whether the S motor temperature risk prediction accuracies meet the temperature risk prediction accuracy constraint, and obtain P superior temperature risk prediction accuracies that meet the temperature risk prediction accuracy constraint, where P is a positive integer and P is less than or equal to S. Based on the proportion of the P superior temperature risk prediction accuracies, the P temperature risk prediction gain coefficients are obtained. Based on the P superior temperature risk prediction accuracy, the S motor temperature risk prediction coefficients are matched to obtain P superior temperature risk prediction coefficients. The motor temperature risk prediction index is obtained by weighting the P winning temperature risk prediction coefficients based on the P temperature risk prediction gain coefficients.

4. The method as described in claim 1, characterized in that, The heat dissipation decision is verified based on the heat dissipation prediction and evaluation unit and the motor heat dissipation constraint rules, and a heat dissipation optimization instruction is generated, including: The heat dissipation prediction and evaluation unit includes a heat dissipation prediction platform and a heat dissipation evaluation model; The material structure information of the motor is collected, and combined with the motor temperature monitoring data, the motor operating condition monitoring data, the motor environmental monitoring data, and the heat dissipation source characteristic data, a heat dissipation prediction model is generated based on the heat dissipation prediction platform. Based on the heat dissipation prediction model, simulated heat dissipation control is performed according to the motor heat dissipation decision to obtain a simulated heat dissipation monitoring dataset. Input the simulated heat dissipation monitoring dataset into the heat dissipation evaluation model to obtain the heat dissipation evaluation results; Determine whether the heat dissipation evaluation result meets the motor heat dissipation constraint rules, wherein the motor heat dissipation constraint rules include multi-dimensional motor heat dissipation constraints; If the heat dissipation evaluation result does not meet the motor heat dissipation constraint rules, the heat dissipation optimization instruction is obtained.

5. The method as described in claim 4, characterized in that, The simulated heat dissipation monitoring dataset is input into the heat dissipation evaluation model to obtain heat dissipation evaluation results, including: The heat dissipation evaluation model includes a multivariate heat dissipation evaluation sub-model, which includes a heat dissipation efficiency evaluation sub-model, a heat dissipation balance evaluation sub-model, a heat dissipation noise evaluation model, and a heat dissipation energy consumption evaluation model. The simulated heat dissipation monitoring dataset is input into the multivariate heat dissipation evaluation sub-model to obtain the heat dissipation efficiency evaluation coefficient, heat dissipation balance evaluation coefficient, heat dissipation noise evaluation coefficient, and heat dissipation energy consumption evaluation coefficient. The heat dissipation efficiency evaluation coefficient, the heat dissipation balance evaluation coefficient, the heat dissipation noise evaluation coefficient, and the heat dissipation energy consumption evaluation coefficient are added to the heat dissipation evaluation result.

6. The method as described in claim 1, characterized in that, According to the heat dissipation optimization instruction, the heat dissipation optimization algorithm is activated. Combining the motor temperature monitoring data, the motor operating condition monitoring data, the motor environmental monitoring data, and the motor heat dissipation constraint rules, the algorithm optimizes and adjusts the motor heat dissipation decision to generate a heat dissipation optimization scheme, including: Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environmental monitoring data, heat dissipation backtracking learning is performed to establish a heat dissipation optimization population, wherein the heat dissipation optimization population includes multiple heat dissipation optimization seeds. The first heat dissipation optimization seed is randomly extracted from the heat dissipation optimization population. The motor heat dissipation decision is adjusted according to the first heat dissipation optimization seed to obtain the first optimized heat dissipation decision; The first optimization heat dissipation decision is input into the heat dissipation prediction and evaluation unit to obtain the heat dissipation evaluation result of the first optimization decision; Determine whether the heat dissipation evaluation result of the first optimization decision satisfies the motor heat dissipation constraint rule; If the heat dissipation evaluation result of the first optimization decision satisfies the motor heat dissipation constraint rule, the first heat dissipation optimization decision is added to the heat dissipation optimization scheme.

7. The method as described in claim 6, characterized in that, Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environmental monitoring data, heat dissipation backtracking learning is performed to establish a heat dissipation optimization population, including: Based on the air-cooled heat dissipation unit, the control element features are identified to obtain multi-dimensional attribute information and multi-dimensional interval information of the control element. Based on the multi-dimensional attribute information of the control elements, a basic matrix for heat dissipation control is constructed; Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environment monitoring data, a heat dissipation correlation backtracking is performed to obtain a heat dissipation correlation decision set; Based on the heat dissipation-related decision set, standardization processing and centralized interval calculation are performed to obtain the multidimensional heat dissipation control centralized interval; Calculate the intersection of the multidimensional attribute information of the control element and the multidimensional heat dissipation control set interval to obtain the heat dissipation control optimization domain; Based on the heat dissipation control optimization domain and the motor heat dissipation decision, a heat dissipation optimization amplitude analysis is performed to obtain the heat dissipation control optimization domain. Based on the heat dissipation control optimization domain, heat dissipation amplitude is set on the heat dissipation control basic matrix to obtain the heat dissipation optimization population, wherein each heat dissipation optimization seed in the heat dissipation optimization population includes a heat dissipation optimization matrix.

8. The method as described in claim 7, characterized in that, Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environmental monitoring data, a heat dissipation correlation backtracking is performed to obtain a heat dissipation correlation decision set, including: Based on the motor, a backtracking retrieval target is set, wherein the backtracking retrieval target includes the motor and multiple motors of the same model as the motor; Based on the backtracking retrieval target, a heat dissipation record retrieval is performed to obtain multiple backtracking heat dissipation records; The first retrospective heat dissipation record is extracted by traversing the multiple retrospective heat dissipation records. The first retrospective heat dissipation record includes first historical motor temperature monitoring data, first historical motor operating condition monitoring data, first historical motor environmental monitoring data, and first historical motor heat dissipation decision. Based on the motor temperature monitoring data, the motor operating condition monitoring data, and the motor environment monitoring data, similarity identification is performed on the first historical motor temperature monitoring data, the first historical motor operating condition monitoring data, and the first historical motor environment monitoring data to obtain the first comprehensive heat dissipation correlation coefficient; If the first comprehensive heat dissipation correlation coefficient is greater than or equal to the comprehensive heat dissipation correlation threshold, the first historical motor heat dissipation decision is added to the heat dissipation correlation decision set.

Images