Intelligent regulation and control method and equipment for operation of textile air conditioner fan and medium

Abstract

The invention discloses an intelligent regulation and control method and device for operation of a textile air conditioner fan and a medium. The method comprises the steps that multi-source data in a textile workshop are collected in real time, and the multi-source data are preprocessed; based on the preprocessed target multi-source data, predicting an environmental parameter change trend in a first time period in the future, inputting the target multi-source data into a pre-trained depth time sequence prediction model, and outputting an environmental parameter change trend prediction result in a second time period in the future; generating a fan regulation and control instruction through a multi-objective optimization algorithm on the basis of the environmental parameter change trend and the current fan operation state parameter in the second time period in the future, and issuing the fan regulation and control instruction to a fan control system; and monitoring the environmental parameters and the fan operation state after the instruction is executed in real time, and triggering regulation and control instruction re-optimization based on the deviation between a monitoring result and an expected target.

Description

Technical Field

[0001] This application relates to the field of industrial environmental control technology, and in particular to an intelligent control method, equipment and medium for the operation of textile air conditioning fans. Background Technology

[0002] Air conditioning fans in textile workshops are key equipment for maintaining a stable production environment, and their operating status directly affects textile quality and production efficiency. Traditional control methods for textile air conditioning fans mainly rely on manual experience or fixed program control, which is difficult to adapt to dynamic changes in the workshop environment, resulting in problems such as insufficient control precision, energy waste, and accelerated equipment wear and tear.

[0003] In existing technologies, the control strategies for textile air conditioning fans are typically based on feedback from a single environmental parameter, lacking the fusion analysis of multi-source data and failing to accurately capture the coupling relationships between environmental parameters such as temperature, humidity, dust concentration, and wind speed. Furthermore, traditional methods exhibit significant lag in responding to environmental changes; fan operating parameter adjustments often fall behind actual demand changes, leading to fluctuations in the workshop environment exceeding the allowable range of the process and affecting product quality stability. In addition, fan operation modes with fixed speeds or simple threshold control struggle to balance energy consumption optimization and equipment protection, resulting in energy waste and accumulated mechanical wear.

[0004] More critically, existing control systems lack predictive control capabilities, failing to optimize fan operation strategies in advance based on changes in production plans, equipment loads, and other operating conditions. In the event of sudden environmental disturbances or production rhythm adjustments, the system can only respond passively; frequent start-ups and shutdowns or overload operation not only increase energy consumption but also shorten equipment lifespan. Furthermore, traditional methods are insufficient for monitoring the fan's health status, making it difficult to detect potential faults such as bearing wear in a timely manner, thus posing a risk of sudden shutdowns. Summary of the Invention

[0005] This application provides an intelligent control method, device, and medium for the operation of textile air conditioning fans to solve the above-mentioned technical problems.

[0006] On the one hand, embodiments of this application provide an intelligent control method for the operation of textile air conditioning fans, including: Real-time acquisition of multi-source data within the textile workshop, followed by preprocessing of the multi-source data; the multi-source data includes fan operating status parameters; Based on the preprocessed target multi-source data, the environmental parameter change trend is predicted in the first time period in the future, and the target multi-source data is input into the pre-trained deep time series prediction model to output the environmental parameter change trend prediction result in the second time period in the future. Based on the environmental parameter change trend and the current fan operation state parameter in the future second time period, a fan regulation instruction is generated through a multi-objective optimization algorithm, and the fan regulation instruction is issued to the fan control system; The environmental parameter and the fan operation state after the real-time monitoring instruction are executed are monitored in real time, and based on the deviation between the monitoring result and the expected target, the regulation instruction is re-optimized.

[0007] In an implementation manner of the present application, multi-source data in the textile workshop is collected in real time, specifically including: The environmental parameter of the textile workshop is collected through the sensor deployed in the textile workshop; the environmental parameter at least includes temperature, humidity, dust concentration and wind speed; The fan operation state parameter in the textile workshop is collected through the fan controller interface; the fan operation state parameter at least includes speed and current; The production equipment operation load parameter in the textile workshop is collected through the production equipment control system.

[0008] In an implementation manner of the present application, the multi-source data is preprocessed, specifically including: The environmental parameter, the fan operation state parameter and the production equipment operation load parameter are subjected to time alignment processing, and based on the spatial layout model of the textile workshop, the multi-source data is mapped to the corresponding spatial region; The dynamic change rate feature in the environmental parameter, the frequency spectrum feature in the production equipment operation load parameter and the correlation feature of fan speed and current in the fan operation state parameter are extracted, to generate a fusion feature data set; The multi-dimensional feature vector in the fusion feature data set is subjected to noise filtering, and the abnormal value in the filtered multi-dimensional feature vector is eliminated, to obtain target multi-source data.

[0009] In an implementation manner of the present application, based on the preprocessed target multi-source data, the environmental parameter change trend in the future first time period is predicted, specifically including: The preprocessed target multi-source data is input into the pre-trained local prediction model, and the environmental parameter change trend prediction result in the future first time period is output; In the case that the edge node detects the communication interruption between the cloud platform, based on the environmental parameter change trend in the future first time period, a fan speed adjustment instruction is generated, and the fan speed adjustment instruction is sent to the fan control system, to dynamically adjust the fan speed in the textile workshop.

[0010] In an implementation form of the present application, based on the trend of the change of the environmental parameters in the future second time period and the current fan operating state parameters, the fan regulation instruction is generated by a multi-objective optimization algorithm, specifically including: A fan energy consumption model is constructed based on the cubic relationship of fan speed, an environmental stability model is constructed based on the sum of absolute values of temperature and humidity deviation, and a device wear model is established based on the square sum of speed change rate, to construct a multi-objective optimization function including the fan energy consumption model, the environmental stability model and the device wear model; An improved non-dominated sorting genetic algorithm is used to solve the multi-objective optimization function, to generate an optimal solution set, and an entropy weight decision method is used to select a comprehensive optimal solution from the optimal solution set, to generate a joint regulation instruction of fan speed and air supply angle.

[0011] In an implementation form of the present application, based on the deviation between the monitoring results and the expected target, the regulation instruction is re-optimized, specifically including: The deviation between the actual environmental parameters and the expected target is calculated, and it is judged whether the deviation deviates from the target range for more than a preset time threshold; If yes, the algorithm parameters of the multi-objective optimization algorithm are optimized through a reinforcement learning mechanism, and the fan regulation instruction is re-generated by the optimized multi-objective optimization algorithm.

[0012] In an implementation form of the present application, before the target multi-source data is input into the pre-trained deep time series prediction model, the method further includes: A deep time series prediction model is constructed based on a double-layer long short-term memory neural network structure, to process a multi-dimensional input vector; wherein the multi-dimensional input vector includes environmental parameters, fan operating state parameters and production equipment operating load parameters; The deep time series prediction model is trained by using a weighted combination of mean absolute error and root mean square error as a loss function; The deep time series prediction model is iteratively trained based on a historical data set, and the learning rate is adaptively adjusted during the training process to optimize the model convergence, to complete the training of the deep time series prediction model.

[0013] In an implementation form of the present application, the environmental parameters and the fan operating state after the execution of the real-time monitoring instruction are monitored in real time, specifically including: The vibration spectrum characteristics of the fan are analyzed in real time to extract the main frequency band energy distribution, and the main frequency band energy distribution is taken as a health indicator to determine the health state data of the fan; In the case that the vibration amplitude of the fan continuously exceeds a preset amplitude threshold, the maximum allowable speed of the fan is reduced, and a fan maintenance alarm is generated; The health status data is fed back to a multi-objective optimization algorithm to dynamically adjust a weight coefficient of equipment wear.

[0014] In another aspect, the embodiments of the present application also provide an intelligent control device for operation of a textile air conditioner fan, the device comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above-mentioned intelligent control method for operation of a textile air conditioner fan.

[0015] In another aspect, the embodiments of the present application also provide a non-volatile computer storage medium storing computer executable instructions, and the computer executable instructions, when executed, implement the above-mentioned intelligent control method for operation of a textile air conditioner fan.

[0016] The embodiments of the present application provide an intelligent control method, device and medium for operation of a textile air conditioner fan, at least including the following beneficial effects: By real-time collection and fusion of multi-dimensional environmental parameters such as temperature and humidity, dust concentration and wind speed, and combining with a deep time series prediction model to accurately predict the change trend of the workshop environment, the fan control instruction can respond to the environmental demand in advance, and the temperature and humidity fluctuation is controlled within the process allowable range, effectively ensuring the stability of textile quality; through a multi-objective optimization algorithm to dynamically balance energy consumption, environmental stability and equipment wear, the optimal matching of fan speed and air supply angle is realized, compared with the traditional fixed power operation mode, the energy consumption is significantly reduced; using a reinforcement learning mechanism to continuously optimize the prediction model and control algorithm parameters, it can adapt to changes in different seasons, production plans or equipment loads, avoid frequent manual intervention, while ensuring emergency control capability in case of communication interruption, and improving system robustness; by real-time monitoring of fan vibration spectrum characteristics, early mechanical abnormalities are identified and operation parameters are adjusted in linkage, reducing the risk of sudden failure. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application, the illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flowchart of an intelligent control method for operation of a textile air conditioner fan provided by the embodiments of the present application; Figure 2 An internal structure diagram of an intelligent control device for operation of a textile air conditioner fan provided by the embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in connection with the specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0019] The technical solutions provided by the embodiments of the present application will be described in detail below in connection with the drawings.

[0020] Figure 1 A flowchart of an intelligent control method for operation of a textile air conditioner fan provided by an embodiment of the present application.

[0021] The implementation of the analysis method involved in the embodiments of the present application can be a terminal device or a server, and the present application does not make special limitations thereon. For the convenience of understanding and description, the following embodiments are described in detail taking the server as an example.

[0022] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server, and the present application does not make specific limitations thereon.

[0023] As shown in the figure, the intelligent control method for operation of a textile air conditioner fan provided by an embodiment of the present application comprises: Figure 1 Step 101, real-time collection of multi-source data in a textile workshop, and pre-processing of the multi-source data; the multi-source data includes fan operation state parameters.

[0024] In the present embodiment, the multi-source data covers three types of environmental parameters, fan operation state parameters and production equipment operation load parameters.

[0025] The multi-source data collection system is composed of a distributed environmental sensor network, a fan state monitoring module and a production equipment data interface. Exemplarily, the environmental sensor network includes temperature and humidity sensors, laser dust detectors and ultrasonic wind speed sensors, which are deployed in a grid according to the process partition of the textile workshop. It can be understood that this deployment method can ensure the spatial representativeness of environmental parameter collection and avoid monitoring blind areas.

[0026] Specifically, the collection of fan operation state parameters is realized through an industrial communication protocol. It should be noted that the fan operation state parameters at least include speed and current, which are obtained in real time through the fan controller interface. At the same time, a vibration sensor is installed at the fan bearing seat position for monitoring the mechanical operation state.

[0027] ​For the data preprocessing process, firstly, a space-time alignment process is performed. Exemplarily, due to the difference in sampling frequencies of different sensors, a linear interpolation algorithm is used to unify the timestamps to a reference frequency. It can be understood that this processing method can eliminate the data deviation caused by asynchronous sampling. Specifically, based on the spatial layout model of the textile workshop, the discrete sensor data is mapped to the corresponding spatial region to form a space-time correlated data matrix. When the temperature and humidity of the weaving area are abnormal, the corresponding air supply fan can be accurately associated.

[0028] The dynamic change rate of the environmental parameters (such as the temperature rise rate), the correlation coefficient of the fan speed and the current (indicating the motor efficiency), and the main component of the frequency domain energy of the vibration signal (reflecting the mechanical state) are extracted to generate a multi-dimensional fusion feature vector. Through a sliding window combined with wavelet denoising to eliminate sensor noise, and using an anomaly detection algorithm to eliminate outliers. It should be noted that this step provides a high-consistency data base for subsequent intelligent decision-making.

[0029] Step 102, based on the preprocessed target multi-source data, the trend of the change of the environmental parameters in the future first time period is predicted, and the target multi-source data is input into the pre-trained deep time series prediction model to output the prediction result of the change trend of the environmental parameters in the future second time period.

[0030] In this embodiment, the preprocessed data is input into a lightweight LSTM model to output the environmental trend prediction in the future first time period, such as minutes. Exemplarily, when it is detected that the humidity change rate is continuously positive and the dust accumulation is accelerated, it is predicted that there will be a high-humidity and high-dust risk in the local area. It should be noted that if the edge node and the cloud link are interrupted, the fan speed adjustment instruction is immediately generated based on the local prediction, such as increasing the speed to strengthen ventilation, so as to maintain the basic regulation function.

[0031] In this embodiment, the data is uploaded to a cloud deep time series prediction model. Specifically, the model uses a double-layer LSTM structure to process the fusion feature vector, which includes environmental, state, and load parameters, and outputs a high-precision prediction in the future second time period, such as half an hour. It can be understood that the MAE and RMSE weighted combination loss function is used during training to balance the stability and sensitivity of the model, and the adaptive learning rate is adjusted to optimize the convergence efficiency. Exemplarily, combined with the raw material switching information in the production plan, such as cotton to chemical fiber, the dust concentration change trend is predicted to adjust the filter air speed in advance.

[0032] Step 103, based on the change trend of the environmental parameters in the future second time period and the current fan operation state parameters, a fan regulation instruction is generated through a multi-objective optimization algorithm, and the fan regulation instruction is sent to the fan control system.

[0033] In this embodiment, for the energy consumption target, an energy consumption model is established according to the cubic relationship between the fan power and the rotating speed, and the total energy consumption is minimized. For the environmental target, the stability is quantified by the sum of the absolute values of the temperature and humidity deviations, and the deviation needs to be minimized. For the equipment target, the mechanical wear is represented by the sum of the squares of the rotating speed change rates, and the sudden operation is inhibited.

[0034] The improved non-dominated sorting genetic algorithm is used to solve the Pareto optimal solution set, and the improvement is embodied in the introduction of the elite reservation strategy to accelerate the convergence. The comprehensive score of each solution is calculated by the entropy weight decision method, and the optimal solution is selected to generate the joint instruction of the rotating speed and the air supply angle. Among them, the entropy weight can dynamically reflect the importance of the target.

[0035] It can be understood that this step realizes the coordinated optimization of multiple targets. For example, under the condition of high temperature and high load, the algorithm may choose to moderately increase the energy consumption to prioritize the temperature control accuracy, while limiting the rotating speed fluctuation rate to protect the equipment. The delay control of the instruction issued to the fan control system is in an extremely short time level, ensuring the real-time response.

[0036] Step 104, real-time monitoring of the environmental parameters and the fan operating state after the execution of the instruction, and based on the deviation between the monitoring results and the expected target, triggering the re-optimization of the control instruction.

[0037] In this embodiment, the deviation between the actual temperature and humidity and the target value is continuously calculated. It can be understood that when the deviation continuously exceeds the allowed range and reaches the set time threshold, the reinforcement learning mechanism is triggered to dynamically adjust the weight parameters of the multi-objective optimization algorithm, such as increasing the environmental target coefficient, and re-generating the control instruction. For example, when the outdoor temperature rises in the afternoon in summer, the system automatically enhances the priority of refrigeration.

[0038] In this embodiment, the vibration frequency spectrum energy distribution of the fan is analyzed in real time, and the main frequency band features are extracted as health indicators. It should be noted that when the vibration amplitude continuously exceeds the limit, two-level responses are executed. First, the maximum allowed rotating speed of the fan is automatically reduced by a preset proportion, such as limiting the peak rotating speed to reduce the mechanical load. Second, a maintenance work order is generated and pushed to the operation and maintenance system, and the equipment state is fed back to the optimization algorithm to dynamically adjust the wear weight. Specifically, this step forms a closed-loop autonomous chain of "monitoring → diagnosis → response → feedback", which significantly improves the robustness of the system.

[0039] The above is the method embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides an intelligent control device for the operation of a textile air conditioner fan, and the structure thereof is shown in Figure 2 .

[0040] Figure 2 An internal structure diagram of an intelligent control device for the operation of a textile air conditioner fan provided by the embodiment of the present application is shown in Figure 2 . As shown, the device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: collect multi-source data in a textile workshop in real time, and pre-process the multi-source data; the multi-source data includes fan operating state parameters; based on the target multi-source data after pre-processing, predict a trend of changes in environmental parameters in a first future time period, and input the target multi-source data into a pre-trained deep time series prediction model to output a prediction result of the trend of changes in environmental parameters in a second future time period; based on the trend of changes in environmental parameters in the second future time period and the current fan operating state parameters, generate fan control instructions through a multi-objective optimization algorithm, and issue the fan control instructions to a fan control system; real-time monitor environmental parameters and fan operating states after execution of the instructions, and trigger re-optimization of the control instructions based on a deviation between the monitoring result and an expected target.

[0041] The embodiments of the present application also provide a non-volatile computer storage medium storing computer executable instructions, and the computer executable instructions are executed to be capable of: collecting multi-source data in a textile workshop in real time, and pre-processing the multi-source data; the multi-source data includes fan operating state parameters; based on the target multi-source data after pre-processing, predicting a trend of changes in environmental parameters in a first future time period, and inputting the target multi-source data into a pre-trained deep time series prediction model to output a prediction result of the trend of changes in environmental parameters in a second future time period; based on the trend of changes in environmental parameters in the second future time period and the current fan operating state parameters, generating fan control instructions through a multi-objective optimization algorithm, and issuing the fan control instructions to a fan control system; real-time monitoring environmental parameters and fan operating states after execution of the instructions, and triggering re-optimization of the control instructions based on a deviation between the monitoring result and an expected target.

[0042] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, the device and medium embodiments are described simply because they are basically similar to the method embodiments, and the relevant parts can be referred to the part of the description of the method embodiments.

[0043] The device and medium provided by the embodiments of the present application are one-to-one corresponding, and therefore the device and medium also have similar beneficial technical effects to the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here again.

[0044] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. In addition, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0045] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the functions specified in one or more blocks.

[0046] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the functions specified in one or more blocks.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that carries out the functions specified in one or more blocks.

[0048] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memories.

[0049] Memory can include non-persistent memory and / or volatile memory, random access memory (RAM), and / or non-volatile memory, e.g., read only memory (ROM) or flash memory, among others. Memory is an example of computer readable media.

[0050] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0051] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0052] The above merely provides an embodiment of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for intelligent control of the operation of a textile air conditioning fan, characterized in that, The method includes: Real-time acquisition of multi-source data within the textile workshop, followed by preprocessing of the multi-source data; the multi-source data includes fan operating status parameters; Based on the preprocessed target multi-source data, the environmental parameter change trend is predicted in the first time period in the future, and the target multi-source data is input into the pre-trained deep time series prediction model to output the environmental parameter change trend prediction result in the second time period in the future. Based on the trend of environmental parameter changes and the current wind turbine operating status parameters in the second future time period, a multi-objective optimization algorithm is used to generate wind turbine control commands, and the wind turbine control commands are sent to the wind turbine control system. The system monitors environmental parameters and wind turbine operating status in real time after the command is executed, and triggers re-optimization of control commands based on the deviation between the monitoring results and the expected targets.

2. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Real-time collection of multi-source data within the textile workshop, specifically including: The environmental parameters of the textile workshop are collected by sensors deployed within the workshop; these environmental parameters include at least temperature, humidity, dust concentration, and wind speed. The operating status parameters of the fans in the textile workshop are collected through the fan controller interface; the fan operating status parameters include at least the speed and current. The operating load parameters of the production equipment in the textile workshop are collected through the production equipment control system.

3. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Preprocessing of the multi-source data specifically includes: Environmental parameters, fan operating status parameters, and production equipment operating load parameters are time-aligned, and the multi-source data is mapped to the corresponding spatial regions based on the spatial layout model of the textile workshop. Extract the dynamic change rate features from the environmental parameters, the spectral features from the production equipment operating load parameters, and the correlation features between the fan speed and current from the fan operating status parameters to generate a fused feature dataset; Noise filtering is performed on the multidimensional feature vectors in the fused feature dataset, and outliers in the filtered multidimensional feature vectors are removed to obtain the target multi-source data.

4. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Based on the preprocessed target multi-source data, the trend of environmental parameter changes in the first time period is predicted, specifically including: The preprocessed target multi-source data is input into a pre-trained local prediction model, which outputs the prediction results of environmental parameter change trends in the first time period in the future. If the edge node detects a communication interruption with the cloud platform, it generates a fan speed adjustment command based on the trend of environmental parameter changes in the first time period in the future, and sends the fan speed adjustment command to the fan control system to dynamically adjust the fan speed in the textile workshop.

5. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Based on the changing trends of environmental parameters in the second future time period and the current operating status parameters of the wind turbines, a multi-objective optimization algorithm is used to generate wind turbine control commands, specifically including: A fan energy consumption model is constructed based on the cubic relationship of fan speed, an environmental stability model is constructed based on the sum of absolute values ​​of temperature and humidity deviations, and an equipment wear model is established based on the sum of squares of the rate of change of speed. In order to construct a multi-objective optimization function that includes the fan energy consumption model, the environmental stability model and the equipment wear model. An improved non-dominated sorting genetic algorithm is used to solve the multi-objective optimization function, generate the optimal solution set, and select the comprehensive optimal solution from the optimal solution set using the entropy weight decision method to generate a joint control command for the fan speed and the air supply angle.

6. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Based on the deviation between monitoring results and expected targets, the regulatory instructions are re-optimized, specifically including: Calculate the deviation between the actual environmental parameters and the expected target, and determine whether the deviation continues to deviate from the target range for more than a preset time threshold; If so, the algorithm parameters of the multi-objective optimization algorithm are optimized through a reinforcement learning mechanism, and the wind turbine control command is regenerated through the optimized multi-objective optimization algorithm.

7. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Before inputting the target multi-source data into the pre-trained deep temporal prediction model, the method further includes: A deep time series prediction model is constructed based on a two-layer long short-term memory neural network structure to process multi-dimensional input vectors; wherein, the multi-dimensional input vectors include environmental parameters, fan operating status parameters, and production equipment operating load parameters; The deep time series prediction model is trained by using a weighted combination of mean absolute error and root mean square error as the loss function. The deep time series prediction model is iteratively trained based on historical datasets, and the learning rate is adaptively adjusted during the training process to optimize model convergence, thereby completing the training of the deep time series prediction model.

8. The intelligent control method for the operation of a textile air conditioning fan according to claim 1, characterized in that, Real-time monitoring of environmental parameters and wind turbine operating status after command execution, specifically including: The vibration spectrum characteristics of the wind turbine are analyzed in real time to extract the energy distribution of the main frequency band, and the energy distribution of the main frequency band is used as a health indicator to determine the health status data of the wind turbine. If the vibration amplitude of the fan continuously exceeds a preset amplitude threshold, the maximum allowable speed of the fan will be reduced, and a fan maintenance alarm will be generated. The health status data is fed back to a multi-objective optimization algorithm to dynamically adjust the weighting coefficients of equipment wear.

9. An intelligent control device for the operation of a textile air conditioning fan, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform an intelligent control method for the operation of a textile air conditioner fan as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, an intelligent control method for the operation of a textile air conditioning fan as described in any one of claims 1-8 is implemented.

Images