A low energy consumption control method, device and storage medium for a large centrifugal fan

Abstract

The present invention discloses a low-energy control method, device, and storage medium for a large centrifugal fan, relating to the technical fields of environmental control and energy management. The present invention uses multi-sensor fusion technology to monitor environmental parameters within a clean room in real time, and utilizes a support vector machine algorithm to establish an air volume prediction model. This model accurately determines the target air volume range, controls the air conditioning system to adjust the air volume, and meets the cleanliness requirements of medical operations. This allows the fan to flexibly adapt to environmental changes, resolving the problem of traditional fans being unable to adjust air volume according to real-time environmental conditions. During the speed regulation process, energy consumption and noise are monitored in real time. When these values ​​exceed the standards, a fuzzy control algorithm is used to adjust the speed to the minimum value that meets the requirements. The intelligent algorithm parameters are optimized to improve control accuracy and response speed, reduce energy waste, and resolve the high energy consumption and low efficiency issues of traditional fans.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental control and energy management, and in particular to a low-energy consumption control method, equipment and storage medium for a large centrifugal fan. Background Art

[0002] During the operation of medical cleanrooms, centrifugal fan speed regulation is a critical technical issue. Cleanroom environmental parameters are complex and variable, such as temperature, humidity, pressure, and cleanliness. Furthermore, different medical procedures require significantly different air volume requirements. Traditional fixed-speed centrifugal fans are unable to flexibly adapt to these changes, easily resulting in excessive or insufficient air volume, impacting the cleanroom's environmental quality and energy efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a low-energy consumption control method, equipment and storage medium for large centrifugal fans, which uses multi-sensor fusion technology to monitor clean room environmental parameters and fan operating status in real time, and combines intelligent algorithms and frequency conversion technology to achieve precise, efficient and energy-saving speed control of centrifugal fans.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] The present application provides a low energy consumption control method for a large centrifugal fan, comprising the following steps:

[0006] Acquire environmental parameter data within the cleanroom, including temperature, humidity, pressure, and cleanliness, and collect and transmit it to the data processing module in real time through multi-sensor fusion technology. The module then determines the target air volume range under the current working conditions based on the preset cleanliness threshold and the air volume requirements of medical operations, combined with the environmental parameter data. This is used to control the air volume of the air conditioning system.

[0007] Frequency conversion technology is used to adjust the speed of the centrifugal fan. By calculating the difference between the target air volume and the current air volume, the speed adjustment range is determined using a fuzzy control algorithm. When the target air volume is higher than the current air volume, the speed is increased; when the target air volume is lower than the current air volume, the speed is reduced.

[0008] The target air volume and current air volume of the centrifugal fan are obtained, and the difference between the target air volume and the current air volume is calculated to obtain the air volume difference value. The positive or negative sign of the air volume difference value is determined. If the air volume difference value is positive, it means that the target air volume is higher than the current air volume, and the fan speed needs to be increased.

[0009] When the air volume difference value is negative, it means that the target air volume is lower than the current air volume, and the fan speed needs to be reduced. According to the size of the air volume difference value, the fuzzy control algorithm is used to determine the adjustment range of the fan speed and obtain the speed adjustment value.

[0010] The speed adjustment value is input into the frequency converter, and the actual speed of the fan is adjusted through frequency conversion technology to gradually approach the target speed;

[0011] In the process of adjusting the fan speed, the current air volume of the fan is obtained in real time, which is used as feedback and compared with the target air volume to form a closed-loop control;

[0012] Analyze the changing trends of environmental parameters through intelligent algorithms, predict the air volume demand in the future, and adjust the fan speed in advance to match the predicted demand;

[0013] During the speed regulation process, energy consumption and noise data are monitored in real time. When energy consumption exceeds the preset threshold or noise exceeds the allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements; then, based on historical data and real-time monitoring results, the parameter settings of the intelligent algorithm are optimized.

[0014] Furthermore, the environmental parameter data in the clean room, including temperature, humidity, pressure and cleanliness, is acquired in real time through multi-sensor fusion technology and transmitted to the data processing module, specifically including:

[0015] Based on the environmental parameter monitoring requirements of the clean room, temperature, humidity, pressure and cleanliness sensors are rationally arranged at different locations within the clean room. Real-time data on environmental parameters such as temperature, humidity, pressure and cleanliness within the clean room are collected through multiple sensors, and the sampling frequency is set according to actual needs.

[0016] The environmental parameter data collected by multiple sensors are transmitted to the data processing module via wired or wireless means;

[0017] In the data processing module, the received multi-sensor data is preprocessed and fused using the Kalman filter algorithm. The optimal values ​​of the environmental parameters are estimated by establishing a state space model.

[0018] Furthermore, based on the preset cleanliness threshold and the air volume requirements of medical operations, combined with environmental parameter data, the target air volume range under the current working conditions is determined, specifically including:

[0019] Obtain the preset cleanliness threshold and air volume requirements for medical operations, and obtain parameter data of the current environment;

[0020] Based on the cleanliness threshold, air volume demand and environmental parameter data, an air volume prediction model is established, and the support vector machine algorithm is used to train the air volume prediction model to obtain the trained air volume prediction model;

[0021] Input the current environmental parameter data into the trained air volume prediction model to predict the target air volume under the current working conditions. Then determine whether the predicted target air volume is within the air volume requirement range of the medical operation. If it is, it is determined as the final target air volume. If not, the air volume prediction model is adjusted and re-predicted.

[0022] The determined target air volume range is output to control the air conditioning system to adjust the air volume.

[0023] Furthermore, an intelligent algorithm is used to analyze the changing trends of environmental parameters, predict the air volume demand in the future, and pre-adjust the fan speed to match the predicted demand. This includes: obtaining historical data of environmental parameters over a period of time, using a time series analysis algorithm to model and predict the changing trends of environmental parameters, and obtaining the predicted values ​​of each parameter in the future;

[0024] According to the predicted environmental parameter values, combined with the pre-established air volume demand model, the predicted air volume demand value in the future period is calculated and compared with the current fan speed.

[0025] When the predicted demand is greater than the air volume corresponding to the current speed, the fan speed is increased to a level that meets the predicted demand; when the predicted demand is less than the air volume corresponding to the current speed, the fan speed is reduced to a level that matches the predicted demand;

[0026] After adjusting the fan speed, the difference between the actual air volume and the predicted demand is continuously monitored. When the difference exceeds the preset threshold, the prediction model is updated and the fan speed is adjusted again.

[0027] The historical data of fan speed adjustment is fed back to the prediction model, and the model parameters are continuously optimized using incremental learning algorithms such as online learning or reinforcement learning.

[0028] Furthermore, energy consumption and noise data are monitored in real time. When energy consumption exceeds a preset threshold or noise exceeds an allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements. Specifically, the following steps are performed:

[0029] Obtain the preset energy consumption threshold and noise tolerance range data, and during the speed regulation process, collect the energy consumption data and noise data of the equipment in real time and compare them with the preset threshold and tolerance range;

[0030] When the real-time collected energy consumption data exceeds the preset threshold, it is determined that the energy consumption exceeds the standard; when the real-time collected noise data exceeds the allowable range, it is determined that the noise exceeds the standard;

[0031] Based on the results of energy consumption and noise, determine whether the equipment speed needs to be adjusted. If energy consumption or noise exceeds the standard, the speed needs to be adjusted.

[0032] When adjusting the speed, a correlation model between the speed and cleanliness is established through a machine learning algorithm to obtain the corresponding minimum speed value while meeting the cleanliness requirements. The actual speed of the equipment is adjusted to the minimum speed value obtained according to the machine learning algorithm.

[0033] Furthermore, based on historical data and real-time monitoring results, the parameter settings of the intelligent algorithm are optimized to improve the accuracy and response speed of speed control, including:

[0034] Obtain historical monitoring data and real-time monitoring data as input data for intelligent algorithms, pre-process the input data, and use machine learning algorithms such as support vector machines or neural networks to establish a speed control model based on the pre-processed data;

[0035] In the established speed control model, relevant parameters are set, and the model performance is improved through parameter optimization. The optimized speed control model is deployed in the actual system, and speed control is performed based on real-time monitoring data.

[0036] During the speed control process, operating data is continuously collected and used as new training data. The model is retrained and optimized regularly. By continuously iterating and optimizing the speed control model, the control accuracy and response speed are continuously improved, and intelligent speed control is performed.

[0037] It also includes: continuously monitoring the environmental parameters and fan operating status of the clean room through multi-sensor fusion technology. When abnormal fluctuations are detected, an alarm is triggered and the fan speed is automatically adjusted. The speed control system is then regularly tested for stability to ensure that the adjustment accuracy and response time of the fan speed under different working conditions meet the preset requirements.

[0038] Furthermore, multi-sensor fusion technology is used to continuously monitor the environmental parameters of the clean room and the operating status of the fan, including:

[0039] Preprocessing and feature extraction are performed based on the acquired environmental parameters and operating status data such as fan speed and current;

[0040] The extracted feature vector is input into a pre-trained support vector machine model to determine whether the current clean room environmental parameters and fan operating status are within the normal range. If abnormal fluctuations are detected, an alarm is triggered.

[0041] According to the degree of abnormal fluctuation of environmental parameters and the deviation of fan operating status, the adjustment amount of fan speed is calculated through fuzzy control algorithm, and the adjustment instruction is sent to the inverter to automatically adjust the fan speed;

[0042] After the fan speed adjustment is completed, the feedback data of the speed control system is filtered through the Kalman filter algorithm to determine whether the speed control system is stable. If the stability does not meet the preset requirements, the speed is fine-tuned until a stable state is reached.

[0043] Then, regularly conduct stability tests on the speed control system. By setting step changes in the fan speed under different working conditions, collect the response data of the speed control system, calculate the speed control accuracy and response time indicators, and determine whether it meets the preset performance requirements;

[0044] When the stability test result fails, the rule base and membership function of the fuzzy controller are optimized online through the incremental learning algorithm;

[0045] The optimized fuzzy controller parameters are written into the non-volatile memory of the fan controller for persistent storage of the speed regulation algorithm.

[0046] A low-energy consumption control device for a large centrifugal fan comprises a processor, a memory and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the low-energy consumption control method for the large centrifugal fan is implemented.

[0047] A storage medium stores computer program instructions, which, when executed by a processor, implement the low-energy consumption control method for a large centrifugal fan described above.

[0048] The beneficial effects of the present invention are:

[0049] Multi-sensor fusion technology is used to collect real-time data on environmental parameters such as temperature, humidity, pressure, and cleanliness in the cleanroom. This data is then transmitted to the data processing module. A support vector machine algorithm is used to establish an air volume prediction model to determine the target air volume range under the current operating conditions. This allows the air conditioning system to accurately control the air volume to meet the cleanliness requirements of medical operations. This allows the fan to flexibly adapt to changes in environmental parameters in the cleanroom, solving the problem of traditional fans being unable to adjust air volume according to real-time environmental changes.

[0050] During the speed regulation process, energy consumption and noise data are monitored in real time. When energy consumption exceeds the preset threshold or noise exceeds the allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements through the fuzzy control algorithm. At the same time, the parameter settings of the intelligent algorithm are optimized based on historical data and real-time monitoring results, further improving the accuracy and response speed of speed regulation control, reducing unnecessary energy waste, and effectively solving the problems of high energy consumption and low efficiency of traditional fans.

[0051] Through multi-sensor fusion technology, the environmental parameters of the clean room and the operating status of the fan are continuously monitored. When abnormal fluctuations are detected, an alarm is triggered and the fan speed is automatically adjusted to ensure that the fan can operate stably under various working conditions. The speed control system is then regularly tested for stability, and the incremental learning algorithm is used to perform online optimization of the fuzzy controller's rule base and membership function to improve the robustness and adaptability of the speed control system, avoid the loss of control strategy due to sudden failures, and improve fault tolerance and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0053] Figure 1 A schematic flow chart of a low energy consumption control method for a large centrifugal fan provided in this application;

[0054] Figure 2 A schematic flow chart of a low-energy consumption control method for a large centrifugal fan provided in this application for determining a target air volume range under current operating conditions;

[0055] Figure 3 A low-energy consumption control method for a large centrifugal fan provided in this application is a flow chart showing a method of determining a speed adjustment range using a fuzzy control algorithm. DETAILED DESCRIPTION

[0056] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present application. Rather, they are merely examples of methods and systems consistent with certain aspects of the present application, as detailed in the appended claims.

[0057] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0058] The following describes in detail the specific implementation methods, features and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0059] See also Figure 1-Figure 3This embodiment provides a low energy consumption control method for a large centrifugal fan, comprising the following steps:

[0060] S1. Obtain environmental parameter data in the clean room, including temperature, humidity, pressure, and cleanliness. This data is collected in real time through multi-sensor fusion technology and transmitted to the data processing module. The target air volume range under the current working conditions is then determined in combination with the environmental parameter data based on the preset cleanliness threshold and the air volume requirements of the medical operation. This is used to control the air volume of the air conditioning system to meet the cleanliness requirements of medical operations.

[0061] Furthermore, the environmental parameter data in the clean room, including temperature, humidity, pressure and cleanliness, is acquired in real time through multi-sensor fusion technology and transmitted to the data processing module, specifically including:

[0062] Based on the environmental parameter monitoring requirements of the clean room, temperature, humidity, pressure and cleanliness sensors are rationally arranged at different locations within the clean room. Real-time data on environmental parameters such as temperature, humidity, pressure and cleanliness within the clean room are collected through multiple sensors, and the sampling frequency is set according to actual needs.

[0063] The environmental parameter data collected by multiple sensors are transmitted to the data processing module via wired or wireless means. Data encryption and error checking are used during the transmission process to ensure the security and integrity of the data.

[0064] In the data processing module, the received multi-sensor data is pre-processed, including data cleaning, denoising, normalization and other operations to improve data quality. The Kalman filter algorithm is used to fuse the multi-sensor data. By establishing a state space model, the optimal value of the environmental parameters is estimated to improve measurement accuracy and reliability.

[0065] Furthermore, step S1 further includes steps S11, S12, S13, and S14, wherein the target air volume range under the current working conditions is determined based on the preset cleanliness threshold and the air volume requirement of the medical operation in combination with the environmental parameter data, specifically including:

[0066] S11. Obtaining the preset cleanliness threshold and air volume requirements for medical operations, and obtaining parameter data of the current environment, including temperature, humidity, pressure, etc.;

[0067] S12. Establish an air volume prediction model based on the cleanliness threshold, air volume demand, and environmental parameter data, and train the air volume prediction model using a support vector machine algorithm to obtain a trained air volume prediction model;

[0068] S13. Inputting the current environmental parameter data into the trained air volume prediction model to predict the target air volume under the current working conditions, and determining whether the predicted target air volume is within the air volume requirement range for medical operations. If so, determining it as the final target air volume; if not, adjusting the air volume prediction model and re-predicting;

[0069] S14. Outputting the determined target air volume range to control the air conditioning system to adjust the air volume to meet the cleanliness requirements of medical operations.

[0070] Specifically, multi-sensor fusion technology is used to collect environmental parameter data such as temperature, humidity, pressure and cleanliness in the clean room in real time, and transmit them to the data processing module for preprocessing and fusion, so as to solve the problem of incomplete and inaccurate data collection; according to the preset cleanliness threshold and the air volume requirements of medical operations, combined with environmental parameter data, the air volume prediction model (trained using the support vector machine algorithm) is used to determine the target air volume range under the current working conditions, solving the problem that traditional methods cannot flexibly adjust the air volume according to real-time environmental changes; thereby accurately controlling the air conditioning system to adjust the air volume, meet the cleanliness requirements of medical operations, provide stable and clean environmental support for medical operations, and improve the safety and reliability of medical operations.

[0071] S2. Use frequency conversion technology to adjust the speed of the centrifugal fan. By calculating the difference between the target air volume and the current air volume, the speed adjustment range is determined using a fuzzy control algorithm. When the target air volume is higher than the current air volume, the speed is increased; when the target air volume is lower than the current air volume, the speed is reduced.

[0072] Furthermore, step S2 further includes steps S21, S22, S23, and S24, wherein S21, obtaining the target air volume and the current air volume of the centrifugal fan, calculating the difference between the target air volume and the current air volume to obtain an air volume difference value, and determining whether the air volume difference value is positive or negative. When the air volume difference value is positive, it indicates that the target air volume is higher than the current air volume, and the fan speed needs to be increased;

[0073] S22. When the air volume difference value is negative, it indicates that the target air volume is lower than the current air volume and the fan speed needs to be reduced. Based on the size of the air volume difference value, a fuzzy control algorithm is used to determine the adjustment range of the fan speed and obtain the speed adjustment value.

[0074] S23, inputting the speed adjustment value into the frequency converter, and adjusting the actual speed of the fan through frequency conversion technology so that it gradually approaches the target speed;

[0075] S24. In the process of adjusting the fan speed, the current air volume of the fan is obtained in real time, which is used as feedback and compared with the target air volume to form a closed-loop control.

[0076] Specifically, frequency conversion technology is used to adjust the speed of the centrifugal fan. By calculating the difference between the target air volume and the current air volume, the speed adjustment range is determined using a fuzzy control algorithm, and the fan speed is accurately adjusted to gradually approach the target speed. At the same time, the current air volume of the fan is obtained in real time as feedback and compared with the target air volume to form a closed-loop control, thereby achieving precise adjustment of the fan air volume, meeting the air volume requirements of the clean room, and improving the operating efficiency and energy-saving effect of the fan.

[0077] S3: Analyze the changing trends of environmental parameters through intelligent algorithms, predict the air volume demand in the future, and adjust the fan speed in advance to match the predicted demand;

[0078] Furthermore, step S3 also includes: acquiring historical data of environmental parameters over a period of time, including temperature, humidity, air pressure, etc., and using a time series analysis algorithm, such as an ARIMA model or an LSTM neural network, to model and predict the changing trends of the environmental parameters, thereby obtaining predicted values ​​of each parameter over a period of time in the future;

[0079] According to the predicted environmental parameter values, combined with the pre-established air volume demand model, the predicted air volume demand value in the future period is calculated and compared with the current fan speed.

[0080] When the predicted demand is greater than the air volume corresponding to the current speed, the fan speed is increased to a level that meets the predicted demand; when the predicted demand is less than the air volume corresponding to the current speed, the fan speed is reduced to a level that matches the predicted demand;

[0081] After adjusting the fan speed, the difference between the actual air volume and the predicted demand is continuously monitored. When the difference exceeds the preset threshold, the prediction model is updated and the fan speed is adjusted again.

[0082] The historical data of fan speed adjustment is fed back to the prediction model, and incremental learning algorithms such as online learning or reinforcement learning are used to continuously optimize the model parameters to improve prediction accuracy and control effect.

[0083] Specifically, by analyzing historical data of environmental parameters through intelligent algorithms, and using time series analysis algorithms (such as ARIMA models or LSTM neural networks) to predict air volume demand in the future, the fan speed is adjusted in advance to match the predicted demand, thereby achieving active and precise adjustment of the fan, adapting to environmental changes in advance, reducing energy waste and environmental instability caused by lagging adjustment, and improving the operating efficiency of the fan and the environmental stability of the clean room.

[0084] S4. During the speed regulation process, energy consumption and noise data are monitored in real time. When energy consumption exceeds the preset threshold or noise exceeds the allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements. Based on historical data and real-time monitoring results, the parameter settings of the intelligent algorithm are optimized to improve the accuracy and response speed of speed regulation control.

[0085] Furthermore, in step S4, energy consumption and noise data are monitored in real time. When energy consumption exceeds a preset threshold or noise exceeds an allowable range, the rotation speed is adjusted to the minimum value that meets the cleanliness requirements, specifically including:

[0086] Obtain the preset energy consumption threshold and noise tolerance range data, and during the speed regulation process, collect the energy consumption data and noise data of the equipment in real time and compare them with the preset threshold and tolerance range;

[0087] When the real-time collected energy consumption data exceeds the preset threshold, it is determined that the energy consumption exceeds the standard; when the real-time collected noise data exceeds the allowable range, it is determined that the noise exceeds the standard;

[0088] Based on the results of energy consumption and noise, determine whether the equipment speed needs to be adjusted. If energy consumption or noise exceeds the standard, the speed needs to be adjusted.

[0089] When adjusting the speed, a correlation model between the speed and cleanliness is established through machine learning algorithms, such as decision trees or support vector machines, to obtain the corresponding minimum speed value while meeting the cleanliness requirements. The actual speed of the equipment is adjusted to the minimum speed value obtained according to the machine learning algorithm to reduce energy consumption and noise while ensuring that the cleanliness requirements are met.

[0090] Specifically, during the speed regulation process, by real-time monitoring of energy consumption and noise data, when energy consumption exceeds the preset threshold or noise exceeds the allowable range, a machine learning algorithm is used to establish a correlation model between speed and cleanliness, and the speed is adjusted to the minimum value that meets the cleanliness requirements, effectively reducing energy consumption and noise. At the same time, the parameter settings of the intelligent algorithm are optimized based on historical data and real-time monitoring results, improving the accuracy and response speed of speed regulation control, and ensuring that the fan achieves efficient, energy-saving and low-noise operation while meeting the cleanliness requirements.

[0091] Furthermore, in step S4, based on historical data and real-time monitoring results, the parameter settings of the intelligent algorithm are optimized to improve the accuracy and response speed of the speed control, specifically including:

[0092] Obtain historical monitoring data and real-time monitoring data as input data for intelligent algorithms, pre-process the input data, and use machine learning algorithms such as support vector machines or neural networks to establish a speed control model based on the pre-processed data;

[0093] In the established speed control model, relevant parameters such as learning rate and regularization coefficient are set to improve model performance through parameter optimization. The optimized speed control model is deployed in the actual system and speed control is performed based on real-time monitoring data.

[0094] During the speed control process, operating data is continuously collected and used as new training data. The model is retrained and optimized regularly. By continuously iterating and optimizing the speed control model, the control accuracy and response speed are continuously improved to achieve intelligent speed control.

[0095] Specifically, by obtaining historical monitoring data and real-time monitoring data, using them as input data for intelligent algorithms, and preprocessing them, a speed control model is established using a machine learning algorithm. Relevant parameters are set in the model for optimization and deployed to the actual system for speed control. At the same time, operating data is continuously collected as new training data, and the model is retrained and optimized regularly. This solves the problems of low precision and slow response speed of traditional speed control methods, realizes intelligent speed control, and continuously improves the precision and response speed of speed control, enabling the fan to adapt to environmental changes and air volume requirements more accurately and quickly, thereby improving the operating efficiency and energy-saving effect of the fan, and ensuring the environmental stability of the clean room and the safety of medical operations.

[0096] S5. Continuously monitor the environmental parameters and fan operating status of the clean room through multi-sensor fusion technology. When abnormal fluctuations are detected, an alarm is triggered and the fan speed is automatically adjusted. The speed control system is then regularly tested for stability to ensure that the adjustment accuracy and response time of the fan speed meet the preset requirements under different working conditions.

[0097] Furthermore, step S5 further includes: performing preprocessing and feature extraction based on the acquired environmental parameters and the operating status data such as the speed and current of the fan;

[0098] The extracted feature vector is input into a pre-trained support vector machine model to determine whether the current clean room environmental parameters and fan operating status are within the normal range. If abnormal fluctuations are detected, an alarm is triggered.

[0099] According to the degree of abnormal fluctuation of environmental parameters and the deviation of fan operating status, the adjustment amount of fan speed is calculated through fuzzy control algorithm, and the adjustment instruction is sent to the inverter to realize automatic adjustment of fan speed;

[0100] After the fan speed adjustment is completed, the feedback data of the speed control system is filtered through the Kalman filter algorithm to determine whether the speed control system is stable. If the stability does not meet the preset requirements, the speed will continue to be fine-tuned until a stable state is reached.

[0101] Regularly test the stability of the speed control system by setting step changes in fan speed under different operating conditions, collecting response data of the speed control system, and calculating indicators such as speed control accuracy and response time to determine whether it meets the preset performance requirements;

[0102] If the stability test result fails, the fuzzy controller's rule base and membership function are optimized online through incremental learning algorithms to improve the robustness and adaptability of the speed control system and ensure long-term stable operation.

[0103] The optimized fuzzy controller parameters are written into the non-volatile memory of the fan controller to achieve persistent storage of the speed regulation algorithm, avoid the loss of control strategy due to sudden failures, and improve the fault tolerance and reliability of the system.

[0104] Specifically, multi-sensor fusion technology continuously monitors cleanroom environmental parameters (such as temperature, humidity, and pressure differential) and fan operating status (such as speed and current), addressing the inability of traditional monitoring methods to comprehensively and accurately obtain information about the cleanroom environment and fan status. When abnormal fluctuations are detected, a pre-trained support vector machine model is used to determine whether the current status is normal, triggering an alarm and promptly alerting operators to avoid potential risks. A fuzzy control algorithm automatically calculates the fan speed adjustment based on the degree of abnormal fluctuation and the deviation of the fan status, and issues adjustment instructions to the inverter, achieving rapid and precise adjustment of the fan speed. This solves the problem of slow response and low accuracy of manual adjustment, enabling the fan to promptly adapt to environmental changes and maintain a stable cleanroom environment. Regular stability tests are performed on the speed control system. By setting step changes in fan speed, collecting response data, and calculating indicators such as speed control accuracy and response time, the system's performance is determined to be up to standard. This addresses the potential performance degradation that may occur with long-term operation of the speed control system. If the test results are unsatisfactory, an incremental learning algorithm is used to optimize the fuzzy controller's rule base and membership function online, improving the robustness and adaptability of the speed control system and ensuring long-term stable operation. The optimized fuzzy controller parameters are written to the fan controller's non-volatile memory, enabling persistent storage of the speed control algorithm. This prevents loss of control strategy due to sudden failures, improves the system's fault tolerance and reliability, ensures the continued stability of the cleanroom environment and fan operation, and provides a solid foundation for medical operations.

[0105] This embodiment uses multi-sensor fusion technology to monitor clean room environmental parameters and fan operating status in real time, and combines intelligent algorithms and frequency conversion technology to achieve precise, efficient, and energy-saving speed control of centrifugal fans. It can dynamically adjust the fan speed according to the actual air volume demand and environmental change trends in the clean room to meet the cleanliness requirements of medical operations, while reducing energy consumption and noise, ensuring the stability of the clean room environment, and improving the safety and reliability of medical operations. Through continuous optimization and stability testing, the long-term stable operation and control accuracy of the speed control system are ensured, solving the problems of traditional fan control methods that cannot flexibly adapt to changes in clean room operating conditions and are prone to energy waste and environmental instability.

[0106] A low-energy consumption control device for a large centrifugal fan comprises a processor, a memory and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the low-energy consumption control method for the large centrifugal fan is implemented.

[0107] A storage medium stores computer program instructions, which, when executed by a processor, implement the low-energy consumption control method for a large centrifugal fan described above.

[0108] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A low energy consumption control method for a large centrifugal fan, characterized by: The steps include: Acquire environmental parameter data within the cleanroom, including temperature, humidity, pressure, and cleanliness. This data is collected in real time through multi-sensor fusion technology and transmitted to the data processing module. The module then determines the target air volume range under the current operating conditions based on the preset cleanliness threshold and the air volume requirements for medical operations, combined with the environmental parameter data. Used to control the air conditioning system to adjust the air volume; The controlling of the air conditioning system to adjust the air volume specifically includes: Obtain the preset cleanliness threshold and air volume requirements for medical operations, and obtain parameter data of the current environment; Based on the cleanliness threshold, air volume demand and environmental parameter data, an air volume prediction model is established, and the support vector machine algorithm is used to train the air volume prediction model to obtain the trained air volume prediction model; Input the current environmental parameter data into the trained air volume prediction model to predict the target air volume under the current working conditions. Then determine whether the predicted target air volume is within the air volume requirement range of the medical operation. If it is, it is determined as the final target air volume. If not, adjust the air volume prediction model and re-predict; Output the determined target air volume range to control the air volume of the air conditioning system; Analyze the changing trends of environmental parameters through intelligent algorithms, predict the air volume demand in the future, and adjust the fan speed in advance to match the predicted demand; During the speed regulation process, energy consumption and noise data are monitored in real time. When energy consumption exceeds the preset threshold or noise exceeds the allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements. The parameter settings of the intelligent algorithm are then optimized based on historical data and real-time monitoring results. The system continuously monitors the cleanroom's environmental parameters and fan operating status through multi-sensor fusion technology. When abnormal fluctuations are detected, an alarm is triggered and the fan speed is automatically adjusted. The system then regularly performs stability tests on the speed control system to ensure that the fan speed adjustment accuracy and response time meet preset requirements under different operating conditions. These include: pre-processing and feature extraction based on the acquired environmental parameters and the speed and current operating status data of the fan; The extracted feature vector is input into a pre-trained support vector machine model to determine whether the current clean room environmental parameters and fan operating status are within the normal range. If abnormal fluctuations are detected, an alarm is triggered. According to the degree of abnormal fluctuation of environmental parameters and the deviation of fan operating status, the adjustment amount of fan speed is calculated through fuzzy control algorithm, and the adjustment instruction is sent to the inverter to automatically adjust the fan speed; After the fan speed adjustment is completed, the feedback data of the speed control system is filtered through the Kalman filter algorithm to determine whether the speed control system is stable. If the stability does not meet the preset requirements, the speed is fine-tuned until a stable state is reached. Then, regularly conduct stability tests on the speed control system. By setting step changes in the fan speed under different working conditions, collect the response data of the speed control system, calculate the speed control accuracy and response time indicators, and determine whether it meets the preset performance requirements; When the stability test result fails, the rule base and membership function of the fuzzy controller are optimized online through the incremental learning algorithm; The optimized fuzzy controller parameters are written into the non-volatile memory of the fan controller to store the speed regulation algorithm.

2. The low energy consumption control method for a large centrifugal fan according to claim 1, characterized in that: Acquire environmental parameter data within the cleanroom, including temperature, humidity, pressure, and cleanliness, and collect and transmit them to the data processing module in real time through multi-sensor fusion technology. Specifically, it includes: Based on the environmental parameter monitoring requirements of the clean room, temperature, humidity, pressure and cleanliness sensors are rationally arranged at different locations within the clean room. The environmental parameter data within the clean room is collected in real time through multiple sensors, and the sampling frequency is set according to actual needs; The environmental parameter data collected by multiple sensors are transmitted to the data processing module via wired or wireless means; In the data processing module, the received multi-sensor data is preprocessed and fused using the Kalman filter algorithm. The optimal values ​​of the environmental parameters are obtained by establishing a state space model.

3. The low energy consumption control method for a large centrifugal fan according to claim 1, characterized in that: Analyze the changing trends of environmental parameters through intelligent algorithms, predict the air volume demand in the future, and pre-adjust the fan speed to match the predicted demand. This includes: obtaining historical data of environmental parameters over a period of time, using time series analysis algorithms to model and predict the changing trends of environmental parameters, and obtaining the predicted values ​​of each parameter in the future; According to the predicted environmental parameter values, combined with the pre-established air volume demand model, the predicted air volume demand value in the future period is calculated and compared with the current fan speed. When the predicted demand is greater than the air volume corresponding to the current speed, the fan speed is increased to a level that meets the predicted demand; when the predicted demand is less than the air volume corresponding to the current speed, the fan speed is reduced to a level that matches the predicted demand; After adjusting the fan speed, the difference between the actual air volume and the predicted demand is continuously monitored. When the difference exceeds the preset threshold, the air volume prediction model is updated and the fan speed is adjusted again. The historical data of fan speed adjustment is fed back to the air volume prediction model, and the model parameters are continuously optimized using incremental learning algorithms such as online learning or reinforcement learning.

4. The low energy consumption control method for a large centrifugal fan according to claim 1, characterized in that: Real-time monitoring of energy consumption and noise data. When energy consumption exceeds a preset threshold or noise exceeds the allowable range, the speed is adjusted to the minimum value that meets the cleanliness requirements. Specifically, the following are included: Obtain the preset energy consumption threshold and noise tolerance range data, and during the speed regulation process, collect the energy consumption data and noise data of the equipment in real time and compare them with the preset threshold and tolerance range; When the real-time collected energy consumption data exceeds the preset threshold, it is determined that the energy consumption exceeds the standard; when the real-time collected noise data exceeds the allowable range, it is determined that the noise exceeds the standard; Based on the results of energy consumption and noise, determine whether the equipment speed needs to be adjusted. If energy consumption or noise exceeds the standard, the speed needs to be adjusted. When adjusting the speed, a correlation model between the speed and cleanliness is established through a machine learning algorithm to obtain the corresponding minimum speed value while meeting the cleanliness requirements. The actual speed of the equipment is adjusted to the minimum speed value obtained according to the machine learning algorithm.

5. The low energy consumption control method for a large centrifugal fan according to claim 1, characterized in that: Based on historical data and real-time monitoring results, optimize the parameter settings of the intelligent algorithm, including: Obtain historical monitoring data and real-time monitoring data as input data for intelligent algorithms, pre-process the input data, and use machine learning algorithms such as support vector machines or neural networks to establish a speed control model based on the pre-processed data; In the established speed control model, relevant parameters are set, and the model performance is improved through parameter optimization. The optimized speed control model is deployed in the actual system, and speed control is performed based on real-time monitoring data. During the speed control process, operating data is continuously collected and used as new training data. The model is retrained and optimized regularly. By continuously iterating and optimizing the speed control model, the control accuracy and response speed are continuously improved, and intelligent speed control is performed.

6. The low energy consumption control method for a large centrifugal fan according to claim 1, characterized in that: Frequency conversion technology is used to adjust the speed of the centrifugal fan. By calculating the difference between the target air volume and the current air volume, the speed adjustment range is determined using a fuzzy control algorithm. When the target air volume is higher than the current air volume, the speed is increased; when the target air volume is lower than the current air volume, the speed is reduced. The target air volume and current air volume of the centrifugal fan are obtained, and the difference between the target air volume and the current air volume is calculated to obtain the air volume difference value. The positive or negative sign of the air volume difference value is determined. If the air volume difference value is positive, it means that the target air volume is higher than the current air volume, and the fan speed needs to be increased. When the air volume difference value is negative, it means that the target air volume is lower than the current air volume, and the fan speed needs to be reduced. According to the size of the air volume difference value, the fuzzy control algorithm is used to determine the adjustment range of the fan speed and obtain the speed adjustment value. The speed adjustment value is input into the frequency converter, and the actual speed of the fan is adjusted through frequency conversion technology to gradually approach the target speed; In the process of adjusting the fan speed, the current air volume of the fan is obtained in real time, which is used as feedback and compared with the target air volume to form a closed-loop control.

7. A low energy consumption control device for a large centrifugal fan, characterized in that: The invention comprises a processor, a memory and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, a low energy consumption control method for a large centrifugal fan as described in any one of claims 1 to 6 is implemented.

8. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by the processor, the low energy consumption control method for a large centrifugal fan described in any one of claims 1 to 6 is implemented.

Images