Water-cooling machine environmental adaptability intelligent adjustment system
By introducing environmental perception, data processing and intelligent adjustment modules into the water-cooling machine system, combining fault prediction and self-healing mechanisms, the problem of insufficient flexibility and fault handling capabilities of traditional water-cooling machine systems is solved, and efficient energy saving and stable operation are achieved, improving The reliability and environmental performance of the system are achieved.
Patent Information
- Application Number
- CN202410990793.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-23
AI Technical Summary
Traditional water-cooling systems lack flexibility and adaptability, and cannot respond to environmental changes and system operating status changes in real time, resulting in limited operating efficiency and reliability, slow fault detection and processing speed, which can easily cause equipment downtime and production interruption.
A water-cooling machine environmental adaptability intelligent regulation system is designed, including environmental perception module, data processing module, cooling demand prediction module, intelligent regulation module, actuator module and fault prediction and self-healing module. By monitoring environmental data in real time, analyzing and Predict cooling requirements, calculate the best operating instructions, adjust the operating parameters of the water pump and cooling equipment, and use machine learning algorithms to predict failures to achieve automatic adjustment and self-healing mechanisms.
It improves the operating efficiency and reliability of the water-cooling machine system, realizes dynamic response to environmental changes, reduces energy waste, timely prevents and deals with faults, reduces downtime and maintenance costs, and complies with the requirements of green environmental protection and sustainable development.
Smart Images

Figure CN118517777B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of fire safety, and in particular to an intelligent regulating system for environmental adaptability of a water chiller. Background Art
[0002] Water chillers play a vital role in many industrial and commercial applications, especially in data centers, manufacturing and large building facilities. Traditional water chiller systems usually rely on fixed operating parameters and manual adjustments, mainly controlling the operating status of water pumps, fans and cooling equipment to achieve cooling effects.
[0003] Existing water chiller systems usually lack flexibility and adaptability, and cannot respond to environmental changes and changes in system operating status in real time. Therefore, under various complex and changeable environmental conditions, the operating efficiency and reliability of traditional water chiller systems are often limited, making it difficult to achieve optimal energy saving and efficient operation. In addition, fault detection and handling methods mainly rely on manual inspection and manual intervention, with slow response speed, and cannot prevent and handle system failures in a timely manner, which easily causes equipment downtime and production interruption. Summary of the invention
[0004] Based on the above purpose, the present invention provides an intelligent adjustment system for environmental adaptability of a water chiller.
[0005] The environmental adaptability intelligent regulation system of the water chiller includes an environmental perception module, a data processing module, a cooling demand prediction module, an intelligent regulation module, an actuator module and a fault prediction and self-healing module, wherein;
[0006] The environmental perception module is responsible for real-time monitoring of environmental data, including temperature, humidity and air quality, and transmitting the environmental data to the data processing module;
[0007] The data processing module analyzes and processes the received environmental data, and outputs corresponding cooling demand parameters to the cooling demand prediction module according to a preset algorithm model;
[0008] The cooling demand prediction module predicts the optimal cooling strategy based on the data from the data processing module and the historical cooling effect data, and transmits it to the intelligent adjustment module;
[0009] The intelligent adjustment module receives the strategy from the cooling demand prediction module and calculates the best operating instructions, including the flow rate, temperature and start and stop time of the cooling water, and then instructs the actuator module to make corresponding adjustments;
[0010] The actuator module adjusts the operating parameters of the water chiller, including the speed of the water pump and the switch of the cooling device, according to the instructions of the intelligent adjustment module to achieve a predetermined cooling effect;
[0011] The fault prediction and self-healing module analyzes the real-time data of the environmental perception module and the data processing module, uses a machine learning algorithm to predict the faults that will occur, and provides early warning and processing before the faults occur. When a fault occurs, the self-healing mechanism is activated to ensure the continuous operation of the cooling device by automatically adjusting the cooling parameters or switching to a spare cooling unit.
[0012] Furthermore, the environment perception module specifically includes:
[0013] Temperature sensor: used to monitor ambient temperature, measure and output temperature data;
[0014] Humidity sensor: used to monitor environmental humidity, measure and output humidity data;
[0015] Air quality sensor: used to monitor ambient air quality, including PM2.5 and CO2 parameters, measure and output air quality data.
[0016] Furthermore, the data processing module specifically includes:
[0017] Data reception: Receive environmental data from the environmental perception module, including temperature, humidity and air quality;
[0018] Data storage unit: The received environmental data is stored in the data storage unit, including real-time environmental data and historical environmental data;
[0019] Algorithm processing: Analyze and process environmental data according to the preset algorithm model;
[0020] Cooling demand parameter generation: After analysis and processing, the algorithm processing unit generates corresponding cooling demand parameters, which include cooling water flow rate, temperature set point, and fan speed.
[0021] Furthermore, the algorithm processing specifically includes:
[0022] Temperature analysis model: The temperature analysis model predicts cooling demand based on the changing trend of current temperature and historical temperature data. Celsius, historical temperature data is , calculated as:
[0023] ;
[0024] in, For temperature requirements, To set the temperature, and is the model coefficient, is the temperature change rate, ,in, is the ambient temperature at the current time point, is the ambient temperature data at a certain point in history. is the current time point, at which the system collects the current temperature , is a historical time point, corresponding to The time point indicates the collection time of historical temperature data;
[0025] Humidity analysis model: The humidity analysis model predicts cooling demand based on the changing trend of current humidity and historical humidity data. , the historical humidity data is , calculated as:
[0026] ;
[0027] in, For humidity requirements, To set the humidity, and is the model coefficient, is the humidity change rate, , is the ambient humidity at the current time point, is the environmental humidity data at a certain point in history. The current time point, indicating that the system records the current humidity time, It is a historical time point, indicating that the system records historical humidity time;
[0028] Air quality analysis model: The air quality analysis model predicts cooling demand based on the changing trend of current air quality and historical air quality data. Suppose the current air quality index is , the historical air quality data is , calculated as:
[0029] ;
[0030] in, To meet air quality requirements, To set the air quality index, and is the model coefficient, is the air quality change rate, , is the air quality index at the current time point, is the air quality index at a certain point in history, The current time point, indicating the collection of current air quality time, It is a historical time point, indicating the record of historical air quality data Time
[0031] Comprehensive analysis model: The comprehensive analysis model combines the requirements of temperature, humidity and air quality to generate the final cooling demand parameter, calculated as: ;
[0032] in, For the final cooling requirement, , and is the weight coefficient of each demand.
[0033] Furthermore, the cooling demand prediction module specifically includes:
[0034] Data receiving: receiving cooling demand parameters output by the data processing module;
[0035] Historical data storage unit: stores historical cooling demand data and environmental data;
[0036] Prediction algorithm processing unit: The prediction algorithm processing unit uses the simple moving average method to process historical cooling demand data and predict future cooling demand parameters. , obtain the most recent cooling demand data through historical cooling demand data Cooling demand data at each time point , this Add the cooling demand data at each time point and divide by , get the predicted cooling demand parameters , calculated as: ;in, is the size of the moving window, For before The cooling demand value at a point in time.
[0037] Furthermore, the calculation of the optimal operation instruction specifically includes:
[0038] Receive forecast data: The intelligent adjustment module receives the forecasted cooling demand parameters from the cooling demand forecast module ;
[0039] Cooling water flow rate Calculated as: ,in, is the cooling water flow rate, and is the empirical coefficient;
[0040] Temperature set point Calculated as: ,in, is the temperature set point, is the reference temperature, is the adjustment coefficient;
[0041] Fan speed Calculated as: ,in, is the fan speed, and is the empirical coefficient;
[0042] Start and stop time: Determine the start and stop time of the cooling equipment according to the cooling demand parameters and the operating status of the equipment. Exceeding the start threshold , then set the device startup time is the current time, Below stop threshold , then set the device stop time is the current time.
[0043] Furthermore, the actuator module specifically includes:
[0044] Receive operation instructions: The actuator module receives the operation instructions of the intelligent adjustment module, including , , , and ;
[0045] Adjust the pump speed: according to Instructions to increase or decrease the speed of the pump to match the flow rate in the instruction;
[0046] Set temperature: According to Instructions to adjust the temperature set point of the cooling equipment so that the temperature set point reaches ;
[0047] Adjust fan speed: according to Instructions to increase or decrease the speed of the fan to match the speed in the instruction;
[0048] Start-Stop Control: At this time, start the cooling equipment. At this point in time, stop cooling the equipment;
[0049] Feedback control: Real-time monitoring of adjusted parameters to ensure that the actual operating parameters are consistent with the parameters in the instructions.
[0050] Furthermore, the fault prediction and self-healing module specifically includes:
[0051] Data reception: Collect equipment operation data from the environment perception module, data processing module, intelligent adjustment module and actuator module. The equipment operation data includes temperature, humidity, cooling water flow rate, temperature set point, fan speed, equipment start and stop status, water pump operation status and cooling equipment switch status;
[0052] Data preprocessing: cleaning and standardizing the received data, including removing noise data, processing missing values, and performing data standardization;
[0053] Feature extraction: Extract the features required for fault prediction from the preprocessed data, including temperature, humidity, air quality, and equipment operating status;
[0054] Fault prediction: Use the random forest model to analyze the extracted features and predict the faults that may occur.
[0055] Furthermore, the fault prediction specifically includes:
[0056] Dataset construction: Use historical data to build training sets and test sets. The training set is used to train the random forest model, and the test set is used to evaluate the performance of the model.
[0057] Model training: Use the training set to train the random forest model to learn fault characteristics, and use the test set to verify and evaluate the performance of the random forest model;
[0058] Model prediction: Use the trained random forest model to analyze and predict real-time data, and output the failure probability or failure type.
[0059] Furthermore, the fault prediction and self-healing module also includes a self-healing mechanism unit, and the self-healing mechanism unit includes:
[0060] Receiving fault prediction signals: When the random forest model predicts a fault, a fault signal is generated and transmitted to the self-healing mechanism unit;
[0061] Start the self-healing mechanism: After receiving the fault signal, the self-healing mechanism unit starts to execute the preset response measures, including automatically adjusting the cooling parameters and switching to the backup cooling unit.
[0062] The present invention uses an environmental sensing module to monitor environmental data such as temperature, humidity, and air quality in real time, and combines a data processing module to analyze and process environmental data to generate accurate cooling demand parameters. The cooling demand prediction module predicts future cooling demand. The intelligent adjustment module receives the predicted cooling demand parameters and calculates the optimal operating instructions, including cooling water flow rate, temperature set point, and fan speed. By accurately adjusting these parameters, the system can dynamically respond to changes in the environment and demand, achieve efficient and energy-saving cooling effects, and significantly improve the operating efficiency of the water chiller system.
[0063] The present invention introduces a fault prediction and self-healing module, which analyzes the real-time data of the environmental perception module and the data processing module and uses a machine learning algorithm to predict possible faults in advance. When a fault is predicted, the system will automatically adjust the cooling parameters, such as increasing the cooling water flow rate, lowering the temperature set point, or increasing the fan speed, to ensure that the cooling effect returns to normal. If the automatic adjustment cannot solve the problem, the system will switch to the backup cooling unit to ensure the continuous operation of the system. The self-healing mechanism can prevent and handle system failures in a timely manner, significantly improve the reliability and stability of the water-cooled machine system, and reduce the downtime and maintenance costs caused by failures.
[0064] The present invention can accurately control the operating status of the water pump, fan and cooling equipment according to the actual cooling demand, avoiding unnecessary energy waste. The overall system optimizes the operating mode of the water chiller through real-time monitoring and intelligent adjustment, achieving the effect of energy saving and consumption reduction, and meeting the requirements of modern industry for green environmental protection and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0066] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;
[0067] Figure 2 The figure is a flowchart of a data processing module according to an embodiment of the present invention. DETAILED DESCRIPTION
[0068] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0069] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0070] like Figure 1-Figure 2 As shown, the environmental adaptability intelligent regulation system of the water chiller includes an environmental perception module, a data processing module, a cooling demand prediction module, an intelligent regulation module, an actuator module and a fault prediction and self-healing module, wherein;
[0071] The environmental perception module is responsible for real-time monitoring of environmental data, including temperature, humidity and air quality, and transmits the environmental data to the data processing module;
[0072] The data processing module analyzes and processes the received environmental data, and outputs the corresponding cooling demand parameters to the cooling demand prediction module according to the preset algorithm model;
[0073] The cooling demand prediction module predicts the optimal cooling strategy based on the data from the data processing module and the historical cooling effect data, and transmits it to the intelligent adjustment module;
[0074] The intelligent regulation module receives the strategy from the cooling demand prediction module and calculates the best operating instructions, including the flow rate, temperature and start and stop time of the cooling water, and then instructs the actuator module to make corresponding adjustments;
[0075] The actuator module adjusts the operating parameters of the water chiller, including the speed of the water pump and the switch of the cooling device, according to the instructions of the intelligent adjustment module to achieve the predetermined cooling effect;
[0076] The fault prediction and self-healing module analyzes the real-time data of the environmental perception module and the data processing module, uses machine learning algorithms to predict possible faults, and provides early warnings and processing before the faults occur. When a fault occurs, the self-healing mechanism is activated to ensure the continuous operation of the cooling device by automatically adjusting the cooling parameters or switching to the backup cooling unit.
[0077] The environmental perception module specifically includes:
[0078] Temperature sensor: used to monitor ambient temperature, measure and output temperature data;
[0079] Humidity sensor: used to monitor environmental humidity, measure and output humidity data;
[0080] Air quality sensor: used to monitor ambient air quality, including PM2.5 and CO2 parameters, measure and output air quality data.
[0081] The data processing module specifically includes:
[0082] Data reception: Receive environmental data from the environmental perception module, including temperature, humidity and air quality;
[0083] Data storage unit: The received environmental data is stored in the data storage unit, including real-time environmental data and historical environmental data. The storage of historical data plays an important role in the subsequent cooling demand prediction;
[0084] Algorithm processing: Analyze and process environmental data according to the preset algorithm model;
[0085] Cooling demand parameter generation: After analysis and processing, the algorithm processing unit generates corresponding cooling demand parameters, which include cooling water flow rate, temperature set point, and fan speed;
[0086] The data processing module receives the real-time data transmitted by the environmental perception module through the data receiving unit, stores it in the data storage unit, analyzes and processes it using the algorithm processing unit, generates cooling demand parameters, and transmits them to the cooling demand prediction module through the data output unit, ensuring the real-time, accuracy and effectiveness of data processing, and providing reliable data support for cooling demand prediction.
[0087] The algorithm processing specifically includes:
[0088] Temperature analysis model: The temperature analysis model predicts cooling demand based on the changing trend of current temperature and historical temperature data. Celsius, historical temperature data is , calculated as:
[0089] ;
[0090] in, For temperature requirements, To set the temperature, and is the model coefficient, is the temperature change rate, ,in, is the ambient temperature at the current time point, is the ambient temperature data at a certain point in history. is the current time point, at which the system collects the current temperature , is a historical time point, corresponding to The time point indicates the collection time of historical temperature data;
[0091] Humidity analysis model: The humidity analysis model predicts cooling demand based on the changing trend of current humidity and historical humidity data. , the historical humidity data is , calculated as:
[0092] ;
[0093] in, For humidity requirements, To set the humidity, and is the model coefficient, is the humidity change rate, , is the ambient humidity at the current time point, is the environmental humidity data at a certain point in history. The current time point, indicating that the system records the current humidity time, It is a historical time point, indicating that the system records historical humidity time;
[0094] Air quality analysis model: The air quality analysis model predicts cooling demand based on the changing trend of current air quality and historical air quality data. Suppose the current air quality index is , the historical air quality data is , calculated as:
[0095] ;
[0096] in, To meet air quality requirements, To set the air quality index, and is the model coefficient, is the air quality change rate, , is the air quality index at the current time point, is the air quality index at a certain point in history, The current time point, indicating the collection of current air quality time, It is a historical time point, indicating the record of historical air quality data Time
[0097] Comprehensive analysis model: The comprehensive analysis model combines the requirements of temperature, humidity and air quality to generate the final cooling demand parameter, calculated as: ;
[0098] in, For the final cooling requirement, , and is the weight coefficient of each demand;
[0099] The data processing module processes the environmental data through the temperature analysis model, humidity analysis model and air quality analysis model to generate respective demand parameters. The comprehensive analysis model integrates these demand parameters to generate the final cooling demand parameters, providing reliable data support for the efficient operation of the system.
[0100] The cooling demand forecasting module specifically includes:
[0101] Data receiving: receiving cooling demand parameters output by the data processing module;
[0102] Historical data storage unit: stores historical cooling demand data and environmental data;
[0103] Prediction algorithm processing unit: The prediction algorithm processing unit uses the simple moving average method to process historical cooling demand data and predict future cooling demand parameters. , obtain the most recent cooling demand data through historical cooling demand data Cooling demand data at each time point , this Add the cooling demand data at each time point and divide by , get the predicted cooling demand parameters , calculated as: ;in, is the size of the moving window, For before The cooling demand value at a time point;
[0104] Example: Assume we have cooling demand data for the past 5 time points;
[0105] They are , , , , ,Window size , collect historical data: 30, 28, 32, 29, 31;
[0106] Calculate the simple moving average: ;
[0107] Get predicted cooling demand parameters is 30.
[0108] Calculating the best operating instructions specifically includes:
[0109] Receive forecast data: The intelligent adjustment module receives the forecasted cooling demand parameters from the cooling demand forecast module ;
[0110] Cooling water flow rate Calculated as: ,in, is the cooling water flow rate, and is the empirical coefficient;
[0111] Temperature set point Calculated as: ,in, is the temperature set point, is the reference temperature, is the adjustment coefficient;
[0112] Fan speed Calculated as: ,in, is the fan speed, and is the empirical coefficient;
[0113] Start and stop time: Determine the start and stop time of the cooling equipment according to the cooling demand parameters and the operating status of the equipment. Exceeding the start threshold , then set the device startup time is the current time, Below stop threshold , then set the device stop time is the current time;
[0114] The intelligent adjustment module receives the predicted cooling demand parameters transmitted by the cooling demand prediction module. , the above calculation formula is used to calculate the best operating instructions, including the flow rate of cooling water, temperature set point and start and stop time. These instructions will be transmitted to the actuator module to ensure that the cooling equipment operates according to the optimal strategy to meet the current cooling needs.
[0115] The actuator module specifically includes:
[0116] Receive operation instructions: The actuator module receives the operation instructions of the intelligent adjustment module, including , , , and ;
[0117] Adjust the pump speed: according to Instructions to increase or decrease the speed of the pump to match the flow rate in the instruction;
[0118] Set temperature: According to Instructions to adjust the temperature set point of the cooling equipment so that the temperature set point reaches ;
[0119] Adjust fan speed: according to Instructions to increase or decrease the speed of the fan to match the speed in the instruction;
[0120] Start-Stop Control: At this time, start the cooling equipment. At this point in time, stop cooling the equipment;
[0121] Feedback control: real-time monitoring of adjusted parameters to ensure that the actual operating parameters are consistent with the parameters in the instructions;
[0122] The actuator module adjusts the operating parameters of the water chiller, including the speed of the water pump, the temperature set point and the fan speed, according to the operating instructions transmitted by the intelligent adjustment module. Through precise control and real-time feedback, it ensures that the cooling equipment operates according to the optimal strategy to achieve the predetermined cooling effect.
[0123] The fault prediction and self-healing module specifically includes:
[0124] Data reception: Collect equipment operation data from the environment perception module, data processing module, intelligent adjustment module and actuator module. The equipment operation data includes temperature, humidity, cooling water flow rate, temperature set point, fan speed, equipment start and stop status, water pump operation status and cooling equipment switch status;
[0125] Data preprocessing: cleaning and standardizing the received data, including removing noise data, processing missing values, and performing data standardization;
[0126] Feature extraction: Extract the features required for fault prediction from the preprocessed data, including temperature, humidity, air quality, and equipment operating status;
[0127] Fault prediction: Use the random forest model to analyze the extracted features and predict the faults that may occur.
[0128] Fault prediction specifically includes:
[0129] Dataset construction: Use historical data to build training sets and test sets. The training set is used to train the random forest model, and the test set is used to evaluate the performance of the model.
[0130] Model training: Use the training set to train the random forest model to learn fault characteristics, and use the test set to verify and evaluate the performance of the random forest model;
[0131] Model prediction: Use the trained random forest model to analyze and predict real-time data, and output the fault probability or fault type;
[0132] Random forest improves the accuracy and robustness of the model by constructing multiple decision trees and combining their prediction results. Make predictions and get prediction results , expressed as: Random forest integrates the prediction results of all decision trees and outputs the final prediction category , expressed as:
[0133] , where mode represents the majority voting principle.
[0134] The fault prediction and self-healing module also includes a self-healing mechanism unit, which includes:
[0135] Receiving fault prediction signals: When the random forest model predicts a fault, a fault signal is generated and transmitted to the self-healing mechanism unit;
[0136] Start the self-healing mechanism: After receiving the fault signal, the self-healing mechanism unit starts to execute the preset response measures, including automatically adjusting the cooling parameters and switching to the backup cooling unit;
[0137] Automatically adjust cooling parameters including:
[0138] Adjust the cooling water flow rate: If a decrease in cooling efficiency is detected, increase the speed of the water pump to increase the cooling water flow rate. The formula is: , if overcooling is detected, the speed of the water pump is reduced to reduce the cooling water flow rate, the formula is: ,in, is the adjustment increment,
[0139] Adjust the temperature set point: Adjust the temperature set point of the cooling equipment to control the cooling effect. If the temperature is too high, lower the temperature set point. The formula is as follows: , if the temperature is too low, increase the temperature set point, the formula is as follows: ,in, is the temperature increment for adjustment,
[0140] Adjust fan speed: Adjust the speed of the cooling fan to change the air flow. If more intense cooling is required, increase the fan speed. The formula is as follows: , if the cooling is too much, reduce the fan speed, the formula is as follows: ,in, is the speed increment for adjustment;
[0141] If the automatic adjustment cannot solve the problem, switch to the backup cooling unit to maintain the normal operation of the system by shutting down the main cooling unit and starting the backup cooling unit;
[0142] Through the above measures, the self-healing mechanism can effectively respond to various faults, ensure the continuous and stable operation of the cooling device, and avoid downtime or performance degradation caused by faults.
[0143] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
[0144] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. The water-cooling machine environmental adaptability intelligent adjustment system is characterized by: It includes an environmental perception module, a data processing module, a cooling demand prediction module, an intelligent adjustment module, an actuator module and a fault prediction and self-healing module, among which; The environmental perception module is responsible for real-time monitoring of environmental data, including temperature, humidity and air quality, and transmitting the environmental data to the data processing module; The data processing module analyzes and processes the received environmental data, and outputs corresponding cooling demand parameters to the cooling demand prediction module according to a preset algorithm model. The data processing module specifically includes: Data reception: Receive environmental data from the environmental perception module, including temperature, humidity and air quality; Data storage unit: The received environmental data is stored in the data storage unit, including real-time environmental data and historical environmental data; Algorithm processing: Analyze and process environmental data according to the preset algorithm model; Cooling demand parameter generation: After analysis and processing, the algorithm processing unit generates corresponding cooling demand parameters, which include cooling water flow rate, temperature set point, and fan speed; The algorithm processing specifically includes: Temperature analysis model: The temperature analysis model predicts cooling demand based on the changing trend of current temperature and historical temperature data. Celsius, historical temperature data is , calculated as: ; in, For temperature requirements, To set the temperature, and is the model coefficient, is the temperature change rate, ,in, is the ambient temperature at the current time point, is the ambient temperature data at a certain point in history. is the current time point, at which the system collects the current temperature , is a historical time point, corresponding to The time point indicates the collection time of historical temperature data; Humidity analysis model: The humidity analysis model predicts cooling demand based on the changing trend of current humidity and historical humidity data. , the historical humidity data is , calculated as: ; in, For humidity requirements, To set the humidity, and is the model coefficient, is the humidity change rate, , is the ambient humidity at the current time point, is the environmental humidity data at a certain point in history. The current time point, indicating that the system records the current humidity time, It is a historical time point, indicating that the system records historical humidity time; Air quality analysis model: The air quality analysis model predicts cooling demand based on the changing trend of current air quality and historical air quality data. Suppose the current air quality index is , the historical air quality data is , calculated as: ; in, To meet air quality requirements, To set the air quality index, and is the model coefficient, is the air quality change rate, , is the air quality index at the current time point, is the air quality index at a certain point in history, The current time point, indicating the collection of current air quality time, It is a historical time point, indicating the record of historical air quality data time; Comprehensive analysis model: The comprehensive analysis model combines the requirements of temperature, humidity and air quality to generate the final cooling demand parameter, calculated as: ; in, For the final cooling requirement, , and is the weight coefficient of each demand; The cooling demand prediction module predicts the optimal cooling strategy based on the data from the data processing module and the historical cooling effect data, and transmits it to the intelligent adjustment module; The intelligent adjustment module receives the strategy from the cooling demand prediction module and calculates the best operating instructions, including the flow rate, temperature and start and stop time of the cooling water, and then instructs the actuator module to make corresponding adjustments; The actuator module adjusts the operating parameters of the water chiller, including the speed of the water pump and the switch of the cooling device, according to the instructions of the intelligent adjustment module to achieve a predetermined cooling effect; The fault prediction and self-healing module analyzes the real-time data of the environmental perception module and the data processing module, uses a machine learning algorithm to predict the faults that will occur, and provides early warning and processing before the faults occur. When a fault occurs, the self-healing mechanism is activated to ensure the continuous operation of the cooling device by automatically adjusting the cooling parameters or switching to a spare cooling unit.
2. The water chiller environmental adaptability intelligent adjustment system according to claim 1, characterized in that: The environment perception module specifically includes: Temperature sensor: used to monitor ambient temperature, measure and output temperature data; Humidity sensor: used to monitor environmental humidity, measure and output humidity data; Air quality sensor: used to monitor ambient air quality, including PM2.5 and CO2 parameters, measure and output air quality data.
3. The water chiller environmental adaptability intelligent adjustment system according to claim 1, characterized in that: The cooling demand prediction module specifically includes: Data receiving: receiving cooling demand parameters output by the data processing module; Historical data storage unit: stores historical cooling demand data and environmental data; Prediction algorithm processing unit: The prediction algorithm processing unit uses the simple moving average method to process historical cooling demand data and predict future cooling demand parameters. , obtain the most recent cooling demand data through historical cooling demand data Cooling demand data at each time point , this Add the cooling demand data at each time point and divide by , get the predicted cooling demand parameters , calculated as: ;in, is the size of the moving window, For before The cooling demand value at a point in time.
4. The water-cooling machine environmental adaptability intelligent adjustment system according to claim 3 is characterized in that: The calculation of the optimal operation instruction specifically includes: Receive forecast data: The intelligent adjustment module receives the forecasted cooling demand parameters from the cooling demand forecast module ; Cooling water flow rate Calculated as: ,in, is the cooling water flow rate, and is the empirical coefficient; Temperature set point Calculated as: ,in, is the temperature set point, is the reference temperature, is the adjustment coefficient; Fan speed Calculated as: ,in, is the fan speed, and is the empirical coefficient; Start and stop time: Determine the start and stop time of the cooling equipment according to the cooling demand parameters and the operating status of the equipment. Exceeding the start threshold , then set the device startup time is the current time, Below stop threshold , then set the device stop time is the current time.
5. The water-cooling machine environmental adaptability intelligent adjustment system according to claim 4 is characterized in that: The actuator module specifically includes: Receive operation instructions: The actuator module receives the operation instructions of the intelligent adjustment module, including , , , and ; Adjust the pump speed: according to Instructions to increase or decrease the speed of the pump to match the flow rate in the instruction; Set temperature: According to Instructions to adjust the temperature set point of the cooling equipment so that the temperature set point reaches ; Adjust fan speed: according to Instructions to increase or decrease the speed of the fan to match the speed in the instruction; Start-Stop Control: At this time, start the cooling equipment. At this point in time, stop cooling the equipment; Feedback control: Real-time monitoring of adjusted parameters to ensure that the actual operating parameters are consistent with the parameters in the instructions.
6. The water-cooling machine environmental adaptability intelligent adjustment system according to claim 5, characterized in that: The fault prediction and self-healing module specifically includes: Data reception: Collect equipment operation data from the environment perception module, data processing module, intelligent adjustment module and actuator module. The equipment operation data includes temperature, humidity, cooling water flow rate, temperature set point, fan speed, equipment start and stop status, water pump operation status and cooling equipment switch status; Data preprocessing: cleaning and standardizing the received data, including removing noise data, processing missing values, and performing data standardization; Feature extraction: Extract the features required for fault prediction from the preprocessed data, including temperature, humidity, air quality, and equipment operating status; Fault prediction: Use the random forest model to analyze the extracted features and predict the faults that may occur.
7. The water chiller environmental adaptability intelligent adjustment system according to claim 6, characterized in that: The fault prediction specifically includes: Dataset construction: Use historical data to build training sets and test sets. The training set is used to train the random forest model, and the test set is used to evaluate the performance of the model. Model training: Use the training set to train the random forest model to learn fault characteristics, and use the test set to verify and evaluate the performance of the random forest model; Model prediction: Use the trained random forest model to analyze and predict real-time data, and output the failure probability or failure type.
8. The water chiller environmental adaptability intelligent adjustment system according to claim 6, characterized in that: The fault prediction and self-healing module further includes a self-healing mechanism unit, and the self-healing mechanism unit includes: Receiving fault prediction signals: When the random forest model predicts a fault, a fault signal is generated and transmitted to the self-healing mechanism unit; Start the self-healing mechanism: After receiving the fault signal, the self-healing mechanism unit starts to execute the preset response measures, including automatically adjusting the cooling parameters and switching to the backup cooling unit.
Citation Information
Patent Citations
Intelligent Internet of Things air quality monitoring system
CN117953995A
Cooling-water machine energy efficiency optimization system based on intelligent algorithm
CN118089287A
Efficient refrigeration cycle system and method
CN118089290A
Intelligent equipment monitoring and maintenance system
CN118134458A
Intelligent heat supply control system, method and device self-adaptive to environmental changes
CN118242702A
