Remote control and monitoring device for cooling system

Abstract

The invention discloses a remote control and monitoring device for a cooling system, and relates to the technical field of automation. Comprising a sensor module, a data acquisition module, a central processing unit CPU, a communication module and a control execution element. The sensor module comprises a temperature sensor and a current transformer, the data acquisition module converts an analog signal into a digital signal through an ADC analog-to-digital converter, and the central processing unit is responsible for carrying out operation and control logic judgment on data and is connected with a remote terminal through the communication module. In the data acquisition stage, temperature and current data are monitored in real time; filtering, calibrating and calculating the data; whether equipment is started or stopped is judged according to the data, and frequent starting and stopping are avoided; transmitting real-time data and receiving a remote instruction through the communication module; the environment parameters and the operation state are used for self-adaptively regulating and controlling equipment operation parameters; and finally, realizing fault prediction through feature extraction and analysis. The intelligent management level of the cooling equipment can be effectively improved, and stable and efficient operation of the cooling equipment is ensured.

Description

Technical Field

[0001] The invention relates to the field of automation technology, and in particular to a cooling system remote control and monitoring device. Background Art

[0002] In modern industrial production, large data centers and the operation of various facilities, cooling systems play a vital role.

[0003] From the perspective of the industrial field, many industrial production processes have strict requirements on temperature. For example, in chemical production, the reaction process is often accompanied by the release or absorption of heat. Accurate temperature control is a key factor in ensuring product quality, improving production efficiency, and ensuring safe production. Traditional cooling systems usually rely on local control and monitoring methods. Operators need to manually check and adjust the operating parameters of the cooling equipment such as oil temperature, water pressure, flow, etc. on site. This not only consumes a lot of manpower and time, but also makes it difficult to achieve unified management of multiple cooling equipment or cooling systems distributed in different areas. Once abnormal conditions such as insufficient cooling or excessive cooling occur, it may cause chemical reactions to get out of control, equipment damage, and even cause serious safety accidents such as explosions and fires, which will bring huge economic losses and irreversible social impacts to the company.

[0004] In terms of data centers, with the rapid development of information technology, the scale and density of data centers are constantly increasing. Computer servers and other equipment will generate a lot of heat during operation. If the heat cannot be dissipated in a timely and effective manner, the temperature of the equipment will be too high, thereby reducing its performance, increasing the failure rate, and shortening its service life. The traditional cooling system management method of data centers faces challenges because data centers have many devices and long operating times, requiring a continuous and stable cooling environment. The cooling system with local monitoring and control is difficult to meet the requirements for the real-time and accuracy of the cooling system. Local hot spots may not be eliminated in time, affecting the overall operational stability of the data center, resulting in serious consequences such as data loss and service interruption, which brings great trouble to the business operations of enterprises and may also affect many users who rely on data center services.

[0005] In addition, cooling systems are also indispensable for some large commercial buildings, hospitals, communication base stations and other places. The cooling needs of these places are complex and diverse, and the loads in different areas vary greatly. In the past, the cooling system management model that relied on manual inspections and local control could not flexibly adjust the cooling strategy in time according to environmental changes and actual needs, which easily caused energy waste. For example, in commercial buildings, the flow of personnel and equipment usage are different in different time periods, and the cooling needs vary significantly. It is difficult for traditional cooling systems to achieve accurate matching, resulting in excessive consumption of energy such as electricity, and increased operating costs.

[0006] Furthermore, from the perspective of equipment maintenance, traditional cooling systems lack effective remote diagnostic functions. When cooling equipment fails, maintenance personnel often need to go to the site to troubleshoot the problem, which not only prolongs equipment downtime and reduces equipment utilization, but also in some emergency situations, the failure may be further aggravated due to untimely maintenance, increasing maintenance costs and difficulty.

[0007] To sum up, in order to improve the operating efficiency, reliability, accuracy of the cooling system and achieve efficient use of energy, the development of remote control and monitoring devices for cooling systems has extremely important practical significance and can meet the urgent needs of modern industry, commerce and other fields for intelligent management of cooling systems. Summary of the invention

[0008] In order to improve the operating efficiency, reliability, and accuracy of a cooling system and achieve efficient use of energy, the present invention provides a remote control and monitoring device for a cooling system.

[0009] The technical solution adopted by the present invention is:

[0010] A cooling system remote control and monitoring device, characterized in that it includes a sensor module, a data acquisition module, a central processing unit CPU, a communication module, and a control actuator; the sensor module includes a temperature sensor installed at a coolant storage tank and a heat exchanger, and a current transformer installed at a transformer; the data acquisition module is connected to the sensor module via a shielded cable, an ADC analog-to-digital converter chip is configured inside the data acquisition module, and is connected to the central processing unit via an RS485 or Ethernet interface; the central processing unit CPU is connected to a remote terminal via a communication module and controls the actions of the actuator at the same time; the control actuator includes a cooling fan, an oil pump, and a solenoid valve, and the central processing unit CPU outputs a control signal, which is driven and controlled by a relay or a transistor.

[0011] Furthermore, the temperature sensor monitors the coolant temperature in real time and outputs an analog voltage signal corresponding to the temperature; the current transformer monitors the transformer current and outputs a current value change signal related to the transformer; the data acquisition module converts the temperature signal into a digital temperature value and converts the current value change signal into a digital current signal; the central processing unit CPU is an industrial-grade embedded microprocessor, which runs control algorithms and logical judgments and stores system parameters and historical data.

[0012] A cooling system remote monitoring and intelligent control method, which is based on the above cooling system remote control and monitoring device, is characterized in that it includes the following steps:

[0013] Step 1, data collection: collect the temperature data V of the coolant through the temperature sensor TThe data acquisition module uses the ADC analog-to-digital converter chip to convert the analog signal into a digital signal: the temperature voltage signal V T Convert to temperature value T;

[0014] Step 2, data processing: filter and calibrate the collected temperature to remove noise and outliers; use a sliding window average filter algorithm to process the temperature signal and liquid level signal;

[0015] Step 3, control logic: determine whether to start or stop the cooling device based on temperature and current data; avoid frequent starts and stops through the dual threshold control strategy of temperature control logic and current control logic;

[0016] Step 4, remote communication: use the communication module to package and transmit real-time data, receive and parse remote instructions, and call the corresponding control logic;

[0017] Step 5, adaptive intelligent control: using environmental parameters including temperature and humidity and operating status including temperature and load as input, calculate the optimal cooling equipment operating parameters; at the same time, use adaptive algorithms based on machine learning to optimize the objective function;

[0018] Step 6, Fault prediction: Predict possible equipment failures by extracting and analyzing the features of the operating data.

[0019] Furthermore, the calculation formula for converting analog signals into digital signals is:

[0020] Temperature value:

[0021] T=k T ·V T +b T

[0022] Where T is the temperature voltage signal V T Converted temperature value; k T 、b T is the calibration coefficient of the temperature sensor.

[0023] Furthermore, the calculation formula of the sliding window average filtering algorithm is:

[0024]

[0025] In the formula, X filtered (t) is the data value at time t after filtering; X(t) is the original data at time t; n is the length of the sliding window; It means taking the sum of n data points from time t forward.

[0026] Further, the temperature control logic is:

[0027]

[0028] In the formula, F cooling (T) represents the state function of the cooling system; T1 is the start temperature threshold; T2 is the stop temperature threshold;

[0029] Current control logic:

[0030]

[0031] In the formula, F fan (I) represents the state function of the fan; I1 is the rated current of the transformer; I is the actual monitored current of the transformer.

[0032] Furthermore, the data packaging format is as follows:

[0033] Packet={"T":T,"I":I,"Status":F cooling ,...}

[0034] The control instruction parsing process is as follows:

[0035]

[0036] In the formula, Packet is a data structure; T represents the temperature value; I represents the current data; Status represents the status of the cooling system; F cooling The result of the calculation is 0 or 1, which means stopping or starting the cooling device respectively; Action is the variable of the command parsing result; start Cooling means that if the command is start, the cooling system is started; stop Cooling means that if the command is stop, the cooling system is stopped.

[0037] Furthermore, the optimization objective function is expressed as:

[0038]

[0039] In the formula, Indicates that the function P(V,Q) needs to be minimized; P(V,Q) is the energy consumption function of the cooling equipment, which depends on the oil pump speed V and the fan air volume Q;

[0040] The constraints are:

[0041] T out ≤T max

[0042] Where, T out is the system output temperature; T max is the maximum allowable temperature;

[0043] The adaptive algorithm uses a reinforcement learning algorithm, and the update strategy is:

[0044]

[0045] Where πθ' is the updated strategy; πθ is the current strategy; η is the learning rate; represents the gradient with respect to the parameter J(θ); J(θ) is the performance of the current strategy.

[0046] Further, the fault prediction process is as follows:

[0047] First, the characteristic vectors are calculated, including temperature, liquid level, current fluctuation, and vibration parameters;

[0048] X=[T,I,ΔI,V vib ,...]

[0049] Where, T is the temperature; I is the current; ΔI is the current fluctuation; V vib is the vibration parameter;

[0050] Fault prediction is based on the fault prediction model, which supports the vector machine SVM and can deeply learn the DBN. The support vector machine SVM is expressed as:

[0051] Y=sign(ω·X+b)

[0052] In the formula, Y is the prediction result, indicating fault or normal; ω and b are model parameters; X is the feature vector;

[0053] Deep learning DBN is represented as:

[0054] Y=f(W l ·f(W l-1 ·...f(W 1 ·X+b 1 )...+b l-1 )+b l )

[0055] Where, Y is the prediction result; W l 、b l is the weight and bias of the lth layer; W l-1 、b l-1 are the weights and biases of the l-1th layer; f is the activation function.

[0056] The beneficial effects of the present invention are:

[0057] Real-time monitoring: Through real-time data collection of temperature sensors and current transformers, the temperature of the coolant and the current changes of the transformer can be monitored in time, which helps to quickly discover potential problems.

[0058] Improve efficiency: Intelligent control logic optimizes the operating parameters of cooling equipment based on real-time data, which can achieve efficient use of energy, reduce energy consumption and improve the overall efficiency of the system.

[0059] Enhanced reliability: Fault prediction can identify potential equipment problems in advance, reduce unexpected downtime and maintenance costs, and improve system reliability and safety.

[0060] Remote control: Supports remote monitoring and operation, allowing managers to view system status in real time at any location, remotely control and adjust equipment, and improve management convenience.

[0061] Data processing optimization: Through data filtering and calibration, the accuracy of temperature and current data can be improved, the impact of noise and outliers can be reduced, and the scientific nature of decision-making can be enhanced.

[0062] Adaptive control: The system can adaptively adjust the control strategy according to environmental parameters and operating status, optimize the cooling effect, and ensure stable operation of the system under different working conditions.

[0063] Cost reduction: Reduce operating costs and maintenance expenses by optimizing energy use and reducing the frequency of failures.

[0064] Intelligent improvement: The adaptive algorithm combined with machine learning can achieve intelligent improvement of system behavior, so that the cooling system can maintain optimal performance under different working conditions.

[0065] The above beneficial effects make the cooling system remote control and monitoring device have significant advantages in industrial applications, and can effectively improve the operating efficiency, reliability and economy of the cooling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0067] Figure 1 It is a schematic diagram of the overall structure of the cooling system remote control and monitoring device of the present invention;

[0068] Figure 2 It is a flow chart of the cooling system remote monitoring and intelligent control method of the present invention. DETAILED DESCRIPTION

[0069] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0070] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely represents some embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should be noted that the embodiments of the present invention and the features and technical solutions in the embodiments can be combined with each other without conflict. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0071] Example 1

[0072] In order to improve the operating efficiency, reliability, and accuracy of a cooling system and achieve efficient use of energy, the present invention provides a remote control and monitoring device for a cooling system.

[0073] like Figure 1 As shown, the cooling system remote control and monitoring device includes a sensor module, a data acquisition module, a central processing unit CPU, a communication module, and a control actuator; the sensor module includes a temperature sensor installed at a coolant storage tank and a heat exchanger, and a current transformer installed at a transformer; the data acquisition module is connected to the sensor module through a shielded cable, an ADC analog-to-digital converter chip is configured inside the data acquisition module, and is connected to the central processing unit through an RS485 or Ethernet interface; the central processing unit CPU is connected to a remote terminal through a communication module, and controls the action of the actuator at the same time; the control actuator includes a cooling fan, an oil pump, and a solenoid valve, and the central processing unit CPU outputs a control signal, which is driven and controlled by a relay or a transistor.

[0074] Specifically, temperature sensors: high-precision temperature sensors are installed at key locations of the cooling system, such as coolant storage tanks, heat exchanger inlets and outlets, to monitor the coolant temperature in real time. At the same time, current transformers are installed at the transformer to monitor transformer current changes. These sensors are connected to the data acquisition module via shielded cables to ensure the stability and anti-interference of signal transmission. They transmit analog electrical signals, such as the voltage value signal corresponding to the temperature output by the temperature sensor.

[0075] Data acquisition module: The data acquisition module receives analog signals from sensors and converts them into digital signals. The module has a multi-channel input function and can process multiple sensor signals at the same time. For example, an ADC analog-to-digital converter chip is used to convert the voltage signal of the temperature sensor into a digital temperature value and the current value change signal into a digital current signal. The converted digital signal is transmitted to the central processing unit CPU through the RS485 or Ethernet interface.

[0076] Central Processing Unit (CPU): An industrial-grade embedded microprocessor such as an ARM architecture chip is used. It is responsible for processing the received digital signals, running control algorithms and logical judgments. For example, based on the preset temperature threshold, it determines whether the current cooling system needs to start cooling fans or oil pumps to cool down. At the same time, it is also responsible for communicating with the remote monitoring terminal, receiving remote control instructions and performing corresponding operations. The CPU stores the system's operating parameters, control strategies, and historical data recording functions for subsequent data analysis and troubleshooting.

[0077] Communication module: Use wireless communication modules, such as 4G, Wi-Fi or LoRa, or wired Ethernet modules, to achieve two-way data transmission with the remote monitoring terminal. The wireless communication module is convenient for use in areas without wired network coverage. It can send real-time status data of the cooling system, such as temperature, current, equipment operation status, etc., to the remote monitoring terminal, and receive control instructions from the remote terminal, such as starting and stopping the cooling equipment, adjusting cooling parameters, etc., and transmit them to the central processing unit CPU for execution.

[0078] Control actuators: including cooling fans, oil pumps, solenoid valves and other equipment. These equipment are controlled by the central processing unit CPU through drive circuits such as relays or transistors. For example, when the central processing unit CPU determines that the temperature is too high, the output control signal drives the relay to close, so that the cooling fan is powered on; or the opening and closing of the solenoid valve is controlled according to the liquid level to replenish the coolant.

[0079] The specific functions and algorithms of the cooling system remote control and monitoring device are as follows:

[0080] Data acquisition and processing program: runs on the central processing unit CPU, responsible for regularly reading the digital signal from the data acquisition module, filtering, calibration and other processing. For example, smoothing the temperature data, removing abnormal data points caused by sensor jitter or electromagnetic interference, and then converting the digital quantity into the actual temperature value according to the sensor's calibration coefficient, and storing it in the memory buffer for use by other programs.

[0081] Control logic program: written according to the preset control strategy. For example, the start temperature threshold of the cooling system is set to T1, and the stop temperature threshold is set to T2 (T1>T2). When the collected temperature value is greater than T1, the control program starts the cooling fan or oil pump; when the temperature drops below T2, the relevant equipment is stopped. When the temperature continues to rise and the collected temperature value is greater than T3, the control program starts multiple sets of cooling fans or oil pumps; when the temperature drops below T1, the relevant equipment stops current control; the transformer rated current I1 is set, and the cooling system is started when the actual current I is greater than or equal to 70% of the rated current I1, and the cooling system is stopped when the actual current I is less than 70% of the rated current I1. At the same time, the system will record the number of operations of each cooling fan or oil pump on the day, the number of operations this month, and the total operating time, which can be queried in the background.

[0082] Remote communication program: implements the data interaction protocol with the remote monitoring terminal. It packages the real-time status data of the cooling system according to the predetermined communication protocol format, such as JSON or XML format, and sends it to the remote terminal. At the same time, it receives the control command data packet sent by the remote terminal, parses the command content and passes it to the control logic program for execution. For example, when the remote monitoring terminal sends a command to start the cooling fan, the communication program receives the command, and the control logic program starts the fan according to the command and feeds back the execution result to the remote terminal.

[0083] Remote monitoring terminal software: The system is presented on the WeChat applet, and the applet interface displays the real-time status information of the cooling system, including charts or digital displays of data such as temperature, current, and equipment operating status. Operators can use the software to remotely send control instructions, such as manually starting or stopping cooling equipment, and modifying control parameters, including temperature thresholds, transformer rated current, etc. At the same time, the software also has a historical data query function, which can view the operating data records of the cooling system over a period of time in the past, so as to conduct operation analysis and fault diagnosis. For example, by viewing the historical temperature curve, the performance of the cooling system under different working conditions can be analyzed to determine whether there are potential fault hazards.

[0084] Example 2

[0085] Based on the cooling system remote control and monitoring device provided in Example 1, this embodiment also provides a cooling system remote monitoring and intelligent control method, such as Figure 2 As shown, the cooling system remote monitoring and intelligent control method comprises the following steps:

[0086] Step 1, data collection: collect the temperature data V of the coolant through the temperature sensor T The data acquisition module uses the ADC analog-to-digital converter chip to convert the analog signal into a digital signal: the temperature voltage signal V TConvert to temperature value T;

[0087] The calculation formula for converting analog signal into digital signal is:

[0088] Temperature value:

[0089] T=k T ·V T +b T

[0090] Where T is the temperature voltage signal V T Converted temperature value; k T 、b T is the calibration coefficient of the temperature sensor.

[0091] Step 2, data processing: filter and calibrate the collected temperature to remove noise and outliers; use a sliding window average filter algorithm to process the temperature signal and liquid level signal;

[0092] The calculation formula of the sliding window average filtering algorithm is:

[0093]

[0094] Where, X filtered (t) is the data value at time t after filtering; X(t) is the original data at time t; n is the length of the sliding window; It means taking the sum of n data points from time t forward.

[0095] Step 3, control logic: determine whether to start or stop the cooling device based on temperature and current data; avoid frequent starts and stops through the dual threshold control strategy of temperature control logic and current control logic;

[0096] The temperature control logic is:

[0097]

[0098] In the formula, F cooling (T) represents the state function of the cooling system; T1 is the start temperature threshold; T2 is the stop temperature threshold;

[0099] Current control logic:

[0100]

[0101] In the formula, F fan (I) represents the state function of the fan; I1 is the rated current of the transformer; I is the actual monitored current of the transformer.

[0102] Step 4, remote communication: use the communication module to package and transmit real-time data, receive and parse remote instructions, and call the corresponding control logic;

[0103] The data packaging format is as follows:

[0104] Packet={"T":T,"I":I,"Status":F cooling ,...}

[0105] The control instruction parsing process is as follows:

[0106]

[0107] In the formula, Packet is a data structure; T represents the temperature value; I represents the current data; Status represents the status of the cooling system; F cooling The result of the calculation is 0 or 1, which means stopping or starting the cooling device respectively; Action is the variable of the command parsing result; start Cooling means that if the command is start, the cooling system is started; stop Cooling means that if the command is stop, the cooling system is stopped.

[0108] Step 5, adaptive intelligent control: using environmental parameters including temperature and humidity and operating status including temperature and load as input, calculate the optimal cooling equipment operating parameters; at the same time, use adaptive algorithms based on machine learning to optimize the objective function;

[0109] The optimization objective function is expressed as:

[0110]

[0111] In the formula, Indicates that the function P(V,Q) needs to be minimized; P(V,Q) is the energy consumption function of the cooling equipment, which depends on the oil pump speed V and the fan air volume Q;

[0112] The constraints are:

[0113] T out ≤T max

[0114] Where, T out is the system output temperature; T max is the maximum allowable temperature;

[0115] The adaptive algorithm uses a reinforcement learning algorithm, and the update strategy is:

[0116]

[0117] Where πθ' is the updated strategy; πθ is the current strategy; η is the learning rate; represents the gradient with respect to the parameter J(θ); J(θ) is the performance of the current strategy.

[0118] Step 6, Fault prediction: Predict possible equipment failures by extracting and analyzing the features of the operating data.

[0119] The fault prediction process is as follows:

[0120] First, the characteristic vectors are calculated, including temperature, liquid level, current fluctuation, and vibration parameters;

[0121] X=[T,I,ΔI,V vib ,...]

[0122] Where, T is the temperature; I is the current; ΔI is the current fluctuation; V vib is the vibration parameter;

[0123] Fault prediction is based on the fault prediction model, which supports the vector machine SVM and can deeply learn the DBN. The support vector machine SVM is expressed as:

[0124] Y=sign(ω·X+b)

[0125] In the formula, Y is the prediction result, indicating fault or normal; ω and b are model parameters; X is the feature vector;

[0126] Deep learning DBN is represented as:

[0127] Y=f(W l ·f(W l-1 ·...f(W 1 ·X+b 1 )...+b l-1 )+b l )

[0128] Where, Y is the prediction result; W l 、b l is the weight and bias of the lth layer; W l-1 、b l-1 are the weights and biases of the l-1th layer; f is the activation function.

[0129] In summary, in combination with Example 1 and Example 2, the cooling system remote control and monitoring device enables the operator to accurately adjust the operating parameters of the cooling system according to actual needs, such as coolant flow rate, cooling fan speed, etc. With the help of real-time monitoring function, the control strategy can be optimized at any time according to system feedback information to ensure that the cooling system always operates in the best working state, maximize cooling efficiency, reduce energy waste, and reduce enterprise operating costs.

[0130] The cooling system remote control and monitoring device can monitor the operating status of each component of the cooling system 24 hours a day, including oil temperature, current, equipment vibration, wear of key components, etc. Once abnormal parameters or potential faults are found, the operating parameters can be adjusted remotely immediately for emergency treatment, and maintenance personnel can be notified in time to go to the site for investigation and maintenance, effectively preventing small faults from turning into big problems, ensuring long-term stable and reliable operation of equipment, and improving production continuity and corporate economic benefits.

[0131] The remote control and monitoring device for the cooling system realizes intelligent management of the cooling system through data collection, transmission, analysis and processing. On the one hand, it can automatically record a large amount of operating data, providing a detailed basis for equipment performance evaluation, fault diagnosis, and maintenance plan formulation; on the other hand, based on the data analysis results, it can realize intelligent early warning and automatic control, such as automatically switching cooling modes according to different seasons and different production conditions, and further optimizing system energy consumption and equipment life under the premise of ensuring cooling effect. At the same time, the remote control function facilitates the centralized management and collaborative work of multiple systems, improves the overall management level and production efficiency of the enterprise, and enhances the competitiveness of the enterprise in the market.

[0132] At the same time, it should be pointed out that the above description is only a typical embodiment of the present invention and does not limit the present invention in any form. Any changes made to the above embodiments based on the ideas and technical essence of the present invention are within the protection scope of the present invention.

Claims

1. A remote control and monitoring device for a cooling system, characterized in that: It includes a sensor module, a data acquisition module, a central processing unit CPU, a communication module, and a control actuator; the sensor module includes a temperature sensor installed at a coolant storage tank and a heat exchanger, and a current transformer installed at a transformer; the data acquisition module is connected to the sensor module through a shielded cable, an ADC analog-to-digital converter chip is configured inside the data acquisition module, and is connected to the central processing unit through an RS485 or Ethernet interface; the central processing unit CPU is connected to a remote terminal through a communication module and controls the actions of the actuator at the same time; the control actuator includes a cooling fan, an oil pump, and a solenoid valve, and the central processing unit CPU outputs a control signal, which is driven and controlled by a relay or a transistor.

2. The cooling system remote control and monitoring device according to claim 1, characterized in that: The temperature sensor monitors the coolant temperature in real time and outputs an analog voltage signal corresponding to the temperature; the current transformer monitors the transformer current and outputs a current value change signal related to the transformer; the data acquisition module converts the temperature signal into a digital temperature value and converts the current value change signal into a digital current signal; the central processing unit CPU is an industrial-grade embedded microprocessor, which runs control algorithms and logical judgments and stores system parameters and historical data.

3. A cooling system remote monitoring and intelligent control method, the cooling system remote monitoring and intelligent control method is based on the cooling system remote control and monitoring device according to claim 1 or 2, characterized in that: The following steps are involved: Step 1, data collection: collect the temperature data V of the coolant through the temperature sensor T The data acquisition module uses the ADC analog-to-digital converter chip to convert the analog signal into a digital signal: the temperature voltage signal V T Convert to temperature value T; Step 2, data processing: filter and calibrate the collected temperature to remove noise and outliers; use a sliding window average filter algorithm to process the temperature signal and liquid level signal; Step 3, control logic: determine whether to start or stop the cooling device based on temperature and current data; avoid frequent starts and stops through the dual threshold control strategy of temperature control logic and current control logic; Step 4, remote communication: use the communication module to package and transmit real-time data, receive and parse remote instructions, and call the corresponding control logic; Step 5, adaptive intelligent control: using environmental parameters including temperature and humidity and operating status including temperature and load as input, calculate the optimal cooling equipment operating parameters; at the same time, use adaptive algorithms based on machine learning to optimize the objective function; Step 6, Fault prediction: Predict possible equipment failures by extracting and analyzing the features of the operating data.

4. The cooling system remote monitoring and intelligent control method according to claim 3 is characterized in that: The calculation formula for converting analog signal into digital signal is: Temperature value: T=k T ·V T +b T Where T is the temperature voltage signal V T Converted temperature value; k T 、b T is the calibration coefficient of the temperature sensor.

5. The cooling system remote monitoring and intelligent control method according to claim 3 is characterized in that: The calculation formula of the sliding window average filtering algorithm is: Where, X filtered (t) is the data value at time t after filtering; X(t) is the original data at time t; n is the length of the sliding window; It means taking the sum of n data points from time t forward.

6. The cooling system remote monitoring and intelligent control method according to claim 3 is characterized in that: The temperature control logic is: In the formula, F cooling (T) represents the state function of the cooling system; T1 is the start temperature threshold; T2 is the stop temperature threshold; Current control logic: In the formula, F fan (I) represents the state function of the fan; I1 is the rated current of the transformer; I is the actual monitored current of the transformer.

7. The cooling system remote monitoring and intelligent control method according to claim 3 is characterized in that: The data packaging format is as follows: Packet={"T":T,"I":I,"Status":F cooling ,...} The control instruction parsing process is as follows: In the formula, Packet is a data structure; T represents the temperature value; I represents current data; Status indicates the status of the cooling system; F cooling The result of the calculation is 0 or 1, which means stopping or starting the cooling device respectively; Action is the variable of the command parsing result; start Cooling means that if the command is start, the cooling system is started; stop Cooling means that if the command is stop, the cooling system is stopped.

8. The cooling system remote monitoring and intelligent control method according to claim 3 is characterized in that: The optimization objective function is expressed as: In the formula, Indicates that the function P(V,Q) needs to be minimized; P(V,Q) is the energy consumption function of the cooling equipment, which depends on the oil pump speed V and the fan air volume Q; The constraints are: T out ≤T max Where, T out is the system output temperature; T max is the maximum allowable temperature; The adaptive algorithm uses a reinforcement learning algorithm, and the update strategy is: Where πθ' is the updated strategy; πθ is the current strategy; η is the learning rate; represents the gradient with respect to the parameter J(θ); J(θ) is the performance of the current strategy.

9. The cooling system remote monitoring and intelligent control method according to claim 3, characterized in that: The fault prediction process is as follows: First, the characteristic vectors are calculated, including temperature, liquid level, current fluctuation, and vibration parameters; X=[T,I,ΔI,V vib ,...] Where T is the temperature value; I is the current; ΔI is the current fluctuation; V vib is the vibration parameter; Fault prediction is based on the fault prediction model, which supports the support vector machine (SVM) and can deeply learn the DBN. Support vector machine SVM is expressed as: Y=sign(ω·X+b) In the formula, Y is the prediction result, indicating fault or normal; ω and b are model parameters; X is the feature vector; Deep learning DBN is represented as: Y=f(W l ·f(W l-1 ·...f(W 1 ·X+b 1 )...+b l-1 )+b l ) Where, Y is the prediction result; W l 、b l is the weight and bias of the lth layer; W l-1 、b l-1 are the weights and biases of the l-1th layer; f is the activation function.

Images