A vortex heating and refrigeration logic control system and method

Abstract

The present invention relates to the field of intelligent temperature control technology, and specifically to a vortex heating and cooling logic control system and method. In the present invention, through the acquisition of coolant flow rate data and entropy value analysis, the fuzzy set is used to perform fuzzy partitioning on the data in different time periods and calculate the fuzzy entropy value, realizing the accurate marking and feature extraction of abnormal coolant flow rate data, and effectively enhancing the recognition ability of abnormal working conditions. In terms of predicting the change trend of coolant temperature, by extracting the characteristic points of the coolant temperature change, constructing the coolant temperature state sequence, and combining with the ideal coolant target temperature trajectory, the optimal path search technology is adopted to ensure that the coolant temperature change is more in line with the target trajectory, improving the temperature control accuracy and stability. The Viterbi algorithm calculates the state transition probability, making the transition of temperature states more accurate and avoiding possible deviations in the temperature control process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent temperature control, and particularly to a vortex heating and cooling logic control system and method. Background Art

[0002] A vortex heating and cooling logic control system refers to a temperature control system that utilizes the eddy current effect to achieve heating and cooling functions and adjusts the operating state through a logic control method. This system is applied to industrial fluid temperature control equipment, mainly including an eddy current generation unit, a flow guiding structure, a heat exchange device, and a control circuit. The eddy current generation unit generates eddy current heat through a rotating conductive material under the action of a magnetic field to heat the fluid; the flow guiding structure is used to optimize the fluid flow path and improve the heat exchange efficiency; the heat exchange device is responsible for transferring the heat generated by the eddy current to the target medium, or reducing the medium temperature through reverse control in the cooling mode; the control circuit performs logical judgments based on temperature sensing data, switches the system operating mode, and adjusts input parameters to ensure normal temperature regulation.

[0003] In the prior art, the vortex heating and cooling system realizes heating and cooling through the eddy current effect. Although it has a certain basic temperature control ability, in the face of a multi-condition environment with complex flow rates and temperature changes, its control accuracy and adaptability are insufficient. The coolant flow rate and temperature mainly rely on fixed thresholds for judgment, making it difficult to dynamically track abnormal conditions, and unable to accurately identify flow rate anomalies and temperature deviations under real-time condition fluctuations, resulting in possible false alarms or misreports, affecting the stability of equipment operation. During the temperature control process, a single real-time feedback adjustment is usually adopted, resulting in a lag response of the heat exchange equipment when the load changes greatly, and the temperature control process fluctuates too much, affecting the temperature control effect. In addition, the adjustment of the heat exchange power and time mostly adopts fixed value settings, which cannot be flexibly adjusted according to real-time needs, and is prone to overshoot or undershoot under high-load or low-load conditions, increasing equipment energy consumption and shortening the equipment service life. This limits the performance optimization of the vortex heating and cooling system under complex conditions and is difficult to meet the requirements of efficient, accurate, and stable temperature control. Summary of the Invention

[0004] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a vortex heating and cooling logic control system and method.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: A vortex heating and cooling logic control system includes:

[0006] The coolant flow rate entropy value analysis module collects the coolant flow rate data entering the heat exchange chamber and constructs a coolant flow rate time series, constructs a fuzzy set according to the coolant flow rate data in different time periods in the coolant flow rate time series, calculates the fuzzy entropy value of the fuzzy set, and generates a fuzzy entropy value analysis result;

[0007] The entropy value anomaly monitoring module marks the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result, and generates the coolant flow rate anomaly feature;

[0008] The temperature optimal path matching module obtains the coolant temperature data, extracts the coolant temperature change feature points from the coolant temperature data, constructs the coolant temperature state sequence, passes through the preset ideal coolant target temperature trajectory, and searches for the optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain the optimal coolant temperature change path analysis result;

[0009] The temperature prediction module predicts the coolant temperature in multiple future time steps according to the coolant temperature change trend collected in the optimal coolant temperature change path analysis result, constructs the coolant temperature prediction sequence, analyzes the heat exchange power adjustment amount and heat exchange time correction value under different heat exchange load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory, and generates the optimized heat exchange control parameters;

[0010] The dynamic parameter adjustment module adjusts the cooling pump control signal of the heat exchange device according to the coolant flow rate anomaly feature, and adjusts the heat exchange power and the duration of the heat exchange process of the heat exchange equipment respectively based on the optimized heat exchange control parameters to generate the eddy current heating and cooling logic control result.

[0011] As a further solution of the present invention, the steps for obtaining the fuzzy entropy value analysis result are specifically as follows:

[0012] Collect the coolant flow rate data entering the heat exchange chamber through the flow sensor of the eddy current refrigeration circuit, segment and preprocess the coolant flow rate data according to a fixed time window, and construct the preprocessed coolant flow rate time series;

[0013] Perform fuzzy partitioning on the coolant flow rate data in different time periods in the preprocessed coolant flow rate time series to generate the corresponding fuzzy sets;

[0014] Based on the fuzzy set, use the formula:

[0015]

[0016] Calculate the fuzzy entropy value of the fuzzy set , integrate different fuzzy entropy values , and generate the fuzzy entropy value analysis result;

[0017] Among them, is the number of data points in the fuzzy set, is the membership degree value of the th data point in the fuzzy set, is the logarithmic transformation of the membership degree value, It is a correction coefficient set according to the fuzzy set.

[0018] As a further solution of the present invention, the step of obtaining the abnormal characteristics of the coolant flow rate is specifically as follows:

[0019] Compare the fuzzy entropy value corresponding to the fuzzy set in the fuzzy entropy value analysis result with the preset entropy value fluctuation range, mark the coolant flow rate data in the time period corresponding to the entropy value fluctuation range as abnormal, and generate an abnormal time period marking result;

[0020] Based on the abnormal coolant flow rate data corresponding to the abnormal time period in the abnormal time period marking result, extract the characteristics of the abnormal coolant flow rate data, including the maximum flow rate, the minimum flow rate, the flow rate change rate and the fluctuation amplitude, and generate the abnormal characteristics of the coolant flow rate.

[0021] As a further solution of the present invention, the step of obtaining the coolant temperature state sequence is specifically as follows:

[0022] Obtain the coolant temperature data collected by the coolant temperature sensor, perform discretization processing on the coolant temperature data, and extract the coolant temperature change characteristic points from the discretized coolant temperature data according to a fixed time step to generate a coolant temperature change characteristic point sequence;

[0023] Divide the coolant temperature change characteristic point sequence into different state intervals, analyze the change trend of adjacent coolant temperature change characteristic points in different state intervals, and generate a coolant temperature state sequence.

[0024] As a further solution of the present invention, the step of obtaining the analysis result of the optimal coolant temperature change path is specifically as follows:

[0025] According to the overall temperature change target of the coolant from the initial high temperature state to the target temperature state obtained, preset an ideal coolant target temperature trajectory, and generate a coolant target temperature trajectory setting result;

[0026] Use the Viterbi algorithm to calculate the maximum state transition probability of the coolant temperature state sequence at different heat exchange time nodes to obtain the node state transition information;

[0027] According to the state transition probability in the node state transition information, search for the optimal path with the smallest deviation between the coolant temperature state sequence and the coolant target temperature trajectory corresponding to the coolant target temperature trajectory setting result, and obtain the analysis result of the optimal coolant temperature change path.

[0028] As a further solution of the present invention, the step of obtaining the coolant temperature prediction sequence is specifically as follows:

[0029] Obtain the coolant temperature change trend in the analysis result of the optimal coolant temperature change path. Through the generalized predictive control algorithm, use the formula:

[0030]

[0031] Calculate at time Under the known conditions, for the coolant temperature at the th time step in the future , integrate to generate the coolant temperature at multiple time steps;

[0032] Among them, is the coolant temperature at the current time in the coolant temperature change trend of the optimal coolant temperature change path analysis result, is the change increment of the coolant temperature from the current time to the th time step in the future with reference to the coolant temperature change trend in the optimal coolant temperature change path analysis result, is the maximum number of time steps for predicting future time, is the correction coefficient set according to the coolant temperature change trend in the optimal coolant temperature change path analysis result;

[0033] Integrate the coolant temperatures at the multiple time steps and mark the abnormal coolant temperature segments among them as a reference for adjusting the heat exchange power or correcting the heat exchange time, and generate a coolant temperature prediction sequence.

[0034] As a further solution of the present invention, the specific steps for obtaining the optimized heat exchange control parameters are as follows:

[0035] Compare the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory to obtain a temperature deviation comparison result;

[0036] Based on the temperature deviation comparison result, analyze the heat exchange power adjustment amount and heat exchange time correction value under different heat exchange load conditions according to the temperature deviation, and generate optimized heat exchange control parameters.

[0037] As a further solution of the present invention, the specific steps for obtaining the eddy current heating and cooling logic control result are as follows:

[0038] Based on the coolant flow rate anomaly feature, determine the coolant pump speed that needs to be corrected, adjust the cooling pump control signal of the heat exchange device, and generate an optimized cooling pump control result;

[0039] Based on the corresponding heat transfer power adjustment amount and heat transfer time correction value in the optimized heat transfer control parameters, adjust the heat transfer power of the heat transfer equipment and the duration of the heat transfer process respectively, and combine the optimization results of the cooling pump control to generate the eddy current heating and cooling logic control result.

[0040] An eddy current heating and cooling logic control method is applied to the eddy current heating and cooling logic control system, and includes the following steps:

[0041] S1: Collect the coolant flow rate data entering the heat exchange chamber and construct a coolant flow rate time series. Construct a fuzzy set according to the coolant flow rate data in different time periods of the coolant flow rate time series, calculate the fuzzy entropy value of the fuzzy set, and generate a fuzzy entropy value analysis result;

[0042] S2: Mark the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result to generate a coolant flow rate abnormality feature;

[0043] S3: Obtain the coolant temperature data, extract the coolant temperature change feature points from the coolant temperature data, construct a coolant temperature state sequence, pass a preset ideal coolant target temperature trajectory, and search for the optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain the optimal coolant temperature change path analysis result;

[0044] S4: According to the coolant temperature change trend in the optimal coolant temperature change path analysis result collected, predict the coolant temperature in multiple future time steps, construct a coolant temperature prediction sequence, and analyze the heat transfer power adjustment amount and heat transfer time correction value under different heat transfer load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory to generate optimized heat transfer control parameters;

[0045] S5: Adjust the cooling pump control signal of the heat exchange device according to the coolant flow rate abnormality feature, and based on the optimized heat transfer control parameters, adjust the heat transfer power of the heat transfer equipment and the duration of the heat transfer process respectively to generate an eddy current heating and cooling logic control result.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0047] In the present invention, through the acquisition of coolant flow rate data and entropy value analysis, the data in different time periods are fuzzily divided by using fuzzy sets and the fuzzy entropy value is calculated, realizing the accurate marking and feature extraction of abnormal coolant flow rate data, and effectively enhancing the recognition ability of abnormal working conditions. In terms of predicting the change trend of coolant temperature, by extracting the characteristic points of coolant temperature change, constructing the coolant temperature state sequence, combining with the ideal coolant target temperature trajectory, and adopting the optimal path search technology, it is ensured that the change of coolant temperature is more in line with the target trajectory, improving the temperature control accuracy and stability. The Viterbi algorithm calculates the state transition probability, making the transition of temperature states more accurate and avoiding possible deviations in the temperature control process. Through the generalized predictive control algorithm, the coolant temperature in multiple future time steps is predicted, providing accurate data support for the power adjustment and heat exchange time correction of the heat exchange equipment, and realizing the dynamic adjustment of the heat exchange process under different load conditions. Combining the coolant flow rate characteristic analysis and the temperature prediction results, the rotational speed of the cooling pump is adjusted to ensure that the heat exchange power and heat exchange time are accurately matched with the requirements of different working conditions, ultimately realizing a more flexible and efficient eddy current heating and cooling logic control, improving the adaptability, operating efficiency and overall safety of the equipment, and significantly reducing the energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is the system flow chart of the present invention;

[0049] Figure 2 is the flow chart of obtaining the fuzzy entropy value analysis result of the present invention;

[0050] Figure 3 is the flow chart of obtaining the abnormal characteristics of coolant flow rate of the present invention;

[0051] Figure 4 is the flow chart of obtaining the coolant temperature state sequence of the present invention;

[0052] Figure 5 is the flow chart of obtaining the analysis result of the optimal coolant temperature change path of the present invention;

[0053] Figure 6 is the flow chart of obtaining the coolant temperature prediction sequence of the present invention;

[0054] Figure 7 is the flow chart of obtaining the optimized heat exchange control parameters of the present invention;

[0055] Figure 8 is the flow chart of obtaining the eddy current heating and cooling logic control result of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] Please refer to Figure 1 , the present invention provides a technical solution: a vortex heating and cooling logic control system, including:

[0058] The coolant flow rate entropy value analysis module collects the coolant flow rate data entering the heat exchange chamber and constructs a coolant flow rate time series. A fuzzy set is constructed based on the coolant flow rate data in different time periods in the coolant flow rate time series, the fuzzy entropy value of the fuzzy set is calculated, and a fuzzy entropy value analysis result is generated;

[0059] The entropy value anomaly monitoring module marks the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result and generates a coolant flow rate anomaly feature;

[0060] The temperature optimal path matching module obtains the coolant temperature data, extracts the coolant temperature change feature points from the coolant temperature data, constructs a coolant temperature state sequence, passes a preset ideal coolant target temperature trajectory, and searches for an optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain an optimal coolant temperature change path analysis result;

[0061] The temperature prediction module predicts the coolant temperature in multiple future time steps according to the coolant temperature change trend in the collected optimal coolant temperature change path analysis result, constructs a coolant temperature prediction sequence, and analyzes the heat exchange power adjustment amount and heat exchange time correction value under different heat exchange load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory, and generates optimized heat exchange control parameters;

[0062] The dynamic parameter adjustment module adjusts the cooling pump control signal of the heat exchange device according to the coolant flow rate anomaly feature, and adjusts the heat exchange power and the duration of the heat exchange process of the heat exchange equipment respectively based on the optimized heat exchange control parameters, and generates a vortex heating and cooling logic control result.

[0063] Please refer to Figure 2 , the specific steps for obtaining the fuzzy entropy value analysis result are as follows:

[0064] The coolant flow rate data entering the heat exchange chamber is collected through the flow sensor of the vortex cooling circuit, segmented and preprocessed according to a fixed time window, and a preprocessed coolant flow rate time series is constructed;

[0065] First, set an appropriate sampling frequency on the flow sensor. Usually, 10 Hz is selected to ensure the real-time nature of data acquisition. Transmit the data to a computer or an embedded processing platform through the flow sensor interface. The data includes the instantaneous coolant flow rate value and the corresponding timestamp. Use scripts written in LabVIEW or Python to implement data acquisition and recording. Store the data in segments according to a fixed time window (such as 1 second or 5 seconds). Then, perform denoising and correction operations on the acquired data. Use the median filtering method to remove single-point high-frequency noise. Use an outlier detection method (such as the 3σ principle) to mark and remove outliers that exceed the normal coolant flow rate range. To fill the data gaps after removal, the linear interpolation method can be used to fill in the missing values. Subsequently, calculate the average coolant flow rate and its change trend for each time period in a sliding window manner. Construct the coolant flow rate data for the obtained time periods into an ordered coolant flow rate time series.

[0066] Perform fuzzy partitioning on the coolant flow rate data for different time periods in the preprocessed coolant flow rate time series to generate corresponding fuzzy sets.

[0067] Perform fuzzy partitioning on the preprocessed coolant flow rate time series. First, use the K-Means clustering algorithm to perform preliminary clustering on the coolant flow rate data. Select the number of clusters as 3, corresponding to high coolant flow rate, medium coolant flow rate, and low coolant flow rate categories respectively. Complete the clustering calculation through the Scikit-learn toolkit in Python to obtain the central values and boundary ranges of each category of data. After clustering, perform normalization processing on each category of data to convert the coolant flow rate data into the interval [0, 1]. Subsequently, calculate the fuzzy membership degree for each coolant flow rate data according to the fuzzy set theory. The membership degree function adopts the form of a linear membership degree function. Determine the membership degree of each data point through the following formula:

[0068]

[0069] where, represents the membership degree value of the coolant flow rate data in the fuzzy set, and the numerical range is [0, 1]. The closer the membership degree value is to 1, the more the data conforms to the fuzzy set category. is the coolant flow rate data point of the current coolant, with the unit of m / s, and is obtained by real-time acquisition through the flow sensor. and are the boundary values of the fuzzy set, representing the minimum and maximum coolant flow rate ranges of the fuzzy set respectively, and are obtained through the clustering analysis method. For example, if the interval of the medium coolant flow rate set obtained by K-Means clustering is [5 m / s, 8 m / s], then and . It is the calculation formula of the linear membership function, indicating that within the interval , the relative position and its membership value of the coolant flow rate data point . The membership value is calculated according to the relative distance of the data point in the interval. The data located at the center of the interval has a higher membership, and the data close to the boundary has a lower membership. is a conditional expression that defines the function value of the membership calculation under different conditions. When is not within the interval, the membership is 0, indicating that the data point does not belong to the fuzzy set.

[0070] For example, assume that in a certain experiment, the coolant flow rate data range is from 3 m / s to 10 m / s. Through K-Means clustering analysis, the boundary of the low coolant flow rate set is determined as [3 m / s, 5 m / s], the medium coolant flow rate set is [5 m / s, 8 m / s], and the high coolant flow rate set is [8 m / s, 10 m / s]. If the coolant flow rate is 5.5 m / s, which belongs to the interval [5, 8] of the medium coolant flow rate set, then the membership value is . Calculate the membership values for all coolant flow rate data points in turn, and finally form a fuzzy set.

[0071] Based on the fuzzy set, use the formula:

[0072]

[0073] Calculate the fuzzy entropy value of the fuzzy set , integrate different fuzzy entropy values , and generate the analysis result of the fuzzy entropy value;

[0074] Among them, is the number of data points in the fuzzy set, which is determined by the coolant flow rate data collected in the experiment. The number of data points is equal to the total number of valid coolant flow rate data within the sampling time window. is the membership value of the th data point in the fuzzy set, which is calculated through the membership function, indicating the membership degree of each data point in the fuzzy set. The membership value range is [0, 1]. is the logarithmic transformation of the membership value, with the unit of dimensionless. The logarithmic operation is used to quantify the distribution complexity of the membership value. The logarithm base is 2, indicating the measurement by binary information entropy. is the correction coefficient set according to the fuzzy set, which is used to adjust the sensitivity of the entropy value to the fluctuation degree of the coolant flow rate. The correction coefficient is obtained through experimental statistics, and the calculation formula is , is the standard deviation of the coolant flow rate, which is obtained through statistical analysis of the collected coolant flow rate data and reflects the amplitude of the coolant flow rate fluctuation. is the average value of the coolant flow rate, obtained by averaging the collected coolant flow rate data, with the unit of m / s.

[0075] Suppose that during a certain measurement, three valid data points appear within the corresponding fuzzy set, and their membership degrees are measured as , , , and it is statistically obtained within the same measurement period that , . Therefore, . Substitute the above content into the improved formula:

[0076]

[0077] This result shows that the fuzzy entropy value of the current coolant flow rate time series is 0.0819. After incorporating the correction of the coolant flow rate fluctuation degree, the value of the entropy more objectively reflects the sensitivity of the system to the unstable components of the coolant flow rate, and can provide a more reliable reference for subsequent judgment of whether the coolant flow rate fluctuation is abnormal.

[0078] Please refer to Figure 3 for the specific steps to obtain the abnormal characteristics of the coolant flow rate:

[0079] Compare the fuzzy entropy value of the corresponding fuzzy set in the fuzzy entropy value analysis result with the preset entropy value fluctuation range, mark the coolant flow rate data in the time period exceeding the entropy value fluctuation range as abnormal, and generate the abnormal time period marking result;

[0080] Extract the entropy value corresponding to each time period from the fuzzy entropy value analysis result, and compare it with the set entropy value fluctuation range. The fluctuation range is based on the mean and standard deviation of the historical entropy value data, and the upper and lower limits are set in the form of "entropy value mean plus or minus twice the entropy value standard deviation". Taking the fuzzy entropy value of the current coolant flow rate time series as 0.0819 as an example, assume that the mean of the historical entropy value is 0.08 and the standard deviation is 0.01. Then the fluctuation range is calculated as the upper and lower limits are 0.08 - 2×0.01 = 0.06 and 0.08 + 2×0.01 = 0.10 respectively. Therefore, when the entropy value fluctuates between 0.06 and 0.10, it belongs to the normal range. If the entropy value exceeds this range (such as 0.11 or 0.05), it is determined to be abnormal. Use the Matplotlib visualization tool to plot these results as a line chart to visually compare the entropy value of each time period with the fluctuation range. If the entropy value of a certain time period exceeds the upper and lower limits, record this time period as an abnormal period, and mark the specific timestamp and abnormal entropy value.

[0081] Based on the abnormal coolant flow rate data corresponding to the abnormal time period in the abnormal time period marking result, the features of the abnormal coolant flow rate data are extracted, including the maximum flow rate, the minimum flow rate, the flow rate change rate and the fluctuation amplitude, and the coolant flow rate abnormality features are generated;

[0082] Extract the time period data that exceeds the entropy value fluctuation range, and filter out the coolant flow rate data of the corresponding time period. First, read and segment the abnormal time period in the flow rate time series, and then use the Pandas data analysis tool to extract features of this data segment. The extracted content includes the maximum flow rate, minimum flow rate, flow rate change rate and fluctuation amplitude. The maximum flow rate and minimum flow rate are obtained by data sorting, and the maximum and minimum values ​​are extracted respectively. The flow rate change rate is obtained by calculating the difference between the flow rates at adjacent time points, specifically the flow rate at the next time point minus the flow rate at the previous time point, and the mean of all differences is used as the overall change rate. The fluctuation amplitude is the maximum flow rate minus the minimum flow rate, which represents the overall fluctuation range of the flow rate during this period of time. Finally, these abnormal features are organized into structured tables and exported or uploaded to the database in CSV format for subsequent analysis and cooling system optimization strategies.

[0083] See also Figure 4 , the steps for obtaining the coolant temperature state sequence are as follows:

[0084] Acquire coolant temperature data collected by a coolant temperature sensor, discretize the coolant temperature data, and extract coolant temperature change feature points from the discretized coolant temperature data according to a fixed time step to generate a coolant temperature change feature point sequence;

[0085] First, the sampling frequency is set to 1 second through the temperature sensor to record the coolant temperature in real time. The collected raw data may contain noise or mutation values. The data needs to be smoothed, and the three-point sliding average method is used to eliminate random fluctuations and eliminate abnormal values ​​beyond the reasonable range (such as temperature below -10°C or above 100°C). The smoothed data is segmented according to a fixed time step (such as every 5 seconds), and the characteristic temperature value is extracted from each segment of data. The characteristic value can select the average temperature in the time period as the representative value. In order to extract the characteristic points of coolant temperature change, the threshold range of temperature change needs to be set. Usually, the temperature change amplitude exceeding 0.5°C is defined as a valid change point. For example, if the temperature of two consecutive time periods is 30.0°C and 30.6°C respectively, the second point is marked as a characteristic point, indicating that the temperature has changed significantly. The characteristic point data is arranged in sequence to form a coolant temperature change sequence, which provides basic data for subsequent trend analysis and state construction.

[0086] Divide the coolant temperature change feature point sequence into different state intervals, analyze the change trends of adjacent coolant temperature change feature points in different state intervals, and generate a coolant temperature state sequence;

[0087] First, divide the temperature feature point data into three state intervals: low temperature state (0°C - 20°C), medium temperature state (20°C - 50°C), and high temperature state (50°C - 80°C), and assign corresponding state labels to each temperature feature point. For example, if the temperature feature point is 35°C, it is marked as the medium temperature state; if the temperature is 65°C, it is marked as the high temperature state. Then, analyze the temperature change trend of adjacent feature points. The specific judgment criteria are as follows: If the temperature rise amplitude between two adjacent feature points is ≥1°C, it is determined as "temperature rising"; if the decline amplitude is ≥1°C, it is determined as "temperature falling"; if the change amplitude is less than 1°C, it is marked as "temperature stable". For example, if the feature point temperatures are 30°C, 32°C, 33°C, 35°C in sequence, this section is marked as a continuous rising trend; if the feature point temperatures are 60°C, 58°C, 57°C in sequence, it is marked as a continuous falling trend. By recording the order and duration of temperature state changes, a temperature state sequence is formed, providing accurate input data for subsequent optimal path matching and state transition probability calculation. Combining with the eddy current heating and cooling logic control scenario, if the temperature state sequence shows that the temperature continuously enters the high temperature interval (≥50°C) and lasts for more than 10 minutes without a downward trend, it can be judged that the coolant temperature fails to decrease in time, which may be due to insufficient heat exchange time or low cooling power setting, and further optimization of parameter configuration is required.

[0088] Please refer to Figure 5 , and the specific steps for obtaining the analysis result of the optimal coolant temperature change path are as follows:

[0089] According to the overall temperature change target of the coolant from the initial high temperature state to the target temperature state obtained, preset an ideal coolant target temperature trajectory, and generate a coolant target temperature trajectory setting result;

[0090] First, it is necessary to clarify the overall temperature change target of the coolant from the initial high-temperature state to the target temperature state. Assume that the initial temperature of the system is 80°C and the final target temperature is 40°C. Then, according to the actual heat exchange efficiency and process requirements, the temperature drop process can be divided into three stages: a rapid cooling stage (80°C - 60°C), a medium-speed cooling stage (60°C - 50°C), and a slow cooling stage (50°C - 40°C). In the rapid cooling stage, the ideal temperature drop rate can be set to 10°C per minute, in the medium-speed stage to 5°C per minute, and in the slow stage to 2°C per minute, thus forming a multi-segment linear cooling trajectory. By recording the target temperature values every minute, a target temperature trajectory sequence is generated. For example, the target temperatures in the first 5 minutes are 80°C, 70°C, 60°C, 55°C, and 50°C respectively. This sequence serves as the ideal coolant target temperature trajectory, providing a reference benchmark for subsequent state matching. In practice, dynamic correction can be carried out through a temperature controller to ensure that the deviation between the actual temperature and the target temperature trajectory is maintained within a reasonable range.

[0091] The Viterbi algorithm is used to calculate the maximum state transition probability of the coolant temperature state sequence at different heat exchange time nodes, obtaining the node state transition information;

[0092] For calculating the maximum state transition probability of the coolant temperature state sequence at different heat exchange time nodes, the formula is used:

[0093]

[0094] where, is the maximum state transition probability that the coolant temperature is in state at time . It is the state transition probability of a single heat exchange time node calculated by the Viterbi algorithm, maximizing the path probability to ensure the selection of the optimal state. is the state transition probability of observing the coolant temperature in state . It is estimated by fitting through statistical historical temperature data and actual temperature distribution. For example, if is the temperature range of 50°C - 80°C, then represents the probability of observing a temperature of 75°C within this range. The histogram estimation method or Gaussian distribution fitting can be used for calculation. is the maximum state transition probability that the coolant temperature is in state at time . It is the optimal path probability of the previous time node state, used to recursively calculate the state probability of the current time node. is the transition from state to state The probability represents the probability of the temperature changing from one interval state to another. It is calculated by statistically analyzing the historical temperature change sequence, calculating the frequency matrix and normalizing it to a probability. For example, if among the past 100 temperature changes, 30 times the temperature jumps from state 1 (0°C - 20°C) to state 2 (20°C - 50°C), then . is the state transition probability that takes the maximum value, which means that among all possible paths, the maximum probability from the previous state to the current state is selected as the optimal path. represents the previous time node The state number under it, such as state 1, state 2, state 3; represents time The state number.

[0095] Suppose there are three temperature state intervals, state 1 (0°C - 20°C), state 2 (20°C - 50°C), and state 3 (50°C - 80°C). It is observed that the actual temperature at time is 35°C, which belongs to state 2 (20°C - 50°C), and its observation probability , time The state probability and state transition probability matrix at the moment are as follows: , , , and the state transition probability matrix is: , and the observation probability: , , .

[0096] Calculate the probability of state 1:

[0097]

[0098] Calculate the probability of state 2:

[0099]

[0100] Calculate the probability of state 3:

[0101]

[0102] The result shows that at time , the transition probability of state 1 is 0.336, the transition probability of state 2 is 0.108, and the transition probability of state 3 is 0.02. Finally, state 1 with the highest probability is selected as the time The optimal conversion state at a moment. This indicates that at this heat exchange time node, the coolant temperature is most likely to be in state 1 (0°C - 20°C). This process recursively calculates the optimal path probability of each state at each time node, ensuring the selection of the path with the smallest deviation, thereby accurately matching the coolant temperature change trajectory and optimizing the heat exchange process.

[0103] According to the state transition probability in the node state transition information, search for the optimal path with the smallest deviation between the coolant temperature state sequence and the corresponding coolant target temperature trajectory in the coolant target temperature trajectory setting result, and obtain the analysis result of the optimal coolant temperature change path;

[0104] First, use the Viterbi algorithm to calculate the state transition probability of each heat exchange time node and determine the optimal temperature state of each time node. For example, at the 1st minute, the transition probability of state 1 (0°C - 20°C) is 0.336, the transition probability of state 2 (20°C - 50°C) is 0.108, and the transition probability of state 3 (50°C - 80°C) is 0.02. Then, select state 1 with the highest probability as the optimal state at the 1st minute. Next, compare each optimal state in the state sequence with the target temperature trajectory point by point, calculate the deviation between the actual temperature and the target temperature, and the deviation value is obtained through the formula "actual temperature value minus target temperature value". For example, if the target temperature is 40°C and the actual temperature is 45°C, then the deviation value is +5°C. If the deviation values of 3 consecutive time nodes exceed ±5°C (such as the deviation values at the 1st minute, 2nd minute, and 3rd minute are +5°C, +6°C, and +7°C respectively), it is determined as an abnormal deviation section, recorded and a prompt is given to adjust the heat exchange time or cooling power. In the process of obtaining the minimum deviation path, through the minimum deviation path search method, starting from time node 0, recursively compare the cumulative deviation sums of each state path, gradually push forward backward, record the cumulative deviation values of all paths, and select the path with the minimum cumulative deviation as the final optimal path. Finally, organize the minimum deviation path into a time series path table, and use the Matplotlib software to draw the temperature change curve, and generate a visualization chart through a Python script to intuitively display the optimal path.

[0105] Please refer to Figure 6 , the specific steps for obtaining the coolant temperature prediction sequence are as follows:

[0106] Obtain the coolant temperature change trend in the analysis result of the optimal coolant temperature change path. Through the generalized predictive control algorithm, use the formula:

[0107]

[0108] Calculate at the moment Under the known conditions, for the coolant temperature at the th future time step , integrate to generate the coolant temperature at multiple time steps;

[0109] Among them, is the coolant temperature at the current moment of the coolant temperature change trend in the optimal coolant temperature change path analysis result, which is used as the starting temperature for prediction and is measured in real time by a coolant temperature sensor, unit: degree Celsius (°C). is the change increment of the coolant temperature from the current moment to the coolant temperature at the th time step in the future in reference to the coolant temperature change trend in the optimal coolant temperature change path analysis result. It is fitted through historical temperature change data, and the temperature increment for each future time step is deduced by combining the optimal temperature change path, unit: degree Celsius (°C). Assuming that in the historical data under similar heat exchange load conditions, the average temperature changes for each time step are -5°C, -3°C, and -2°C, then can be fitted to these temperature change increments. is to predict the coolant temperature at the future moment based on the known information at the moment. is the coolant temperature at the future represents the th time step pushed forward from the current time to the future. It is the time step index, range: , the maximum value is set according to the prediction needs. Usually, 5 - 10 time steps are selected for prediction. is the future time point, and the calculated temperature will correspond to the predicted value of the coolant temperature at this moment. The time step can be determined according to the system sampling frequency or operation requirements. For example, if the time step is 2 seconds, then represents 2 seconds later, represents 4 seconds later. is the maximum number of time steps for predicting the future time, that is, the upper limit of the number of time steps extended from the current moment to the future. It is determined by the control requirements of the heat exchange process and can be comprehensively determined according to the system response time, the change speed of the coolant temperature, and the performance of the heat exchange equipment. Usually, 5 - 10 time steps are selected to cover a reasonable prediction range. is a dimensionless correction coefficient set according to the coolant temperature change trend in the optimal coolant temperature change path analysis result, indicating the influence intensity of external environment or heat exchange load changes on the temperature increment. It is fitted based on the statistical data of the actual load fluctuation situation or environmental changes. The specific setting process is as follows: the range of external load changes and the influence on the coefficient: when the external load is large, the change amplitude of the temperature increment will be faster, and at this time, the correction coefficient should be appropriately amplified to , to improve the response speed to the temperature change trend. When the external load is small and the temperature change is relatively gentle, the correction coefficient should be reduced to , to avoid excessive adjustment of the temperature change increment. Judgment criteria and range setting: Load change rate (unit: kW / s), high load change rate (>2.5kW / s): The value range is 1.1–1.2, medium load change rate (1–2.5kW / s): The value range is 0.95–1.05, low load change rate (<1kW / s): The value range is 0.8–0.9. Assuming that the external load change during the heat exchange process is 3kW / s (within the high load change rate range), the correction coefficient can be set to , to amplify the temperature change increment and reflect the acceleration effect of high load on temperature change. Fluctuation range of coolant flow rate and its influence on the coefficient: An increase in flow rate will improve the heat exchange efficiency, the temperature will drop faster, and the correction coefficient should be increased to . A decrease in flow rate will reduce the heat exchange efficiency and the temperature change will slow down, and the correction coefficient should be reduced to . Judgment criteria and range setting: Flow rate change range (unit: L / min), high flow rate (>50L / min): The value range is 1.1–1.3, medium flow rate (20–50L / min): The value range is 1.0–1.1, low flow rate (<20L / min): The value range is 0.8–1.0. If the coolant flow rate increases from 10L / min to 60L / min, this indicates a significant increase in flow rate, and the correction coefficient can be set to , corresponding to a faster temperature change rate. Influence of ambient temperature: When the ambient temperature is high (>35°C), it is difficult for the coolant temperature to drop, and the correction coefficient should be reduced to , to reduce the temperature change increment. When the ambient temperature is low (<15°C), the coolant temperature drops quickly, and the correction coefficient should be increased to, to amplify the temperature change increment. Judgment criteria and range setting: Ambient temperature range (unit: °C), high ambient temperature (>35°C): The value range is 0.85–0.95, medium ambient temperature (15–35°C): The value range is 1.0–1.1, low ambient temperature (<15°C): The value range is 1.1–1.2. Assuming the current ambient temperature is 40°C, at this time it is difficult for the coolant temperature to drop quickly, and the correction coefficient can be set to , to slow down the temperature change increment and avoid error accumulation. In actual operation, the correction coefficient It is set according to the comprehensive influence of the load change rate, the coolant flow rate change, and the ambient temperature. For example: If the current load change rate is 2.8 kW / s (high), the coolant flow rate is 55 L / min (high), and the ambient temperature is 10 °C (low), the correction factor can be set according to the above criteria as , indicating that the temperature change increment is amplified by 15% on the original basis. is the total temperature change within the future time steps. After being adjusted by the correction factor, it represents the total temperature change amplitude.

[0110] Assume that the coolant temperature at the current moment is . The predicted temperature change increments for the next 3 time steps are: Step 1: , Step 2: , Step 3: . The dimensionless correction factor: Step 1: , Step 2: , Step 3: .

[0111] Calculate step by step for Step 1:

[0112]

[0113] Step 2:

[0114]

[0115] Step 3:

[0116]

[0117] Accumulate and calculate the total temperature change:

[0118]

[0119] The final predicted temperature:

[0120]

[0121] The results show that through predictive calculation, it is obtained that the coolant temperature will drop from 50 °C to 39.9 °C within the next 3 time steps, and the correction factor increases at the second time step, indicating that the influence of the external load is slightly higher at this time step. The final prediction sequence provides accurate reference data for the future temperature control strategy adjustment, ensuring a more efficient and stable cooling process.

[0122] Integrate the coolant temperatures at multiple time steps, mark the abnormal coolant temperature segments from them, use them as a reference for adjusting the heat exchange power or correcting the heat exchange time, and generate a coolant temperature prediction sequence;

[0123] First, gradually accumulate the temperature change increments at each prediction moment according to the time step, and arrange the predicted temperature values at each time node in chronological order as a prediction sequence. For example, assume the initial temperature is 50°C, and assume the temperatures in the next 10 time steps are 45°C, 42°C, 40°C, 38°C, etc. A complete temperature prediction sequence is obtained through recursive calculation. Then, compare the prediction sequence with the preset coolant target temperature trajectory point by point, analyze the deviation values between the two, and record the deviation results at each time step. If the deviation values at 5 consecutive time nodes exceed ±2°C, it is marked as an abnormal temperature segment, indicating that the heat exchange power needs to be adjusted or the heat exchange time needs to be corrected. Finally, use the prediction sequence to guide the adjustment of the heat exchange strategy to ensure the accuracy and reliability of the cooling process.

[0124] Please refer to Figure 7 , and the specific steps for obtaining the optimized heat exchange control parameters are as follows:

[0125] Compare the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory to obtain the temperature deviation comparison result;

[0126] Suppose it is predicted through calculation that the coolant temperature will drop from 50°C to 39.9°C in the next 3 time steps. Combining this prediction result, compare it with the preset ideal coolant target temperature trajectory to clarify the temperature deviation between the actual temperature and the target temperature. The ideal coolant target temperature trajectory is from 80°C to 40°C, which is divided into a rapid cooling stage (80°C to 60°C), a medium-speed cooling stage (60°C to 50°C), and a slow cooling stage (50°C to 40°C). In the rapid cooling stage, the temperature drop rate is set to 10°C per minute, in the medium-speed stage, 5°C per minute, and in the slow stage, 2°C per minute, thus generating a multi-segment linear target temperature trajectory. Suppose the current predicted temperature sequence is 50°C, 45°C, 39.9°C in the next 3 time steps, and the corresponding target temperature trajectory sequence is 50°C, 46°C, 42°C. Comparing the two, the temperature deviations are 0°C, -1°C, -2.1°C respectively. The deviations are small but show a continuous increasing trend. Especially at the third time step, the deviation reaches -2.1°C, indicating that the effect of the heat exchange load in the slow cooling stage has weakened, possibly due to changes in the external load resulting in a decrease in the heat exchange efficiency. In practice, by visualizing the deviation data and dynamically tracking it in combination with the target trajectory sequence, the specific trend and peak position of the deviation development can be clarified, providing basic data support for subsequent heat exchange power adjustment and heat exchange time correction, so as to achieve precise control.

[0127] Based on the temperature deviation comparison results, analyze the adjustment amount of the heat exchange power and the correction value of the heat exchange time under different heat exchange load conditions according to the temperature deviation, and generate optimized heat exchange control parameters.

[0128] According to the temperature deviation results, further analyze the adjustment amount of the heat exchange power and the correction value of the heat exchange time under different heat exchange load conditions, and generate optimized heat exchange control parameters. First, for the temperature deviation data of the next 3 time steps, clarify the amplitude of the temperature deviation and its change trend. Assume that the deviation is 0°C in the first time step, no power adjustment and time correction are required. The temperature deviation in the second time step is -1°C, and a slight power compensation is needed. Increase the heat exchange power by 5% to improve the heat exchange efficiency. At the same time, the temperature deviation in the third time step expands to -2.1°C, indicating that a greater adjustment is needed in the heat exchange process. At this time, the heat exchange power can be increased by 10%, and the heat exchange time can be extended by 2 minutes to ensure that the temperature change is consistent with the target trajectory. In actual operation, the heat exchange power can be achieved by adjusting the rotation speed of the cooling pump in real time. For example, it is increased to 105% of the original power in the second time step and 110% in the third time step. The correction value of the heat exchange time is achieved by extending the heat exchange time window to achieve more accurate temperature control. Combining these adjustment operations, finally generate optimized heat exchange control parameters to guide subsequent dynamic heat exchange operations, ensure that the coolant temperature change is more in line with the preset target trajectory, and improve the heat exchange efficiency and stability of the overall system.

[0129] Please refer to Figure 8 , and the specific steps for obtaining the control result of the eddy current heating and refrigeration logic are as follows:

[0130] Based on the abnormal characteristics of the coolant flow rate, judge the rotation speed of the coolant pump that needs to be corrected, adjust the control signal of the cooling pump of the heat exchange device, and generate an optimized result for the cooling pump control.

[0131] First, obtain the real-time data of the coolant flow rate, and use data analysis methods to identify the deviation between the current flow rate and the preset target value, and determine whether the pump speed needs to be corrected. Assume that the current target coolant flow rate is 6 L / min, while the actually measured flow rate is 5.1 L / min, resulting in a flow rate deviation of -0.9 L / min, which exceeds the preset allowable deviation range (±0.5 L / min). According to the PID control rule, calculate the corresponding speed correction amount. Assume that the basic speed of the cooling pump is 1000 rpm, and each 0.1 L / min deviation corresponds to a correction amount of 15 rpm. Then, this deviation requires a correction of 135 rpm, and the pump speed is adjusted to 1135 rpm. The corrected cooling pump control signal is transmitted to the pump driver through PWM (pulse width modulation) to adjust the pump speed in real time to maintain the target flow rate, and then continuous data monitoring and flow rate feedback are carried out. If the flow rate deviation measured every 2 seconds within 5 consecutive time steps is within ±0.2 L / min, it is considered that the pump speed has stabilized and the flow rate has returned to the target range. This process ensures the stability of the coolant flow rate and provides basic data support for the precise adjustment of the subsequent heat transfer power and heat transfer time.

[0132] Based on the corresponding heat transfer power adjustment amount and heat transfer time correction value in the optimized heat transfer control parameters, adjust the heat transfer power of the heat transfer equipment and the duration of the heat transfer process respectively, and combine the optimization results of the cooling pump control to generate the eddy current heating and cooling logic control result.

[0133] First, analyze the current temperature deviation to clarify the increase or decrease amount of the heat transfer power and the time correction requirement. Assume that the target temperature is 38 °C and the actual temperature is 42 °C, and the temperature deviation is +4 °C. According to the heat transfer power adjustment rule, each 1 °C deviation corresponds to a 10% power increase. Then, at this time, the heat transfer power needs to be increased by 40%. If the current heat transfer power is 800 W, the corrected power should be set to 1120 W. In addition, calculate the time correction value through the heat transfer rate curve and the temperature change trend. Assume that the standard heat transfer duration is 15 minutes, and the extended time is adjusted by 3 minutes according to the current power increase. The final heat transfer time is 18 minutes. The adjustment of the heat transfer power is completed by adjusting the current intensity of the eddy current heating equipment, and the time correction is achieved through the start and stop control of the heat transfer process. Continuous temperature monitoring ensures that the correction process is consistent with the target temperature trajectory, avoiding temperature overshoot or insufficiency, and finally generates the eddy current heating and cooling logic control result to ensure the efficient and stable operation of the system.

[0134] An eddy current heating and cooling logic control method is applied to the eddy current heating and cooling logic control system, including the following steps:

[0135] S1: Collect the coolant flow rate data entering the heat exchange chamber and construct a coolant flow rate time series. Construct a fuzzy set based on the coolant flow rate data in different time periods in the coolant flow rate time series, calculate the fuzzy entropy value of the fuzzy set, and generate a fuzzy entropy value analysis result;

[0136] S2: Mark the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result to generate coolant flow rate abnormal characteristics;

[0137] S3: Obtain the coolant temperature data, extract the coolant temperature change characteristic points from the coolant temperature data, construct a coolant temperature state sequence, pass a preset ideal coolant target temperature trajectory, and search for the optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain the optimal coolant temperature change path analysis result;

[0138] S4: According to the coolant temperature change trend in the collected optimal coolant temperature change path analysis result, predict the coolant temperature in multiple future time steps, construct a coolant temperature prediction sequence, and analyze the heat transfer power adjustment amount and heat transfer time correction value under different heat transfer load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory to generate optimized heat transfer control parameters;

[0139] S5: Adjust the cooling pump control signal of the heat exchange device according to the coolant flow rate abnormal characteristics, and based on the optimized heat transfer control parameters, adjust the heat transfer power and the duration of the heat transfer process of the heat exchange equipment respectively to generate an eddy current heating and cooling logic control result.

[0140] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A vortex heating and refrigeration logic control system, characterized in that, The system includes: The coolant flow rate entropy value analysis module collects the coolant flow rate data entering the heat exchange chamber and constructs a coolant flow rate time series. A fuzzy set is constructed based on the coolant flow rate data in different time periods in the coolant flow rate time series, the fuzzy entropy value of the fuzzy set is calculated, and a fuzzy entropy value analysis result is generated; The entropy value anomaly monitoring module marks the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result, and generates a coolant flow rate anomaly feature; The temperature optimal path matching module obtains the coolant temperature data, extracts the coolant temperature change feature points from the coolant temperature data, constructs a coolant temperature state sequence, passes a preset ideal coolant target temperature trajectory, and searches for the optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain an optimal coolant temperature change path analysis result; The temperature prediction module predicts the coolant temperature in multiple future time steps according to the coolant temperature change trend in the collected optimal coolant temperature change path analysis result, constructs a coolant temperature prediction sequence, and analyzes the heat exchange power adjustment amount and heat exchange time correction value under different heat exchange load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory, and generates optimized heat exchange control parameters; The dynamic parameter adjustment module adjusts the cooling pump control signal of the heat exchange device according to the coolant flow rate anomaly feature, and adjusts the heat exchange power of the heat exchange device and the duration of the heat exchange process respectively based on the optimized heat exchange control parameters, and generates a vortex heating and cooling logic control result.

2. The eddy current heating and refrigeration logic control system according to claim 1, characterized in that, The specific steps for obtaining the fuzzy entropy value analysis result are as follows: Collect the coolant flow rate data entering the heat exchange chamber through the flow sensor of the vortex cooling circuit, segment the coolant flow rate data according to a fixed time window and perform preprocessing to construct a preprocessed coolant flow rate time series; Perform fuzzy partitioning on the coolant flow rate data in different time periods in the preprocessed coolant flow rate time series to generate corresponding fuzzy sets; Based on the fuzzy set, use the formula: ， Calculate the fuzzy entropy value of the fuzzy set , integrate different fuzzy entropy values , and generate the analysis result of the fuzzy entropy value; Among them, is the number of data points in the fuzzy set, is the membership degree value of the th data point in the fuzzy set, is the logarithmic transformation of the membership degree value, is the correction coefficient set according to the fuzzy set.

3. The eddy current heating and refrigeration logic control system according to claim 1, characterized in that, The specific steps for obtaining the coolant flow rate anomaly feature are as follows: Compare the fuzzy entropy value of the fuzzy set corresponding to the fuzzy entropy value analysis result with a preset entropy value fluctuation range, mark the coolant flow rate data in the corresponding time period exceeding the entropy value fluctuation range as abnormal, and generate an abnormal time period marking result; Based on the abnormal coolant flow rate data in the corresponding abnormal time period in the abnormal time period marking result, extract the features of the abnormal coolant flow rate data, including the maximum flow rate, the minimum flow rate, the flow rate change rate, and the fluctuation amplitude, and generate a coolant flow rate anomaly feature.

4. The eddy current heating and refrigeration logic control system according to claim 1, characterized in that, The specific steps for obtaining the coolant temperature state sequence are as follows: Obtain the coolant temperature data collected by the coolant temperature sensor, perform discretization processing on the coolant temperature data, and extract the coolant temperature change feature points from the discretized coolant temperature data according to a fixed time step to generate a coolant temperature change feature point sequence; Divide the coolant temperature change characteristic point sequence into different state intervals, analyze the change trends of adjacent coolant temperature change characteristic points in different state intervals, and generate a coolant temperature state sequence.

5. The eddy current heating and refrigeration logic control system according to claim 4, wherein The specific steps for obtaining the analysis result of the optimal coolant temperature change path are as follows: According to the overall temperature change target of the coolant from the initial high temperature state to the target temperature state obtained, preset an ideal coolant target temperature trajectory, and generate a coolant target temperature trajectory setting result; Use the Viterbi algorithm to calculate the maximum state transition probability of the coolant temperature state sequence at different heat exchange time nodes to obtain node state transition information; According to the state transition probability in the node state transition information, search for the optimal path with the smallest deviation between the coolant temperature state sequence and the corresponding coolant target temperature trajectory in the coolant target temperature trajectory setting result to obtain the analysis result of the optimal coolant temperature change path.

6. The eddy current heating and refrigeration logic control system according to claim 1, wherein, The specific steps for obtaining the coolant temperature prediction sequence are as follows: Obtain the coolant temperature change trend in the analysis result of the optimal coolant temperature change path. Through the generalized predictive control algorithm, use the formula: ， Calculate at the moment Under the known conditions, for the future The coolant temperature at the time step, and integrate to generate the coolant temperature at multiple time steps; Among them, is the coolant temperature at the current moment of the coolant temperature change trend in the analysis result of the optimal coolant temperature change path ; is the change increment of the coolant temperature from the current moment to the coolant temperature at the th time step in the future, with reference to the coolant temperature change trend in the analysis result of the optimal coolant temperature change path; is the maximum number of time steps for predicting future time; is the correction coefficient set according to the coolant temperature change trend in the analysis result of the optimal coolant temperature change path. Integrate the coolant temperatures at multiple time steps and mark the abnormal coolant temperature segments among them as a reference for adjusting the heat exchange power or correcting the heat exchange time to generate a coolant temperature prediction sequence.

7. The eddy current heating and refrigeration logic control system according to claim 6, wherein The specific steps for obtaining the optimized heat exchange control parameters are as follows: Compare the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory to obtain a temperature deviation comparison result; Based on the temperature deviation comparison result, analyze the heat exchange power adjustment amount and heat exchange time correction value under different heat exchange load conditions according to the temperature deviation to generate optimized heat exchange control parameters.

8. The eddy current heating and refrigeration logic control system according to claim 1, wherein The specific steps for obtaining the eddy current heating and cooling logic control result are as follows: Based on the coolant flow rate anomaly feature, determine the coolant pump speed that needs to be corrected, adjust the cooling pump control signal of the heat exchange device, and generate an optimized cooling pump control result; Based on the corresponding heat exchange power adjustment amount and heat exchange time correction value in the optimized heat exchange control parameters, adjust the heat exchange power of the heat exchange equipment and the duration of the heat exchange process respectively, and combine the optimized cooling pump control result to generate an eddy current heating and cooling logic control result.

9. A vortex heating and refrigeration logic control method, applied to the vortex heating and refrigeration logic control system according to any one of claims 1-8, characterized in that, Include the following steps: S1: Collect the coolant flow rate data entering the heat exchange chamber and construct a coolant flow rate time sequence. Construct a fuzzy set according to the coolant flow rate data in different time periods of the coolant flow rate time sequence, calculate the fuzzy entropy value of the fuzzy set, and generate a fuzzy entropy value analysis result; S2: Mark the abnormal coolant flow rate data in the fuzzy set corresponding to the fuzzy entropy value analysis result to generate a coolant flow rate anomaly feature; S3: Obtain the coolant temperature data, extract the coolant temperature change characteristic points from the coolant temperature data, construct a coolant temperature state sequence, preset an ideal coolant target temperature trajectory, and search for the optimal path between the coolant temperature state sequence and the coolant target temperature trajectory to obtain the analysis result of the optimal coolant temperature change path; S4: According to the coolant temperature change trend in the analysis result of the optimal coolant temperature change path collected, predict the coolant temperature in multiple future time steps, construct a coolant temperature prediction sequence, and analyze the heat transfer power adjustment amount and heat transfer time correction value under different heat transfer load conditions by comparing the temperature deviation between the coolant temperature prediction sequence and the ideal coolant target temperature trajectory, so as to generate optimized heat transfer control parameters; S5: Adjust the cooling pump control signal of the heat exchange device according to the abnormal characteristics of the coolant flow rate, and adjust the heat transfer power and the duration of the heat transfer process of the heat exchange equipment respectively based on the optimized heat transfer control parameters to generate an eddy current heating and cooling logic control result.

Images