Control method and system of spiral wound heat exchanger based on internet of things

Abstract

This invention relates to the field of heat exchanger technology and discloses a control method and system for a spiral wound tube heat exchanger based on the Internet of Things (IoT). The method acquires real-time flow velocity distribution data within the tube using multi-point sensors, forming a first dataset. This dataset is then analyzed by region to obtain flow velocity deviation values, assessing heat exchange anomalies and locating anomaly locations, generating an anomaly region distribution map. A dynamic parameter adjustment scheme is calculated based on the heat exchange efficiency target, generating a first set of adjustment instructions. After execution, a second flow velocity dataset is acquired, and the matching degree is evaluated using a fuzzy control algorithm. If the preset standard is not met, a second set of adjustment instructions is generated based on operating conditions, ultimately outputting an operational status report. This method achieves the following effects: precise control of the internal flow velocity distribution of the spiral wound tube heat exchanger is realized, effectively solving the problems of local overheating and uneven heat exchange, improving heat exchange efficiency, achieving energy balance targets, and ensuring stable system operation.

Description

Technical Field

[0001] This invention relates to the field of heat exchanger technology, and in particular to a control method and system for a spiral wound tube heat exchanger based on the Internet of Things. Background Technology

[0002] Heat exchangers, as core equipment for energy transfer in industrial and civil sectors, play an irreplaceable role in industries such as chemical engineering, energy, and construction. Spiral wound tube heat exchangers are highly favored due to their compact structure and high heat transfer efficiency, but the development of their control technology faces numerous challenges. With the increasing demands for energy efficiency and system stability in industrial production, the shortcomings of existing control methods in dynamically adapting to complex operating conditions are becoming increasingly apparent.

[0003] Currently, most traditional control schemes rely on fixed parameters or empirical adjustments, making it difficult to respond in real time to changes in fluid properties or fluctuations in the external environment. Under high loads or variable operating conditions, the system response is slow, failing to effectively balance heat exchange efficiency and energy consumption, resulting in significant energy waste. Furthermore, fluid velocity, as a key factor affecting heat exchange efficiency, faces a significant technical bottleneck in its precise control. Existing methods typically rely solely on a single sensor to collect average flow velocity, ignoring the dynamic changes in velocity distribution within the pipe. This often leads to localized overheating or insufficient heat exchange within the heat exchanger, reducing equipment efficiency and potentially causing pipe scaling, wear, and other problems, affecting the long-term stable operation of the system.

[0004] Furthermore, existing control strategies exhibit significant response delays to adjustments in valve opening and pump speed. Due to a lack of refined analysis of flow velocity distribution, the system struggles to achieve dynamic matching of flow velocity and heat exchange efficiency under complex operating conditions, further exacerbating the problem of insufficient control precision. Therefore, how to dynamically adjust control parameters to achieve precise flow velocity regulation by real-time acquisition and in-depth analysis of in-tube flow velocity distribution data, combined with optimization targets for heat exchange efficiency and energy consumption, has become a critical issue that urgently needs to be addressed in the intelligent control of spiral wound tube heat exchangers. Summary of the Invention

[0005] This invention provides a control method and system for a spiral wound tube heat exchanger based on the Internet of Things, so as to achieve precise control of the internal flow velocity distribution of the spiral wound tube heat exchanger and improve heat exchange efficiency.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a control method for a spiral wound tube heat exchanger based on the Internet of Things, comprising:

[0007] By deploying multiple sensors, the flow velocity distribution data inside the spiral wound tube heat exchanger is acquired in real time, forming the first flow velocity distribution dataset.

[0008] The first velocity distribution dataset is analyzed by region to obtain the velocity deviation value of each region, and the heat transfer anomaly is evaluated based on the velocity deviation value to obtain the heat transfer anomaly evaluation result.

[0009] Based on the heat transfer anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated.

[0010] Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through the parameter calculation model;

[0011] After the valves and pumps have executed the first set of control instructions, the flow velocity distribution data in the pipe is reacquired to form a second flow velocity distribution dataset.

[0012] Based on the second velocity distribution dataset, the matching degree between velocity distribution and heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result.

[0013] When the matching degree evaluation result does not meet the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and the working condition requirements, and a second set of adjustment instructions for valve opening and pump speed is generated.

[0014] After the valves and pumps have executed the second set of adjustment instructions, they reacquire the flow velocity distribution data and heat exchange efficiency data, and output the adjusted operating status report.

[0015] In one optional implementation, the step of deploying multiple sensors to acquire real-time velocity distribution data within the spiral wound tube heat exchanger tubes, forming a first velocity distribution dataset, includes:

[0016] The multi-point sensors are used to collect real-time flow velocity distribution data in the pipe, forming an initial flow velocity distribution dataset.

[0017] The initial velocity distribution dataset is denoised and calibrated to obtain an intermediate velocity distribution dataset;

[0018] The intermediate velocity distribution data is stored in a structured manner according to timestamps and location coordinates to form the first velocity distribution dataset.

[0019] In one optional implementation, the step of performing regional analysis on the first velocity distribution dataset to obtain velocity deviation values ​​for each region, and then performing heat transfer anomaly assessment based on the velocity deviation values ​​to obtain heat transfer anomaly assessment results, includes:

[0020] Flow velocity information is extracted from the first flow velocity distribution dataset and preprocessed using stratified sampling to obtain a cleaned flow velocity dataset.

[0021] The pipe environment is divided into sub-regions using data segmentation technology, and the flow velocity distribution characteristics of each sub-region are determined based on the cleaned flow velocity dataset.

[0022] The flow velocity fluctuation amplitude of each sub-region is calculated using a preset flow velocity change analysis method, and a dynamic flow velocity index is generated to reflect the flow velocity change.

[0023] Based on the aforementioned dynamic flow velocity index, the deviation range is quantized to determine the flow velocity deviation value for each sub-region.

[0024] When the flow velocity deviation value exceeds a preset threshold, local overheating detection is triggered. By comparing the flow velocity deviation value with the distribution analysis data, abnormal areas with insufficient heat exchange are located.

[0025] The abnormal regions are classified using a support vector machine model to obtain the heat transfer anomaly assessment results.

[0026] In one optional implementation, the step of determining the anomaly location through deviation analysis based on the heat transfer anomaly assessment results and generating an anomaly area distribution map includes:

[0027] Based on the heat transfer anomaly assessment results, the spatial distribution characteristics of the deviation are calculated through deviation analysis to determine the preliminary location of the anomaly area;

[0028] The K-means clustering algorithm is used to classify the deviation data of the preliminary location and divide the abnormal areas into categories of local overheating or insufficient heat exchange.

[0029] Based on the abnormal region category, extract the geometric features and flow velocity distribution features within the region to generate a spatial distribution dataset;

[0030] The spatial distribution dataset is preprocessed using spatial interpolation methods to generate a high-resolution map of anomaly regions.

[0031] If there are continuous abnormal regions in the abnormal region distribution map, the region boundaries are located using a boundary detection algorithm to obtain the precise location;

[0032] By combining the precise location, flow velocity deviation value, and anomaly category, a distribution map of the anomaly area is generated.

[0033] In one optional implementation, the step of obtaining the flow velocity demand information of the corresponding region based on the abnormal region distribution map, and combining it with the heat exchange efficiency optimization target, and generating a first set of adjustment instructions for valve opening and pump speed through a parameter calculation model, includes:

[0034] Based on the distribution map of the abnormal areas, obtain the flow velocity demand information at the corresponding locations to form a flow velocity demand dataset;

[0035] Based on the preset heat exchange efficiency standard and the flow rate demand dataset, the adjustment data is calculated to obtain the initial configuration result of the dynamic parameters;

[0036] Based on the initial configuration results, determine the priority and magnitude of parameter adjustments, and output the first adjustment strategy;

[0037] When there are abnormal parameters in the first adjustment strategy, the abnormal parameters are corrected through data smoothing processing, and the second adjustment strategy is output.

[0038] Based on the second adjustment strategy, specific adjustment commands for valve opening and pump speed are generated, forming command set data;

[0039] By comparing the instruction set data with the real-time flow rate feedback information, the instruction set data is fine-tuned to obtain the first adjustment instruction set.

[0040] In one optional implementation, the step of evaluating the matching degree between the velocity distribution and heat transfer efficiency using a fuzzy control algorithm based on the second velocity distribution dataset to obtain the matching degree evaluation result includes:

[0041] Based on the second velocity distribution dataset, relevant fluid parameters and heat transfer characteristic parameters are extracted from a preset database to construct initial input data;

[0042] The initial input data is analyzed by the fuzzy control algorithm, and the matching degree between the flow velocity distribution and the heat exchange efficiency is calculated by combining the preset control rules to obtain the matching degree evaluation value.

[0043] Determine whether the matching degree evaluation value is greater than a preset evaluation threshold;

[0044] If so, the flow velocity distribution is determined to be highly matched with the heat transfer efficiency, and this is output as the matching degree evaluation result.

[0045] If not, it is determined that the flow velocity distribution and heat transfer efficiency are not well matched, and this is output as the matching degree evaluation result.

[0046] In one optional implementation, the step of recalculating the parameters to be adjusted and generating a second set of adjustment instructions for valve opening and pump speed by combining the second velocity distribution dataset and operating conditions includes:

[0047] The matching degree evaluation results are compared with the balance standard. If the analysis results do not meet the preset balance standard, a feedback adjustment mechanism is triggered to obtain preliminary adjustment requirement information.

[0048] Based on the preliminary adjustment requirements information, a parameter correction mechanism is used to generate secondary instruction data;

[0049] Based on the requirements of complex operating conditions, a preliminary control strategy for valve opening and pump speed is generated according to the secondary command data;

[0050] If the initial control strategy cannot meet the requirements of changing operating conditions, the optimized control strategy data can be obtained through iterative optimization.

[0051] Based on the control strategy data, a second set of adjustment instructions is generated for valve opening and pump speed.

[0052] In one optional implementation, the step of reacquiring the flow velocity distribution data and heat transfer efficiency data, and outputting an adjusted operating status report, includes:

[0053] The raw dataset is obtained by collecting flow velocity distribution data and heat exchange efficiency data after the equipment has been adjusted using sensors;

[0054] The original dataset was classified using the K-means clustering algorithm to obtain a feature pattern classification set of flow velocity distribution and heat transfer efficiency;

[0055] Based on the feature pattern classification set and the preset running status mapping table, the current running status is determined by matching, and the running status identifier is obtained;

[0056] The operating status report is generated by integrating the operating status identifier, flow rate distribution, and heat exchange efficiency data.

[0057] Secondly, the present invention provides a control system for a spiral wound tube heat exchanger based on the Internet of Things, comprising:

[0058] First data acquisition module: By deploying multiple sensors, it acquires the velocity distribution data inside the spiral wound tube heat exchanger tube in real time, forming the first velocity distribution dataset;

[0059] Heat transfer anomaly assessment module: Performs regional analysis on the first velocity distribution dataset to obtain the velocity deviation value of each region, and performs heat transfer anomaly assessment based on the velocity deviation value to obtain the heat transfer anomaly assessment result;

[0060] Anomaly map generation module: Based on the heat transfer anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated;

[0061] Adjustment command generation module: Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through parameter calculation model;

[0062] Second data acquisition module: After the valve and pump equipment complete the first set of adjustment instructions, it reacquires the flow velocity distribution data in the pipe to form a second flow velocity distribution dataset;

[0063] Matching degree evaluation module: Based on the second velocity distribution dataset, the matching degree between the velocity distribution and the heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result;

[0064] Adjustment command optimization module: When the matching degree evaluation result does not reach the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and working condition requirements, and a second adjustment command set for valve opening and pump speed is generated;

[0065] Operation status output module: After the valves and pumps have completed the second set of adjustment instructions, the flow velocity distribution data and heat exchange efficiency data are reacquired, and the adjusted operation status report is output.

[0066] Thirdly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the control method for the Internet of Things-based spiral wound heat exchanger described in any one of the above-described methods.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] (1) The first velocity distribution dataset is analyzed by region to obtain the velocity deviation value of each region, and the heat transfer anomaly assessment is performed based on the velocity deviation value to obtain the heat transfer anomaly assessment result. This step accurately obtains the velocity deviation of each region by analyzing the velocity data by region. Compared with the traditional average velocity acquisition, it can quickly locate abnormal areas such as local overheating and insufficient heat transfer, providing a reliable basis for subsequent parameter adjustment, effectively improving the accuracy of heat transfer anomaly detection, helping to optimize heat transfer efficiency, reduce equipment wear, and ensure stable system operation.

[0069] (2) Based on the heat exchange anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated. This step, based on the heat exchange anomaly assessment results, accurately locates the anomaly location through deviation analysis and presents the anomaly area distribution in the form of a visual map. It can intuitively show the anomaly range and characteristics, provide clear guidance for subsequent targeted adjustments, effectively shorten the fault investigation time, improve the anomaly handling efficiency, and ensure the stable and efficient operation of the spiral wound tube heat exchanger.

[0070] (3) Based on the distribution map of the abnormal areas, obtain the flow velocity demand information of the corresponding areas, and in conjunction with the heat exchange efficiency optimization target, generate the first set of adjustment instructions for valve opening and pump speed through a parameter calculation model. This step accurately obtains the flow velocity demand based on the distribution map of the abnormal areas, and generates the adjustment instruction set using a parameter calculation model in conjunction with the heat exchange efficiency target. It can achieve precise control of valve opening and pump speed for abnormal areas, effectively improve the problem of uneven flow velocity distribution, improve heat exchange efficiency, optimize energy consumption, and enable the heat exchanger to quickly return to a highly efficient and stable operating state.

[0071] (4) Based on the second velocity distribution dataset, the matching degree between the velocity distribution and heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result. This step evaluates the matching degree between the velocity distribution and heat transfer efficiency using a fuzzy control algorithm, which can adaptively handle uncertainties under complex operating conditions and accurately identify the dynamic relationship between the two. Compared with traditional methods, it avoids dependence on precise mathematical models, improves the flexibility and accuracy of evaluation, provides a reliable basis for subsequent parameter optimization, and helps to achieve an efficient and stable heat transfer process.

[0072] (5) Based on the second velocity distribution dataset and operating conditions, recalculate the parameters to be adjusted and generate a second set of adjustment instructions for valve opening and pump speed. This step combines the second velocity dataset and operating conditions to dynamically calculate the adjustment parameters and generate a second set of adjustment instructions. It can adapt to complex operating conditions, accurately match the velocity distribution and heat exchange efficiency, improve the pertinence and real-time performance of parameter adjustment, further optimize heat exchange efficiency, reduce energy consumption, and ensure stable and efficient operation of the heat exchanger under varying operating conditions. Attached Figure Description

[0073] Figure 1 This is a schematic flowchart of a control method for a spiral wound tube heat exchanger based on the Internet of Things provided in an embodiment of the present invention;

[0074] Figure 2 This is a schematic diagram of the control system of an Internet of Things-based spiral wound heat exchanger provided in an embodiment of the present invention. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] Reference Figure 1 The first embodiment of the present invention provides a control method for a spiral wound tube heat exchanger based on the Internet of Things, including the following steps:

[0077] S11. By deploying multiple sensors, the flow velocity distribution data inside the spiral wound tube heat exchanger tube is acquired in real time to form the first flow velocity distribution dataset.

[0078] S12, perform regional analysis on the first velocity distribution dataset to obtain the velocity deviation value of each region, and perform heat transfer anomaly assessment based on the velocity deviation value to obtain the heat transfer anomaly assessment result.

[0079] S13, Based on the heat transfer anomaly assessment results, determine the anomaly location through deviation analysis and generate an anomaly area distribution map;

[0080] S14. Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through the parameter calculation model.

[0081] S15, after the valve and pump equipment have completed the first set of adjustment instructions, the flow velocity distribution data in the pipe is reacquired to form a second flow velocity distribution dataset;

[0082] S16, Based on the second velocity distribution dataset, the matching degree between the velocity distribution and the heat exchange efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result;

[0083] S17, When the matching degree evaluation result does not meet the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and working condition requirements, and a second adjustment instruction set for valve opening and pump speed is generated.

[0084] S18, after the valves and pumps have completed the second set of adjustment instructions, reacquire the flow velocity distribution data and heat exchange efficiency data, and output the adjusted operating status report.

[0085] In step S11, by deploying multiple sensors, the velocity distribution data inside the spiral wound tube heat exchanger tube is acquired in real time to form the first velocity distribution dataset.

[0086] In one embodiment, the flow velocity distribution data in the pipe is collected in real time by the multi-point sensor to form an initial flow velocity distribution dataset; the initial flow velocity distribution dataset is denoised and calibrated to obtain an intermediate flow velocity distribution dataset; the intermediate flow velocity distribution data is structured and stored according to timestamps and location coordinates to form the first flow velocity distribution dataset.

[0087] In one specific embodiment, to form the first velocity distribution dataset, a set of ultrasonic velocity sensors is installed every 0.5 meters along the axial direction of the pipe inside the spiral wound tube heat exchanger, deploying a total of 20 points to construct a monitoring network covering the entire length of the pipe. These sensors collect velocity data at a frequency of 10 times per second and an accuracy of 0.01 meters per second, and upload it to a cloud database in real time via a wireless transmission module with a transmission rate of 100 Mbps, ensuring zero-latency data transmission. The collected raw data constitutes the initial velocity distribution dataset, which is processed using a wavelet transform denoising method based on Daubechies level 4 decomposition. A threshold of 0.05 is set to effectively separate noise signals, completing denoising and calibration to obtain an intermediate velocity distribution dataset. Finally, the velocity data from each sensor point is structured and stored according to a 1-second timestamp interval and 0.5-meter position coordinates, forming a three-dimensional matrix dataset containing three dimensions: time, location, and velocity value (the velocity value ranges from 0.2 to 5.0 meters per second), thereby constructing the first velocity distribution dataset that meets the requirements of subsequent processing.

[0088] In step S12, the first velocity distribution dataset is analyzed by region to obtain the velocity deviation value of each region, and the heat transfer anomaly is evaluated based on the velocity deviation value to obtain the heat transfer anomaly evaluation result.

[0089] In one implementation, flow velocity information is extracted from the first flow velocity distribution dataset, and preprocessed using stratified sampling to obtain a cleaned flow velocity dataset. Data segmentation technology is used to divide the pipe environment into sub-regions, and the flow velocity distribution characteristics of each sub-region are determined based on the cleaned flow velocity dataset. A preset flow velocity change analysis method is used to calculate the flow velocity fluctuation amplitude of each sub-region, generating a dynamic flow velocity index. The deviation range is quantized based on the dynamic flow velocity index to determine the flow velocity deviation value of each sub-region. When the flow velocity deviation value exceeds a preset threshold, local overheating detection is triggered. By comparing the flow velocity deviation value with the distribution analysis data, abnormal areas with insufficient heat exchange are located. A support vector machine model is used to classify the abnormal areas to obtain the heat exchange anomaly assessment result.

[0090] In a specific embodiment, for a first velocity distribution dataset containing 100 nodes (velocity range 0.5 to 2.0 m / s) within a pipe, the following operations are used to achieve regional analysis and heat transfer anomaly assessment: First, the dataset is preprocessed using stratified sampling. After stratification according to velocity ranges (0.5-1.0 m / s, 1.0-1.5 m / s, 1.5-2.0 m / s), 20% of the samples are extracted based on the number of nodes. Outliers other than 3σ are removed using the Laida criterion. Then, linear interpolation is used... Missing data was filled in using a value-based method to remove interfering information, resulting in a cleaned flow velocity dataset. Next, the K-means clustering algorithm (K=4) was used to divide the pipe environment into four sub-regions. Euclidean distances were iteratively calculated and cluster centers were updated to determine the flow velocity distribution characteristics of region A (mean velocity 1.8 m / s, standard deviation 0.2), region B (mean 1.5 m / s, standard deviation 0.15), region C (mean 1.2 m / s, standard deviation 0.1), and region D (mean 0.6 m / s, standard deviation 0.05). Subsequently, using the global mean flow velocity of 1.4 m / s as a baseline, the flow velocity deviation value for each region was calculated using the formula "deviation value = |region mean - global mean|", yielding values ​​of 0.4 for region A, 0.1 for region B, 0.2 for region C, and 0.8 for region D. A deviation threshold of 0.5 was set. Region D was identified as having insufficient heat transfer due to a deviation value of 0.8 exceeding the threshold. Region A, although not exceeding the threshold, had a high flow velocity, requiring monitoring for localized overheating. To verify the anomaly, the flow velocity distribution data of the regions was input into a heat conduction model. The calculated heat transfer coefficient for region D was 200 W / (m²•K), significantly lower than the normal value of 300 W / (m²•K), confirming it as an abnormal region with insufficient heat transfer. Finally, a support vector machine model was used to classify the abnormal regions, generating an anomaly report. Region D was marked as an area with insufficient heat transfer, and region A as a region with localized overheating risk monitoring, completing the heat transfer anomaly assessment.

[0091] In step S13, based on the heat exchange anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated.

[0092] In one embodiment, based on the heat transfer anomaly assessment results, the spatial distribution characteristics of the deviation are calculated through deviation analysis to determine the preliminary location of the anomaly region; the deviation data at the preliminary location is classified using a K-means clustering algorithm to categorize the anomaly regions into those with local overheating or insufficient heat transfer; based on the anomaly region categories, geometric features and flow velocity distribution features within the regions are extracted to generate a spatial distribution dataset; the spatial distribution dataset is preprocessed using a spatial interpolation method to generate a high-resolution anomaly region distribution map; if continuous anomaly regions exist in the anomaly region distribution map, the region boundaries are located using a boundary detection algorithm to obtain the precise location; and the anomaly region distribution map is generated by combining the precise location, flow velocity deviation value, and anomaly category.

[0093] In one specific embodiment, during the process of handling abnormal flow velocity deviations and generating an anomaly distribution map of the region, for example, when the sensor collects a flow velocity value of 2.5 m / s in a certain area, exceeding the normal range of 1.8-2.2 m / s, and the deviation value of 0.3 m / s exceeds the preset threshold of 0.2 m / s, the system immediately triggers an anomaly alarm. Subsequently, the deviation analysis module calls historical data and the current flow velocity distribution matrix, and uses a deviation location algorithm based on weighted average to calculate the flow velocity differences between this area and four neighboring areas as 0.3, 0.4, 0.2, and 0.1 m / s, respectively. Using a weighted average difference of 0.25 m / s as the deviation weight, and combining it with the spatial coordinate system, the abnormal area is initially located in the middle-left of the heat exchanger; at the same time, combined with the temperature data of 85 degrees Celsius in this area (above the normal range of 75-80 degrees Celsius), the anomaly type is confirmed to be insufficient heat exchange. Next, the system uses the K-means clustering algorithm to classify the deviation data of the initial location, extract regional geometric features and flow velocity distribution features, and generate a spatial distribution dataset. After preprocessing using spatial interpolation methods, a high-resolution distribution map of abnormal regions is generated, and a boundary detection algorithm is used to determine the precise boundaries of continuous abnormal regions. Finally, the system highlights the precise location, the flow velocity deviation value of 0.3 m / s, and the "insufficient heat exchange" category in red on the 3D heat exchanger model, with the color intensity corresponding to the degree of deviation. Specific coordinates and anomaly types are simultaneously labeled, generating an analysis report and completing the drawing of the abnormal region distribution map, providing a precise basis for subsequent optimization.

[0094] In step S14, based on the abnormal area distribution map, the flow velocity demand information of the corresponding area is obtained, and combined with the heat exchange efficiency optimization target, the first adjustment command set of valve opening and pump speed is generated through the parameter calculation model.

[0095] In one implementation, flow rate demand information at corresponding locations is obtained based on the abnormal area distribution map, forming a flow rate demand dataset; adjustment data is calculated based on the flow rate demand dataset in conjunction with a preset heat exchange efficiency standard to obtain an initial configuration result for dynamic parameters; the priority and magnitude of parameter adjustment are determined based on the initial configuration result, and a first adjustment strategy is output; when abnormal parameters exist in the first adjustment strategy, the abnormal parameters are corrected through data smoothing processing, and a second adjustment strategy is output; specific adjustment instructions for valve opening and pump speed are generated based on the second adjustment strategy, forming an instruction set data; the instruction set data is fine-tuned by comparing it with real-time flow rate feedback information to obtain the first adjustment instruction set.

[0096] In one specific embodiment, the system performs parameter adjustments based on an anomaly region distribution map: First, a high-resolution (1024×768) heat exchanger surface temperature data is acquired using a thermal imaging sensor to accurately identify an anomaly region at coordinates (200, 300) with a temperature reaching 85°C (the normal temperature range is below 70°C, exceeding the standard by 15°C). Using a K-means clustering algorithm (K=3, divided into high-temperature, medium-temperature, and anomaly temperature zones according to temperature gradient), the Euclidean distance between the center point of the anomaly region and surrounding pixels is calculated, ultimately determining a circular anomaly range with a radius of 50 pixels. The flow velocity in the pipe within the anomaly region is measured using an ultrasonic flow meter, obtaining a real-time flow velocity of 1.2 m / s (the standard design velocity of this equipment is 1.8 m / s). A PID control algorithm is used to calculate the flow rate adjustment (where the proportional coefficient Kp = 0.5 for rapid response to flow rate deviation; integral time Ti = 10s to eliminate accumulated errors from long-term operation; and derivative time Td = 2s to predict the flow rate change trend). Based on the difference between the target flow rate of 1.8 m / s and the measured value, a flow rate adjustment of 0.6 m / s is calculated. Using the heat exchange efficiency formula as the optimization objective, and considering the current operating conditions of an outlet temperature of 70°C, an inlet temperature of 30°C, and a hot fluid temperature of 100°C, the values ​​are substituted into the formula. The calculated actual efficiency is 0.6, and the target efficiency is set at 0.65. This is based on the quadratic function relationship between efficiency and flow rate. Through equation The target flow velocity is calculated to be v = 1.85 m / s. A dynamic parameter adjustment scheme is generated using a linear programming algorithm, considering the constraints of valve opening (0-100%, limited by mechanical structure) and pump speed (500-2000 rpm, the safe operating range of the equipment): Valve opening and flow velocity satisfy a linear relationship v = 0.02d (d is the opening percentage). An initial opening of 60% corresponds to a flow velocity of 1.2 m / s, and the target flow velocity of 1.85 m / s requires an opening of d = 92.5%. Pump speed and flow velocity satisfy v = 0.001n (n is the speed). An initial speed of 1200 rpm corresponds to 1.2 m / s, and the target speed needs to be adjusted to 1850 rpm. Finally, the command set "Adjust valve opening to 92.5%, adjust pump speed to 1850 rpm" is generated and sent to the PLC controller for execution via the Modbus protocol. The system collects flow rate feedback data in real time. When the deviation between the measured value and the target value exceeds 5%, a secondary optimization is triggered. By comparing the instruction set data with the real-time feedback information, fine adjustments are made to finally obtain the first adjustment instruction set.

[0097] In step S16, based on the second velocity distribution dataset, the matching degree between the velocity distribution and the heat exchange efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result.

[0098] In one implementation, based on the second velocity distribution dataset, relevant fluid parameters and heat transfer characteristic parameters are extracted from a preset database to construct initial input data. The initial input data is analyzed using the fuzzy control algorithm, and combined with preset control rules, the matching degree between the velocity distribution and heat transfer efficiency is calculated to obtain a matching degree evaluation value. It is then determined whether the matching degree evaluation value is greater than a preset evaluation threshold. If so, the velocity distribution and heat transfer efficiency are determined to be highly matched, and this is output as the matching degree evaluation result. If not, the matching degree between the velocity distribution and heat transfer efficiency is determined to be insufficient, and this is also output as the matching degree evaluation result.

[0099] In a specific embodiment, for a second velocity distribution dataset containing 100 sampling points, with velocity values ​​ranging from 0.5 to 5.0 m / s and heat transfer efficiencies ranging from 60% to 95%, the system first normalizes the velocity and heat transfer efficiency data to the 0-1 range using a data preprocessing module. For example, a velocity of 2.5 m / s is normalized to 0.5. Next, a fuzzy control system is constructed, defining velocity distribution and heat transfer efficiency as input variables and matching degree as output variables. A fuzzy rule base is established, such as "high velocity and high heat transfer efficiency, then high matching degree." The input variables are then fuzzified using a triangular membership function. For example, a velocity of 0.5 m / s corresponds to a "high" membership degree of 0.8 and a "medium" membership degree of 0.2, while a heat transfer efficiency of 0.7 (after normalization) corresponds to a "high" membership degree of 0.6 and a "medium" membership degree of 0.4. Then, the Mamdani method is used to calculate the fuzzy matching degree value through a fuzzy inference engine. The centroid method is used to defuzzify the value to obtain a specific value of 0.75 (i.e., a matching degree of 75%). This value is compared with the target matching degree threshold of 0.8. Since 0.75 is less than 0.8, the system determines that the flow velocity distribution and heat exchange efficiency are not well matched, and the matching degree evaluation result is output.

[0100] In step S17, the parameters to be adjusted are recalculated by combining the second flow velocity distribution dataset and the operating conditions, and a second set of adjustment instructions for valve opening and pump speed is generated.

[0101] In one implementation, a balance analysis is performed between the matching degree evaluation result and the balance standard. If the analysis result does not meet the preset balance standard, a feedback adjustment mechanism is triggered to obtain preliminary adjustment requirement information. Based on the preliminary adjustment requirement information, a parameter correction mechanism is used to generate secondary command data. Combining the requirements of complex operating conditions, a preliminary control strategy for valve opening and pump speed is generated based on the secondary command data. If the preliminary control strategy cannot meet the requirements of changing operating conditions, iterative optimization is performed to obtain optimized control strategy data. Based on the control strategy data, a second adjustment command set for valve opening and pump speed is generated.

[0102] In one specific embodiment, when the system detects that the matching degree evaluation result of 0.82 has not reached the preset balance standard of 0.9, the feedback adjustment module is triggered. The module collects real-time operating data (pipeline pressure 2.5MPa, flow rate 18m³ / h, temperature 45℃), and, considering complex operating conditions such as high-viscosity media (viscosity 150mPa•s), uses a PID algorithm (proportional coefficient Kp=0.6, integral time Ti=0.3s, derivative time Td=0.05s) to calculate the valve opening and pump speed deviations. Based on the formula... (Where e is the difference between the target flow rate of 20 m³ / h and the actual flow rate,) , (Kp represents the proportional coefficient, Ti represents the integral time, Ki represents the integral coefficient, Td represents the derivative time, and Kd represents the derivative coefficient), indicating that the valve opening needs to be adjusted from 35% to 42%; based on the flow-speed curve... (k is the pump characteristic coefficient 0.002, Q is the flow rate, and n is the pump speed). The calculation shows that the pump speed needs to be increased from 1200 rpm to 1350 rpm. The system sends this correction command to the actuator, the valve adjusts its opening at a rate of 0.5% / s, the pump adjusts its speed at a rate of 10 rpm / s, and the motor current is monitored (measured at 45A, not exceeding the 50A limit). After adjustment, data is collected again; the flow rate increases to 19.8 m³ / h, the pressure stabilizes at 2.48 MPa, and the matching degree increases to 0.89. Since this still does not meet the standard, the module iteratively optimizes Ki to 0.35 and repeats the calculation, ultimately generating a second set of adjustment commands for a valve opening of 42% and a pump speed of 1350 rpm.

[0103] In step S18, the flow velocity distribution data and heat exchange efficiency data are reacquired, and the adjusted operating status report is output.

[0104] In one implementation, the system collects adjusted flow velocity distribution data and heat exchange efficiency data using sensors to obtain an original dataset; it then classifies the original dataset using a K-means clustering algorithm to obtain a feature pattern classification set for flow velocity distribution and heat exchange efficiency; based on the feature pattern classification set and a preset operating status mapping table, the current operating status is determined by matching to obtain an operating status identifier; finally, the operating status identifier, flow velocity distribution, and heat exchange efficiency data are integrated to generate the operating status report.

[0105] In one specific embodiment, after the system performs equipment adjustments, it first uses a quadratic correction algorithm (based on Bernoulli's equation and the continuity equation) and pipe geometric parameters (inlet area A1 = 1.0 m², outlet area A2 = 0.5 m²) to apply the formula... (Where v1 is the inlet velocity and v2 is the outlet velocity), the initial uniform velocity of 2.0 m / s is adjusted to a linear distribution of 2.0 m / s at the inlet and 4.0 m / s at the outlet, resulting in a velocity distribution dataset [v1, v2] = [2.0, 4.0] m / s. Next, the heat transfer efficiency formula is used... (T_in is the inlet temperature, T_out is the outlet temperature, and T_max is the maximum theoretical temperature). Substituting T_in = 20°C, T_out = 60°C, and T_max = 100°C, the heat transfer efficiency is calculated to be 50%. Then, through the data comparison module, based on the stability threshold (flow rate change < 1.0 m / s², heat transfer efficiency fluctuation < 5%), a judgment is made using the formula... (Δv is the change in flow velocity, Δt is the adjustment time) The calculated flow velocity change rate is 1.0 m / s². By comparing with historical data, the heat exchange efficiency fluctuation is found to be 2%, which meets the requirements. Finally, the above data is collected by sensors to form a raw dataset, which is classified by K-means clustering algorithm. Combined with the preset operating status mapping table, the current operating status is determined. The operating status identifier, flow velocity distribution and heat exchange efficiency data are integrated to generate an operating status report: "System operating status: stable, flow velocity distribution [2.0, 4.0] m / s, heat exchange efficiency 50%, meeting the preset requirements."

[0106] refer to Figure 2 The second embodiment of the present invention provides a control system for a spiral wound tube heat exchanger based on the Internet of Things, including:

[0107] First data acquisition module: By deploying multiple sensors, it acquires the velocity distribution data inside the spiral wound tube heat exchanger tube in real time, forming the first velocity distribution dataset;

[0108] Heat transfer anomaly assessment module: Performs regional analysis on the first velocity distribution dataset to obtain the velocity deviation value of each region, and performs heat transfer anomaly assessment based on the velocity deviation value to obtain the heat transfer anomaly assessment result;

[0109] Anomaly map generation module: Based on the heat transfer anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated;

[0110] Adjustment command generation module: Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through parameter calculation model;

[0111] Second data acquisition module: After the valve and pump equipment complete the first set of adjustment instructions, it reacquires the flow velocity distribution data in the pipe to form a second flow velocity distribution dataset;

[0112] Matching degree evaluation module: Based on the second velocity distribution dataset, the matching degree between the velocity distribution and the heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result;

[0113] Adjustment command optimization module: When the matching degree evaluation result does not reach the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and working condition requirements, and a second adjustment command set for valve opening and pump speed is generated;

[0114] Operation status output module: After the valves and pumps have completed the second set of adjustment instructions, the flow velocity distribution data and heat exchange efficiency data are reacquired, and the adjusted operation status report is output.

[0115] It should be noted that the control system of the IoT-based spiral wound heat exchanger provided in the embodiments of the present invention is used to execute all process steps of the control method of the IoT-based spiral wound heat exchanger in the above embodiments. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0116] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, it implements the steps in the various control method embodiments for IoT-based spiral wound tube heat exchangers described above, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the data acquisition module.

[0117] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0118] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0119] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0120] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0121] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0122] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0123] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A control method for a spiral wound tube heat exchanger based on the Internet of Things, characterized in that, include: By deploying multiple sensors, the flow velocity distribution data inside the spiral wound tube heat exchanger is acquired in real time, forming the first flow velocity distribution dataset. The first velocity distribution dataset is analyzed by region to obtain the velocity deviation value of each region, and the heat transfer anomaly is evaluated based on the velocity deviation value to obtain the heat transfer anomaly evaluation result. Based on the heat transfer anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated. Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through the parameter calculation model; After the valves and pumps have executed the first set of control instructions, the flow velocity distribution data in the pipe is reacquired to form a second flow velocity distribution dataset. Based on the second velocity distribution dataset, the matching degree between velocity distribution and heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result. When the matching degree evaluation result does not meet the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and the working condition requirements, and a second set of adjustment instructions for valve opening and pump speed is generated. After the valves and pumps have executed the second set of adjustment instructions, they reacquire the flow velocity distribution data and heat exchange efficiency data, and output the adjusted operating status report.

2. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The process involves deploying multiple sensors to acquire real-time flow velocity distribution data within the spiral wound tube heat exchanger tubes, forming a first flow velocity distribution dataset, including: The multi-point sensors are used to collect real-time flow velocity distribution data in the pipe, forming an initial flow velocity distribution dataset. The initial velocity distribution dataset is denoised and calibrated to obtain an intermediate velocity distribution dataset; The intermediate velocity distribution data is stored in a structured manner according to timestamps and location coordinates to form the first velocity distribution dataset.

3. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The process of performing regional analysis on the first velocity distribution dataset to obtain velocity deviation values ​​for each region, and then performing heat transfer anomaly assessment based on the velocity deviation values ​​to obtain heat transfer anomaly assessment results includes: Flow velocity information is extracted from the first flow velocity distribution dataset and preprocessed using stratified sampling to obtain a cleaned flow velocity dataset. Data segmentation technology was used to divide the pipe environment into sub-regions, and the flow velocity distribution characteristics of each sub-region were determined based on the flow velocity dataset after cleaning. The flow velocity fluctuation amplitude of each sub-region is calculated using a preset flow velocity change analysis method, and a dynamic flow velocity index is generated to reflect the flow velocity change. Based on the aforementioned dynamic flow velocity index, the deviation range is quantized to determine the flow velocity deviation value for each sub-region. When the flow velocity deviation value exceeds a preset threshold, local overheating detection is triggered. By comparing the flow velocity deviation value with the distribution analysis data, abnormal areas with insufficient heat exchange are located. The abnormal regions are classified using a support vector machine model to obtain the heat transfer anomaly assessment results.

4. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The step of determining the anomaly location through deviation analysis based on the heat transfer anomaly assessment results and generating an anomaly area distribution map includes: Based on the heat transfer anomaly assessment results, the spatial distribution characteristics of the deviation are calculated through deviation analysis to determine the preliminary location of the anomaly area; The K-means clustering algorithm is used to classify the deviation data of the preliminary location and divide the abnormal areas into categories of local overheating or insufficient heat exchange. Based on the abnormal region category, extract the geometric features and flow velocity distribution features within the region to generate a spatial distribution dataset; The spatial distribution dataset is preprocessed using spatial interpolation methods to generate a high-resolution map of anomaly regions. If there are continuous abnormal regions in the abnormal region distribution map, the region boundaries are located using a boundary detection algorithm to obtain the precise location; By combining the precise location, flow velocity deviation value, and anomaly category, a distribution map of the anomaly area is generated.

5. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The step involves obtaining flow velocity demand information for the corresponding region based on the abnormal region distribution map, and combining this with the heat exchange efficiency optimization objective. A first set of adjustment commands for valve opening and pump speed is then generated through a parameter calculation model, including: Based on the distribution map of the abnormal areas, obtain the flow velocity demand information at the corresponding locations to form a flow velocity demand dataset; Based on the preset heat exchange efficiency standard and the flow rate demand dataset, the adjustment data is calculated to obtain the initial configuration result of the dynamic parameters; Based on the initial configuration results, determine the priority and magnitude of parameter adjustments, and output the first adjustment strategy; When there are abnormal parameters in the first adjustment strategy, the abnormal parameters are corrected through data smoothing processing, and the second adjustment strategy is output. Based on the second adjustment strategy, specific adjustment commands for valve opening and pump speed are generated, forming command set data; By comparing the instruction set data with the real-time flow rate feedback information, the instruction set data is fine-tuned to obtain the first adjustment instruction set.

6. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The step of evaluating the matching degree between the flow velocity distribution and heat transfer efficiency using a fuzzy control algorithm based on the second flow velocity distribution dataset to obtain the matching degree evaluation result includes: Based on the second velocity distribution dataset, relevant fluid parameters and heat transfer characteristic parameters are extracted from a preset database to construct initial input data; The initial input data is analyzed by the fuzzy control algorithm, and the matching degree between the flow velocity distribution and the heat exchange efficiency is calculated by combining the preset control rules to obtain the matching degree evaluation value. Determine whether the matching degree evaluation value is greater than a preset evaluation threshold; If so, the flow velocity distribution is determined to be highly matched with the heat transfer efficiency, and this is output as the matching degree evaluation result. If not, it is determined that the flow velocity distribution and heat transfer efficiency are not well matched, and this is output as the matching degree evaluation result.

7. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The process of combining the second flow velocity distribution dataset and operating conditions to recalculate the parameters to be adjusted and generate a second set of adjustment instructions for valve opening and pump speed includes: The matching degree evaluation results are compared with the balance standard. If the analysis results do not meet the preset balance standard, a feedback adjustment mechanism is triggered to obtain preliminary adjustment requirement information. Based on the preliminary adjustment requirements information, a parameter correction mechanism is used to generate secondary instruction data; Based on the requirements of complex operating conditions, a preliminary control strategy for valve opening and pump speed is generated according to the secondary command data; If the initial control strategy cannot meet the requirements of changing operating conditions, the optimized control strategy data can be obtained through iterative optimization. Based on the control strategy data, a second set of adjustment instructions is generated for valve opening and pump speed.

8. The control method for an IoT-based spiral wound tube heat exchanger according to claim 1, characterized in that, The process of reacquiring flow velocity distribution data and heat transfer efficiency data, and outputting an adjusted operating status report, includes: The raw dataset is obtained by collecting flow velocity distribution data and heat exchange efficiency data after the equipment has been adjusted using sensors; The original dataset was classified using the K-means clustering algorithm to obtain a feature pattern classification set of flow velocity distribution and heat transfer efficiency; Based on the feature pattern classification set and the preset running status mapping table, the current running status is determined by matching, and the running status identifier is obtained; The operating status report is generated by integrating the operating status identifier, flow rate distribution, and heat exchange efficiency data.

9. A control system for an Internet of Things-based spiral wound tube heat exchanger, characterized in that, include: First data acquisition module: By deploying multiple sensors, it acquires the velocity distribution data inside the spiral wound tube heat exchanger tube in real time, forming the first velocity distribution dataset; Heat transfer anomaly assessment module: The first velocity distribution dataset is analyzed by region to obtain the velocity deviation value of each region, and the heat transfer anomaly assessment is performed based on the velocity deviation value to obtain the heat transfer anomaly assessment result. Anomaly map generation module: Based on the heat transfer anomaly assessment results, the anomaly location is determined through deviation analysis, and an anomaly area distribution map is generated; Adjustment command generation module: Based on the abnormal area distribution map, obtain the flow velocity demand information of the corresponding area, and combine it with the heat exchange efficiency optimization target to generate the first adjustment command set of valve opening and pump speed through parameter calculation model; Second data acquisition module: After the valve and pump equipment complete the first set of adjustment instructions, it reacquires the flow velocity distribution data in the pipe to form a second flow velocity distribution dataset; Matching degree evaluation module: Based on the second velocity distribution dataset, the matching degree between the velocity distribution and the heat transfer efficiency is evaluated using a fuzzy control algorithm to obtain the matching degree evaluation result; Adjustment command optimization module: When the matching degree evaluation result does not reach the preset matching degree standard, the parameters to be adjusted are recalculated in combination with the second flow velocity distribution dataset and working condition requirements, and a second adjustment command set for valve opening and pump speed is generated; Operation status output module: After the valves and pumps have completed the second set of adjustment instructions, the flow velocity distribution data and heat exchange efficiency data are reacquired, and the adjusted operation status report is output.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the control method for an Internet of Things-based spiral wound heat exchanger as described in any one of claims 1 to 8.

Images