Low-temperature coupled heat pump remote monitoring and data acquisition system based on internet of things

Abstract

The application provides a low-temperature coupled heat pump remote monitoring and data acquisition system based on the Internet of Things, which comprises a data acquisition component that acquires key parameters such as water temperature, flow, compressor state and environmental temperature in real time through sensors, preliminarily processes the acquired key parameters to obtain the preliminarily processed key parameters, a data transmission component that transmits the preliminarily processed key parameters to a cloud server in real time through the Internet of Things, a cloud server that processes the key parameters by using a machine learning algorithm to optimize the operating parameters of the compressor, a feedback control component that automatically adjusts the working state of the low-temperature coupled heat pump according to the analysis result of the cloud server, and an intelligent terminal that is used for real-time viewing of the key parameters and receiving of the state alarm of the low-temperature coupled heat pump. The application realizes continuous monitoring, intelligent analysis and rapid response. The system realizes efficient energy use and optimized management, reduces energy consumption, and improves the reliability and service life of the equipment.

Description

Technical Field

[0001] This invention relates to the field of thermal energy conversion equipment technology, and in particular to a remote monitoring and data acquisition system for a low-temperature coupled heat pump based on the Internet of Things. Background Technology

[0002] A low-temperature coupled heat pump is a device specifically designed for heat transfer, extracting heat from low-temperature sources (such as air, water, or underground) and transferring it to a higher-temperature environment. It operates on the principle of a reverse Carnot cycle, transferring heat through the compression and expansion of the refrigerant. Low-temperature coupled heat pumps are efficient and environmentally friendly heat transfer devices suitable for various heating and cooling scenarios. Their outstanding energy efficiency and environmentally friendly characteristics make them an increasingly popular energy solution in modern buildings and industries, promoting the widespread application of renewable energy. However, the operating efficiency and capacity of existing low-temperature coupled heat pumps still need further improvement.

[0003] Prior art 1, application number: CN 202410470412.5, discloses a simulation and visualization system for coupled heating of an air source heat pump and a gas boiler. The system includes: an operation terminal for operating and controlling the system; a remote calculation module for calculating coupled heating data of the air source heat pump and gas boiler connected to the operation terminal's output; and a data storage database for storing the coupled heating data. Although this system utilizes coupled heating of an air source heat pump and a gas boiler, analyzes the shortcomings of these two systems when used alone, establishes a simulation model, and determines the basic heating methods of both systems based on their characteristics, resulting in a heating system scheme with good economic benefits, low energy consumption, and minimal environmental impact, its limited monitoring methods for key parameters such as water temperature and flow rate prevent effective remote monitoring and control, leading to poor operating efficiency of the low-temperature coupled heat pump.

[0004] Prior art two, application number: CN 202310368505.2, discloses a method for refined evaluation of the long-term operational performance of a ground source heat pump system. It uses design parameter data clusters for simulation calculations to establish a database of coupled heat transfer models between the buried pipe heat exchanger, heat pump, and building. It establishes a mapping between design parameters and operational results, forming a neural network model for fitting the long-term operational performance of the ground source heat pump system. By inputting design parameters, the neural network model is used to fit and predict the energy efficiency ratio, energy saving and emission reduction, and ground temperature in the buried pipe area, thus providing a refined assessment of the system's long-term applicability, economy, and environmental friendliness. While this method has advantages such as fast calculation speed, high calculation accuracy, and a comprehensive evaluation system for evaluating the energy efficiency ratio, energy saving and emission reduction, and ground temperature in the buried pipe area of ​​a ground source heat pump system over its life cycle, it lacks remote control of the heat pump, resulting in a need to improve the level of intelligent control of the equipment.

[0005] Prior art three, application number CN 202311504768.8, discloses a numerical heat transfer model and solution method for the thermal infiltration coupling of a medium-deep casing-type buried pipe. It establishes the governing equations for the thermal infiltration coupling between the medium-deep casing-type buried pipe and the soil / rock; establishes the equations for the fluid within the outer annulus of the medium-deep casing-type buried pipe; establishes the equations for the fluid within the inner pipe of the medium-deep casing-type buried pipe; obtains the formulas for the convective heat transfer coefficient and the Nusselt number; and derives the heat transfer model based on the above equations and formulas. While the numerical heat transfer model, considering complex factors such as soil / rock stratification, geothermal gradient, and groundwater seepage, can be used to reveal the influence of groundwater seepage and other factors on the heat extraction characteristics of buried pipes, and proposes a method for rapid model solving while ensuring computational accuracy, significantly improving the computational efficiency of the numerical heat transfer model and enabling it to guide engineering practice, it has limited improvement on the operating efficiency and response capability of heat pumps, and lacks effective monitoring of operating parameters.

[0006] Current technologies 1, 2, and 3 lack remote real-time monitoring and feedback adjustment capabilities, resulting in poor operational efficiency and responsiveness. Therefore, this invention provides an IoT-based remote monitoring and data acquisition system for low-temperature coupled heat pumps. This system uses IoT technology to collect and transmit key parameter data such as water temperature, flow rate, and compressor status in real time. Based on data analysis, it provides remote real-time monitoring and feedback adjustment functions. Through real-time monitoring and data analysis optimization, it effectively improves system operating efficiency and responsiveness. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a remote monitoring and data acquisition system for low-temperature coupled heat pumps based on the Internet of Things, comprising:

[0008] The data acquisition component is responsible for collecting key parameters in real time, performing preliminary processing on the collected key parameters, and obtaining the preliminary processed key parameters.

[0009] The data transmission component is responsible for transmitting the pre-processed key parameters to the cloud server in real time via the Internet of Things; the cloud server processes the key parameters and optimizes the compressor's operating parameters.

[0010] The feedback control component is responsible for automatically adjusting the operating status of the low-temperature coupled heat pump based on the analysis results from the cloud server.

[0011] Optional, data acquisition components, including:

[0012] The location filtering module is responsible for acquiring target data of the area to be tested of the low-temperature coupled heat pump, acquiring multiple target points in the area to be tested, and the target points correspond to the measurement points of key data. The module uses a classification strategy to classify multiple measurement points and obtains at least two measurement points with the same target data based on the correspondence.

[0013] The equipment deployment module is responsible for obtaining the response time of key parameters at measurement points based on the historical change patterns of key parameters, and selecting the measurement point with the shortest response time to the target parameter from at least two measurement points with the same target data, i.e., the deployment point.

[0014] The data fusion module is responsible for synchronizing data from different types of sensors according to timestamps, comprehensively calculating the confidence levels and characteristics of data from different types of sensors, and generating the key parameters for final monitoring.

[0015] Optional, the data fusion module includes:

[0016] The time synchronization submodule is responsible for collecting data from each sensor within a set time interval, synchronizing the data from all sensors according to the timestamp, and ensuring that the data are collected at the same point in time.

[0017] The feature extraction submodule is responsible for assigning a confidence value to the data collected by each sensor, and deriving the confidence level of each sensor's data at the current moment based on the standard deviation and mean of historical data; and performing uniform feature extraction for each data type.

[0018] The weighted fusion submodule is responsible for setting the weight of each sensor feature, dynamically adjusting the weight based on reaction time and confidence level, merging the features and corresponding confidence levels of each sensor, and combining the data results from all sensors through a weighted sum to obtain the final key parameters.

[0019] Optional, a data transmission component, including:

[0020] The signal processing module is responsible for implementing the key parameters after the initial processing of IoT signals. During IoT transmission, it uses algorithms to suppress interference in IoT signals and transmits the key parameters after interference suppression to the cloud server.

[0021] The model training module is responsible for preprocessing the key parameters after interference suppression, obtaining the preprocessed key parameters, and dividing them into training set and test set according to the ratio.

[0022] The model evaluation module is responsible for evaluating the support vector machine using test set data, assessing the performance of the support vector machine through mean squared error and accuracy, and adjusting the support vector machine parameters.

[0023] Optional, a signal processing module, including:

[0024] The signal normalization submodule is responsible for defining the normalization scaling function for the IoT signals that need to be processed;

[0025] The interference detection submodule is responsible for defining the time-frequency positioning strategy when IoT signals are interfered with, and determining whether there is interference in the IoT signal to be processed.

[0026] The suppression execution submodule is responsible for suppressing the interference components of the IoT signal and outputting the suppressed IoT signal.

[0027] Optional, model training module, including:

[0028] The dataset construction submodule is responsible for labeling the preprocessed key parameters according to the data source.

[0029] The dataset processing submodule is responsible for dividing the dataset into training and testing sets;

[0030] The training execution submodule is responsible for inputting the training set for training and updating the support vector machine model parameters through optimization algorithms.

[0031] Optionally, the dataset construction submodule constructs a dataset from the preprocessed key parameters and annotation information.

[0032] Optionally, the dataset processing submodule uses a center-pruning method to downsample the preprocessed key parameters in the dataset, and then performs inversion or rotation operations on the downsampled preprocessed key parameters according to a preset probability to expand the preprocessed key parameters; by expanding the preprocessed key parameters, a new dataset is obtained.

[0033] Optionally, the training execution submodule selects the core function of the support vector machine and sets the penalty parameter C and the kernel parameter.

[0034] Optional, feedback control components, including:

[0035] The instruction sending module is responsible for generating control instructions based on analysis results and decision-making, and sending them to the feedback control component via the cloud server.

[0036] The status adjustment module is responsible for adjusting the working status of the low-temperature coupled heat pump after receiving instructions from the cloud, and regulating the compressor status and circulation flow.

[0037] The alarm module is responsible for viewing key parameters in real time through smart terminals and monitoring the operation of the low-temperature coupled heat pump; if the low-temperature coupled heat pump malfunctions, it will promptly send an alarm notification.

[0038] The data acquisition component of this invention collects key parameters such as water temperature, flow rate, compressor status, and ambient temperature in real time through various sensors (such as temperature sensors, flow sensors, and pressure sensors). It performs preliminary data processing (such as filtering and correction) to ensure the accuracy and validity of the data. The pre-processed key parameters are then formatted for subsequent transmission to reduce network load. The significance is that real-time and accurate parameter acquisition improves the effectiveness of system monitoring, helping to detect potential anomalies early. It provides accurate and reliable basic data for subsequent data analysis and feedback control, aiding in the optimization of management and operational strategies. The data transmission component utilizes Internet of Things (IoT) technologies (such as LoRa, NB-IoT, and Wi-Fi) to securely and quickly transmit the pre-processed key parameters to the cloud server, ensuring real-time data upload for rapid response. Significance Achieved: Real-time data transmission enables the monitoring system to quickly adapt to changes and react promptly; seamless data connection between distributed IoT edge devices and the cloud enhances system flexibility and accessibility; the cloud server centrally stores all received key parameter data and provides an effective database management system; historical data analysis utilizes machine learning algorithms to optimize compressor operating parameters, improving energy efficiency and reducing wear; real-time reports are generated, identifying trends and anomaly patterns to support decision-making. Significance Achieved: Data-driven decisions are more scientific, effectively improving system operating efficiency and stability; through continuous algorithm learning and optimization, the system can adapt to different operating conditions and environments, improving overall performance. The feedback control component automatically adjusts the operating status of the low-temperature coupled heat pump (such as compressor speed, operating time, etc.) based on the analysis results from the cloud server; it provides a smart terminal view, allowing users to view key parameters at any time and receive alarm notifications regarding equipment status. Significance Achieved: Allows the system to automatically adjust based on real-time data, improving responsiveness to environmental and load changes; real-time monitoring and instant alerts enhance user experience, allowing users to maintain transparency regarding equipment status at any time, enabling timely maintenance actions.

[0039] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0040] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0041] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0042] Figure 1 This is a block diagram of the IoT-based remote monitoring and data acquisition system for low-temperature coupled heat pumps in Embodiment 1 of the present invention.

[0043] Figure 2 This is a block diagram of the data acquisition component in Embodiment 2 of the present invention;

[0044] Figure 3 This is a block diagram of the data fusion module in Embodiment 3 of the present invention;

[0045] Figure 4 This is a block diagram of the data transmission component in Embodiment 4 of the present invention;

[0046] Figure 5 This is a block diagram of the signal processing module in Embodiment 5 of the present invention;

[0047] Figure 6 This is a block diagram of the model training module in Embodiment 6 of the present invention;

[0048] Figure 7 This is a block diagram of the training execution submodule in Embodiment 7 of the present invention;

[0049] Figure 8 This is a block diagram of the training set input unit in Embodiment 8 of the present invention;

[0050] Figure 9 This is a block diagram of the model evaluation module in Embodiment 9 of the present invention;

[0051] Figure 10 This is a block diagram of the feedback control component in Embodiment 10 of the present invention. Detailed Implementation

[0052] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0053] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0054] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0055] Example 1: As Figure 1 As shown, this embodiment of the invention provides a remote monitoring and data acquisition system for a low-temperature coupled heat pump based on the Internet of Things, comprising:

[0056] The data acquisition component is responsible for collecting key parameters such as water temperature, flow rate, compressor status, and ambient temperature in real time through sensors. It performs preliminary processing on the collected key parameters to obtain the preliminary key parameters. The preliminary processing includes filtering, verification, and outlier handling.

[0057] The data transmission component is responsible for transmitting the pre-processed key parameters to the cloud server in real time via the Internet of Things; the cloud server uses machine learning algorithms to process the key parameters and optimize the compressor's operating parameters.

[0058] The feedback control component is responsible for automatically adjusting the operating status of the low-temperature coupled heat pump based on the analysis results from the cloud server; at the same time, it allows users to view key parameters in real time and receive status alarms from the low-temperature coupled heat pump via a smart terminal.

[0059] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the data acquisition component collects key parameters such as water temperature, flow rate, compressor status, and ambient temperature in real time through sensors. The collected key parameters undergo preliminary processing to obtain pre-processed key parameters. The data transmission component transmits the pre-processed key parameters to a cloud server in real time via the Internet of Things (IoT). The cloud server uses machine learning algorithms to process the key parameters and optimize the compressor's operating parameters. The feedback control component automatically adjusts the operating status of the low-temperature coupled heat pump based on the analysis results from the cloud server. Simultaneously, key parameters are viewed in real time through a smart terminal, and status alarms from the low-temperature coupled heat pump are received. The data acquisition component of the above solution collects key parameters such as water temperature, flow rate, compressor status, and ambient temperature in real time through various sensors (such as temperature sensors, flow sensors, and pressure sensors). The collected data undergoes preliminary processing (such as filtering and correction) to ensure accuracy and validity. The pre-processed key parameters are formatted for subsequent transmission to reduce network load. The significance achieved is that real-time and accurate parameter acquisition improves the effectiveness of system monitoring, helps to detect potential anomalies early, and provides accurate and reliable basic data for subsequent data analysis and feedback control, contributing to the optimization of management and operation strategies. The data transmission component utilizes IoT technologies (such as LoRa, NB-IoT, and Wi-Fi) to securely and rapidly transmit pre-processed key parameters to the cloud server, ensuring real-time data uploads for rapid response. The benefits include: enabling the monitoring system to quickly adapt to changes and react promptly through instant data transmission; seamless data connection between distributed IoT edge devices and the cloud, enhancing system flexibility and accessibility; centralized storage of all received key parameter data on the cloud server, providing an effective database management system; analysis of historical data, using machine learning algorithms to optimize compressor operating parameters to improve energy efficiency and reduce wear; and generation of real-time reports to identify trends and anomalies, supporting the decision-making process. The benefits also include: more scientific decisions based on data analysis, effectively improving system efficiency and stability; and continuous algorithm learning and optimization allowing the system to adapt to different operating conditions and environments, improving overall performance. The feedback control component automatically adjusts the operating status of the cryogenic coupled heat pump (such as compressor speed and operating time) based on the analysis results from the cloud server; it provides a smart terminal view, allowing users to view key parameters at any time and receive alarm notifications regarding equipment status. Significance achieved: The system is allowed to automatically adjust based on real-time data, improving its responsiveness to environmental and load changes; real-time monitoring and instant alerts enhance the user experience, allowing users to maintain transparency about equipment status at any time and thus take timely maintenance actions.

[0060] In summary, this embodiment of the IoT-based low-temperature coupled heat pump remote monitoring and data acquisition system achieves continuous monitoring, intelligent analysis, and rapid response through the collaborative work of its various components. The system enables efficient energy use and optimized management, reduces energy consumption, improves equipment reliability and lifespan, and provides users with greater control and convenience. This not only enhances the overall performance of the equipment but also promotes sustainable development goals, contributing to smart buildings and the utilization of green energy.

[0061] Example 2: Figure 2 As shown, based on Embodiment 1, the data acquisition component provided in this embodiment of the invention includes:

[0062] The location filtering module is responsible for acquiring target data of the test area of ​​the low-temperature coupled heat pump, acquiring multiple target points in the test area, and the target points corresponding to the measurement points of key data. The module uses a classification strategy to classify multiple measurement points to obtain the correspondence between the number of targets and the measurement points, and obtains at least two measurement points of the same target data based on the correspondence.

[0063] The equipment deployment module is responsible for obtaining the response time of key parameters at measurement points based on the historical change patterns of key parameters. It selects the measurement point with the shortest response time to the target parameter from at least two measurement points with the same target data, which are the deployment points of temperature sensors, flow sensors, pressure sensors, or ambient temperature sensors, etc., which are used as target data. Multiple deployment points are constructed into a key parameter monitoring network.

[0064] The data fusion module is responsible for synchronizing data from different types of sensors according to timestamps, comprehensively calculating the confidence levels and characteristics of data from different types of sensors, and generating the key parameters for final monitoring.

[0065] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the location screening module acquires target data of the area to be detected by the low-temperature coupled heat pump, acquires multiple target points in the area to be detected, and the target points correspond to the measurement points of key data. The multiple measurement points are classified using a classification strategy to obtain the correspondence between the number of targets and the measurement points. Based on the correspondence, at least two measurement points with the same target data are obtained. The equipment deployment module obtains the key parameter response time of the measurement points according to the historical key parameter change pattern, and selects the measurement point with the shortest response time to the target parameter from at least two measurement points with the same target data. That is, it serves as the deployment point for the temperature sensor, flow sensor, pressure sensor, or ambient temperature sensor of the target data. Multiple deployment points are constructed into a key parameter monitoring network. The data fusion module synchronizes the data of different types of sensors according to the timestamp, and comprehensively calculates the confidence and characteristics of the data of different types of sensors to generate the final monitored key parameters. The location screening module of the above scheme can effectively identify key equipment and related measurement points within the detection area, including the monitoring locations of important parameters such as temperature, flow rate, pressure, and environment. It effectively classifies measurement points using a classification strategy, associating them with target data to provide basic data support for subsequent data analysis. It establishes a clear correspondence between each target point and its measurement point, ensuring that data collection has a clear direction and target. Significance: Through accurate identification and classification, redundant measurement point selection and unnecessary data collection are avoided, thereby improving monitoring efficiency. Clear correspondence provides a reliable basis for subsequent data processing and analysis, ensuring the validity and accuracy of the data. It lays the foundation for future automatic adjustment and optimization strategies, enabling intelligent monitoring and management. The equipment deployment module analyzes historical data to determine the reaction time of each measurement point, thereby selecting the most suitable sensor location for deployment. Based on the principle of the shortest reaction time for parameters, it selects the optimal measurement points for sensor deployment to improve response speed and data real-time performance. It integrates multiple selected deployment points into a key parameter monitoring network, achieving comprehensive monitoring of the entire heat pump system. Significance: Optimized measurement point layout enables faster response times for key parameters, thereby improving the overall system's agility and responsiveness; timely feedback on changes in key parameters helps quickly identify potential faults and reduce equipment operational risks; rapid data updates and monitoring ensure that managers can grasp the system status in real time, supporting rapid decision-making. The data fusion module synchronizes measurement data from different sensors according to timestamps, ensuring data consistency within the same time frame; by calculating the confidence levels and characteristics of data from different types of sensors, comprehensive monitoring data is formed, generating the final key parameters; redundant data and noise are effectively suppressed, improving the accuracy and reliability of monitoring data and providing strong support for subsequent decision-making.Significance: High-quality fused data can support more accurate intelligent analysis and decision-making, helping to optimize the operating efficiency of heat pumps; integrating data from different sources enables comprehensive monitoring, laying the foundation for system-level monitoring and analysis; through precise data analysis and feedback, it can improve the overall efficiency of low-temperature coupled heat pumps, reduce energy waste, and support sustainable development.

[0066] In summary, each module in this embodiment plays a crucial role in the low-temperature coupled heat pump data acquisition system. It not only achieves scientific and accurate data acquisition but also improves system performance, reduces operational risks, and supports intelligent decision-making and management functions, thus having profound significance for the effective operation of the entire heat pump system. The multi-layered, multi-module design provides strong support and assurance for future intelligent and digital energy management systems.

[0067] Example 3: As Figure 3 As shown, based on Example 2, the data fusion module specifically includes:

[0068] The time synchronization submodule is responsible for collecting data from each sensor within a set time interval, synchronizing the data from all sensors according to the timestamp, and ensuring that the data are collected at the same point in time.

[0069] The feature extraction submodule is responsible for assigning a confidence value to the data collected by each sensor. Based on the standard deviation and mean of historical data, it calculates the confidence level of each sensor's data at the current moment. It performs unified feature extraction for each data type, and the features include: mean, standard deviation, maximum value, minimum value, and rate of change.

[0070] The weighted fusion submodule is responsible for setting the weight of each sensor feature, dynamically adjusting the weight based on reaction time and confidence level, merging the features and corresponding confidence levels of each sensor, and combining the data results from all sensors through a weighted sum to obtain the final key parameters.

[0071] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the time synchronization submodule collects data from each sensor within a set time interval, synchronizing the data of all sensors according to timestamps to ensure the same point in time; the feature extraction submodule assigns a confidence value to the data of each sensor during collection, and derives the confidence level of each sensor's data at the current moment based on the standard deviation and mean of historical data; uniform feature extraction is performed on each data type, and the features include: mean, standard deviation, maximum value, minimum value, and rate of change; the weighted fusion submodule sets the weight of each sensor's feature, dynamically adjusts the weight according to the reaction time and confidence level, and merges the features of each sensor with the corresponding confidence level; the data results of all sensors are combined and fused through a weighted sum to obtain the final key parameters. The time synchronization submodule of the above solution ensures that all sensors collect data synchronously within a set time interval (e.g., once per second); by aligning the data of each sensor through timestamps, it can effectively handle the time delay that may exist when different sensors collect data, ensuring that data at the same point in time can be compared and fused. Significance: Accurate time synchronization ensures data timeliness and consistency, enabling subsequent analysis to be based on a precise time dimension; it ensures that the interrelationships between various monitoring parameters are accurately reflected in real-time data monitoring, allowing processing results to reflect the system status in real time; and it lays a solid foundation for subsequent data analysis and feature extraction. The feature extraction submodule calculates the confidence level for each sensor's data, assessing the reliability of current data by statistically analyzing the standard deviation and mean of historical data; it extracts multiple key features from sensor data, such as mean, standard deviation, and rate of change, for subsequent analysis. Significance: By calculating confidence levels, unreliable data can be identified and eliminated, increasing the credibility of subsequent calculation results; a unified feature extraction strategy allows managers to systematically compare and analyze data from different types of sensors, thereby uncovering deeper operational patterns; rich feature data provides in-depth understanding of the system's operational status, supporting intelligent decision-making and optimization adjustments. The weighted fusion submodule dynamically adjusts the feature weights based on the reaction time and confidence level of each sensor, ensuring the fusion algorithm adapts to changes in input data. By merging the features of each sensor with their corresponding confidence levels, it comprehensively generates the final key parameters, ensuring a complete set of monitoring parameters is effectively output. Significance: By adjusting the weights, reliable data is prioritized, improving the quality of the data output; data from different sensors are effectively fused through weighted averaging to form a global perspective, aiding in the overall system status assessment; the final output key parameters provide more reliable data support for operational decisions, helping technical personnel make more effective adjustments and optimizations.

[0072] In summary, this embodiment, through the organic cooperation of these three sub-modules, enables the data fusion module to achieve real-time, accurate, and efficient data processing, integrating data from various sensors to improve the monitoring capabilities of the low-temperature coupled heat pump system. This not only enhances the reliability and efficiency of system operation but also provides a rich data foundation for subsequent intelligent management and decision support, laying the groundwork for optimizing energy use and establishing fault early warning mechanisms. The synergistic effect between the various sub-modules enhances the intelligent analysis and control capabilities of the entire system, contributing to the achievement of sustainable energy management goals.

[0073] Example 4: Figure 4 As shown, based on Embodiment 1, the data transmission component provided in this embodiment of the invention includes:

[0074] The signal processing module is responsible for implementing the key parameters after the initial processing of IoT signals. During IoT transmission, the algorithm suppresses interference in the IoT signal to obtain the IoT signal after interference suppression. Then, the key parameters after interference suppression are transmitted to the cloud server.

[0075] The model training module is responsible for preprocessing the key parameters after interference suppression to obtain the preprocessed key parameters, which are then divided into training and test sets according to the proportion. The training set is used to train the support vector machine to obtain strategies for optimizing compressor operating parameters and to learn the relationship between input features (such as water temperature, flow rate, etc.) and target variables (such as compressor energy efficiency ratio, power consumption, etc.).

[0076] The model evaluation module is responsible for evaluating the support vector machine using test set data, assessing its performance through mean squared error and accuracy, and adjusting its parameters.

[0077] The working principle and beneficial effects of the above technical solution are as follows: The signal processing module in this embodiment realizes the key parameters after preliminary processing of IoT signals. During IoT transmission, interference suppression is performed on the IoT signal using algorithms to obtain the interference-suppressed IoT signal, and then the interference-suppressed key parameters are transmitted to the cloud server. The model training module preprocesses the interference-suppressed key parameters to obtain preprocessed key parameters, which are then divided into training and testing sets according to a ratio. The training set is used to train the support vector machine to obtain strategies for optimizing compressor operating parameters, learning the relationship between input features (such as water temperature, flow rate, etc.) and target variables (such as compressor energy efficiency ratio, power consumption, etc.). The model evaluation module uses the test set data to evaluate the support vector machine, assessing its performance through mean square error and accuracy, and adjusting the support vector machine parameters. The signal processing module in the above solution effectively suppresses interference in the received IoT signal through signal processing algorithms (such as filtering algorithms or error detection), ensuring the signal quality of data transmission; by eliminating noise and errors, it improves the accuracy and reliability of sensor data, making it suitable for subsequent data analysis and processing. Significance Achieved: Ensuring reliable and accurate data transmission to subsequent processing stages improves the overall system reliability and accuracy; reduces faults and errors caused by data interference, enhances the stability of the entire IoT system, and ensures effective operation in complex environments. The model training module further cleans and extracts features from the key parameters after interference suppression to generate data suitable for training machine learning models; it uses the training set data to train the Support Vector Machine (SVM) to obtain the relationship between input features (such as water temperature and flow rate) and target variables (such as the compressor's energy efficiency ratio and power consumption). Significance Achieved: By training the model, the system can predict the compressor's operating behavior based on historical data and key parameters, thereby achieving optimized operation under different conditions; it generates optimization strategies for compressor operation, improving system efficiency under different working conditions, reducing energy consumption, and extending equipment lifespan. The model evaluation module uses test set data to evaluate the trained SVM, calculating metrics such as mean squared error and accuracy to reflect the model's predictive performance; based on the evaluation results, it adjusts the model's hyperparameters to optimize model performance, enabling it to better adapt to real-world data. The significance of this achievement is to ensure that the trained model has good generalization ability in practical applications and can make accurate predictions on unknown data; through model evaluation and optimization, the system can continuously learn and adapt to new environments, improve its self-regulation and decision-making capabilities, and thus enhance the overall performance of the system.

[0078] In summary, this embodiment, through the synergistic effect of the signal processing module, model training module, and model evaluation module, enables the data transmission component to effectively receive, process, train, and evaluate IoT data, thereby providing intelligent support for the operational optimization of the low-temperature coupled heat pump system. This improves data quality and reliability, laying the foundation for subsequent analysis; enhances the system's predictive and intelligent decision-making capabilities, enabling it to optimize operating parameters and improve energy efficiency under different environments and operating conditions; and achieves intelligent management and maintenance through continuous feedback and optimization mechanisms, allowing the system to adapt to ever-changing usage requirements.

[0079] Example 5: Figure 5 As shown, based on Embodiment 4, the signal processing module provided in this embodiment of the invention includes:

[0080] The signal normalization submodule is responsible for defining the normalization scaling function for the IoT signals that need to be processed;

[0081] The scaling function expression is:

[0082]

[0083] In the formula, R represents the slope of the IoT signal to be processed. min and R max Minimum and maximum values ​​of the slope of the IoT signal to be processed;

[0084] The interference detection submodule is responsible for defining the time-frequency positioning strategy when IoT signals are interfered with, and determining whether there is interference in the IoT signal to be processed.

[0085] The expression is:

[0086]

[0087] In the formula, Mask(n,k) represents the interference mask for a specific signal, with a value of 1 or 0. A value of 1 indicates that the signal is not interfered with, and a value of 0 indicates that the IoT signal is interfered with. n represents the index of the nth sample or observation point in the signal sequence, k represents the index of the kth feature or dimension in the IoT signal sequence, and R(n,k); τ-c represents the filtered signal value, τ represents the time delay, c represents the offset, and R represents the threshold used to determine whether the signal is interfered with. If the absolute value of the transformed IoT signal is greater than this threshold, the IoT signal is considered to be interfered with.

[0088] The suppression execution submodule is responsible for suppressing the interference components of the IoT signal and outputting the suppressed IoT signal.

[0089] The expression is:

[0090]

[0091] In the formula, The output represents the suppressed IoT signal, used to represent the IoT signal after interference suppression processing. R(n,k) represents the original value of the IoT signal to be processed, representing the signal data under sample n and feature k. ⊙ represents the point-by-point multiplication operation. S(n,k) represents the useful part or effective signal component of the IoT signal. I(n,k) represents the interference component, i.e. the signal part that needs to be suppressed. Ω(n,k) represents the extra components in the IoT signal, which may be noise or other non-interference signal components.

[0092] The working principle and beneficial effects of the above technical solution are as follows: The signal normalization submodule of this embodiment defines a normalization scaling function for the IoT signal to be processed; the interference judgment submodule defines a time-frequency positioning strategy when the IoT signal is interfered with, and judges whether there is interference in the IoT signal to be processed; the suppression execution submodule suppresses the interference components of the IoT signal with interference and outputs the suppressed IoT signal. The signal normalization submodule of the above solution normalizes the slope of the signal to be processed through a standardized formula, which will ensure that the value of the signal is within a uniform range, usually [0,1]. The significance achieved is: after normalization, the magnitude difference between different signal features is eliminated, preventing numerical instability during training or processing; in subsequent model training or signal analysis, the learning effect of the algorithm on each feature is balanced, and the training effect of the entire model will not be affected by the large value of some features; after scaling the signal value to a uniform range, users can intuitively understand the relative situation of different signals. The interference judgment submodule uses a threshold discrimination method to mark whether the signal is interfered with by using a mask. The formula compares the filtered signal value with the set threshold to achieve automatic identification of interference signals. Significance Achieved: The system can quickly assess signal quality, ensuring that interference does not lead to erroneous data analysis or decisions during use; effectively identifying and processing interfered signals helps maintain system stability and reliability, as signals can only be incorporated into subsequent data processing when deemed undisturbed; by dynamically monitoring signal interference, the system can adaptively adjust processing strategies, thereby improving the flexibility of signal processing. The suppression execution submodule outputs a suppressed signal through point-by-point multiplication operations, primarily by suppressing signal components marked as interference, thus restoring the effective components of the signal. Significance Achieved: By suppressing interference components, the quality of the final output signal is improved, better reflecting real IoT parameters and playing a crucial role in subsequent analysis and decision-making; through effective interference processing and signal recovery, the system can provide more accurate data, supporting data-driven decision-making and prediction; after interference suppression, the system can use data more efficiently for learning and inference, avoiding misleading results and resource waste.

[0093] In summary, this embodiment, through the organic integration of the signal normalization submodule, interference judgment submodule, and suppression execution submodule, achieves the following key technical effects and systemic significance in the entire signal processing module: ensuring the quality of the input signal, thereby enabling subsequent data analysis and processing to proceed smoothly; real-time monitoring and interference suppression help the system dynamically adjust its operating state to adapt to the ever-changing environment; and providing accurate and high-quality data for subsequent analysis and model training, ultimately promoting the intelligence and efficiency improvement of the IoT system. This series of functions not only enhances the system's performance but also improves its feasibility and effectiveness in practical applications, enabling end users to better obtain valuable information and insights.

[0094] Example 6: As Figure 6 As shown, based on Example 4, the model training module provided in this embodiment of the invention includes:

[0095] The dataset construction submodule is responsible for labeling the preprocessed key parameters according to the data source, and constructing the preprocessed key parameters and labeling information into a dataset. The labeling information is the type index and deployment point location of each sensor in each preprocessed key parameter.

[0096] The dataset processing submodule is responsible for downsampling the preprocessed key parameters in the dataset using a center-pruning method, and then performing inversion or rotation operations on the downsampled preprocessed key parameters according to preset probabilities to expand the preprocessed key parameters and obtain a new dataset. The dataset is divided into training and testing sets in an 8:2 ratio. Inversion (such as flipping up and down) for sensors involves performing negative inversion on the data, representing reverse behavior; rotation is used to transform the time series signals in the data; for example, for periodic signals, they can be scrolled or moved in the time dimension.

[0097] The training execution submodule is responsible for selecting the core function of the support vector machine and setting the penalty parameter C and kernel parameters; inputting the training set for training; and updating the support vector machine model parameters through optimization algorithms.

[0098] The working principle and beneficial effects of the above technical solution are as follows: The dataset construction submodule of this embodiment annotates the preprocessed key parameters according to the data source, and constructs a dataset from the preprocessed key parameters and annotation information. The annotation information is the type index and deployment point location of each sensor in each preprocessed key parameter. The dataset processing submodule downsamples the preprocessed key parameters in the dataset by center pruning, and performs inversion or rotation operations on the downsampled preprocessed key parameters according to a preset probability to expand the preprocessed key parameters and obtain a new dataset. The dataset is divided into training set and test set in an 8:2 ratio. Among them, inversion (such as flipping up and down) for sensors involves performing negative inversion on the data, which represents reverse behavior; rotation is to transform the time series signal in the data; for example, for periodic signals, it can be rolled or moved in the time dimension. The training execution submodule selects the core function of the support vector machine and sets the penalty parameter C and kernel parameter. It inputs the training set for training and updates the support vector machine model parameters through optimization algorithms. The dataset construction submodule of the above scheme includes annotation information such as the type index and deployment location of each sensor, providing rich contextual information for subsequent model training. The significance is that by constructing a dataset with labeled information, background knowledge can be better utilized, improving the model's learning efficiency; accurate annotation provides a basis for subsequent data analysis, enabling the model to better understand sensor characteristics and environmental factors when processing real-world data, thereby improving prediction accuracy. The dataset processing submodule uses center-pruned downsampling preprocessing of key parameters to reduce the amount of data while retaining important features; it expands the dataset through inversion and rotation operations to provide diverse samples for model training, improving the model's robustness; the dataset is divided into training and test sets in an 8:2 ratio to ensure effective validation of model performance. The significance is that downsampling and data augmentation not only provide richer training data, helping to prevent overfitting, but also improve the model's adaptability to different situations and signal anomalies; dividing the dataset into training and test sets ensures the rigor of model evaluation, helping to ensure that the model performs well even on unknown data. The training execution submodule selects and sets the core function, penalty parameter C, and kernel parameters of the Support Vector Machine (SVM) to suit the characteristics of the dataset; it inputs the training set for model training, updates the SVM model parameters through optimization algorithms (such as gradient descent, SMO, etc.), and evaluates the model on the test set. The significance is that by adjusting the SVM parameters for a specific dataset, the model's learning effect can be improved, thereby achieving better performance.

[0099] In summary, the three sub-modules in this embodiment each perform their respective functions throughout the model training process, and their collaborative work ensures efficient data processing, model training, and performance evaluation. By constructing a richly labeled dataset, implementing effective data processing and augmentation, and employing optimized training methods, this modular system can significantly improve the model's performance and reliability in practical applications. This approach provides a systematic method for the analysis and processing of various sensor data, effectively addressing real-world problems.

[0100] Example 7: Figure 7 As shown, based on Example 6, the training execution submodule provided in this embodiment of the invention includes:

[0101] The kernel function validation unit is responsible for defining multiple kernel functions, including linear kernels, polynomial kernels, and radial basis kernels. For each kernel function, a support vector machine model is built using k subsets of the dataset. The support vector machine model is trained using k-1 subsets each time, and validated using the remaining subset. The average validation accuracy of each kernel function is recorded. The validation results of all kernel functions are compared, and the kernel function with the highest validation accuracy is selected as the final kernel function used.

[0102] The hyperparameter validation unit is responsible for writing an objective function to evaluate the effects of different hyperparameter combinations; determining the range of hyperparameter values; initially sampling parameter combinations randomly in the hyperparameter space, training the model, and calculating the effect of the combinations; based on the initial sampling results, constructing a probabilistic model to capture the relationship between hyperparameters and model performance; selecting the point with the greatest uncertainty in the probabilistic model for sampling (i.e., the hyperparameter combination with the highest potential for improving model performance), and updating the performance results at that point; after reaching a given number of iterations or a performance threshold, selecting the best-performing hyperparameter combination and providing it to the support vector machine model for training;

[0103] The training set input unit is responsible for feeding the training set into the selected support vector machine model, training the support vector machine model, and obtaining the trained support vector machine model.

[0104] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the kernel function verification unit sets multiple kernel functions, including linear kernels, polynomial kernels, and radial basis function kernels. For each kernel function, a support vector machine model is constructed using k subsets of the dataset. Each time, the support vector machine model is trained using k-1 subsets, and the remaining subset is used for verification. The average verification accuracy of each kernel function is recorded. The verification results of all kernel functions are compared, and the kernel function with the highest verification accuracy is selected as the final kernel function used. The hyperparameter verification unit writes an objective function to evaluate the effect of different hyperparameter combinations. The range of hyperparameter values ​​is determined. Initially... In this approach, parameter combinations are randomly sampled in the hyperparameter space to train the model, and the effect of the combinations is calculated. Based on the initial sampling results, a probabilistic model is constructed to capture the relationship between hyperparameters and model performance. On the probabilistic model, the point with the greatest uncertainty is selected for sampling (i.e., the hyperparameter combination with the highest potential for improving model performance), and the performance result at that point is updated. Once a given number of iterations or a performance threshold is reached, the best-performing hyperparameter combination is selected and provided to the support vector machine (SVM) model for training. The training set input unit inputs the training set into the selected SVM model for training, resulting in the trained SVM model. The kernel function validation unit in this scheme sets multiple kernel functions (such as linear kernels, polynomial kernels, and radial basis kernels) to ensure the model can handle data with various distribution characteristics. Each kernel function is trained and validated using k-fold cross-validation to ensure a comprehensive evaluation of its performance. Each training iteration uses k-1 subsets, and the remaining subset is used for validation, thus reducing the risk of overfitting. The average validation accuracy of each kernel function is recorded and compared to select the best-performing kernel function. Significance: By setting various kernel functions, this unit enables the model to adapt to linear and nonlinear features, improving classification ability. Systematic evaluation of the performance of different kernel functions ensures that the final selected kernel function is the validated optimal choice, thereby improving model stability and prediction accuracy. The hyperparameter confirmation unit constructs a clear objective function for evaluating different hyperparameter combinations, accurately measuring the model's performance under specific hyperparameter settings, facilitating subsequent optimization. Initial random sampling explores the hyperparameter space and evaluates model performance, laying the foundation for efficient subsequent optimization. Using the initially sampled data, a probabilistic model between hyperparameters and model performance is established, enabling systematic analysis and selection of hyperparameters. Significance: Through scientific and systematic exploration and evaluation of hyperparameters, the hyperparameter confirmation unit eliminates reliance on empirical selection during model training, improving the efficiency and effectiveness of parameter tuning. Optimizing hyperparameters significantly improves the model's classification performance, making it more adaptable to data distributions in real-world application scenarios and enhancing the model's generalization ability.The training set input unit feeds the selected training set data into the optimized SVM model for training, updating the model parameters during the training process. After training, the output is the trained support vector machine model, ready for prediction and application on new samples. Significance: This unit represents the final step in the entire training process, consolidating the work of the first two units to form a model usable in practical applications. By using a training set for model training, it ensures that the model fully learns the features of the data. Especially after kernel function and hyperparameter optimization, the model can more effectively identify features, improving prediction accuracy on new data.

[0105] In summary, the training execution submodule in this embodiment forms a complete support vector machine training system by hierarchically defining the functions of different units. The kernel function confirmation unit ensures that the model can flexibly handle different data features, the hyperparameter confirmation unit improves the efficiency and accuracy of parameter selection, and the training set input unit realizes the final construction and application of the model. The modular design accelerates the model training speed and optimizes model performance, enabling the final model to not only have excellent classification capabilities but also maintain good stability in different application scenarios.

[0106] Example 8: As Figure 8 As shown, based on Embodiment 7, the training set input unit provided in this embodiment of the invention includes:

[0107] The data batch processing subunit is responsible for obtaining the real-time stream of input data, processing the data by splitting it into small batches, and initializing the support vector machine model parameters, including weight vectors and bias terms.

[0108] The iterative training subunit is responsible for calculating the current support vector machine model output for each batch of data, comparing it with the true value, and obtaining the loss. Based on the loss of the current sample, the support vector machine model parameters are updated using stochastic gradient descent, and the weights and biases are updated.

[0109] The online learning mechanism subunit is responsible for randomly selecting whether to accept new data samples after each iteration, and adjusting the support vector machine model according to the characteristics of the new samples; setting a threshold, and updating the support vector machine model if the score of the new sample differs significantly from the current model output.

[0110] The working principle and beneficial effects of the above technical solution are as follows: The data batch processing subunit of this embodiment obtains the real-time stream of input data and processes it by splitting the data into small batches; it initializes the support vector machine model parameters, including weight vectors and bias terms; the iterative training subunit calculates the current support vector machine model output for each batch of data and compares it with the true value to obtain the loss; based on the loss of the current sample, it updates the support vector machine model parameters, weights, and biases using stochastic gradient descent; the online learning mechanism subunit randomly selects whether to accept new data samples after each iteration and adjusts the support vector machine model according to the characteristics of the new samples; a threshold is set, and if the score of the new sample differs significantly from the current model output, the support vector machine model is updated. The data batch processing subunit of the above solution, by obtaining the real-time stream of input data, can receive and process new data instantly, adapting to dynamically changing environments; splitting the data into small batches helps reduce memory usage and speeds up data processing; processing only the current small batch of data in each iteration improves training efficiency; and it prepares initial parameters for the training of the support vector machine model, including weight vectors and bias terms. Proper initialization of these parameters helps the model converge faster. Significance: Mini-batch processing allows the model to maintain high efficiency even with large-scale or real-time data. Its adaptable design better handles streaming data and constantly changing inputs; effective parameter initialization lays the foundation for effective model learning, making the training process more efficient and reducing convergence time. The iterative training subunit infers from each batch of data, calculating the current output value of the support vector machine model. This process allows the model to evaluate its classification performance based on existing parameters; by comparing with the true values, the loss between the current output and the actual label is calculated, evaluating the model's performance. This is a crucial step in the training process, essential for guiding parameter updates; stochastic gradient descent is used to update the model parameters (weights and biases) based on the calculated loss; the model is adjusted using gradient information to gradually reduce the loss. Significance: By providing feedback on each batch of data, the model parameters are continuously optimized, ensuring the model continuously improves during training and converges towards higher accuracy; stochastic gradient descent effectively handles large datasets, especially when dealing with mini-batch data, reducing the computational cost of each iteration, accelerating the training process, and ensuring that new samples can be quickly incorporated into the model. After each iteration, the online learning mechanism subunit randomly selects whether to accept new data samples, flexibly responding to dynamic changes in the data stream; based on the characteristics of the new samples, it updates the model online. This allows the model to quickly adapt to changes when new data is input without requiring complete retraining; a threshold is set to judge the degree of difference between the new sample and the current model output; if the difference is significant, the model parameters are updated to ensure the model's adaptability and accuracy.Significance: Online learning mechanisms enable models to adjust their decision boundaries in a timely manner as they continuously receive new data, improving their responsiveness to the real-world environment. By dynamically updating the model, it is possible to effectively address data drift and changes, reduce the risk of model obsolescence, and thus ensure continuous predictive accuracy and reliability.

[0111] In summary, the synergistic effect of these sub-units in this embodiment ensures the effectiveness, flexibility, and adaptability of the support vector machine model training. The batch data processing sub-unit enables the model to efficiently handle real-time streaming data, the iterative training sub-unit ensures that the model continuously optimizes in each iteration, and the online learning mechanism sub-unit allows the model to adapt to changes in new data and maintain long-term performance. This design not only improves training efficiency but also enhances the model's performance in practical applications, giving it greater practical value.

[0112] Example 9: As Figure 9 As shown, based on Example 4, the model evaluation module provided in this embodiment of the invention includes:

[0113] The result prediction submodule is responsible for inputting the test set data into the trained support vector machine model and obtaining the prediction results of the support vector machine model.

[0114] The Performance Classification submodule is responsible for calculating the performance metrics of the mean squared error machine accuracy; constructing a confusion matrix to statistically analyze the relationship between each category predicted by the support vector machine model and the true category; and displaying the confusion matrix graphically to intuitively show the classification performance of the support vector machine model on each category.

[0115] The results feedback submodule is responsible for parameter tuning and support vector machine model improvement based on feedback from the confusion matrix and performance metrics.

[0116] The working principle and beneficial effects of the above technical solution are as follows: The result prediction submodule of this embodiment inputs the test set data into the trained support vector machine model to obtain the prediction results of the support vector machine model; the effect classification submodule calculates the performance index of the mean squared error machine accuracy; a confusion matrix is ​​constructed to statistically analyze the relationship between each category predicted by the support vector machine model and the true category; the confusion matrix is ​​displayed graphically to intuitively show the classification effect of the support vector machine model on each category; the result feedback submodule performs parameter tuning and support vector machine model improvement based on the feedback of the confusion matrix and performance index. The result prediction submodule of the above solution inputs the prepared test set data into the trained support vector machine model to generate prediction results; it is the basis for model evaluation, ensuring that we can view the classification of unseen data from the model's perspective; through prediction operations, it obtains the model's predicted label for each sample, and these results will be used for subsequent performance evaluation. Significance: It provides direct feedback on the model's classification ability for new, unseen data, laying the foundation for evaluating the model's performance; it ensures the comparison between the prediction results and the true labels, forming the basic data for subsequent effect classification. The performance classification submodule quantitatively measures the model's predictive performance on the test set by calculating mean squared error (MSE) and accuracy. It also counts the number of true positives, false positives, false negatives, and true negatives to form a confusion matrix, thus showing the model's specific performance in each category. The confusion matrix is ​​then displayed graphically, such as as a heatmap, to help visualize the classification performance across categories. Significance: By comprehensively evaluating the model's performance through multiple metrics (MSE and accuracy) and the confusion matrix, the module identifies the model's classification accuracy across each category. The graphical representation of the confusion matrix helps non-technical personnel more easily understand the model's classification performance, thereby improving the scientific basis of decision-making. The results feedback submodule analyzes the model's strengths and weaknesses based on the confusion matrix and performance metrics (such as mean squared error and accuracy). For misclassifications identified in the confusion matrix (e.g., a high number of false positives or negatives in certain classes), it fine-tunes parameters, adjusting hyperparameters of the support vector machine model, such as the penalty parameter C and kernel function type. Optimizations can be made based on feedback, such as data resampling (e.g., SMOTE), increasing the training set size, or modifying feature selection methods. Significance: This provides a foundation for continuous model optimization and improvement, ensuring the model can adapt to new data environments and improving its long-term stability and accuracy. Data feedback allows for targeted modifications, reducing the error rate and enhancing the model's performance under specific conditions.

[0117] In summary, the synergistic effect of these three sub-modules in this embodiment ensures a comprehensive evaluation of the support vector machine model. The result prediction sub-module provides basic prediction output, the effect classification sub-module comprehensively reflects model performance through multiple evaluation metrics and a confusion matrix, and the result feedback sub-module dynamically adjusts and optimizes based on this. Through this design, the model evaluation module not only promotes the improvement of model performance but also ensures a deep understanding of model performance, providing solid data support and a feedback loop for subsequent applications.

[0118] Example 10: As Figure 10 As shown, based on Embodiment 1, the feedback control component provided in this embodiment of the invention includes:

[0119] The instruction sending module is responsible for generating control instructions based on analysis results and decision-making. The cloud server generates control instructions and sends them to the feedback control component. These instructions include adjusting the compressor's operating speed, switching working modes (such as cooling or heating), adjusting flow rate, or changing the water temperature setpoint.

[0120] The status adjustment module is responsible for adjusting the operating status of the low-temperature coupled heat pump after receiving instructions from the cloud. This includes adjusting the compressor status and circulation flow. Adjusting the compressor status includes changing the compressor's operating speed or stopping / starting the compressor. Adjusting the circulation flow includes adjusting the pump's output or valve settings.

[0121] The alarm module is responsible for viewing key parameters in real time through smart terminals and monitoring the operation of the low-temperature coupled heat pump; if the low-temperature coupled heat pump malfunctions (such as overheating, compressor failure, etc.), it will promptly send an alarm notification.

[0122] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, the instruction sending module, based on analysis results and decision-making, generates control instructions from the cloud server and sends them to the feedback control component. These instructions include adjusting the compressor's operating speed, switching operating modes (e.g., cooling or heating), adjusting flow rate, or changing the water temperature setpoint. After receiving the instructions from the cloud, the status adjustment module adjusts the operating status of the low-temperature coupled heat pump, regulating the compressor status and circulation flow. Adjusting the compressor status includes changing the compressor's operating speed or stopping / starting the compressor. Adjusting the circulation flow includes adjusting the pump's output or valve settings. The alarm issuing module monitors the operating status of the low-temperature coupled heat pump in real time via a smart terminal. If the low-temperature coupled heat pump malfunctions (e.g., overheating, compressor failure), an alarm notification is sent promptly. The instruction sending module of the above solution receives analysis results and decisions from the cloud server and generates accurate control instructions based on this information, ensuring that the operating status of the low-temperature coupled heat pump can be adjusted in a timely manner. The instructions cover adjusting the compressor's operating speed, switching operating modes (e.g., cooling / heating), adjusting flow rate, or changing the water temperature setpoint, ensuring that the system adapts to different operating conditions. Significance: This module enables automated management and control of the heat pump, reducing manual intervention and improving system intelligence. Through timely command transmission, the system can quickly respond to environmental or load demand changes, improving overall operating efficiency and energy savings. The status adjustment module, based on instructions from the command transmission module, is responsible for actually adjusting the compressor and flow rate. By changing the compressor's operating speed or performing stop / start operations, it ensures the compressor operates in optimal condition. By adjusting the pump's output or valve settings, it rationally controls fluid flow in the system, optimizing heat exchange. Significance: Precise status adjustment ensures the heat pump continues to operate efficiently even when load demand changes, avoiding energy waste. Reasonable operating parameter settings can reduce equipment wear and damage, extend equipment lifespan, and lower maintenance costs. The alarm module continuously monitors key parameters of the low-temperature coupled heat pump (such as temperature, flow rate, and compressor status) through a smart terminal to ensure timely detection of abnormalities. When an operational abnormality (such as overheating or compressor failure) is detected, an alarm notification is immediately sent, prompting maintenance personnel to take immediate action. Significance: Through real-time monitoring and anomaly alarm mechanisms, potential risks can be identified early, preventing equipment damage or personal injury, and improving system stability and security; through the alarm function of smart terminals, maintenance personnel can obtain system status information in a timely manner, respond quickly and take appropriate measures, reduce the possibility of accidents, and improve maintenance efficiency.

[0123] In summary, these three modules in this embodiment each play a unique role in the feedback control component, and together they form a complete feedback control system. The command sending module is responsible for implementing intelligent decisions, the state adjustment module executes specific operations, and the alarm issuing module ensures the safe operation of the system and responds promptly to anomalies. The feedback control component not only improves the automation and intelligence level of the low-temperature coupled heat pump, but also creates conditions for optimizing operating efficiency and equipment safety, ultimately promoting continuous improvement and optimization of the system.

[0124] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An Internet of Things-based remote monitoring and data acquisition system for low-temperature coupled heat pumps, characterized in that, Comprise: Data acquisition component, responsible for real-time acquisition of key parameters, preliminary processing of the acquired key parameters, and obtaining the preliminary processed key parameters; Data transmission component, responsible for transmitting the preliminary processed key parameters to the cloud server in real time through the Internet of Things; The cloud server processes the key parameters and optimizes the operating parameters of the compressor; Feedback control component, responsible for automatically adjusting the working state of the low-temperature coupled heat pump according to the analysis results of the cloud server; The data acquisition component comprises: Position screening module, responsible for obtaining target data of the low-temperature coupled heat pump detection area, obtaining multiple target points of the detection area, the target points corresponding to the measurement points of the key data, using a classification strategy to classify and process multiple measurement points, and obtaining at least two measurement points of the same target data based on the corresponding relationship; Equipment layout module, responsible for obtaining the reaction time of the key parameters of the measurement points according to the historical key parameter change law, and screening the measurement point with the shortest reaction target parameter time from at least two measurement points of the same target data, i.e. the layout point; Data fusion module, responsible for synchronizing the data of different types of sensors according to the time stamp, comprehensively calculating the confidence and features of different types of sensor data, and generating the final monitored key parameters; real-time acquisition of water temperature, flow, compressor state and environmental temperature through different types of sensors; The data fusion module comprises: Time synchronization submodule, responsible for data acquisition of each sensor within a set time interval, synchronizing the data of all sensors according to the time stamp, and ensuring the same time point; Feature extraction submodule, responsible for assigning a confidence value to the data of each sensor during acquisition, obtaining the data confidence of each sensor at the current time based on the standard deviation and mean value of historical data; uniform feature extraction is performed on each data type; Weighted fusion submodule, responsible for setting the weight of each sensor feature, dynamically adjusting the weight according to the reaction time and confidence, merging the features of each sensor with the corresponding confidence; integrate all sensor data results, and fuse by weighted sum to obtain the final key parameters; The data transmission component comprises: Signal processing module, responsible for receiving the preliminary processed key parameters through the Internet of Things, and suppressing the interference of the Internet of Things signal through an algorithm during Internet of Things transmission, and transmitting the key parameters after interference suppression processing to the cloud server; Model training module, responsible for preprocessing the key parameters after interference suppression processing to obtain preprocessed key parameters, and dividing them into training set and test set according to the proportion; Model evaluation module, responsible for using test set data to evaluate support vector machine, evaluating the performance of support vector machine through mean square error and accuracy, and adjusting support vector machine parameters.

2. The IoT based remote monitoring and data acquisition system for cryogenic coupled heat pumps as claimed in claim 1 wherein, The signal processing module comprises: Signal normalization submodule, responsible for defining a normalization scale function for the Internet of Things signal to be processed; Interference judgment submodule, responsible for defining a time-frequency positioning strategy when the Internet of Things signal is interfered, and judging whether there is interference in the Internet of Things signal to be processed; Suppression execution submodule, responsible for suppressing the interference components of the Internet of Things signal with interference, and outputting the suppressed Internet of Things signal.

3. The IoT based remote monitoring and data acquisition system for cryogenic coupled heat pumps as claimed in claim 1 wherein, The model training module comprises: A dataset construction submodule is responsible for annotating the preprocessed key parameters according to the data source; A dataset processing submodule is responsible for dividing the dataset into a training set and a test set; A training execution submodule is responsible for inputting the training set for training and updating the support vector machine model parameters through an optimization algorithm.

4. The IoT-based remote monitoring and data acquisition system for cryogenic coupling heat pumps as claimed in claim 3 wherein, The dataset construction submodule constructs the preprocessed key parameters and annotation information into a dataset.

5. The IoT based remote monitoring and data acquisition system for cryogenic coupled heat pumps as claimed in claim 3 wherein, The dataset processing submodule uses a center cropping method to downsample the preprocessed key parameters in the dataset, and performs a reverse or rotation operation on the downsampled preprocessed key parameters according to a preset probability to expand the preprocessed key parameters. The expanded preprocessed key parameters are used to obtain a new dataset.

6. The IoT-based remote monitoring and data acquisition system for cryogenic coupling heat pumps as claimed in claim 3 wherein, The training execution submodule selects a core function of the support vector machine and sets a penalty parameter C and a kernel parameter.

7. The IoT-based remote monitoring and data acquisition system for cryogenic coupling heat pumps of claim 1, wherein, The feedback control component comprises: An instruction sending module is responsible for generating control instructions based on analysis results and decision making, and sending the instructions to the feedback control component; A state adjustment module is responsible for adjusting the working state of the low-temperature coupled heat pump after receiving the instructions from the cloud, adjusting the state of the compressor and the circulating flow; An alarm sending module is responsible for real-time monitoring of the running status of the low-temperature coupled heat pump through the intelligent terminal; If the low-temperature coupled heat pump is abnormal, an alarm will be sent in time.

Images