Online modeling method for heat pump system based on data fusion

Abstract

The present application relates to the technical field of online modeling, in particular to a kind of online modeling method of heat pump system based on data fusion.The method comprises the following steps: obtaining the operation log data of heat pump system, and based on these data, the operating environment data and initial state performance data of system are collected; temperature difference detection and refrigerant pressure growth estimation are carried out, further analysis of pipe stress growth and abnormal state of heat pump system; through heat pump system design data and abnormal state data, build heat pump system anomaly detection model, assess the risk level of system; all analysis results are uploaded through cloud platform, realize remote early warning and monitoring; the present application realizes heat pump system anomaly identification more accurately through the online modeling of heat pump system.

Description

TECHNICAL FIELD

[0001] The present application relates to the online modeling technical field, and in particular to a heat pump system online modeling method based on data fusion. BACKGROUND

[0002] As a kind of efficient heat conversion equipment, heat pump system is widely used in building heating, refrigeration and industrial waste heat recovery and other fields, and its performance directly affects the energy efficiency and operating cost of system. However, due to the complexity of heat pump system operating environment, and the dynamic changes of refrigerant pressure, temperature difference, compressor load and other key parameters, traditional monitoring and fault diagnosis means have been difficult to meet the modernization needs. Traditional methods mainly rely on artificial periodic inspection and static analysis based on single parameter, and there are problems such as single data dimension, lack of real-time performance and lack of prediction ability, which can easily lead to the discovery and solution of potential faults in the running process not in time, and even cause system shutdown or energy waste and other serious consequences. The online modeling method based on data fusion provides a new idea for solving the heat pump system operation state monitoring and fault diagnosis. By collecting system operation log, environmental parameters, design data and historical performance data, and combining data fusion technology and dynamic modeling theory, the real-time monitoring and intelligent analysis of heat pump system operation state are realized. However, the traditional online modeling method based on data fusion of heat pump system has the problems of inaccurate evaluation of abnormal state of heat pump system and inaccurate risk assessment of heat pump system. SUMMARY

[0003] Therefore, it is necessary to provide a heat pump system online modeling method based on data fusion to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a heat pump system online modeling method based on data fusion comprises the following steps:

[0005] Step S1: obtaining heat pump system operation log data; collecting heat pump system operating environment data according to heat pump system operation log data; obtaining heat pump system initial state performance data by analyzing heat pump system initial state performance according to heat pump system operation log data;

[0006] Step S2: obtaining heat pump system operating environment temperature difference data by detecting heat pump system temperature difference according to heat pump system operating environment data; estimating refrigerant pressure growth data of heat pump system based on heat pump system operating environment temperature difference data and heat pump system operation log data and heat pump system initial state performance data;

[0007] Step S3: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data; and evaluating the heat pump system abnormal state based on the heat pump system pipeline stress growth data to obtain the heat pump system abnormal state data.

[0008] Step S4: Obtain heat pump system design data; construct a heat pump system anomaly detection model based on the heat pump system design data and the heat pump system abnormal status data to obtain a heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain heat pump system risk data, and upload it to the cloud platform for early warning.

[0009] The present application realizes comprehensive analysis and intelligent management of the system running state through multiple steps, has obvious technical advantages and application value, obtains running log data and performs running environment collection and initial state performance analysis, can comprehensively understand the initial working state of the heat pump system, and provides accurate basic data support for subsequent monitoring and modeling. The beneficial effect of this step is that the running environment and initial performance parameters of the system can be reflected in real time, laying a solid foundation for data fusion and state evaluation. Through temperature difference detection of the running environment data, the influence of external environment changes on system performance can be effectively captured, providing reliable input data for subsequent refrigerant pressure growth prediction. This analysis method based on temperature difference change can reveal potential thermodynamic uneven problems in the system running process, helping to improve the accuracy and reliability of system performance analysis. On this basis, the prediction of refrigerant pressure growth can discover the existing pressure abnormal problems of the system in advance, effectively avoiding equipment wear or system failure caused by pressure fluctuation. This prediction method not only optimizes the running conditions, but also provides a scientific basis for reducing energy consumption and prolonging equipment life. The pipeline stress growth calculation is performed by combining the refrigerant pressure data, and the real-time monitoring and analysis of stress change helps to identify the hidden problems of the pipeline, thereby reducing the risk of pipeline rupture. Further abnormal state evaluation can comprehensively predict the potential abnormal behavior of the system. This whole-process abnormal analysis method improves the safety and stability of the system, and provides important support for ensuring the efficient operation of the system. In addition, the construction of the abnormal detection model combined with the design data not only makes the detection model have strong pertinence and applicability, but also can improve the accuracy of system diagnosis through fine analysis. The application of the abnormal detection model makes the abnormal state evaluation of the heat pump system more comprehensive and intelligent, and can provide an important reference for risk assessment. Therefore, the present application is an optimization processing of the traditional data fusion-based online modeling method of the heat pump system, solves the problems of inaccurate abnormal state evaluation of the heat pump system and inaccurate risk assessment of the heat pump system in the traditional data fusion-based online modeling method of the heat pump system, and improves the accuracy of abnormal state evaluation of the heat pump system and the accuracy of risk assessment of the heat pump system.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: obtaining heat pump system running log data;

[0012] Step S12: collecting heat pump system running environment according to heat pump system running log data, to obtain heat pump system running environment data;

[0013] Step S13: analyzing the initial state of the heat pump system according to the heat pump system running log data, to obtain the initial state data of the heat pump system;

[0014] Step S14: performing an initial state performance analysis of the heat pump system according to the initial state data of the heat pump system to obtain the initial state performance data of the heat pump system.

[0015] The acquisition of operation log data by the present invention comprehensively records the system's operational status, including changes in key parameters over time. This data foundation provides reliable support for subsequent system status analysis and model building, while also avoiding misjudgments or inaccurate analysis caused by missing data. Operating environment data collected based on the operation log data accurately reflects the impact of the external environment on system operation, enabling the system to adapt to different operating conditions in real time. This collection process not only improves the timeliness of the data but also provides data support for coupled analysis of the operating environment and system performance, ensuring the scientific nature and accuracy of subsequent analysis. Subsequently, initial system state analysis using the operation log data accurately captures the system's current operating state, providing an important basis for assessing system health. This initial state analysis effectively identifies potential anomalies or declining system performance trends, thereby preventing the accumulation of faults during long-term system operation. Performance analysis of the initial state data further deepens a comprehensive understanding of the system and clarifies the performance of various performance indicators during the initial operation phase. This not only provides a reference benchmark for subsequent system operation optimization but also lays a data foundation for the construction of anomaly detection and prediction models.

[0016] Preferably, step S2 includes the following steps:

[0017] Step S21: performing a temperature difference detection on the heat pump system according to the operating environment data of the heat pump system to obtain the operating environment temperature difference data of the heat pump system;

[0018] Step S22: performing a heat pump system operation overload analysis on the heat pump system initial state performance data based on the heat pump system operation environment temperature difference data and the heat pump system operation log data to obtain heat pump system operation overload data;

[0019] Step S23: estimating the aggravated wear of the heat pump system based on the overload data of the heat pump system operation, and obtaining aggravated wear data of the heat pump system;

[0020] Step S24: estimating the refrigerant pressure increase based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure increase data.

[0021] The present invention conducts analysis based on the operating environment data and related log data of the heat pump system. Each step has a significant beneficial effect, effectively improving the evaluation and prediction capabilities of the system's operating status. The temperature difference detection of the heat pump system can quickly reflect the dynamic changes in the system's operating environment, providing a direct basis for identifying potential operating anomalies. The accurate acquisition of temperature difference data can not only timely reflect the abnormal heat exchange conditions that occur during the operation of the heat pump, but also provide key support for subsequent overload analysis and wear prediction. The overload analysis of the initial state performance based on temperature difference data and log data further deepens the understanding of the system load distribution, helps to identify overload areas or potential bottlenecks in the early stages of operation, and thus provides direction for the optimization of system operating parameters. By analyzing the operating overload situation, the system can more comprehensively evaluate the load response under complex operating conditions and avoid the risk of component failure due to long-term overload. In addition, wear aggravation is estimated based on overload data, and the wear rate of key components in the system is effectively predicted, which provides an important basis for the formulation of maintenance strategies. Wear prediction not only extends equipment life by proactively identifying high-wear risk areas, but also reduces operational interruptions caused by unexpected failures. Wear acceleration data, used to predict refrigerant pressure growth, further enables precise control of system internal pressure dynamics, ensuring the stability of refrigerant circulation efficiency and overall system energy efficiency. Overall, this series of analytical steps, through comprehensive monitoring and prediction of the operating environment, load distribution, component wear, and refrigerant pressure, enhances the stability and adaptability of heat pump systems under complex operating conditions, while also providing a scientific basis and data support for intelligent operation and maintenance.

[0022] Preferably, step S22 includes the following steps:

[0023] Step S221: collecting the peak operation period of the heat pump system according to the heat pump system operation log data to obtain the peak operation period data of the heat pump system;

[0024] Step S222: performing a heat pump system thermal overload state analysis on the heat pump system initial state performance data based on the heat pump system operation peak period data to obtain heat pump system thermal overload data;

[0025] Step S223: performing a heat pump system operating environment temperature difference over-limit calculation based on the heat pump system operating environment temperature difference data to obtain operating environment temperature difference over-limit data;

[0026] Step S224: estimating the excessive load of the heat pump system compressor based on the initial state performance data of the heat pump system according to the operating environment temperature difference exceeding limit data, and obtaining the excessive load data of the compressor operation;

[0027] Step S225: performing heat pump system operation overload analysis based on the compressor operation overload data and the heat pump system thermal overload data to obtain the heat pump system operation overload data.

[0028] Through the gradual analysis and processing of the operating data of the heat pump system, the present invention demonstrates significant effects in improving system monitoring, optimizing performance and preventing faults in the overall steps. The collection of data during peak operating periods can accurately identify the performance of the heat pump system under high-load operating conditions, providing key data support for subsequent performance analysis and load balancing. Based on the analysis of the thermal overload status of the peak period data, we can gain an in-depth understanding of the thermal balance performance of the heat pump system under extreme conditions, timely discover and warn of potential thermal overload risks, thereby effectively preventing performance degradation or component damage caused by high temperature. The over-limit calculation of the operating environment temperature difference further evaluates the impact of external environmental changes on system operation, provides a scientific basis for dynamically adjusting operating parameters, and improves system adaptability. The estimation of excessive compressor load, combined with a comprehensive analysis of thermal overload data, helps to gain a deep insight into the operating status of the compressor, identify overload problems in advance, and reduce the risk of failure caused by overload operation. This series of closely connected steps not only achieves accurate monitoring of the operating status of the heat pump system, but also improves fault prediction capabilities through data-driven analysis methods, providing important support for extending equipment life, optimizing operating efficiency and reducing maintenance costs.

[0029] Preferably, step S222 includes the following steps:

[0030] Calculate the peak operation time of the heat pump system according to the peak operation time data of the heat pump system to obtain the peak operation time data of the heat pump system;

[0031] Based on the peak operating time data of the heat pump system, the heat accumulation effect of the heat pump system is analyzed to obtain the heat accumulation effect data of the heat pump system;

[0032] Perform overheat detection of the expansion valve of the heat pump system according to the heat accumulation effect data of the heat pump system to obtain overheat data of the expansion valve of the heat pump system;

[0033] Perform refrigerant dynamic flow anomaly detection based on the heat pump system peak operating time data and the heat pump system expansion valve overheating data to obtain refrigerant dynamic flow anomaly data;

[0034] The heat distribution heterogeneity of the heat pump system is estimated based on the abnormal data of refrigerant dynamic flow, and the heat distribution heterogeneity data of the heat pump system is obtained;

[0035] Based on the heat pump system's heat distribution heterogeneity data and the refrigerant dynamic flow anomaly data, the heat pump system's local overheating analysis is performed to obtain the heat pump system's local overheating data;

[0036] The heat pump system thermal overload state analysis is performed on the heat pump system compressor thermal cumulative effect data and the heat pump system local overheating data and the heat pump system initial state performance data to obtain the heat pump system thermal overload data.

[0037] The present application can accurately calculate the peak running time length by in-depth analysis of the heat pump system operation peak period data, thereby providing basic data support for performance optimization during high load operation of the system. The use of peak running time length data makes the heat accumulation effect analysis more accurate, which can effectively identify the accumulation trend of heat in the system during long-term operation, and lays a foundation for preventing potential overheating risks. Based on the heat accumulation effect data of the expansion valve overheating detection, the monitoring ability of the key components is further refined to ensure the stable operation of the system under the condition of heat load change. The implementation of the refrigerant dynamic flow abnormality detection can quickly identify abnormal conditions in the refrigerant flow by combining the expansion valve overheating and peak running time length data, thereby reducing the system efficiency decline or component damage caused by dynamic flow problems. The subsequent heat distribution heterogeneity estimation provides an important reference for evaluating the uniformity of heat distribution in the heat pump system, and improves the perception ability of local high temperature areas. Combined with local overheating analysis, it is helpful to comprehensively understand the specific location and degree of high temperature areas in the heat pump system, and to provide data support for taking effective measures to reduce local temperature accumulation. Through the comprehensive analysis of the compressor heat accumulation effect and local overheating, the thermal overload state of the system can be accurately evaluated, thereby effectively avoiding the threat of high temperature to the overall performance and service life of the system, and realizing the optimization of operation efficiency and significant reduction of fault risk.

[0038] Preferably, step S224 comprises the following steps:

[0039] According to the operation environment temperature difference over-limit data, the heat pump system heat acquisition demand growth estimation is performed to obtain heat pump system heat acquisition demand growth data;

[0040] Based on the heat pump system heat acquisition demand growth data, the heat pump system compression ratio growth calculation is performed to obtain heat pump system compression ratio growth data;

[0041] According to the heat pump system compression ratio growth data, the heat pump system compressor pressure growth calculation is performed to obtain heat pump system compressor pressure growth data;

[0042] The heat pump system compressor pressure growth data is used to estimate the heat pump system compressor power consumption growth to obtain heat pump system compressor power consumption growth data;

[0043] Based on the heat pump system compressor power consumption growth data and the heat pump system compressor pressure growth data, the heat pump system compressor load overestimation is performed to obtain compressor operation load overestimation data.

[0044] By analyzing data on temperature differentials exceeding operating limits, the present invention accurately predicts the growth trend of a heat pump system's heat demand, providing an important basis for predicting changes in the system's energy demand. This prediction helps adjust system operating parameters in advance to accommodate future load changes and avoid system performance degradation or failure due to sudden load increases. By calculating the compression ratio increase based on the heat demand growth data, the compressor's operating efficiency is further optimized, ensuring that the compressor can adapt to higher workloads when the load increases, while also improving the overall performance of the heat pump system. The subsequent compressor pressure growth calculation enables the system to maintain stable operation in higher pressure environments, preventing system damage or reduced operating efficiency due to excessive pressure. Power consumption growth estimation based on compressor pressure growth data provides a reference for further optimizing energy consumption, helping to determine whether compressor equipment needs to be adjusted or upgraded to reduce unnecessary energy waste. Through comprehensive analysis of compressor power consumption growth and pressure growth data, the system accurately predicts increases in compressor load, promptly identifying potential risks of excessive compressor load, avoiding equipment failures caused by overload, extending system life, and improving overall operational safety.

[0045] Preferably, step S24 includes the following steps:

[0046] Step S241: estimating the change in clearance of valve components of the heat pump system based on the wear aggravation data of the heat pump system, and obtaining the change data of clearance of valve components of the heat pump system;

[0047] Step S242: performing a heat pump system transmission pipeline deformation analysis based on the heat pump system wear aggravation data to obtain heat pump system transmission pipeline deformation data;

[0048] Step S243: Calculating the fluid resistance growth based on the heat pump system transmission pipeline deformation data and the heat pump system valve component clearance change data to obtain the heat pump system fluid resistance growth data;

[0049] Step S244: performing a refrigerant throttling effect attenuation analysis based on the heat pump system fluid resistance growth data to obtain refrigerant throttling effect attenuation data for the heat pump system;

[0050] Step S245: estimating the high-pressure-side refrigerant retention status of the heat pump system based on the refrigerant throttling effect attenuation data of the heat pump system to obtain the refrigerant high-pressure-side retention status data;

[0051] Step S246: estimating the refrigerant pressure increase based on the refrigerant high-pressure side retention status data and the heat pump system refrigerant throttling effect attenuation data to obtain the heat pump system refrigerant pressure increase data.

[0052] The present invention effectively predicts changes in the clearances of valve components by analyzing the wear-intensified data of the heat pump system, promptly discovers wear problems that occur in valve components, ensures the accuracy of system sealing and fluid control, and avoids unstable flow or reduced efficiency due to changes in valve clearance. The deformation analysis of the transmission pipeline based on the wear-intensified data helps to identify problems such as uneven force, corrosion or aging of the pipeline in advance, avoids leakage or pressure loss due to pipeline deformation, and improves the safety and stability of the system. By combining the pipeline deformation data and the valve component clearance change data to calculate the fluid resistance growth, the increase in fluid resistance during system operation is accurately predicted, providing a basis for system adjustment in advance, and avoiding reduced energy efficiency or unstable pressure due to increased resistance. Further analysis of the attenuation of the refrigerant throttling effect of the fluid resistance growth reveals the efficiency loss in the throttling process, helps adjust the working state of the throttling device or optimizes the design to improve refrigeration efficiency and energy saving effects. The estimation of the refrigerant high-pressure side retention condition based on the refrigerant throttling effect attenuation data can timely detect the refrigerant retention phenomenon, avoid excessive or uneven system pressure caused by refrigerant retention, and ensure the normal operation of the system. Based on the comprehensive analysis of the retention condition data and the refrigerant throttling effect attenuation data, the refrigerant pressure growth trend can be effectively estimated, and measures can be taken in advance to avoid compressor overload or system failure, ensuring the efficient and safe operation of the heat pump system.

[0053] Preferably, step S3 includes the following steps:

[0054] Step S31: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data;

[0055] Step S32: Calculating the rupture probability of the heat pump system based on the heat pump system pipeline stress growth data to obtain heat pump system rupture probability data;

[0056] Step S33: Predicting refrigerant leakage of the heat pump system based on the heat pump system rupture probability data to obtain refrigerant leakage data of the heat pump system;

[0057] Step S34: performing an abnormal state assessment of the heat pump system based on the refrigerant leakage data of the heat pump system and the rupture probability data of the heat pump system to obtain abnormal state data of the heat pump system.

[0058] The present invention accurately evaluates the stress change trend of the internal pipelines of the system through pipeline stress growth calculation based on refrigerant pressure growth data, promptly discovers the overload operation of the pipeline, and avoids pipeline rupture or leakage caused by excessive stress. Calculating the rupture probability in combination with pipeline stress growth data can effectively predict the rupture risk of the pipeline under different working environments, take necessary measures in advance to reduce the probability of rupture, and ensure the long-term safe operation of the system. By estimating refrigerant leakage based on rupture probability data, potential leakage risks can be identified, and the system can be helped to take preventive measures before refrigerant leakage occurs, reducing energy waste and environmental pollution. The abnormal state assessment of the heat pump system combined with refrigerant leakage data and rupture probability data comprehensively assesses the operating risks of the system under different states, promptly discovers potential faults and repairs them, thereby improving the stability and reliability of the system, reducing maintenance costs and downtime, and ensuring the efficient operation of the heat pump system.

[0059] Preferably, step S34 includes the following steps:

[0060] Step S341: performing heat pump system refrigerant reduction calculation based on the heat pump system refrigerant leakage to obtain heat pump system refrigerant reduction data;

[0061] Step S342: performing a thermodynamic balance attenuation analysis based on the refrigerant reduction data of the heat pump system to obtain thermodynamic balance attenuation data of the heat pump system;

[0062] Step S343: estimating the heat exchange efficiency attenuation of the heat pump system based on the heat pump system thermal balance attenuation data and the heat pump system rupture probability data, to obtain the heat exchange efficiency attenuation data of the heat pump system;

[0063] Step S344: performing a heat pump system energy efficiency attenuation prediction based on the heat exchange efficiency attenuation data of the heat pump system to obtain the heat pump system energy efficiency attenuation data;

[0064] Step S345: performing an abnormal state assessment of the heat pump system based on the heat pump system energy efficiency attenuation data and the heat exchange efficiency attenuation data of the heat pump system to obtain abnormal state data of the heat pump system.

[0065] The present invention performs refrigerant reduction calculations on refrigerant leakage in the heat pump system, monitors changes in the amount of refrigerant in real time, promptly detects potential leakage, and prevents system efficiency reduction or failure due to insufficient refrigerant. The refrigerant reduction data is combined with a thermodynamic balance decay analysis to accurately evaluate the system's thermodynamic balance status, revealing the system's thermodynamic imbalance caused by refrigerant leakage, and providing a basis for subsequent optimization measures. Based on the thermodynamic balance decay data and the rupture probability data, the heat exchange efficiency decay is estimated to predict the decrease in heat exchange efficiency due to the reduction in refrigerant flow, helping to take timely measures for adjustment or maintenance to avoid premature degradation of the system. Further energy efficiency decay prediction based on the heat exchange efficiency decay data helps to fully understand the changing trend of system performance, ensure that the system energy efficiency is maintained at an optimal level, and prevent unnecessary energy waste due to low energy efficiency. The abnormal state assessment of the heat pump system based on the energy efficiency decay data and the heat exchange efficiency decay data can achieve comprehensive monitoring of the system's operating status, provide early warning of potential failures, reduce maintenance costs, and improve system stability and service life.

[0066] Preferably, step S4 includes the following steps:

[0067] Step S41: Acquire heat pump system design data; perform heat pump system structure acquisition based on the heat pump system design data to obtain heat pump system structure data;

[0068] Step S42: constructing a heat pump system anomaly detection model based on the heat pump system structure data and the heat pump system abnormal state data to obtain a heat pump system anomaly detection model;

[0069] Step S43: estimating the aging trend of the heat pump system based on the abnormal state data of the heat pump system to obtain aging trend data of the heat pump system;

[0070] Step S44: Perform a heat pump system risk assessment based on the heat pump system aging trend data, obtain heat pump system risk data, and upload it to the cloud platform for early warning.

[0071] The present invention obtains and analyzes the design data and structural data of the heat pump system to fully understand the structural characteristics of the system and ensure that every detail of the system operation can be accurately monitored and evaluated. The anomaly detection model constructed based on the heat pump system structural data and abnormal state data can effectively identify potential abnormal conditions in the system and issue early warnings before problems occur, greatly improving the safety and reliability of the system. By estimating the aging trend of the abnormal state data of the heat pump system, monitoring the aging process of the system in real time, preventing performance degradation and failures, and planning maintenance work in advance, the risk assessment based on the aging trend data can accurately predict the potential risks of the heat pump system, and upload and warn in real time through the cloud platform, providing timely information, avoiding losses or interruptions due to system failures, and ensuring the long-term stable operation of the heat pump system.

[0072] This invention achieves comprehensive analysis and intelligent management of the system's operating status through multiple steps, offering significant technical advantages and application value. By acquiring operating log data, collecting operating environment data, and analyzing initial state performance, this method provides a comprehensive understanding of the heat pump system's initial operating state, providing accurate basic data support for subsequent monitoring and modeling. This step also provides real-time reflection of the system's operating environment and initial performance parameters, laying a solid foundation for data fusion and state assessment. By detecting temperature differences in operating environment data, the impact of environmental changes on system performance is effectively captured, providing reliable input data for subsequent refrigerant pressure growth estimation. This analysis method based on temperature differences can reveal potential thermodynamic inhomogeneities during system operation, helping to improve the accuracy and reliability of system performance analysis. Furthermore, the prediction of refrigerant pressure growth can proactively identify pressure anomalies in the system, effectively preventing equipment wear or system failures caused by pressure fluctuations. This prediction method not only optimizes operating conditions but also provides a scientific basis for reducing energy consumption and extending equipment life. Pipeline stress growth calculations are performed in conjunction with refrigerant pressure data. Real-time monitoring and analysis of stress changes help identify hidden pipeline problems, thereby reducing the risk of pipeline rupture. Further abnormal state assessment can integrate multiple data sources and predict potential abnormal behaviors of the system in advance. This full-process abnormality analysis method improves the safety and stability of the system and provides important support for ensuring the efficient operation of the system. In addition, the construction of the abnormality detection model in combination with the design data not only makes the detection model more targeted and applicable, but also improves the accuracy of system diagnosis through refined analysis. The application of the abnormality detection model makes the abnormal state assessment of the heat pump system more comprehensive and intelligent, and can provide an important reference for risk assessment. Therefore, the present invention is an optimization of a traditional online modeling method of a heat pump system based on data fusion, which solves the problem of inaccurate abnormal state assessment of the heat pump system and the problem of inaccurate risk assessment of the heat pump system in the traditional online modeling method of a heat pump system based on data fusion, and improves the accuracy of the abnormal state assessment of the heat pump system and the accuracy of the risk assessment of the heat pump system. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A flowchart of the steps of an online modeling method for a heat pump system based on data fusion is shown;

[0074] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0075] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0076] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0077] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0078] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0079] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0080] To achieve this, please refer to Figures 1 to 3 , an online modeling method for a heat pump system based on data fusion, comprising the following steps:

[0081] Step S1: Acquire heat pump system operation log data; collect heat pump system operation environment data based on the heat pump system operation log data to obtain heat pump system operation environment data; perform heat pump system initial state performance analysis based on the heat pump system operation log data to obtain heat pump system initial state performance data;

[0082] Step S2: performing a temperature difference detection on the heat pump system based on the heat pump system operating environment data to obtain the heat pump system operating environment temperature difference data; performing a refrigerant pressure growth estimation on the heat pump system initial state performance data based on the heat pump system operating environment temperature difference data and the heat pump system operating log data to obtain the heat pump system refrigerant pressure growth data;

[0083] Step S3: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data; and evaluating the heat pump system abnormal state based on the heat pump system pipeline stress growth data to obtain the heat pump system abnormal state data.

[0084] Step S4: Obtain heat pump system design data; construct a heat pump system anomaly detection model based on the heat pump system design data and the heat pump system abnormal status data to obtain a heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain heat pump system risk data, and upload it to the cloud platform for early warning.

[0085] In the embodiment of the present invention, reference Figure 1 As shown, in this example, the online modeling method of a heat pump system based on data fusion includes the following steps:

[0086] Step S1: Acquire heat pump system operation log data; collect heat pump system operation environment data based on the heat pump system operation log data to obtain heat pump system operation environment data; perform heat pump system initial state performance analysis based on the heat pump system operation log data to obtain heat pump system initial state performance data;

[0087] In this embodiment of the present invention, all operational parameter information related to the heat pump system is collected through the heat pump system's operational log data, including key performance indicators such as system startup and shutdown times, refrigerant flow, temperature, and pressure. This data is then used to monitor operating environment parameters through sensors and automated data acquisition equipment, analyzing changes in temperature, humidity, and air pressure, thereby obtaining the heat pump system's operational environment data. Subsequently, an initial state performance analysis is performed based on the operational log data. Specifically, this involves comparing the device's startup conditions and operating parameters to determine the system's normal operating range. The initial state performance data is then analyzed based on the device's historical operating records and parameter changes.

[0088] Step S2: performing a temperature difference detection on the heat pump system based on the heat pump system operating environment data to obtain the heat pump system operating environment temperature difference data; performing a refrigerant pressure growth estimation on the heat pump system initial state performance data based on the heat pump system operating environment temperature difference data and the heat pump system operating log data to obtain the heat pump system refrigerant pressure growth data;

[0089] In an embodiment of the present invention, temperature difference detection is performed based on the operating environment data of the heat pump system. This process identifies whether the system is within the normal operating temperature difference range by analyzing the pattern of temperature changes in the operating environment. Real-time monitoring is performed using an ambient temperature sensor and a high-precision data acquisition system, and the temperature difference data of each time period is recorded to calculate and determine whether there is a temperature difference anomaly. Based on this temperature difference data and the collected operation logs, the refrigerant pressure growth is further estimated. By correlating historical data with real-time temperature difference changes, a trend prediction algorithm is used to calculate the growth trend of the refrigerant pressure as the temperature difference changes, thereby obtaining data on the refrigerant pressure growth of the heat pump system.

[0090] Step S3: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data; and evaluating the heat pump system abnormal state based on the heat pump system pipeline stress growth data to obtain the heat pump system abnormal state data.

[0091] In an embodiment of the present invention, after obtaining refrigerant pressure growth data, pipeline stress calculations are performed based on this information. Specifically, finite element analysis is used to model the heat pump system's pipelines and simulate the stress response of the pipelines under different pressure conditions. Through a detailed analysis of factors such as pipeline material, size, and operating pressure, data on stress changes in the pipelines during operation is obtained. Combined with this stress data, an abnormal condition assessment is performed to analyze whether the pipelines are experiencing problems such as excessive stress or deformation. This process combines data analysis with physical modeling to identify potential risks that could lead to system failure or performance degradation.

[0092] Step S4: Obtain heat pump system design data; construct a heat pump system anomaly detection model based on the heat pump system design data and the heat pump system abnormal status data to obtain a heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain heat pump system risk data, and upload it to the cloud platform for early warning.

[0093] In an embodiment of the present invention, the design data of the heat pump system is obtained, including key information such as the system's structural layout, equipment specifications, pipeline design, and refrigerant type. These data are collected through system design drawings, equipment manuals, and technical documents provided by the manufacturer, and are digitally processed. An anomaly detection model is constructed by combining the system's design data with the abnormal state data of the heat pump system. This model identifies abnormal behavior of the heat pump system by learning known abnormal patterns and combining it with real-time operating data. In the process of constructing the anomaly detection model, a rule-based algorithm or an adaptive algorithm is used to analyze the differences between the system operating data and the design parameters to promptly identify potential problems. On this basis, a risk assessment of the heat pump system is conducted, various risk indicators are evaluated, and the assessment results are uploaded to the cloud platform. The cloud platform uses big data processing technology and real-time monitoring functions to conduct a comprehensive analysis of the system's operating status and generate early warning information.

[0094] Preferably, step S1 includes the following steps:

[0095] Step S11: Obtaining heat pump system operation log data;

[0096] Step S12: collecting the heat pump system operating environment data based on the heat pump system operating log data to obtain the heat pump system operating environment data;

[0097] Step S13: performing an initial state analysis of the heat pump system based on the heat pump system operation log data to obtain initial state data of the heat pump system;

[0098] Step S14: performing an initial state performance analysis of the heat pump system according to the initial state data of the heat pump system to obtain the initial state performance data of the heat pump system.

[0099] In an embodiment of the present invention, obtaining the heat pump system operation log data is achieved through high-frequency data acquisition equipment. In this step, various sensors in the heat pump system (such as temperature sensors, pressure sensors, flow sensors, etc.) record the real-time data of the system operation, covering key operating parameters such as working temperature, refrigerant pressure, flow, and ambient temperature. All collected data information will be stored in a local data storage device to ensure that all operating data can be recorded in detail regardless of the operating mode changes of the system. The log data is collected through the interface of the automated monitoring platform. The platform supports real-time monitoring of the operating status of all equipment in the heat pump system. The system transmits data with each device interface through a standardized communication protocol, and the heat pump system operation log data is obtained to collect the heat pump system operation environment data. In this step, environmental monitoring equipment (such as ambient temperature and humidity sensors, air pressure sensors, etc.) is used to synchronize data acquisition with the heat pump system operation log. By combining the collected operation log with real-time environmental data, a comprehensive understanding of the external environmental impact of the heat pump system is obtained, forming a comprehensive operating environment data set. This dataset contains information about the heat pump system's environmental temperature fluctuations, humidity changes, and air pressure variations. Based on the heat pump system's operational log data, a detailed analysis of the heat pump system's initial state is performed. Initial state analysis involves comprehensive monitoring and data collection during the device's first operating cycle after a normal startup. The system compares historical data with the device's operating parameters to determine whether current operation is within the initially designed parameter range. The analysis includes key information such as device startup time, initial refrigerant pressure, startup load, and system temperature fluctuations to ensure that there are no abnormalities during startup. After data collection, statistical analysis methods are used to process the data to generate initial state data. Initial state performance analysis is conducted based on the heat pump system's initial state data, primarily evaluating the long-term and short-term performance of the device after startup. This step calibrates the data based on the collected operating parameters, removing data that falls outside the normal fluctuation range. Then, by comparing the data with the heat pump system's design parameters, the initial performance is determined to meet design requirements. Key performance indicators during the initial phase are examined, including energy efficiency, temperature fluctuation range, and refrigerant pressure stability. The analysis tools include performance testing software and data mining algorithms, which can quickly extract useful information and analyze trends from massive amounts of data. Through multi-dimensional performance analysis, the overall performance data of the heat pump system during the initial startup period was obtained.

[0100] Preferably, step S2 includes the following steps:

[0101] Step S21: performing a temperature difference detection on the heat pump system according to the operating environment data of the heat pump system to obtain the operating environment temperature difference data of the heat pump system;

[0102] Step S22: performing a heat pump system operation overload analysis on the heat pump system initial state performance data based on the heat pump system operation environment temperature difference data and the heat pump system operation log data to obtain heat pump system operation overload data;

[0103] Step S23: estimating the aggravated wear of the heat pump system based on the overload data of the heat pump system operation, and obtaining aggravated wear data of the heat pump system;

[0104] Step S24: estimating the refrigerant pressure increase based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure increase data.

[0105] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0106] Step S21: performing a temperature difference detection on the heat pump system according to the operating environment data of the heat pump system to obtain the operating environment temperature difference data of the heat pump system;

[0107] In an embodiment of the present invention, temperature difference detection is performed based on the operating environment data of the heat pump system, which is achieved by deploying temperature sensors at key locations of the system (such as the evaporator, condenser, and environmental air inlet and outlet, etc.). The temperature sensor can record the temperature change data of the environment and different parts inside the system in real time. Through the data acquisition equipment, the output value of each sensor is read in real time, and the temperature difference between different parts is calculated to ensure that the collected data is continuously monitored during the operation of the heat pump. These data are transmitted to the central monitoring system in real time, and dynamic temperature difference analysis is performed. During the data processing process, by setting a reasonable temperature difference threshold, abnormal temperature differences caused by changes in the external environment or problems with the system itself can be detected. If the temperature difference exceeds the set threshold, it is marked as an abnormal state, providing a data basis for subsequent analysis. Through this process, detailed temperature difference data of the heat pump system is obtained.

[0108] Step S22: performing a heat pump system operation overload analysis on the heat pump system initial state performance data based on the heat pump system operation environment temperature difference data and the heat pump system operation log data to obtain heat pump system operation overload data;

[0109] In an embodiment of the present invention, the operating performance of the system under different temperature difference conditions is analyzed in combination with the data in the operation log (including workload, refrigerant flow, system pressure, etc.). By comparing the system operating data under different ambient temperature difference conditions with the standard operating state, it is analyzed whether the heat pump system is overloaded. If the operating parameters such as the refrigerant pressure or current load of the system deviate significantly from the normal range under a high temperature difference environment, it is considered that the system has entered an overload state. The overload analysis performs multi-dimensional calculations on various system data and uses a differential analysis method to compare them with the standard performance model to obtain the overload data of the heat pump system.

[0110] Step S23: estimating the aggravated wear of the heat pump system based on the overload data of the heat pump system operation, and obtaining aggravated wear data of the heat pump system;

[0111] In an embodiment of the present invention, an estimation of the aggravated wear of the heat pump system is performed based on the heat pump system operation overload data obtained in step S22. By matching the operation overload state with the performance data of the heat pump system components (such as compressors, expansion valves, pipelines, etc.) when overloaded, a reliability analysis method is used to evaluate the impact of overload on equipment wear. In this step, the main focus is on the physical changes of key components in the overload state during long-term operation, especially the fatigue of metal parts, aging of seals and other influencing factors. Combining actual test data with theoretical models, a cumulative wear model is used to predict aggravated wear. After fusing the operation overload data and equipment performance data, a statistical method is used to analyze the rate of aggravated wear, and to estimate future changes in system wear. Through this analysis, aggravated wear data of the heat pump system can be generated.

[0112] Step S24: estimating the refrigerant pressure increase based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure increase data.

[0113] In an embodiment of the present invention, based on the heat pump system wear aggravation data obtained in step S23, the refrigerant pressure growth is estimated, and the refrigerant pressure data in the heat pump system is collected using a pressure sensor, and combined with the wear aggravation data, the impact of the wear of various components of the system on the refrigerant pressure is evaluated. Since long-term overload causes wear of pipes, valves and other components, which in turn affects the refrigerant flow and pressure stability, the degree of wear of each component and the pressure fluctuation range are taken into account during the analysis process. By constructing a prediction model for refrigerant pressure growth and combining it with the change trend of wear data, the growth of refrigerant pressure in the future is predicted. This step is calculated through pressure curve analysis and a dynamic derivation method based on the wear model, which can accurately estimate the pressure change trend.

[0114] Preferably, step S22 includes the following steps:

[0115] Step S221: collecting the peak operation period of the heat pump system according to the heat pump system operation log data to obtain the peak operation period data of the heat pump system;

[0116] Step S222: performing a heat pump system thermal overload state analysis on the heat pump system initial state performance data based on the heat pump system operation peak period data to obtain heat pump system thermal overload data;

[0117] Step S223: performing a heat pump system operating environment temperature difference over-limit calculation based on the heat pump system operating environment temperature difference data to obtain operating environment temperature difference over-limit data;

[0118] Step S224: estimating the excessive load of the heat pump system compressor based on the initial state performance data of the heat pump system according to the operating environment temperature difference exceeding limit data, and obtaining the excessive load data of the compressor operation;

[0119] Step S225: performing heat pump system operation overload analysis based on the compressor operation overload data and the heat pump system thermal overload data to obtain the heat pump system operation overload data.

[0120] In an embodiment of the present invention, peak operating periods of the heat pump system are collected based on the heat pump system operation log data. Various operating parameters of the heat pump system, such as refrigerant pressure, flow rate, temperature, and system load, are acquired in real time through a data acquisition unit. By analyzing the time series of historical operation log data, the maximum load conditions within each time period, i.e., the peak operating period of the system, are identified. To ensure accurate capture of the peak period, a peak detection algorithm (e.g., an algorithm based on local extreme values) is used to extract load fluctuations and extreme points in the data, thereby determining the time when the peak operating period occurs. During this process, the log data is stored in a database and timestamped for subsequent data analysis. The resulting peak operating period data for the heat pump system provides peak data on the system load during different time periods. Based on the peak operating period data obtained in step S221, a heat pump system thermal overload status analysis is performed. By comparing the load data during the peak operating period with the standard design load data, the system overload condition during the peak period is analyzed. Specifically, a reasonable load threshold is set and an overload determination algorithm is employed to determine whether the system exceeds the normal operating load range. The algorithm used includes load statistical analysis and data smoothing to eliminate the impact of short-term fluctuations on overload determination. Furthermore, by analyzing the equipment's operating conditions under peak load, combined with key indicators such as temperature and pressure, the heat pump system is assessed for thermal overload. If the load remains above a set threshold and is accompanied by abnormal temperature or pressure fluctuations, a thermal overload condition is determined and the overload data is recorded. Based on the heat pump system's operating ambient temperature differential data, the system's ambient temperature differential exceedance calculation is performed. Real-time ambient temperature data is collected and compared with the system's internal temperature data to determine whether the ambient temperature differential exceeds the set safety range. Temperature data from various locations (such as inlet and outlet temperatures and outdoor ambient temperature) is input into the calculation system and compared against preset temperature differential limits. If the ambient temperature differential exceeds the set value, this data is recorded as an exceedance. During the exceedance calculation process, the temperature differential is combined with actual operating data using a mathematical model to determine the specific value and duration of the exceedance. To improve calculation accuracy, a comprehensive analysis is performed incorporating environmental variables (such as wind speed and humidity) to ensure that the timing and magnitude of temperature differential anomalies are accurately captured in dynamic environments. The output of this process is ambient temperature differential overrun data. Based on this data, obtained in step S223, the heat pump system's compressor overload is estimated. The impact of excessive external temperature differentials on the compressor's workload is analyzed based on the heat pump system's design parameters and operating status data. Excessive temperature differentials can lead to frequent compressor starts and stops or excessive loads, necessitating real-time monitoring and analysis of compressor load data. By recording key electrical parameters such as compressor current and voltage in real time and combining them with temperature differential data, a load estimation model is used to calculate the compressor's load trends.When an abnormal ambient temperature difference is detected, changes in the system load and the compressor's operating status are analyzed to predict whether the compressor is overloaded. The estimation process takes into account the short-term and long-term impact of the temperature difference on the compressor, assessing whether its load exceeds the equipment's capacity. This generates compressor overload data. Based on the compressor overload data obtained in step S224 and the heat pump system's thermal overload data, a heat pump system overload analysis is performed. Combining this data with the thermal overload status data, a multi-dimensional analysis is performed. The compressor load is compared with the overall system load to assess the overload risk to the entire heat pump system. During data processing, by setting reasonable load ratios and operating tolerances, an analysis is performed to determine whether there is a correlation between the compressor load and the system load. This analysis combines a heat pump system load model with an equipment performance model to estimate the load status of different equipment. The type, duration, and resulting failure risk of the overload are recorded. This analysis helps determine the overall overload status of the heat pump system and provides data support for subsequent decisions, such as equipment maintenance and early warning.

[0121] Preferably, step S222 includes the following steps:

[0122] Calculate the peak operation time of the heat pump system according to the peak operation time data of the heat pump system to obtain the peak operation time data of the heat pump system;

[0123] Based on the peak operating time data of the heat pump system, the heat accumulation effect of the heat pump system is analyzed to obtain the heat accumulation effect data of the heat pump system;

[0124] Perform overheat detection of the expansion valve of the heat pump system according to the heat accumulation effect data of the heat pump system to obtain overheat data of the expansion valve of the heat pump system;

[0125] Perform refrigerant dynamic flow anomaly detection based on the heat pump system peak operating time data and the heat pump system expansion valve overheating data to obtain refrigerant dynamic flow anomaly data;

[0126] The heat distribution heterogeneity of the heat pump system is estimated based on the abnormal data of refrigerant dynamic flow, and the heat distribution heterogeneity data of the heat pump system is obtained;

[0127] Based on the heat pump system's heat distribution heterogeneity data and the refrigerant dynamic flow anomaly data, the heat pump system's local overheating analysis is performed to obtain the heat pump system's local overheating data;

[0128] The heat pump system thermal overload state analysis is performed on the heat pump system compressor thermal cumulative effect data and the heat pump system local overheating data and the heat pump system initial state performance data to obtain the heat pump system thermal overload data.

[0129] In the embodiments of the present application, according to the peak period data of the heat pump system operation, the peak period of system operation load is identified by timestamp analysis of each peak period. The data of these periods is summarized to calculate the running time of the heat pump system under peak load in units of time length. In the specific operation, the time window-based algorithm is used to obtain the duration of each peak period, and the load value of these periods will be higher than the set threshold, and the system is in the maximum load operation state. Through the time difference calculation method, the interval time from the start time to the end time of each peak period is summed up to obtain the heat pump system peak running time data. Based on the heat pump system peak running time data, further heat accumulation effect analysis of the heat pump system is carried out. In this step, the temperature change during the peak running period needs to be tracked in combination with the heat flow model, working cycle model and operation parameters (such as pressure, temperature, etc.) of the heat pump system design. On the basis of each peak running time, the heat accumulation of each part of the heat pump system (such as compressor, expansion valve, evaporator, etc.) in this period is analyzed. The heat accumulation effect analysis adopts the integral method to calculate the heat accumulation of each peak period, and the heat effect value of each component is obtained through the heat flux density and time integral. Through the accumulated heat effect data, the total amount of heat accumulation of each part of the heat pump system under peak load is evaluated, and further the heat accumulation effect data of the heat pump system is obtained. According to the heat accumulation effect data of the heat pump system, the expansion valve overheating detection of the heat pump system is carried out, and the thermal load of the expansion valve is calculated by detecting the inlet and outlet temperature and pressure parameters of the expansion valve. Combined with the heat accumulation effect data of the heat pump system in the peak running period, it is judged whether the expansion valve is overheated due to long-term high load operation. The overheating of the expansion valve is usually caused by unstable flow or high temperature in the expansion valve, therefore, by calculating the temperature change and heat flux density in the expansion valve area, it is judged whether it exceeds the maximum working temperature designed by the expansion valve. By using the temperature monitoring and heat effect modeling method, the working state of the expansion valve is compared with the thermal load, so as to obtain whether the expansion valve exists overheating phenomenon, and the heat pump system expansion valve overheating data is obtained. Combined with the heat pump system peak running time data and the expansion valve overheating data, the dynamic flow anomaly of the refrigerant is detected, and the flow of the refrigerant between each component in the system is analyzed, especially the flow of the key nodes such as the expansion valve, evaporator, compressor, etc. Real-time flow rate, pressure and temperature data are obtained by sensors, and the standard flow characteristics of the system are compared. If significant differences are found between the actual flow rate and the expected flow rate, or the flow is interrupted or unstable under the condition of expansion valve overheating, it is considered that the refrigerant exists dynamic flow anomaly. The flow analysis and real-time data calibration method is used for monitoring, and according to the temperature difference between the inside and outside of the system and the overheating data of the expansion valve, it is detected whether the refrigerant exists flow anomaly. The detection result forms the refrigerant dynamic flow anomaly data, and based on the refrigerant dynamic flow anomaly data, the heat pump system heat distribution heterogeneity estimation is carried out.In this step, information such as refrigerant flow conditions, pressure, and temperature is collected and combined with flow anomaly data to calculate the heat distribution between various components. By analyzing heat transfer and heat flux density within each region of the heat pump system, the system is assessed for uneven heat distribution. Using thermodynamic models, the heat load of each component is calculated to determine whether heat is evenly distributed across components. If significant heat accumulation or uneven heat distribution occurs in certain areas, heat distribution heterogeneity exists. This analysis generates heat distribution heterogeneity data for the heat pump system. This data is combined with refrigerant flow anomaly data to analyze localized overheating in the heat pump system. By combining this heat distribution data with refrigerant flow anomaly data, localized overheating areas in the system are identified. Localized overheating typically occurs in areas with concentrated heat accumulation or restricted flow, such as the evaporator and expansion valve. Using real-time flow and temperature data, thermodynamic models are used to identify overheating locations and assess their severity and impact. By combining the heat pump system's historical operating data and failure cases, the probability of local overheating and its impact were further verified to obtain local overheating data for the heat pump system. Combined with the heat accumulation effect data of the heat pump system's compressor and the local overheating data, a thermal overload analysis was conducted on the heat pump system's initial performance data. By analyzing the system's thermal load and combining the heat accumulation of the equipment under high load, an assessment was made as to whether the system was overloaded. In this step, a thermal overload analysis algorithm was used to calculate the load of each component of the system and assess the risk of overall thermal overload. If equipment such as the compressor and expansion valve in the heat pump system exhibits excessive load or local overheating, the system is considered to be at risk of thermal overload, and the resulting thermal overload data for the heat pump system is obtained.

[0130] Preferably, step S224 includes the following steps:

[0131] Estimate the growth of heat acquisition demand of the heat pump system based on the temperature difference exceeding the limit data of the operating environment, and obtain the growth data of heat acquisition demand of the heat pump system;

[0132] Calculate the compression ratio growth of the heat pump system based on the heat acquisition demand growth data of the heat pump system to obtain the compression ratio growth data of the heat pump system;

[0133] Calculate the heat pump system compressor pressure growth according to the heat pump system compression ratio growth data to obtain the heat pump system compressor pressure growth data;

[0134] Estimating the power consumption growth of the heat pump system compressor based on the pressure growth data of the heat pump system compressor to obtain the power consumption growth data of the heat pump system compressor;

[0135] Based on the heat pump system compressor power consumption growth data and the heat pump system compressor pressure growth data, the heat pump system compressor overload is estimated to obtain the compressor operating overload data.

[0136] In an embodiment of the present invention, the heat demand of a heat pump system under excessive temperature differential conditions is assessed by calculating the change in system heat requirements under different environmental conditions based on data indicating excessive operating temperature differentials. Specifically, this data is acquired by a temperature sensor, which records changes in ambient temperature differentials during operation and analyzes fluctuations in ambient temperature over different time periods. Based on the periods of excessive temperature differentials, a heat transfer formula is used to dynamically estimate the heat demand of the heat pump system. The heat demand growth value of the heat pump system under the current operating conditions is derived by factoring in multiple factors, including ambient temperature, flow rate, heat load, and heat transfer efficiency. These calculations combine real-time environmental data with historical operating data through data fusion to accurately predict future changes in heat demand and generate data on the heat demand growth of the heat pump system. Based on this data on the heat demand growth of the heat pump system, a compression ratio growth calculation is further performed, employing thermodynamic principles and a compressor performance model to estimate the change in compression ratio of the compressor under different loads. The compression ratio refers to the volume ratio of the gas before and after compression in a heat pump system, and its changes are generally closely correlated with changes in heat demand. Based on the heat demand growth data, the required increase in compression ratio of the compressor under increased heat load is calculated. The calculation combines the change in heat demand with factors such as the compressor's gas flow rate, temperature, and pressure. Fluid dynamics and thermodynamics equations are then applied to derive the heat pump system's compression ratio growth data. This data is used to assess the system's operating conditions under increasing heat loads. The heat pump system's compression ratio growth data is then used to further calculate the heat pump system's compressor pressure growth. Compressor pressure typically increases with increasing compression ratio, so it's necessary to infer the pressure change based on the compression ratio change. Specifically, the relationship between compressor flow rate, density, temperature, and compression ratio is analyzed using the ideal gas state equation or compressor characteristic curve to calculate the pressure change in the heat pump system as the compression ratio increases. The calculation requires data such as the compressor's inlet and outlet temperature, pressure, and flow rate. This data is then used to infer the internal operating pressure of the compressor. As the compression ratio increases, the corresponding increase in compressor outlet pressure is calculated to obtain the heat pump system's compressor pressure growth data. This data effectively reflects the trend in compressor pressure changes under increasing system load. Based on this pressure growth data, the heat pump system's compressor power consumption increase is estimated. Power consumption is positively correlated with compressor pressure and compression ratio, so the power consumption increase can be inferred from the pressure change. Specifically, by analyzing the operating principles and energy efficiency characteristics of the compressor, a power formula is used to calculate the additional energy required by the compressor during the boosting process. The change in power is determined by factors such as flow rate, pressure differential, compression ratio, and efficiency. Based on the pressure increase, a cost-effectiveness ratio (COP) model and a thermodynamic calculation model are used to accurately calculate the compressor power consumption, determining the increase in compressor power consumption under the current load change.This calculation uses real-time system pressure data and equipment efficiency parameters to derive the heat pump system compressor power consumption growth data. Based on this data, the heat pump system compressor overload is estimated. By combining the relationship between power consumption growth and pressure growth, the compressor workload is further analyzed. In a system, an overloaded compressor manifests as a significant increase in temperature, pressure, and power consumption. Real-time power consumption and pressure data are needed to assess whether the compressor workload exceeds its rated load range. Using a load calculation formula combined with the compressor's operating parameters, it is possible to estimate whether overload could lead to overheating or failure. System monitoring data, such as compressor current, power, pressure, and temperature, is used to further assess whether the compressor is overloaded. If power consumption and pressure changes exceed the normal operating range, the system will issue a warning signal, indicating the risk of compressor overload, and generate compressor overload data.

[0137] Preferably, step S24 includes the following steps:

[0138] Step S241: estimating the change in clearance of valve components of the heat pump system based on the wear aggravation data of the heat pump system, and obtaining the change data of clearance of valve components of the heat pump system;

[0139] Step S242: performing a heat pump system transmission pipeline deformation analysis based on the heat pump system wear aggravation data to obtain heat pump system transmission pipeline deformation data;

[0140] Step S243: Calculating the fluid resistance growth based on the heat pump system transmission pipeline deformation data and the heat pump system valve component clearance change data to obtain the heat pump system fluid resistance growth data;

[0141] Step S244: performing a refrigerant throttling effect attenuation analysis based on the heat pump system fluid resistance growth data to obtain refrigerant throttling effect attenuation data for the heat pump system;

[0142] Step S245: estimating the high-pressure-side refrigerant retention status of the heat pump system based on the refrigerant throttling effect attenuation data of the heat pump system to obtain the refrigerant high-pressure-side retention status data;

[0143] Step S246: estimating the refrigerant pressure increase based on the refrigerant high-pressure side retention status data and the heat pump system refrigerant throttling effect attenuation data to obtain the heat pump system refrigerant pressure increase data.

[0144] In an embodiment of the present invention, wear of valve components is assessed based on wear accumulation data from a heat pump system. Changes in valve component clearances are a common phenomenon during wear accumulation. Therefore, wear indicator signals from real-time monitoring data are needed to predict changes in valve component clearances. In a specific implementation, parameters such as valve fluid pressure, flow rate, temperature, and operating time are used to analyze the extent of valve component wear. Fluid dynamics models are then combined with historical wear accumulation data to estimate changes in valve clearances. This calculation takes into account friction between the fluid and the valve surface, the effects of temperature fluctuations on metal components, and the loss of valve sealing due to continuous operation. This predicts the trend of valve component clearance changes and generates valve component clearance change data for the heat pump system. Based on the wear accumulation data for the heat pump system, deformation analysis of the heat pump system's transmission pipeline is performed. Pipeline deformation is typically caused by factors such as temperature changes, pressure fluctuations, fluid flow rate, and fatigue of the pipeline material during long-term operation. In this implementation, structural mechanics methods are used to quantitatively analyze pipeline deformation by collecting pipeline stress, temperature, and pressure data and combining them with material physical properties such as elastic modulus and thermal expansion coefficient. Finite element analysis (FEA) was used to analyze pipeline stress and strain, simulating pipeline deformation under different operating conditions. By comparing historical operating data with current real-time data, pipeline deformation under increased wear was predicted, resulting in heat pump system transmission pipeline deformation data. This data was combined with valve component clearance change data to calculate fluid resistance growth. Both pipeline deformation and valve clearance change directly affect fluid flow resistance. Especially after long-term operation, pipeline deformation and valve clearance change can alter the fluid flow path, thereby increasing flow resistance. To calculate fluid resistance growth, the effect of changes in the pipeline's internal cross-section on fluid flow must be analyzed based on pipeline deformation data. For valve clearance change data, the change in flow area within the valve channel must be calculated to assess fluid pressure loss. By combining fluid mechanics formulas such as the Darcy-Weisbach equation and the Bronco equation, the fluid resistance growth under the combined effects of these factors was calculated, resulting in heat pump system fluid resistance growth data. This heat pump system fluid resistance growth data was used to analyze the attenuation of refrigerant throttling. Refrigerant throttling devices (such as expansion valves) primarily regulate system temperature and pressure by controlling flow. When fluid resistance increases, the throttling effect diminishes, affecting the system's cooling efficiency. In a specific implementation, a thermodynamic model is used to simulate the performance of the throttling device, taking into account the changes in flow and pressure caused by the increase in fluid resistance. This model evaluates the change in the refrigerant's throttling effect as the fluid resistance increases. Furthermore, based on the refrigerant's thermodynamic properties and the design parameters of the throttling device, the degree of throttling effect attenuation is calculated, resulting in data on the attenuation of the refrigerant's throttling effect in the heat pump system. This data is then used to estimate the refrigerant's high-pressure side retention.In heat pump systems, the loss of throttling device efficiency can lead to poor refrigerant flow, resulting in stagnation on the high-pressure side. This stagnation reduces the refrigerant's heat transfer efficiency between the compressor and condenser, impacting overall system performance. During implementation, the degree of poor refrigerant flow is assessed based on throttling device decay data. Combined with system pressure and temperature changes, the refrigerant stagnation on the high-pressure side is then estimated. A fluid dynamics model is used to simulate the refrigerant flow process, determine the degree of poor flow and the probability of stagnation, and generate data on the high-pressure side stagnation. This high-pressure side stagnation data and throttling device decay data are combined to estimate refrigerant pressure growth. When stagnation occurs, the refrigerant pressure on the high-pressure side gradually increases, impacting system stability. During implementation, the high-pressure side stagnation data is combined with throttling device decay data, and the pressure changes are calculated using a fluid dynamics model. Based on the changes in the refrigerant's flow resistance, condensing pressure, and evaporating pressure, the refrigerant pressure growth trend under retention conditions is calculated, and the refrigerant pressure growth data for the heat pump system is obtained.

[0145] Preferably, step S3 includes the following steps:

[0146] Step S31: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data;

[0147] Step S32: Calculating the rupture probability of the heat pump system based on the heat pump system pipeline stress growth data to obtain heat pump system rupture probability data;

[0148] Step S33: Predicting refrigerant leakage of the heat pump system based on the heat pump system rupture probability data to obtain refrigerant leakage data of the heat pump system;

[0149] Step S34: performing an abnormal state assessment of the heat pump system based on the refrigerant leakage data of the heat pump system and the rupture probability data of the heat pump system to obtain abnormal state data of the heat pump system.

[0150] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0151] Step S31: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data;

[0152] In an embodiment of the present invention, the pipeline stress growth is calculated based on the refrigerant pressure growth data of the heat pump system. The increase in refrigerant pressure will generate additional stress on the inside of the pipeline, especially during long-term operation, when pressure fluctuations aggravate the stress of the pipeline material. In order to accurately calculate the growth of pipeline stress, based on the refrigerant pressure growth data, the material properties of the pipeline (such as elastic modulus, yield strength, etc.) and structural dimensions (such as pipeline diameter, wall thickness, etc.) are used to calculate using the stress-strain relationship and fluid dynamics model. A mechanical model is used to simulate the impact of refrigerant pressure changes on the inner and outer walls of the pipeline, and the maximum stress value generated under different working conditions is calculated. Furthermore, considering factors such as temperature changes and material aging, the stress growth of the pipeline is predicted by the integration method to obtain the stress growth data of the heat pump system pipeline. This data can be used to evaluate the structural safety of the pipeline during long-term use.

[0153] Step S32: Calculating the rupture probability of the heat pump system based on the heat pump system pipeline stress growth data to obtain heat pump system rupture probability data;

[0154] In an embodiment of the present invention, the rupture probability of the heat pump system is calculated based on the stress growth data of the heat pump system pipeline. Pipeline stress growth will cause fatigue of the pipeline material and increase the risk of rupture. During implementation, it is necessary to identify the weak links of the pipeline through the pipeline stress growth data. Using a material fatigue analysis model, the rupture probability of the pipeline under different operating cycles is calculated based on the historical pipeline stress data and the fatigue strength characteristics of the material. The rupture probability of the pipeline under different working conditions is evaluated through numerical simulation (such as Monte Carlo simulation), taking into account the influence of the external environment (such as temperature fluctuations, pressure fluctuations, etc.), and the probability of rupture is calculated based on the stress growth trend to obtain the rupture probability data of the heat pump system pipeline.

[0155] Step S33: Predicting refrigerant leakage of the heat pump system based on the heat pump system rupture probability data to obtain refrigerant leakage data of the heat pump system;

[0156] In an embodiment of the present invention, refrigerant leakage is estimated based on the rupture probability data of the heat pump system. In the event of a rupture in the pipeline, refrigerant leakage will be inevitable. During implementation, a refrigerant leakage prediction model is established by combining the rupture probability data with the crack propagation rate of the pipeline material. By combining numerical simulation with experimental data, the refrigerant leakage rate after the rupture occurs is calculated, and the leakage path, the number of leakage points and the flow rate are analyzed. By comparing historical data and combining the actual operating environment of the pipeline, the key factors leading to refrigerant leakage (such as pipeline position, pressure fluctuation, refrigerant flow rate, etc.) are calculated. Through refrigerant leakage simulation, the refrigerant leakage data of the heat pump system is obtained.

[0157] Step S34: performing heat pump system abnormal state evaluation according to the heat pump system refrigerant leakage data and the heat pump system rupture probability data, to obtain heat pump system abnormal state data.

[0158] In the embodiment of the present application, the heat pump system abnormal state evaluation is performed by combining the heat pump system refrigerant leakage data and the heat pump system rupture probability data. On the basis of the refrigerant leakage and rupture probability analysis, the system needs to comprehensively evaluate the overall abnormal state. In implementation, the refrigerant leakage data is used to identify the existing leakage source and analyze the influence of the leakage point on the entire system. Then, the rupture probability data is combined with the leakage risk, and through a multi-dimensional system model, it is evaluated whether the system is in a dangerous state. Considering the factors such as system efficiency reduction, equipment damage or environmental pollution caused by refrigerant leakage, the real-time monitoring data (such as pressure, flow, temperature change, etc.) is used to dynamically detect the system running state, to determine whether there is an abnormal state, and to obtain the heat pump system abnormal state data.

[0159] Preferably, step S34 comprises the following steps:

[0160] Step S341: performing heat pump system refrigerant reduction calculation according to the heat pump system refrigerant leakage, to obtain heat pump system refrigerant reduction data;

[0161] Step S342: performing heat balance decay analysis according to the heat pump system refrigerant reduction data, to obtain heat pump system heat balance decay data;

[0162] Step S343: performing heat pump system heat exchange efficiency decay estimation based on the heat pump system heat balance decay data and the heat pump system rupture probability data, to obtain heat pump system heat exchange efficiency decay data;

[0163] Step S344: performing heat pump system energy efficiency decay prediction according to the heat pump system heat exchange efficiency decay data, to obtain heat pump system energy efficiency decay data;

[0164] Step S345: performing heat pump system abnormal state evaluation based on the heat pump system energy efficiency decay data and the heat pump system heat exchange efficiency decay data, to obtain heat pump system abnormal state data.

[0165] In embodiments of the present invention, refrigerant leakage in a heat pump system can lead to a reduction in refrigerant volume, impacting the system's cooling and heating performance. Based on the refrigerant leakage, the refrigerant pressure, flow rate, and temperature changes in the system are monitored in real time using measurement equipment (such as pressure sensors and flow meters). The refrigerant reduction is calculated. The refrigerant reduction is estimated using mass conservation methods and fluid dynamics models based on factors such as the leak size, leak frequency, and operating pressure. Data fusion methods are used to accurately calculate the specific amount of refrigerant reduction at the time of the leak, combining the refrigerant circulation system and valve switching status of the heat pump system. Furthermore, the refrigerant reduction rate is calculated based on the leakage situation to obtain refrigerant reduction data for the heat pump system. Refrigerant reduction can cause a decrease in the heat pump system's thermal balance, thereby affecting the system's operating efficiency. In this step, the refrigerant reduction data obtained in the previous step are combined with thermodynamic equations to analyze the heat pump system's thermal balance. During operation, the refrigerant's thermal changes (such as evaporation and condensation) must maintain thermal equilibrium. When refrigerant is reduced, the system's heat transfer efficiency during evaporation and condensation changes, causing thermal degradation. By establishing a mathematical model that models the impact of changes in refrigerant volume on heat transfer, the system's internal heat losses are calculated. Combined with sensor data, the system's temperature and pressure changes are monitored in real time to assess the heat pump system's thermal equilibrium state, generating thermal equilibrium decay data. The heat pump system's heat transfer efficiency is directly affected by the thermal equilibrium and losses in system components. In this step, the heat pump system's heat transfer efficiency decay is estimated by combining thermal equilibrium decay data with rupture probability data. The heat exchanger's operating efficiency is evaluated based on the system's design parameters and operating environment. As refrigerant volume decreases and the risk of rupture increases, the system's heat transfer capacity gradually decreases. Using a thermodynamic analysis model, factors such as temperature difference, fluid flow rate, and heat transfer area are combined to estimate heat exchanger efficiency decay. Furthermore, considering the reduction in refrigerant volume within the heat exchanger due to pipe rupture or refrigerant leakage, combined with rupture probability data, the declining trend in heat transfer efficiency is calculated to generate heat pump system efficiency decay data. Heat transfer efficiency decay directly impacts the heat pump system's energy efficiency. Based on the heat exchange efficiency decay data obtained in the previous step, the heat pump system's energy efficiency decay is predicted. Using the heat pump system's operating model, combined with the refrigerant's state and changes in heat transfer, the energy input required for the system is estimated when heat exchange efficiency decreases. As efficiency decays, the heat pump system requires more energy to maintain the same heat output, resulting in reduced energy efficiency. By comparing energy efficiency changes under different workloads and incorporating factors such as system operating time and refrigerant volume changes, a system energy efficiency prediction calculation is performed to obtain heat pump system energy efficiency decay data. Combining the heat pump system's energy efficiency decay data with the heat exchange efficiency decay data, an abnormal system status assessment is performed. In this step, through multi-dimensional data fusion analysis, the degree of energy efficiency decay is used to determine whether the heat pump system has experienced a significant decrease in operating efficiency.Secondly, combined with heat exchange efficiency decay data, we assess whether the system has reached its heat exchange capacity bottleneck. Using real-time monitoring data from the heat pump system, combined with the aforementioned decay data, we use an anomaly detection algorithm to comprehensively analyze the system's operating status. When the system's energy efficiency falls below the set normal operating range, or when there's a significant decrease in heat exchange efficiency, this indicates a system abnormality. This comprehensive assessment yields data on the heat pump system's abnormal status.

[0166] Preferably, step S4 includes the following steps:

[0167] Step S41: Acquire heat pump system design data; perform heat pump system structure acquisition based on the heat pump system design data to obtain heat pump system structure data;

[0168] Step S42: constructing a heat pump system anomaly detection model based on the heat pump system structure data and the heat pump system abnormal state data to obtain a heat pump system anomaly detection model;

[0169] Step S43: estimating the aging trend of the heat pump system based on the abnormal state data of the heat pump system to obtain aging trend data of the heat pump system;

[0170] Step S44: Perform a risk assessment of the heat pump system based on the aging trend data of the heat pump system, obtain the risk data of the heat pump system, and upload it to the cloud platform for early warning.

[0171] In embodiments of the present invention, design data typically includes the main components of the heat pump system, operating parameters, component dimensions, material properties, and the like. System structure data is collected based on system design drawings, equipment manuals, and relevant standards, gathering key physical parameters such as the design dimensions, efficiency, power, and fluid type of components such as the condenser, evaporator, compressor, and expansion valve. The design data is digitally entered into a computer system using CAD drawings, BIM models, or a data acquisition module within a PLC control system. By processing the design data, the heat pump system's structural data is obtained. After obtaining this heat pump system structural data, a heat pump system anomaly detection model is constructed using the heat pump system's abnormal state data (including deviation data during equipment operation, such as compressor overtemperature and pressure fluctuations). Based on the heat pump system's structural data, an operating model for each component is established, taking into account its operating characteristics and the type of fault that may occur. The system is then monitored using sensor data, operation logs, and actual equipment performance data. Data mining and machine learning methods (such as support vector machines, random forests, and decision trees) are employed to construct an anomaly detection model based on historical fault data and real-time sensor data. This model can identify abnormal data that is inconsistent with normal operating conditions and assess the system's health status in real time based on the heat pump system's actual operating conditions, thereby detecting failures or performance degradation early. Based on abnormal status data of the heat pump system, the aging trend of the heat pump system is estimated. Long-term operating data of the heat pump system is collected, including abnormal conditions (such as compressor overload and pipeline vibration) and their corresponding operating environment (such as temperature and pressure). By analyzing historical failure patterns and utilizing statistical methods (such as regression analysis and time series analysis), an aging prediction model for the heat pump system is established. The model analyzes the aging rate and wear trend of each system component based on the system's operating time, load changes, and failure frequency. Combining the heat pump system's design data and operating conditions, aging trend data is generated. Based on this aging trend data, a risk assessment of the heat pump system is conducted. Based on the system's aging model, the probability of failure of each component within a certain period of time is estimated. The overall risk level of the system is calculated by combining data such as equipment usage frequency and maintenance history. During the risk assessment process, risk analysis methods (such as Fault Tree Analysis (FMEA) or Monte Carlo simulation) are used to quantify the system's risk level, taking into account factors such as failure modes, system capacity degradation, and refrigerant leaks. The assessment results include the risk level of each component, the overall system health status, and the expected time to failure. The resulting heat pump system risk data is uploaded to a cloud platform via the internet or intranet for remote monitoring. The cloud platform analyzes the system's risk data in real time and automatically issues warnings based on pre-set risk thresholds.

[0172] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A heat pump system online modeling method based on data fusion, characterized in that: The following steps are involved: Step S1: Acquire heat pump system operation log data; collect heat pump system operation environment data based on the heat pump system operation log data to obtain heat pump system operation environment data; perform heat pump system initial state performance analysis based on the heat pump system operation log data to obtain heat pump system initial state performance data; Step S2: performing a temperature difference detection on the heat pump system according to the operating environment data of the heat pump system to obtain the operating environment temperature difference data of the heat pump system; performing a refrigerant pressure growth estimation on the initial state performance data of the heat pump system based on the operating environment temperature difference data of the heat pump system and the operating log data of the heat pump system to obtain the refrigerant pressure growth data of the heat pump system, wherein step S2 includes the following steps: Step S21: performing a temperature difference detection on the heat pump system according to the operating environment data of the heat pump system to obtain the operating environment temperature difference data of the heat pump system; Step S22: performing a heat pump system operation overload analysis on the heat pump system initial state performance data based on the heat pump system operation environment temperature difference data and the heat pump system operation log data to obtain heat pump system operation overload data; Step S23: estimating the aggravated wear of the heat pump system based on the overload data of the heat pump system operation, and obtaining aggravated wear data of the heat pump system; Step S24: estimating the refrigerant pressure increase based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure increase data, wherein step S24 includes the following steps: Step S241: estimating the change in clearance of valve components of the heat pump system based on the wear aggravation data of the heat pump system, and obtaining the change data of clearance of valve components of the heat pump system; Step S242: performing a heat pump system transmission pipeline deformation analysis based on the heat pump system wear aggravation data to obtain heat pump system transmission pipeline deformation data; Step S243: Calculating the fluid resistance growth based on the heat pump system transmission pipeline deformation data and the heat pump system valve component clearance change data to obtain the heat pump system fluid resistance growth data; Step S244: performing a refrigerant throttling effect attenuation analysis based on the heat pump system fluid resistance growth data to obtain refrigerant throttling effect attenuation data for the heat pump system; Step S245: estimating the high-pressure-side refrigerant retention status of the heat pump system based on the refrigerant throttling effect attenuation data of the heat pump system to obtain the refrigerant high-pressure-side retention status data; Step S246: estimating the refrigerant pressure increase based on the refrigerant high-pressure side retention status data and the heat pump system refrigerant throttling effect attenuation data to obtain the heat pump system refrigerant pressure increase data; Step S3: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data; and evaluating the heat pump system abnormal state based on the heat pump system pipeline stress growth data to obtain the heat pump system abnormal state data. Step S4: Obtain heat pump system design data; construct a heat pump system anomaly detection model based on the heat pump system design data and the heat pump system abnormal status data to obtain a heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain heat pump system risk data, and upload it to the cloud platform for early warning.

2. The online modeling method of heat pump system based on data fusion according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining heat pump system operation log data; Step S12: collecting the heat pump system operating environment data based on the heat pump system operating log data to obtain the heat pump system operating environment data; Step S13: analyzing the initial state of the heat pump system according to the heat pump system operation log data to obtain the initial state data of the heat pump system; Step S14: performing an initial state performance analysis of the heat pump system based on the initial state data of the heat pump system to obtain the initial state performance data of the heat pump system.

3. The online modeling method of heat pump system based on data fusion according to claim 1 is characterized in that: Step S22 includes the following steps: Step S221: collecting the peak operation period of the heat pump system according to the heat pump system operation log data to obtain the peak operation period data of the heat pump system; Step S222: performing a heat pump system thermal overload state analysis on the heat pump system initial state performance data based on the heat pump system operation peak period data to obtain heat pump system thermal overload data; Step S223: performing a heat pump system operating environment temperature difference over-limit calculation based on the heat pump system operating environment temperature difference data to obtain operating environment temperature difference over-limit data; Step S224: estimating the excessive load of the heat pump system compressor based on the initial state performance data of the heat pump system according to the operating environment temperature difference exceeding limit data, and obtaining the excessive load data of the compressor operation; Step S225: performing heat pump system operation overload analysis based on the compressor operation overload data and the heat pump system thermal overload data to obtain the heat pump system operation overload data.

4. The online modeling method of heat pump system based on data fusion according to claim 3 is characterized in that: Step S222 includes the following steps: Calculate the peak operation time of the heat pump system according to the peak operation time data of the heat pump system to obtain the peak operation time data of the heat pump system; Based on the peak operating time data of the heat pump system, the heat accumulation effect of the heat pump system is analyzed to obtain the heat accumulation effect data of the heat pump system; Perform overheat detection of the expansion valve of the heat pump system according to the heat accumulation effect data of the heat pump system to obtain overheat data of the expansion valve of the heat pump system; Perform refrigerant dynamic flow anomaly detection based on the heat pump system peak operating time data and the heat pump system expansion valve overheating data to obtain refrigerant dynamic flow anomaly data; The heat distribution heterogeneity of the heat pump system is estimated based on the abnormal data of refrigerant dynamic flow, and the heat distribution heterogeneity data of the heat pump system is obtained; Based on the heat pump system's heat distribution heterogeneity data and the refrigerant dynamic flow anomaly data, the heat pump system's local overheating analysis is performed to obtain the heat pump system's local overheating data; The heat pump system thermal overload state analysis is performed on the heat pump system compressor thermal cumulative effect data and the heat pump system local overheating data and the heat pump system initial state performance data to obtain the heat pump system thermal overload data.

5. The online modeling method of heat pump system based on data fusion according to claim 3 is characterized in that: Step S224 includes the following steps: Estimate the growth of heat acquisition demand of the heat pump system based on the temperature difference exceeding the limit data of the operating environment, and obtain the growth data of heat acquisition demand of the heat pump system; Calculate the compression ratio growth of the heat pump system based on the heat acquisition demand growth data of the heat pump system to obtain the compression ratio growth data of the heat pump system; Calculate the heat pump system compressor pressure growth according to the heat pump system compression ratio growth data to obtain the heat pump system compressor pressure growth data; Estimating the power consumption growth of the heat pump system compressor based on the pressure growth data of the heat pump system compressor to obtain the power consumption growth data of the heat pump system compressor; Based on the heat pump system compressor power consumption growth data and the heat pump system compressor pressure growth data, the heat pump system compressor overload is estimated to obtain the compressor operating overload data.

6. The online modeling method of heat pump system based on data fusion according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Calculating the heat pump system pipeline stress growth based on the heat pump system refrigerant pressure growth data to obtain the heat pump system pipeline stress growth data; Step S32: Calculating the rupture probability of the heat pump system based on the heat pump system pipeline stress growth data to obtain heat pump system rupture probability data; Step S33: Predicting refrigerant leakage of the heat pump system based on the heat pump system rupture probability data to obtain refrigerant leakage data of the heat pump system; Step S34: performing an abnormal state assessment of the heat pump system based on the refrigerant leakage data of the heat pump system and the rupture probability data of the heat pump system to obtain abnormal state data of the heat pump system.

7. The online modeling method of heat pump system based on data fusion according to claim 6 is characterized in that: Step S34 includes the following steps: Step S341: performing heat pump system refrigerant reduction calculation based on the heat pump system refrigerant leakage to obtain heat pump system refrigerant reduction data; Step S342: performing a thermodynamic balance attenuation analysis based on the refrigerant reduction data of the heat pump system to obtain thermodynamic balance attenuation data of the heat pump system; Step S343: estimating the heat exchange efficiency attenuation of the heat pump system based on the heat pump system thermal balance attenuation data and the heat pump system rupture probability data, to obtain the heat exchange efficiency attenuation data of the heat pump system; Step S344: performing a heat pump system energy efficiency attenuation prediction based on the heat exchange efficiency attenuation data of the heat pump system to obtain the heat pump system energy efficiency attenuation data; Step S345: performing an abnormal state assessment of the heat pump system based on the heat pump system energy efficiency attenuation data and the heat exchange efficiency attenuation data of the heat pump system to obtain abnormal state data of the heat pump system.

8. The online modeling method of heat pump system based on data fusion according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Acquire heat pump system design data; perform heat pump system structure acquisition based on the heat pump system design data to obtain heat pump system structure data; Step S42: constructing a heat pump system anomaly detection model based on the heat pump system structure data and the heat pump system abnormal state data to obtain a heat pump system anomaly detection model; Step S43: estimating the aging trend of the heat pump system based on the abnormal state data of the heat pump system to obtain aging trend data of the heat pump system; Step S44: Perform a risk assessment of the heat pump system based on the aging trend data of the heat pump system, obtain the risk data of the heat pump system, and upload it to the cloud platform for early warning.

Images