Heat pump system online modeling method based on data fusion

Abstract

The invention relates to the technical field of online modeling, in particular to a heat pump system online modeling method based on data fusion. The method comprises the following steps: acquiring operation log data of the heat pump system, and acquiring operation environment data and initial state performance data of the system based on the data; temperature difference detection and refrigerant pressure increase estimation are conducted, and pipeline stress increase and the abnormal state of the heat pump system are further analyzed; a heat pump system anomaly detection model is constructed through heat pump system design data and abnormal state data, and the risk level of the system is evaluated; all analysis results are uploaded through the cloud platform to realize remote early warning and monitoring; through online modeling of the heat pump system, abnormity identification of the heat pump system is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of online modeling, and in particular to an online modeling method for a heat pump system based on data fusion. Background Art

[0002] As an efficient heat energy conversion device, heat pump system is widely used in building heating, refrigeration and industrial waste heat recovery. Its performance directly affects the energy efficiency and operation cost of the system. However, due to the complexity of the operating environment of heat pump system and the dynamic changes of key parameters such as refrigerant pressure, temperature difference and compressor load, traditional monitoring and fault diagnosis methods can no longer meet the needs of modernization. Traditional methods mainly rely on manual regular inspection and static analysis based on single parameters. There are problems such as single data dimension, insufficient real-time performance and lack of prediction ability, which can easily lead to the untimely discovery and solution of potential faults during operation, and even cause serious consequences such as system shutdown or energy waste. The online modeling method based on data fusion provides a new idea for solving the operation status monitoring and fault diagnosis of heat pump system. By collecting system operation logs, environmental parameters, design data and historical performance data, and combining data fusion technology and dynamic modeling theory, real-time monitoring and intelligent analysis of the operation status of heat pump system can be realized. However, the traditional online modeling method of heat pump system based on data fusion has the problem of inaccurate evaluation of abnormal state of heat pump system and inaccurate risk assessment of heat pump system. Summary of the invention

[0003] Based on this, it is necessary to provide an online modeling method for a heat pump system 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 includes the following steps:

[0005] Step S1: Acquire the operation log data of the heat pump system; collect the operation environment of the heat pump system according to the operation log data of the heat pump system to obtain the operation environment data of the heat pump system; perform the initial state performance analysis of the heat pump system according to the operation log data of the heat pump system to obtain the initial state performance data of the heat pump system;

[0006] Step S2: performing a temperature difference detection of 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;

[0007] Step S3: Calculate 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; evaluate 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: Acquire the design data of the heat pump system; construct a heat pump system anomaly detection model based on the heat pump system design data and the abnormal state data of the heat pump system to obtain the heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain the heat pump system risk data, and upload it to the cloud platform for early warning.

[0009] The present invention realizes comprehensive analysis and intelligent management of the system operation status through multiple steps, has significant technical advantages and application value, obtains operation log data and performs operation environment collection and initial state performance analysis, can fully understand the initial working state of the heat pump system, and provide accurate basic data support for subsequent monitoring and modeling. The beneficial effect of this step is that it can reflect the system's operating environment and initial performance parameters in real time, laying a solid foundation for data fusion and state evaluation. By detecting the temperature difference of the operating environment data, the impact of external environmental changes on system performance is effectively captured, and reliable input data is provided for subsequent refrigerant pressure growth estimation. This analysis method based on temperature difference changes can reveal potential thermodynamic unevenness problems during system operation, which helps to improve the accuracy and reliability of system performance analysis. On this basis, the prediction of refrigerant pressure growth can detect the abnormal pressure problems in the system in advance, and effectively avoid equipment wear or system failure caused by pressure fluctuations. This prediction method can not only optimize the operating conditions, but also provide a scientific basis for reducing energy consumption and extending equipment life. The pipeline stress growth calculation is carried out by combining the refrigerant pressure data, and the real-time monitoring and analysis of stress changes help identify hidden problems in the pipeline, thereby reducing the risk of pipeline rupture. Further abnormal state assessment can integrate multiple data sources to predict potential abnormal behaviors of the system in advance. This full-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 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 abnormal 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 for a heat pump system based on data fusion, which solves the problem of inaccurate abnormal state assessment of the heat pump system and inaccurate risk assessment of the heat pump system in a traditional online modeling method for a heat pump system based on data fusion, and improves the accuracy of abnormal state assessment 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 operation log data;

[0012] Step S12: collecting the operating environment of the heat pump system according to the operating log data of the heat pump system to obtain the operating environment data of the heat pump system;

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

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

[0015] The acquisition of the operation log data of the present invention can comprehensively record the operation of the system, including the changes of key parameters in the time series. This data foundation provides reliable support for the subsequent system state analysis and model construction, and avoids the problem of misjudgment or inaccurate analysis caused by data loss. Based on the operation log data, the operation environment is collected to accurately reflect the impact of the external environment on the system operation, so that the system can 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 the coupling analysis of the operating environment and system performance, ensuring the scientificity and accuracy of the subsequent analysis. Then, the initial state analysis of the system is performed using the operation log data, which can accurately capture the current working state of the system and provide an important basis for the evaluation of the health state of the system. Through such an initial state analysis, potential anomalies or the decline trend of system performance can be effectively identified, thereby avoiding the accumulation of faults in the long-term operation of the system. Through the performance analysis of the initial state data, the comprehensive understanding of the system is further deepened, and the performance of each performance indicator in the initial operation stage is clarified. This not only provides a reference benchmark for the subsequent system operation optimization, but also lays a data foundation for the construction of anomaly detection and prediction models.

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

[0017] Step S21: performing a temperature difference detection of 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 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 the 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 growth based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure growth 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 operating status. The temperature difference detection of the heat pump system can quickly reflect the dynamic changes of the system operating environment, and provide a direct basis for identifying potential operating abnormalities. The accurate acquisition of temperature difference data can not only timely reflect the abnormal heat exchange situation that occurs 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, which helps to identify overload areas or potential bottlenecks in the early stage of operation, thereby providing 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 caused by 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 can not only extend the service life of the equipment by identifying high wear risk areas in advance, but also reduce operation interruptions caused by unexpected failures. Wear aggravation data is used to estimate the increase in refrigerant pressure, which further realizes the precise control of the pressure dynamics inside the system and ensures the stability of the refrigerant circulation efficiency and the overall energy efficiency of the system. Overall, this series of analysis steps improves the stability and adaptability of the heat pump system under complex working conditions through comprehensive monitoring and prediction of the operating environment, load distribution, component wear and refrigerant pressure, while providing scientific basis and data support for intelligent operation and maintenance.

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

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

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

[0026] Step S224: performing an overload estimation of the compressor of the heat pump system based on the initial state performance data of the heat pump system according to the over-limit data of the operating environment temperature difference, and obtaining the over-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] The present invention gradually analyzes and processes the operating data of the heat pump system, and the overall steps show the significant effect of improving system monitoring, optimizing performance and preventing faults. The collection of data during the peak period of operation can accurately identify the performance of the heat pump system under high-load operation, providing key data support for subsequent performance analysis and load balancing. Based on the analysis of the thermal overload state of the peak period data, we can deeply understand the thermal balance performance of the heat pump system under extreme conditions, timely discover and warn 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 the operation of the system, provides a scientific basis for dynamically adjusting the operating parameters, and improves the adaptability of the system. The estimation of the excessive load of the compressor, combined with the comprehensive analysis of the thermal overload data, helps to gain a deep insight into the operating status of the compressor, identify the overload problem in advance, and reduce the risk of failure caused by overload operation. This series of closely connected steps not only realizes the accurate monitoring of the operating status of the heat pump system, but also improves the fault prediction capability 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 period data of the heat pump system to obtain the peak operation time data of the heat pump system;

[0031] Based on the peak operation 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 peak operation time data of the heat pump system and the overheating data of the expansion valve of the heat pump system to obtain refrigerant dynamic flow anomaly data;

[0034] Based on the abnormal data of refrigerant dynamic flow, the heat distribution heterogeneity of the heat pump system is estimated to obtain the heat distribution heterogeneity data of the heat pump system;

[0035] According to the heat distribution heterogeneity data of the heat pump system and the abnormal dynamic flow data of the refrigerant, the local overheating analysis of the heat pump system is carried out to obtain the local overheating data of the heat pump system;

[0036] The heat overload state of the heat pump system is analyzed by using the heat accumulation effect data of the heat pump system compressor and the local overheating data of the heat pump system and the initial state performance data of the heat pump system to obtain the heat overload data of the heat pump system.

[0037] Through in-depth analysis of the peak operation period data of the heat pump system, the present invention can accurately calculate the peak operation time, thereby providing basic data support for performance optimization during high-load operation of the system. The use of peak operation time data makes the thermal accumulation effect analysis more accurate, and can effectively identify the accumulation trend of heat inside the system during long-term operation, laying the foundation for preventing potential overheating risks. Expansion valve overheat detection based on thermal accumulation effect data further refines the monitoring capabilities of key components to ensure the stable operation of the system under changing thermal load conditions. The implementation of refrigerant dynamic flow anomaly detection, by combining expansion valve overheating and peak operation time data, can quickly identify abnormal conditions in refrigerant flow and reduce system efficiency reduction or component damage caused by dynamic flow problems. The subsequent estimation of heat distribution heterogeneity provides an important reference for evaluating the uniformity of heat distribution inside the heat pump system and improves the perception of local areas with excessive heat. Combined with local overheating analysis, it is helpful to fully understand the specific location and extent of high-temperature areas in the heat pump system, and provide data support for taking effective measures to reduce local temperature accumulation. Through comprehensive analysis of the compressor thermal accumulation effect and local overheating, the thermal overload state of the system can be accurately assessed, thereby effectively avoiding the threat of high temperature to the overall performance and life of the system, and achieving optimization of operating efficiency and significant reduction of failure risks.

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

[0039] According to the temperature difference exceeding the limit data of the operating environment, the heat acquisition demand growth of the heat pump system is estimated to obtain the heat acquisition demand growth data of the heat pump system;

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

[0041] Calculate the compressor pressure growth of the heat pump system according to the compression ratio growth data of the heat pump system to obtain the compressor pressure growth data of the heat pump system;

[0042] The heat pump system compressor power consumption growth is estimated based on the heat pump system compressor pressure growth data to obtain the 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 overload is estimated to obtain the compressor operating overload data.

[0044] The present invention accurately estimates the growth trend of the heat acquisition demand of the heat pump system by analyzing the over-limit data of the temperature difference of the operating environment, and provides an important prediction basis for the energy demand change of the system. This prediction helps to adjust the system operating parameters in advance to adapt to future load changes and avoid system performance degradation or failure caused by sudden load increase. Through the compression ratio growth calculation based on the heat acquisition demand growth data, the operating efficiency of the compressor is further optimized to ensure that the compressor can adapt to higher work intensity when the load increases, and at the same time improve the overall performance of the heat pump system. The subsequent compressor pressure growth calculation enables the system to maintain stable operation when dealing with a higher pressure environment, preventing system damage or reduced operating efficiency due to excessive pressure. The power consumption growth estimation based on the compressor pressure growth data provides a reference for further optimizing energy consumption, helps to determine whether it is necessary to adjust or upgrade the compressor equipment to reduce unnecessary energy waste, and accurately estimates the increase in compressor load through comprehensive analysis of the compressor power consumption growth data and pressure growth data, timely discovers the potential risk of excessive compressor load, avoids equipment failure caused by overload, extends the service life of the system, and improves the overall operation safety.

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

[0046] Step S241: Predicting the change in clearance of valve components of the heat pump system according to the wear aggravation data of the heat pump system, and obtaining the change in clearance of valve components of the heat pump system;

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

[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 the heat pump system refrigerant throttling effect attenuation data;

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

[0051] Step S246: The refrigerant pressure increase is estimated 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 estimates the change of the clearance of valve components through the analysis of the wear aggravation data of the heat pump system, promptly discovers the wear problems of valve components, ensures the accuracy of system sealing and fluid control, and avoids unstable flow or reduced efficiency caused by changes in valve clearance. The deformation analysis of the transmission pipeline based on the wear aggravation data helps to identify problems such as uneven force, corrosion or aging of the pipeline in advance, avoids leakage or pressure loss caused by 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 of fluid resistance during system operation is accurately estimated, and a basis is provided for system adjustment in advance to avoid reduced energy efficiency or unstable pressure caused by 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 the refrigeration efficiency and energy saving effect. 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 comprises 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 the heat pump system rupture probability data;

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

[0057] Step S34: evaluating the abnormal state of the heat pump system according to 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 pipeline 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 probability of rupture 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 according to the refrigerant leakage of the heat pump system to obtain the refrigerant reduction data of the heat pump system;

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

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

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

[0064] Step S345: Based on the heat pump system energy efficiency attenuation data and the heat exchange efficiency attenuation data of the heat pump system, an abnormal state evaluation of the heat pump system is performed 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, and promptly discovers potential leakage situations to prevent system efficiency reduction or failures due to insufficient refrigerant. Thermodynamic balance attenuation analysis is performed in combination with refrigerant reduction data to accurately evaluate the thermal balance status of the system, reveal the thermal imbalance of the system caused by refrigerant leakage, and provide a basis for subsequent optimization measures. Heat exchange efficiency attenuation is estimated based on thermal balance attenuation data and rupture probability data to predict the decrease in heat exchange efficiency due to reduced refrigerant flow, and help take timely measures to adjust or repair to avoid premature system decline. Further energy efficiency attenuation prediction based on heat exchange efficiency attenuation data helps to fully understand the changing trend of system performance, ensure that the system energy efficiency remains at an optimal level, and prevent unnecessary energy waste due to low energy efficiency. The abnormal state assessment of the heat pump system combined with energy efficiency attenuation data and heat exchange efficiency attenuation data can achieve comprehensive monitoring of the system operation status, early warning of potential failures, reduce maintenance costs, and improve system stability and service life.

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

[0067] Step S41: Acquire heat pump system design data; collect heat pump system structure data according to the heat pump system design data to obtain heat pump system structure data;

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

[0070] 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.

[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 predicting 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 combined with 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] The present invention is to realize comprehensive analysis and intelligent management of the system operation status through multiple steps, has significant technical advantages and application value, obtains operation log data and performs operation environment collection and initial state performance analysis, can fully understand the initial working state of the heat pump system, and provide accurate basic data support for subsequent monitoring and modeling. The beneficial effect of this step is that it can reflect the operating environment and initial performance parameters of the system in real time, laying a solid foundation for data fusion and state evaluation. By detecting the temperature difference of the operating environment data, the impact of external environmental changes on system performance is effectively captured, and reliable input data is provided for subsequent refrigerant pressure growth estimation. This analysis method based on temperature difference changes can reveal potential thermodynamic unevenness problems during system operation, which helps to improve the accuracy and reliability of system performance analysis. On this basis, the prediction of refrigerant pressure growth can detect the abnormal pressure problems in the system in advance, and effectively avoid equipment wear or system failure caused by pressure fluctuations. This prediction method can not only optimize the operating conditions, but also provide a scientific basis for reducing energy consumption and extending equipment life. The pipeline stress growth calculation is carried out by combining the refrigerant pressure data, and the real-time monitoring and analysis of stress changes help identify hidden problems in the pipeline, thereby reducing the risk of pipeline rupture. Further abnormal state assessment can integrate multiple data sources to predict potential abnormal behaviors of the system in advance. This full-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 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 abnormal 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 for a heat pump system based on data fusion, which solves the problem of inaccurate abnormal state assessment of the heat pump system and inaccurate risk assessment of the heat pump system in a traditional online modeling method for a heat pump system based on data fusion, and improves the accuracy of abnormal state assessment of the heat pump system and the accuracy of risk assessment of the heat pump system. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic flow chart of the steps of an online modeling method for a heat pump system based on data fusion;

[0074] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

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

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

[0077] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0078] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0079] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" 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 the operation log data of the heat pump system; collect the operation environment of the heat pump system according to the operation log data of the heat pump system to obtain the operation environment data of the heat pump system; perform the initial state performance analysis of the heat pump system according to the operation log data of the heat pump system to obtain the initial state performance data of the heat pump system;

[0082] Step S2: performing a temperature difference detection of 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;

[0083] Step S3: Calculate 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; evaluate 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: Acquire the design data of the heat pump system; construct a heat pump system anomaly detection model based on the heat pump system design data and the abnormal state data of the heat pump system to obtain the heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain the 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 the heat pump system based on data fusion includes the following steps:

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

[0087] In the embodiment of the present invention, all parameter information related to the operation is collected through the operation log data of the heat pump system, including key performance indicators such as system startup and shutdown time, refrigerant flow, temperature, pressure, etc. This data is used to monitor the operating environment parameters through sensors and automated data acquisition equipment, and analyze changes in temperature, humidity, air pressure, etc., so as to obtain the operating environment data of the heat pump system. Secondly, based on the operation log data, the initial state performance analysis is performed. The specific operation is to compare the startup conditions and operating parameters of the equipment, determine the normal working range of the system, and analyze the initial state performance data of the system based on the historical operation records of the equipment and the parameter changes.

[0088] Step S2: performing a temperature difference detection of 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;

[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. Use an ambient temperature sensor and a high-precision data acquisition system for real-time monitoring, and record the temperature difference data of each time period to calculate and determine whether there is a temperature difference abnormality. 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 the data of the refrigerant pressure growth of the heat pump system.

[0090] Step S3: Calculate 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; evaluate 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 the refrigerant pressure growth data, the pipeline stress calculation is performed based on the growth information of the refrigerant pressure of the heat pump system. The specific operation is to use the finite element analysis method to model the pipeline of the heat pump system and simulate the stress response of the pipeline under different pressure conditions. Through a detailed analysis of factors such as pipeline material, size, and working pressure, data on the stress changes of the pipeline during operation are obtained. Combined with these stress data, an abnormal state assessment is performed to analyze whether the pipeline has problems such as excessive stress and deformation. This process combines data analysis with physical modeling to identify potential risks that lead to system failure or performance degradation.

[0092] Step S4: Acquire the design data of the heat pump system; construct a heat pump system anomaly detection model based on the heat pump system design data and the abnormal state data of the heat pump system to obtain the heat pump system anomaly detection model; perform a heat pump system risk assessment based on the heat pump system anomaly detection model to obtain the 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 structural layout of the system, 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 design data of the system with the abnormal state data of the heat pump system. This model identifies the abnormal behavior of the heat pump system by learning known abnormal patterns and combining real-time operation 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 operation data and the design parameters to promptly discover potential problems. On this basis, a risk assessment of the heat pump system is performed, various risk indicators are evaluated, and the evaluation results are uploaded to the cloud platform. The cloud platform uses big data processing technology and real-time monitoring functions to comprehensively analyze the system operation status and generate early warning information.

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

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

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

[0097] Step S13: analyzing the initial state of the heat pump system according to the operation log data of the heat pump system to obtain the initial state data of the heat pump system;

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

[0099] In an embodiment of the present invention, obtaining the operation log data of the heat pump system is achieved through a high-frequency data acquisition device. 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 obtains the heat pump system operation log data to collect the heat pump system operating 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, the external environmental impact of the heat pump system is fully understood to form a comprehensive operating environment data set. This data set contains information such as temperature fluctuations, humidity changes, and air pressure changes in the environment where the heat pump system is located. Based on the acquired heat pump system operation log data, the initial state of the heat pump system is analyzed in detail. The initial state analysis is carried out by comprehensively monitoring and collecting data on the equipment during the first operation cycle after normal startup. The system determines whether its current operation is within the parameter range of the initial design by comparing historical data with the operating state parameters of the equipment. The analysis content includes key information such as equipment startup time, initial refrigerant pressure, startup load, system temperature changes, etc., to ensure that there are no abnormal phenomena when the equipment starts. After data collection, the data is processed using statistical analysis methods to generate initial state data. Based on the initial state data of the heat pump system, the initial state performance analysis is carried out, mainly including long-term and short-term performance evaluation of the operating performance of the equipment after startup. This step is based on data correction based on the operating parameters collected from the equipment, and data that does not meet the conventional fluctuation range is cleaned. Then, by comparing with the design parameters of the heat pump system, it is judged whether the initial performance meets the design requirements. Focus on checking the performance of key indicators such as energy efficiency, temperature fluctuation range, and refrigerant pressure stability in the initial stage. The tools used in the analysis include performance testing software and data mining algorithms, which can quickly extract useful information from massive amounts of data and analyze its trends. Through multi-dimensional performance analysis, the overall performance data of the heat pump system at the initial startup was obtained.

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

[0101] Step S21: performing a temperature difference detection of 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 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 the 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 growth based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure growth 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 of 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 evaporators, condensers, and environmental air inlets and outlets, 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 in 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 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 the 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 is in 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 operation overload data of the heat pump system 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 the actual test data with the theoretical model, the wear aggravation prediction is performed through the cumulative wear model. After the operation overload data and the equipment performance data are merged, the rate of aggravated wear is analyzed using statistical methods, and future changes in system wear are estimated. Through this analysis, the wear aggravation data of the heat pump system can be generated.

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

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

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

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

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

[0118] Step S224: performing an overload estimation of the compressor of the heat pump system based on the initial state performance data of the heat pump system according to the over-limit data of the operating environment temperature difference, and obtaining the over-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 the embodiment of the present invention, the peak period of operation of the heat pump system is collected according to the operation log data of the heat pump system, and various operation parameters of the heat pump system, such as refrigerant pressure, flow, temperature, system load, etc., are obtained in real time through the data acquisition unit. By analyzing the time series of the historical operation log data, the maximum load situation in each period is identified, that is, the peak period of system operation. In order to ensure that the peak period is accurately captured, a peak detection algorithm (such as an algorithm based on local extreme values) is used to extract load fluctuations and extreme points in the data, so as to determine the time when the operation peak occurs. In this process, the log data will be stored in the database and marked by a timestamp for subsequent data analysis. The obtained peak period data of the heat pump system operation provides the peak data of the system load in different time periods. Based on the peak period data of the heat pump system operation obtained in step S221, the heat overload state analysis of the heat pump system is performed, and the overload situation of the system in the peak period is analyzed by comparing the load data of the peak period of operation with the standard design load data. In the specific operation, a reasonable load threshold is set and an overload determination algorithm is used to determine whether the system exceeds the normal working load range. The algorithms used include load statistical analysis and data smoothing to eliminate the impact of short-term fluctuations on the judgment of overload status. Furthermore, combined with key indicators such as temperature and pressure, by analyzing the working status of the equipment under peak load, it is evaluated whether the heat pump system is in a thermal overload state. If the load is continuously higher than the set threshold and accompanied by abnormal temperature or pressure fluctuations, it is determined to be a thermal overload state, and the thermal overload data is recorded. According to the temperature difference data of the heat pump system operating environment, the temperature difference of the heat pump system operating environment is calculated. By collecting the ambient temperature data in real time and comparing it with the internal temperature data of the system, it is analyzed whether the ambient temperature difference exceeds the set safety range, and the temperature data of different locations (such as inlet and outlet temperatures, outdoor ambient temperature, etc.) are input into the calculation system, and compared with the preset temperature difference limit value. If the ambient temperature difference exceeds the set value, this data is recorded as the over-limit data. During the over-limit calculation process, the temperature difference will be combined with the actual operation data through a mathematical model to obtain the specific value and duration of the over-limit. In order to improve the calculation accuracy, a comprehensive analysis is performed in combination with environmental change factors (such as wind speed, humidity, etc.) to ensure that the time and amplitude of temperature difference abnormalities are accurately captured in a dynamic environment. The output of this process is the operating environment temperature difference exceeding limit data. Based on the operating environment temperature difference exceeding limit data obtained in step S223, the excessive load of the heat pump system compressor is estimated, and the impact of the external temperature difference exceeding limit on the compressor workload is analyzed based on the design parameters and operating status data of the heat pump system. The temperature difference exceeding limit causes the compressor to start and stop frequently or operate under excessive load, so it is necessary to monitor and analyze the load data of the compressor in real time. By real-time recording of key electrical parameters such as compressor current and voltage, combined with temperature difference data, the load estimation model is used to calculate the load change trend of the compressor.When the ambient temperature difference is found to be abnormal, the changes in the system load and the working state of the compressor are analyzed to predict whether the compressor is in an overload state. The estimation process takes into account the short-term and long-term effects of the temperature difference on the compressor, evaluates whether its load exceeds the bearing capacity of the equipment, generates compressor operation overload data, and performs heat pump system operation overload analysis based on the compressor operation overload data obtained in step S224 and the heat pump system thermal overload data. Combined with the compressor load overload data and thermal overload state data, a multi-dimensional analysis is performed. The compressor load is compared with the overall load of the system to evaluate its overload risk to the entire heat pump system. During the data processing process, by setting a reasonable load ratio and operating tolerance, it is analyzed whether there is an associated over-limit situation between the compressor load and the system load. This analysis process combines the load model of the heat pump system with the equipment performance model to calculate the load state of different equipment. In this process, the type, duration and failure risk of the overload are recorded. This analysis helps determine the overall overload condition of the heat pump system and provides data support for subsequent decisions such as equipment maintenance and early warning to obtain the heat pump system operation overload data.

[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 period data of the heat pump system to obtain the peak operation time data of the heat pump system;

[0123] Based on the peak operation 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 peak operation time data of the heat pump system and the overheating data of the expansion valve of the heat pump system to obtain refrigerant dynamic flow anomaly data;

[0126] Based on the abnormal data of refrigerant dynamic flow, the heat distribution heterogeneity of the heat pump system is estimated to obtain the heat distribution heterogeneity data of the heat pump system;

[0127] According to the heat distribution heterogeneity data of the heat pump system and the abnormal dynamic flow data of the refrigerant, the local overheating analysis of the heat pump system is carried out to obtain the local overheating data of the heat pump system;

[0128] The heat overload state of the heat pump system is analyzed by using the heat accumulation effect data of the heat pump system compressor and the local overheating data of the heat pump system and the initial state performance data of the heat pump system to obtain the heat overload data of the heat pump system.

[0129] In the embodiment of the present invention, according to the peak period data of the heat pump system, the peak period of the system operation load is identified by performing timestamp analysis on each peak period. The data of these periods are summarized, and the operation time of the heat pump system under the peak load is calculated in units of time length. In the specific operation, an algorithm based on a time window is used to obtain the duration of each peak period. 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 peak operation time data of the heat pump system. Based on the peak operation time data of the heat pump system, the heat accumulation effect analysis of the heat pump system is further performed. In this step, it is necessary to track the temperature change during the peak operation period in combination with the heat flow model, the duty cycle model and the operating parameters (such as pressure, temperature, etc.) designed by the heat pump system. On the basis of each peak operation time, the heat accumulation of each part of the heat pump system (such as the 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 by heat flux density and time integral. Through the accumulated thermal effect data, the total amount of heat accumulated in each part of the heat pump system under peak load is evaluated, and the heat accumulation effect data of the heat pump system is further obtained. According to the heat accumulation effect data of the heat pump system, the overheating detection of the expansion valve of the heat pump system is carried out, and the heat 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 during the peak operation 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 excessive temperature inside the expansion valve. Therefore, by calculating the temperature change and heat flow density in the expansion valve area, it is judged whether the maximum operating temperature of the expansion valve design is exceeded. Using the method of temperature monitoring and thermal effect modeling, the working state of the expansion valve is compared with the heat load, so as to determine whether the expansion valve is overheated and obtain the overheating data of the expansion valve of the heat pump system. Combined with the peak operation time data of the heat pump system and the overheating data of the expansion valve, the dynamic flow anomaly of the refrigerant is detected, and the flow of the refrigerant between the various components in the system is analyzed, especially the flow of key nodes such as the expansion valve, evaporator, and compressor. Real-time flow rate, pressure and temperature data are obtained through sensors and compared based on the standard flow characteristics of the system. If the actual flow rate is significantly different from the expected flow rate, or the flow is interrupted or unstable when the expansion valve is overheated, it is considered that the refrigerant has dynamic flow anomaly. Flow analysis and real-time data calibration methods are used for monitoring, and the refrigerant is detected to see if there is flow anomaly based on the temperature difference between the inside and outside of the system and the overheating data of the expansion valve. The test results will form refrigerant dynamic flow anomaly data, based on which the heat distribution heterogeneity of the heat pump system is estimated.In this step, the flow state, pressure, temperature and other information of the refrigerant are collected, and the distribution of heat between the various components is calculated in combination with the flow anomaly data. By analyzing the heat transfer and heat flux density of each area of ​​the heat pump system, it is evaluated whether the system has uneven heat distribution. Using the thermodynamic model, the heat load of each part is calculated to determine whether the heat is evenly distributed between different components. If there is a large heat accumulation or uneven heat distribution in some areas, there is a problem of heterogeneity in heat distribution. Through this analysis, the heat distribution heterogeneity data of the heat pump system is obtained, and the local overheating analysis of the heat pump system is carried out by combining the heat distribution heterogeneity data of the heat pump system with the dynamic flow anomaly data of the refrigerant. By combining the heat distribution data with the refrigerant flow anomaly data, the area where local overheating occurs in the system is analyzed. Local overheating usually occurs in places where heat accumulation is more concentrated or flow is restricted, such as evaporators, expansion valves, etc. According to the real-time data of flow and temperature, the thermodynamic model is used for calculation to find out the overheated parts and evaluate the severity and impact of local overheating. Combined with the historical operation data and failure cases of the heat pump system, the probability of occurrence of local overheating and its impact are further verified to obtain the local overheating data of the heat pump system. Combined with the heat accumulation effect data of the heat pump system compressor and the local overheating data of the heat pump system, the initial state performance data of the heat pump system is analyzed for thermal overload status. By analyzing the thermal load of the system and combining the heat accumulation of the equipment under high load conditions, an assessment is made as to whether the system is overloaded. In this step, the thermal overload analysis algorithm is used to calculate the load of each part of the system to assess the risk of overall thermal overload of the system. If the compressor, expansion valve and other equipment in the heat pump system are overloaded or locally overheated, it is considered that the system is at risk of thermal overload and the thermal overload data of the heat pump system is obtained.

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

[0131] According to the temperature difference exceeding the limit data of the operating environment, the heat acquisition demand growth of the heat pump system is estimated to obtain the heat acquisition demand growth data of the heat pump system;

[0132] Based on the heat acquisition demand growth data of the heat pump system, the compression ratio growth of the heat pump system is calculated to obtain the compression ratio growth data of the heat pump system;

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

[0134] The heat pump system compressor power consumption growth is estimated based on the heat pump system compressor pressure growth data to obtain the heat pump system compressor power consumption growth data;

[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, according to the operating environment temperature difference exceeding limit data, by calculating the heat change required by the system under different environmental conditions, the heat acquisition demand of the heat pump system under the condition of exceeding the limit temperature difference is evaluated. Specifically, the temperature difference exceeding limit data is obtained by a temperature sensor, recording the change of the ambient temperature difference during operation, and analyzing the fluctuation of the ambient temperature in different time periods. According to the period of temperature difference exceeding limit, the heat transfer formula is used to dynamically estimate the heat acquisition demand of the heat pump system. Through the influence of multiple factors such as ambient temperature, flow rate, heat load and heat transfer efficiency, the heat acquisition demand growth value of the heat pump system under the current operating environment is obtained. These calculations combine real-time environmental data with historical operating data by data fusion, accurately predict future changes in heat demand, and obtain the heat acquisition demand growth data of the heat pump system. Based on the heat acquisition demand growth data of the heat pump system, the compression ratio growth calculation is further performed, and the compression ratio change of the compressor under different loads is estimated by using thermodynamic principles and compressor performance models. The compression ratio refers to the volume ratio of the gas before and after compression in the heat pump system, and its change is usually closely related to the change of heat demand. According to the heat acquisition demand growth data, the compression ratio that the compressor needs to increase under the condition of increased heat load is calculated. When calculating, it is necessary to combine the change in heat demand with factors such as the gas flow, temperature, and pressure of the compressor, and use fluid dynamics and thermodynamics equations to deduce and obtain the compression ratio growth data of the heat pump system. This data is used to evaluate the working state of the system under the condition of increasing heat load. The compression ratio growth data of the heat pump system is used to further calculate the pressure growth of the heat pump system compressor. The pressure of the compressor usually increases with the increase of the compression ratio. Therefore, it is necessary to infer the pressure change based on the change of the compression ratio. In specific operations, the pressure change of the heat pump system after increasing the compression ratio is calculated by using the relationship between the flow, density, temperature and compression ratio of the compressor, and using the ideal gas state equation or the compressor characteristic curve. During the calculation process, it is necessary to obtain the temperature, pressure, flow and other data of the compressor inlet and outlet, and use these data to infer the working pressure inside the compressor. When the compression ratio is increased, calculate how the pressure at the compressor outlet increases accordingly, and obtain the pressure growth data of the heat pump system compressor. These data can effectively reflect the changing trend of the compressor pressure of the system under the condition of increased load. According to the pressure growth data of the heat pump system compressor, the power consumption growth of the heat pump system compressor is estimated. The power consumption is positively correlated with the pressure and compression ratio of the compressor, so the power consumption growth is inferred by the change of pressure. Specifically, by analyzing the working principle and energy efficiency characteristics of the compressor, the power formula is used to calculate the additional energy required by the compressor during the supercharging process. The change in power is determined by factors such as flow, pressure difference, compression ratio and efficiency. Based on the pressure increase, the energy efficiency ratio model (COP) and thermodynamic calculation model are used to accurately calculate the compressor power consumption and obtain the increase in compressor power consumption under the current load change.This calculation is derived through the real-time collected system pressure data and equipment efficiency parameters to obtain the power consumption growth data of the heat pump system compressor. Based on the power consumption growth data of the heat pump system compressor and the pressure growth data of the heat pump system compressor, the overload of the heat pump system compressor is estimated. The workload of the compressor is further analyzed by combining the relationship between power consumption growth and pressure growth. In the system, when the compressor is overloaded, it will show a significant increase in temperature, pressure and power consumption. It is necessary to evaluate whether the workload of the compressor exceeds its rated load range based on the real-time change data of power consumption and pressure. The load calculation formula is combined with the working parameters of the compressor to calculate whether it will cause overheating or failure due to overload operation. Through system monitoring data such as compressor current, power, pressure, temperature, etc., it is further evaluated whether the compressor is overloaded. If the power consumption and pressure changes exceed the normal operating range, the system will issue a warning signal to identify the risk of excessive compressor operation load and obtain the compressor overload data.

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

[0138] Step S241: Predicting the change in clearance of valve components of the heat pump system according to the wear aggravation data of the heat pump system, and obtaining the change in clearance of valve components of the heat pump system;

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

[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 the heat pump system refrigerant throttling effect attenuation data;

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

[0143] Step S246: The refrigerant pressure increase is estimated 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 the embodiment of the present invention, the wear of the valve components is evaluated according to the wear aggravation data of the heat pump system. The change of the clearance of the valve components is a common phenomenon in the process of wear aggravation. Therefore, it is necessary to predict the change of the clearance of the valve components by the wear indication signal in the real-time monitoring data. In the specific implementation, the parameters such as the pressure, flow rate, temperature and working time of the fluid in the valve are used to analyze the degree of wear of the valve components, and the change of the valve clearance is estimated by using the fluid dynamics model combined with the historical data of wear aggravation. The friction of the fluid on the valve surface, the influence of temperature change on the metal components, and the loss of valve sealing due to continuous operation are taken into account during the calculation, so as to predict the change trend of the clearance of the valve components and obtain the clearance change data of the valve components of the heat pump system. According to the wear aggravation data of the heat pump system, the deformation analysis of the transmission pipeline of the heat pump system is carried out. The deformation of the pipeline is usually caused by factors such as temperature change, pressure fluctuation, fluid flow rate and fatigue of the pipeline material during long-term operation. In the implementation process, the deformation of the pipeline is quantitatively analyzed by using the structural mechanics method by collecting the stress, temperature and pressure data of the pipeline and combining the physical properties of the material, such as elastic modulus and thermal expansion coefficient. Finite element analysis (FEA) is used to perform stress-strain analysis on the pipeline to simulate the deformation of the pipeline under different working conditions. By comparing the historical operation data with the current real-time data, the deformation of the pipeline under increased wear is predicted, and the deformation data of the heat pump system transmission pipeline is obtained. Combined with the deformation data of the heat pump system transmission pipeline and the clearance change data of the valve components, the fluid resistance growth calculation is performed. Pipeline deformation and valve clearance change both directly affect the fluid flow resistance. Especially after long-term operation, the deformation of the pipeline and the clearance change of the valve will cause the change of the fluid flow path, thereby increasing the flow resistance. In order to calculate the fluid resistance growth, it is necessary to analyze the impact of the change of the internal cross-section of the pipeline on the fluid flow based on the pipeline deformation data. For the valve clearance change data, it is necessary to calculate the flow area change of the valve channel to evaluate the pressure loss of the fluid flow. By combining fluid mechanics formulas such as the Darcy-Weisbach equation and the Bronco equation, the fluid resistance growth under the combined action of the above factors is calculated, and the fluid resistance growth data of the heat pump system is obtained. The attenuation analysis of the refrigerant throttling effect is performed based on the fluid resistance growth data of the heat pump system. The main function of the refrigerant throttling device (such as the expansion valve) is to adjust the temperature and pressure in the system by controlling the flow rate. When the fluid resistance increases, the throttling effect will decay, thus affecting the cooling efficiency of the system. In the specific implementation, the performance of the throttling device is simulated using a thermodynamic model in combination with the changes in flow and pressure caused by the increase in fluid resistance, and the change in the throttling effect of the refrigerant when the fluid resistance increases is evaluated. Furthermore, based on the thermodynamic properties of the refrigerant and the design parameters of the throttling device, the degree of attenuation of the throttling effect is calculated, and the attenuation data of the throttling effect of the refrigerant in the heat pump system is obtained. Based on the attenuation data of the throttling effect of the refrigerant in the heat pump system, the retention condition of the refrigerant on the high-pressure side is estimated.In the heat pump system, the attenuation of the efficiency of the throttling device will cause the refrigerant to flow poorly, resulting in retention on the high-pressure side. The retention phenomenon will cause the heat transfer efficiency of the refrigerant between the compressor and the condenser to decrease, affecting the overall performance of the system. During the implementation process, the degree of poor refrigerant flow is evaluated based on the attenuation data of the refrigerant throttling effect, and the retention status of the refrigerant on the high-pressure side is calculated in combination with the changes in pressure and temperature in the system. The refrigerant flow process is simulated by a fluid dynamics model to determine the degree of poor flow and the probability of retention, and then the data on the retention status of the refrigerant on the high-pressure side is obtained. The refrigerant pressure growth is estimated by combining the refrigerant high-pressure side retention status data and the refrigerant throttling effect attenuation data. When the retention phenomenon occurs, the pressure of the refrigerant on the high-pressure side will gradually increase, affecting the stable operation of the system. During implementation, the pressure change is calculated using a fluid dynamics model by combining the refrigerant high-pressure side retention status data with the throttling effect attenuation data. According to the changes in the refrigerant flow resistance, condensation pressure and evaporation pressure, the refrigerant pressure growth trend under the condition of retention is calculated, and the refrigerant pressure growth data of the heat pump system is obtained.

[0145] Preferably, step S3 comprises 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 the heat pump system rupture probability data;

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

[0149] Step S34: evaluating the abnormal state of the heat pump system according to 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 calculation is performed based on the refrigerant pressure growth data of the heat pump system. The increase in refrigerant pressure will generate additional stress inside 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 effect 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 integral 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 the 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 the 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 by 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 the refrigerant leakage of the heat pump system according to the rupture probability data of the heat pump system to obtain the refrigerant leakage data of the heat pump system;

[0156] In an embodiment of the present invention, a 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 fluctuations, refrigerant flow rate, etc.) are calculated. Through refrigerant leakage simulation, the refrigerant leakage data of the heat pump system is obtained.

[0157] Step S34: evaluating the abnormal state of the heat pump system according to 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.

[0158] In an embodiment of the present invention, the heat pump system abnormal state assessment is performed by combining the refrigerant leakage data of the heat pump system and the rupture probability data of the heat pump system. Based on the analysis of refrigerant leakage and rupture probability, the system needs to conduct a comprehensive assessment of the overall abnormal state. During implementation, the refrigerant leakage data is used to identify the existing leakage source and analyze the impact of the leakage point on the entire system. Next, the rupture probability data is combined with the leakage risk, and a multi-dimensional system model is used to evaluate whether the system is in a dangerous state. Considering factors such as reduced system efficiency, equipment damage or environmental pollution caused by refrigerant leakage, the system operation status is dynamically detected using real-time monitoring data (such as pressure, flow, temperature changes, etc.) to determine whether there is an abnormal state and obtain the abnormal state data of the heat pump system.

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

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

[0161] Step S342: performing a thermodynamic balance decay analysis based on the refrigerant reduction data of the heat pump system to obtain thermodynamic balance decay data of the heat pump system;

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

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

[0164] Step S345: Based on the heat pump system energy efficiency attenuation data and the heat exchange efficiency attenuation data of the heat pump system, an abnormal state evaluation of the heat pump system is performed to obtain abnormal state data of the heat pump system.

[0165] In the embodiment of the present invention, the refrigerant leakage of the heat pump system will lead to a reduction in the amount of refrigerant, affecting the cooling and heating effects of the system. According to the amount of refrigerant leakage, the refrigerant pressure, flow rate and temperature changes in the system are monitored in real time by measuring equipment (such as pressure sensors, flow meters, etc.), and the refrigerant reduction is calculated. According to the size of the leakage point, the leakage frequency, the working pressure and other factors, the mass conservation method and the fluid mechanics model are used to estimate the refrigerant reduction. Combined with the refrigerant circulation system of the heat pump system, the valve switch state, etc., the specific amount of refrigerant reduction when the leakage occurs is accurately calculated through the data fusion method. Further, depending on the different leakage conditions, the rate of refrigerant reduction is calculated to obtain the refrigerant reduction data of the heat pump system. The reduction of refrigerant will cause the thermal balance of the heat pump system to decay, thereby affecting the working efficiency of the system. In this step, combined with the refrigerant reduction data obtained in the previous step, the thermodynamic balance of the heat pump system is analyzed using thermodynamic equations. During the operation of the heat pump system, the thermodynamic changes of the refrigerant (such as evaporation, condensation and other processes) must maintain heat balance. In the case of refrigerant reduction, the heat transfer efficiency of evaporation and condensation of the system will change, thereby causing thermal decay. By establishing a mathematical model of the effect of changes in the amount of refrigerant on heat transfer, the heat loss inside the system is calculated. Combined with sensor data, the temperature and pressure changes in the system are monitored in real time, the thermodynamic balance state of the heat pump system is evaluated, and the thermodynamic balance attenuation data of the heat pump system is obtained. The heat exchange efficiency of the heat pump system is directly affected by the loss of thermodynamic balance and system components. In this step, the attenuation of the heat exchange efficiency of the heat pump system is estimated by combining the thermodynamic balance attenuation data and the rupture probability data, and the working efficiency of the heat exchanger is evaluated according to the design parameters and operating environment of the heat pump system. With the reduction of refrigerant and the increase of the risk of rupture, the heat exchange capacity of the system will gradually decrease. Through the thermodynamic analysis model, combined with factors such as temperature difference, fluid flow rate, and heat exchange area, the attenuation of the heat exchanger efficiency is estimated. Further, considering the reduction of the amount of refrigerant in the heat exchanger caused by pipeline rupture or refrigerant leakage, combined with the rupture probability data, the downward trend of the heat exchange efficiency is calculated to obtain the heat exchange efficiency attenuation data of the heat pump system. The attenuation of the heat exchange efficiency directly affects the energy efficiency performance of the heat pump system. Based on the heat exchange efficiency attenuation data obtained in the previous step, the energy efficiency attenuation of the heat pump system is predicted. The working model of the heat pump system is used, combined with the state of the refrigerant and the changes in heat transfer, to estimate the energy input required by the system when the heat exchange efficiency is reduced. As the efficiency decays, the heat pump system requires more energy to maintain the same output heat, resulting in reduced energy efficiency. By comparing the energy efficiency changes under different workloads, combined with factors such as system operating time and refrigerant volume changes, the system energy efficiency is predicted and calculated to obtain the energy efficiency attenuation data of the heat pump system. Combined with the energy efficiency attenuation data of the heat pump system and the heat exchange efficiency attenuation data, the abnormal state of the system is evaluated. In this step, through multi-dimensional data fusion analysis, it is judged whether the heat pump system has a significant decrease in operating efficiency based on the degree of energy efficiency decay.Secondly, combined with the attenuation data of the heat exchange efficiency, evaluate whether the system has reached the bottleneck of heat exchange capacity. Through the real-time monitoring data of the heat pump system, combined with the aforementioned attenuation data, use the abnormality detection algorithm to conduct a comprehensive analysis of the system's operating status. When the system's energy efficiency is lower than the set normal operating range, or the heat exchange efficiency drops significantly, it can be determined that the system is in an abnormal state. Through comprehensive evaluation, the abnormal state data of the heat pump system can be obtained.

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

[0167] Step S41: Acquire heat pump system design data; collect heat pump system structure data according to the heat pump system design data to obtain heat pump system structure data;

[0168] Step S42: constructing a heat pump system abnormality detection model based on the heat pump system structure data and the heat pump system abnormal state data to obtain a heat pump system abnormality 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 the 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 the embodiment of the present invention, the design data generally includes the main components, working parameters, component dimensions, material properties, etc. of the heat pump system. The system structure is collected according to the system design drawings, equipment manuals and relevant standards, and key physical parameters such as the design dimensions, efficiency, power, fluid type and other information of components such as condensers, evaporators, compressors, and expansion valves are collected. The design data is entered into the computer system by digital means, using the data acquisition module in the CAD drawings, BIM models or PLC control systems. The structural data of the heat pump system is obtained by processing the design data. After obtaining the structural data of the heat pump system, the abnormal state data of the heat pump system (including deviation data during the operation of the equipment, such as excessive compressor temperature, pressure fluctuations, etc.) is used to construct an abnormal detection model for the heat pump system. Based on the structural data of the heat pump system, the working model of each component is established, taking into account the working characteristics of each component and the type of fault that occurs. Then, the system is monitored using sensor data, operation logs and actual performance data of the equipment. Data mining and machine learning methods (such as support vector machines, random forests, decision trees, etc.) are used to construct an abnormal detection model based on historical fault data and real-time sensor data. The model can identify abnormal data that is inconsistent with the normal operating state, and evaluate the health status of the system in real time according to the actual operation of the heat pump system, so as to detect faults or performance degradation early. Based on the abnormal state data of the heat pump system, the aging trend of the heat pump system is estimated, and the operation data of the heat pump system over a long period of time is collected, including the abnormal conditions of the system (such as compressor overload operation, pipeline vibration, etc.) and its corresponding working environment (such as temperature, pressure, etc.). Through the analysis of historical failure modes, the aging prediction model of the heat pump system is established using statistical methods (such as regression analysis, time series analysis, etc.). The model analyzes the aging rate and loss trend of each component of the system according to the system usage time, load changes and the frequency of failures. Combined with the design data and operating conditions of the heat pump system, the aging trend data of the heat pump system is obtained. According to the aging trend data of the heat pump system, the risk assessment of the heat pump system is carried out. Based on the aging model of the system, the probability of failure of each component in a certain period of time in the future is evaluated. Combined with the equipment usage frequency, maintenance history and other data, the overall risk level of the system is calculated. During the risk assessment process, risk analysis methods (such as fault tree analysis FMEA or Monte Carlo simulation) are used to quantify the risk level of the system, taking into account factors such as failure modes, system capacity reduction, and refrigerant leakage. The assessment results include the risk level of each component, the health status of the entire system, and the expected failure time. The assessed heat pump system risk data will be uploaded to the cloud platform via the Internet or intranet connection for remote monitoring. The cloud platform will analyze the system's risk data in real time and automatically warn based on the preset risk threshold.

[0172] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for online modeling of a heat pump system based on data fusion, characterized in that: The following steps are involved: Step S1: Acquire the operation log data of the heat pump system; collect the operation environment of the heat pump system according to the operation log data of the heat pump system to obtain the operation environment data of the heat pump system; perform the initial state performance analysis of the heat pump system according to the operation log data of the heat pump system to obtain the initial state performance data of the heat pump system; Step S2: performing a temperature difference detection of 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; Step S3: Calculate 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; evaluate 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: Acquire heat pump system design data; construct a heat pump system abnormality detection model based on the heat pump system design data and the heat pump system abnormal state data to obtain a heat pump system abnormality detection model; The heat pump system risk assessment is performed based on the heat pump system anomaly detection model to obtain the heat pump system risk data, which is then uploaded 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 operating environment of the heat pump system according to the operating log data of the heat pump system to obtain the operating environment data of the heat pump system; Step S13: analyzing the initial state of the heat pump system according to the operation log data of the heat pump system to obtain the initial state data of the heat pump system; Step S14: performing initial state performance analysis of the heat pump system according to the initial state data of the heat pump system to obtain 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 S2 includes the following steps: Step S21: performing a temperature difference detection of 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 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 the 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 growth based on the heat pump system wear aggravation data to obtain the heat pump system refrigerant pressure growth data.

4. The online modeling method of heat pump system based on data fusion according to claim 3 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 operation log data of the heat pump system 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 the heat pump system thermal overload data; Step S223: performing over-limit calculation of the operating environment temperature difference of the heat pump system according to the operating environment temperature difference data of the heat pump system to obtain over-limit data of the operating environment temperature difference; Step S224: performing an overload estimation of the compressor of the heat pump system based on the initial state performance data of the heat pump system according to the over-limit data of the operating environment temperature difference, and obtaining the over-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.

5. The online modeling method of heat pump system based on data fusion according to claim 4 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 period data of the heat pump system to obtain the peak operation time data of the heat pump system; Based on the peak operation 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 peak operation time data of the heat pump system and the overheating data of the expansion valve of the heat pump system to obtain refrigerant dynamic flow anomaly data; Based on the abnormal data of refrigerant dynamic flow, the heat distribution heterogeneity of the heat pump system is estimated to obtain the heat distribution heterogeneity data of the heat pump system; According to the heat distribution heterogeneity data of the heat pump system and the abnormal dynamic flow data of the refrigerant, the local overheating analysis of the heat pump system is carried out to obtain the local overheating data of the heat pump system; The heat overload state of the heat pump system is analyzed by using the heat accumulation effect data of the heat pump system compressor and the local overheating data of the heat pump system and the initial state performance data of the heat pump system to obtain the heat overload data of the heat pump system.

6. The online modeling method of heat pump system based on data fusion according to claim 4 is characterized in that: Step S224 includes the following steps: According to the temperature difference exceeding the limit data of the operating environment, the heat acquisition demand growth of the heat pump system is estimated to obtain the heat acquisition demand growth data of the heat pump system; Based on the heat acquisition demand growth data of the heat pump system, the compression ratio growth of the heat pump system is calculated to obtain the compression ratio growth data of the heat pump system; Calculate the compressor pressure growth of the heat pump system according to the compression ratio growth data of the heat pump system to obtain the compressor pressure growth data of the heat pump system; The heat pump system compressor power consumption growth is estimated based on the heat pump system compressor pressure growth data to obtain the heat pump system compressor power consumption growth data; 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.

7. The online modeling method of heat pump system based on data fusion according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: Predicting the change in clearance of valve components of the heat pump system according to the wear aggravation data of the heat pump system, and obtaining the change in clearance of valve components of the heat pump system; Step S242: performing a deformation analysis of the transmission pipeline of the heat pump system according to the wear aggravation data of the heat pump system to obtain deformation data of the transmission pipeline of the heat pump system; 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 the refrigerant throttling effect attenuation data of the heat pump system; Step S245: estimating the retention status of the refrigerant high-pressure side of the heat pump system based on the refrigerant throttling effect attenuation data of the heat pump system, and obtaining the refrigerant high-pressure side retention status data; Step S246: The refrigerant pressure increase is estimated 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.

8. 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 the heat pump system rupture probability data; Step S33: Predicting the refrigerant leakage of the heat pump system according to the rupture probability data of the heat pump system to obtain the refrigerant leakage data of the heat pump system; Step S34: evaluating the abnormal state of the heat pump system according to 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.

9. The online modeling method of heat pump system based on data fusion according to claim 8 is characterized in that: Step S34 includes the following steps: Step S341: performing heat pump system refrigerant reduction calculation according to the refrigerant leakage of the heat pump system to obtain the refrigerant reduction data of the heat pump system; Step S342: performing a thermodynamic balance decay analysis based on the refrigerant reduction data of the heat pump system to obtain thermodynamic balance decay data of the heat pump system; Step S343: based on the heat pump system thermal balance decay data and the heat pump system rupture probability data, the heat pump system heat exchange efficiency decay data is estimated to obtain the heat pump system heat exchange efficiency decay data; Step S344: performing a heat pump system energy efficiency attenuation prediction according to the heat exchange efficiency attenuation data of the heat pump system to obtain the heat pump system energy efficiency attenuation data; Step S345: Based on the heat pump system energy efficiency attenuation data and the heat exchange efficiency attenuation data of the heat pump system, an abnormal state evaluation of the heat pump system is performed to obtain abnormal state data of the heat pump system.

10. 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; collect heat pump system structure data according to the heat pump system design data to obtain heat pump system structure data; Step S42: constructing a heat pump system abnormality detection model based on the heat pump system structure data and the heat pump system abnormal state data to obtain a heat pump system abnormality 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 the 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