A blockchain-based air energy heat pump monitoring and control method and system

Abstract

The present invention relates to the field of heat pump control technology, specifically a blockchain-based air-energy heat pump monitoring and control method and system, comprising the following steps: collecting the operating data of the air-energy heat pump and extracting the corresponding parameters, determining the key points of parameter changes through time series analysis, marking abnormal fluctuations, and generating operating data analysis results. The present invention accurately identifies the key change points of the operating parameters of the air-energy heat pump through time series analysis, marks abnormal fluctuations in real time, and effectively predicts potential equipment failures. The Bayesian network model is used to accurately simulate the fault propagation path and impact range, which significantly improves the accuracy and efficiency of fault diagnosis. The combination of real-time fault probability updates and blockchain technology realizes the automation of maintenance tasks and spare parts scheduling, significantly improving the response speed and maintenance efficiency. Automatically adjust operating parameters to quickly and accurately match and handle faults, ensuring that the equipment resumes normal operation in the shortest time.

Description

Technical Field

[0001] The present invention relates to the field of heat pump control technology, and in particular to a blockchain-based air energy heat pump monitoring and control method and system. Background Art

[0002] The field of heat pump control technology involves the operation and management of heat pump systems to improve efficiency, save energy and ensure continuous operation. Air-to-air heat pumps are energy conversion devices that can extract heat energy from one environment and transfer it to another. They are commonly used in water heaters, dryers, and air conditioners. The field includes temperature control, pressure control, flow control and other methods. By adjusting parameters, heat pump systems can operate efficiently under different environmental and load conditions.

[0003] Among them, the air source heat pump monitoring and control method is a heat pump control technology used to monitor and adjust the operating status of the air source heat pump to adapt to changes in the external environment and user needs. This method evaluates the efficiency and performance of the system by collecting working data of the air source heat pump, such as temperature, humidity, pressure and other parameters. Then, based on the data feedback, the working mode of the heat pump is automatically adjusted, such as adjusting the refrigerant flow or changing the operating speed of the compressor, to maintain the best energy efficiency ratio.

[0004] In the existing technology, the monitoring and control method of air energy heat pump mainly adjusts the equipment by monitoring basic parameters. This method is difficult to accurately predict and respond quickly in the early stage of a fault, which may cause processing delays and affect system efficiency and reliability. Fault diagnosis depends on surface parameters, making it difficult to fully evaluate the potential impact and propagation path of the fault. The low level of automation in fault information management and maintenance task scheduling may lead to long response time and low spare parts scheduling efficiency, thereby increasing maintenance costs and time, extending equipment maintenance cycles, and increasing operating costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and propose a blockchain-based air-energy heat pump monitoring and control method and system.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solution: a blockchain-based air energy heat pump monitoring and control method, comprising the following steps:

[0007] S1: Collect the operation data of the air energy heat pump and extract the corresponding parameters, determine the key points of parameter changes through time series analysis, identify abnormal fluctuations, and generate operation data analysis results;

[0008] S2: Based on the analysis results of the operation data, establish a correlation diagram of key components of the air energy heat pump, simulate the fault propagation path and impact range, and establish a Bayesian network model;

[0009] S3: Based on the Bayesian network model, the currently collected air-to-energy heat pump operation data is input, the changes in the operation parameters are compared, potential fault points are identified through the set thresholds, and real-time fault probability update results are generated;

[0010] S4: Based on the real-time fault probability update result, the fault information is synchronized to the blockchain network, the maintenance tasks and spare parts scheduling of the air energy heat pump are automatically assigned, and the fault response record is created;

[0011] S5: Based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, the operating parameters of the equipment are automatically adjusted, and the fault matching and processing results are obtained;

[0012] S6: Based on the fault matching and processing results, monitor the operating performance of the air-to-energy heat pump after recovery, compare it with the set standard, and generate the air-to-energy heat pump performance monitoring result.

[0013] The present invention has improvements in that the operation data analysis results include abnormal points, fluctuation frequencies and timestamps of parameter out-of-bounds of key parameters, the Bayesian network model includes the influence weights of components, interaction strengths and predicted fault transmission paths, the real-time fault probability update results include identification information of potential fault points, fault probability values ​​and warning levels of fault occurrence, the fault response records include the time of fault occurrence, processing steps, response time of maintenance personnel and spare parts usage information, the fault matching and processing results include automatic identification of fault types, successfully matched fault modes and parameters that need to be adjusted, and the air energy heat pump performance monitoring results include adjusted equipment operating efficiency, temperature stability evaluation and comparison data with preset performance indicators.

[0014] The present invention is improved in that the operation data of the air energy heat pump is collected, the temperature, pressure and current parameters are extracted, the key points of parameter changes are determined by time series analysis, the abnormal fluctuations in the operation data are marked, and the specific steps of generating the operation data analysis results are as follows:

[0015] S101: Based on all the operation records of the air-to-energy heat pump, key monitoring data points are selected, and the temperature, pressure, and current parameter data are sorted and preliminarily screened to obtain a time series data set;

[0016] S102: Based on the time series data set, identify mutation points and abnormal fluctuations in the data, mark key anomalies, and generate abnormal data information;

[0017] S103: Based on the abnormal data information, analyze the environmental conditions and potential factors of each marked data, extract key change points associated with the fault, and generate operation data analysis results.

[0018] The present invention has been improved in that, based on the analysis results of the operation data, a correlation diagram of key components of the air energy heat pump is established, and the specific steps of establishing the Bayesian network model are as follows by gradually adjusting the influence weights between components, simulating the fault propagation path and influence range:

[0019] S201: Based on the analysis results of the operation data, identify and list key components in the air-to-energy heat pump, and generate a component association list by evaluating the occurrence frequency of the components in the fault records;

[0020] S202: Based on the component association list, referring to the impact degree and frequency of the component in the failure mode, dynamically adjusting the weight of each component, and creating a component weight relationship diagram;

[0021] S203: Based on the component weight relationship diagram, a Bayesian network algorithm is applied to simulate the propagation effects under various fault scenarios, including the path and speed of the fault spreading from one component to adjacent components, and a Bayesian network model is established.

[0022] The present invention is improved in that the Bayesian network algorithm calculates the conditional probability according to the following formula to obtain the probability that component j will also fail when component i' fails: :

[0023] ;

[0024] Among them, W j is the weight of component j, A i' is the data encryption strength index of component i' in the blockchain, B j is the fault monitoring sensitivity of component j, C j is the maintenance response rating of part j, n is the total number of parts, and k is the part index.

[0025] The present invention is improved in that, based on the Bayesian network model, the currently collected air-energy heat pump operation data is input, the changes in the operation parameters are compared, the fluctuations of the current equipment state are monitored, potential fault points are identified through the set thresholds, and the specific steps of generating real-time fault probability update results are as follows:

[0026] S301: Based on the Bayesian network model, receiving the current operating data of the air energy heat pump, recording key operating parameters, analyzing the real-time changes of the parameters, and generating real-time parameter analysis results;

[0027] S302: Based on the instant parameter analysis result, compared with the preset normal operating range, using the set threshold to identify abnormal changes in the parameters, marking the changes as potential fault warnings, and generating warning identification results;

[0028] S303: Based on the early warning identification result, all marked potential fault points are analyzed, the current failure probability of the equipment is calculated, and a real-time failure probability update result is generated.

[0029] The present invention has the following improvements: based on the real-time fault probability update result, the fault information is synchronized to the blockchain network, the preset response rules are executed through the smart contract, the maintenance tasks and spare parts scheduling of the air energy heat pump are automatically allocated, and the problems and progress are fed back in real time during the fault handling process. The specific steps of creating a fault response record are as follows:

[0030] S401: Based on the real-time fault probability update result, the new fault data is uploaded to the blockchain to generate a data upload result;

[0031] S402: Based on the data upload result, trigger the smart contract on the blockchain, and the smart contract automatically schedules maintenance resources and spare parts according to the current fault data to generate a maintenance task scheduling result;

[0032] S403: Based on the maintenance task scheduling result, monitor and record the maintenance progress and problem feedback in real time, and create a fault response record.

[0033] The present invention is improved in that, based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, the operating parameters of the equipment are automatically adjusted to match the preset requirements of the fault response, and the specific steps of obtaining the fault matching and processing results are as follows:

[0034] S501: extracting fault features in the current record based on the fault response record, listing and classifying the features of each record, preparing to compare with a preset fault mode, and generating a fault feature extraction result;

[0035] S502: Based on the fault feature extraction result, matching the extracted fault feature with the defined fault mode, checking the matching degree, marking the matching fault mode, and generating a fault mode matching result;

[0036] S503: Based on the fault mode matching result, automatically adjust the operating parameters of the air energy heat pump to correspond to the matched fault mode, and obtain the fault matching and processing results.

[0037] The present invention is improved in that, based on the fault matching and processing results, the operating performance of the air energy heat pump after recovery is monitored, the energy efficiency and temperature control accuracy parameters are recorded, and compared with the set standards. The specific steps of generating the air energy heat pump performance monitoring results are as follows:

[0038] S601: based on the fault matching and processing results, restart the air energy heat pump, record the first batch of performance data after startup, and generate initial performance monitoring data;

[0039] S602: Based on the initial performance monitoring data, continuously track the energy efficiency and temperature control accuracy of the equipment during operation, regularly update the performance data, and generate continuous performance tracking results;

[0040] S603: Based on the continuous performance tracking results, compare the set performance standards and current operating data, evaluate the recovery status and maintenance effect of the equipment, and generate air energy heat pump performance monitoring results.

[0041] A blockchain-based air energy heat pump monitoring and control system, the system comprising:

[0042] The parameter analysis module conducts detailed analysis of parameters including temperature, pressure, and current based on the historical operating data of the air energy heat pump, identifies key points and abnormal fluctuations, and generates operating data analysis results;

[0043] The fault analysis module establishes a correlation diagram of key components of the air energy heat pump based on the analysis results of the operation data, uses a simulation method to refine the fault propagation path and impact range, and generates a Bayesian network model;

[0044] The real-time monitoring module monitors the currently collected air-energy heat pump operation data based on the Bayesian network model, identifies potential fault points by comparing changes and setting thresholds, and generates real-time fault probability update results;

[0045] The fault response module synchronizes the fault information to the blockchain network based on the real-time fault probability update result, automatically allocates maintenance tasks and spare parts scheduling using smart contracts, records the fault processing status in real time, and creates a fault response record;

[0046] Based on the fault response record, the performance evaluation module compares the fault characteristics of the air energy heat pump with the defined fault mode, automatically adjusts the operating parameters of the equipment, monitors the performance recovery of the equipment, compares it with the set standard, and generates the air energy heat pump performance monitoring result.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, the key change points of the operating parameters of the air-to-energy heat pump are accurately identified through time series analysis, abnormal fluctuations are marked in real time, and potential equipment failures are effectively predicted. The Bayesian network model is used to accurately simulate the fault propagation path and impact range, which significantly improves the accuracy and efficiency of fault diagnosis. The combination of real-time fault probability updates and blockchain technology realizes the automation of maintenance tasks and spare parts scheduling, significantly improving response speed and maintenance efficiency. Automatically adjust operating parameters to quickly and accurately match and handle faults, ensuring that the equipment resumes normal operation in the shortest time. Monitor the performance of the equipment after recovery to ensure that all maintenance operations meet the predetermined performance standards and maintain the stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a blockchain-based air energy heat pump monitoring and control method is proposed for the present invention.

[0050] Figure 2 This is a detailed flow chart of step S1 in the present invention.

[0051] Figure 3 This is a detailed flow chart of step S2 in the present invention.

[0052] Figure 4 This is a detailed flow chart of step S3 in the present invention.

[0053] Figure 5 This is a detailed flow chart of step S4 in the present invention.

[0054] Figure 6 This is a detailed flow chart of step S5 in the present invention.

[0055] Figure 7 This is a detailed flow chart of step S6 in the present invention.

[0056] Figure 8 A module diagram of an air energy heat pump monitoring and control system based on blockchain is proposed for the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0059] See also Figure 1 The present invention provides a technical solution: a blockchain-based air energy heat pump monitoring and control method, comprising the following steps:

[0060] S1: Collect the operation data of the air energy heat pump and extract the corresponding parameters, determine the key points of parameter changes through time series analysis, identify abnormal fluctuations, and generate operation data analysis results;

[0061] S2: Based on the analysis results of the operating data, establish the correlation diagram of the key components of the air-to-energy heat pump, simulate the fault propagation path and impact range, and establish a Bayesian network model;

[0062] S3: Based on the Bayesian network model, the currently collected air-to-energy heat pump operation data is input, the changes in the operation parameters are compared, potential fault points are identified through the set thresholds, and real-time fault probability update results are generated;

[0063] S4: Based on the real-time fault probability update results, the fault information is synchronized to the blockchain network, the maintenance tasks and spare parts scheduling of the air energy heat pump are automatically assigned, and the fault response record is created;

[0064] S5: Based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, the operating parameters of the equipment are automatically adjusted, and the fault matching and processing results are obtained;

[0065] S6: Based on the fault matching and processing results, monitor the operating performance of the air energy heat pump after recovery, compare it with the set standards, and generate the air energy heat pump performance monitoring results.

[0066] The operation data analysis results include abnormal points, fluctuation frequency and timestamps of parameter out-of-bounds of key parameters. The Bayesian network model includes the influence weights of components, interaction strength and predicted fault transmission paths. The real-time fault probability update results include the identification information of potential fault points, fault probability values ​​and warning levels of fault occurrence. The fault response records include the time of fault occurrence, processing steps, response time of maintenance personnel and spare parts usage information. The fault matching and processing results include automatic identification of fault types, successfully matched fault modes and parameters that need to be adjusted. The air energy heat pump performance monitoring results include the adjusted equipment operating efficiency, temperature stability evaluation and comparison data with preset performance indicators.

[0067] See also Figure 2 , collect the operating data of the air energy heat pump, extract the temperature, pressure and current parameters, determine the key points of parameter changes through time series analysis, identify abnormal fluctuations in the operating data, and generate the specific steps of operating data analysis results as follows:

[0068] S101: Based on all the operation records of the air-to-energy heat pump, select key monitoring data points, sort and preliminarily screen the temperature, pressure, and current parameter data, and obtain the specific process of the time series data set;

[0069] By sorting and preliminarily screening the temperature, pressure, and current parameters, we can filter out data anomalies such as temperature exceeding the set upper and lower limits (such as -10°C to 50°C) or pressure and current data deviating from the normal operating range. We select key monitoring data points, such as the average, maximum, and minimum values ​​per hour, to construct a time series data set. In this process, we calculate the daily coefficient of variation for each parameter. , to identify the volatility of the data, the calculation formula is:

[0070] ;

[0071] in, is the daily coefficient of variation, which indicates the percentage of intraday data fluctuation. σ is the standard deviation of daily data, which indicates the degree of dispersion of intraday data points relative to the average value. μ is the average value of daily data, which indicates the center point of all data points within the day. After data cleaning and formatting, a time series data set is formed. These data are automatically collected from the monitoring system of the air energy heat pump and transmitted to the analysis platform through the data interface for processing.

[0072] S102: Based on the time series data set, identify mutation points and abnormal fluctuations in the data, mark key anomalies, and generate abnormal data information. The specific process is as follows;

[0073] Using the time series data set, the sliding window method is applied to detect abnormal fluctuations and mutation points. The difference between each data point and the previous and next data points is calculated, and the Z-score method is used to identify outliers. The formula is:

[0074] ;

[0075] Where Z is the Z-score, which measures the degree of deviation of a single data point from the window mean. v is the value of the current data point. μ w is the average value within the sliding window. w is the standard deviation within the sliding window. The mutation point is defined as the point where the Z-score exceeds a threshold (e.g. |Z|>3). These points are marked to generate abnormal data information. The selection of these data points is automatically completed by the real-time monitoring system to ensure immediate response and recording.

[0076] S103: Based on the abnormal data information, the environmental conditions and potential factors of each marked data are analyzed, key change points associated with the fault are extracted, and the specific process of generating the operation data analysis results is as follows;

[0077] Based on the abnormal data information, each marked data point is analyzed in depth. Environmental conditions such as temperature fluctuations and pressure changes are considered to identify the potential factors behind these abnormal data. Using correlation analysis, the correlation between the abnormal points and the fault records is calculated:

[0078] ;

[0079] Among them, R is the correlation coefficient, which is used to measure the correlation between abnormal points and fault occurrence. i is the parameter value of the marked outlier point. i is with x i Related fault occurrence flag (0 or 1, 1 indicates fault, 0 indicates no fault). , are all x i and i This analysis helps extract key change points directly associated with faults and generates detailed operation data analysis results. The calculation of the correlation coefficient R involves all marked abnormal data points, and its value is calculated and updated in real time through the data analysis platform, providing data support for fault prevention and response.

[0080] See also Figure 3 Based on the analysis results of the operating data, the association diagram of the key components of the air-to-energy heat pump is established. By gradually adjusting the influence weights between components, the fault propagation path and impact range are simulated. The specific steps for establishing the Bayesian network model are as follows:

[0081] S201: Based on the operation data analysis results, identify and list the key components in the air energy heat pump, and generate a component association list by evaluating the frequency of occurrence of the components in the fault records. The specific process is as follows;

[0082] All key components in the air-to-energy heat pump system are identified through data mining technology. Then, the failure frequency of each component is statistically analyzed using the historical fault record database. The formula is as follows:

[0083] ;

[0084] Among them, F p is the component failure frequency, which indicates the proportion of component failures. N f is the number of fault records for this component, obtained through database query. N t is the total number of detections during the observation period, which is calculated cumulatively through system monitoring data. Based on these frequency data, an interaction diagram between components is constructed, using nodes in graph theory to represent components, and edge weights based on failure frequencies, thus forming a component association list. This list describes in detail the interaction strength of each component with other components in the system, providing basic data for subsequent weight adjustments.

[0085] S202: Based on the component association list, referring to the impact degree and frequency of the component in the failure mode, the weight of each component is dynamically adjusted, and the specific process of creating a component weight relationship diagram is as follows;

[0086] Starting from the component association list, the weight of each component is dynamically adjusted according to the impact and frequency of the component in the failure mode. The weight adjustment is based on the following formula to ensure that the weight reflects the latest trend of the actual failure data:

[0087] ;

[0088] Among them, W i' is the weight of the component. α1 and β1 are adjustment coefficients determined based on historical data analysis to balance the weight of failure frequency and component impact. f It is the impact factor of the component, which is based on the assessment of its functional importance in the system and is usually set by the maintenance team based on experience, thereby creating a component weight relationship diagram containing all key components and their interaction weights. The diagram shows in detail the dependencies and interaction strengths between different components.

[0089] S203: Based on the component weight relationship diagram, the Bayesian network algorithm is applied to simulate the propagation effects under various fault scenarios, including the path and speed of the fault spreading from one component to adjacent components. The specific process of establishing the Bayesian network model is as follows;

[0090] Using the obtained component weight relationship graph, the Bayesian network algorithm is used to simulate the propagation effects under various fault scenarios. The algorithm first defines that each node in the network represents a component, the edges between nodes represent the dependency relationship between components, and the weight of the edge represents the possibility of fault propagation.

[0091] The Bayesian network algorithm calculates the conditional probability according to the following formula to obtain the probability that component j will also fail when component i' fails: :

[0092] ;

[0093] Among them, W j is the weight of component j, reflecting the importance of the component in the entire system or the degree of impact of its failure on the system. The weight is obtained by evaluating the operational criticality and historical failure data of the component. i' It is the data encryption strength index of component i' in the blockchain. This index reflects the confidentiality and integrity of data in the blockchain and is an important parameter for ensuring data security through blockchain technology. j is the fault monitoring sensitivity of component j, indicating the reaction speed and sensitivity of the monitoring system of the component to the fault. The sensitivity is set according to the technical specifications and historical performance records of the monitoring equipment. j is the maintenance response rating of component j, which is evaluated based on the maintenance history and response time of the component, involving feedback from the maintenance team and analysis of historical maintenance data, n is the total number of components, and k is the component index;

[0094] The calculation process is as follows:

[0095] First, historical failure data and operation records of each component are collected.

[0096] Assess criticality: Assess each component's impact and frequency of failure.

[0097] Weight allocation: Based on the evaluation results, a weight W is assigned to each component. The higher the weight, the greater the impact of the component on system stability.

[0098] Calculate the encryption strength A:

[0099] Blockchain connection: Cooperate with blockchain technology providers to obtain the encryption standard of each component data. Encryption standard application: According to the sensitivity and security requirements of the component, an encryption strength index A is set for each component. Highly sensitive components will have higher encryption standards.

[0100] Set the fault monitoring sensitivity B:

[0101] Monitoring Device Analysis: Analyze the performance of the monitoring devices to which the component is connected, such as sensor accuracy and response time.

[0102] Sensitivity assessment: Based on equipment performance, a fault monitoring sensitivity index B is set for each component. Components with high sensitivity can respond to potential faults more quickly.

[0103] Assessment Maintenance Response Rating C:

[0104] Maintenance History Analysis: Review the maintenance history of each component, including maintenance response time and success rate. Rating Setting: Based on historical performance, each component is assigned a response rating of C, which reflects the quality and speed of the component's performance during the maintenance process.

[0105] Total weight calculation: Calculate the weight of all components multiplied by the sum of their corresponding A, B, and C values ​​as the denominator. Single component impact calculation: Calculate W×A×B×C for each component as the numerator.

[0106] Probability update: Update the conditional probability of fault propagation using the above numerator and denominator .

[0107] The improved Bayesian network not only improves the accuracy of fault prediction through this calculation method, but also enhances the ability to respond to dynamic changes in system faults. Through real-time updates and accurate risk assessment, the model can help maintenance teams optimize resource allocation, reduce unnecessary maintenance expenses, and improve system reliability and safety. Ultimately, this approach can significantly improve the monitoring and control efficiency of air-to-energy heat pumps, especially in an environment that integrates blockchain technology to ensure data transparency and immutability.

[0108] See also Figure 4 ,Based on the Bayesian network model, the currently collected air-energy heat pump operation data is input, the changes in the operating parameters are compared, the fluctuations of the current equipment status are monitored, potential fault points are identified through the set thresholds, and the specific steps for generating real-time fault probability update results are as follows:

[0109] S301: Based on the Bayesian network model, the current operating data of the air energy heat pump is received, key operating parameters are recorded, and the instant changes of the parameters are analyzed to generate the specific process of instant parameter analysis results;

[0110] Receive real-time data from the air-to-energy heat pump monitoring system, covering key parameters such as temperature, pressure and flow rate. These parameters are recorded by sensors every five minutes and transmitted to the data processing center in real time. The processing center uses threshold analysis methods to conduct instant checks on the received data, such as whether the temperature and pressure are within the normal operating range. If the data shows abnormal fluctuations, the system marks these data points as objects that need further analysis and updates the monitoring dashboard in real time so that the operator can see the latest operating status.

[0111] For parameter normalization, follow the formula:

[0112] ;

[0113] Among them, x represents the parameter value monitored in real time, x min and x max They represent the preset minimum and maximum normal values ​​of the parameter respectively, and S(x) represents the standardized value of the parameter.

[0114] S302: Based on the instant parameter analysis results, compared with the preset normal operating range, using the set threshold to identify abnormal changes in the parameters, marking the changes as potential fault warnings, the specific process of generating warning identification results is as follows;

[0115] The analysis platform performs anomaly detection on each parameter based on the real-time parameter analysis results. If the parameter value exceeds the preset normal operating range, the system automatically calculates the deviation of the parameter from the threshold and immediately triggers the early warning mechanism. The process includes recording the time when the deviation occurred, the parameter value and its specific deviation from the threshold to generate a detailed early warning identification report. This information is used to quickly locate possible problem areas and provide real-time data support for the maintenance team.

[0116] For the calculation of abnormal status, follow the formula:

[0117] ;

[0118] Where x represents the parameter value, μ1 represents the normal operation threshold of the parameter, σ1 represents the maximum allowed deviation, and D(x) represents the anomaly detection result.

[0119] S303: Based on the early warning identification result, the specific process of analyzing all marked potential fault points, calculating the current fault probability of the equipment, and generating a real-time fault probability update result is as follows;

[0120] The data of all marked potential failure points are combined to calculate the overall failure probability of the equipment. This calculation considers the frequency of occurrence and severity of each failure point, and these failure points are weighted and summed to obtain the total failure probability of the equipment. The data is updated in real time in the system and used to adjust the maintenance plan of the equipment, giving priority to equipment that shows high risk. For the calculation of failure probability, according to the formula:

[0121] ;

[0122] Among them, w q represents the weight of the qth fault point, p q represents the probability of the fault point, Q represents the total number of fault points, P f Represents the total failure probability of the equipment.

[0123] See also Figure 5 Based on the real-time fault probability update results, the fault information is synchronized to the blockchain network, and the preset response rules are executed through smart contracts to automatically allocate maintenance tasks and spare parts scheduling for air-to-energy heat pumps. Problems and progress are fed back in real time during the fault handling process. The specific steps for creating a fault response record are as follows:

[0124] S401: Based on the real-time fault probability update result, the new fault data is uploaded to the blockchain. The specific process of generating the data upload result is as follows;

[0125] The real-time failure probability P calculated from the system is serialized into a data format suitable for blockchain. Through a secure communication protocol, these data are encrypted by a hash algorithm and uploaded to the blockchain. In the blockchain, data is permanently recorded after its validity is verified by network nodes to ensure data security and non-tamperability. For the specific representation of data encryption and uploading, follow the formula:

[0126] ;

[0127] Among them, z represents the fault data P to be uploaded, g represents the encryption key, and the result U(z) represents the encrypted data, which will be stored on the blockchain.

[0128] S402: Based on the data upload result, the smart contract on the blockchain is triggered. The smart contract automatically schedules maintenance resources and spare parts according to the current fault data. The specific process of generating the maintenance task scheduling result is as follows;

[0129] When the blockchain records new fault data, the corresponding smart contract is automatically executed. The smart contract analyzes the fault data and dispatches the necessary maintenance resources and spare parts according to the preset logic. The system automatically sends resource allocation requests to the logistics and warehouse management systems, which respond to the requirements of the smart contract to ensure that the maintenance team obtains the necessary resources. For the specific representation of resource scheduling, follow the formula:

[0130] ;

[0131] Where v' represents the basic cost of resource allocation, b' represents the degree of demand, calculated according to the severity of the fault, and t h represents the number of h-th resource, and Q' represents the total resource scheduling amount.

[0132] S403: Based on the maintenance task scheduling result, the specific process of real-time monitoring and recording the maintenance progress and problem feedback and creating the fault response record is as follows;

[0133] The monitoring system collects progress reports and problem feedback from the maintenance team in real time. The system analyzes the collected data and automatically updates the maintenance record database to ensure that all maintenance activities are recorded in detail and can be used for future analysis and strategy adjustments. For the specific expression of maintenance progress tracking, follow the formula:

[0134] ;

[0135] in, represents the completion percentage of the pth maintenance task at time q', l represents the total number of tasks, and H(q') represents the average completion rate of all maintenance tasks.

[0136] See also Figure 6 , based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, and the operating parameters of the equipment are automatically adjusted to match the preset requirements of the fault response. The specific steps for obtaining the fault matching and processing results are as follows:

[0137] S501: Based on the fault response record, extract the fault features in the current record, list and classify the features of each record, prepare to compare with the preset fault mode, and generate the specific process of fault feature extraction result;

[0138] The system extracts historical records related to the current fault from the blockchain-based fault database. The data is verified and stored through smart contracts to ensure data authenticity and immutability. After screening the data and removing non-compliant records, in-depth analysis is performed to identify key fault features such as temperature anomalies and pressure imbalances, and classify them. The frequency of occurrence and successful repair rate of each type of fault feature are calculated to form a feature vector. The formula is:

[0139] ;

[0140] Among them, a represents the strength of a single fault feature, m is the influence coefficient of the feature, and F(a) represents the weighted fault feature strength. These parameters are obtained through historical data analysis and expert experience.

[0141] S502: Based on the fault feature extraction result, the extracted fault feature is matched with the defined fault mode, the matching degree is checked, the matching fault mode is marked, and the specific process of generating the fault mode matching result is as follows;

[0142] The weighted fault feature vector is compared with the fault pattern library stored on the blockchain. The pattern library is defined by experts and contains a set of feature vectors and processing strategies, which are stored on the blockchain to ensure integrity and transparency. The similarity is calculated using the formula:

[0143] ;

[0144] Among them, e represents the feature vector of the current fault, f' represents the feature vector of a certain fault mode in the database, and the similarity result Used to select the most suitable fault handling strategy.

[0145] S503: Based on the fault mode matching result, automatically adjust the operating parameters of the air energy heat pump to correspond to the matched fault mode, and the specific process of obtaining the fault matching and processing results is as follows;

[0146] Based on the matching results, the blockchain smart contract automatically instructs the control system of the air energy heat pump to adjust operating parameters, such as compressor speed, refrigerant flow, etc., to optimize operations to reduce the impact of failures. The effect of parameter adjustment is evaluated through real-time data feedback. Formula:

[0147] ;

[0148] Where r is the adjustment coefficient, g' is the recommended parameter value after fault mode matching, and s is the offset calculated based on historical data. are the adjusted parameters. These parameters and coefficients are obtained through data analysis and simulation tests.

[0149] See also Figure 7 Based on the fault matching and processing results, monitor the operating performance of the air energy heat pump after recovery, record the energy efficiency and temperature control accuracy parameters, and compare them with the set standards. The specific steps to generate the air energy heat pump performance monitoring results are as follows:

[0150] S601: Based on the fault matching and processing results, restart the air energy heat pump, record the first batch of performance data after startup, and generate the specific process of initial performance monitoring data;

[0151] After the fault is resolved, the system instructs the air energy heat pump to restart and records key startup performance data in real time through the connected sensor network. These data include startup time (t rsp ) and initial operating efficiency (e strt ). All data is ensured to be complete and tamper-proof through blockchain. Startup performance data is used to evaluate the heat pump startup effect and quickly diagnose possible startup problems. The performance formula is defined as:

[0152] ;

[0153] Among them, e strt represents the starting efficiency, t rsp represents the response time. These data are automatically collected by sensors and uploaded through a secure channel. init Represents the initial performance index, which is the result of performance evaluation and is used to evaluate the ratio of startup efficiency to response time.

[0154] S602: Based on the initial performance monitoring data, continuously track the energy efficiency and temperature control accuracy of the equipment during operation, regularly update the performance data, and generate the specific process of continuous performance tracking results;

[0155] The performance monitoring system of the air energy heat pump regularly obtains equipment operation data from the sensor network, including energy efficiency (e eff ) and temperature control accuracy (t acc ). Data is also recorded and verified through blockchain technology to ensure the accuracy of tracking and the reliability of data. Continuous tracking is used to optimize maintenance strategies and prevent potential failures in advance. The tracking formula is:

[0156] ;

[0157] Among them, e eff is the equipment energy efficiency, t acc is the accuracy of temperature control, w eff and w acc are the weight coefficients of these two indicators respectively. The data is automatically collected by the system regularly. track It is a continuous performance tracking indicator that represents the overall evaluation result of equipment performance and is a weighted average of energy efficiency and temperature control accuracy.

[0158] S603: Based on the continuous performance tracking results, the specific process of comparing the set performance standards with the current operating data, evaluating the recovery status and maintenance effect of the equipment, and generating the performance monitoring results of the air energy heat pump is as follows;

[0159] The performance evaluation system regularly compares the real-time monitoring data with the performance standards (s std). This assessment helps identify trends in performance degradation and adjust maintenance plans. The assessment formula is:

[0160] ;

[0161] Among them, s real Indicates the performance data monitored in real time, s std The formula is generated through regular performance reports to evaluate and guide maintenance decisions for the set performance standards, R eval It is the performance evaluation result, expressed as a percentage, showing the deviation of the actual performance of the equipment from the standard performance.

[0162] A blockchain-based air energy heat pump monitoring and control system, the system includes:

[0163] The parameter analysis module conducts detailed analysis of parameters including temperature, pressure, and current based on the historical operating data of the air energy heat pump, identifies key points and abnormal fluctuations, and generates operating data analysis results;

[0164] The fault analysis module establishes a correlation diagram of key components of the air-to-energy heat pump based on the analysis results of the operating data, uses simulation methods to refine the fault propagation path and impact range, and generates a Bayesian network model;

[0165] The real-time monitoring module is based on the Bayesian network model to monitor the currently collected air-energy heat pump operation data, identify potential fault points by comparing changes and setting thresholds, and generate real-time fault probability update results;

[0166] The fault response module updates the results based on the real-time fault probability, synchronizes the fault information to the blockchain network, uses smart contracts to automatically assign maintenance tasks and spare parts scheduling, records the fault handling status in real time, and creates fault response records;

[0167] Based on the fault response records, the performance evaluation module compares the fault characteristics of the air energy heat pump with the defined fault modes, automatically adjusts the operating parameters of the equipment, monitors the performance recovery of the equipment, compares it with the set standards, and generates air energy heat pump performance monitoring results.

[0168] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A blockchain-based air energy heat pump monitoring and control method, characterized in that: The following steps are involved: Collect the operating data of the air energy heat pump and extract the corresponding parameters. Determine the key points of parameter changes through time series analysis, identify abnormal fluctuations, and generate operating data analysis results. Based on the analysis results of the operating data, a correlation diagram of key components of the air-to-energy heat pump is established, the fault propagation path and impact range are simulated, and a Bayesian network model is established; Based on the Bayesian network model, the currently collected air-energy heat pump operation data is input, the changes in the operation parameters are compared, potential fault points are identified through the set thresholds, and real-time fault probability update results are generated; Based on the real-time fault probability update result, the fault information is synchronized to the blockchain network, the maintenance tasks and spare parts scheduling of the air energy heat pump are automatically assigned, and the fault response record is created; Based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, the operating parameters of the equipment are automatically adjusted, and the fault matching and processing results are obtained; Based on the fault matching and processing results, the operating performance of the air-to-energy heat pump after recovery is monitored and compared with the set standards to generate air-to-energy heat pump performance monitoring results.

2. The air energy heat pump monitoring and control method based on blockchain according to claim 1 is characterized in that: The operation data analysis results include abnormal points, fluctuation frequencies and timestamps of parameter out-of-bounds of key parameters, the Bayesian network model includes the influence weights of components, interaction strength and predicted fault transmission paths, the real-time fault probability update results include identification information of potential fault points, fault probability values ​​and warning levels of fault occurrence, the fault response records include the time of fault occurrence, processing steps, response time of maintenance personnel and spare parts usage information, the fault matching and processing results include automatic identification of fault types, successfully matched fault modes and parameters that need to be adjusted, and the air energy heat pump performance monitoring results include adjusted equipment operating efficiency, temperature stability evaluation and comparison data with preset performance indicators.

3. The blockchain-based air-energy heat pump monitoring and control method according to claim 1 is characterized in that: Collect the operating data of the air energy heat pump, extract the temperature, pressure and current parameters, determine the key points of parameter changes through time series analysis, identify abnormal fluctuations in the operating data, and generate the specific steps of operating data analysis results as follows: Based on all the operation records of the air-to-energy heat pump, key monitoring data points are selected, and the temperature, pressure, and current parameter data are sorted and preliminarily screened to obtain a time series data set; Based on the time series data set, identifying mutation points and abnormal fluctuations in the data, marking key anomalies, and generating abnormal data information; Based on the abnormal data information, the environmental conditions and potential factors of each marked data are analyzed, key change points associated with the fault are extracted, and the operation data analysis results are generated.

4. The air energy heat pump monitoring and control method based on blockchain according to claim 1 is characterized in that: Based on the analysis results of the operating data, a correlation diagram of the key components of the air-to-energy heat pump is established. By gradually adjusting the influence weights between the components, the fault propagation path and the impact range are simulated. The specific steps for establishing the Bayesian network model are as follows: Based on the analysis results of the operation data, identify and list the key components in the air-to-energy heat pump, and generate a component association list by evaluating the frequency of occurrence of the components in the fault records; Based on the component association list, the weight of each component is dynamically adjusted with reference to the impact degree and frequency of the component in the failure mode, and a component weight relationship diagram is created; Based on the component weight relationship diagram, the Bayesian network algorithm is applied to simulate the propagation effects under various fault scenarios, including the path and speed of the fault spreading from one component to adjacent components, and a Bayesian network model is established.

5. The blockchain-based air-energy heat pump monitoring and control method according to claim 4 is characterized in that: The Bayesian network algorithm calculates the conditional probability according to the following formula to obtain the probability that component j will also fail when component i' fails: : ； Among them, W j is the weight of component j, A i' is the data encryption strength index of component i' in the blockchain, B j is the fault monitoring sensitivity of component j, C j is the maintenance response rating of part j, n is the total number of parts, and k is the part index.

6. The air energy heat pump monitoring and control method based on blockchain according to claim 1 is characterized in that: Based on the Bayesian network model, the currently collected air-energy heat pump operation data is input, the changes in the operation parameters are compared, the fluctuations of the current equipment status are monitored, potential fault points are identified through the set thresholds, and the specific steps for generating real-time fault probability update results are as follows: Based on the Bayesian network model, the current operating data of the air energy heat pump is received, key operating parameters are recorded, the instant changes of the parameters are analyzed, and instant parameter analysis results are generated; Based on the instant parameter analysis results, compared with the preset normal operating range, using the set threshold to identify abnormal changes in the parameters, marking the changes as potential fault warnings, and generating warning identification results; Based on the early warning identification results, all marked potential fault points are analyzed, the current failure probability of the equipment is calculated, and a real-time failure probability update result is generated.

7. The air energy heat pump monitoring and control method based on blockchain according to claim 1 is characterized in that: Based on the real-time fault probability update results, the fault information is synchronized to the blockchain network, and the preset response rules are executed through smart contracts to automatically allocate maintenance tasks and spare parts scheduling for air-to-energy heat pumps. Problems and progress are fed back in real time during the fault handling process. The specific steps for creating fault response records are as follows: Based on the real-time fault probability update result, the new fault data is uploaded to the blockchain to generate a data upload result; Based on the data upload result, the smart contract on the blockchain is triggered, and the smart contract automatically schedules maintenance resources and spare parts according to the current fault data and generates a maintenance task scheduling result; Based on the maintenance task scheduling results, the maintenance progress and problem feedback are monitored and recorded in real time, and a fault response record is created.

8. The air energy heat pump monitoring and control method based on blockchain according to claim 1 is characterized in that: Based on the fault response record, the fault characteristics of the air energy heat pump are compared with the defined fault mode, the operating parameters of the equipment are automatically adjusted to match the preset requirements of the fault response, and the specific steps for obtaining the fault matching and processing results are as follows: Based on the fault response record, extract the fault features in the current record, list and classify the features of each record, prepare to compare with the preset fault mode, and generate a fault feature extraction result; Based on the fault feature extraction result, the extracted fault feature is matched with the defined fault mode, the matching degree is checked, the matching fault mode is marked, and the fault mode matching result is generated; Based on the fault mode matching result, the operating parameters of the air energy heat pump are automatically adjusted to correspond to the matched fault mode to obtain the fault matching and processing results.

9. The blockchain-based air-energy heat pump monitoring and control method according to claim 1 is characterized in that: Based on the fault matching and processing results, the operating performance of the air energy heat pump after recovery is monitored, the energy efficiency and temperature control accuracy parameters are recorded, and compared with the set standards. The specific steps for generating the air energy heat pump performance monitoring results are as follows: Based on the fault matching and processing results, restart the air energy heat pump, record the first batch of performance data after startup, and generate initial performance monitoring data; Based on the initial performance monitoring data, continuously track the energy efficiency and temperature control accuracy of the equipment during operation, regularly update the performance data, and generate continuous performance tracking results; Based on the continuous performance tracking results, the set performance standards and current operating data are compared to evaluate the equipment's recovery and maintenance effects, and generate air energy heat pump performance monitoring results.

10. A blockchain-based air energy heat pump monitoring and control system, characterized in that: According to any one of claims 1 to 9, the blockchain-based air-energy heat pump monitoring and control method is implemented, and the system includes: The parameter analysis module conducts detailed analysis of parameters including temperature, pressure, and current based on the historical operating data of the air energy heat pump, identifies key points and abnormal fluctuations, and generates operating data analysis results; The fault analysis module establishes a correlation diagram of key components of the air energy heat pump based on the analysis results of the operation data, uses a simulation method to refine the fault propagation path and impact range, and generates a Bayesian network model; The real-time monitoring module monitors the currently collected air-energy heat pump operation data based on the Bayesian network model, identifies potential fault points by comparing changes and setting thresholds, and generates real-time fault probability update results; The fault response module synchronizes the fault information to the blockchain network based on the real-time fault probability update result, automatically allocates maintenance tasks and spare parts scheduling using smart contracts, records the fault processing status in real time, and creates a fault response record; Based on the fault response record, the performance evaluation module compares the fault characteristics of the air energy heat pump with the defined fault mode, automatically adjusts the operating parameters of the equipment, monitors the performance recovery of the equipment, compares it with the set standard, and generates the air energy heat pump performance monitoring result.

Images