A heat meter online fault diagnosis method and system

Abstract

The application discloses a heat meter online fault diagnosis method and system, and relates to the technical field of energy metering.The system runs, real-time data collection and preprocessing are realized through integrated sensor groups, key features are extracted to form a feature vector FVEC, and an online anomaly detection algorithm and a fault type judgment model are used to accurately calculate an anomaly detection index AS and a fault feature probability index TYP.These data can not only reflect the health status of the system in real time, but also further optimize the response strategy and fault judgment by executing an iteration module, so that the system has the ability of self-diagnosis and adaptive adjustment.This optimization process can effectively solve the problem that the traditional heat meter system cannot realize online real-time processing and fault detection, improve the accuracy and response speed of fault identification, avoid equipment damage or energy waste caused by delayed detection, and further ensure the continuous and stable operation of the system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy metering, in particular to a heat meter online fault diagnosis method and system. BACKGROUND

[0002] Energy metering technology is a key technology widely used in many fields such as heating systems, industrial processes and building energy management. Heat meters, as an important tool in this field, are used to measure energy consumption in heating systems for accurate billing and energy efficiency management. In large residential complexes or industrial parks, heat meters can monitor the heat consumption of each user in real time.

[0003] In the daily operation of heat meters, data anomalies often occur due to environmental factors, sensor aging and signal interference. These anomalies may manifest as drift, mutation or long-term deviation of measurement data, directly affecting the accuracy of heat energy metering. However, existing fault detection methods rely heavily on periodic manual calibration and offline analysis, which cannot handle and detect data anomalies in real time. This method not only consumes time and effort, but also may miss early signs of failure, leading to accumulated problems and affecting the performance of the entire heating system. In addition, traditional detection methods mainly rely on pre-set rules or experience-based judgment for fault type determination, lacking the ability to dynamically adjust and provide real-time feedback, making it difficult to cope with complex and changing actual operating environments. The lack of online processing and detection capabilities further limits the possibility of effective intervention by the system in the early stages of failure, making subsequent problems more complex. SUMMARY

[0004] To overcome the shortcomings of the prior art, the present application provides a heat meter online fault diagnosis method and system, which solves the problems mentioned in the background art.

[0005] To achieve the above purpose, the present application realizes the following technical scheme: a heat meter online fault diagnosis system, comprising a data acquisition and preprocessing module, a feature extraction module, an anomaly detection module, a fault type judgment module and an execution iteration module;

[0006] The data acquisition and preprocessing module collects heat meter operating area data in real time by integrating a sensor group at the heat meter operating area location, and performs preprocessing to form an acquisition data set DAT;

[0007] The feature extraction module extracts features from the preprocessed acquisition data set DAT, obtains temperature difference feature TDF, flow change feature FCF, pressure fluctuation feature PWF, vibration frequency feature VDF and noise intensity feature NRF, and forms feature vector FVEC;

[0008] The anomaly detection module processes the obtained feature vector FVEC by using an online anomaly detection algorithm to obtain an anomaly detection index AS, and matches the anomaly detection index AS with a preset running anomaly state threshold YZ to obtain a heat meter running state result;

[0009] The fault type judgment module fits the anomaly detection index AS and the feature vector FVEC to obtain a fault feature probability index TYP;

[0010] The execution iteration module matches the obtained fault feature probability index TYP with a preset heat meter running feature anomaly evaluation threshold TZ to obtain a heat meter running anomaly feature response strategy scheme, and specifically executes the heat meter running anomaly feature response strategy scheme content, records the execution result, and iteratively adjusts the fault feature probability index TYP.

[0011] Preferably, the data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0012] The data acquisition unit acquires heat meter running area data in real time by integrating a sensor group at the heat meter running area position, including fluid temperature TMP, flow rate FLW, pipeline pressure PRS, ambient temperature ENV, vibration intensity VIB, and running noise NRM;

[0013] The sensor group includes a fluid temperature sensor, an ultrasonic flow sensor, a pressure sensor, an ambient temperature sensor, a vibration sensor, and a noise sensor.

[0014] The data preprocessing unit pre-processes the acquired running area data, including noise removal processing, missing value processing, and data standardization processing, to form an acquisition data group DAT.

[0015] The noise removal processing includes using moving average filtering to remove noise in time series data while retaining the trend of the running area data; the missing value processing includes using linear interpolation to fill in missing values by linear relationship between adjacent data points, thereby restoring the complete data sequence; and the data standardization preprocessing includes using Z-score standardization for standardization processing, thereby adjusting different parameters to the same dimension.

[0016] Preferably, the feature extraction module includes a feature calculation unit and a feature integration unit.

[0017] The feature calculation unit extracts features from the pre-processed acquisition data group DAT to obtain temperature difference feature TDF, flow change feature FCF, pressure fluctuation feature PWF, vibration frequency feature VDF, and noise intensity feature NRF.

[0018] The feature integration unit labels time t of the temperature difference feature TDF, the flow change feature FCF, the pressure wave fluctuation feature PWF, the vibration frequency feature VDF and the noise intensity feature NRF, and then integrates them to form a feature vector FVEC.

[0019] Preferably, the temperature difference feature TDF is used to reflect the difference state between the fluid temperature of the heat meter and the ambient temperature; the flow change feature FCF is used to reflect the change rate of the flow and its stability; the pressure wave fluctuation feature PWF is used to reflect the stability of the pressure in the pipeline; the vibration frequency feature VDF is used to analyze the vibration state of the equipment or pipeline, and specifically feedback is performed by extracting the frequency component of the vibration signal through Fourier transform; and the noise intensity feature NRF is used to reflect the noise level of the equipment and pipeline during operation.

[0020] Preferably, the anomaly detection module includes an anomaly detection unit and a state matching unit.

[0021] The anomaly detection unit performs weight assignment and weighted calculation processing on the temperature difference feature TDF, the flow change feature FCF, the pressure wave fluctuation feature PWF, the vibration frequency feature VDF and the noise intensity feature NRF in the acquired feature vector FVEC by using an online anomaly detection algorithm, and obtains an anomaly detection index AS by comprehensively processing the weighted deviations of the temperature difference feature TDF, the flow change feature FCF, the pressure wave fluctuation feature PWF, the vibration frequency feature VDF and the noise intensity feature NRF, which is used to trigger the heat meter running state result matching of the state matching unit.

[0022] The state matching unit matches the anomaly detection index AS with a preset running anomaly state threshold YZ to obtain a heat meter running state result, and triggers the execution of the fault type judgment module according to the heat meter running state result.

[0023] Preferably, the heat meter running state result is marked as a return signal, and the execution of the fault type judgment module is triggered according to the return signal.

[0024] When the return signal is 1, the heat meter running state is abnormal, and the execution of the fault type judgment module is triggered.

[0025] When the return signal is 0, the heat meter running state is normal, and the execution of the fault type judgment module is not triggered.

[0026] Preferably, the fault type judgment module checks the anomaly detection index AS and the feature vector FVEC through a checking mechanism, verifies the integrity and consistency of the verification data, synchronously stores the anomaly detection index AS and the feature vector FVEC in a cache area, processes them in sequence according to a time sequence, and then uses an online fitting algorithm to comprehensively process the anomaly detection index AS and the feature vector FVEC, so as to obtain a fault feature probability index TYP and realize quantitative evaluation of different fault types.

[0027] Preferably, the execution iteration module comprises an anomaly evaluation unit and an iteration control unit.

[0028] The anomaly evaluation unit matches the obtained fault feature probability index TYP with a preset heat meter running feature anomaly evaluation threshold TZ, and obtains a heat meter running anomaly feature response strategy scheme.

[0029] The iteration control unit specifically executes the heat meter running anomaly feature response strategy scheme content, records the execution result, and iteratively adjusts the fault feature probability index TYP.

[0030] Preferably, the heat meter running anomaly feature response strategy scheme is obtained through the following matching mode:

[0031] When the fault feature probability index TYP is greater than or equal to the heat meter running feature anomaly evaluation threshold TZ, a heat meter running state anomaly response strategy scheme is obtained, which includes switching a running mode, starting a self-diagnosis function of the heat meter, issuing an alarm, recording a log, and notifying a relevant inspection personnel to perform maintenance.

[0032] When the fault feature probability index TYP is less than the heat meter running feature anomaly evaluation threshold TZ, a heat meter running state anomaly non-response strategy scheme is obtained.

[0033] A heat meter online fault diagnosis method comprises the following steps:

[0034] Step one: a data acquisition and preprocessing module acquires heat meter running area data in real time through a sensor group integrated in a heat meter running area position, and pre-processes the data to form an acquisition data group DAT.

[0035] Step two: a feature extraction module extracts features from the pre-processed acquisition data group DAT, obtains a temperature difference feature TDF, a flow change feature FCF, a pressure fluctuation feature PWF, a vibration frequency feature VDF, and a noise intensity feature NRF, and forms a feature vector FVEC.

[0036] Step three: the anomaly detection module processes the obtained feature vector FVEC using an online anomaly detection algorithm to obtain an anomaly detection index AS, and matches it with a preset operating anomaly state threshold YZ to obtain a heat meter operating state result;

[0037] Step four: the fault type judgment module fits the anomaly detection index AS and the feature vector FVEC to obtain a fault feature probability index TYP;

[0038] Step five: the execution iteration module matches the obtained fault feature probability index TYP with a preset heat meter operating feature anomaly evaluation threshold TZ to obtain a heat meter operating anomaly feature response strategy scheme, and specifically executes according to the content of the heat meter operating anomaly feature response strategy scheme, and records the execution result to iteratively adjust the fault feature probability index TYP.

[0039] The present application provides a heat meter online fault diagnosis method and system, which has the following beneficial effects:

[0040] (1) When the system is running, the data is collected and preprocessed in real time by the integrated sensor group, the key features are extracted to form the feature vector FVEC, and the anomaly detection index AS and the fault feature probability index TYP are accurately calculated by using the online anomaly detection algorithm and the fault type judgment model. These data not only reflect the health status of the system in real time, but also further optimize the response strategy and fault judgment through the execution iteration module, so that the system has the ability of self-diagnosis and self-adaptive adjustment. This optimization process can effectively solve the problem of not being able to process and detect faults in real time in traditional heat meter systems, improve the accuracy and response speed of fault identification, avoid equipment damage or energy waste caused by delayed detection, and further ensure the continuous and stable operation of the system, as well as provide more accurate and timely fault warning and response mechanism.

[0041] (2) In the data collection and preprocessing stage, a variety of high-precision sensors are integrated to obtain key parameters in real time, and preprocessing is performed, including moving average filtering, linear interpolation and Z-score standardization, to ensure the high quality and consistency of the data. In the feature extraction process, the system extracts multi-dimensional features reflecting the operating state of the heat meter through complex feature calculation formulas, and integrates these features into a time-labeled feature vector FVEC. This process not only ensures the integrity and accuracy of the data, but also enables the system to fully capture the dynamic changes of the operating state. Compared with traditional methods, the present system has higher sensitivity and robustness in detecting small anomalies and various complex fault modes, thereby effectively avoiding misjudgment caused by inaccurate data or improper processing, ensuring the stable operation and accurate measurement of the heat meter.

[0042] (3) The feature vector FVEC is processed by the online anomaly detection algorithm, the anomaly detection index AS is accurately calculated, and the running state of the heat meter is judged in real time by matching with the preset running anomaly state threshold YZ. Through strict standardization and weight calculation, this module ensures the sensitive capture of the deviation degree of various features, can accurately identify the abnormal state; at the same time, through the return mechanism of the return signal, the intelligent triggering of the fault type judgment module is realized, and only when the anomaly is detected, further fault analysis is carried out, thereby avoiding the waste of system resources; it is also suitable for continuous monitoring under complex working conditions, ensures that the system can quickly make judgments and responses when facing sudden conditions, reduces unnecessary downtime, and improves the overall operation efficiency and stability of the heat meter.

[0043] (4) The anomaly detection index AS and the feature vector FVEC are fitted and calculated, the fault feature probability index TYP can be accurately obtained, and then the anomaly response strategy with strong pertinence is intelligently generated by matching with the preset threshold TZ. This not only ensures that the system can quickly switch the operation mode, start the self-diagnosis function, and timely notify the maintenance personnel when the actual fault occurs, but also can reduce unnecessary intervention under non-serious abnormal conditions, and optimize the system resource utilization rate. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The present application provides a heat meter online fault diagnosis system block diagram;

[0045] Figure 2 The present application provides a heat meter online fault diagnosis system block diagram. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0047] Embodiment 1

[0048] The present application provides a heat meter online fault diagnosis system, please refer to Figure 1 , comprising a data acquisition and preprocessing module, a feature extraction module, an anomaly detection module, a fault type judgment module and an execution iteration module;

[0049] The data acquisition and preprocessing module collects heat meter running area data in real time through the integrated sensor group in the heat meter running area position, and pre-processes to form the acquisition data group DAT;

[0050] The feature extraction module extracts features from the preprocessed acquired data set DAT, obtaining temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF), which together form the feature vector FVEC.

[0051] The anomaly detection module processes the acquired feature vector FVEC using an online anomaly detection algorithm to obtain the anomaly detection index AS, and matches it with the preset abnormal operation state threshold YZ to obtain the heat meter operation status result.

[0052] The fault type determination module fits the anomaly detection index AS and the feature vector FVEC to obtain the fault feature probability index TYP.

[0053] The execution iteration module matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme, and executes it in detail according to the content of the heat meter operation anomaly feature response strategy scheme. By recording the execution results, the fault feature probability index TYP is iteratively adjusted.

[0054] In this embodiment, data is collected and preprocessed in real time by an integrated sensor array. Key features are extracted to form a feature vector FVEC. An online anomaly detection algorithm and a fault type judgment model are then used to accurately calculate the anomaly detection index AS and the fault characteristic probability index TYP. This data not only reflects the system's health status in real time but also further optimizes the response strategy and fault judgment through iterative modules, enabling the system to have self-diagnosis and adaptive adjustment capabilities. This optimization process effectively addresses the shortcomings of traditional heat meter systems in terms of online real-time fault processing and detection, improving the accuracy and response speed of fault identification, avoiding equipment damage or energy waste caused by delayed detection, thereby ensuring the continuous and stable operation of the system and providing a more accurate and timely fault warning and response mechanism.

[0055] Example 2

[0056] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically: the data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0057] The data acquisition unit collects real-time data on the heat meter's operating area by integrating a sensor group at the heat meter's operating area location, including fluid temperature TMP, flow rate FLW, pipeline pressure PRS, ambient temperature ENV, vibration intensity VIB, and operating noise NRM.

[0058] The sensor group includes a fluid temperature sensor, an ultrasonic flow sensor, a pressure sensor, an ambient temperature sensor, a vibration sensor, and a noise sensor.

[0059] The data preprocessing unit preprocesses the collected data from the operating area, including noise removal, missing value handling, and data standardization, forming the collected data group DAT, specifically DAT={TMP, FLW, PRS, ENV, VIB, NRM}.

[0060] The noise removal process includes using moving average filtering to remove noise from time series data while preserving the trend of the data in the running area; missing value processing includes using linear interpolation to fill in missing values ​​by establishing the linear relationship between adjacent data points, thereby restoring the complete data sequence; and data standardization preprocessing includes using Z-score standardization to standardize the data, thereby adjusting different parameters to the same dimension.

[0061] The feature extraction module includes a feature calculation unit and a feature integration unit;

[0062] The feature calculation unit performs feature extraction on the preprocessed acquired data set DAT to obtain temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF).

[0063] The feature integration unit marks the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF) with time t, and then integrates them to form a feature vector FVEC, specifically FVEC={TDF, FCF, PWF, VDF, NRF, t}.

[0064] Among them, the temperature difference feature (TDF) is used to reflect the difference between the temperature of the fluid in the heat meter and the ambient temperature; the flow rate change feature (FCF) is used to reflect the rate of change and stability of the flow rate; the pressure fluctuation feature (PWF) is used to reflect the stability of the pressure in the pipeline; the vibration frequency feature (VDF) is used to analyze the vibration state of the equipment or pipeline, specifically by extracting the frequency components of the vibration signal through Fourier transform and feeding them back; and the noise intensity feature (NRF) is used to reflect the noise level of the equipment and pipeline during operation.

[0065] Temperature difference characteristics (TDF) are obtained using the following formula:

[0066] ;

[0067] In the formula, TMPi represents the fluid temperature at the i-th time point, ENVi represents the ambient temperature at the i-th time point, Δti represents the time interval at the i-th time point, log represents the logarithmic function, TMPmax represents the peak fluid temperature, and TMPmin represents the valley fluid temperature.

[0068] The flow change characteristic FCF is obtained through the following formula:

[0069] ;

[0070] In the formula, T represents the total observation time, specifically multiple time intervals Δt, each time interval Δt includes multiple time points i, FLWi represents the flow rate at time point i, and d represents the derivative. FLW represents the rate of change of flow rate FLW with time point i, FLWmax represents the peak flow rate, and FLWmin represents the valley flow rate.

[0071] Pressure fluctuation characteristics (PWF) are obtained using the following formula:

[0072] ;

[0073] In the formula, n represents the total number of time points, and PRSi represents the pipeline pressure at the i-th time point. PRSprev represents the average pipeline pressure, and PRSprev represents the pipeline pressure at the (i-1)th time point.

[0074] The vibration frequency characteristic VDF is obtained through the following characteristic calculation formula:

[0075] ;

[0076] In the formula, w represents the total number of frequency components after Fourier transform, VIBk represents the k-th frequency component of the vibration intensity signal, and F(VIBk) represents the Fourier transform result of the vibration intensity VIB signal on the k-th frequency component, specifically representing the amplitude of the vibration intensity VIB.

[0077] Noise intensity characteristics (NRF) are obtained using the following formula:

[0078] ;

[0079] In the formula, NRMi represents the operating noise at the i-th time point. This represents the average operating noise level.

[0080] In this embodiment, during the data acquisition and preprocessing stage, key parameters are acquired in real time by integrating multiple high-precision sensors and preprocessed, including moving average filtering, linear interpolation, and Z-score standardization, to ensure high-quality and consistent data. During feature extraction, the system extracts multi-dimensional features reflecting the operating status of the heat meter through complex feature calculation formulas and integrates these features into a time-stamped feature vector (FVEC). This process not only ensures data integrity and accuracy but also enables the system to comprehensively capture dynamic changes in operating status. Compared to traditional methods, this system exhibits higher sensitivity and robustness in detecting minor anomalies and various complex fault modes, effectively avoiding misjudgments caused by inaccurate data or improper processing, thus ensuring stable operation and accurate measurement of the heat meter.

[0081] Example 3

[0082] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically: the anomaly detection module includes an anomaly detection unit and a state matching unit;

[0083] The anomaly detection unit uses an online anomaly detection algorithm to assign weights and perform weighted calculations on the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF) in the acquired feature vector FVEC. It then obtains the anomaly detection index AS by comprehensively considering the weighted deviations of the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF). This AS is used to trigger the matching of the heat meter operating status results in the status matching unit.

[0084] The anomaly detection index AS is obtained using the following formula:

[0085] ;

[0086] In the formula, m represents the total number of features in the feature vector FVEC, and FVECj represents the j-th feature in the feature vector FVEC. Let represent the mean of the j-th feature in the feature vector FVEC. This represents the standard deviation of the j-th feature in the eigenvector FVEC, specifically indicating the range of fluctuation of the feature values. This represents the standardized deviation of the j-th feature in the feature vector FVEC, specifically indicating the degree of deviation of the feature, where uj represents the preset weight value of the j-th feature;

[0087] The status matching unit matches the preset abnormal operation status threshold YZ with the abnormal detection index AS to obtain the heat meter operation status result, and triggers the execution of the fault type judgment module based on the heat meter operation status result.

[0088] The heat meter's operating status result is marked as a return signal, and the execution of the fault type judgment module is triggered based on the return signal;

[0089] The return signal is transmitted through Obtained by marking method;

[0090] When the return signal is 1, it indicates that the heat meter is in an abnormal operating state, triggering the execution of the fault type judgment module.

[0091] When the return signal is 0, the heat meter's operating status is found to be normal, and the execution of the fault type judgment module is not triggered.

[0092] In this embodiment, the feature vector FVEC is processed by an online anomaly detection algorithm to accurately calculate the anomaly detection index AS. This index AS is then matched with a preset anomaly state threshold YZ to determine the heat meter's operating status in real time. This module, through rigorous standardization and weight calculation, ensures sensitive capture of deviations from various features, accurately identifying anomalies. Simultaneously, the return signal mechanism enables intelligent triggering of the fault type judgment module, performing further fault analysis only when an anomaly is detected, thus avoiding waste of system resources. It is also suitable for continuous monitoring under complex operating conditions, ensuring the system can quickly make judgments and responses to emergencies, reducing unnecessary downtime and improving the overall operating efficiency and stability of the heat meter.

[0093] Example 4

[0094] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically: The fault type judgment module verifies the anomaly detection index AS and feature vector FVEC through a verification mechanism to verify the integrity and consistency of the data. Simultaneously, the anomaly detection index AS and feature vector FVEC are temporarily stored in the cache and processed sequentially according to the time series. Then, the anomaly detection index AS and feature vector FVEC are comprehensively processed using an online fitting algorithm to obtain the fault feature probability index TYP, thereby realizing the quantitative assessment of different fault types.

[0095] The fault characteristic probability index TYP is obtained through the following formula:

[0096] ;

[0097] In the formula, TYPk represents the fault feature probability index TYP for the k-th fault type, m represents the total number of features in the feature vector FVEC, Pk,j represents the preset weight value between the k-th fault type and the j-th feature, and FVECj represents the j-th feature in the feature vector FVEC. The standard deviation of the j-th feature in the feature vector FVEC is represented as . This represents the sensitivity coefficient for the k-th fault type;

[0098] The fault types include abnormal temperature, abnormal flow, abnormal pressure, abnormal vibration, and abnormal noise.

[0099] The execution iteration module includes an anomaly evaluation unit and an iteration control unit;

[0100] The anomaly assessment unit matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme.

[0101] The iterative control unit executes the response strategy based on the abnormal characteristics of the heat meter operation, and iteratively adjusts the fault characteristic probability index TYP by recording the execution results.

[0102] The response strategy for abnormal operation characteristics of heat meters is obtained through the following matching method:

[0103] When the fault characteristic probability index TYP is greater than or equal to the heat meter operation characteristic abnormal assessment threshold TZ, obtain the heat meter operation status abnormal response strategy plan, including switching the operation mode, starting the heat meter's self-diagnosis function, issuing an alarm, recording logs, and notifying relevant inspection personnel to carry out maintenance.

[0104] When the fault characteristic probability index TYP is less than the heat meter operation characteristic abnormality assessment threshold TZ, obtain the heat meter operation status abnormality non-response strategy scheme.

[0105] In this embodiment, the anomaly detection index AS and the feature vector FVEC are fitted and calculated to accurately obtain the fault feature probability index TYP. This TYP is then matched with a preset threshold TZ to intelligently generate a highly targeted anomaly response strategy. This not only ensures that the system can quickly switch operating modes, activate self-diagnostic functions, and promptly notify maintenance personnel when an actual fault occurs, but also reduces unnecessary intervention and optimizes system resource utilization in non-serious anomaly situations.

[0106] Example 5

[0107] A method for online fault diagnosis of heat meters, please refer to... Figure 2 Specifically, it includes the following steps:

[0108] Step 1: The data acquisition and preprocessing module integrates a sensor group at the operating area of ​​the heat meter to collect data in real time, and performs preprocessing to form the acquired data group DAT;

[0109] Step 2: The feature extraction module performs feature extraction on the preprocessed acquired data set DAT to obtain the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF), which are combined to form the feature vector FVEC.

[0110] Step 3: The anomaly detection module processes the acquired feature vector FVEC using an online anomaly detection algorithm to obtain the anomaly detection index AS, and matches it with the preset abnormal operation state threshold YZ to obtain the heat meter operation status result.

[0111] Step 4: The fault type determination module fits the anomaly detection index AS and the feature vector FVEC to obtain the fault feature probability index TYP.

[0112] Step 5: The execution iteration module matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme, and executes it in detail according to the content of the heat meter operation anomaly feature response strategy scheme. By recording the execution results, the fault feature probability index TYP is iteratively adjusted.

[0113] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An online fault diagnosis system for heat meters, characterized in that: It includes a data acquisition and preprocessing module, a feature extraction module, an anomaly detection module, a fault type determination module, and an execution iteration module; The data acquisition and preprocessing module integrates a sensor group at the operating area of ​​the heat meter to collect data in real time, and performs preprocessing to form the acquired data group DAT; The feature extraction module extracts features from the preprocessed acquired data set DAT, obtaining temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF), forming a feature vector FVEC. Specifically, the temperature difference feature (TDF) reflects the difference between the fluid temperature in the heat meter and the ambient temperature; the flow rate change feature (FCF) reflects the rate of change and stability of the flow rate; the pressure fluctuation feature (PWF) reflects the stability of the pressure within the pipeline; the vibration frequency feature (VDF) analyzes the vibration state of the equipment or pipeline, specifically by extracting the frequency components of the vibration signal through Fourier transform and providing feedback; and the noise intensity feature (NRF) reflects the noise level of the equipment and pipeline during operation. The anomaly detection module processes the acquired feature vector FVEC using an online anomaly detection algorithm to obtain the anomaly detection index AS, and matches it with the preset abnormal operation state threshold YZ to obtain the heat meter operation status result. The fault type determination module fits the anomaly detection index AS and the feature vector FVEC to obtain the fault feature probability index TYP. The execution iteration module matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme, and executes it in detail according to the content of the heat meter operation anomaly feature response strategy scheme. By recording the execution results, the fault feature probability index TYP is iteratively adjusted.

2. The online fault diagnosis system for a heat meter according to claim 1, characterized in that: The data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit collects real-time data on the heat meter's operating area by integrating a sensor group at the heat meter's operating area location, including fluid temperature TMP, flow rate FLW, pipeline pressure PRS, ambient temperature ENV, vibration intensity VIB, and operating noise NRM. The sensor group includes a fluid temperature sensor, an ultrasonic flow sensor, a pressure sensor, an ambient temperature sensor, a vibration sensor, and a noise sensor. The data preprocessing unit preprocesses the collected data from the operating area, including noise removal, missing value handling, and data standardization, forming the collected data set DAT. The noise removal process includes using moving average filtering to remove noise from time series data while preserving the trend of the data in the running area; missing value processing includes using linear interpolation to fill in missing values ​​by establishing the linear relationship between adjacent data points, thereby restoring the complete data sequence; and data standardization preprocessing includes using Z-score standardization to standardize the data, thereby adjusting different parameters to the same dimension.

3. The online fault diagnosis system for a heat meter according to claim 1, characterized in that: The feature extraction module includes a feature calculation unit and a feature integration unit; The feature calculation unit performs feature extraction on the preprocessed acquired data set DAT to obtain temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF). The feature integration unit marks the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF) with time t before integrating them. The feature vector FVEC is formed.

4. The online fault diagnosis system for a heat meter according to claim 1, characterized in that: The anomaly detection module includes an anomaly detection unit and a state matching unit; The anomaly detection unit uses an online anomaly detection algorithm to assign weights and perform weighted calculations on the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF) in the acquired feature vector FVEC. It then obtains the anomaly detection index AS by comprehensively considering the weighted deviations of the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF). This AS is used to trigger the matching of the heat meter operating status results in the status matching unit. The status matching unit matches the preset abnormal operation status threshold YZ with the abnormal detection index AS to obtain the heat meter operation status result, and triggers the execution of the fault type judgment module based on the heat meter operation status result.

5. An online fault diagnosis system for a heat meter according to claim 4, characterized in that: The heat meter's operating status result is marked as a return signal, and the execution of the fault type judgment module is triggered based on the return signal; When the return signal is 1, it indicates that the heat meter is in an abnormal operating state, triggering the execution of the fault type judgment module. When the return signal is 0, the heat meter's operating status is found to be normal, and the execution of the fault type judgment module is not triggered.

6. An online fault diagnosis system for a heat meter according to claim 5, characterized in that: The fault type judgment module verifies the anomaly detection index AS and feature vector FVEC through a verification mechanism to verify the integrity and consistency of the data. Simultaneously, the anomaly detection index AS and feature vector FVEC are temporarily stored in the cache and processed sequentially according to the time series. Then, the anomaly detection index AS and feature vector FVEC are comprehensively processed using an online fitting algorithm to obtain the fault feature probability index TYP, thereby realizing the quantitative assessment of different fault types.

7. An online fault diagnosis system for a heat meter according to claim 6, characterized in that: The execution iteration module includes an anomaly evaluation unit and an iteration control unit; The anomaly assessment unit matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme. The iterative control unit executes the response strategy based on the abnormal characteristics of the heat meter operation, and iteratively adjusts the fault characteristic probability index TYP by recording the execution results.

8. An online fault diagnosis system for a heat meter according to claim 7, characterized in that: The response strategy for abnormal operation characteristics of heat meters is obtained through the following matching method: When the fault characteristic probability index TYP is greater than or equal to the heat meter operation characteristic abnormal assessment threshold TZ, obtain the heat meter operation status abnormal response strategy plan, including switching the operation mode, starting the heat meter's self-diagnosis function, issuing an alarm, recording logs, and notifying relevant inspection personnel to carry out maintenance. When the fault characteristic probability index TYP is less than the heat meter operation characteristic abnormality assessment threshold TZ, obtain the heat meter operation status abnormality non-response strategy scheme.

9. A method for online fault diagnosis of a heat meter, applied to an online fault diagnosis system for a heat meter according to any one of claims 1-8, characterized in that: Includes the following steps: Step 1: The data acquisition and preprocessing module integrates a sensor group at the operating area of ​​the heat meter to collect data in real time, and performs preprocessing to form the acquired data group DAT; Step 2: The feature extraction module performs feature extraction on the preprocessed acquired data set DAT to obtain the temperature difference feature (TDF), flow rate change feature (FCF), pressure fluctuation feature (PWF), vibration frequency feature (VDF), and noise intensity feature (NRF), which are combined to form the feature vector FVEC. Step 3: The anomaly detection module processes the acquired feature vector FVEC using an online anomaly detection algorithm to obtain the anomaly detection index AS, and matches it with the preset abnormal operation state threshold YZ to obtain the heat meter operation status result. Step 4: The fault type determination module fits the anomaly detection index AS and the feature vector FVEC to obtain the fault feature probability index TYP. Step 5: The execution iteration module matches the obtained fault feature probability index TYP with the preset heat meter operation feature anomaly assessment threshold TZ to obtain a heat meter operation anomaly feature response strategy scheme, and executes it in detail according to the content of the heat meter operation anomaly feature response strategy scheme. By recording the execution results, the fault feature probability index TYP is iteratively adjusted.

Images