Remote fault diagnosis method and system for intelligent temperature transmitter

Abstract

The present invention relates to the field of remote control technology and discloses a remote fault diagnosis method and system for an intelligent temperature transmitter, comprising: defining a confidence distribution function for multi-source sensor data, performing conflict elimination on the multi-source sensor data, and obtaining conflict elimination data; extracting a cross-modal correlation feature matrix of the conflict elimination data, determining the thermodynamic transfer sub-equations of the temperature transmitter and an LSTM-PHY joint modeling framework, and constructing a hybrid digital twin model of the temperature transmitter; simulating the normal operating conditions of the temperature transmitter using the hybrid digital twin model and analyzing behavioral deviations of the temperature transmitter; constructing a hierarchical collaborative network for the temperature transmitter and using the hierarchical collaborative network to analyze multi-layer fault analysis results of the temperature transmitter; determining fault optimization parameters for the temperature transmitter, and performing fault diagnosis of the intelligent temperature transmitter based on the fault optimization parameters. The present invention can improve the efficiency of fault analysis for temperature transmitters.

Description

Technical Field

[0001] The present invention relates to a remote fault diagnosis method and system for an intelligent temperature transmitter, belonging to the technical field of remote control. Background Art

[0002] Remote fault diagnosis of temperature transmitters refers to a technical system that uses technologies such as the Internet of Things and artificial intelligence to monitor the operating status of temperature transmitters in real time, perform data analysis, and diagnose faults, and achieve early warning, precise positioning, and remote handling of faults without the need for manual on-site intervention.

[0003] Traditional remote fault diagnosis of temperature transmitters typically relies on simple monitoring and regular inspections. This involves comparing real-time data with preset thresholds to determine device status. Once an anomaly is detected, technicians are notified for on-site inspection and repair. This diagnostic approach relies on a limited single signal and lacks comprehensive analysis of multi-source data, making it difficult to accurately predict and locate faults, resulting in low diagnostic efficiency. Summary of the Invention

[0004] The present invention provides a remote fault diagnosis method and system for an intelligent temperature transmitter, the main purpose of which is to improve the fault analysis efficiency of the temperature transmitter.

[0005] To achieve the above objectives, the present invention provides a remote fault diagnosis method for an intelligent temperature transmitter, comprising:

[0006] collecting multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal time series data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters; defining a confidence allocation function for the multi-source sensor data; and performing conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict elimination data;

[0007] Extracting a cross-modal correlation feature matrix of the conflict elimination data, determining a thermodynamic transfer sub-equation and an LSTM-PHY joint modeling framework of the temperature transmitter, and constructing a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equation and the LSTM-PHY joint modeling framework;

[0008] simulating a normal operating condition of the temperature transmitter by using the hybrid digital twin model, and analyzing a behavioral deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix;

[0009] Constructing a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer, and analyzing multi-layer fault analysis results of the temperature transmitter using the hierarchical collaborative network based on the behavioral deviation;

[0010] The fault optimization parameters of the temperature transmitter are determined through the multi-layer fault analysis results, and the fault diagnosis of the intelligent temperature transmitter is performed based on the fault optimization parameters.

[0011] Optionally, defining a confidence distribution function for the multi-source sensing data includes:

[0012] Preprocessing the multi-source sensor data to obtain processed multi-source sensor data;

[0013] Analyzing confidence influencing factors of processing multi-source sensor data, wherein the confidence influencing factors include data source accuracy, data source stability, data source reliability, and environmental impact coefficient;

[0014] Defining factor weights of the confidence influencing factors;

[0015] Based on the confidence influencing factors and the factor weights, the confidence allocation function of the multi-source sensor data is constructed using the following formula, wherein the confidence allocation function includes:

[0016] ;

[0017] in, represents the confidence of the cth data source of multi-source sensor data, Indicates that the cth data source of multi-source sensor data corresponds to the The value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The maximum value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The factor weight of the confidence influence factor.

[0018] Optionally, performing conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict elimination data includes:

[0019] Analyzing the confidence of the multi-source sensor data using the confidence allocation function;

[0020] Determining, based on the multi-source sensing data, a heat transfer coefficient, an effective heat transfer area, a temperature difference, and a radiation heat transfer term of a temperature transmitter corresponding to the multi-source sensing data;

[0021] Analyzing the energy deviation value of the temperature transmitter through the heat transfer coefficient, effective heat transfer area, temperature difference and radiation heat transfer term;

[0022] analyzing data conflicts of the multi-source sensing data according to the energy deviation value;

[0023] Conflict elimination is performed on the multi-source sensor data based on the data conflict and the confidence level to obtain conflict-eliminated data.

[0024] Optionally, analyzing the energy deviation value of the temperature transmitter by using the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term includes:

[0025] The heat transfer rate of the temperature transmitter is calculated using the following formula based on the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term:

[0026] ;

[0027] in, Indicates the heat conversion rate of the temperature transmitter, represents the heat transfer coefficient, represents the effective heat transfer area, Indicates the temperature difference, represents the radiation heat transfer term, represents the Stefan-Boltzmann constant, represents the surface emissivity, represents the radiating surface area, Indicates the absolute surface temperature;

[0028] An energy deviation value of the temperature transmitter is calculated based on the actual heat change rate measured in advance and the heat conversion rate.

[0029] Optionally, extracting a cross-modal correlation feature matrix of the conflict resolution data includes:

[0030] Establishing a coordinate system transformation matrix for the conflict elimination data;

[0031] Performing spatial registration on the conflict elimination data according to the coordinate system conversion matrix to obtain registration data;

[0032] extracting unimodal features of the registration data;

[0033] Constructing a graph structure of the unimodal feature;

[0034] A cross-modal correlation feature matrix of the conflict resolution data is constructed through the graph structure.

[0035] Optionally, determining the thermodynamic transfer sub-equation of the temperature transmitter and the LSTM-PHY joint modeling framework includes:

[0036] dividing the temperature transmitter into a plurality of control volumes;

[0037] determining heat balance equations for the plurality of control volumes;

[0038] According to the heat balance equation, construct the thermodynamic transfer sub-equation of the temperature transmitter;

[0039] Determine the LSTM-PHY network structure of the temperature transmitter;

[0040] The thermodynamic transfer sub-equation is integrated into the LSTM-PHY network structure to obtain the LSTM-PHY joint modeling framework of the temperature transmitter.

[0041] Optionally, constructing the thermodynamic transfer sub-equation of the temperature transmitter according to the heat balance equation includes:

[0042] According to the thermal balance equation, the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency and damping ratio of the temperature transmitter are analyzed;

[0043] Based on the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency and damping ratio, the thermodynamic transfer sub-equation of the temperature transmitter is constructed using the following formula, wherein the thermodynamic transfer sub-equation is:

[0044] ;

[0045] in, represents the thermodynamic transfer sub-equation, represents the time constant, Represents pure delay time, represents the Laplace variable, represents the exponential function, represents the thermoelastic coupling coefficient, represents the damping ratio, Indicates the natural frequency of mechanical vibration.

[0046] Optionally, analyzing the behavior deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix includes:

[0047] Analyzing characteristic distribution of the normal operating condition;

[0048] Normalizing the cross-modal correlation feature matrix to obtain a normalized correlation feature matrix;

[0049] defining a deviation index of the temperature transmitter;

[0050] The behavior deviation of the temperature transmitter is analyzed based on the deviation index, the normalized correlation feature matrix, and the feature distribution.

[0051] Optionally, constructing the hierarchical collaborative network of the temperature transmitter includes:

[0052] Constructing a hierarchical collaborative structure of the temperature transmitter, wherein the hierarchical collaborative structure includes an edge layer structure, a fog node layer structure, and a cloud layer structure;

[0053] Performing network integration on the edge layer structure, fog node layer structure, and cloud layer structure to obtain a hierarchical collaborative network structure;

[0054] Defining collaborative analysis rules for the hierarchical collaborative network structure;

[0055] Analyzing the interoperability between layers of the hierarchical collaborative network structure;

[0056] When the inter-layer interoperability meets a preset inter-layer interoperability threshold, a hierarchical collaborative network of the temperature transmitter is constructed based on the hierarchical collaborative network structure and the collaborative analysis rule.

[0057] In order to solve the above problems, the present invention also provides a remote fault diagnosis system for an intelligent temperature transmitter, the system comprising:

[0058] a data conflict resolution module configured to collect multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal timing data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters; define a confidence allocation function for the multi-source sensor data; and perform conflict resolution on the multi-source sensor data using the confidence allocation function to obtain conflict resolution data;

[0059] a twin model construction module, configured to extract a cross-modal correlation feature matrix of the conflict elimination data, determine a thermodynamic transfer sub-equation and an LSTM-PHY joint modeling framework for the temperature transmitter, and construct a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equation and the LSTM-PHY joint modeling framework;

[0060] a behavioral deviation analysis module, configured to simulate a normal operating condition of the temperature transmitter through the hybrid digital twin model, and analyze the behavioral deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix;

[0061] a multi-layer fault analysis module, configured to construct a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer, and to analyze the multi-layer fault analysis results of the temperature transmitter using the hierarchical collaborative network based on the behavioral deviation;

[0062] A fault parameter optimization module is used to determine the fault optimization parameters of the temperature transmitter through the multi-layer fault analysis results, and perform fault diagnosis of the intelligent temperature transmitter based on the fault optimization parameters.

[0063] Compared with the problems described in the background technology, first, the confidence allocation function of multi-source sensor data effectively eliminates data conflicts and improves data quality and reliability. By integrating temperature signal time series data, power supply current harmonic characteristic data, equipment vibration spectrum data and environmental parameters, more comprehensive and accurate equipment status information is obtained. Secondly, the extraction of cross-modal correlation feature matrix, combined with thermodynamic transfer sub-equations and LSTM-PHY joint modeling framework, enables the hybrid digital twin model to accurately simulate the normal operating conditions of the temperature transmitter, providing strong support for behavioral deviation analysis. Thirdly, the construction of a hierarchical collaborative network realizes distributed processing and intelligent analysis of data, improving the efficiency and accuracy of fault diagnosis. The collaborative work of the edge layer, fog node layer and cloud layer makes the fault analysis results more comprehensive and in-depth, providing a scientific basis for fault prevention and maintenance decisions. In addition, the fault optimization parameters determined based on the multi-layer fault analysis results effectively guide the fault diagnosis of the intelligent temperature transmitter. The optimization of these parameters helps to reduce the failure rate, extend the equipment life and reduce maintenance costs. Finally, the application of the entire method significantly improves the operational reliability of the temperature transmitter and ensures the continuity and safety of the production process. Therefore, the present invention can improve the fault analysis efficiency of the temperature transmitter. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a remote fault diagnosis method for an intelligent temperature transmitter provided by an embodiment of the present invention;

[0065] Figure 2 A schematic diagram of a module for implementing the remote fault diagnosis method of an intelligent temperature transmitter provided in one embodiment of the present invention.

[0066] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0067] 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.

[0068] The present invention provides a method for remote fault diagnosis of an intelligent temperature transmitter. The method can be performed by at least one of the following electronic devices, including a server and a terminal, that can be configured to perform the method provided by the present invention. In other words, the method can be performed by software or hardware installed on a terminal or server. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0069] Example 1:

[0070] Reference Figure 1 FIG. 1 is a flow chart of a remote fault diagnosis method for an intelligent temperature transmitter according to an embodiment of the present invention. In this embodiment, the remote fault diagnosis method for an intelligent temperature transmitter includes:

[0071] S1. Collect multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal timing data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters; define a confidence allocation function for the multi-source sensor data; and perform conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict elimination data.

[0072] It should be explained that the temperature signal timing data refers to the sequence of temperature readings recorded by the temperature transmitter over time, the power supply current harmonic characteristic data is the harmonic component data obtained by analyzing the power supply current waveform, the equipment vibration spectrum data is the spectrum analysis result of the equipment vibration signal collected by the vibration sensor, and the environmental parameters refer to the environmental condition data that affects the performance of the temperature transmitter, which may include but are not limited to ambient temperature, humidity, pressure, wind speed, pollution level and other data.

[0073] The confidence distribution function defined in the present invention for the multi-source sensing data can provide a basis for later data conflict elimination.

[0074] In detail, the definition of the confidence distribution function of the multi-source sensor data includes:

[0075] Preprocessing the multi-source sensor data to obtain processed multi-source sensor data;

[0076] Analyzing confidence influencing factors of processing multi-source sensor data, wherein the confidence influencing factors include data source accuracy, data source stability, data source reliability, and environmental impact coefficient;

[0077] Defining factor weights of the confidence influencing factors;

[0078] Based on the confidence influencing factors and the factor weights, the confidence allocation function of the multi-source sensor data is constructed using the following formula, wherein the confidence allocation function includes:

[0079] ;

[0080] in, represents the confidence of the cth data source of multi-source sensor data, Indicates that the cth data source of multi-source sensor data corresponds to the The value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The maximum value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The factor weight of the confidence influence factor.

[0081] Among them, the processed multi-source sensor data refers to pre-processed sensor data, the data source accuracy refers to the degree of proximity between the sensor measurement value and the true value, the data source stability refers to the degree of change of the sensor output over a long period of time, the data source reliability refers to the ability of the sensor to work without failure under specific conditions, the environmental impact coefficient refers to the degree of influence of environmental factors (such as temperature, humidity, pressure, etc.) on the sensor reading, the factor weight refers to the relative importance of each confidence influencing factor in the overall confidence assessment, the confidence allocation function refers to the algorithm used to calculate the confidence of each data source, and the maximum value of the confidence influencing factor refers to the maximum value that each confidence influencing factor may reach.

[0082] The present invention eliminates conflicts in the multi-source sensor data through the confidence distribution function, and obtains conflict-eliminated data, which can effectively eliminate conflicts in the multi-source sensor data and improve the reliability of the data and the overall performance of the system.

[0083] In detail, performing conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict elimination data includes:

[0084] Analyzing the confidence of the multi-source sensor data using the confidence allocation function;

[0085] Determining, based on the multi-source sensing data, a heat transfer coefficient, an effective heat transfer area, a temperature difference, and a radiation heat transfer term of a temperature transmitter corresponding to the multi-source sensing data;

[0086] Analyzing the energy deviation value of the temperature transmitter through the heat transfer coefficient, effective heat transfer area, temperature difference and radiation heat transfer term;

[0087] analyzing data conflicts of the multi-source sensing data according to the energy deviation value;

[0088] Conflict elimination is performed on the multi-source sensor data based on the data conflict and the confidence level to obtain conflict-eliminated data.

[0089] Among them, the confidence level refers to a quantitative indicator of the reliability of each data source, reflecting the credibility of the sensor data under the current working conditions; the heat transfer coefficient refers to a physical quantity that characterizes the efficiency of heat conduction / conduction; the effective heat transfer area refers to the actual surface area of ​​the temperature transmitter involved in heat exchange; the temperature difference refers to the temperature gradient between the temperature transmitter and the environment or adjacent components; the radiation heat transfer term refers to the radiation energy calculated by the Stefan-Boltzmann law, which is proportional to the surface emissivity and the fourth power of the temperature; the energy deviation value refers to the absolute difference between the measured heat change rate and the value predicted by the theoretical model; the data conflict refers to the inconsistency between multi-source data that violates physical or statistical laws; the conflict elimination data refers to the fused data with data conflicts removed after confidence weighting and physical verification of multi-source sensor data.

[0090] Furthermore, analyzing the energy deviation value of the temperature transmitter by using the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term includes:

[0091] The heat transfer rate of the temperature transmitter is calculated using the following formula based on the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term:

[0092] ;

[0093] in, Indicates the heat conversion rate of the temperature transmitter, represents the heat transfer coefficient, represents the effective heat transfer area, Indicates the temperature difference, represents the radiation heat transfer term, represents the Stefan-Boltzmann constant, represents the surface emissivity, represents the radiating surface area, Indicates the absolute surface temperature;

[0094] An energy deviation value of the temperature transmitter is calculated based on the actual heat change rate measured in advance and the heat conversion rate.

[0095] The heat conversion rate refers to the rate of change of thermal energy predicted by the theoretical model, the actual heat change rate refers to the change in heat flow directly calculated from the temperature transmitter measurement value, the Stefan-Boltzmann constant refers to the proportionality constant of the blackbody radiation law, typically 5.67×10−8W / m2⋅K4, the surface emissivity refers to the ratio of the surface radiation capacity of the temperature transmitter material to that of an ideal blackbody, the radiative surface area refers to the effective surface area involved in thermal radiation, and the absolute surface temperature refers to the Kelvin temperature at the temperature transmitter measurement point.

[0096] S2. Extract the cross-modal correlation feature matrix of the conflict elimination data, determine the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework of the temperature transmitter, and construct a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework.

[0097] The cross-modal correlation feature matrix extracted from the conflict elimination data in the present invention can provide a data basis for subsequent fault analysis.

[0098] In detail, extracting the cross-modal correlation feature matrix of the conflict resolution data includes:

[0099] Establishing a coordinate system transformation matrix for the conflict elimination data;

[0100] Performing spatial registration on the conflict elimination data according to the coordinate system conversion matrix to obtain registration data;

[0101] extracting unimodal features of the registration data;

[0102] Constructing a graph structure of the unimodal feature;

[0103] A cross-modal correlation feature matrix of the conflict resolution data is constructed through the graph structure.

[0104] Among them, the coordinate system conversion matrix refers to the transformation matrix that describes the spatial relationship between measurement data of different sensors, which includes rotation and translation parameters. The registration data refers to multi-source data after spatial alignment to ensure that all sensor data are in the same coordinate system. The single modal feature refers to the time domain / frequency domain / statistical features extracted from a single sensor data. The graph structure refers to the topological structure that represents the correlation relationship between modalities, with nodes as feature vectors and edge weights reflecting coupling strength. The cross-modal correlation feature matrix refers to a matrix that quantifies the nonlinear relationship between multimodal features and is used for comprehensive fault diagnosis.

[0105] Optionally, the graph structure for constructing the unimodal features can be constructed through a graph attention network.

[0106] The present invention determines that the thermodynamic transfer sub-equations of the temperature transmitter and the LSTM-PHY joint modeling framework can establish a model that combines deep learning and physical knowledge, which can more accurately predict the behavior of the temperature transmitter and improve the understanding of complex thermodynamic processes.

[0107] In detail, the thermodynamic transfer sub-equations and LSTM-PHY joint modeling framework for determining the temperature transmitter include:

[0108] dividing the temperature transmitter into a plurality of control volumes;

[0109] determining heat balance equations for the plurality of control volumes;

[0110] According to the heat balance equation, construct the thermodynamic transfer sub-equation of the temperature transmitter;

[0111] Determine the LSTM-PHY network structure of the temperature transmitter;

[0112] The thermodynamic transfer sub-equation is integrated into the LSTM-PHY network structure to obtain the LSTM-PHY joint modeling framework of the temperature transmitter.

[0113] Among them, the multiple control volumes refer to the fact that in a temperature transmitter, dividing the device into multiple control volumes means treating different parts of the transmitter (such as sensor elements, electronic components, housing, etc.) as independent volume units. The heat balance equation refers to an equation that describes how heat is exchanged through conduction, convection and radiation within a control volume, and how it interacts with other forms of energy within the system. The thermodynamic transfer sub-equation refers to an equation that describes how heat is transferred between multiple control volumes. The LSTM-PHY network structure refers to a neural network structure that combines a long short-term memory network (LSTM) and a physical model (PHY). The LSTM-PHY joint modeling framework refers to an integrated framework that combines the sequence data processing capabilities of the LSTM network and the physical model.

[0114] Furthermore, the thermodynamic transfer sub-equation of the temperature transmitter is constructed according to the heat balance equation, including:

[0115] According to the thermal balance equation, the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency and damping ratio of the temperature transmitter are analyzed;

[0116] Based on the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency and damping ratio, the thermodynamic transfer sub-equation of the temperature transmitter is constructed using the following formula, wherein the thermodynamic transfer sub-equation is:

[0117] ;

[0118] in, represents the thermodynamic transfer sub-equation, represents the time constant, Represents pure delay time, represents the Laplace variable, represents the exponential function, represents the thermoelastic coupling coefficient, represents the damping ratio, Indicates the natural frequency of mechanical vibration.

[0119] Among them, the time constant refers to the time required for the system response to reach 63.2% of its final value, which reflects the speed of the thermal dynamic characteristics of the temperature transmitter system. The pure delay time refers to the time lag between the input change and the start of the system response change. The thermoelastic coupling coefficient describes the degree of change in mechanical stress and strain caused by temperature change. The mechanical vibration natural frequency refers to the frequency of free vibration of the system in the absence of external force. The damping ratio refers to the ratio of the damping force to the critical damping force, which determines the speed of vibration decay. The Laplace variable refers to a complex variable used in the Laplace transform to convert the differential equation in the time domain into an algebraic equation in the frequency domain.

[0120] The present invention constructs a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer equations and the LSTM-PHY joint modeling framework. This model combines the traditional accuracy of physical models with the predictive capabilities of deep learning models, providing a powerful analysis and optimization tool for temperature transmitters. The hybrid digital twin model is a composite model that integrates the thermodynamic transfer equations (physical model) and the LSTM-PHY joint modeling framework (data-driven model). Specifically, the hybrid digital twin model is implemented by integrating the thermodynamic transfer equations and the LSTM-PHY joint modeling framework into a pre-built digital twin framework.

[0121] S3. Simulate the normal operating condition of the temperature transmitter through the hybrid digital twin model, and analyze the behavioral deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix.

[0122] It should be explained that the normal operating condition refers to inputting multi-source sensor data into the hybrid digital twin model to simulate the scenario behavior state of the normal operation of the temperature transmitter.

[0123] The present invention analyzes the behavioral deviation of the temperature transmitter based on the normal operating conditions and the cross-modal correlation feature matrix, and can systematically analyze the deviation of the temperature transmitter, thereby realizing monitoring and maintenance of equipment performance.

[0124] In detail, analyzing the behavior deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix includes:

[0125] Analyzing characteristic distribution of the normal operating condition;

[0126] Normalizing the cross-modal correlation feature matrix to obtain a normalized correlation feature matrix;

[0127] defining a deviation index of the temperature transmitter;

[0128] The behavior deviation of the temperature transmitter is analyzed based on the deviation index, the normalized correlation feature matrix, and the feature distribution.

[0129] Among them, the feature distribution refers to the statistical characteristics of the feature values ​​extracted from the data, including but not limited to the mean, median, standard deviation, variance, distribution shape (such as normal distribution, skewed distribution), range, quartiles, etc. The standardized correlation feature matrix refers to a matrix that performs mathematical transformation on the cross-modal correlation feature matrix, in which the eigenvalues ​​have been adjusted to a common scale so that different features can be directly compared. The deviation index refers to the elements in the feature matrix that are significantly different from normal operating conditions, including indicators such as abnormal temperature changes, abnormal current harmonics, and abnormal vibration amplitude. The behavioral deviation refers to the difference between the actual behavior of the temperature transmitter and the expected normal behavior.

[0130] Optionally, the analysis of the characteristic distribution of the normal operating condition may be performed by statistical methods.

[0131] S4. Construct a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer. According to the behavioral deviation, the hierarchical collaborative network is used to analyze the multi-layer fault analysis results of the temperature transmitter.

[0132] The present invention constructs a hierarchical collaborative network of the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer to build an efficient and reliable hierarchical collaborative network for real-time monitoring, data analysis, and intelligent control of the temperature transmitter.

[0133] In detail, the construction of the hierarchical collaborative network of the temperature transmitter includes:

[0134] Constructing a hierarchical collaborative structure of the temperature transmitter, wherein the hierarchical collaborative structure includes an edge layer structure, a fog node layer structure, and a cloud layer structure;

[0135] Performing network integration on the edge layer structure, fog node layer structure, and cloud layer structure to obtain a hierarchical collaborative network structure;

[0136] Defining collaborative analysis rules for the hierarchical collaborative network structure;

[0137] Analyzing the interoperability between layers of the hierarchical collaborative network structure;

[0138] When the inter-layer interoperability meets a preset inter-layer interoperability threshold, a hierarchical collaborative network of the temperature transmitter is constructed based on the hierarchical collaborative network structure and the collaborative analysis rule.

[0139] Among them, the edge layer structure refers to the computing and storage resources located near the data source (such as temperature transmitter), which is responsible for collecting data, performing local processing and preliminary analysis; the fog node layer structure refers to the intermediate layer located between the edge layer and the cloud, which usually contains relatively strong computing power and storage capacity, used to process data from the edge layer and perform more complex computing tasks; the cloud layer structure refers to the high-performance computing and storage resources at the top layer of the network, which is responsible for storing large amounts of data, performing complex data analysis and machine learning model training; the hierarchical collaborative network structure refers to the network architecture that integrates the edge layer, fog node layer and cloud layer, which can realize distributed processing and analysis of data, as well as effective management of resources. Analysis rules refer to a set of rules that define how different network layers collaborate to perform analysis and make decisions, including data transmission protocols, data processing procedures, and the selection of analysis models. Inter-layer interoperability refers to the ability of different network layers (edge ​​layer, fog node layer, and cloud layer) to effectively communicate and collaborate, including data exchange, control instruction transmission, and task coordination. Inter-layer interoperability thresholds refer to interoperability performance standards set to ensure the normal operation of the network, such as the minimum requirements for indicators such as data transmission delay, bandwidth, and reliability. The layered collaborative network refers to a network system that integrates the edge layer, fog node layer, and cloud layer. It can realize real-time data collection, distributed processing, and intelligent decision-making to improve the monitoring and control efficiency of temperature transmitters.

[0140] The present invention utilizes the hierarchical collaborative network to analyze the multi-layer fault analysis results of the temperature transmitter, effectively improving the accuracy and efficiency of fault diagnosis. The multi-layer fault analysis results refer to the output of fault diagnosis and analysis of the temperature transmitter at different network layers (edge ​​layer, fog node layer, and cloud layer). These multi-layer fault analysis results include fault diagnosis (fault diagnosis information derived from data analysis at each layer, such as fault type, occurrence time, and duration); fault mode (fault occurrence patterns identified through data analysis); fault cause (fault root cause inference, which may include equipment aging, environmental factors, operational errors, etc.); and fault impact (fault impact assessment of the impact of the fault on the performance of the temperature transmitter and overall system operation).

[0141] S5. Determine the fault optimization parameters of the temperature transmitter based on the multi-layer fault analysis results, and perform fault diagnosis of the intelligent temperature transmitter based on the fault optimization parameters.

[0142] The present invention determines the fault optimization parameters of the temperature transmitter based on the multi-layer fault analysis results, effectively optimizing the fault parameters of the temperature transmitter and improving its reliability and operational efficiency. The fault optimization parameters are a series of parameters adjusted to reduce the frequency of faults, minimize their impact, and improve equipment reliability and maintenance efficiency. These parameters include threshold settings, warning conditions, maintenance cycles, and other parameters.

[0143] Compared with the problems described in the background technology, first, the confidence allocation function of multi-source sensor data effectively eliminates data conflicts and improves data quality and reliability. By integrating temperature signal time series data, power supply current harmonic characteristic data, equipment vibration spectrum data and environmental parameters, more comprehensive and accurate equipment status information is obtained. Secondly, the extraction of cross-modal correlation feature matrix, combined with thermodynamic transfer sub-equations and LSTM-PHY joint modeling framework, enables the hybrid digital twin model to accurately simulate the normal operating conditions of the temperature transmitter, providing strong support for behavioral deviation analysis. Thirdly, the construction of a hierarchical collaborative network realizes distributed processing and intelligent analysis of data, improving the efficiency and accuracy of fault diagnosis. The collaborative work of the edge layer, fog node layer and cloud layer makes the fault analysis results more comprehensive and in-depth, providing a scientific basis for fault prevention and maintenance decisions. In addition, the fault optimization parameters determined based on the multi-layer fault analysis results effectively guide the fault diagnosis of the intelligent temperature transmitter. The optimization of these parameters helps to reduce the failure rate, extend the equipment life and reduce maintenance costs. Finally, the application of the entire method significantly improves the operational reliability of the temperature transmitter and ensures the continuity and safety of the production process. Therefore, the present invention can improve the fault analysis efficiency of the temperature transmitter.

[0144] Example 2:

[0145] like Figure 2 FIG. 1 is a functional module diagram of a remote fault diagnosis system for an intelligent temperature transmitter according to the present invention.

[0146] The intelligent temperature transmitter remote fault diagnosis system 200 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the intelligent temperature transmitter remote fault diagnosis system may include a data conflict resolution module 201, a twin model construction module 202, a behavioral deviation analysis module 203, a multi-layer fault analysis module 204, and a fault parameter optimization module 205. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function. These are stored in the electronic device's memory.

[0147] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0148] The data conflict elimination module 201 is configured to collect multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal timing data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters, define a confidence allocation function for the multi-source sensor data, and perform conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict-resolved data;

[0149] The twin model construction module 202 is used to extract the cross-modal correlation feature matrix of the conflict elimination data, determine the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework of the temperature transmitter, and construct a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework;

[0150] The behavior deviation analysis module 203 is configured to simulate the normal operating condition of the temperature transmitter through the hybrid digital twin model, and analyze the behavior deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix;

[0151] The multi-layer fault analysis module 204 is configured to construct a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer, and analyze the multi-layer fault analysis results of the temperature transmitter using the hierarchical collaborative network based on the behavioral deviation;

[0152] The fault parameter optimization module 205 is configured to determine the fault optimization parameters of the temperature transmitter based on the multi-layer fault analysis results, and perform fault diagnosis of the intelligent temperature transmitter based on the fault optimization parameters.

[0153] In detail, the modules in the intelligent temperature transmitter remote fault diagnosis system 200 according to the embodiment of the present invention are used in the same manner as above. Figure 1 The remote fault diagnosis method of the intelligent temperature transmitter described in the preceding text is the same technical means and can produce the same technical effects, so I will not go into details here.

[0154] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A remote fault diagnosis method for an intelligent temperature transmitter, characterized in that: The method comprises: collecting multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal time series data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters; defining a confidence allocation function for the multi-source sensor data; and performing conflict elimination on the multi-source sensor data using the confidence allocation function to obtain conflict elimination data; Extracting a cross-modal correlation feature matrix of the conflict elimination data, determining a thermodynamic transfer sub-equation of the temperature transmitter and an LSTM-PHY joint modeling framework, wherein determining the thermodynamic transfer sub-equation of the temperature transmitter comprises: dividing the temperature transmitter into a plurality of control volumes; determining a heat balance equation of the plurality of control volumes; and constructing a thermodynamic transfer sub-equation of the temperature transmitter based on the heat balance equation. The step of constructing the thermodynamic transfer sub-equation of the temperature transmitter according to the heat balance equation includes: According to the thermal balance equation, the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency, and damping ratio of the temperature transmitter are analyzed; based on the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency, and damping ratio, the thermodynamic transfer sub-equation of the temperature transmitter is constructed using the following formula, wherein the thermodynamic transfer sub-equation is: ； in, represents the thermodynamic transfer sub-equation, represents the time constant, Represents pure delay time, represents the Laplace variable, represents the exponential function, represents the thermoelastic coupling coefficient, represents the damping ratio, Indicates the natural frequency of mechanical vibration; Constructing a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equations and the LSTM-PHY joint modeling framework; simulating a normal operating condition of the temperature transmitter by using the hybrid digital twin model, and analyzing a behavioral deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix; Constructing a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer, and analyzing multi-layer fault analysis results of the temperature transmitter using the hierarchical collaborative network based on the behavioral deviation; The fault optimization parameters of the temperature transmitter are determined through the multi-layer fault analysis results, and the fault diagnosis of the intelligent temperature transmitter is performed based on the fault optimization parameters.

2. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 1, characterized in that: Defining the confidence distribution function of the multi-source sensor data includes: Preprocessing the multi-source sensor data to obtain processed multi-source sensor data; Analyzing confidence influencing factors of processing multi-source sensor data, wherein the confidence influencing factors include data source accuracy, data source stability, data source reliability, and environmental impact coefficient; Defining factor weights of the confidence influencing factors; Based on the confidence influencing factors and the factor weights, the confidence allocation function of the multi-source sensor data is constructed using the following formula, wherein the confidence allocation function includes: ； in, represents the confidence of the cth data source of multi-source sensor data, Indicates that the cth data source of multi-source sensor data corresponds to the The value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The maximum value of the confidence factor, Indicates that the cth data source of multi-source sensor data corresponds to the The factor weight of the confidence influence factor.

3. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 2, characterized in that: The performing conflict elimination on the multi-source sensor data by using the confidence distribution function to obtain conflict elimination data includes: Analyzing the confidence of the multi-source sensor data using the confidence allocation function; Determining, based on the multi-source sensing data, a heat transfer coefficient, an effective heat transfer area, a temperature difference, and a radiation heat transfer term of a temperature transmitter corresponding to the multi-source sensing data; Analyzing the energy deviation value of the temperature transmitter through the heat transfer coefficient, effective heat transfer area, temperature difference and radiation heat transfer term; analyzing data conflicts of the multi-source sensing data according to the energy deviation value; Conflict elimination is performed on the multi-source sensor data based on the data conflict and the confidence level to obtain conflict-eliminated data.

4. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 3, wherein: Analyzing the energy deviation value of the temperature transmitter by using the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term includes: The heat transfer rate of the temperature transmitter is calculated using the following formula based on the heat transfer coefficient, effective heat transfer area, temperature difference, and radiation heat transfer term: ； in, Indicates the heat conversion rate of the temperature transmitter, represents the heat transfer coefficient, represents the effective heat transfer area, Indicates the temperature difference, represents the radiation heat transfer term, represents the Stefan-Boltzmann constant, represents the surface emissivity, represents the radiating surface area, Indicates the absolute surface temperature; An energy deviation value of the temperature transmitter is calculated based on the actual heat change rate measured in advance and the heat conversion rate.

5. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 4, characterized in that: The extracting of the cross-modal correlation feature matrix of the conflict elimination data includes: Establishing a coordinate system transformation matrix for the conflict elimination data; Performing spatial registration on the conflict elimination data according to the coordinate system conversion matrix to obtain registration data; extracting unimodal features of the registration data; Constructing a graph structure of the unimodal feature; A cross-modal correlation feature matrix of the conflict resolution data is constructed through the graph structure.

6. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 5, characterized in that: Determining the LSTM-PHY joint modeling framework includes: Determine the LSTM-PHY network structure of the temperature transmitter; The thermodynamic transfer sub-equation is integrated into the LSTM-PHY network structure to obtain the LSTM-PHY joint modeling framework of the temperature transmitter.

7. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 6, characterized in that: The analyzing the behavior deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix includes: Analyzing characteristic distribution of the normal operating condition; Normalizing the cross-modal correlation feature matrix to obtain a normalized correlation feature matrix; defining a deviation index of the temperature transmitter; The behavior deviation of the temperature transmitter is analyzed based on the deviation index, the normalized correlation feature matrix, and the feature distribution.

8. The remote fault diagnosis method for an intelligent temperature transmitter according to claim 7, characterized in that: The step of constructing the hierarchical collaborative network of the temperature transmitter includes: Constructing a hierarchical collaborative structure of the temperature transmitter, wherein the hierarchical collaborative structure includes an edge layer structure, a fog node layer structure, and a cloud layer structure; Performing network integration on the edge layer structure, fog node layer structure, and cloud layer structure to obtain a hierarchical collaborative network structure; Defining collaborative analysis rules for the hierarchical collaborative network structure; Analyzing the interoperability between layers of the hierarchical collaborative network structure; When the inter-layer interoperability meets a preset inter-layer interoperability threshold, a hierarchical collaborative network of the temperature transmitter is constructed based on the hierarchical collaborative network structure and the collaborative analysis rule.

9. A remote fault diagnosis system for an intelligent temperature transmitter, characterized in that: The system comprises: a data conflict resolution module configured to collect multi-source sensor data from a temperature transmitter, wherein the multi-source sensor data includes temperature signal timing data, power supply current harmonic characteristic data, equipment vibration spectrum data, and environmental parameters; define a confidence allocation function for the multi-source sensor data; and perform conflict resolution on the multi-source sensor data using the confidence allocation function to obtain conflict resolution data; A twin model construction module is used to extract the cross-modal correlation feature matrix of the conflict elimination data, determine the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework of the temperature transmitter, and construct a hybrid digital twin model of the temperature transmitter based on the thermodynamic transfer sub-equation and LSTM-PHY joint modeling framework. The determination of the thermodynamic transfer sub-equation of the temperature transmitter includes: dividing the temperature transmitter into multiple control volumes; determining the thermal balance equations of the multiple control volumes; and constructing the thermodynamic transfer sub-equation of the temperature transmitter based on the thermal balance equation. The construction of the thermodynamic transfer sub-equation of the temperature transmitter based on the thermal balance equation includes: analyzing the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency, and damping ratio of the temperature transmitter based on the thermal balance equation; and constructing the thermodynamic transfer sub-equation of the temperature transmitter based on the time constant, pure delay time, thermoelastic coupling coefficient, mechanical vibration natural frequency, and damping ratio using the following formula. ； in, represents the thermodynamic transfer sub-equation, represents the time constant, Represents pure delay time, represents the Laplace variable, represents the exponential function, represents the thermoelastic coupling coefficient, represents the damping ratio, Indicates the natural frequency of mechanical vibration; a behavioral deviation analysis module, configured to simulate a normal operating condition of the temperature transmitter through the hybrid digital twin model, and analyze the behavioral deviation of the temperature transmitter based on the normal operating condition and the cross-modal correlation feature matrix; a multi-layer fault analysis module, configured to construct a hierarchical collaborative network for the temperature transmitter, wherein the hierarchical collaborative network includes an edge layer, a fog node layer, and a cloud layer, and to analyze the multi-layer fault analysis results of the temperature transmitter using the hierarchical collaborative network based on the behavioral deviation; A fault parameter optimization module is used to determine the fault optimization parameters of the temperature transmitter through the multi-layer fault analysis results, and perform fault diagnosis of the intelligent temperature transmitter based on the fault optimization parameters.

Images