Intelligent diagnosis method and system for pressure transmitter

By laying a measurement array of multiple pressure transmitters and redundant transmitters in the pressure measurement system, using the Industrial Internet of Things for real-time abnormality detection and fault isolation, a multi-dimensional fault detection strategy is pre-built to solve pressure transmitter failures The rapid positioning and handling of problems has improved the reliability and efficiency of industrial production.

CN118706326BActive Publication Date: 2024-11-08TIANJIN WANZHONG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411186601.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-08
Estimated Expiration
2044-08-28

AI Technical Summary

Technical Problem

In the prior art, the pressure measurement system detects abnormalities of the pressure transmitter in a timely and inaccurate manner, and it is difficult to locate and isolate the fault. The troubleshooting strategy is single and lacks systematic, so it is impossible to effectively prevent similar faults from occurring on other transmitters. This results in the impact of the accuracy, continuity and stability of pressure measurement in industrial production.

Method used

By laying a measurement array of multiple pressure transmitters and redundant transmitters in the target industrial scenario, the industrial Internet of Things receives output signals in real time, detects abnormalities and locates risk transmitters, isolates risk transmitters and activates redundant transmitters The transmitter performs temporary measurements, pre-built a multi-dimensional fault detection strategy for troubleshooting, and if the result is not empty, analyze the cause of the fault and update the measurement array.

Benefits of technology

It realizes rapid positioning and handling of pressure measurement faults, reduces production risks and losses, and improves the reliability and operating efficiency of industrial production systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118706326B_ABST
    Figure CN118706326B_ABST
Patent Text Reader

Abstract

The present invention discloses an intelligent diagnosis method and system for pressure transmitters, which relates to the field of industrial automation control and monitoring technology. The method includes: deploying a measurement array containing multiple pressure transmitters and redundant transmitters in a target industrial scene, receiving output signals in real time based on the industrial Internet of Things, detecting anomalies to locate risk transmitters, isolating risk transmitters and activating temporary measurements of redundant transmitters, pre-building a multi-dimensional strategy to troubleshoot and obtain identification results, and if the result is not empty, analyzing the cause of the fault to obtain environmental information, interactively obtaining the device model to troubleshoot hidden dangers and obtain an updated array. The method solves the technical problems of untimely and inaccurate detection of pressure transmitter anomalies in existing pressure measurement systems, difficulty in fault location and isolation, and difficulty in ensuring the accuracy and continuity of pressure measurement in industrial production, and achieves the technical effect of reducing production risks and losses caused by pressure measurement failures and improving the reliability and operating efficiency of the entire industrial production system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of industrial automation control and monitoring technology, and in particular to an intelligent diagnosis method and system for a pressure transmitter. Background Art

[0002] In the pressure measurement scenario of industrial production, it is extremely critical to ensure the accuracy and reliability of pressure measurement. The impact of pressure transmitter failure is becoming more and more significant. Timely and effective diagnosis and resolution of pressure transmitter problems have become an important part of ensuring the stable operation of industrial production. Traditional pressure transmitter management methods usually have many defects, such as insufficient real-time and comprehensive monitoring, limited detection and diagnosis capabilities for transmitter failures, difficulty in adapting to complex and changing industrial environments, lack of comprehensive analysis and utilization of transmitter operation data, and inability to accurately locate potential faults. In terms of fault handling, the methods are not scientific and efficient enough, resulting in long troubleshooting time and affecting production efficiency. The maintenance plan for pressure transmitters is not flexible enough and it is difficult to cope with the ever-changing pressure measurement needs in industrial production.

[0003] In the current relevant technologies, the abnormal detection of pressure transmitters in the pressure measurement system is not timely and accurate, fault location and isolation are difficult, the troubleshooting strategy is single and lacks systematicity, and insufficient consideration of environmental factors leads to the inability to effectively prevent similar faults from occurring in other transmitters, making it difficult to ensure the accuracy, continuity and stability of pressure measurement in industrial production. Summary of the invention

[0004] The present application provides an intelligent diagnosis method and system for pressure transmitters, deploys a measurement array containing multiple pressure transmitters and redundant transmitters in the target industrial scenario, receives output signals in real time based on the industrial Internet of Things, detects anomalies to locate risk transmitters, isolates risk transmitters and activates temporary measurements of redundant transmitters, pre-builds a multi-dimensional strategy to troubleshoot and obtain identification results, analyzes the cause of the fault if the result is not empty, obtains environmental information through interactive acquisition of equipment models to troubleshoot hidden dangers and obtains an updated array, thereby achieving the technical effect of reducing production risks and losses caused by pressure measurement failures and improving the reliability and operating efficiency of the entire industrial production system.

[0005] The present application provides an intelligent diagnosis method for a pressure transmitter, comprising:

[0006] A pressure measurement array is deployed in a target industrial scene, wherein the pressure measurement array includes multiple pressure transmitters and multiple redundant transmitters; output signals are received in real time based on the industrial Internet of Things to obtain multiple output signals of the multiple pressure transmitters; abnormality detection is performed on the multiple output signals, and the risk transmitter is located among the multiple pressure transmitters based on the detection results; fault isolation is performed on the risk transmitter, and the target redundant transmitter is activated according to the mapping of the risk transmitter to the multiple redundant transmitters to perform temporary measurement on the target industrial scene; a multi-dimensional fault detection strategy is pre-constructed, and the risk transmitter is troubleshooted according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result; if the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain an environment-related information set; the device model information of the risk transmitter is interactively obtained, and the transmitter hidden danger inspection of the pressure measurement array is performed according to the device model information and the environment-related information to obtain an updated measurement array.

[0007] The present application also provides an intelligent diagnostic system for a pressure transmitter, comprising:

[0008] A pressure measurement array deployment module, the pressure measurement array deployment module is used to deploy a pressure measurement array in a target industrial scene, wherein the pressure measurement array includes multiple pressure transmitters and multiple redundant transmitters; an output signal acquisition module, the output signal acquisition module is used to receive output signals in real time based on the industrial Internet of Things, and obtain multiple output signals of the multiple pressure transmitters; an anomaly detection module, the anomaly detection module is used to perform anomaly detection on the multiple output signals, and locate the risk transmitter among the multiple pressure transmitters based on the detection results; a fault isolation module, the fault isolation module is used to perform fault isolation on the risk transmitter, and activate the target redundant transmitter to the target industrial scene according to the mapping of the risk transmitter in the multiple redundant transmitters The present invention relates to a transmitter fault identification result acquisition module, wherein the transmitter fault identification result acquisition module is used to pre-build a multi-dimensional fault detection strategy, and troubleshoot the risk transmitter according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result; an environment-related information set acquisition module, wherein the environment-related information set acquisition module is used to analyze the cause of the fault of the risk transmitter if the transmitter fault identification result is a non-empty set, and obtain an environment-related information set; an update measurement array acquisition module, wherein the update measurement array acquisition module is used to interactively obtain the device model information of the risk transmitter, and perform a transmitter hidden danger inspection on the pressure measurement array according to the device model information and the environment-related information to obtain an updated measurement array.

[0009] The intelligent diagnosis method and system for pressure transmitters proposed in this application first deploys a measurement array containing multiple pressure transmitters and redundant transmitters in the target industrial scenario, receives output signals in real time based on the industrial Internet of Things, detects anomalies to locate risk transmitters, isolates risk transmitters and activates temporary measurements of redundant transmitters, pre-builds a multi-dimensional strategy to troubleshoot and obtain identification results, and if the result is not empty, analyzes the cause of the fault to obtain environmental information, interactively obtains equipment models to troubleshoot hidden dangers and obtains an updated array, thereby achieving the technical effect of reducing production risks and losses caused by pressure measurement failures and improving the reliability and operation efficiency of the entire industrial production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as required. At the same time, other operations can also be added to these processes, or a certain step or several steps of operations can be removed from these processes.

[0011] Figure 1 A flow chart of an intelligent diagnosis method for a pressure transmitter provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of an intelligent diagnostic system for a pressure transmitter provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: pressure measurement array layout module 10 , output signal acquisition module 20 , anomaly detection module 30 , fault isolation module 40 , transmitter fault identification result acquisition module 50 , environment-related information set acquisition module 60 , updated measurement array acquisition module 70 . DETAILED DESCRIPTION

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0017] The present application embodiment provides an intelligent diagnosis method for a pressure transmitter, such as Figure 1 As shown, the method includes:

[0018] Step S100, deploy a pressure measurement array in the target industrial scene, wherein the pressure measurement array includes multiple pressure transmitters and multiple redundant transmitters. Specifically, the pressure measurement array refers to a combination of equipment deployed in the target industrial scene for measuring pressure. Select the target industrial scene, clarify the measurement requirements, prepare pressure transmitters and redundant transmitters, set installation parameters, such as the measurement range, accuracy requirements, installation location, etc. of the transmitter, start installation and deployment, and obtain preliminary installation location layout data. The preliminary installation location layout data represents the transmitter installation location preliminarily determined according to the scene and requirements, and its characteristics are preliminary planning. Continue to improve the installation deployment and obtain the final installation location determination data. The final installation location determination data represents the precise installation location after adjustment and optimization, and its characteristics are precise positioning. After completing the installation of all transmitters, conduct a comprehensive inspection and acceptance.

[0019] Step S200, based on the industrial Internet of Things, real-time reception of output signals is performed to obtain multiple output signals of the multiple pressure transmitters. Specifically, establishing a connection with multiple pressure transmitters in the industrial Internet of Things system involves network configuration of each pressure transmitter, including setting its IP address, communication protocol and other parameters to ensure that they can effectively interact with the Internet of Things system. At the system level, a platform and infrastructure for data reception must be built, including servers, databases, and related data processing software and algorithms. When the pressure transmitter starts working and generates an output signal, the signal will be sent to the industrial Internet of Things system through various communication methods (such as wireless transmission, wired network, etc.). The receiving module in the Internet of Things system will always be in a listening state. Once a signal from the pressure transmitter is received, it will be immediately parsed and processed. During the parsing process, the system will convert the received raw data into an understandable and processable form according to the pre-set format and encoding rules. In order to ensure the accuracy and integrity of the data, the system will perform data verification. For example, the system checks whether the length and format of the data are as expected, and whether there are any missing or erroneous parts. For the output signals of multiple pressure transmitters, the system will classify and mark them so that the data sent by each transmitter can be clearly distinguished. The received output signals will be stored in the database in real time for subsequent analysis and processing. The system constantly monitors the quality and stability of communication. If there is a signal interruption, delay or other abnormal situation, an alarm will be issued in time and corresponding measures will be taken, such as reconnecting, requesting retransmission of data, etc.

[0020] Step S300, perform anomaly detection on the multiple output signals, and locate the risky transmitter among the multiple pressure transmitters based on the detection results. Specifically, the output signals of multiple pressure transmitters are obtained, and these output signals are comprehensively analyzed using specially designed anomaly detection algorithms and models. Anomaly detection is considered from multiple aspects, for example, the current signal is compared with the pattern and characteristics of historical normal signals, including the mean, variance, periodicity, trend, etc. of the signal, and the signal is checked for sudden large fluctuations, spikes, abnormal continuous stability or irregular noise. For each output signal, a series of indicators for measuring its degree of abnormality are calculated. The indicators combine multiple characteristics and statistics of the signal, and determine whether it is abnormal based on a preset threshold. During the detection process, the correlation and consistency between multiple output signals are also considered. If a pressure transmitter The output signal of the pressure transmitter shows significant differences from the signals of other related transmitters. According to the results of abnormality detection, each pressure transmitter is evaluated. The pressure transmitter whose output signal is judged to be abnormal and exceeds a certain severity is positioned as a risk transmitter. When positioning the risk transmitter, not only the abnormality of a single signal is considered, but also its position, function and relationship with other transmitters in the entire pressure measurement system are considered for comprehensive judgment. For example, if in a chemical production process, the output signal of a pressure transmitter at a key link shows a fluctuation that obviously deviates from the normal range, after abnormality detection and comprehensive evaluation, it will be positioned as a risk transmitter for subsequent more in-depth fault diagnosis and processing.

[0021] In a possible implementation, the multiple output signals are detected for abnormalities, and the risk transmitter is located among the multiple pressure transmitters based on the detection results. Step S300 further includes step S310, pre-building a signal abnormality detection unit, and performing abnormality detection on the multiple output signals through the signal abnormality detection unit to obtain multiple signal abnormality coefficients. Specifically, a signal identifier is constructed based on a signal processing algorithm, for example, a fast Fourier transform algorithm is used to identify the frequency components of the signal, and a peak detection algorithm is used to determine the peak and valley values ​​of the signal. The constructed signal identifier is synchronized to the signal recognition layer of the signal abnormality detection unit, and a signal abnormality evaluation function is introduced in the signal abnormality calculation layer. After the construction of the signal abnormality detection unit is completed, multiple output signals are input into the unit one by one, and the signal features are extracted through the signal recognition layer, and then the signal abnormality calculation layer is calculated according to the evaluation function, so as to obtain a signal abnormality coefficient for each output signal that can reflect its degree of abnormality.

[0022] Step S320, performing stability detection on the multiple output signals to obtain multiple signal stability coefficients. Specifically, for each output signal, analyze its change trend over a period of time, calculate the signal's variance, coefficient of variation, or evaluate stability by comparing the differences between adjacent data points. If the signal changes slightly and is relatively stable, its stability coefficient is high; conversely, if the signal has large fluctuations or unstable changes, the stability coefficient is low, and a signal stability coefficient is obtained for each output signal.

[0023] Step S330, based on the preset weight configuration, the multiple signal abnormality coefficients and the multiple signal stability coefficients are weightedly calculated to obtain multiple transmitter abnormality coefficients. Specifically, according to the degree of emphasis on signal abnormality and stability, the weight value is set in advance. For example, if more attention is paid to the abnormality of the signal, a higher weight may be set for the signal abnormality coefficient; if stability is equally important, a relatively balanced weight is assigned to it, and the signal abnormality coefficient and signal stability coefficient corresponding to each output signal are weighted and summed according to the preset weights. Through weighted calculation, the abnormality degree and stability of the signal are comprehensively considered, and a transmitter abnormality coefficient that can more comprehensively reflect its condition is obtained for each pressure transmitter.

[0024] Step S340, serialize the abnormal coefficients of the multiple transmitters, and locate the risk transmitter among the multiple pressure transmitters according to the extreme value of the serialization result. Specifically, the calculated abnormal coefficients of the multiple transmitters are arranged in order from large to small or from small to large. If they are arranged from large to small, the pressure transmitter corresponding to the maximum value may be considered to be the most risky; if they are arranged from small to large, the pressure transmitter corresponding to the minimum value may be the most risky. According to the extreme value of the serialization result, the risk transmitter can be accurately located among the many pressure transmitters for subsequent focus and processing.

[0025] In a possible implementation, a signal anomaly detection unit is pre-constructed, and the multiple output signals are subjected to anomaly detection by the signal anomaly detection unit to obtain multiple signal anomaly coefficients. Step S310 further includes step S311, and the signal anomaly detection unit includes a cascaded signal recognition layer and a signal anomaly calculation layer. Specifically, the signal anomaly detection unit is composed of two key parts, namely, a signal recognition layer and a signal anomaly calculation layer. The signal recognition layer is mainly responsible for preliminary feature extraction and analysis of the input output signal, such as identifying basic features such as peak values, valley values, and frequencies of the signal. The signal anomaly calculation layer further uses specific calculation methods and rules to evaluate the degree of abnormality of the signal based on the feature information provided by the signal recognition layer.

[0026] Step S312, pre-build a signal identifier based on the signal processing algorithm, and synchronize the signal identifier to the signal recognition layer. Specifically, based on mature signal processing algorithms, such as wavelet transform algorithm, Kalman filter algorithm, etc., a signal identifier that can accurately extract signal features is pre-built, and the signal identifier can capture key feature information in the output signal, such as mutation points, periodic changes, etc. After the construction is completed, this signal identifier is synchronized with the signal recognition layer of the signal anomaly detection unit to ensure that the signal recognition layer can use this identifier to effectively process the input output signal.

[0027] Step S313, introduce a signal anomaly evaluation function into the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit. Specifically, a specially designed signal anomaly evaluation function is introduced into the signal anomaly calculation layer. By introducing the function, the signal anomaly calculation layer can calculate the abnormality value of the signal using the evaluation function according to the features provided by the signal recognition layer. At this point, the construction of the entire signal anomaly detection unit is completed.

[0028] Step S314, synchronize the multiple output signals to the signal anomaly detection unit, perform anomaly detection via the signal recognition layer and the signal anomaly calculation layer, and obtain the multiple signal anomaly coefficients. Specifically, the multiple output signals generated by the multiple pressure transmitters are simultaneously transmitted to the constructed signal anomaly detection unit, and the signals enter the signal recognition layer, and the synchronized signal identifier extracts and preliminarily analyzes the signals. The processed feature information is transmitted to the signal anomaly calculation layer, and the introduced anomaly evaluation function is used for calculation and evaluation, and a signal anomaly coefficient that can quantify the degree of anomaly is obtained for each input output signal. For example, in a pressure monitoring scenario of an electric power system, the output signals of multiple pressure transmitters are input to the signal anomaly detection unit, and after the above-mentioned layer-by-layer processing, the anomaly coefficient of each signal is obtained, so that the pressure transmitter that may have an abnormality can be quickly and accurately found.

[0029] In a possible implementation, a signal identifier is pre-constructed based on a signal processing algorithm, and the signal identifier is synchronized to the signal identification layer. Step S312 further includes step S3121, and the identification types of the signal identifier include signal peak extreme value, signal valley extreme value, peak value, valley value, and peak-valley time interval. Specifically, when constructing a signal identifier, it is clear that multiple types need to be identified. For the identification of the signal peak extreme value, the entire signal will be monitored comprehensively and continuously. During the monitoring process, the signal value at each moment is recorded, and it is continuously compared and updated to find the positive value with the largest absolute value in the entire signal propagation process. The peak extreme value is a key indicator for evaluating the stability of signal propagation. If the peak extreme value remains relatively stable for a period of time, or its change is within an acceptable range, it indicates that the signal propagation is relatively stable; on the contrary, if the peak extreme value fluctuates frequently and greatly, it means that the signal propagation may be unstable. The identification of the signal valley extreme value is similar to the peak extreme value, but it is to find the negative value with the largest absolute value in the signal propagation process. Similarly, by observing the changes in the valley extremes, we can understand the extreme performance of the signal in the negative direction and its stability. The identification of the peak focuses on the maximum value of the signal in the positive direction. For periodic signals, detection is performed in each cycle, and when the signal reaches the maximum positive value, it is confirmed as the peak. By analyzing the peak value, we can understand the strength performance of the signal in the positive direction, and the identification of the valley value is aimed at the minimum value of the signal in the negative direction. In each cycle, when the signal drops to the minimum negative value, it is identified as a valley value. The valley value reflects the intensity limit of the signal in the negative direction. The identification of the peak-valley time interval requires accurate recording of the specific time points when the peak and valley values ​​appear. During the signal propagation process, whenever a peak and valley value are detected, the corresponding time is recorded at the same time. Then, by calculating the time difference between adjacent peaks and valleys, the peak-valley time interval is obtained. The analysis of these time intervals can reveal the time law of the signal intensity change. If the peak extreme value fluctuation is found to be abnormal, or the peak-valley time interval does not meet expectations, it can be judged that the circuit may have a fault or interference, so that corresponding maintenance and optimization measures can be taken to ensure the normal transmission of the signal and the stable operation of the system.

[0030] In a possible implementation, a signal anomaly evaluation function is introduced into the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit. Step S313 further includes step S3131, and the signal anomaly evaluation function is as follows: ,in, is the signal anomaly coefficient, is the signal peak value, is the signal valley extreme value, For the Peak value, For the A valley value, is the number of adjacent peak-valley pairs, For the The time point of the peak value, For the The time node of the valley value, is the maximum peak-to-valley weight, is the adjacent peak-to-valley amplitude weight, is the time weight of adjacent peaks and valleys. Specifically, the signal peak extreme value ( ) and signal valley extremes ( ) represent the maximum peak value and minimum valley value of the entire signal respectively. , we can get the maximum peak-to-valley degree of the signal, which reflects the extreme change degree of the signal in amplitude. For each pair of adjacent peaks ( ) and valley value ( ), and calculate their difference ( ), sum all the differences and divide by the number of adjacent peak-to-valley pairs ( ), the average difference of adjacent peak-to-valley amplitudes is obtained. The indicator reflects the average amplitude change of the signal between adjacent peaks and valleys. For each pair of adjacent peaks ( ) and valley value ( ), calculate their difference and divide it by the time nodes corresponding to the peak and valley values ​​( and ), sum all the results and divide by , and get the average impact of adjacent peak-valley time changes. The indicator takes into account the changing characteristics of the signal in the time dimension, analyzes each weight, and the maximum peak-valley weight ( ) is used to adjust the importance of the maximum peak-to-valley degree in the overall signal anomaly coefficient. If Larger, indicating that more attention is paid to the impact of extreme amplitude changes of the signal on the degree of abnormality, and the adjacent peak-valley amplitude weights ( ) determines the contribution of the average difference in adjacent peak-to-valley amplitudes to the signal anomaly coefficient. This means that the average amplitude change between adjacent peaks and valleys plays a more important role in evaluating anomalies, and the time weight of adjacent peaks and valleys ( ) affects the proportion of the average influence of the adjacent peak-to-valley time changes in the signal anomaly coefficient. The effect of time factor on the degree of signal anomaly is emphasized. ), first calculate the values ​​of the above three parts separately, and then perform weighted summation according to their corresponding weights. For example, in a pressure monitoring system, if a signal Larger, Smaller, and Higher, then will be large, indicating that the signal may have a large anomaly. is also larger, which will also make If the time variation characteristics of adjacent peaks and valleys are obvious, and Larger, will also increase Through such function design and weight configuration, the characteristics of the signal in terms of amplitude, difference between adjacent peak-to-valley values, and time change can be comprehensively considered to comprehensively and accurately evaluate the degree of abnormality of the signal.

[0031] Step S400, isolate the risk transmitter for faults, and activate the target redundant transmitter according to the mapping of the risk transmitter in the multiple redundant transmitters to perform temporary measurements on the target industrial scene. Specifically, when the risk transmitter is determined, the fault isolation mechanism is immediately started, and the risk transmitter is disconnected from the entire measurement system by electronic or mechanical means to prevent its fault from affecting other parts of the system, which involves operations such as closing related circuit switches and interrupting data transmission channels. After the fault isolation is completed, the target redundant transmitter that can replace the risk transmitter for measurement is determined from multiple redundant transmitters according to the pre-set mapping relationship. The mapping relationship is usually planned and set based on factors such as the pressure measurement requirements of the industrial scene, the location and performance of the redundant transmitters, etc. Once the target redundant transmitter is determined, an activation instruction is sent. After receiving the instruction, the target redundant transmitter starts to measure the pressure of the target industrial scene and transmits the measured data to the system. In the process of activating the target redundant transmitter, it is also necessary It needs to be initialized and calibrated to ensure the accuracy and reliability of the measurement data. For example, the measurement parameters of the target redundant transmitter are adjusted according to the pressure range and accuracy requirements of the target industrial scenario. At the same time, the system will continuously monitor the working status and measurement data of the target redundant transmitter to ensure that it can perform temporary measurements stably and accurately. If an abnormality is found in the target redundant transmitter, further measures will be taken in time, such as switching to other spare redundant transmitters or issuing an alarm to prompt maintenance. For example, in a petrochemical production unit, when a pressure transmitter at a key position is determined to be a risk transmitter and isolated, the system quickly activates the target redundant transmitter pre-deployed nearby, ensuring the continuity and stability of pressure measurement during the production process and avoiding production accidents or quality problems that may be caused by pressure measurement interruptions.

[0032] Step S500, pre-build a multi-dimensional fault detection strategy, and troubleshoot the risk transmitter according to the multi-dimensional fault detection strategy to obtain the transmitter fault identification result. Specifically, build a multi-dimensional fault detection strategy to determine the multiple dimensions to be covered, such as the electrical characteristic dimension, including checking whether the transmitter circuit has short circuit, open circuit, abnormal resistance and other problems; the mechanical connection dimension, check whether the connection between the transmitter and the pipeline or equipment is loose and whether the seal is good; the analog signal dimension, analyze whether the amplitude, frequency, phase, etc. of the analog signal output by the transmitter are within the normal range; the cross-validation dimension, compare and verify the data with other related measuring equipment or systems to find potential faults, and formulate specific detection methods and standards for each dimension. For example, in electrical characteristic detection, use professional circuit testing instruments for measurement; in mechanical connection detection, check the tightness by visual observation combined with tools such as torque wrenches; in analog signal detection, use signal analysis software for frequency Spectral and time domain analysis; in the cross-validation test, establish a data comparison model and an allowable error range. After building a multi-dimensional fault detection strategy, conduct a comprehensive troubleshooting of the risk transmitter based on the strategy. For the electrical characteristic dimension, use the corresponding test equipment to test the transmitter circuit one by one, record various electrical parameters, and compare them with normal standards. In the mechanical connection dimension, carefully check the physical state of the connection parts, including wear and deformation of the connectors. In the analog signal dimension, collect the signal output by the transmitter, and use professional analysis tools for in-depth analysis to check whether there are distortions, interference and other anomalies. In the cross-validation dimension, obtain data from other related equipment or systems, compare them with the data of the risk transmitter, and calculate the error. Through detailed detection and analysis of each dimension, comprehensively judge whether the risk transmitter has a fault. If a fault exists, further determine the type, location, severity and other information of the fault, and finally obtain the transmitter fault identification result. For example, in the pressure measurement system of a smart factory, when a risky transmitter is found, use a pre-built multi-dimensional fault detection strategy to detect from multiple angles such as electrical, mechanical, signal and cross-validation, and accurately identify that the transmitter has an abnormal output signal due to a circuit short circuit, and record this result as a fault identification result, providing a clear basis for subsequent maintenance and processing.

[0033] In a possible implementation, a multi-dimensional fault detection strategy is pre-constructed, and the risk transmitter is troubleshooted according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result. Step S500 further includes step S510, and the multi-dimensional fault detection strategy includes an electrical characteristic detection strategy, a mechanical connection detection strategy, an analog signal detection strategy, and a cross-validation detection strategy. Specifically, the multi-dimensional fault detection strategy includes an electrical characteristic detection strategy, a mechanical connection detection strategy, an analog signal detection strategy, and a cross-validation detection strategy, wherein the electrical characteristic detection strategy uses professional electrical testing instruments, such as a multimeter, an oscilloscope, etc., to conduct a comprehensive inspection of the circuit of the risk transmitter, check whether the power supply is stable, measure the resistance value to determine whether the circuit has a short circuit or an open circuit, detect whether the parameters of components such as capacitors and inductors are within the normal range, observe whether the current and voltage changes in the circuit are as expected, and at the same time, check whether the electronic components have signs of overheating, burning or damage. Perform functional tests on the integrated circuit inside the transmitter to ensure that it works properly. The mechanical connection detection strategy uses the naked eye to observe the connection between the risk transmitter and the pipeline or equipment to check whether the connection parts are loose, falling off or damaged. Use tools such as torque wrenches to check the tightness according to the specified torque standards. Check whether the seals are intact and whether there is any leakage. Check whether the mechanical transmission parts are flexible and whether there is any jamming or abnormal wear. For parts with threaded connections, check the integrity and matching accuracy of the threads. The analog signal detection strategy uses a signal generator to inject specific analog signals into the risk transmitter, such as standard sine waves, square waves, etc., and monitor the output response of the transmitter. Analyze the consistency of the output signal's amplitude, frequency, phase and other parameters with the input signal. Use a spectrum analyzer to perform spectrum analysis on the output signal to check whether there is clutter or harmonic distortion. Observe the linearity and dynamic response characteristics of the transmitter by changing the strength and frequency of the input signal. The cross-validation detection strategy obtains data from other reliable measurement devices or systems at the same measurement point or related measurement points, and compares them with the measurement results of the risk transmitter. Establish a data comparison model to calculate the deviation and error between the two. Analyze the distribution law and trend of the error to determine whether it is within an acceptable range. If there is a large deviation, further investigate whether it is a problem with the transmitter itself or other external factors that cause the difference. At the same time, the measurement data of the risk transmitter can also be compared with the historical data to observe whether there are abnormal changes. For example, on an industrial automation production line, the above four detection strategies are applied in sequence to the pressure transmitter with the risk of failure. First, the electrical characteristics test found that there was voltage fluctuation in the power supply part; then the mechanical connection test found no obvious problems; then the analog signal test found that the amplitude of the output signal was attenuated; finally, the cross-validation test determined that the measurement result of the transmitter had a large deviation from the similar transmitter in the adjacent position.By combining these test results, the cause and location of the transmitter failure can be accurately determined, providing strong support for subsequent maintenance and adjustments.

[0034] Step S600: If the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain an environment-related information set. Specifically, when the result of transmitter fault identification is a non-empty set, it means that the risk transmitter has been determined to be faulty. Various information related to the risk transmitter is collected, including basic information such as the installation location, usage time, and maintenance records of the transmitter. A comprehensive investigation is conducted on the environment where the risk transmitter is located, and the surrounding physical environmental parameters such as temperature, humidity, and pressure are checked to determine whether there are any conditions that exceed the normal working range of the transmitter. Check whether there are electromagnetic interference sources, such as large motors and transformers, that may affect the normal operation of the transmitter. Analyze the process flow and operation conditions in the industrial scenario to determine whether there are abnormal process conditions or operational errors that cause the transmitter failure. Check other equipment and lines connected to the risk transmitter to see if there are short circuits, open circuits, poor contact, and other problems. Analyze the input and output signals of the transmitter again, observe the change patterns of the signals before and after the fault occurs, and infer the possible causes of the fault. Consider factors such as dust and corrosive gases in the industrial scenario to determine whether the components of the transmitter are damaged. Based on the above multi-faceted investigation and analysis results, screen out environmental factors and related information related to the fault to form an environmental related information set.

[0035] In a possible implementation, if the transmitter fault identification result is a non-empty set, the risk transmitter is subjected to fault cause analysis to obtain an environment-related information set, and step S600 further includes step S610, generating a search instruction based on the multi-dimensional fault detection strategy and the device model information, and performing information networking call based on the search instruction to obtain multi-dimensional environment-related information. Specifically, the specific content of the multi-dimensional fault detection strategy and the device model information of the risk transmitter are integrated and analyzed, and accurate search instructions are constructed based on the information. The instructions include a description of a specific type of fault, device characteristics, and possibly related environmental factors. Then, these search instructions are sent to a related database, knowledge base, or online resource platform through a network connection. After receiving the instructions, the platform screens and extracts according to the conditions in the instructions, and returns the matching multi-dimensional environment-related information. The information covers failure cases of similar devices in different environments, common failure environmental factors of specific models of equipment, and environmental standards and specifications of related industries.

[0036] Step S620, using the transmitter fault identification result to traverse the multi-dimensional environment-related information to obtain risk environment-related information. Specifically, the transmitter fault identification result obtained previously, including the specific manifestation of the fault, the severity and other information, is used as a screening condition, and each piece of data in the multi-dimensional environment-related information is compared and analyzed in turn to screen out the environment-related information that is highly relevant to the current fault identification result, for example, the environmental factors mentioned in the case similar to the specific fault manifestation, or the environmental influencing factors that match the current equipment model and the severity of the fault, etc., and the screened information is determined as the risk environment-related information.

[0037] Step S630, based on the location of the risk transmitter, the local environment data of the target industrial scene is called to obtain a local environment information set. Specifically, the specific location of the risk transmitter in the target industrial scene is determined, and the local environment data of the location and its surrounding area are obtained by using sensors, monitoring equipment installed on site or locally stored environment data records. The data includes real-time physical environment parameters such as temperature, humidity, air quality, vibration, and related information such as production activities and equipment operation status in the area. These data are integrated into a local environment information set.

[0038] Step S640, solve the intersection data of the risk environment associated information and the local environment information to obtain the environment associated information set. Specifically, the risk environment associated information and the local environment information are comprehensively compared and analyzed to find out the environmental factors and associated data that exist in common between the two, and these intersection data are extracted through data matching, screening and integration methods. These intersection data are the final environment associated information set, which can more accurately reflect the environmental factors and conditions related to the current risk transmitter failure, and provide strong support for subsequent fault analysis and resolution. For example, in an automated production line of a large factory, a pressure transmitter fails. Through the above steps, the environmental information of the same model of equipment under similar failures is first obtained from the network, and then combined with the real-time environmental data of the transmitter location in the local production line, it is finally determined that excessive temperature and strong vibration of nearby equipment are key environmental factors that may cause failures.

[0039] In a possible implementation, if the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain an environment-related information set, and step S600 further includes step S650. If the transmitter fault identification result is an empty set, the fault isolation of the risk transmitter is revoked, and the risk transmitter is used to take over the target redundant transmitter. Specifically, when it is determined that the transmitter fault identification result is an empty set, it means that the previous conclusion that the transmitter has a fault may be wrong. First, the system will perform an operation to revoke the fault isolation. This may involve hardware-level operations such as reconnecting the previously disconnected circuit and restoring the normal connection of the data transmission channel. After the physical connection is restored, the risk transmitter is changed from an isolated state to a workable state through software-level instructions and configuration adjustments. Then, the takeover process is started to transfer the measurement task previously undertaken by the target redundant transmitter to this risk transmitter. This requires reconfiguring the measurement task allocation and data processing logic of the system to ensure that the risk transmitter can smoothly and accurately undertake the measurement work.

[0040] Step S660, preset a signal transmission monitoring window, and monitor and identify signal transmission failures of the risk transmitter. Specifically, the preset signal transmission monitoring window is to set a specific time period or monitoring condition in advance, which is used to focus on the signal transmission of the risk transmitter. The setting of this window will take into account the operating cycle of the system, key production stages or other relevant factors. During the window period, special monitoring equipment and software tools will be used to capture the signal transmitted by the risk transmitter in real time. The tool will analyze various key indicators of the signal, such as whether the signal strength is stable, whether it fluctuates within the normal value range, whether the data transmission frequency meets the settings, etc. By comparing the real-time monitored data with the pre-set normal signal mode and standard, if any deviation or abnormality is found, such as a sudden and significant drop in signal strength, obvious errors in data, or transmission interruption, the system will immediately identify it as a signal transmission failure, and trigger the corresponding alarm mechanism to notify relevant personnel to take further inspection and repair measures.

[0041] Step S700, interactively obtain the device model information of the risk transmitter, and perform a transmitter hidden danger check on the pressure measurement array according to the device model information and the environment-related information to obtain an updated measurement array. Specifically, the device model information of the risk transmitter is obtained through human-computer interaction, which can be realized by inputting on the system interface, querying and selecting from the database, or communicating with relevant staff. After obtaining the device model information, it is combined with the environment-related information obtained by the previous analysis, and the technical specifications, performance characteristics and applicable environmental range corresponding to the device model are carefully studied. Each transmitter in the entire pressure measurement array is checked one by one to check whether the installation position of the transmitter is reasonable and whether it is in an unfavorable position susceptible to environmental influences. The current working environment parameters are compared with the environmental conditions allowed by the device model to determine whether there are environmental factors that exceed the device's tolerance. The operating time and maintenance records of the transmitter are checked to evaluate its aging degree and potential failure risks. For transmitters with the same or similar models as the risk transmitter, higher attention and stricter inspection are given. According to the results of the inspection, it is determined which transmitters may have hidden dangers. For transmitters with hidden dangers, take corresponding measures, such as adjusting the installation position, strengthening protective measures, arranging early maintenance or replacement, etc., to reconfigure and optimize the pressure measurement array to form an updated measurement array. Ensure that the new array can measure pressure more stably and accurately to reduce the possibility of failure. For example, in a petrochemical production unit, after obtaining the model of the risky transmitter, combined with environmental related information, it is found that this model of transmitter is prone to failure in high temperature and high humidity environments. The entire pressure measurement array was checked and it was found that several transmitters of the same model were installed in similar harsh environments. Immediately, these transmitters were given additional insulation and moisture-proof measures or replaced with models more suitable for the environment, thereby obtaining an updated and more reliable measurement array.

[0042] The embodiment of the present application adopts a measurement array containing multiple pressure transmitters and redundant transmitters deployed in the target industrial scenario, receives output signals in real time based on the industrial Internet of Things, detects anomalies to locate risk transmitters, isolates risk transmitters and activates redundant transmitters for temporary measurement, pre-builds a multi-dimensional strategy to troubleshoot and obtain identification results, and if the result is not empty, analyzes the cause of the fault to obtain environmental information, interactively obtains equipment models to check for hidden dangers and obtains an updated array, thereby achieving the technical effect of reducing production risks and losses caused by pressure measurement failures and improving the reliability and operation efficiency of the entire industrial production system.

[0043] In the above, refer to Figure 1 The intelligent diagnosis method for a pressure transmitter according to an embodiment of the present invention is described in detail. Figure 2 An intelligent diagnosis system for a pressure transmitter according to an embodiment of the present invention is described.

[0044] The intelligent diagnostic system for a pressure transmitter according to an embodiment of the present invention is used to solve the technical problems in the existing pressure measurement system, such as the untimely and inaccurate detection of pressure transmitter anomalies, the difficulty in fault location and isolation, the single and lack of systematic troubleshooting strategy, and the inability to effectively prevent similar faults from occurring in other transmitters due to insufficient consideration of environmental factors, making it difficult to ensure the accuracy, continuity and stability of pressure measurement in industrial production, thereby achieving the technical effect of reducing production risks and losses caused by pressure measurement failures and improving the reliability and operating efficiency of the entire industrial production system.

[0045] The intelligent diagnosis system for pressure transmitters includes: a pressure measurement array layout module 10, an output signal acquisition module 20, an anomaly detection module 30, a fault isolation module 40, a transmitter fault identification result acquisition module 50, an environment-related information set acquisition module 60, and an updated measurement array acquisition module 70.

[0046] The pressure measurement array deployment module 10 is used to deploy a pressure measurement array in a target industrial scenario, wherein the pressure measurement array includes a plurality of pressure transmitters and a plurality of redundant transmitters.

[0047] The output signal acquisition module 20 is used to receive output signals in real time based on the industrial Internet of Things, and obtain multiple output signals of the multiple pressure transmitters.

[0048] The abnormality detection module 30 is used to perform abnormality detection on the multiple output signals, and locate the risky transmitter among the multiple pressure transmitters based on the detection result.

[0049] The fault isolation module 40 is used to perform fault isolation on the risk transmitter, and activate a target redundant transmitter according to the mapping of the risk transmitter to the multiple redundant transmitters to perform temporary measurement on the target industrial scene.

[0050] The transmitter fault identification result acquisition module 50 is used to pre-build a multi-dimensional fault detection strategy, and troubleshoot the risk transmitter according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result.

[0051] The environment-related information set acquisition module 60 is used to analyze the cause of the failure of the risk transmitter and obtain the environment-related information set if the transmitter fault identification result is a non-empty set.

[0052] The updated measurement array acquisition module 70 is used to interactively obtain the device model information of the risk transmitter, and perform transmitter hidden danger inspection on the pressure measurement array according to the device model information and the environment-related information to obtain an updated measurement array.

[0053] The specific configuration of the abnormality detection module 30 will be described in detail below. As described above, the multiple output signals are subjected to abnormality detection, and the risk transmitter is located among the multiple pressure transmitters based on the detection results. The abnormality detection module 30 may further include: a signal abnormality coefficient acquisition unit for pre-building a signal abnormality detection unit, and performing abnormality detection on the multiple output signals through the signal abnormality detection unit to obtain multiple signal abnormality coefficients; a signal stability coefficient acquisition unit for performing stability detection on the multiple output signals to obtain multiple signal stability coefficients; a transmitter abnormality coefficient acquisition unit for performing weighted calculation on the multiple signal abnormality coefficients and the multiple signal stability coefficients based on a preset weight configuration to obtain multiple transmitter abnormality coefficients; a serialization unit for serializing the multiple transmitter abnormality coefficients, and locating the risk transmitter among the multiple pressure transmitters according to the extreme values ​​of the serialization results.

[0054] Among them, a signal anomaly detection unit is pre-constructed, and anomaly detection is performed on the multiple output signals through the signal anomaly detection unit to obtain multiple signal anomaly coefficients. The signal anomaly coefficient acquisition unit may further include: a signal processing layer sub-unit is used for the signal anomaly detection unit to include a cascaded signal recognition layer and a signal anomaly calculation layer; a signal synchronization sub-unit is used to pre-construct a signal identifier based on a signal processing algorithm, and synchronize the signal identifier to the signal recognition layer; a signal anomaly detection unit construction sub-unit is used to introduce a signal anomaly evaluation function in the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit; an anomaly detection sub-unit is used to synchronize the multiple output signals to the signal anomaly detection unit, perform anomaly detection via the signal recognition layer and the signal anomaly calculation layer, and obtain the multiple signal anomaly coefficients.

[0055] Among them, a signal identifier is pre-constructed based on a signal processing algorithm, and the signal identifier is synchronized to the signal identification layer. The signal synchronization subunit may further include: an identification type composition micro-unit, and the identification types of the signal identifier include signal peak extreme values, signal valley extreme values, peak values, valley values, and peak-valley time intervals.

[0056] Wherein, a signal anomaly evaluation function is introduced into the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit. The signal anomaly detection unit construction subunit may further include: a signal anomaly evaluation function microunit is used for the signal anomaly evaluation function as follows: ,in, is the signal anomaly coefficient, is the signal peak value, is the signal valley extreme value, For the Peak value, For the A valley value, is the number of adjacent peak-valley pairs, For the The time point of the peak value, For the The time node of the valley value, is the maximum peak-to-valley weight, is the adjacent peak-to-valley amplitude weight, is the time weight of adjacent peaks and valleys.

[0057] The specific configuration of the transmitter fault identification result acquisition module 50 will be described in detail below. As described above, a multi-dimensional fault detection strategy is pre-built, and the risk transmitter is troubleshooted according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result. The transmitter fault identification result acquisition module 50 may further include: a multi-dimensional fault detection strategy component unit for the multi-dimensional fault detection strategy including an electrical characteristic detection strategy, a mechanical connection detection strategy, an analog signal detection strategy, and a cross-validation detection strategy.

[0058] The specific configuration of the environment-related information set acquisition module 60 will be described in detail below. As described above, if the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain the environment-related information set. The environment-related information set acquisition module 60 may further include: a multi-dimensional environment-related information acquisition unit for generating a retrieval instruction based on the multi-dimensional fault detection strategy and the equipment model information and performing an information networking call based on the retrieval instruction to obtain multi-dimensional environment-related information; a risk environment-related information acquisition unit for traversing the multi-dimensional environment-related information using the transmitter fault identification result to obtain risk environment-related information; a local environment information set acquisition unit for performing a local environment data call on the target industrial scene according to the layout position of the risk transmitter to obtain a local environment information set; and an environment-related information set acquisition unit for performing an intersection data solution on the risk environment-related information and the local environment information to obtain the environment-related information set.

[0059] Among them, the environment-related information set acquisition module 60 may further include: a fault isolation revocation unit is used to revoke the fault isolation of the risk transmitter if the transmitter fault identification result is an empty set, and use the risk transmitter to take over the target redundant transmitter; a signal transmission fault monitoring and identification unit is used to preset a signal transmission monitoring window and perform signal transmission fault monitoring and identification on the risk transmitter.

[0060] The intelligent diagnosis system for a pressure transmitter provided in the embodiment of the present invention can execute the intelligent diagnosis method for a pressure transmitter provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0062] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent diagnostic method for a pressure transmitter, characterized in that: The method comprises: Deploying a pressure measurement array in a target industrial scenario, wherein the pressure measurement array includes a plurality of pressure transmitters and a plurality of redundant transmitters; Receiving output signals in real time based on the industrial Internet of Things to obtain multiple output signals of the multiple pressure transmitters; Performing abnormality detection on the plurality of output signals, and locating a risky transmitter among the plurality of pressure transmitters based on the detection result; Performing fault isolation on the risk transmitter, and activating a target redundant transmitter according to the mapping of the risk transmitter to the multiple redundant transmitters to perform temporary measurement on the target industrial scene; Pre-building a multi-dimensional fault detection strategy, and troubleshooting the risk transmitter according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result; If the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain an environment-related information set; Interactively obtain device model information of the risk transmitter, and perform transmitter hidden danger inspection on the pressure measurement array according to the device model information and the environment-related information to obtain an updated measurement array; Performing abnormality detection on the multiple output signals, and locating a risky transmitter among the multiple pressure transmitters based on the detection results, the method further comprising: Pre-constructing a signal anomaly detection unit, and performing anomaly detection on the multiple output signals through the signal anomaly detection unit to obtain multiple signal anomaly coefficients; Performing stability detection on the multiple output signals to obtain multiple signal stability coefficients; Performing weighted calculation on the plurality of signal abnormality coefficients and the plurality of signal stability coefficients based on a preset weight configuration to obtain a plurality of transmitter abnormality coefficients; Serializing the abnormal coefficients of the plurality of transmitters, and locating the risky transmitter among the plurality of pressure transmitters according to an extreme value of the serialization result; A signal anomaly detection unit is pre-constructed, and anomaly detection is performed on the multiple output signals by the signal anomaly detection unit to obtain multiple signal anomaly coefficients. The method further includes: The signal anomaly detection unit includes a cascaded signal recognition layer and a signal anomaly calculation layer; Pre-constructing a signal identifier based on a signal processing algorithm, and synchronizing the signal identifier to the signal recognition layer; Introducing a signal anomaly evaluation function into the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit; Synchronize the multiple output signals to the signal anomaly detection unit, perform anomaly detection via the signal recognition layer and the signal anomaly calculation layer, and obtain the multiple signal anomaly coefficients; The identification types of the signal identifier include signal peak extreme value, signal valley extreme value, peak value, valley value, peak-valley time interval; The signal anomaly evaluation function is as follows: ; in, is the signal anomaly coefficient, is the signal peak value, is the signal valley extreme value, For the Peak value, For the A valley value, is the number of adjacent peak-valley pairs, For the The time point of the peak value, For the The time node of the valley value, is the maximum peak-to-valley weight, is the adjacent peak-to-valley amplitude weight, is the time weight of adjacent peaks and valleys.

2. The intelligent diagnosis method for a pressure transmitter according to claim 1, characterized in that: The multi-dimensional fault detection strategy includes an electrical characteristic detection strategy, a mechanical connection detection strategy, an analog signal detection strategy, and a cross-validation detection strategy.

3. The intelligent diagnosis method for a pressure transmitter according to claim 2, characterized in that: If the transmitter fault identification result is a non-empty set, the fault cause analysis is performed on the risk transmitter to obtain an environment-related information set, and the method further includes: Generate a search instruction based on the multi-dimensional fault detection strategy and the equipment model information, and perform information networking call based on the search instruction to obtain multi-dimensional environment related information; Using the transmitter fault identification result to traverse the multi-dimensional environment association information to obtain risk environment association information; Calling local environment data of the target industrial scene according to the layout position of the risk transmitter to obtain a local environment information set; The intersection data of the risk environment association information and the local environment information is solved to obtain the environment association information set.

4. The intelligent diagnosis method for a pressure transmitter according to claim 1, characterized in that: The method further comprises: If the transmitter fault identification result is an empty set, the fault isolation of the risk transmitter is cancelled, and the risk transmitter is used to take over the target redundant transmitter; A signal transmission monitoring window is preset to monitor and identify signal transmission failures of the risk transmitter.

5. Intelligent diagnostic system for pressure transmitter, characterized in that: The system is used to implement the intelligent diagnosis method for a pressure transmitter according to any one of claims 1 to 4, and the system comprises: A pressure measurement array deployment module, the pressure measurement array deployment module is used to deploy a pressure measurement array in a target industrial scenario, wherein the pressure measurement array includes a plurality of pressure transmitters and a plurality of redundant transmitters; An output signal acquisition module, the output signal acquisition module is used to receive output signals in real time based on the industrial Internet of Things, and obtain multiple output signals of the multiple pressure transmitters; an abnormality detection module, the abnormality detection module is used to perform abnormality detection on the multiple output signals, and locate the risk transmitter among the multiple pressure transmitters based on the detection result; A fault isolation module, the fault isolation module is used to perform fault isolation on the risk transmitter, and activate a target redundant transmitter according to the mapping of the risk transmitter to the multiple redundant transmitters to perform temporary measurement on the target industrial scene; A transmitter fault identification result acquisition module, the transmitter fault identification result acquisition module is used to pre-build a multi-dimensional fault detection strategy, and troubleshoot the risk transmitter according to the multi-dimensional fault detection strategy to obtain a transmitter fault identification result; An environment-related information set acquisition module, wherein if the transmitter fault identification result is a non-empty set, the environment-related information set acquisition module is used to analyze the cause of the fault of the risk transmitter to obtain an environment-related information set; An updated measurement array acquisition module, the updated measurement array acquisition module is used to interactively obtain device model information of the risk transmitter, and perform transmitter hidden danger inspection on the pressure measurement array according to the device model information and the environment-related information to obtain an updated measurement array; The anomaly detection module further includes: The signal anomaly coefficient acquisition unit is used to pre-build a signal anomaly detection unit, and perform anomaly detection on the multiple output signals through the signal anomaly detection unit to obtain multiple signal anomaly coefficients; The signal stability coefficient acquisition unit is used to perform stability detection on the multiple output signals to obtain multiple signal stability coefficients; The transmitter abnormality coefficient acquisition unit is used to perform weighted calculation on the multiple signal abnormality coefficients and the multiple signal stability coefficients based on a preset weight configuration to obtain multiple transmitter abnormality coefficients; The serialization unit is used to serialize the abnormal coefficients of the plurality of transmitters, and locate the risk transmitter among the plurality of pressure transmitters according to the extreme value of the serialization result; The signal anomaly coefficient acquisition unit further includes: The signal processing layer subunit is used for the signal anomaly detection unit including a cascaded signal recognition layer and a signal anomaly calculation layer; The signal synchronization subunit is used to pre-build a signal identifier based on a signal processing algorithm and synchronize the signal identifier to the signal recognition layer; The signal anomaly detection unit construction subunit is used to introduce a signal anomaly evaluation function into the signal anomaly calculation layer to complete the construction of the signal anomaly detection unit; The anomaly detection subunit is used to synchronize the multiple output signals to the signal anomaly detection unit, perform anomaly detection via the signal recognition layer and the signal anomaly calculation layer, and obtain the multiple signal anomaly coefficients; The signal synchronization subunit further comprises: The identification type constituent micro-units used for the signal identifier include signal peak extreme value, signal valley extreme value, peak value, valley value, peak-valley time interval; The signal anomaly detection unit construction subunit further includes: The signal anomaly evaluation function micro-unit is used for the signal anomaly evaluation function as follows: ; in, is the signal anomaly coefficient, is the signal peak value, is the signal valley extreme value, For the Peak value, For the A valley value, is the number of adjacent peak-valley pairs, For the The time point of the peak value, For the The time node of the valley value, is the maximum peak-to-valley weight, is the adjacent peak-to-valley amplitude weight, is the time weight of adjacent peaks and valleys.