An intelligent temperature transmitter fault diagnosis method, system, device and medium

Abstract

The application discloses a kind of intelligent temperature transmitter fault diagnosis method, system, equipment and medium, it is related to fault diagnosis technical field, comprising: the environment parameter and operating parameter of temperature transmitter are acquired, initial reference value is compensated according to environment parameter and operating parameter Processing, obtain current reference value;Continuous multiple output signal data of temperature transmitter are collected, fluctuation characteristics, trend characteristics and deviation characteristics are extracted from output signal data;According to fluctuation characteristics, trend characteristics and deviation characteristics, construct fault feature vector;Fault feature vector is matched with fault judgment rule, and the fault type of temperature transmitter is determined according to matching result.The application eliminates the interference of environmental factors on fault judgment by environmental compensation, realizes the accurate identification of different fault types by multidimensional feature extraction, solves the problem of low fault diagnosis accuracy and high false alarm rate in the prior art, improves the reliability and practicality of temperature transmitter fault diagnosis.

Description

Technical Field

[0001] This application relates to the field of fault diagnosis technology, and in particular to a fault diagnosis method, system, device and medium for intelligent temperature transmitters. Background Technology

[0002] Temperature transmitters, as key measuring instruments in industrial process control systems, directly impact the safety of production processes and product quality through their operational reliability. Modern industrial production places higher demands on temperature measurement accuracy and system stability, making temperature transmitter fault diagnosis technology a crucial means to ensure production continuity. Currently, widely used intelligent temperature transmitters in industrial settings possess basic fault detection functions, capable of outputting corresponding alarm signals when obvious faults such as sensor burnout or signal over-limit occur. This type of diagnostic technology primarily relies on threshold judgment of the output signal; a lower-limit alarm is determined when the output current is below 3.8mA, and an upper-limit alarm is determined when it exceeds 20.5mA, thus achieving basic identification of serious faults.

[0003] However, existing temperature transmitter fault diagnosis technologies have several limitations in practical applications. First, the impact of environmental factors on fault diagnosis is not effectively compensated. When temperature transmitters operate within a wide temperature range of -25℃ to 60℃, changes in ambient temperature and equipment aging can cause reference value drift, making false alarms likely when using fixed thresholds. Second, the ability to identify fault types is limited. Existing technologies can only identify significant faults such as sensor burnout and signal over-limit, lacking effective early warning capabilities for progressive faults such as sensor performance degradation and systematic shifts. Third, fault feature extraction is limited in scope, relying solely on the comparison of instantaneous signal values ​​with thresholds, ignoring the temporal characteristics and trends of the signal, making it difficult to distinguish between transient interference and persistent faults, resulting in insufficient reliability of diagnostic results. Summary of the Invention

[0004] In view of the aforementioned problems, this application is hereby filed.

[0005] Therefore, this application provides a method, system, device and medium for diagnosing faults in intelligent temperature transmitters, which can solve the problems mentioned in the background art.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] In a first aspect, this application provides a fault diagnosis method for an intelligent temperature transmitter, comprising: acquiring environmental parameters and operating parameters of the temperature transmitter; compensating an initial reference value based on the environmental parameters and operating parameters to obtain a current reference value; collecting multiple consecutive output signal data from the temperature transmitter; extracting fluctuation features, trend features, and deviation features from the output signal data; constructing a fault feature vector based on the fluctuation features, trend features, and deviation features; matching the fault feature vector with fault judgment rules; and determining the fault type of the temperature transmitter based on the matching result.

[0008] Preferably, the step of acquiring the environmental and operating parameters of the temperature transmitter, and compensating the initial reference value based on the environmental and operating parameters to obtain the current reference value, includes: acquiring the current ambient temperature of the temperature transmitter as the environmental parameter; acquiring the cumulative operating time of the temperature transmitter as the operating parameter; calculating a temperature compensation value based on the deviation between the current ambient temperature and the standard temperature and the temperature compensation ratio; calculating a time compensation value based on the relationship between the cumulative operating time and the standard time and the time compensation ratio; and performing calculations on the initial reference value, the temperature compensation value, and the time compensation value to obtain the current reference value.

[0009] Preferably, the step of acquiring multiple consecutive output signal data from the temperature transmitter and extracting fluctuation characteristics, trend characteristics, and deviation characteristics from the output signal data includes: acquiring multiple output signal data from the temperature transmitter within a time window; calculating the dispersion value of the multiple output signal data and using the dispersion value as the fluctuation characteristic; calculating the trend characteristic based on the change in the first and last output signal data within the time window; and calculating the difference between each output signal data and the current reference value, using the maximum difference value as the deviation characteristic.

[0010] Preferably, the fault feature vector is matched with fault judgment rules, and the fault type of the temperature transmitter is determined based on the matching result, including: if the fluctuation feature meets the first judgment condition and the trend feature meets the second judgment condition, the fault type is determined to be sensor aging; if the deviation feature meets the third judgment condition and continues for a preset number of time windows, the fault type is determined to be system offset; if the fluctuation feature meets the fourth judgment condition or an output signal data interruption is detected, the fault type is determined to be hardware fault; if none of the above fault conditions are met, the temperature transmitter is determined to be in normal condition.

[0011] Preferably, after matching the fault feature vector with the fault judgment rule, the method further includes: obtaining a set of historical fault feature vectors, which stores multiple historical feature vectors and corresponding confirmed fault types; calculating the similarity between the fault feature vector and each historical feature vector in the set of historical fault feature vectors; selecting multiple historical feature vectors with the highest similarity and statistically analyzing the fault type distribution corresponding to the multiple historical feature vectors; and if the highest proportion type in the fault type distribution is inconsistent with the fault type, using the highest proportion type as the re-determined fault type.

[0012] Preferably, the method further includes: storing the fault feature vector and the re-determined fault type into the historical fault feature vector set; analyzing the feature value distribution corresponding to each fault type in the historical fault feature vector set; and adjusting the first judgment condition, the second judgment condition, the third judgment condition, and the fourth judgment condition according to the feature value distribution. Preferably, after determining the fault type of the temperature transmitter based on the matching result, the method further includes: generating a diagnostic report, which records the fault type, fault feature value, and fault occurrence time; determining the corresponding alarm level according to the fault type; and sending the diagnostic report and the alarm level to the monitoring system via a communication interface.

[0013] Secondly, this application also provides an intelligent temperature transmitter fault diagnosis system, including a reference value compensation module, a feature extraction module, a vector construction module, and a fault judgment module, wherein: the reference value compensation module is used to acquire the environmental parameters and operating parameters of the temperature transmitter, and to compensate the initial reference value according to the environmental parameters and the operating parameters to obtain the current reference value; the feature extraction module is used to collect multiple consecutive output signal data of the temperature transmitter, and to extract fluctuation features, trend features, and deviation features from the output signal data; the vector construction module is used to construct a fault feature vector according to the fluctuation features, the trend features, and the deviation features; the fault judgment module is used to match the fault feature vector with fault judgment rules, and to determine the fault type of the temperature transmitter according to the matching result.

[0014] Thirdly, this application also provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring environmental parameters and operating parameters of a temperature transmitter; compensating an initial reference value based on the environmental parameters and the operating parameters to obtain a current reference value; acquiring multiple consecutive output signal data from the temperature transmitter; extracting fluctuation features, trend features, and deviation features from the output signal data; constructing a fault feature vector based on the fluctuation features, trend features, and deviation features; matching the fault feature vector with fault judgment rules; and determining the fault type of the temperature transmitter based on the matching result.

[0015] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, performs the following steps: acquiring environmental parameters and operating parameters of a temperature transmitter; compensating an initial reference value based on the environmental parameters and operating parameters to obtain a current reference value; acquiring multiple consecutive output signal data from the temperature transmitter; extracting fluctuation features, trend features, and deviation features from the output signal data; constructing a fault feature vector based on the fluctuation features, trend features, and deviation features; matching the fault feature vector with fault judgment rules; and determining the fault type of the temperature transmitter based on the matching result.

[0016] Implementing this application has the following beneficial effects: This application provides a method, system, device, and medium for fault diagnosis of intelligent temperature transmitters. By compensating the reference value through environmental parameters and operating parameters, when the temperature transmitter is at different ambient temperatures or operating durations, the corresponding compensation value can be calculated according to the current operating conditions, thereby correcting the initial reference value. Therefore, even under conditions of drastic changes in ambient temperature or long-term operation of the equipment, a stable and accurate judgment reference can be maintained. At the same time, by extracting fluctuation characteristics, trend characteristics, and deviation characteristics from the signal data within a continuous time window, when abnormal fluctuations occur in the signal, a comprehensive characterization can be performed from the dimensions of time sequence, change trend, and deviation, thereby constructing a complete fault feature vector. Therefore, it can not only identify instantaneous anomalies but also capture gradual change trends.

[0017] When the fault feature vector constructed in this application is matched with the fault judgment rules, sensor aging can be determined when both fluctuation and trend features meet the corresponding conditions; system offset can be identified when deviation features continuously exceed the judgment conditions; and hardware fault can be determined when fluctuation features reach the hardware fault condition or a signal interruption is detected. Therefore, accurate differentiation of different fault types is achieved through multi-condition combination judgment. Furthermore, by introducing a set of historical fault feature vectors for similarity verification, corrections can be made based on historical experience when the judgment result is inconsistent with the historical data distribution. Moreover, the judgment rules can be continuously optimized as historical data accumulates, thus forming a fault diagnosis system with learning capabilities. Therefore, this application not only solves the limitations of environmental interference and single feature judgment, but also realizes early warning and accurate identification of multiple fault types, significantly improving the reliability and practicality of temperature transmitter fault diagnosis. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of a fault diagnosis method for an intelligent temperature transmitter involved in this application;

[0020] Figure 2 This is an application environment diagram of a fault diagnosis method for an intelligent temperature transmitter involved in this application;

[0021] Figure 3 This is a schematic diagram of the overall structure of an intelligent temperature transmitter fault diagnosis system involved in this application;

[0022] Figure 4 This is a computer device diagram of a fault diagnosis method for an intelligent temperature transmitter involved in this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] Intelligent temperature transmitters, as core measuring instruments in industrial automation systems, play a crucial role in temperature monitoring in industries such as petrochemicals, power, metallurgy, and pharmaceuticals. The reliable operation of temperature transmitters is directly related to production safety and product quality. Failure to detect a malfunction in a timely manner can lead to production accidents or product spoilage, resulting in significant economic losses.

[0025] In related technologies, fault diagnosis of temperature transmitters mainly relies on simple threshold judgments, such as triggering an alarm when the output signal is below 3.8mA or above 20.5mA. However, this diagnostic method has significant shortcomings: on the one hand, changes in ambient temperature and equipment aging can cause the judgment benchmark to drift, resulting in false alarms or missed alarms; on the other hand, it can only detect significant faults and lacks the ability to warn of progressive faults such as sensor performance degradation and system deviation. How to achieve accurate fault diagnosis of temperature transmitters under complex operating conditions has become a technical problem that urgently needs to be solved in industrial fields.

[0026] To address the issues of low accuracy and poor environmental adaptability in fault diagnosis of temperature transmitters in related technologies, an intelligent fault diagnosis method for temperature transmitters is proposed. This method compensates the initial reference value by acquiring environmental and operating parameters to eliminate interference from environmental factors; it extracts fluctuation, trend, and deviation features from continuous signal data to construct a multidimensional fault feature vector; and it matches the fault feature vector with fault judgment rules to achieve accurate identification of different fault types.

[0027] The intelligent temperature transmitter fault diagnosis method provided in this application embodiment can be applied to, for example, Figure 2 The industrial monitoring system shown includes a field temperature transmitter 102 that communicates with the monitoring host 104 via HART communication protocol or a 4-20mA signal. A fault diagnosis database stores historical data and diagnostic rules that the monitoring host 104 needs to process. This database can be integrated into the monitoring host 104 or deployed on an industrial cloud platform or enterprise data center. The monitoring host acquires the output signal from the temperature transmitter, environmental parameters from the ambient temperature sensor, and system-recorded operating parameters through the communication interface. It compensates for the initial reference value to obtain the current reference value; it collects multiple consecutive output signal data from the temperature transmitter, extracting fluctuation, trend, and deviation characteristics; it constructs a fault feature vector based on the extracted features; it matches the fault feature vector with fault judgment rules to determine the fault type of the temperature transmitter; it generates a diagnostic report containing the fault type, feature value, and occurrence time, and displays it on the monitoring interface or triggers a corresponding alarm.

[0028] The field temperature transmitter 102 can be, but is not limited to, various industrial temperature measurement devices such as intelligent integrated temperature transmitters, split-type temperature transmitters, and wireless temperature transmitters. It supports multiple sensor types, including thermocouples and resistance temperature detectors (RTDs), and has HART communication functionality or other digital communication capabilities. The monitoring host 104 can be an operator station for an industrial control computer, a programmable logic controller (PLC), or a distributed control system (DCS), or an industrial Internet of Things (IoT) platform deployed in the cloud. Running the fault diagnosis method of this application, it can receive and process signal data from multiple temperature transmitters, enabling centralized monitoring and fault early warning.

[0029] In one exemplary embodiment, such as Figure 1 As shown, a fault diagnosis method for an intelligent temperature transmitter is provided, which is applied to... Figure 2 Taking an industrial monitoring system as an example, the explanation includes steps 100 to 300. Among them:

[0030] Step 100: Obtain the environmental and operating parameters of the temperature transmitter, and perform compensation processing on the initial reference value based on the environmental and operating parameters to obtain the current reference value.

[0031] Among them, environmental parameters reflect the influence of the operating environment of the temperature transmitter on the measurement reference, while operating parameters reflect the influence of the equipment's usage time on the measurement reference. The initial reference value is the theoretical output value of the temperature transmitter under standard conditions. When environmental conditions or equipment status change, the initial reference value needs to be corrected to maintain the accuracy of the diagnosis.

[0032] When temperature transmitters operate in actual industrial settings, their output signals are affected by both ambient temperature changes and equipment aging. Deviations in ambient temperature from the standard temperature cause electronic component parameters to drift, thus affecting the reference level of the output signal. Over long-term operation, the sensor and circuit components age, leading to gradual changes in output characteristics. Therefore, compensation processing is necessary to eliminate the influence of environmental and aging factors.

[0033] Step 100 includes steps 101 to 105:

[0034] Step 101: Obtain the current ambient temperature of the temperature transmitter as an environmental parameter.

[0035] For example, the current ambient temperature value is acquired by an ambient temperature sensor located within the junction box of the temperature transmitter. The ambient temperature sensor can be a PT100 platinum resistance thermometer or a digital temperature sensor, with a measurement range covering -25°C to 60°C, matching the operating temperature range of the temperature transmitter. The current ambient temperature is then converted from analog to digital and transmitted as a digital signal to the monitoring host.

[0036] Step 102: Obtain the cumulative running time of the temperature transmitter as the operating parameter.

[0037] The cumulative operating time is counted from the first time the temperature transmitter is put into use, and is accumulated in hours. The monitoring system is equipped with an operating time counter, which continuously increments while the temperature transmitter is in operation. The cumulative operating time reflects the degree of equipment aging; the longer the operating time, the more significant the performance degradation of the components.

[0038] Step 103: Calculate the temperature compensation value based on the deviation between the current ambient temperature and the standard temperature and the temperature compensation ratio.

[0039] The standard temperature is typically set to 25℃, consistent with the calibration temperature of the temperature transmitter. The temperature compensation ratio is obtained through experimental calibration and reflects the degree of influence of a unit temperature change on the output reference. When the ambient temperature is higher than the standard temperature, the temperature compensation value is positive; when the ambient temperature is lower than the standard temperature, the temperature compensation value is negative.

[0040] For example, the calculation process for the temperature compensation value is as follows: First, calculate the difference between the current ambient temperature and the standard temperature. ,in The current ambient temperature. Standard temperature The temperature deviation is then compared with the temperature compensation ratio. Multiply to obtain the temperature compensation value. ,in This is the temperature compensation value. This refers to the temperature compensation ratio. Temperature compensation ratio The typical value range is 0.0001 to 0.001 / ℃, and the specific value is determined according to the model and characteristics of the temperature transmitter.

[0041] Step 104: Calculate the time compensation value based on the relationship between the cumulative running time and the standard time, as well as the time compensation ratio.

[0042] The standard time is the baseline time point for equipment performance evaluation, usually set at 1000 hours or 8760 hours (one year). The time compensation ratio reflects the degree of impact of equipment aging on the output baseline, and is obtained through accelerated aging tests or long-term operating data statistics.

[0043] For example, the time compensation value is calculated using a logarithmic model because component aging is faster in the early stages and tends to stabilize in the later stages. The calculation process is as follows: First, calculate the natural logarithm of the ratio of runtime. ,in For cumulative running time, The standard time is used; then the logarithm is compared with the time compensation ratio. Multiply by each other to obtain the time compensation value. ,in This is the time compensation value. This refers to the time compensation ratio. Time compensation ratio The typical value range is 0.001 to 0.01, ensuring that equipment operating for a long time can still maintain a reasonable baseline value.

[0044] Step 105: Calculate the initial reference value with the temperature compensation value and the time compensation value to obtain the current reference value.

[0045] For example, the current baseline value is calculated using a linear superposition method: ,in This is the current baseline value. As the initial baseline value, This is the temperature compensation value. This is the time compensation value. Initial baseline value. Typically, it is 4mA (corresponding to the zero-point output of the temperature transmitter) or 12mA (corresponding to the midpoint output of the temperature transmitter), with the specific value determined according to diagnostic requirements. The current reference value after compensation processing can accurately reflect the normal output level of the temperature transmitter under the current operating conditions, providing a reliable reference benchmark for subsequent fault feature extraction.

[0046] Step 200: Collect multiple consecutive output signal data from the temperature transmitter, and extract fluctuation characteristics, trend characteristics, and deviation characteristics from the output signal data.

[0047] The output signal data consists of a 4-20mA current signal output by the temperature transmitter under normal operating conditions, which is converted into a digital signal sequence after analog-to-digital conversion. Continuous acquisition can reflect the temporal variation pattern of the signal, providing data support for fault feature extraction. Fluctuation characteristics reflect the stability of the signal, trend characteristics reflect the direction of signal change, and deviation characteristics reflect the degree to which the signal deviates from the normal reference.

[0048] Temperature transmitter malfunctions often manifest as abnormal changes in the output signal. Sensor aging can lead to increased signal fluctuations and a slow drift trend; system offset can cause the overall signal to deviate from the reference value; hardware failures can cause drastic fluctuations or abrupt changes in the signal. Therefore, it is necessary to extract signal features from multiple dimensions to comprehensively characterize the abnormal signal patterns.

[0049] Step 200 includes steps 201 to 204:

[0050] Step 201: Collect multiple output signal data from the temperature transmitter within the time window.

[0051] The time window is a set sampling period used to limit the time range of feature extraction. The length of the time window needs to balance the real-time nature and reliability of feature extraction; too short a window will lead to unstable features, while too long a window will reduce the timeliness of fault detection.

[0052] For example, the time window length is set to 60 seconds to 300 seconds, and the sampling interval is set to 0.5 seconds to 2 seconds. When the time window length is 120 seconds and the sampling interval is 1 second, 120 sampling points are collected within one time window. The collected output signal data sequence is denoted as... ,in Indicates the first The output signal value at each sampling time. This represents the total number of sampling points, expressed in mA.

[0053] Step 202: Calculate the dispersion value of multiple output signal data and use the dispersion value as the fluctuation feature.

[0054] The dispersion value is quantified using the standard deviation, which reflects the degree of dispersion of the data relative to the mean. Under normal operating conditions, the standard deviation of the temperature transmitter output signal is relatively small; when a fault occurs, the signal fluctuation increases, and the standard deviation increases.

[0055] For example, the calculation process for the fluctuation characteristic is as follows: first, calculate the mean of the signal sequence; then, calculate the sum of squares of the differences between each signal value and the mean; finally, take the square root to obtain the standard deviation. The standard deviation is the fluctuation characteristic value, with the unit being mA. Under normal circumstances, the fluctuation characteristic value is less than 0.1 mA; when the sensor has poor contact or the circuit noise increases, the fluctuation characteristic value will exceed 0.2 mA.

[0056] Step 203: Calculate the trend characteristics based on the changes in the first and last output signal data within the time window.

[0057] The trend feature reflects the overall trend of the signal within the time window. The average rate of change is obtained by calculating the difference between the first and last signal values ​​and dividing it by the time interval. Positive values ​​indicate an upward trend, negative values ​​indicate a downward trend, and the absolute value reflects the speed of change.

[0058] For example, the trend characteristic is calculated by subtracting the first signal value from the last signal value within the time window, and then dividing by the time interval between the two. The unit of the trend characteristic is mA / s. When the temperature transmitter is in a stable state, the trend characteristic value is close to 0; when the sensor ages or zero drifts, it will show a continuous upward or downward trend, and the absolute value of the trend characteristic value will exceed 0.001 mA / s.

[0059] Step 204: Calculate the difference between each output signal data and the current reference value, and use the maximum difference value as the deviation feature.

[0060] The current reference value is the environmentally compensated reference value calculated in step 105, representing the expected output value of the temperature transmitter under the current operating conditions. By calculating the deviation between the actual output and the reference value, systematic offset faults can be identified.

[0061] For example, the calculation process for the deviation characteristic is as follows: calculate the absolute value of the difference between each signal value and the reference value, and select the maximum value from all absolute differences as the deviation characteristic value. The unit of the deviation characteristic is mA. Under normal circumstances, the deviation characteristic value is less than 0.5 mA; when system offset or range drift occurs, the deviation characteristic value will remain greater than 1.0 mA.

[0062] Step 300: Construct a fault feature vector based on fluctuation characteristics, trend characteristics, and deviation characteristics.

[0063] The fault feature vector is a vector representation formed by combining the three extracted feature values ​​in the order of fluctuation feature, trend feature, and deviation feature, and is used for subsequent fault type determination. Vectorized representation facilitates feature space analysis and matching.

[0064] For example, the fault feature vector is constructed as a three-dimensional column vector, with the first dimension representing fluctuation feature values, the second dimension representing trend feature values, and the third dimension representing deviation feature values. By combining feature values ​​of different dimensions into a vector, a structured representation of fault features is achieved, providing a standardized input format for rule-based fault judgment in subsequent steps. Different fault types have different distribution patterns in the feature space, and the feature vector can distinguish between various fault types.

[0065] Step 400: Match the fault feature vector with the fault judgment rules, and determine the fault type of the temperature transmitter based on the matching result.

[0066] The fault diagnosis rules employ a severity-based priority judgment process, judging faults in the following order: hardware failure, system offset, and sensor aging. Hardware failure causes measurement function to malfunction and requires immediate attention; system offset affects measurement accuracy; sensor aging falls under the category of preventative maintenance. This priority design ensures that serious faults are identified promptly.

[0067] Specifically, if the fluctuation characteristics meet the first judgment condition and the trend characteristics meet the second judgment condition, the fault type is determined to be sensor aging.

[0068] The first criterion is judging the range of fluctuation characteristic values, used to identify signal instability caused by sensor performance degradation. The second criterion is judging the threshold of trend characteristic values, used to identify slow drift caused by sensor aging. Both conditions must be met simultaneously, because an increase in fluctuation alone may be caused by environmental interference, and a drift alone may be caused by temperature changes; only when both occur simultaneously can it be identified as an aging characteristic.

[0069] For example, the implementation of the first judgment condition includes several methods. One method is fixed threshold judgment, which sets upper and lower limits for the fluctuation characteristic value. The lower limit is used to distinguish normal states, and the upper limit is used to distinguish hardware faults. In specific implementation, the lower threshold is set as a multiple of the maximum value of the fluctuation characteristic under normal operating conditions, such as 1.5 times or 2 times, to ensure that normal fluctuations will not trigger fault judgment; the upper threshold is set as a multiple of the lower threshold, such as 3 to 5 times, and within this range, it is identified as an aging characteristic. This method is simple to implement, has a fast judgment speed, and is suitable for applications with relatively stable operating conditions and minimal environmental interference.

[0070] Another approach is to use relative judgment based on historical data, comparing the current fluctuation characteristic value with the fluctuation level during historical normal operation. In practice, a baseline fluctuation level for normal operation is first established, which can be the average or median of the fluctuation characteristics during the most recent period of normal operation. Then, the ratio of the current fluctuation characteristic value to the baseline level is calculated. When the ratio exceeds a set multiple but does not reach the level of hardware failure, the first judgment condition is met. This method can adapt to individual differences in different equipment and the basic noise level under different operating conditions, avoiding potential misjudgments caused by fixed thresholds.

[0071] Alternatively, statistical distribution can be used to determine aging characteristics by constructing a feature distribution model based on historical aging cases. In practice, fluctuating characteristic values ​​of confirmed sensor aging cases are collected and fitted using a normal distribution or other suitable distribution model to determine the distribution parameters. For the current fluctuating characteristic value, its probability density or cumulative probability in the aging characteristic distribution is calculated. When the probability value exceeds a set threshold, the first judgment condition is deemed met. This approach fully utilizes historical experience data, enabling more accurate identification of aging characteristics and reducing misjudgments and omissions.

[0072] The second judgment condition can also be implemented in several ways. The basic method is to determine whether the absolute value of the trend characteristic exceeds a set threshold, indicating that the signal is experiencing continuous drift. In practice, the threshold setting needs to consider the range and accuracy class of the temperature transmitter, and is typically set as a certain percentage of the full scale divided by the time window length, such as 0.1% of the full scale per minute, ensuring that slow but continuous drift can be detected. This method treats both positive and negative drift equally and is suitable for applications where the drift direction is not critical.

[0073] Another approach is to set separate thresholds for positive and negative drift, as drift in different directions may correspond to different aging mechanisms. In practice, the positive drift threshold can be set relatively loosely, because temperature sensor aging typically manifests as decreased sensitivity, leading to lower output; the negative drift threshold is set relatively strictly, as negative drift may indicate more serious problems. This differentiated setting improves the targeting of fault diagnosis and provides directional guidance for subsequent maintenance.

[0074] Cumulative drift can also be used to calculate the cumulative change over multiple time windows. In practice, this involves not only examining the trend characteristics within a single time window but also calculating the cumulative value of the trend characteristics across multiple consecutive windows. Even if the trend characteristics of a single window do not exceed a threshold, if the cumulative value exceeds a set limit, the second judgment condition is still considered met. This method can capture extremely slow drift processes, making it particularly effective for early warning and avoiding potential missed detections that may occur with single-window judgment.

[0075] Through the flexible application of the above-mentioned various implementation methods, the first and second judgment conditions can comprehensively cover various manifestations of sensor aging, ensuring both the detection rate and controlling the false alarm rate, thus achieving reliable identification of sensor aging.

[0076] If the deviation characteristics meet the third judgment condition and continue for a preset number of time windows, the fault type is determined to be system offset.

[0077] The third judgment condition is a threshold judgment of the deviation characteristic value, used to identify the degree to which the overall output signal deviates from the reference. The preset quantity refers to the number of time windows that need to continuously meet the condition, used to confirm the persistence and stability of the offset. The persistence requirement avoids misjudgments caused by transient interference.

[0078] For example, the threshold for the third judgment condition needs to be determined based on the accuracy class of the temperature transmitter and the application requirements. For a transmitter with an accuracy class of 0.1, the deviation threshold can be set to 1% of the full scale; for a transmitter with an accuracy class of 0.5, it can be appropriately relaxed. The preset number of time windows is usually set to 3 to 5, and the specific value needs to balance the timeliness and reliability of fault detection.

[0079] If the fluctuation characteristics meet the fourth judgment condition or an interruption in the output signal data is detected, the fault type is determined to be a hardware fault.

[0080] The fourth criterion is the upper limit of the fluctuation characteristic value; exceeding this limit indicates that the signal is severely distorted. Signal interruption detection includes two situations: signal value exceeding the limit and communication abnormalities. "OR" logic is used because hardware faults manifest in various ways.

[0081] For example, the threshold setting for the fourth judgment condition needs to be significantly higher than the fluctuation level during normal operation. The normal output range of a temperature transmitter is 4-20mA, and the judgment threshold for signal interruption is usually set slightly below 4mA and slightly above 20mA, such as 3.6mA and 21mA, leaving a certain margin within the normal range. The judgment of communication interruption is based on communication failures for multiple consecutive sampling cycles.

[0082] If none of the above fault conditions are met, the temperature transmitter is determined to be in normal condition.

[0083] Furthermore, after matching the fault feature vector with the fault judgment rules, this application also includes the following steps:

[0084] Obtain the set of historical fault feature vectors, which stores multiple historical feature vectors and their corresponding confirmed fault types.

[0085] For example, the historical fault feature vector set is stored in the monitoring system's database. Each record contains information such as a timestamp, device number, values ​​of each dimension of the feature vector, and the confirmed fault type. The retention period and quantity of historical data are determined based on storage capacity and statistical requirements.

[0086] Calculate the similarity between the fault feature vector and each historical feature vector in the historical fault feature vector set.

[0087] For example, similarity calculation uses a distance metric. First, the features are normalized in each dimension, mapping features with different dimensions to the same numerical range. Then, the distance between the vectors is calculated; the smaller the distance, the higher the similarity. Normalization methods can include min-max normalization or z-score normalization.

[0088] Select the historical feature vectors with the highest similarity and statistically analyze the distribution of fault types corresponding to the historical feature vectors.

[0089] For example, select the top 5 to 10 historical feature vectors with the highest similarity and count the frequency of their corresponding fault types. If a certain fault type occurs most frequently, then that type is the highest-proportion type. The selected number needs to ensure the representativeness of the statistics.

[0090] If the type with the highest percentage in the fault type distribution is inconsistent with the fault type, the type with the highest percentage will be used as the redefined fault type.

[0091] Inconsistency refers to a difference between the results of rule-based judgments and those based on historical data statistics. Historical data validation provides empirical references and can correct potential biases in rule-based judgments. Correction is contingent on the historical data possessing sufficient similarity and reliability.

[0092] Furthermore, the fault feature vector and the redefined fault type are stored in the historical fault feature vector set.

[0093] New diagnostic results must be confirmed before being added to the historical database. Confirmation methods include automatic and manual confirmation, with manually confirmed data having higher reliability. The confirmation method should be recorded during data storage for differentiated treatment in subsequent use.

[0094] Analyze the feature value distribution corresponding to each fault type in the historical fault feature vector set.

[0095] For example, for each fault type, the numerical distribution of each characteristic dimension is statistically analyzed, including statistical parameters such as mean, standard deviation, and distribution range. The analysis results are used to evaluate the rationality of the current judgment conditions.

[0096] Adjust the first, second, third, and fourth judgment conditions based on the distribution of eigenvalues.

[0097] The principle behind these adjustments is to improve diagnostic accuracy and reduce false positives and false negatives. Adjustments must be based on sufficient data accumulation to avoid frequent changes. Each adjustment should be moderate in magnitude and must be validated before formal application.

[0098] Furthermore, after determining the fault type of the temperature transmitter based on the matching results, this application also includes the following steps:

[0099] A diagnostic report is generated, which records the fault type, fault characteristic values, and the time of fault occurrence.

[0100] For example, the diagnostic report uses a structured format and includes equipment identification information, fault diagnosis results, detailed characteristic data, environmental condition records, etc. The report format follows industry standards, facilitating archiving and traceability.

[0101] Determine the corresponding alarm level based on the type of fault.

[0102] The alarm levels are divided into several grades, with different alarm levels corresponding to different fault types. Sensor aging usually corresponds to a lower alarm level, used to alert maintenance personnel; system offset corresponds to a medium alarm level, requiring timely handling; hardware failure corresponds to the highest alarm level, requiring immediate response.

[0103] The diagnostic report and alarm level are sent to the monitoring system via the communication interface.

[0104] For example, the communication interface supports industrial communication standards such as HART and Modbus protocols. Diagnostic information is encoded and transmitted according to the format specified in the protocol. For high-level alarms, in addition to digital communication, a hardwired switch signal can also be output to trigger the audible and visual alarm device.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] Based on the same inventive concept, this application also provides an intelligent temperature transmitter fault diagnosis system. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more intelligent temperature transmitter fault diagnosis system embodiments provided below can be found in the limitations of the intelligent temperature transmitter fault diagnosis method described above, and will not be repeated here.

[0107] In one exemplary embodiment, such as Figure 3 As shown, an intelligent temperature transmitter fault diagnosis system is provided, including a reference value compensation module, a feature extraction module, a vector construction module, and a fault judgment module, wherein:

[0108] The reference value compensation module is used to acquire the environmental and operating parameters of the temperature transmitter, and to compensate the initial reference value based on the environmental and operating parameters to obtain the current reference value.

[0109] The feature extraction module is used to acquire multiple consecutive output signal data from the temperature transmitter and extract fluctuation features, trend features, and deviation features from the output signal data.

[0110] The vector construction module is used to construct fault feature vectors based on fluctuation characteristics, trend characteristics, and deviation characteristics.

[0111] The fault diagnosis module is used to match fault feature vectors with fault diagnosis rules and determine the fault type of the temperature transmitter based on the matching results.

[0112] The modules in the aforementioned intelligent temperature transmitter fault diagnosis system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0113] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a fault diagnosis method for an intelligent temperature transmitter. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0114] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0116] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0117] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0121] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A fault diagnosis method for an intelligent temperature transmitter, characterized in that, include: The environmental and operating parameters of the temperature transmitter are acquired, and the initial reference value is compensated based on the environmental and operating parameters to obtain the current reference value. Collect multiple consecutive output signal data from the temperature transmitter, and extract fluctuation characteristics, trend characteristics, and deviation characteristics from the output signal data; A fault feature vector is constructed based on the fluctuation characteristics, trend characteristics, and deviation characteristics; The fault feature vector is matched with the fault judgment rules, and the fault type of the temperature transmitter is determined based on the matching result. After matching the fault feature vector with the fault judgment rules, the method further includes: Obtain a set of historical fault feature vectors, wherein the set of historical fault feature vectors stores multiple historical feature vectors and corresponding confirmed fault types; Calculate the similarity between the fault feature vector and each historical feature vector in the historical fault feature vector set; Select the historical feature vectors with the highest similarity and statistically analyze the distribution of fault types corresponding to the historical feature vectors. If the type with the highest percentage in the fault type distribution is inconsistent with the fault type, the type with the highest percentage shall be used as the redefined fault type. The method further includes: The fault feature vector and the redefined fault type are stored in the historical fault feature vector set; Analyze the feature value distribution corresponding to each fault type in the historical fault feature vector set; The first, second, third, and fourth judgment conditions are adjusted based on the distribution of the characteristic values. The first judgment condition is a range judgment of the fluctuation characteristic value, i.e., the fluctuation characteristic value exceeds the lower threshold of the normal state but does not exceed the upper threshold, used to identify signal instability caused by sensor performance degradation. The second judgment condition is a threshold judgment of the trend characteristic value, i.e., the trend characteristic value exceeds a preset drift threshold, used to identify slow drift caused by sensor aging. The third judgment condition is a threshold judgment of the deviation characteristic value, i.e., the deviation characteristic value exceeds a preset deviation threshold, used to identify the degree to which the overall output signal deviates from the reference. The fourth judgment condition is an upper limit judgment of the fluctuation characteristic value, i.e., the fluctuation characteristic value exceeds the upper limit threshold, indicating that the signal has been severely distorted. After determining the fault type of the temperature transmitter based on the matching result, the method further includes: A diagnostic report is generated, which records the fault type, fault characteristic values, and fault occurrence time. Determine the corresponding alarm level based on the fault type; The diagnostic report and the alarm level are sent to the monitoring system via the communication interface.

2. The fault diagnosis method for an intelligent temperature transmitter as described in claim 1, characterized in that: The process of acquiring environmental and operating parameters of the temperature transmitter, and compensating the initial reference value based on the environmental and operating parameters to obtain the current reference value includes: The current ambient temperature of the temperature transmitter is obtained as the environmental parameter. The cumulative operating time of the temperature transmitter is obtained as the operating parameter; Calculate the temperature compensation value based on the deviation between the current ambient temperature and the standard temperature, and the temperature compensation ratio. Calculate the time compensation value based on the relationship between the cumulative running time and the standard time, as well as the time compensation ratio; The initial reference value is calculated by combining it with the temperature compensation value and the time compensation value to obtain the current reference value.

3. The fault diagnosis method for an intelligent temperature transmitter as described in claim 2, characterized in that: The process of acquiring multiple consecutive output signal data from the temperature transmitter and extracting fluctuation characteristics, trend characteristics, and deviation characteristics from the output signal data includes: Collect multiple output signal data from the temperature transmitter within a time window; Calculate the dispersion value of the plurality of output signal data, and use the dispersion value as the fluctuation feature; The trend characteristics are calculated based on the changes in the first and last output signal data within the time window. Calculate the difference between each output signal data and the current reference value, and use the maximum difference value as the deviation feature.

4. The fault diagnosis method for an intelligent temperature transmitter as described in claim 3, characterized in that: The fault feature vector is matched with fault judgment rules, and the fault type of the temperature transmitter is determined based on the matching result, including: If the fluctuation characteristics meet the first judgment condition and the trend characteristics meet the second judgment condition, the fault type is determined to be sensor aging; If the deviation characteristics meet the third judgment condition and continue for a preset number of time windows, the fault type is determined to be system offset; If the fluctuation characteristics meet the fourth judgment condition or an interruption in the output signal data is detected, the fault type is determined to be a hardware fault. If none of the above fault conditions are met, the temperature transmitter is determined to be in normal condition.

5. A fault diagnosis system for an intelligent temperature transmitter, employing the fault diagnosis method for an intelligent temperature transmitter as described in any one of claims 1 to 4, characterized in that, It includes a baseline compensation module, a feature extraction module, a vector construction module, and a fault diagnosis module, among which: The reference value compensation module is used to acquire the environmental parameters and operating parameters of the temperature transmitter, and to perform compensation processing on the initial reference value according to the environmental parameters and operating parameters to obtain the current reference value. The feature extraction module is used to collect multiple consecutive output signal data from the temperature transmitter and extract fluctuation features, trend features and deviation features from the output signal data. The vector construction module is used to construct a fault feature vector based on the fluctuation characteristics, the trend characteristics, and the deviation characteristics. The fault determination module is used to match the fault feature vector with the fault determination rules, and determine the fault type of the temperature transmitter based on the matching result. After matching the fault feature vector with the fault judgment rules, the method further includes: Obtain a set of historical fault feature vectors, wherein the set of historical fault feature vectors stores multiple historical feature vectors and corresponding confirmed fault types; Calculate the similarity between the fault feature vector and each historical feature vector in the historical fault feature vector set; Select the historical feature vectors with the highest similarity and statistically analyze the distribution of fault types corresponding to the historical feature vectors. If the type with the highest percentage in the fault type distribution is inconsistent with the fault type, the type with the highest percentage shall be used as the redefined fault type. The method further includes: The fault feature vector and the redefined fault type are stored in the historical fault feature vector set; Analyze the feature value distribution corresponding to each fault type in the historical fault feature vector set; The first judgment condition, the second judgment condition, the third judgment condition, and the fourth judgment condition are adjusted according to the feature value distribution. After determining the fault type of the temperature transmitter based on the matching result, the method further includes: A diagnostic report is generated, which records the fault type, fault characteristic values, and fault occurrence time. Determine the corresponding alarm level based on the fault type; The diagnostic report and the alarm level are sent to the monitoring system via the communication interface.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent temperature transmitter fault diagnosis method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent temperature transmitter fault diagnosis method according to any one of claims 1 to 4.

Images