Valve path detection method and system based on Internet of Things

Abstract

The invention relates to the technical field of fault detection of the Internet of Things, in particular to a valve path detection method and system based on the Internet of Things, and the method comprises the following steps: based on real-time data of a valve path, removing high-frequency noise and high-frequency components in temperature fluctuation through a low-pass filter, carrying out the mean value smoothing operation of pressure data, and carrying out the mean value smoothing operation; and performing data standardization conversion on the flow data to obtain valve operation state data. According to the method, through real-time collection and optimization processing of valve operation data, it is ensured that the data is accurate and stable, weighted calculation is carried out in combination with the data influence degree, the representativeness of state feature extraction and the perception ability of working condition changes are enhanced, and based on state feature trend analysis, the sensitivity of fault detection is improved; and health state evaluation is carried out in combination with the operation duration and the load change, so that health state scoring is realized, the predictability of the long-term operation state is improved, false alarms and missing alarms are reduced, and the accuracy of fault early warning and the equipment health monitoring capability are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things fault detection, and in particular to a valve circuit detection method and system based on the Internet of Things. Background Art

[0002] The field of IoT fault detection technology includes real-time monitoring, diagnosis and processing of IoT device faults through sensors, communication networks and data processing. The core content of this technology is to ensure that IoT devices can detect and resolve faults in a timely manner during operation, thereby ensuring their stability and reliability. IoT fault detection technology involves the identification of equipment failure modes, the collection and analysis of sensor data, the establishment of fault diagnosis models and fault prediction. It can improve the operation and maintenance efficiency of equipment, reduce maintenance costs, and take corresponding preventive or repair measures when equipment fails.

[0003] Among them, the valve path detection method refers to a fault detection technology for valve control systems in the Internet of Things. It aims to monitor the working status of the valve, promptly discover faults in valve operation and diagnose them. This method mainly involves real-time monitoring of the valve status, collection and analysis of fault characteristic data, and identification of whether the valve is faulty by comparing normal and abnormal data. This method uses sensors to obtain the valve's opening and closing status, pressure changes and related parameters. By setting the standard value of the valve operation, it detects the degree of deviation and then determines whether the valve's working status is abnormal.

[0004] The existing technology has the problem of a single data processing method in valve status monitoring. It mainly relies on basic numerical comparison and fails to fully utilize the correlation between data, resulting in insufficient sensitivity to capture state changes. The data fusion method is relatively simple, only making limit judgments on single parameters, and failing to comprehensively analyze different data dimensions for weighted analysis, resulting in incomplete extraction of fault characteristics. In terms of anomaly detection, the existing technology is mainly based on fixed threshold judgments and lacks trend analysis capabilities. It is difficult to effectively identify gradual faults, especially when the pressure and flow offsets are small, resulting in the problem of failure to detect faults in time. For health status assessment, the existing technology relies on the changing trend of a single variable and fails to conduct a comprehensive assessment based on the equipment's operating time and load conditions, which limits the accuracy of health status prediction, reduces the accuracy of fault detection, and fails to identify potential risks in a timely manner, thereby increasing the maintenance cost of the equipment and affecting the stability and reliability of the overall system. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a valve circuit detection method and system based on the Internet of Things.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a valve circuit detection method based on the Internet of Things, comprising the following steps: S1: Based on the real-time data of the valve circuit, high-frequency noise is removed through a low-pass filter, high-frequency components in temperature fluctuations are removed, mean smoothing calculations are performed on the pressure data, and data standardization conversion is performed on the flow data to obtain the valve operation status data; S2: Based on the valve operating status data, weights are set for the degree of influence of the valve status, weighted fusion is performed, the status mean is calculated, the status mean and fluctuation range are identified, and trends of each group of data are compared to obtain valve status fusion feature values; S3: Based on the valve state fusion characteristic value, analyze the change trend of the state characteristics, extract the vibration amplitude and flow offset to identify the valve sealing state offset, evaluate the abnormal pressure offset based on the correlation of each set of data, analyze the state change trend, and obtain the valve operation state offset trend; S4: Based on the deviation trend of the valve operating state, perform abnormal detection rules to compare the current state data, analyze the deviation range of pressure mutation, flow mutation, and vibration abnormality, judge seal damage, blockage and leakage, identify the abnormal impact range, classify the fault warning level, and output the valve abnormality detection warning signal.

[0007] As a further solution of the present invention, the valve operation status data includes temperature characteristic data, pressure characteristic data, flow characteristic data, and vibration characteristic data; the valve state fusion characteristic value includes state mean, state fluctuation range, and data trend characteristics; the valve operation state offset trend includes sealing offset characteristics, pressure abnormality offset characteristics, and state change trend characteristics; the valve abnormality detection warning signal includes sealing damage judgment, blockage judgment, leakage judgment, and fault warning level.

[0008] As a further solution of the present invention, the steps for obtaining the valve operating status data are specifically as follows: S111: Based on the real-time data of the valve circuit, temperature, pressure, flow and vibration data are extracted. High-frequency signals are filtered out for the temperature data. By applying a low-pass filter, the energy of the high-frequency segment in the time series is attenuated, the high-frequency components in the frequency distribution are suppressed, and the instantaneous high-frequency interference signals are eliminated to obtain stable temperature data. S112: Calculating a sliding mean of the pressure data based on the temperature steady data, smoothing short-term fluctuation signals, eliminating deviations caused by drastic changes in the data, and obtaining pressure smoothing data; S113: Call the pressure smoothing data and perform standardization conversion on the flow data using the formula: ; Calculate the standardized flow value and obtain the valve operation status data; in, represents the normalized flow value, Represents the original traffic data, and Respectively represent the minimum and maximum values of the flow data, represents the pressure smoothed data, Represents temperature steady state data.

[0009] As a further solution of the present invention, the steps for obtaining the valve state fusion characteristic value are specifically as follows: S211: Based on the valve operating status data, an influence weight of each type of status parameter is set, and weight normalization calculation is performed on the temperature, pressure, flow, and vibration data. The influence degree of the valve status is analyzed, and a corresponding normalized weight coefficient is assigned. Then, weighted fusion is performed to obtain a state weighted fusion value. S212: Calling the state weighted fusion value to identify the stability of temperature, pressure, flow, and vibration data, analyzing the fluctuation range of each type of data, evaluating the change of the state mean in each time segment, and obtaining the state mean and fluctuation range; S213: Based on the state mean and fluctuation range, the change trend of each group of data is compared using the formula: ; Fusion trend information to obtain valve status fusion feature value; in, represents the valve state fusion eigenvalue, Representative The weighting coefficient of each state data, Representative The state value of each state data time segment, represents the state mean of the state data, Representative The standard deviation of the state data, Represents the number of categories of status data.

[0010] As a further solution of the present invention, the steps for obtaining the deviation trend of the valve operation state are specifically as follows: S311: Based on the valve state fusion characteristic value, identifying the vibration amplitude offset and the flow rate offset, comparing the current measurement value with the reference value, screening the characteristic items with prominent offset amplitudes, and obtaining a characteristic offset amplitude index; S312: Call the characteristic offset amplitude index to analyze the impact of the vibration amplitude offset on the flow offset using the formula: ; Calculate the sealing state deviation value, filter the influencing feature items, and obtain the key sealing deviation characteristics; in, Represents the deviation value of the sealing status, represents the vibration amplitude offset, represents the flow offset, Representative The offset correction value that affects the characteristic item, Represents the number of influencing feature items, Representative The flow offset that affects the characteristic item; S313: Call the key sealing deviation feature, combine it with the pressure change trend, evaluate the correlation between the sealing deviation and the pressure abnormality, identify the abnormal deviation, and obtain the valve operation status deviation trend.

[0011] As a further solution of the present invention, the steps for obtaining the valve abnormality detection warning signal are specifically as follows: S411: Based on the deviation trend of the valve operation state, extract the original operation data and real-time monitoring data, calculate the pressure mutation rate, flow mutation rate, and vibration deviation rate, compare them with the set deviation reference value, determine whether they exceed the deviation range, and obtain the abnormal deviation degree; S412: calling the abnormal deviation degree, combining it with the valve sealing status data, comparing the leakage determination threshold and the blockage determination threshold, analyzing the degree of seal damage and the degree of blockage, and obtaining a seal damage index and a blockage index; S413: Based on the seal damage index and the blockage index, combined with the valve operating load change rate, identify the abnormal impact range and fault warning level using the formula: ; Calculate the abnormal impact range index, call the warning level classification standard, match the corresponding warning level, and output the valve abnormality detection warning signal; in, Represents the abnormal impact range index, Represents the seal damage index, represents the congestion index, Represents the operating load change rate, Represents the current vibration deviation rate, Indicates the vibration reference value.

[0012] As a further embodiment of the present invention, the method further comprises step S5: S5: Based on the valve abnormality detection warning signal, identify the probability of health status change according to the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude, analyze the status change trend in the future time period, identify the health status change direction according to the operating time and load change, evaluate the health status score, and obtain valve health status detection data; The valve health status detection data includes health change probability, health change trend, health change direction, and health status score.

[0013] As a further solution of the present invention, the steps for obtaining the valve health status detection data are specifically as follows: S511: Based on the valve abnormality detection warning signal, extract the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude data, calculate the change rate, identify the health state change probability, determine the deviation between the current data and the health state baseline value, and obtain the health state deviation amount; S512: The health status deviation is called, and the state change rate is analyzed according to the running time and load change, using the formula: ; Calculate the health status score and obtain the health status assessment value after normalization; in, represents the health status score, Represents the health status deviation in the kth time period, Represents the load change impact factor, represents the environmental pressure impact coefficient, Represents the running time impact coefficient of the k-th time period, Represents the state change rate correction value, represents the volatility adjustment coefficient, Represents the number of data segments; S513: Call the health status assessment value, analyze the health status trend, identify the short-term prediction value, combine the state change probability, and output the valve health status detection data.

[0014] The valve path detection system based on the Internet of Things is used to execute the valve path detection method based on the Internet of Things. The system includes: The state perception module is based on real-time valve circuit data, including valve operation data monitored by temperature sensors, pressure sensors, flow sensors, and vibration sensors. It performs low-pass filtering on temperature data, multi-point mean calculation on pressure data, standardizes flow data to form a unified dimension, and performs amplitude normalization on vibration data to obtain the original valve state parameter set. The signal conversion module sets weights for the temperature, pressure, flow, and vibration data based on the original valve state parameter set, performs weighted conversion, analyzes the fluctuation range of the state data, and compares the corresponding change trends to obtain the valve state value set; The state feature module selects the fluid delivery pipe section, segmented valve, and vibration node based on the valve state value set, analyzes the positional relationship between the vibration amplitude change and the flow fluctuation, identifies the distribution degree of the state change on the participating items of the differentiated scenarios, and obtains the state deviation trend data group; Based on the state deviation trend data group, the abnormality identification module selects the remote pipeline interface, multi-valve joint control area, and abnormal mutation node, identifies the data group location and continuous change amplitude corresponding to the vibration peak, screens the sealing abnormal section, blockage area and leakage channel, and outputs the valve abnormality detection warning signal; The health assessment module performs a time period analysis on the abnormal data group based on the output valve abnormality detection warning signal, determines the superposition trend and downward turning point of the change value under the continuous operation state, adjusts the health scoring model parameters, and obtains the valve health status detection data.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are: The present invention optimizes data processing methods by collecting and processing multiple key data points in real time during valve operation, employing low-pass filtering, mean smoothing, and normalization conversion methods to ensure more accurate and stable acquired status data. During data fusion, weighted calculations are performed based on the influence of different data categories, making the extracted status features more representative and enhancing the ability to perceive valve status changes under different operating conditions. Trend analysis based on status features enables earlier detection of sealing anomalies, pressure excursions, and status fluctuations, increasing sensitivity to potential faults. Anomaly detection utilizes an offset range comparison method, cross-analyzing multi-dimensional data such as pressure, flow, and vibration to achieve more accurate fault identification and distinguish different types of anomalies. Based on the changing trends of status data, the valve health status is further assessed. A health status score is generated based on operating time and load variations, improving the predictability of the long-term operating status of the equipment. This combination of data processing, fusion, trend analysis, anomaly detection, and health assessment significantly improves the accuracy and reliability of fault detection, effectively reduces false positives and false negatives, improves the accuracy of fault warnings, and enhances the ability to continuously monitor the health of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 This is a flow chart for obtaining valve operating status data in the present invention; Figure 3This is a flow chart for obtaining valve state fusion feature values in the present invention; Figure 4 A flow chart for obtaining a valve operating state deviation trend in the present invention; Figure 5 This is a flow chart for obtaining a warning signal for valve abnormality detection in the present invention; Figure 6 This is a flow chart for obtaining valve health status detection data in the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0019] Example 1 See also Figure 1 The present invention provides a technical solution: a valve circuit detection method based on the Internet of Things, comprising the following steps: S1: Based on the real-time data of the valve circuit, including temperature, pressure, flow, and vibration data, a low-pass filter is used to remove high-frequency noise and high-frequency components in temperature fluctuations. The pressure data is averaged and smoothed, and the flow data is normalized to obtain the valve operating status data. S2: Based on the valve operating status data, weights are set for the degree of influence on the valve status, and weighted fusion is performed. The temperature, pressure, flow, and vibration data are standardized and converted based on the weights. The status mean is calculated, the status mean and fluctuation range are identified, and the trend of each type of data is compared to obtain the valve status fusion characteristic value. S3: Based on the valve state fusion feature value, analyze the change trend of the state characteristics, extract the vibration amplitude and flow offset to identify the valve sealing state offset, evaluate the abnormal pressure offset based on the correlation of each set of data, analyze the state change trend, and obtain the valve operation state offset trend; S4: Based on the deviation trend of the valve operating status, the abnormality detection rules are compared with the current status data to analyze the deviation range of pressure mutation, flow mutation, and vibration abnormality, determine seal damage, blockage and leakage, identify the abnormal impact range, classify the fault warning level, and output the valve abnormality detection warning signal; S5: Based on the valve abnormality detection warning signal, the probability of health status change is identified according to the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude. The status change trend in the future time period is analyzed. The direction of health status change is identified according to the operating time and load change. The health status score is evaluated to obtain the valve health status detection data.

[0020] Valve operation status data includes temperature characteristic data, pressure characteristic data, flow characteristic data, and vibration characteristic data. The valve state fusion characteristic values include state mean, state fluctuation range, and data trend characteristics. The valve operation state deviation trend includes sealing deviation characteristics, pressure abnormality deviation characteristics, and state change trend characteristics. The valve abnormality detection warning signal includes sealing damage judgment, blockage judgment, leakage judgment, and fault warning level. The valve health status detection data includes health change probability, health change trend, health change direction, and health status score.

[0021] See also Figure 2 , the specific steps for obtaining valve operation status data are as follows: S111: Based on the real-time data of the valve circuit, temperature, pressure, flow and vibration data are extracted. High-frequency signals are filtered out for the temperature data. By applying a low-pass filter, the energy of the high-frequency segment in the time series is attenuated, the high-frequency components in the frequency distribution are suppressed, and the instantaneous high-frequency interference signals are eliminated to obtain stable temperature data. Stable temperature data: refers to data that has been smoothed by low-pass filtering and other processes to remove high-frequency noise and fluctuations, reflecting the stable trend of temperature changes in the system. This process ensures the stability of temperature data and facilitates subsequent status analysis and standardization. First, the temperature, pressure, flow and vibration data in the valve circuit are collected. The data is monitored in real time by sensors and uploaded to the data processing center. In the processing of temperature data, a low-pass filter is applied to process the temperature signal. This process is mainly to reduce the impact of high-frequency noise. The low-pass filter weakens the signal frequencies above a specific frequency threshold according to this threshold, thereby maintaining the stability and reliability of the data. For example, in a chemical plant, temperature monitoring is a key factor. The temperature of the chemical reaction must be kept within a relatively stable range to ensure product quality. In this way, production deviations caused by sudden temperature changes can be effectively reduced, and finally temperature-stable data can be obtained. The data reflects the temperature changes after the high-frequency noise is reduced, providing a basis for further data analysis and use.

[0022] S112: Based on the temperature steady data, calculate the sliding mean of the pressure data, smooth the short-term fluctuation signal, eliminate the deviation of the data with drastic changes, and obtain the pressure smoothed data; Pressure smoothing data: This is pressure data processed by means of mean smoothing, etc. The main purpose is to remove sudden changes and noise interference, highlight the stable change characteristics of pressure, and avoid the influence of short-term fluctuations on the judgment of valve status; Smoothing the pressure data includes calculating the sliding mean of the pressure data. That is, by setting a fixed time window, the average value of the pressure data within the window is continuously calculated. As the window slides, new data enters the window and old data exits, thereby updating the average value. This method can effectively reduce the impact of sudden pressure changes and improve the stability of the data. For example, in a water treatment plant, the stability of pressure directly affects the flow rate of the water flow and the filtration efficiency of the filter. Through smoothing, abnormal equipment operation caused by pressure fluctuations can be avoided, and finally pressure smoothed data is obtained. The data provides a reliable basis for subsequent flow control and equipment protection.

[0023] S113: Call the pressure smoothing data and perform standardization conversion on the flow data using the formula: ; Calculate the standardized flow value and obtain the valve operation status data; in, represents the normalized flow value, Represents the original traffic data, and Respectively represent the minimum and maximum values of the flow data, represents the pressure smoothed data, represents temperature steady data; Call the pressure smoothing data and temperature steady data to standardize the flow data. Assume that in an actual operation, the original flow data The measurement range is 300 to 800 units, where That is, the minimum value is 300. That is, the maximum value is 800. If the pressure smoothing data is obtained is 50 units, while the temperature is stable If the unit is 20, then substitute the formula to calculate the standardized flow rate The process is as follows: According to the formula, the normalized ratio of the flow needs to be calculated, namely: ; Calculate the square root portion of the temperature and pressure difference: ; Multiplying these two calculations gives the normalized flow rate: ; At the lowest flow rate, since the scale factor is 0, the normalized flow rate This indicates that the normalized flow rate under these specific conditions is extremely low. This calculation not only provides an intuitive understanding of the normalization of flow data, but also, through the introduction of actual data, closely relates the processing to actual application scenarios. For example, in water treatment facilities, such data can be used to monitor the response of equipment under extreme operating conditions. This method is very useful in actual operations, helping operators understand the changes in fluid flow under different operating conditions, thereby making better adjustments and optimization decisions.

[0024] See also Figure 3 ,The specific steps for obtaining the valve state fusion feature value are: S211: Based on the valve operating status data, the influence weight of each type of status parameter is set, and the temperature, pressure, flow, and vibration data are weighted normalized. The influence of the valve status is analyzed, and the corresponding normalized weight coefficient is assigned. The weighted fusion is performed to obtain the state weighted fusion value; Temperature, pressure, flow and vibration data are collected from real-time monitoring. The data is obtained through high-precision sensors and transmitted to the control center in real time. In order to accurately reflect the specific impact of each data on the valve status, the weight of each data is determined based on historical data and prediction models. The weight reflects the relative importance of different data in valve performance. For example, in oil pipelines, sudden changes in pressure indicate potential leakage or blockage. Pressure data is given a higher weight. The weight is used to perform weighted fusion on the data to obtain a weighted value that comprehensively reflects the current status of the valve. This weighted value ensures that the response more accurately reflects the actual operating conditions by comprehensively considering each data point and its importance. The final state weighted fusion value provides a quantitative and comprehensive data reference for subsequent analysis.

[0025] S212: Calling the state weighted fusion value to identify the stability of temperature, pressure, flow, and vibration data, analyzing the fluctuation range of each type of data, evaluating the change of the state mean in each time segment, and obtaining the state mean and fluctuation range; Calculate the mean and fluctuation range of the state weighted fusion value, identify abnormal states and fluctuation trends, and calculate the mean of each data point within a set time window. This method can smooth short-term fluctuations and observe trend changes over a longer period. For example, in the chemical production process, the stability of temperature and pressure has a direct impact on product quality. By monitoring their mean and fluctuation, control parameters can be adjusted in time to avoid production anomalies. The calculation of the fluctuation range provides information on the amplitude of data changes, which helps to evaluate stability and maintenance needs. Through complex data processing, the state mean and fluctuation range are finally obtained, providing data support for subsequent trend analysis and early warning.

[0026] S213: Based on the state mean and fluctuation range, the change trend of each group of data is compared using the formula: ; Fusion trend information to obtain valve status fusion feature value; in, represents the valve state fusion eigenvalue, Representative The weighting coefficient of each state data, Representative The state value of each state data time segment, represents the state mean of the state data, Representative The standard deviation of the state data, The number of categories representing status data; Compare data trends to identify any anomalies or long-term changes. In practical applications, for example, in an industrial steam pipeline, four types of data need to be analyzed: temperature, pressure, flow, and vibration to monitor valve operation. Suppose the data within a certain time period is analyzed: Temperature data (unit: °C): ; Pressure data (unit: MPa): ; Flow data (unit: L / s): ; Vibration data (unit: mm / s): ; Calculate the mean and standard deviation for each data type: Temperature mean ; Pressure average ; Traffic mean ; Vibration mean ; Next, calculate the standard deviation: ; ; ; ; Assume that the weights are , calculate the valve state fusion eigenvalue : ; ; ; The final calculated valve state fusion eigenvalue is 1.083, which represents the weighted sum of the standardized deviation degrees of each state parameter during the current monitoring period and can be used to judge the overall health status or operating trend of the valve.

[0027] See also Figure 4 , the specific steps for obtaining the valve operation status deviation trend are: S311: Based on the valve state fusion characteristic value, the vibration amplitude offset and the flow offset are identified, the current measurement value is compared with the reference value, and the characteristic items with prominent offset amplitude are screened to obtain the characteristic offset amplitude index; Calculating the vibration amplitude offset and flow offset involves comparative analysis of real-time monitoring data and set benchmark values. For example, in an industrial process monitoring, the set benchmark vibration amplitude is 0.5mm, and the real-time data is displayed as 0.65mm. Through this calculation, the current vibration amplitude offset can be known, and then a joint analysis is performed based on the offset value and flow offset. Assuming that the baseline value of the flow is 100m³ / h and the real-time measurement value is 120m³ / h, the flow offset is significant. Then, the offset amplitude and change rate are calculated using statistical analysis methods. The key offset features are screened out based on the offset trend, and the feature items of significant offset are selected. For example, when the offset amplitude exceeds 10% of the benchmark value, it is considered significant, thereby deciding whether to adjust the control parameters of the industrial process. Finally, the characteristic offset amplitude indicator is obtained, which can effectively monitor and adjust the dynamic changes on the production line to ensure production safety and efficiency.

[0028] S312: Call the characteristic offset amplitude index to analyze the impact of the vibration amplitude offset on the flow offset using the formula: ; Calculate the sealing state deviation value, filter the influencing feature items, and obtain the key sealing deviation characteristics; in, Represents the deviation value of the sealing status, represents the vibration amplitude offset, represents the flow offset, Representative The offset correction value that affects the characteristic item, Represents the number of influencing feature items, Representative The flow offset that affects the characteristic item; Call the acquired characteristic offset amplitude indicator and substitute the specific values of the vibration amplitude offset and flow offset into the calculation. Assuming that the vibration amplitude of a key valve on a chemical production line is measured to be 0.65mm and the baseline value is 0.50mm, the vibration amplitude offset is calculated as follows: ; At the same time, the flow rate of the valve is measured to be 120, and the reference value is 100. The flow offset is calculated as follows: ; In addition, considering multiple influencing feature items (assuming m=3), the corresponding flow offsets are 10, 15, and 5, and the corresponding offset correction values are Set to 0.05, 0.03, and 0.07 respectively; Substituting into the formula: ; Calculate the molecular part: ; Calculate the denominator: ; The final calculated sealing state deviation value is: ; This value indicates that the current sealing state of the valve has a certain degree of deviation. If the deviation exceeds the set safety threshold (assuming the threshold is 0.12), maintenance or replacement of the sealing component is required. In industrial applications, a reasonable safety range is set. For example, if The maintenance process is triggered. If Stop the machine immediately for inspection; The calculated sealing state deviation indicates that the valve has a leakage risk. By further screening the characteristic items that have the most significant impact on sealing, the key parts can be identified. For example, if it is found that the main contribution comes from the characteristic item with a large flow deviation, it is necessary to check whether the fluid delivery pressure is stable. If the main contribution comes from abnormal vibration amplitude, it is necessary to check whether the pipeline has structural changes or loose supports. Finally, the key sealing deviation characteristics are obtained, which can be used for further status evaluation and optimization of the early warning mechanism.

[0029] S313: Invoke key sealing deviation features, combine them with pressure change trends, evaluate the correlation between sealing deviation and pressure anomalies, identify abnormal deviations, and obtain the valve operation status deviation trend; Evaluate the correlation between sealing deviation and pressure anomalies. Assume that the normal operating pressure range of the current valve should be between 200-250psi. Through monitoring, it is found that the pressure suddenly drops to 180psi, which is significantly lower than the normal value. At this time, calculate the abnormal deviation and analyze the overall trend. If it is found that the sealing deviation is highly correlated with the pressure drop, it is necessary to further inspect the physical condition of the valve, which involves replacing the seal or the entire valve. Through this comprehensive analysis, the operating parameters of the factory can be adjusted in real time, improving the accuracy and response speed of safety management, and ultimately determining the deviation trend of the valve operating status.

[0030] See also Figure 5, the specific steps for obtaining the valve abnormality detection warning signal are as follows: S411: Based on the deviation trend of the valve operation status, extract the original operation data and real-time monitoring data, calculate the pressure mutation rate, flow mutation rate, and vibration deviation rate, compare them with the set deviation reference value, determine whether it exceeds the deviation range, and obtain the abnormal deviation degree; Monitor the valve operation status and conduct real-time monitoring of the valve's pressure mutation, flow mutation and vibration status. In intelligent manufacturing scenarios, such as the automated management and control of a chemical plant, real-time monitoring data can be collected through sensors. Pressure sensors, flow meters and vibration sensors continuously send data to the control center. By analyzing the data and comparing it with the preset safe operation parameters, it is determined whether there is an abnormality. For the pressure mutation rate, if the monitored pressure value exceeds the preset range of change in a short period of time (such as within 5% is normal, and more than 5% is considered abnormal), it is considered a pressure mutation. The same is true for flow and vibration, using similar parameters and thresholds for judgment. In this way, abnormal conditions in equipment operation can be effectively identified, accidents can be prevented, and abnormal deviation can be obtained.

[0031] S412: Calling the abnormal deviation degree, combining it with the valve sealing status data, comparing the leakage judgment threshold and the blockage judgment threshold, analyzing the degree of seal damage and the degree of blockage, and obtaining the seal damage index and the blockage index; Diagnose valve seal damage and blockage. If the abnormal deviation is higher than the preset threshold (such as the threshold is set to 0.1), further data analysis is performed to determine whether the seal is damaged or the valve is blocked. The degree of seal damage and blockage can be calculated by comparing the deviation between the current data and the historical normal operation data. For example, if the calculated seal damage index is 0.3 and the blockage index is 0.2, the set benchmark values (such as the normal range is 0-0.5) are used for judgment. Through analysis, the maintenance team can make timely repair or replacement decisions to obtain the seal damage index and blockage index.

[0032] S413: Based on the seal damage index and blockage index, combined with the valve operating load change rate, identify the abnormal impact range and fault warning level using the formula: ; Calculate the abnormal impact range index, call the warning level classification standard, match the corresponding warning level, and output the valve abnormality detection warning signal; in, Represents the abnormal impact range index, Represents the seal damage index, represents the congestion index, Represents the operating load change rate, Represents the current vibration deviation rate, Represents the vibration reference value; For example, in an oil pipeline, the operating load of the valve is affected by factors such as the conveying flow rate, pipeline pressure and temperature. In daily operation, the normal change rate of the flow rate is within the range of ±5%, which is considered a normal operating condition. If the load change exceeds this range, it is necessary to further analyze its impact on the system. The calculation method is as follows: First, obtain the seal damage index and congestion index ,These two parameters can be obtained by comparing the historical data of flow, pressure and leakage detection sensors.,For example, the currently measured seal damage index is 0.3 and the blockage index is 0.2,,which means that the degree of seal damage and blockage in the current state is 30% and 20% respectively; Calculate the operating load change rate , assuming the instantaneous flow rate of the current pipeline is 1200 liters / hour and the historical average flow rate is 1000 liters / hour, then: ; The flow rate change rate is 20%, which is in the abnormal range and requires further calculation of the abnormal impact range index; Calculate the difference in vibration deflection rate , assuming that the currently measured vibration deviation rate , historical vibration reference value ,but: ; Substitute the above calculation results into the formula: ; Substituting the values: ; Calculate the denominator first: , ; Calculate the numerator: ; Final calculation: ; Abnormal impact range index The value is 0.085, indicating that the valve abnormality is in the slight deviation range at the current state, which is still within the acceptable range, but requires continuous monitoring to prevent further deterioration; According to the warning level classification standard, it is assumed that the warning level is divided into: low risk ( ), medium risk ( ), high risk ( ), the calculated It is in the low-risk range, so no warning is triggered. Only enhanced monitoring is required. If subsequent data deteriorates further, the risk level needs to be reassessed based on the new value, and finally a valve abnormality detection warning signal is output.

[0033] See also Figure 6 ,The specific steps for obtaining valve health status detection data are as follows: S511: Based on the valve abnormality detection warning signal, extract the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude data, calculate the change rate, identify the health status change probability, determine the deviation between the current data and the health status baseline value, and obtain the health status deviation amount; Real-time data is collected from valves, such as flow rate records per second, vibration intensity index per minute, and pressure fluctuation range. This data is monitored in actual industrial pipelines via sensors. Basic data can be obtained in real time based on the valve's operating mode. For example, in a hydraulic system, a properly operating valve should maintain relatively stable flow and pressure in the absence of external interference. Any deviation from preset thresholds indicates potential failure or performance degradation. By monitoring this data in real time, parameters can be adjusted or necessary maintenance performed to avoid equipment failure. The rate of change of each parameter is calculated, and standard deviation and mean methods are used to quantitatively analyze data fluctuations. For example, if the standard deviation of flow exceeds a set threshold of 5%, it is considered a significant flow excursion. This allows not only real-time monitoring of valve status, but also data analysis to predict future maintenance needs and failure points. Finally, based on the changing trends of data features, the health status deviation is calculated after normalization. This result is a measure of the deviation of the valve's current health status from the standard operating mode.

[0034] S512: Call the health status deviation value, analyze the status change rate based on the running time and load changes, and use the formula: ; Calculate the health status score and obtain the health status assessment value after normalization; in, represents the health status score, Represents the health status deviation in the kth time period, Represents the load change impact factor, represents the environmental pressure impact coefficient, Represents the running time impact coefficient of the k-th time period, Represents the state change rate correction value, represents the volatility adjustment coefficient, Represents the number of data segments; In the calculation of health status score, represents the health status score, Representative The health status deviation of a time period is calculated from the real-time data of the valve. For example, if the standard flow value of a valve is 100L / min, and the flow rate drops to 95L / min during a certain time period, the flow deviation of the time period is calculated as L / min; Represents the load change impact factor, which depends on the working environment of the valve. For example, if a valve operates at an 80% load level and increases to 90% due to production demand during a certain period of time, the load change impact factor can be calculated as ; Represents the environmental pressure influence coefficient, which is used to correct the influence of the external environment on the valve operation state. For example, in the environment of 25℃ and 50℃, the wear degree of the valve seal is different, which can be set Corresponding to standard temperature, in high temperature environment ; For the denominator, Represents the operating time impact coefficient, which is used to measure the impact of long-term operation of the valve on its health status. For example, on a production line with an 8-hour working cycle, if the operating time of a valve increases to 12 hours, it can be calculated ; Represents the state change rate correction value, which depends on the suddenness of the health state change. For example, if the flow deviation change rate increases by 50% within a certain period of time, it can be set ; Represents the system fluctuation adjustment coefficient. This value is used to balance the impact of sudden fluctuations. For example, if the vibration data in a certain time period increases by 20% compared with the previous time period, you can set ; Assume calculation time period to The data is as follows: ; ; ; ; ; ; Substitute into the formula to calculate the numerator: ; Calculate the denominator: ; Final calculation of health status score:

[0035] The result shows that the current valve health score is 2.97, which is high, indicating that the valve is in a relatively stable state. The maintenance threshold can be set based on this score. For example, when If it is lower than 2.0, it is recommended to carry out maintenance. If it is lower than 1.5, it indicates that there is a hidden danger of valve failure and it needs immediate maintenance or replacement.

[0036] S513: Call the health status assessment value, analyze the health status trend, identify the short-term prediction value, combine the state change probability, and output the valve health status detection data; The direction of health status changes in future time periods is analyzed by combining the change trend. The process involves complex data analysis and prediction models. Based on historical health assessment value data, time series analysis techniques, such as the ARIMA model, are applied to predict future status score trends. The data comes from the long-term operation records of the valve under different working conditions. Through model analysis, it is possible to foresee the trend of the valve's health status in the next operating cycle. For example, if the prediction results show that the health score gradually decreases, this means that the valve will face the risk of failure or performance degradation. The prediction is not based on a single score, but combines the probability of state change and historical trends, making the prediction more accurate and reliable. Through this analysis, the valve health status detection data is output, providing a specific prediction of the valve operating status in the next few months, and providing decision support for the maintenance team.

[0037] The valve path detection system based on the Internet of Things is used to execute the above-mentioned valve path detection method based on the Internet of Things. The system includes: The state perception module is based on real-time valve circuit data, including valve operation data monitored by temperature sensors, pressure sensors, flow sensors, and vibration sensors. It performs low-pass filtering on temperature data, multi-point mean calculation on pressure data, standardizes flow data to form a unified dimension, and performs amplitude normalization on vibration data to obtain the original valve state parameter set. Based on the original valve status parameter set, the signal conversion module sets weights for temperature, pressure, flow, and vibration data, performs weighted conversion, analyzes the fluctuation range of status data, and compares the corresponding change trends to obtain the valve status value set; The state feature module, based on the valve state value set, screens fluid delivery pipe sections, segmented valves, and vibration nodes, analyzes the positional relationship between vibration amplitude changes and flow fluctuations, identifies the distribution of state changes on the participating items of differentiated scenarios, and obtains a state deviation trend data set. Based on the state deviation trend data set, the anomaly identification module selects remote pipeline interfaces, multi-valve joint control areas, and abnormal mutation nodes, identifies the data set location and continuous change amplitude corresponding to the vibration peak, screens the sealing abnormality section, blockage area and leakage channel, and outputs the valve abnormality detection warning signal; The health assessment module outputs valve abnormality detection warning signals, performs time period analysis on abnormal data groups, determines the superposition trend and downward turning point of the change values under continuous operation, adjusts the health scoring model parameters, and obtains valve health status detection data.

[0038] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A valve circuit detection method based on the Internet of Things, characterized in that: The following steps are involved: S1: Based on the real-time data of the valve circuit, high-frequency noise is removed through a low-pass filter, high-frequency components in temperature fluctuations are removed, mean smoothing calculations are performed on the pressure data, and data standardization conversion is performed on the flow data to obtain the valve operation status data; S2: Based on the valve operating status data, weights are set for the degree of influence of the valve status, weighted fusion is performed, the status mean is calculated, the status mean and fluctuation range are identified, and trends of each group of data are compared to obtain valve status fusion feature values; S3: Based on the valve state fusion characteristic value, analyze the change trend of the state characteristics, extract the vibration amplitude and flow offset to identify the valve sealing state offset, evaluate the abnormal pressure offset based on the correlation of each set of data, analyze the state change trend, and obtain the valve operation state offset trend; S4: Based on the deviation trend of the valve operating state, perform abnormal detection rules to compare the current state data, analyze the deviation range of pressure mutation, flow mutation, and vibration abnormality, judge seal damage, blockage and leakage, identify the abnormal impact range, classify the fault warning level, and output the valve abnormality detection warning signal.

2. The valve circuit detection method based on the Internet of Things according to claim 1 is characterized in that: The valve operation status data includes temperature characteristic data, pressure characteristic data, flow characteristic data, and vibration characteristic data; the valve state fusion characteristic value includes state mean, state fluctuation range, and data trend characteristics; the valve operation state offset trend includes sealing offset characteristics, pressure abnormality offset characteristics, and state change trend characteristics; the valve abnormality detection warning signal includes sealing damage judgment, blockage judgment, leakage judgment, and fault warning level.

3. The valve circuit detection method based on the Internet of Things according to claim 1 is characterized in that: The steps for obtaining the valve operation status data are specifically as follows: S111: Based on the real-time data of the valve circuit, temperature, pressure, flow and vibration data are extracted. High-frequency signals are filtered out for the temperature data. By applying a low-pass filter, the energy of the high-frequency segment in the time series is attenuated, the high-frequency components in the frequency distribution are suppressed, and the instantaneous high-frequency interference signals are eliminated to obtain stable temperature data. S112: Calculating a sliding mean of the pressure data based on the temperature steady data, smoothing short-term fluctuation signals, eliminating deviations caused by drastic changes in the data, and obtaining pressure smoothing data; S113: Call the pressure smoothing data and perform standardization conversion on the flow data using the formula: ； Calculate the standardized flow value and obtain the valve operation status data; in, represents the normalized flow value, Represents the original traffic data, and Respectively represent the minimum and maximum values of the flow data, represents the pressure smoothed data, Represents temperature steady state data.

4. The valve circuit detection method based on the Internet of Things according to claim 3 is characterized in that: The steps for obtaining the valve state fusion characteristic value are specifically as follows: S211: Based on the valve operating status data, an influence weight of each type of status parameter is set, and weight normalization calculation is performed on the temperature, pressure, flow, and vibration data. The influence degree of the valve status is analyzed, and a corresponding normalized weight coefficient is assigned. Then, weighted fusion is performed to obtain a state weighted fusion value. S212: Calling the state weighted fusion value to identify the stability of temperature, pressure, flow, and vibration data, analyzing the fluctuation range of each type of data, evaluating the change of the state mean in each time segment, and obtaining the state mean and fluctuation range; S213: Based on the state mean and fluctuation range, the change trend of each group of data is compared using the formula: ； Fusion trend information to obtain valve status fusion feature value; in, represents the valve state fusion eigenvalue, Representative The weighting coefficient of each state data, Representative The state value of each state data time segment, represents the state mean of the state data, Representative The standard deviation of the state data, Represents the number of categories of status data.

5. The valve circuit detection method based on the Internet of Things according to claim 4 is characterized in that: The steps for obtaining the deviation trend of the valve operation status are specifically as follows: S311: Based on the valve state fusion characteristic value, identifying the vibration amplitude offset and the flow rate offset, comparing the current measurement value with the reference value, screening the characteristic items with prominent offset amplitudes, and obtaining a characteristic offset amplitude index; S312: Call the characteristic offset amplitude index to analyze the impact of the vibration amplitude offset on the flow offset using the formula: ； Calculate the sealing state deviation value, filter the influencing feature items, and obtain the key sealing deviation characteristics; in, Represents the deviation value of the sealing status, represents the vibration amplitude offset, represents the flow offset, Representative The offset correction value that affects the characteristic item, Represents the number of influencing feature items, Representative The flow offset that affects the characteristic item; S313: Call the key sealing deviation feature, combine it with the pressure change trend, evaluate the correlation between the sealing deviation and the pressure abnormality, identify the abnormal deviation, and obtain the valve operation status deviation trend.

6. The valve circuit detection method based on the Internet of Things according to claim 5 is characterized in that: The steps for obtaining the valve abnormality detection warning signal are specifically as follows: S411: Based on the deviation trend of the valve operation state, extract the original operation data and real-time monitoring data, calculate the pressure mutation rate, flow mutation rate, and vibration deviation rate, compare them with the set deviation reference value, determine whether they exceed the deviation range, and obtain the abnormal deviation degree; S412: calling the abnormal deviation degree, combining it with the valve sealing status data, comparing the leakage determination threshold and the blockage determination threshold, analyzing the degree of seal damage and the degree of blockage, and obtaining a seal damage index and a blockage index; S413: Based on the seal damage index and the blockage index, combined with the valve operating load change rate, identify the abnormal impact range and fault warning level using the formula: ； Calculate the abnormal impact range index, call the warning level classification standard, match the corresponding warning level, and output the valve abnormality detection warning signal; in, Represents the abnormal impact range index, Represents the seal damage index, represents the congestion index, Represents the operating load change rate, Represents the current vibration deviation rate, Indicates the vibration reference value.

7. The valve circuit detection method based on the Internet of Things according to claim 1 is characterized in that: The method further comprises step S5: S5: Based on the valve abnormality detection warning signal, identify the probability of health status change according to the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude, analyze the status change trend in the future time period, identify the health status change direction according to the operating time and load change, evaluate the health status score, and obtain valve health status detection data; The valve health status detection data includes health change probability, health change trend, health change direction, and health status score.

8. The valve circuit detection method based on Internet of Things according to claim 7, characterized in that: The steps for obtaining the valve health status detection data are specifically as follows: S511: Based on the valve abnormality detection warning signal, extract the flow deviation trend, vibration intensity change, and pressure fluctuation amplitude data, calculate the change rate, identify the health state change probability, determine the deviation between the current data and the health state baseline value, and obtain the health state deviation amount; S512: The health status deviation is called, and the state change rate is analyzed according to the running time and load change, using the formula: ； Calculate the health status score and obtain the health status assessment value after normalization; in, represents the health status score, Represents the health status deviation in the kth time period, Represents the load change impact factor, represents the environmental pressure impact coefficient, Represents the running time impact coefficient of the k-th time period, Represents the state change rate correction value, represents the volatility adjustment coefficient, Represents the number of data segments; S513: Call the health status assessment value, analyze the health status trend, identify the short-term prediction value, combine the state change probability, and output the valve health status detection data.

9. A valve circuit detection system based on the Internet of Things, characterized in that: According to the valve path detection method based on the Internet of Things according to any one of claims 1 to 8, the system comprises: The state perception module is based on real-time valve circuit data, including valve operation data monitored by temperature sensors, pressure sensors, flow sensors, and vibration sensors. It performs low-pass filtering on temperature data, multi-point mean calculation on pressure data, standardizes flow data to form a unified dimension, and performs amplitude normalization on vibration data to obtain the original valve state parameter set. The signal conversion module sets weights for the temperature, pressure, flow, and vibration data based on the original valve state parameter set, performs weighted conversion, analyzes the fluctuation range of the state data, and compares the corresponding change trends to obtain the valve state value set; The state feature module selects the fluid delivery pipe section, segmented valve, and vibration node based on the valve state value set, analyzes the positional relationship between the vibration amplitude change and the flow fluctuation, identifies the distribution degree of the state change on the participating items of the differentiated scenarios, and obtains the state deviation trend data group; Based on the state deviation trend data group, the abnormality identification module selects the remote pipeline interface, multi-valve joint control area, and abnormal mutation node, identifies the data group location and continuous change amplitude corresponding to the vibration peak, screens the sealing abnormal section, blockage area and leakage channel, and outputs the valve abnormality detection warning signal; The health assessment module performs a time period analysis on the abnormal data group based on the output valve abnormality detection warning signal, determines the superposition trend and downward turning point of the change value under the continuous operation state, adjusts the health scoring model parameters, and obtains the valve health status detection data.

Images