Wireless digital pressure gauge performance data monitoring management method based on Internet of Things

Abstract

The invention discloses a wireless digital pressure gauge performance data monitoring management method based on the Internet of Things, and relates to the technical field of pressure gauge technical performance data monitoring, and the method comprises the following steps: building a historical behavior model and a neighborhood behavior joint model when a wireless digital pressure gauge is in an equipment address abnormal overlapping condition, fitting the uploaded performance data to obtain a first residual error and a second residual error, and generating a residual error coupling degree and a coupling degree change trend which are used for representing a transmission mapping chaos degree of the performance data based on the first residual error and the second residual error; and judging whether the uploaded performance data has an affiliation error problem or not according to the residual coupling degree and the transmission mapping confusion degree corresponding to the coupling degree change trend. According to the method, the problem of data affiliation errors of the wireless digital pressure gauge of the Internet of Things when the addresses are abnormally overlapped is solved, and intelligent identification, dynamic correction and trend modeling safety guarantee of data affiliation are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure gauge technical performance data monitoring, and in particular to a wireless digital pressure gauge performance data monitoring and management method based on the Internet of Things. Background Art

[0002] Wireless digital pressure gauge performance data refers to dynamic performance metrics generated and wirelessly transmitted by wireless digital pressure gauges during the pressure measurement process, including operational status, measurement accuracy, response speed, signal stability, power supply status, and environmental adaptability. This data not only reflects the pressure gauge's real-time measurement capabilities but also reveals the device's stability and reliability in real-world operating environments. Traditional pressure gauges rely on manual inspections and local readings, which are inefficient and prone to errors. Centralized management and real-time response are also difficult to implement in large-scale industrial applications. Therefore, monitoring and managing wireless digital pressure gauge performance data based on the Internet of Things (IoT) technology enables remote, automated data collection, real-time upload, and centralized analysis through sensor networks and communication modules, significantly improving transparency and controllability of equipment operations. IoT platforms can centrally manage, analyze trends, provide anomaly warnings, and facilitate maintenance scheduling for massive amounts of device performance data, effectively reducing operational costs and improving system security and management efficiency. These platforms are particularly suitable for data-intensive applications such as industrial automation, energy management, and smart cities.

[0003] Existing IoT-based wireless digital pressure gauge performance data monitoring and management technologies primarily integrate pressure sensors, data acquisition units, wireless communication modules, and low-power processing chips within wireless digital pressure gauges to achieve real-time collection and local pre-processing of pressure data and equipment operating status. These data are then uploaded to a cloud or edge server via IoT communication methods (such as NB-IoT, LoRa, 4G / 5G, or Wi-Fi) for centralized processing and management. This technology typically includes several key components: First, the front-end perception layer, consisting of multiple wireless digital pressure gauges deployed at different measurement points, collects pressure values ​​and equipment operating parameters in real time. Second, the network transmission layer transmits the collected data to back-end systems via stable and reliable IoT communication links. Third, the platform processing layer, relying on an IoT management platform, performs data reception, parsing, storage, statistical analysis, and visualization. Fourth, the application management layer, through configured threshold judgments, algorithm model analysis, trend warnings, and operation and maintenance scheduling, enables intelligent monitoring and efficient management of equipment performance. During the entire process, the system supports distributed device access, encrypted data transmission, remote diagnosis and remote upgrade, forming an automated, highly real-time and scalable closed-loop system for pressure gauge performance data management, effectively improving the overall reliability and intelligence level of the system.

[0004] The existing technology has the following deficiencies: During the multi-point deployment of the IoT wireless digital pressure gauge system, if multiple wireless digital pressure gauges are installed at adjacent pressure measurement locations in the same fluid network (such as between the main pipeline and the branch pipeline), and a broadcast communication protocol (such as LoRa) is used in conjunction with an automatic addressing mechanism for data reporting, it is possible that when the device is brought back online, the address is erased, or the ID is refreshed, the device communication identifier (such as the logical ID or MAC address) may overlap abnormally, causing the background system to mistakenly attribute performance data from different physical locations to the data source of the same logical measurement point; since these devices were originally distributed in different pressure characteristic areas, their actual pressure measurement behavior There are differences, so after the data is merged, the platform will show pressure fluctuations that "do not conform to the laws of fluid physics", such as frequent sudden rises and falls or periodic conflicting waveforms. The existing performance data monitoring and management technology of wireless digital pressure gauges based on the Internet of Things cannot judge whether there is an attribution error problem in the current data based on the degree of confusion in the transmission mapping of performance data of the wireless digital pressure gauge when the device address is abnormally overlapped. As a result, the background will continue to use the erroneous data for trend analysis, anomaly identification and strategy execution, which will eventually cause equipment failures to be misjudged, normal status to be erroneously warned, and trend models to be misled in learning, thereby affecting the decision-making accuracy and operation and maintenance efficiency of the entire system.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a wireless digital pressure gauge performance data monitoring and management method based on the Internet of Things to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things, which specifically includes the following steps: Obtain pressure disturbance response data of the wireless digital pressure gauge in a static fluid environment during the initial deployment, construct a behavior label based on the pressure disturbance response data, and bind the behavior label to the wireless digital pressure gauge; After the wireless digital pressure gauge uploads its performance data, the pressure disturbance response time series is extracted and compared with the response time of adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in an abnormal device address overlap situation. When the wireless digital pressure gauge is in a situation where the device address is abnormally overlapped, a historical behavior model and a neighborhood behavior joint model are constructed, and the uploaded performance data are fitted separately to obtain the first residual and the second residual. Based on the first residual and the second residual, the residual coupling degree and the coupling degree change trend are generated to characterize the degree of transmission mapping chaos of the performance data; Based on the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend, determine whether the uploaded performance data has attribution errors; For performance data with misattribution issues, the performance data is divided into continuous time segments. The behavioral characteristics of each time segment are matched with the historical data of a preset number of measurement points. Based on the matching results, the target attribution measurement point of the performance data is determined through attribution voting to complete the attribution adjustment operation. After completing the attribution adjustment, the residual coupling degree, coupling degree change trend, judgment results and target attribution measurement points are recorded to form an attribution judgment trajectory, and intervention processing is performed in areas where attribution errors are concentrated, including reconstructing behavior labels, enabling the joint verification process of behavior characteristics and measurement point locations, and restricting the uploaded data in this area from participating in trend modeling.

[0008] Preferably, after the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted and compared with the response time of adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in an abnormal device address overlap situation, specifically: After the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted. The pressure disturbance response time series consists of continuous pressure change data from the disturbance triggering starting point to the pressure value entering the stable range. The disturbance response time of the wireless digital pressure gauge is obtained by calculating the time interval between the moment when the pressure change rate reaches the maximum value and the disturbance triggering starting point in the pressure disturbance response time series; From the same data synchronization period, a preset number of adjacent measuring points are selected, the pressure disturbance response time series of each measuring point is extracted respectively, and the disturbance response time set of the adjacent measuring points is calculated in the same way; Based on the physical topology information between the wireless digital pressure gauge and each adjacent measuring point, the corresponding physical connection path and pipeline distance data are obtained. In combination with the preset fluid medium propagation speed, the theoretical disturbance propagation time from each adjacent measuring point to the wireless digital pressure gauge is calculated. Based on the difference between the response time of each measuring point in the set of neighboring measuring point disturbance response times and its theoretical propagation time, the average propagation offset time of the disturbance under the current topology is calculated, and the theoretical response time delay range is constructed. The disturbance response time of the wireless digital pressure gauge is compared with the theoretical response time delay range. When the response time exceeds a boundary threshold of the theoretical range, it is determined that the wireless digital pressure gauge is in an abnormal device address overlap situation.

[0009] Preferably, when the wireless digital pressure gauge is in a situation where the device address is abnormally overlapped, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in the historical period, and a neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measuring points that have a physical topological connection relationship with the wireless digital pressure gauge. The uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. By calculating the average difference and trend difference between the first residual and the second residual, the residual coupling degree and the coupling degree change trend are generated to characterize the degree of transmission mapping confusion of the performance data.

[0010] Preferably, when the wireless digital pressure gauge is in a state of abnormal device address overlap, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in a historical period, specifically: Selecting continuous pressure change data from the disturbance triggering start point to the pressure value entering the stable range in a preset number of historical periods; Based on the continuous pressure change data, the pressure change rate per unit time is calculated to form a pressure change rate sequence, and the pressure change rate sequence is clustered using a time series similarity algorithm to extract a disturbance response behavior feature sequence containing pressure change rate samples of a preset time length; A piecewise linear function model is constructed based on the characteristic sequence fitting of each disturbance response behavior. The combination weight is set according to the disturbance response amplitude and duration corresponding to each piecewise linear function model. The piecewise linear function models are weighted combined to construct a historical behavior model for describing the disturbance response behavior of the wireless digital pressure gauge.

[0011] Preferably, a neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measuring points having a physical topological connection relationship with the wireless digital pressure gauge, specifically: Obtain physical connection path and distance information based on the physical pipeline connection diagram between the wireless digital pressure gauge and other measuring points, and filter out adjacent measuring points whose physical distance does not exceed the set distance threshold; The continuous pressure change data of each adjacent measuring point from the disturbance triggering point to the pressure value entering the stable range within multiple historical periods are selected, and each data segment is normalized according to the unified time sampling interval and length. The pressure change rate series is obtained by performing unit time difference calculation on the continuous pressure data. In each pressure change rate sequence, the maximum pressure change rate, the duration of the change rate and the time position of the occurrence of the change rate are calculated, and a triplet containing their values ​​is constructed as the measuring point feature vector. The feature vectors of all neighboring measuring points are combined into a set of joint feature vectors by weighted average of distance, and a neighborhood behavior joint model is constructed based on the joint feature vectors through multi-segment linear fitting.

[0012] Preferably, the uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. The residual coupling degree and the coupling degree change trend are generated by calculating the average difference and the trend difference between the first residual and the second residual, which are used to characterize the degree of transmission mapping confusion of the performance data, specifically: The pressure disturbance response time series in the uploaded performance data is used as input and substituted into the historical behavior model and neighborhood behavior joint model corresponding to the wireless digital pressure gauge. At each unified sampling time point, the difference between the model prediction value and the actual pressure value is calculated to form the first residual sequence and the second residual sequence respectively. Based on the two residual sequences, the difference of the residual values ​​of each corresponding sampling point is calculated to form a residual difference sequence; All the differences in the residual difference sequence are averaged to obtain an average difference that reflects the overall deviation degree of the fitting; Perform local linear regression on the residual difference series in a fixed-time sliding window manner, extract the fitting slope in each window, and calculate the standard deviation of the slope values ​​in all windows to obtain the trend difference used to characterize the changing trend of the fitting difference; The average difference and the trend difference are respectively subjected to minimum-maximum normalization processing, and form the residual coupling degree and the coupling degree change trend, which are used to characterize the degree of transmission mapping confusion of the uploaded performance data in the case of abnormal address overlap. Specifically: when the residual coupling degree and the coupling degree change trend are both in the preset high value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is high; when the residual coupling degree and the coupling degree change trend are both in the preset low value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is low; when the residual coupling degree and the coupling degree change trend are neither in the preset high value range nor in the preset low value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is medium.

[0013] Preferably, whether the uploaded performance data has an attribution error problem is determined based on the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend, specifically: When the transmission mapping disorder degree is high, it is determined that there is an attribution error problem in the currently uploaded performance data; When the transmission mapping disorder level is medium, based on the average historical fitting error level of the performance data in the behavior model of the current measurement point, if the first residual of the performance data at the current measurement point exceeds a preset tolerance interval of the average historical fitting error level, then it is determined that the performance data has an attribution error problem; otherwise, it is determined that the performance data does not have an attribution error problem; When the transmission mapping confusion level is low, it is determined that there is no attribution error problem in the currently uploaded performance data.

[0014] Preferably, for performance data with attribution errors, the performance data is divided into continuous time segments according to a fixed time window length, the pressure disturbance response time series in each time segment is extracted, and the pressure change rate per unit time is calculated to form a pressure change rate sequence; the pressure change rate sequence is similarly matched with a historical pressure change rate sample sequence generated by a preset number of pressure disturbance response time series of the same length in a historical period, and a similarity scoring algorithm based on dynamic time warping (DTW) is used to calculate the matching score of each measuring point. A weighted vote is performed based on the matching scores of all measuring points, and the measuring point with the highest number of votes is selected as the target attribution measuring point for the current time segment. The attribution measuring points of all time segments are subjected to frequency statistics, and finally the measuring point with the highest frequency is determined as the target attribution measuring point for the performance data, completing the attribution adjustment operation.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. This invention, through the construction of a closed-loop mechanism combining "disturbance response behavior labeling, coupled fitting residual analysis, and attribution behavior optimization," achieves, for the first time, the automatic identification and correction of data attribution errors caused by abnormal overlap of device communication addresses in an IoT wireless digital pressure gauge system. Traditional IoT platforms often rely on communication identifiers (such as logical IDs and MAC addresses) to uniquely identify measurement points, making conflicts highly likely to occur during device re-onboarding or automatic addressing. This solution, by using "disturbance response behavior" as a dynamic identification basis independent of communication identifiers, effectively resolves data mismatches caused by incorrect attribution of communication identifiers, significantly improving the platform's data identification robustness and fault tolerance.

[0016] 2. The present invention introduces a dual fitting mechanism of "historical behavior model and neighborhood behavior joint model". Through difference sequence analysis and trend detection between the first residual and the second residual, a coupling index is constructed to quantify the "degree of confusion in performance data transmission mapping". Probabilistic early warning and quantitative identification of data anomaly attribution can be achieved before the attribution error occurs, effectively avoiding the use of erroneous data for highly sensitive operations such as trend learning and fault judgment, improving the overall prediction accuracy and stability of the system, and possessing highly intelligent data governance capabilities.

[0017] 3. Utilizing a strategy of "attribution voting + behavioral feature matching + determination trajectory recording," this solution automatically reallocates measurement points to their target attributes after identifying data attribution errors. It also implements intervention and optimization measures in areas where attribution errors are concentrated, such as reconstructing behavioral labels, jointly verifying measurement point locations, and isolating participating modeling data. This achieves closed-loop control from identification and correction to self-optimization. Compared to traditional static configuration or manual intervention, this approach not only responds more promptly and accurately, but also significantly improves the system's autonomous evolutionary capabilities and operational efficiency over the long term. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 The figure is a flow chart of the method for monitoring and managing the performance data of a wireless digital pressure gauge based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0021] The present invention provides Figure 1 The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things specifically includes the following steps: Obtain pressure disturbance response data of the wireless digital pressure gauge in a static fluid environment during the initial deployment, construct a behavior label based on the pressure disturbance response data, and bind the behavior label to the wireless digital pressure gauge; After the wireless digital pressure gauge is physically installed, the platform sends a remote trigger command to generate a controllable short-term disturbance in the fluid pipeline where the pressure gauge is located. For example, by controlling the port valve to achieve slight opening and closing or applying instantaneous load changes, the pressure in the pipeline is induced to produce a disturbance response. During the disturbance, the system continuously collects the pressure data of the wireless digital pressure gauge at a high sampling frequency to form a complete disturbance response data sequence. To ensure that the environment is in a static fluid condition during data collection, the platform synchronously detects data from adjacent measuring points during the collection period. When the pressure change of other measuring points within the set time window is lower than the preset threshold, it is determined that the current environment meets the static condition, and the disturbance response data is marked as the initial deployment pressure disturbance response data.

[0022] After completing the collection of pressure disturbance response data, the platform analyzes the data sequence through a feature extraction algorithm, extracts multiple key parameters including the starting position of the disturbance response, the maximum pressure change, the length of stable time, the rate of change of the waveform slope, the attenuation trend, etc., and merges them in the form of a multi-dimensional feature vector. Subsequently, the platform calls the feature encoding function to encode the above feature vector, generates a unique behavioral label, and binds the behavioral label to the device identification of the wireless digital pressure gauge. The binding operation is completed by writing the behavioral label index into the device metadata database to ensure that the performance data uploaded subsequently can be compared with the label, thereby establishing a behavioral reference relationship for data attribution.

[0023] Through the above operations, even in scenarios where the device communication identifier undergoes abnormal changes or overlaps, the data ownership of the wireless digital pressure gauge can still be identified based on its behavioral characteristics, thereby effectively improving the accuracy and robustness of data analysis. In the IoT environment, phenomena such as address re-refresh, ID reuse, and communication conflicts may cause performance data to be incorrectly mapped to the wrong measurement point, thereby interfering with the system's identification and decision-making of the device status. By collecting disturbance response data in the initial deployment to establish behavioral tags, and completing tag binding and calling in software, the platform can be provided with a behavioral identification mechanism independent of the communication identifier, ensuring a dynamic behavioral baseline in subsequent data attribution judgments, which helps to accurately identify attribution errors and perform attribution adjustment operations.

[0024] After the wireless digital pressure gauge uploads its performance data, the pressure disturbance response time series is extracted and compared with the response time of adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in an abnormal device address overlap situation. In this embodiment, after the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted and compared with the response time of adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in an abnormal device address overlap situation. Specifically: After the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted. The pressure disturbance response time series consists of continuous pressure change data from the disturbance triggering starting point to the pressure value entering the stable range. After the wireless digital pressure gauge uploads its performance data, the disturbance triggering starting point is located in the uploaded data stream, and the complete response process from the disturbance triggering starting point to the pressure value returning to stability is further extracted to construct a pressure disturbance response time series. This process first sets a disturbance detection threshold (such as a pressure change rate threshold or a small mutation threshold) and identifies the location in the time series where the pressure slope first continuously exceeds the threshold as the disturbance triggering starting point. The system then continuously tracks the pressure curve changes after this starting point and determines whether the amplitude of its change in several consecutive time windows is lower than the set stability interval threshold. If the stability criteria are met within the consecutive time windows, the pressure is determined to have entered the stable interval and the time point is recorded as the end point of the sequence. Finally, the pressure sampling data between the starting point and the end point are intercepted in chronological order to form the pressure disturbance response time series. For example, if a wireless digital pressure gauge with a sampling frequency of 1Hz detects a rapid rise in pressure from 0.85MPa to 0.96MPa at the 120th second within a certain cycle, and then gradually approaches 0.92MPa over the following 50 seconds with a fluctuation amplitude of less than 0.002MPa, the system can determine that the 120th second is the starting point of the disturbance and the 170th second is the starting point of the stable range, and extract the pressure value sequence within these 50 seconds as a complete pressure disturbance response time series. This method allows for structured segmentation of raw performance data at the software level, providing an accurate dynamic behavior foundation for subsequent response behavior analysis and attribution judgment.

[0025] The disturbance response time of the wireless digital pressure gauge is obtained by calculating the time interval between the moment when the pressure change rate reaches the maximum value and the disturbance triggering starting point in the pressure disturbance response time series; After obtaining the pressure disturbance response time series, the system performs differential calculation and rate analysis on the time series to extract the time point at which the pressure change rate reaches its maximum value. Combined with the starting position of the disturbance trigger, the disturbance response time of the wireless digital pressure gauge is calculated. Specifically, the system first performs a first-order derivative calculation on the disturbance response time series, performing differential processing on adjacent pressure sampling points using a sliding time window to obtain a pressure change rate sequence per unit time. Next, the position with the maximum absolute value of the rate is located in the rate sequence. The original time point corresponding to this position is the moment of the strongest response during the disturbance process. The time difference between this time point and the initial disturbance trigger moment is then calculated to obtain the disturbance response time. For example, if the starting point of the disturbance response time series is the 120th second, and differential analysis reveals that the pressure change rate reaches its maximum value (e.g., 0.007 MPa / s) at the 125th second, then the 125th second can be determined to be the maximum response moment. Finally, 120 is subtracted from 125 to obtain the disturbance response time of 5 seconds. This method can be implemented in software through standard algorithms such as data sliding windows, differential arrays, and extreme value extraction. It is versatile and highly precise, and can provide accurate behavioral characteristic parameters for subsequent construction of topological response models and judgment of attribution errors.

[0026] From the same data synchronization period, a preset number of adjacent measuring points are selected, the pressure disturbance response time series of each measuring point is extracted respectively, and the disturbance response time set of the adjacent measuring points is calculated in the same way; Within the same data synchronization cycle, a preset number of adjacent measurement points are selected and their pressure disturbance response time series are extracted. Physical proximity relationships and time synchronization windows can be set in the IoT platform through software. Combined with pressure change feature recognition methods, dynamic behavior extraction and response time calculation of multiple measurement points can be achieved. Specifically, the platform first selects a preset number of measurement points as a set of adjacent measurement points based on a topology configuration table or deployment coordinate system, from measurement points that have direct pipeline connections to the target wireless digital pressure gauge or are within a physical distance threshold. Then, within the synchronization time window (e.g., ±2 seconds) when the target device detects a disturbance event, continuous pressure data segments corresponding to the disturbance starting point are intercepted from the performance data of these measurement points. For each adjacent measurement point, the platform calculates its respective disturbance response time using the same processing as the target device—identifying the disturbance trigger point, extracting the response time series, and calculating the time difference between the maximum pressure change rate and the trigger point. These disturbance response times are ultimately combined into a response time set. For example, if a target device responds to a disturbance at 120 seconds, the system will synchronously extract data from three adjacent measurement points within the window of 118 to 122 seconds. Applying the same disturbance time extraction logic as for the target device to each measurement point, the system will derive response times of, for example, 5.2 seconds, 4.8 seconds, and 5.5 seconds, respectively. These values ​​are combined to form a set of adjacent measurement point disturbance response times. This set is then used for subsequent comparative analysis with theoretical propagation models to help determine whether the target device has experienced data attribution errors or abnormal response behavior.

[0027] Based on the physical topology information between the wireless digital pressure gauge and each adjacent measuring point, the corresponding physical connection path and pipeline distance data are obtained. In combination with the preset fluid medium propagation speed, the theoretical disturbance propagation time from each adjacent measuring point to the wireless digital pressure gauge is calculated. Based on the physical topology information between the wireless digital pressure gauge and each adjacent measuring point, the system obtains the physical connection path and pipeline distance data, and calculates the theoretical disturbance propagation time based on the preset fluid medium propagation velocity. This is achieved by constructing a topological graph model of the fluid network within the IoT platform and introducing a path weight calculation method. Specifically, during the deployment or initialization phase, the physical location information and pipeline connection relationship of each measuring point are entered into a topology database. A graph-like connection structure is then established between the measuring points, where each edge represents a pipeline segment, with the pipeline length as the path weight. After the target wireless digital pressure gauge triggers a disturbance, the system performs a shortest path search (such as the Dijkstra algorithm or the A* algorithm) on each adjacent measuring point in the topology graph to obtain the physical connection path from the adjacent measuring point to the target measuring point and its cumulative pipeline length. Then, based on the pre-configured fluid medium type (e.g., water, gas) and its propagation velocity parameters in the environment (e.g., the shock wave velocity of water in a steel pipe is approximately 1400 m / s), the theoretical disturbance propagation time from the adjacent measuring point to the target wireless digital pressure gauge is calculated using the formula "propagation time = total pipeline length / propagation velocity." For example, if the total length of the connection path between a nearby measurement point and the target device is 21 meters, the current medium is water, and the propagation speed is set to 1400 meters per second, the theoretical propagation time is 0.015 seconds. This software modeling and path calculation method can quickly and efficiently calculate the theoretical propagation time without additional hardware intervention, providing basic support for subsequent response behavior comparison and address anomaly determination.

[0028] Based on the difference between the response time of each measuring point in the set of neighboring measuring point disturbance response times and its theoretical propagation time, the average propagation offset time of the disturbance under the current topology is calculated, and the theoretical response time delay range is constructed. Based on the difference between the response time of each measuring point in the set of neighboring measuring point disturbance response times and its theoretical propagation time, the average propagation offset time of the disturbance under the current topology is calculated, and the theoretical response time delay range is constructed. This can be achieved by statistically analyzing and modeling the response errors of multiple measuring points through software. In the specific operation, first, for each neighboring measuring point, the difference between the actual measured disturbance response time and its corresponding theoretical disturbance propagation time is calculated to obtain the propagation offset time of the measuring point; then, the propagation offset times of all neighboring measuring points are summarized, and the average propagation offset time under the current topology is calculated using the mean or weighted mean calculation method. This value can be regarded as the overall dynamic offset characteristic of the disturbance response in the local fluid system; on this basis, the standard deviation or maximum fluctuation amplitude of all offset times is further calculated to characterize the degree of uncertainty of the propagation offset. Finally, the theoretical response time delay range is constructed using the "average propagation offset time ± tolerance range" as a reference interval for judging the rationality of the target device response time. For example, if three adjacent measurement points have response times of 5.3 seconds, 4.9 seconds, and 5.6 seconds, respectively, and their theoretical propagation times are 5.0 seconds, 4.8 seconds, and 5.2 seconds, then the offset times are 0.3 seconds, 0.1 seconds, and 0.4 seconds, respectively. The average offset time is 0.266 seconds, and the standard deviation is approximately 0.124 seconds. The theoretical response time delay range can ultimately be set to "theoretical propagation time + 0.266 seconds ± 0.15 seconds." This method integrates neighborhood behavioral offset characteristics to construct an adaptive judgment interval, improving the robustness and accuracy of address anomaly identification.

[0029] The disturbance response time of the wireless digital pressure gauge is compared with the theoretical response time delay range. When the response time exceeds a boundary threshold of the theoretical range, it is determined that the wireless digital pressure gauge is in an abnormal device address overlap situation.

[0030] The disturbance response time of the wireless digital pressure gauge is compared with the theoretical response time delay range, and based on this, it is determined whether it is in an abnormal device address overlap situation. The interval judgment mechanism integrated in the software can be used to achieve comparative analysis and abnormal identification. In the specific implementation, after completing the construction of the theoretical response time delay range, the system uses this range as a reference interval for the disturbance response behavior of the target measuring point. For example, a dynamic judgment threshold interval is generated in the form of "theoretical propagation time + average offset time ± tolerance". Subsequently, the system calls the actual disturbance response time of the wireless digital pressure gauge calculated in the early stage and compares it with the upper and lower boundaries of the interval. If the response time is earlier than the lower boundary or later than the upper boundary, it is determined that its behavioral response does not conform to the reasonable timing derived based on the topological structure and propagation law, and then marks the device as having the risk of abnormal address overlap. For example, if the system establishes a theoretical response time delay range of "5.0 to 5.4 seconds" based on the behavior of neighboring measurement points, and the target wireless digital pressure gauge's disturbance response time is 4.6 or 5.8 seconds, it significantly deviates from this reasonable range, indicating that the uploaded data did not arrive in the physical and logical order of propagation, and there is a high probability of data attribution errors due to overlapping device addresses. This judgment process can be embedded in the IoT platform's data pre-storage process for automatic execution. It is not only real-time but also independent of manual review, making it suitable for dynamic anomaly identification and label correction needs in large-scale deployments.

[0031] When the wireless digital pressure gauge is in a situation where the device address is abnormally overlapped, a historical behavior model and a neighborhood behavior joint model are constructed, and the uploaded performance data are fitted separately to obtain the first residual and the second residual. Based on the first residual and the second residual, the residual coupling degree and the coupling degree change trend are generated to characterize the degree of transmission mapping chaos of the performance data; In this embodiment, when the wireless digital pressure gauge is in a situation of abnormal device address overlap, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in the historical period, and a neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measuring points that have a physical topological connection relationship with the wireless digital pressure gauge. The uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. By calculating the average difference and trend difference between the first residual and the second residual, the residual coupling degree and the coupling degree change trend are generated to characterize the degree of transmission mapping chaos of the performance data.

[0032] In this embodiment, when the wireless digital pressure gauge is in a state of abnormal device address overlap, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in the historical period, specifically: Selecting continuous pressure change data from the disturbance triggering start point to the pressure value entering the stable range in a preset number of historical periods; The system selects continuous pressure change data from a preset number of historical cycles, from the start of a disturbance trigger to the point where the pressure value enters a stable range. This is accomplished by segmenting the wireless digital pressure gauge's historical data into periods, identifying disturbance events, and extracting valid data segments using a stability judgment mechanism. First, the system identifies the disturbance start time point in each historical cycle based on known disturbance trigger mechanisms or periodic external event markers (such as control signals like valve opening and pump start). It then scans the pressure data sequence backward from this time point and detects the start of the pressure stabilization range based on a predefined stability judgment rule (e.g., pressure fluctuations below a set threshold for several consecutive sampling points, and the gradient rate of change approaches zero). The system then extracts the complete pressure change data from the disturbance start point to the stable start point as the disturbance response segment for the current cycle. Within a continuous operating cycle, the system selects a preset number of periods that meet data integrity and accuracy requirements based on time windows or event tags for processing. The data segments corresponding to each period are formatted and stored for subsequent behavioral modeling and analysis. In this way, the system can accurately extract disturbance response fragments with consistent structure, clear timing, and physical integrity from large-scale data sets, and prepare basic data for the historical behavior of wireless digital pressure gauges.

[0033] Based on the continuous pressure change data, the pressure change rate per unit time is calculated to form a pressure change rate sequence, and the pressure change rate sequence is clustered using a time series similarity algorithm to extract a disturbance response behavior feature sequence containing pressure change rate samples of a preset time length; The calculation of the pressure change rate per unit time based on continuous pressure change data and the formation of a pressure change rate sequence can be accomplished through differential calculation. Specifically, the system first normalizes the sampling point time of the disturbance response segment extracted from each cycle, and then performs a difference operation on the pressure values ​​between adjacent sampling points, and divides it by the corresponding time interval to obtain the pressure change rate per unit time. This sequence reflects the response speed and change trend during the disturbance process, and can better reflect the essential characteristics of the disturbance. Subsequently, based on the sliding window mechanism, the system divides each pressure change rate sequence into a group of time segments of the same length as pressure change rate samples. In order to identify typical disturbance response patterns, the system uses a time series similarity algorithm to cluster all samples, and extracts the sample in each class that best represents the structural characteristics of the class as the disturbance response behavior feature sequence. For example, given 30 cycles of historical data from a wireless digital pressure gauge, the system generates 30 pressure change rate sequences. Each sequence is segmented into one-second segments using a sliding window. Clustering reveals three primary response patterns: rapid rise followed by slow stabilization, slow rise followed by rapid stabilization, and linear smooth transition. From each cluster, a representative sample with the smallest distance to the center is extracted to form the behavioral feature sequence used for modeling.

[0034] Time series similarity algorithms measure the structural similarity between two sequences along the time axis. Common methods include dynamic time warping (DTW), Euclidean distance, and edit distance on real sequences (EDR). DTW is an algorithm that allows for nonlinear alignment along the time dimension. It enables flexible comparison of sequences with inconsistent lengths or time offsets, making it particularly suitable for processing disturbance response data. In this scenario, DTW automatically matches pressure change rate sequences from two different periods along the time axis, allowing structural similarity to be identified even when the two disturbance responses have different response durations. For example, if a rapid pressure increase lasts only 0.8 seconds in one period and 1.2 seconds in another, DTW will automatically align their structural changes along the time dimension, allowing for a more accurate assessment of their behavioral similarity. This approach provides a robust similarity metric for identifying pressure disturbance patterns and is a key step in extracting behavioral features.

[0035] A piecewise linear function model is constructed based on the characteristic sequence fitting of each disturbance response behavior. The combination weight is set according to the disturbance response amplitude and duration corresponding to each piecewise linear function model. The piecewise linear function models are weighted combined to construct a historical behavior model for describing the disturbance response behavior of the wireless digital pressure gauge.

[0036] The process of fitting a piecewise linear function model based on each disturbance response behavior characteristic sequence and generating a historical behavior model based on this model is accomplished by analyzing the characteristic sequence's changing trends and identifying key inflection points. Specifically, the system first applies first-order derivative analysis to each disturbance response behavior characteristic sequence to identify significant inflection points in the pressure change rate. Based on these inflection points, the entire sequence is divided into several intervals with a single trend, such as a continuous rise, a smooth transition, or a slow decline. The data for each interval is fitted to a linear function of the form P(t)=at+b, where a represents the pressure change rate within the segment, t is time, and b is the initial pressure value. The least squares method is used to determine the optimal linear parameters during the fitting process to minimize the fitting error. Next, the system calculates the contribution of each segment's pressure change amplitude and duration to the overall behavior pattern and assigns a normalized weight. All piecewise linear functions are weighted and combined according to their weights to form a continuous function sequence with different slope characteristics, which serves as the historical behavior model of the wireless digital pressure gauge. For example, if a characteristic sequence contains three response features: rapid rise (0–0.4s), slow rise (0.4–1.0s), and stable level (1.0–2.0s), they are fitted into three-segment linear functions and then weighted combined to reflect the typical disturbance behavior process of the measuring point as a whole.

[0037] A piecewise linear function model approximates a nonlinear or multi-stage process as a series of continuous linear segments. It is suitable for describing pressure response trajectories exhibiting varying trends during a disturbance response. Each piecewise model uses a linear function to approximate the actual data within a local time interval, significantly reducing fitting errors and improving modeling accuracy. For example, in a pressure response sequence, the 0–0.3 second segment exhibits a rapid linear rise and can be fitted with P1(t)=2.5t+0.8; the 0.3–0.9 second segment exhibits a slow pressure change and can be fitted with P2(t)=0.6t+1.4; and the 0.9–1.5 second segment, which tends to plateau, can be fitted with an approximate horizontal line, P3(t)=1.8. This structured representation preserves the staged nature of the pressure response process while facilitating comparison and combination of models across different cycles, making it a valuable tool for achieving behaviorally normalized modeling.

[0038] In this embodiment, a neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measurement points that have a physical topological connection relationship with the wireless digital pressure gauge, specifically: Obtain physical connection path and distance information based on the physical pipeline connection diagram between the wireless digital pressure gauge and other measuring points, and filter out adjacent measuring points whose physical distance does not exceed the set distance threshold; The system constructs a topological database to obtain physical connection paths and distance information between wireless digital pressure gauges and other measuring points. Using a graph-theoretic path search algorithm, it then selects neighboring measuring points whose physical distances do not exceed a set threshold. Specifically, the system first creates a complete pipe network topology map, in which nodes represent wireless digital pressure gauges or other measuring points, edges represent pipeline connections, and each edge is weighted by the actual pipeline length. The system then loads this topology map into a data structure in the form of an adjacency matrix or adjacency table. During runtime, the system uses a weighted shortest path algorithm (such as Dijkstra or A*) to calculate the shortest physical paths between the target wireless digital pressure gauge node and all other measuring points. The system then accumulates the lengths of all pipe segments in the path to obtain the actual physical distance. The system then marks all measuring points whose distances do not exceed a set threshold (e.g., 50 or 100 meters) as neighboring measuring points and records the corresponding path structure for subsequent disturbance propagation time calculations. For example, if measuring point A is connected to target pressure gauge B via three sections of pipe with a total length of 47 meters, and the path in the topology map is A→X→Y→B, then A will be included in the set of neighboring measuring points. This approach allows the system to accurately and automatically identify neighboring areas with physical topological associations with a measuring point in complex, large-scale pipe networks, providing precise spatial boundaries for subsequent disturbance behavior correlation analysis.

[0039] The continuous pressure change data of each adjacent measuring point from the disturbance triggering point to the pressure value entering the stable range within multiple historical periods are selected, and each data segment is normalized according to the unified time sampling interval and length. The pressure change rate series is obtained by performing unit time difference calculation on the continuous pressure data. To select disturbance response data from each adjacent measuring point over multiple historical periods and generate a uniformly formatted pressure rate sequence, the software first establishes a point-by-point historical data cache. Using external disturbance event logs or an internal pressure mutation detection algorithm, the system locates the disturbance trigger point within each historical period. Subsequently, starting from the disturbance trigger point, the system continuously scans the pressure change data backward until the pressure curve enters a stable range (i.e., the value fluctuation falls below the stability threshold within a specified window). The complete pressure change sequence within this range is then captured as a single-period response data segment. To standardize data analysis, the system performs time alignment and length normalization on each extracted response segment. This involves using linear interpolation or resampling algorithms to map data with varying numbers of sampling points across different periods to a standardized format with the same time length and sampling interval. The system then performs time-unit difference operations on these standardized pressure sequences to calculate the pressure rate of change between adjacent sampling points, thereby constructing a complete pressure rate sequence. Taking a nearby measuring point as an example, its historical data contains five disturbance events. The system extracts the start and end pressure data segments of each disturbance respectively, and unifies them into a standard sequence consisting of 100 time points through linear interpolation. Then, five equal-length rate of change sequences are generated through differential calculation for subsequent feature analysis and joint modeling.

[0040] The time period from the disturbance trigger to the pressure value entering the stable range refers to the period from the time the system detects the first significant pressure disturbance (such as an instantaneous increase or decrease) until the pressure fluctuation range stabilizes within a set threshold (such as ±0.05 MPa) for multiple consecutive time points. This period is a key data window for characterizing the response of the measuring point to the disturbance. "Normalization processing" refers to unifying pressure data of different lengths or sampling densities into a standard structure with equal length and equal sampling interval. A common method is linear resampling. For example, linear interpolation is used to expand the data of 83 sampling points collected within 0.8 seconds to 100 points to align it with other periodic data. "Unit time difference calculation" is to perform a first-order difference operation on the normalized series. That is, the difference between the pressure values ​​of two adjacent sampling points is divided by the sampling interval (for example, if sampling is once every 10 ms, the difference is divided by 0.01 s). This yields the rate of change of pressure per unit time, thus forming a numerical time series describing the change in the disturbance rate, which facilitates subsequent trend identification and model fitting. For example, a normalized pressure sequence of [1.0, 1.2, 1.35, 1.4] MPa corresponds to a rate of change sequence of [(1.2–1.0) / 0.01, (1.35–1.2) / 0.01, (1.4–1.35) / 0.01], or [20, 15, 5] MPa / s. This sequence intuitively reveals the rate of change and the degree of stability during the disturbance response process.

[0041] In each pressure change rate sequence, the maximum pressure change rate, the duration of the change rate and the time position of the occurrence of the change rate are calculated. A numerical triplet containing these three parameters is constructed as the measuring point feature vector. The feature vectors of all neighboring measuring points are combined into a set of joint feature vectors by weighted average according to distance. Based on the joint feature vectors, a neighborhood behavior joint model is constructed through multi-segment linear fitting.

[0042] To extract and jointly model the feature vectors of adjacent measurement points, each pressure rate of change sequence must first be scanned and statistically analyzed point by point. The system uses a sliding window detection method to identify local extreme points, thereby extracting the maximum pressure rate of change in each sequence (i.e., the maximum positive or negative value in the rate of change sequence). The system then determines the minimum time period (e.g., ≥0.1 seconds) during which the maximum rate of change continuously exceeds a set threshold and records this time period as the rate of change duration. The system then calculates the index of the sampling point where the maximum rate of change first occurs (e.g., the 30th point) and converts this into the occurrence time based on a standard sampling period (e.g., every 10 ms). The system then constructs a numerical triplet consisting of the maximum rate of change, the rate of change duration, and the rate of change occurrence time for each sequence as the disturbance response feature vector for that data. For example, if a sequence has a maximum rate of change of 15 MPa / s, a duration of 0.12 seconds, and first occurs at the 25th point (i.e., 0.25 seconds), its feature vector is (15, 0.12, 0.25). After performing the above operations on a preset number of adjacent measurement points, the system obtains a set of feature vectors. Combined with the physical distance from each measurement point to the target wireless digital pressure gauge, the system applies an inverse weighting function (e.g., wi = 1 / di) to weight these vectors and sums them. This yields a joint vector that incorporates the neighborhood disturbance characteristics. Finally, the system uses the joint vector as a parameter input and employs a multi-segment linear fitting method to restore the neighborhood disturbance trend model, which serves as an expression of the joint model of neighborhood behavior.

[0043] "Multi-segment linear fitting" treats the entire neighborhood disturbance response process as consisting of several linear stages. The trend of each stage is fitted separately, and these stages are represented by linear expressions with different slope and intercept parameters, which are then combined to form a complete model. This method captures multiple inflection points in the pressure change during the disturbance, reflecting the dynamic process from rapid response to relief and then stabilization. For example, the joint vector representing the rapid rise in the early stage (0–0.3s), the gradual change in the middle stage (0.3–0.7s), and the gradual stabilization in the late stage (0.7–1.0s) is fitted to three straight lines, y1=20t+1.0, y2=5t+1.5, and y3=1.8, respectively. The resulting "joint neighborhood behavior model" is a combination of these multi-segment functions, representing the typical variation of the disturbance response in the physical neighborhood. It is a key criterion for subsequently evaluating whether the data uploaded by the current target measurement point conforms to the physical laws of the neighborhood, especially in scenarios with address anomalies or misattribution of data, and serves as a comparison benchmark.

[0044] In this embodiment, the uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. The average difference and trend difference between the first residual and the second residual are calculated to generate the residual coupling degree and the coupling degree change trend, which are used to characterize the degree of transmission mapping chaos of the performance data. Specifically, The pressure disturbance response time series in the uploaded performance data is used as input and substituted into the historical behavior model and neighborhood behavior joint model corresponding to the wireless digital pressure gauge. At each unified sampling time point, the difference between the model prediction value and the actual pressure value is calculated to form the first residual sequence and the second residual sequence respectively. To fit the pressure disturbance response time series from the uploaded performance data into the corresponding historical behavior model and neighborhood behavior joint model for the wireless digital pressure gauge, a model function mapping relationship can be established. First, during the initialization phase, the system constructs a historical behavior model for the wireless digital pressure gauge based on multiple historical periods and stores it as a model expression (e.g., slope and intercept for each time period) using a piecewise linear or regression function. Simultaneously, disturbance response features are extracted and aggregated from a preset number of adjacent measurement points to construct a neighborhood behavior joint model, expressed as a multi-segment linear or weighted curve. Subsequently, during the actual monitoring period, the system receives the performance data uploaded by the wireless digital pressure gauge, extracts the pressure disturbance response time series for the current period, and normalizes the time axis to ensure that the input is aligned with the time of the two models. The system then inserts this time series point by point into the historical behavior model and the neighborhood behavior joint model, outputting predicted values ​​based on the fitted expressions of each model, forming a one-to-one corresponding prediction result sequence with the original data.

[0045] Taking the specific calculation process as an example, assume that the uploaded pressure disturbance response time series is a sequence of length 100 P = {p1, p2, ..., p100}, and each item corresponds to a time sampling point. The historical behavior model is a three-segment linear expression, such as: the function f1(t) = 20t + 1.0 for the 1st to 30th points, f2(t) = 5t + 1.5 for the 31st to 70th points, and f3(t) = 1.8 for the 71st to 100th points. The system compares the pi corresponding to each ti with the fj(ti) output value of the model at each time point and calculates the residual , forming the first residual sequence R(1)={r1(1),...,r100(1)}. The neighborhood behavior joint model performs the same steps to form the second residual sequence R(2). The entire process is synchronized on the time axis, so that the subsequent residual difference value sequence calculation has an accurate sampling point correspondence. This calculation method can effectively identify model fitting deviations and reveal whether the uploaded data is more consistent with the local historical pattern or the neighborhood linkage pattern, thus laying the foundation for attribution judgment.

[0046] Based on the two residual sequences, the difference of the residual values ​​of each corresponding sampling point is calculated to form a residual difference sequence; To calculate the difference in residual values ​​for each corresponding sampling point based on two residual sequences and thus form a residual difference sequence, the two residual sequences can be indexed and aligned at the data structure level for point-by-point calculation. In the specific implementation, the system first ensures that the time sampling points used by the historical behavior model and the neighborhood behavior joint model when constructing the residual sequence are completely consistent, for example, both are 100 points with an interval of 10ms. Suppose the first residual sequence is R(1)={r1(1),r2(1),...,r100(1)}, and the second residual sequence is R(2)={r1(2),r2(2),...,r100(2)}, the system can construct a dual-pointer synchronous traversal structure in memory and perform difference calculation point by point: for each sampling point i, calculate , store the difference Δri into the new sequence ΔR={Δr1,Δr2,...,Δr100}, which is the residual difference sequence. Take a specific example: if the 25th sampling point is 0.15 in the first residual sequence and -0.05 in the second residual sequence, then the difference is The entire residual difference sequence reflects the difference in response between the historical model fit results and the neighborhood model fit results at each moment, providing an important basis for subsequent evaluation of fit consistency and identification of data attribution errors. This sequence can also be used for further analysis tasks such as constructing statistical graphs, sliding trend windows, and identifying similarity thresholds.

[0047] All the differences in the residual difference sequence are averaged to obtain an average difference that reflects the overall deviation degree of the fitting; To quantitatively assess the overall fit deviation of the residual difference sequence, the "average difference" can be obtained by taking the arithmetic mean of all the differences in the sequence. This is accomplished by first ensuring that the residual difference sequence is a complete array of floating-point numbers, for example, ΔR = {Δr1, Δr2, ..., Δrn}, where each entry represents the difference between the residual values ​​of two models at the i-th time sampling point. The system then calculates the average difference by traversing the entire array, summing the values ​​of all Δri, and dividing this sum by the total number of sampling points, n. For example, assuming the residual difference sequence has five sampling points, with values ​​{0.02, 0.04, 0.01, 0.03, 0.05}, the sum is 0.15, and the average difference is 0.03. A higher value indicates a greater discrepancy between the two models' fits for the currently uploaded performance data, suggesting that the data may not conform to the typical behavior of either model and carries a higher risk of attribution confusion. Conversely, a lower average difference indicates that both models can explain the data well, resulting in a lower risk of attribution determination. This approach not only simplifies the calculation process and produces intuitive results, but also facilitates subsequent normalization and trend coupling, making it a crucial foundation for building intelligent attribution identification mechanisms.

[0048] Perform local linear regression on the residual difference series in a fixed-time sliding window manner, extract the fitting slope in each window, and calculate the standard deviation of the slope values ​​in all windows to obtain the trend difference used to characterize the changing trend of the fitting difference; To quantitatively identify trends in fitting differences within a residual difference sequence, a fixed-length sliding window approach can be used to perform local linear regression analysis. Specifically, the system first sets a time window length (e.g., 10 sampling points) and iteratively slides across the entire residual difference sequence with a sliding step size (e.g., 1 or 2), extracting continuous difference subsequences of equal length. Linear regression is performed on each subsequence within the sliding window, using the window's time index as the independent variable t={1,2,...,k} and the corresponding difference Δr={Δr1,...,Δrk} as the dependent variable. A linear model y=at+b is fitted, where the slope a represents the trend of the difference within that time period. Linear regression is performed once for each window, and its slope is extracted to form a sliding slope sequence. Assuming the residual difference sequence length is 100, the window length is 10, and the sliding step size is 1, 91 windows are obtained, and 91 slope values ​​are calculated, forming the slope sequence A={a1,a2,...,a91}.

[0049] By calculating the standard deviation of the slope series, we can obtain the trend difference, which characterizes the changing trend of the fitting discrepancy. A larger standard deviation indicates greater slope fluctuations within each local window, indicating a clear upward or downward trend in the residual difference over the time series. This suggests a structural shift in the fit results between the two models for the current data, suggesting potentially unstable attribution decisions. Conversely, a smaller standard deviation indicates a more stable fit error and a more stable attribution decision. For example, if the slopes of the five windows are {0.01, 0.03, −0.02, 0.00, 0.02}, the mean is 0.008 and the standard deviation is approximately 0.017. The sliding window approach captures local fluctuations in the data, while linear regression extracts trend signals. Aggregating the slope standard deviations as the trend difference effectively reflects the stability of the overall fitting state over time, providing a dynamic quantitative basis for attribution error risk analysis.

[0050] The average difference and the trend difference are respectively subjected to minimum-maximum normalization processing, and form the residual coupling degree and the coupling degree change trend, which are used to characterize the degree of transmission mapping confusion of the uploaded performance data in the case of abnormal address overlap. Specifically: when the residual coupling degree and the coupling degree change trend are both in the preset high value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is high; when the residual coupling degree and the coupling degree change trend are both in the preset low value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is low; when the residual coupling degree and the coupling degree change trend are neither in the preset high value range nor in the preset low value range, it is characterized that the transmission mapping confusion degree of the current uploaded performance data in the case of abnormal address overlap is medium.

[0051] In order to normalize the average difference and trend difference, and construct two evaluation indicators, namely the residual coupling degree and the coupling degree change trend, the Min-Max Normalization method can be used to normalize the original values. This processing method can transform the values ​​of different dimensions or scales into a unified interval by setting a normalization interval (usually [0,1]), which is convenient for subsequent joint evaluation. In the specific implementation, the system first extracts the historical minimum value of the average difference from the historical training data or statistical samples over a long period of time. With the maximum value , and similarly obtain the historical minimum and maximum values ​​of the trend difference. Suppose the average difference currently calculated is , then the normalized value calculation formula is: , the trend difference is also processed in the same way. For example, if the historical average difference interval is [0.01, 0.10] and the current average difference is 0.07, then the normalized value is This value is defined as the "residual coupling degree", which is used to measure the consistency of the overall deviation of the residual fitting of the two models; similarly, the trend difference is defined as the "coupling degree change trend" after normalization, which is used to quantify the intensity of the fluctuation of the fitting state over time. This normalization process not only improves the versatility and comparability of the algorithm, but also provides a unified and controllable evaluation dimension for subsequent attribution judgment and classification based on threshold intervals, ensuring that in the case of abnormal overlap of device addresses, the system can stably measure the degree of confusion in the transmission mapping of performance data.

[0052] In the performance data attribution judgment based on residual comparison, the residual coupling degree reflects the overall fit difference between the current uploaded performance data under the historical behavior model and the joint neighborhood behavior model, while the coupling degree trend reflects the dynamic fluctuation characteristics of this difference over time. When both indicators are simultaneously in the preset high value range, it indicates that the uploaded performance data deviates significantly from both models, and this deviation fluctuates greatly over time, reflecting extremely poor consistency with the historical behavior pattern and neighborhood behavior structure. Therefore, it is judged as a high degree of transmission mapping confusion. Conversely, when both indicators are in the preset low value range, it indicates that the uploaded performance data exhibits stable and small fitting errors in both models, showing high consistency and almost no risk of attribution errors caused by address anomaly overlap. Therefore, it is judged as a low degree of confusion. When both indicators are neither in the high nor low value range, that is, they are in the intermediate fuzzy zone, it indicates that the current data may be partially distorted, but the overall perturbation behavior has not completely deviated from the model prediction. The possibility of attribution anomaly exists, but it is not yet serious. Therefore, it is classified as moderate.

[0053] Different levels of transmission mapping chaos correspond to different risk levels and processing strategies: High levels of chaos mean that the data segment is highly likely from a non-target measurement point, and its attribution label is highly misleading. If used for subsequent trend modeling or policy execution, this will significantly reduce prediction accuracy and system stability. Therefore, immediate data isolation and attribution reconstruction are required. Moderate levels of chaos indicate a high probability of attribution anomaly, but some behavioral consistency remains. Such data requires triggering intermediate intervention measures such as behavioral feature backtracking and measurement point matching correction, and is marked as pending for semi-supervised modeling. Low levels of chaos indicate that the data is generally reliable and can be used as a normal sample for behavioral learning and state inference without intervention. Through this classification mechanism, wireless digital pressure gauges in IoT systems can make data attribution more accurate and their layered responses more flexible in the presence of address anomalies and overlap, effectively improving the intelligence and robustness of the monitoring platform.

[0054] Based on the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend, determine whether the uploaded performance data has attribution errors; In this embodiment, the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend is used to determine whether the uploaded performance data has an attribution error problem. Specifically, When the transmission mapping disorder degree is high, it is determined that there is an attribution error problem in the currently uploaded performance data; When the transmission mapping disorder level is medium, based on the average historical fitting error level of the performance data in the behavior model of the current measurement point, if the first residual of the performance data at the current measurement point exceeds a preset tolerance interval of the average historical fitting error level, then it is determined that the performance data has an attribution error problem; otherwise, it is determined that the performance data does not have an attribution error problem; When the transmission mapping confusion level is low, it is determined that there is no attribution error problem in the currently uploaded performance data.

[0055] In actual implementation, the degree of transmission mapping confusion in performance data under abnormal address overlap can be categorized into three categories using preset thresholds for residual coupling and coupling trend, namely high, medium, and low. Corresponding data attribution judgment logic can then be developed accordingly. A high degree of confusion indicates a significant deviation in the fit between the historical behavior model and the joint neighborhood behavior model for the current data, indicating that the data's behavior cannot be reasonably explained at either the local measurement point or its neighborhood. Therefore, the performance data is directly deemed to have misattribution, thus avoiding incorporating significantly abnormal data into subsequent analysis. A low degree of confusion indicates high consistency and minimal discrepancy between the local and neighborhood models, resulting in stable and predictable data behavior. Therefore, the data is deemed to have no misattribution. For medium confusion, while the fit deviation has not yet reached abnormal levels, there is still a potential risk of misattribution. Comparison should be made with the average level of the first residuals in the historical behavior model over a recent period. If the first residual of the current data exceeds the preset tolerance interval of the historical average residual, the fit error is significantly large and the data is likely to be considered abnormal. Otherwise, it is considered normal data. Through this multi-level judgment mechanism, not only can timely identification of high-risk misattributed data be achieved, but the intelligent fault-tolerant processing capability of boundary data is also retained, thereby improving the accuracy and robustness of data attribution judgment, avoiding misjudgment caused by error fluctuations, and ensuring the stable operation of the monitoring and management system in complex field environments.

[0056] For performance data with misattribution issues, the performance data is divided into continuous time segments. The behavioral characteristics of each time segment are matched with the historical data of a preset number of measurement points. Based on the matching results, the target attribution measurement point of the performance data is determined through attribution voting to complete the attribution adjustment operation. In this embodiment, for performance data with attribution errors, the performance data is divided into continuous time segments according to a fixed time window length, the pressure disturbance response time series within each time segment is extracted, and the pressure change rate per unit time is calculated to form a pressure change rate sequence; the pressure change rate sequence is similarly matched with a historical pressure change rate sample sequence generated by a preset number of pressure disturbance response time series of the same length in a historical period, and a similarity scoring algorithm based on dynamic time warping (DTW) is used to calculate the matching score of each measuring point. A weighted vote is performed based on the matching scores of all measuring points, and the measuring point with the highest number of votes is selected as the target attribution measuring point for the current time segment. The attribution measuring points of all time segments are frequency counted, and finally the measuring point with the highest frequency is determined as the target attribution measuring point for the performance data, completing the attribution adjustment operation.

[0057] During implementation, the performance data with misattribution issues is first divided into multiple, continuous, non-overlapping time segments, using a fixed time window length (e.g., 10 seconds, 30 seconds, or 1 minute) set by the system. The resulting time series is then extracted from each time segment. This series consists of the pressure data recorded from the start to the end of the time segment. Assuming the data is recorded at a fixed sampling rate, the pressure difference between adjacent time points in the series is calculated and divided by the sampling interval to obtain a pressure rate of change per unit time. For example, if pressure data is collected once per second in a time segment and continuously recorded as [P1, P2, P3, ..., Pn], the rate of change sequence is [(P2-P1) / 1, (P3-P2) / 1, ..., (Pn-Pn-1) / 1], representing the pressure change rate per second. This rate of change sequence effectively extracts the characteristics of the disturbance behavior within the current segment and is subsequently used for dynamic matching analysis with historical measurement point data. This process can be completed in real time after data is uploaded through programming, without the need for human intervention, and is suitable for large-scale concurrent device data processing.

[0058] During the implementation process, the pressure disturbance response time series of each candidate measurement point, with a length equal to the current time segment, are first obtained from a preset number of candidate measurement points. The pressure change rate per unit time is calculated for these series to form a historical pressure change rate sample sequence. Next, the dynamic time warping (DTW) algorithm is used to calculate the similarity score between the pressure change rate series of the current time segment and each historical sample sequence. DTW can effectively align fluctuation characteristics with time misalignment, improving matching robustness. The DTW matching score of each measurement point is normalized and converted into a matching weight. Lower scores indicate higher similarity and a greater weight. A weighted voting mechanism is then used to factor the matching weights of all measurement points into the total voting score. The measurement point with the highest number of votes is designated as the target attribution measurement point for that time segment. The frequency of the target attribution measurement points for all time segments is calculated, i.e., the number of times each measurement point was selected as the target attribution. The measurement point with the highest frequency is selected as the final target attribution measurement point for the entire performance data. Attribution adjustment is then performed based on this score to ensure reasonable data attribution. For example, if the performance data is divided into five time segments, three of which are voted to belong to measurement point A and two are voted to belong to measurement point B, the data will ultimately be attributed to measurement point A.

[0059] Similarity matching is the process of evaluating the degree of similarity between two data sequences in feature space and is commonly used in pattern recognition and anomaly detection scenarios. The DTW algorithm is a classic time series alignment algorithm that can handle data streams with inconsistent rates. It uses dynamic programming to find the shortest "alignment path" between two sequences to minimize the overall distance. For example, comparing a response sequence with a sudden pressure change with a historical sample sequence that has a slightly misaligned occurrence but a consistent trend can yield a lower DTW score. Weighted voting is an aggregate decision-making mechanism. In this solution, DTW similarities are converted into voting weights to make a comprehensive decision on the attribution of multiple measurement points, avoiding occasional mismatches in a single time slice. Frequency statistics uses global statistical analysis to extract consistent attribution trends across most time slices, thereby improving the stability and accuracy of the final decision. For example, if measurement point A receives three votes and measurement point B receives two votes in five segments, measurement point A is the final target attribution. Combining these methods effectively enables intelligent identification and automatic correction of misattributed data.

[0060] After completing the attribution adjustment, the residual coupling degree, coupling degree change trend, judgment results and target attribution measurement points are recorded to form an attribution judgment trajectory, and intervention processing is performed in areas where attribution errors are concentrated, including reconstructing behavior labels, enabling the joint verification process of behavior characteristics and measurement point locations, and restricting the uploaded data in this area from participating in trend modeling.

[0061] In order to achieve the traceability and optimization of the ownership adjustment process, the key data in the ownership judgment process can be structured and recorded to form an "ownership judgment track". Specifically, after completing each ownership adjustment, the system needs to automatically extract and record the parameters related to the ownership decision at that time, including the normalized values ​​of the residual coupling degree and the coupling degree change trend, the ownership judgment conclusion made based on the value, the identification information of the target ownership measurement point and its corresponding matching confidence. These data are bound and stored in the logical record corresponding to the wireless digital pressure gauge in the form of a time series, and can be used for subsequent ownership judgment result comparison, model tracing and strategy adjustment. This method combines the judgment module in the software logic with the storage mechanism to achieve traceability and explainability of the ownership judgment process without human intervention.

[0062] In order to further improve the accuracy of attribution judgment and the system's adaptability, when the system detects that attribution errors occur frequently and concentratedly in a specific physical area, an intervention process can be triggered. The first step in the intervention process is to reconstruct the behavioral labels of the wireless digital pressure gauges in the area, that is, to re-collect their pressure disturbance response data under static fluid conditions, and generate and bind new behavioral features through a unified process. Secondly, the system enables a joint verification process of behavioral features and the spatial position of the measuring points, that is, it not only relies on the behavioral model to make attribution judgments on the data, but also incorporates the relative position of the device in the topology into the comparison parameters to ensure that the behavioral logic is reasonable and the spatial attribution is correct. This joint verification can be achieved by setting data consistency indicators and distance confidence weights within the spatial neighborhood.

[0063] Furthermore, to prevent erroneous data from interfering with the trend modeling process, the system temporarily restricts raw data uploaded within this physical area from directly participating in modeling operations. Until data attribution stability is restored, this data will be used only as an auxiliary comparison and will not be used as training input for updating trend prediction models. This strategy, implemented through modeling permission control and tag filtering mechanisms at the software level, ensures the accuracy of model training data while preventing misattributed data from misleading the overall monitoring decision-making chain, thereby improving the stability and robustness of the entire IoT-based wireless digital pressure gauge performance data monitoring and management method.

[0064] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0065] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means (e.g., infrared, wireless, microwave, etc.). A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0066] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0067] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0069] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0070] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0071] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A wireless digital pressure gauge performance data monitoring and management method based on the Internet of Things, characterized in that: The specific steps include: Obtain pressure disturbance response data of the wireless digital pressure gauge in a static fluid environment during the initial deployment, construct a behavior label based on the pressure disturbance response data, and bind the behavior label to the wireless digital pressure gauge; After the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted and compared with the response time of the adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in a situation of abnormal device address overlap. When the wireless digital pressure gauge is in a situation of abnormal device address overlap, a historical behavior model and a neighborhood behavior joint model are constructed to fit the uploaded performance data respectively to obtain the first residual and the second residual. Based on the first residual and the second residual, the residual coupling degree and the coupling degree change trend are generated to characterize the degree of transmission mapping confusion of the performance data. According to the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend, it is determined whether the uploaded performance data has an attribution error problem. For performance data with misattribution issues, the performance data is divided into continuous time segments. The behavioral characteristics of each time segment are matched with the historical data of a preset number of measurement points. Based on the matching results, the target attribution measurement point of the performance data is determined through attribution voting to complete the attribution adjustment operation. After completing the attribution adjustment, the residual coupling degree, coupling degree change trend, judgment results and target attribution measurement points are recorded to form an attribution judgment trajectory, and intervention processing is performed in areas where attribution errors are concentrated, including reconstructing behavior labels, enabling the joint verification process of behavior characteristics and measurement point locations, and restricting the uploaded data in this area from participating in trend modeling.

2. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 1 is characterized in that: After the wireless digital pressure gauge uploads its performance data, the pressure disturbance response time series is extracted and compared with the response time of adjacent measuring points. Combined with the physical topological relationship between the measuring points, it is determined whether the wireless digital pressure gauge is in an abnormal device address overlap situation. Specifically: After the wireless digital pressure gauge uploads performance data, the pressure disturbance response time series is extracted. The pressure disturbance response time series consists of continuous pressure change data from the disturbance triggering starting point to the pressure value entering the stable range. The disturbance response time of the wireless digital pressure gauge is obtained by calculating the time interval between the moment when the pressure change rate reaches the maximum value and the disturbance triggering starting point in the pressure disturbance response time series; From the same data synchronization period, a preset number of adjacent measuring points are selected, the pressure disturbance response time series of each measuring point is extracted respectively, and the disturbance response time set of the adjacent measuring points is calculated in the same way; Based on the physical topology information between the wireless digital pressure gauge and each adjacent measuring point, the corresponding physical connection path and pipeline distance data are obtained. In combination with the preset fluid medium propagation speed, the theoretical disturbance propagation time from each adjacent measuring point to the wireless digital pressure gauge is calculated. Based on the difference between the response time of each measuring point in the set of neighboring measuring point disturbance response times and its theoretical propagation time, the average propagation offset time of the disturbance under the current topology is calculated, and the theoretical response time delay range is constructed. The disturbance response time of the wireless digital pressure gauge is compared with the theoretical response time delay range. When the response time exceeds the theoretical range boundary threshold, it is determined that the wireless digital pressure gauge is in an abnormal device address overlap situation.

3. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 2 is characterized in that: When the wireless digital pressure gauge is in a situation of abnormal device address overlap, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in the historical period, and a neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measuring points that have a physical topological connection relationship with the wireless digital pressure gauge. The uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. The residual coupling degree and the coupling degree change trend are generated by calculating the average difference and trend difference between the first residual and the second residual, which are used to characterize the degree of transmission mapping chaos of the performance data.

4. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 3 is characterized in that: When the wireless digital pressure gauge is in a state of abnormal device address overlap, a historical behavior model is constructed based on the pressure disturbance response time series uploaded by the wireless digital pressure gauge in the historical period. Specifically, Selecting continuous pressure change data from the disturbance triggering start point to the pressure value entering the stable range in a preset number of historical periods; Based on the continuous pressure change data, the pressure change rate per unit time is calculated to form a pressure change rate sequence, and the pressure change rate sequence is clustered using a time series similarity algorithm to extract a disturbance response behavior feature sequence containing pressure change rate samples of a preset time length; A piecewise linear function model is constructed based on the characteristic sequence fitting of each disturbance response behavior. The combination weight is set according to the disturbance response amplitude and duration corresponding to each piecewise linear function model. The piecewise linear function models are weighted combined to construct a historical behavior model for describing the disturbance response behavior of the wireless digital pressure gauge.

5. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 4 is characterized in that: A neighborhood behavior joint model is constructed based on the pressure disturbance response time series of a preset number of neighboring measurement points that have a physical topological connection relationship with the wireless digital pressure gauge. Specifically: Obtain physical connection path and distance information based on the physical pipeline connection diagram between the wireless digital pressure gauge and other measuring points, and filter out adjacent measuring points whose physical distance does not exceed the set distance threshold; The continuous pressure change data of each adjacent measuring point from the disturbance triggering point to the pressure value entering the stable range within multiple historical periods are selected, and each data segment is normalized according to the unified time sampling interval and length. The pressure change rate series is obtained by performing unit time difference calculation on the continuous pressure data. In each pressure change rate sequence, the maximum pressure change rate, the duration of the change rate and the time position of the occurrence of the change rate are calculated, and a triplet containing their values ​​is constructed as the measuring point feature vector. The feature vectors of all neighboring measuring points are combined into a set of joint feature vectors by weighted average of distance, and a neighborhood behavior joint model is constructed based on the joint feature vectors through multi-segment linear fitting.

6. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 5 is characterized in that: The uploaded performance data is used as input, and fitting is performed in the historical behavior model and the neighborhood behavior joint model to obtain the first residual and the second residual. The average difference and trend difference between the first and second residuals are calculated to generate the residual coupling degree and the coupling degree change trend, which are used to characterize the degree of transmission mapping chaos of the performance data. Specifically: The pressure disturbance response time series in the uploaded performance data is used as input and substituted into the historical behavior model and neighborhood behavior joint model corresponding to the wireless digital pressure gauge. At each unified sampling time point, the difference between the model prediction value and the actual pressure value is calculated to form the first residual sequence and the second residual sequence respectively. Based on the two residual sequences, the difference of the residual values ​​of each corresponding sampling point is calculated to form a residual difference sequence; All the differences in the residual difference sequence are averaged to obtain an average difference that reflects the overall deviation degree of the fitting; Perform local linear regression on the residual difference series in a fixed-time sliding window manner, extract the fitting slope in each window, and calculate the standard deviation of the slope values ​​in all windows to obtain the trend difference used to characterize the changing trend of the fitting difference; The average difference and trend difference are respectively subjected to minimum-maximum normalization processing, and the residual coupling degree and coupling degree change trend are formed to represent the degree of transmission mapping confusion of the uploaded performance data under the condition of abnormal address overlap. Specifically, when the residual coupling degree and the coupling degree change trend are both in the preset high value range, it indicates that the transmission mapping confusion degree of the current uploaded performance data under the condition of abnormal address overlap is high; When the residual coupling degree and the coupling degree change trend are both in the preset low value range, it indicates that the transmission mapping confusion degree of the current uploaded performance data under the condition of abnormal address overlap is low; When the residual coupling degree and the coupling degree change trend are both not in the preset high value range and not in the preset low value range, it indicates that the transmission mapping confusion degree of the current upload performance data under the condition of abnormal address overlap is medium.

7. The method for monitoring and managing performance data of a wireless digital pressure gauge based on the Internet of Things according to claim 6 is characterized in that: Based on the degree of transmission mapping confusion corresponding to the residual coupling degree and the coupling degree change trend, it is determined whether the uploaded performance data has an attribution error problem. Specifically: When the transmission mapping disorder degree is high, it is determined that there is an attribution error problem in the currently uploaded performance data; When the transmission mapping disorder level is medium, based on the average historical fitting error level of the performance data in the behavior model of the current measurement point, if the first residual of the performance data at the current measurement point exceeds a preset tolerance interval of the average historical fitting error level, then it is determined that the performance data has an attribution error problem; otherwise, it is determined that the performance data does not have an attribution error problem; When the transmission mapping confusion level is low, it is determined that there is no attribution error problem in the currently uploaded performance data.

8. The method for monitoring and managing performance data of wireless digital pressure gauges based on the Internet of Things according to claim 7 is characterized in that: For performance data with attribution errors, the performance data is divided into continuous time segments according to a fixed time window length, the pressure disturbance response time series within each time segment is extracted, and its unit time pressure change rate is calculated to form a pressure change rate sequence; the pressure change rate sequence is matched with the historical pressure change rate sample sequence generated by the pressure disturbance response time series of the same length at a preset number of measuring points in the historical period, and the matching score of each measuring point is calculated using a similarity scoring algorithm based on dynamic time warping (DTW). A weighted vote is performed based on the matching scores of all measuring points, and the measuring point with the highest number of votes is selected as the target attribution measuring point for the current time segment. The frequency of the attribution measuring points of all time segments is counted, and finally the measuring point with the highest frequency is determined as the target attribution measuring point for the performance data, completing the attribution adjustment operation.

Images