High-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters

Abstract

The invention discloses a high-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters. The high-temperature steam pipeline stress-strain state monitoring system comprises a sensor acquisition module, a data processing module, a wireless communication module, an energy acquisition module, an edge calculation module, a fault self-diagnosis module and a server. The sensor acquisition module acquires first sensing information through a heterogeneous sensor combination distributed on the surface of a pipeline, and the data processing module extracts stress concentration coefficient, strain rate, temperature gradient and vibration frequency characteristic parameters. And the wireless communication module adopts a multi-hop network mode to transmit data to the edge calculation module for secondary processing to obtain pipeline operation information. The energy acquisition module acquires energy from the pipeline surface to supply power to the sensor. And the fault self-diagnosis module realizes abnormal device positioning isolation through cross validation and link bit error rate analysis. The server comprehensively receives various kinds of information to complete continuous monitoring of the pipeline state, and a complete self-powered intelligent monitoring system is formed.

Description

Technical Field

[0001] The invention relates to the field of stress monitoring, and in particular to a high-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters. Background Art

[0002] As a core component of the energy transportation system, real-time monitoring of the stress and strain state of high-temperature steam pipelines is of great significance for preventing structural failure. Traditional monitoring methods mostly use a single type of sensor for local parameter collection, which is difficult to fully characterize the multi-dimensional stress distribution characteristics of the pipeline, and there are monitoring blind spots caused by insufficient sensor complementarity. Existing wired transmission solutions rely on fixed wiring, which is prone to line aging and breakage under harsh working conditions such as high temperature and vibration, causing data interruption; at the same time, the external power supply mode is limited by the pipeline environment and is difficult to meet the energy needs of long-term monitoring. Most systems lack autonomous fault diagnosis capabilities, which can easily lead to overall monitoring failure when the sensor is abnormal or the communication link fails. In addition, traditional data processing methods have problems such as large transmission load and high response delay, making it difficult to achieve real-time assessment of the health status of the pipeline. In addition, existing technologies often use global shutdown and maintenance strategies to deal with abnormal conditions, lacking local fault tolerance mechanisms, which seriously affects monitoring continuity. Summary of the invention

[0003] In view of the above problems, the present invention provides a monitoring system that meets the requirements of intelligent monitoring of high-temperature steam pipelines in terms of monitoring accuracy, environmental adaptability and operation and maintenance efficiency.

[0004] To achieve the above-mentioned purpose, the present application provides a high-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters, including a sensor acquisition module, a data processing module, a wireless communication module, an energy acquisition module, an edge computing module, a fault self-diagnosis module and a server. The sensor acquisition module includes multiple heterogeneous sensors, and is distributed on the pipeline in a first preset manner. The heterogeneous sensors are configured as at least two of strain gauges, optical fiber sensors and vibration sensors. The sensor acquisition module is used to collect first sensor information; the data processing module is used to receive and process the first sensor information and extract characteristic safety parameters, and the characteristic safety parameters include stress concentration factor, strain rate, temperature gradient and vibration frequency; the wireless communication module is configured to use a multi-hop network communication mode to transmit the first sensor information and / or characteristic safety parameters to the server. Transmitted to the edge computing module; the energy collection module is arranged on the surface of the pipeline, the energy collection module is electrically connected to the sensor collection module, the energy collection module is used to collect energy from the surface of the pipeline and convert it into electrical energy to be transmitted to the heterogeneous sensor; the edge computing module is used to perform data processing on the characteristic safety parameters to obtain the first processing information, and transmit the first processing information to the server, the first processing information is the operation information of the pipeline; the fault self-diagnosis module is used to detect the abnormal state, the abnormal state is configured as any one of the collection abnormality, communication abnormality, and power supply abnormality, the fault self-diagnosis module is used to realize the isolation of fault location and abnormal devices through cross-validation and link bit error rate analysis; the server is used to receive the first sensing information and / or the first processing information and / or the characteristic safety parameters and continuously monitor the working state of the pipeline.

[0005] In some embodiments, the fault self-diagnosis module is used to implement fault location and isolation of abnormal devices through cross-validation and link bit error rate analysis, including: Cross-validate the plurality of first sensing information to obtain a plurality of first stress calculation values, synchronously obtain the first stress actual value associated with the first sensing information corresponding to each first stress calculation value, and judge whether the deviation value between the first stress calculation value and the first stress actual value is within the range of a first preset threshold value, if not, it indicates that the heterogeneous sensor corresponding to the first stress actual value is in acquisition abnormality; and, monitoring the communication link status of the wireless communication module and calculating the link bit error rate, and determining whether the link bit error rate is within a second preset threshold, if not, indicating that the wireless communication module is in a communication abnormality; and, monitoring the power access value of each heterogeneous sensor, and obtaining the calibrated power value of the heterogeneous sensor; When the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, a deviation between the power access value and the calibrated power value is calculated and recorded as a first deviation value; Determine whether the first deviation value is within a range of a third preset threshold value, and if not, it indicates that the heterogeneous sensor corresponding to the power access value is in power supply abnormality; If the abnormal device is a heterogeneous sensor, the heterogeneous sensor is fault-isolated and the backup acquisition mode associated with the heterogeneous sensor is enabled; If the abnormal device is a wireless communication module, switch to a backup communication link, or adjust the backup communication mode of the wireless communication module.

[0006] In some embodiments, the alternate acquisition mode is configured to: Acquire location information of the heterogeneous sensor in an abnormal state, record it as abnormal location information, and record the heterogeneous sensor in the abnormal state as an abnormal sensor; Taking the abnormal location information as the center and the preset length as the radius, a backup collection area is divided, and other heterogeneous sensors except the abnormal sensor in the backup collection area are recorded as backup sensors; and, obtaining a predetermined collection frequency of the abnormal sensor, recorded as a first collection frequency; generating a second collection frequency according to the first collection frequency; Controlling the standby sensor to collect standby sensor information according to the second collection frequency; Performing data fusion on the plurality of spare sensor information to obtain a second calculated stress value; The second calculated stress value is used as the stress value corresponding to the abnormal position information.

[0007] In some embodiments, if the abnormal device is a wireless communication module, switching to a backup communication link, or adjusting the backup communication mode of the wireless communication module includes: The backup communication link is a pre-configured redundant communication path; If the backup communication link is unavailable, the backup communication mode of the wireless communication module is enabled, and the backup communication mode includes reducing the communication rate and switching the communication protocol; And, record abnormal communication events and transmit them to the edge computing module and the server.

[0008] In some embodiments, the wireless communication module includes multiple sensor nodes, which are distributed on the pipeline in a second preset manner to form a multi-hop network. Each sensor node is configured to have data receiving and relay forwarding functions. Each sensor node establishes a communication connection with at least one neighbor node, and the neighbor nodes are configured as other sensor nodes arranged adjacent to the sensor node.

[0009] In some embodiments, the multi-hop network communication mode is configured to include the following steps: When a sensor node needs to send data, it selects the nearest neighbor node as the next hop node according to the preset routing protocol; After receiving the data, the neighbor node forwards the data to the next relay node according to the routing protocol until the data reaches the edge computing module. The relay node is the neighbor node adjacent to the neighbor node; The edge computing module receives data from multiple sensor nodes and aggregates and processes them; The communication status of each sensor node in the multi-hop network is monitored in real time. If a fault is detected, the routing protocol automatically adjusts the network topology and selects an alternative path for data transmission.

[0010] In some embodiments, the energy harvesting module includes a vibration energy harvester, a wind speed energy harvester, a power storage unit, and a power management circuit. The energy harvesting module is used to harvest energy from the pipeline surface and convert it into electrical energy for transmission to the heterogeneous sensor. Vibration energy collectors and wind speed energy collectors are set at key locations of the pipeline, including pipeline elbow areas, weld areas, gas flow ports and high stress concentration areas. The vibration energy collector is used to convert mechanical vibration energy on the pipeline surface into electrical energy, and the wind speed energy collector is used to convert the air flow velocity around the pipeline into electrical energy. storing the electric energy generated by the vibration energy harvester and the wind speed energy harvester in a power storage unit; The power management circuit monitors the reserve power value of the power reserve unit and the power access value of the heterogeneous sensor in real time; When the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, a deviation between the power access value and the calibrated power value is calculated and recorded as a second deviation value; determining whether the reserve power value is greater than a second deviation value, and if so, connecting the power reserve unit and the heterogeneous sensor; If not, do not connect.

[0011] In some embodiments, the data processing module is used to receive and process the first sensor information and extract the characteristic safety parameter, including: Generate a data processing task according to the first sensor information, decompose the data processing task into multiple processing subtasks, and assign the multiple processing subtasks to a multi-core CPU for parallel calculation; Multi-core CPU parallel computing includes the following steps: Using wavelet transform or Fourier transform to compress and reduce noise of the first sensor information, so as to reduce the data volume of the first sensor information; Using a Kalman filter algorithm to eliminate sensor noise and environmental interference noise in the first sensor information to obtain second sensor information; The second sensor information is fused by using a data fusion algorithm to obtain characteristic safety parameters; Send characteristic security parameters to the edge computing module.

[0012] In some embodiments, the edge computing module is used to process the characteristic security parameter to obtain the first processing information, including: The characteristic safety parameters are processed by incremental calculation, and the data processing includes the following steps: Performing Huffman coding on the characteristic security parameter, and recording the processed characteristic security parameter as the first packaged data; and, constructing a pipeline operation status feature vector based on the feature safety parameter; Performing status evaluation on the operating status feature vector to obtain evaluation results, the evaluation results including warning status, maintenance status, overhaul status and normal status; Performing Huffman coding on the evaluation result, and recording the processed evaluation result as second packaged data; Integrate the second packaged data with the first packaged data to form first processed information, and transmit the first processed information to the server; And, store the characteristic safety parameters and evaluation results in a local database.

[0013] In some embodiments, the operating state feature vector is evaluated to obtain an evaluation result including: Inputting the operating state feature vector into the multi-level state classification model, the operating state feature vector includes the pipeline axial stress gradient, the hoop strain fluctuation rate, the temperature-stress coupling coefficient, the steam pressure change entropy value and the vibration spectrum distortion degree; The multi-level state classification model performs the following classification judgments: First-level judgment: When the temperature-stress coupling coefficient exceeds the preset dynamic threshold and the duration exceeds the range of the preset duration threshold, the warning state is triggered; Second level judgment: If the product of the axial stress gradient and the hoop strain fluctuation rate exceeds the material yield critical value, the maintenance state is triggered; The third level judgment: when the vibration spectrum distortion degree and the vibration spectrum distortion degree under the preset fault mode are placed within the same cosine similarity threshold, the maintenance state is triggered; Fourth level judgment: If the operating state feature vector is within the range of the preset operating threshold, the normal state is triggered; Establish a decision fusion mechanism based on fuzzy logic to perform weighted fusion on the judgment results output by the multi-level state classification model; A sliding time window algorithm is used to perform trend analysis on the evaluation results of a preset number of consecutive sampling cycles, and the evaluation result output is triggered when the same operating state appears for a preset number of consecutive times; And, the evaluation results are matched with historical failure cases in the local database for similarity, and the credibility level of the evaluation results is corrected.

[0014] Different from the prior art, the above technical solution has the following beneficial effects: The present invention provides a stress-strain state monitoring system for a high-temperature steam pipeline based on characteristic safety parameters, including a sensor acquisition module, a data processing module, a wireless communication module, an energy acquisition module, an edge computing module, a fault self-diagnosis module and a server. The sensor acquisition module collects first sensing information through a combination of heterogeneous sensors distributed on the surface of the pipeline, and extracts characteristic parameters such as stress concentration factor, strain rate, temperature gradient and vibration frequency through the data processing module. The wireless communication module uses a multi-hop network mode to transmit data to the edge computing module for secondary processing to obtain pipeline operation information. The energy acquisition module obtains energy from the surface of the pipeline to power the sensor. The fault self-diagnosis module realizes the location and isolation of abnormal devices through cross-validation and link bit error rate analysis. The server comprehensively receives various types of information to complete continuous monitoring of the pipeline status, forming a complete self-powered intelligent monitoring system.

[0015] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0017] In the drawings of the specification: Figure 1 This is a schematic diagram of steps S101 to S106 of the standby acquisition mode described in the specific implementation method; Figure 2 This is a schematic diagram of steps S201 to S204 of the multi-hop network communication mode described in the specific implementation method; Figure 3 It is a schematic diagram of steps S301 to S307 of the energy harvesting module according to the specific implementation method. DETAILED DESCRIPTION

[0018] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0019] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0020] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0021] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0022] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0023] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0024] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0025] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0026] The processor described in the embodiments of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein.

[0027] The computer program involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disk, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve the same or equivalent functions as the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner, or it can be stored in multiple media in a distributed manner. The memory containing the computer device readable storage medium can be a non-volatile memory or a random access memory. These computer device readable storage media can be built into the device, or they can be connected to the device involved in the embodiment as an external device or a part of an external device. In some embodiments, a memory with a computer device readable storage medium is deployed locally; in other embodiments, a solution of deploying the memory away from the processor may also be adopted, such as a network attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment may be stored in plaintext / ciphertext form, or may be designed as training data, which may be integrated and reorganized through model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0028] See also Figures 1 to 3To achieve the above-mentioned purpose, the present embodiment provides a stress-strain state monitoring system for a high-temperature steam pipeline based on characteristic safety parameters, including a sensor acquisition module, a data processing module, a wireless communication module, an energy acquisition module, an edge computing module, a fault self-diagnosis module and a server. The sensor acquisition module includes a plurality of heterogeneous sensors distributed on the pipeline in a first preset manner. The heterogeneous sensors are configured as at least two of strain gauges, optical fiber sensors and vibration sensors. The sensor acquisition module is used to collect first sensing information; the data processing module is used to receive and process the first sensing information and extract characteristic safety parameters, and the characteristic safety parameters include stress concentration factor, strain rate, temperature gradient and vibration frequency; the wireless communication module is configured to use a multi-hop network communication mode to transmit the first sensing information and / or characteristic safety parameters to the server. The energy collection module is arranged on the surface of the pipeline, and the energy collection module is electrically connected to the sensor collection module. The energy collection module is used to collect energy from the surface of the pipeline and convert it into electrical energy to be transmitted to the heterogeneous sensor. The edge computing module is used to process the characteristic safety parameters to obtain the first processing information, and transmit the first processing information to the server. The first processing information is the operation information of the pipeline. The fault self-diagnosis module is used to detect the abnormal state, and the abnormal state is configured as any one of the collection abnormality, communication abnormality and power supply abnormality. The fault self-diagnosis module is used to realize the isolation of fault location and abnormal device through cross-validation and link bit error rate analysis. The server is used to receive the first sensing information and / or the first processing information and / or the characteristic safety parameters and continuously monitor the working state of the pipeline.

[0029] In this embodiment, the heterogeneous sensors of the sensor acquisition module are understood as sensors with various different sensing principles, including optical sensors, infrared sensors, acoustic sensors, electromagnetic sensors, mechanical sensors, etc. The sensors are packaged with high-temperature resistant ceramics and corrosion-resistant alloy structures to withstand high temperatures on the pipeline surface and steam corrosion environments. The first preset method refers to the layout of sensor nodes in a combination of annular arrays and axial gradients at elbows, welds and support parts according to the distribution characteristics of the pipeline stress concentration area to ensure key area monitoring coverage. Heterogeneous sensors are set on the surface of the equipment, and cross-validation is performed by using different types of sensors to avoid the limitations of a single type of sensor. The data processing module is used to receive and process the first sensing information, eliminate environmental interference, and accurately extract characteristic parameters such as stress concentration coefficients. The wireless communication module uses wireless communication technology for data transmission to reduce wiring difficulty and cost. The multi-hop network communication mode refers to taking each sensor as a node, autonomously selecting adjacent nodes as relays based on a dynamic routing protocol, forming a self-organizing mesh topology, and automatically switching to a backup path to maintain the communication link when a single node fails. Multi-hop communication technology is used to ensure that data can be transmitted to the central node through multiple paths to avoid single-point communication failures. The specific content is described below. The energy collection module can convert other types of energy in the pipeline working environment into electrical energy for temporary storage, and serve as a backup power supply to ensure the normal power supply of heterogeneous sensors, ensure that when the main power supply fails, the backup power supply can temporarily take over, and synchronously send power failure information to the server to avoid heterogeneous sensors from missing information due to power supply abnormalities, thereby reducing the accident rate. The edge computing module performs preliminary data processing and analysis on the edge device to reduce the amount of data transmission. The fault self-diagnosis module verifies the collection consistency through cross-comparison of heterogeneous sensor data, combines the communication link bit error rate threshold judgment and power supply deviation detection, and triggers the isolation of abnormal devices, which can significantly improve the maintainability and reliability of the system and reduce the need for manual intervention. The specific content is described below.

[0030] The stress-strain state monitoring system for high-temperature steam pipelines based on characteristic safety parameters provided in this embodiment realizes closed-loop monitoring of the entire process from data acquisition to state assessment through a multi-module collaborative working mechanism. First, based on the distribution characteristics of the pipeline stress concentration area, the system adopts a heterogeneous sensor layout method of a ring array and an axial gradient combination in the elbow, weld and support parts, and synchronously collects multi-dimensional physical quantity data through strain gauges, optical fiber sensors and vibration sensors with high-temperature ceramic packaging and corrosion-resistant alloy structures. Through the heterogeneous sensor layout and cross-validation mechanism, the three-dimensional strain field and vibration characteristics of the key areas of the pipeline are effectively covered. Combined with the high-temperature resistant packaging design and corrosion-resistant structure, the long-term stability of the sensor in extreme environments is ensured, and the reliability of characteristic parameter extraction is significantly improved. The collected original signal (i.e., the first sensing information) is extracted through the data processing module to extract characteristic safety parameters such as stress concentration coefficient, strain rate, temperature gradient and vibration frequency. The processed data is transmitted to the edge computing module through a multi-hop network, where data processing and standardization are performed locally to generate pipeline operation information that can be directly used for status assessment. Finally, continuous monitoring and abnormal warning are achieved through the server. Compared with traditional wired solutions, it not only reduces the complexity of wiring, but also enhances the adaptability to complex industrial environments. The fault self-diagnosis module achieves rapid positioning and isolation of abnormal devices through heterogeneous sensor data mutual verification, link bit error rate threshold judgment and power supply deviation detection. Combined with the deep learning analysis model on the server, it can identify pipeline creep damage trends in advance, provide technical support for preventive maintenance, and provide reliable technical means to ensure the safe operation of industrial pipelines.

[0031] In some embodiments, the fault self-diagnosis module is used to implement fault location and isolation of abnormal devices through cross-validation and link bit error rate analysis, including: Cross-validate the plurality of first sensing information to obtain a plurality of first stress calculation values, synchronously obtain the first stress actual value associated with the first sensing information corresponding to each first stress calculation value, and judge whether the deviation value between the first stress calculation value and the first stress actual value is within the range of a first preset threshold value, if not, it indicates that the heterogeneous sensor corresponding to the first stress actual value is in acquisition abnormality; and, monitoring the communication link status of the wireless communication module and calculating the link bit error rate, and determining whether the link bit error rate is within a second preset threshold, if not, indicating that the wireless communication module is in a communication abnormality; and, monitoring the power access value of each heterogeneous sensor, and obtaining the calibrated power value of the heterogeneous sensor; When the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, a deviation between the power access value and the calibrated power value is calculated and recorded as a first deviation value; Determine whether the first deviation value is within a range of a third preset threshold value, and if not, it indicates that the heterogeneous sensor corresponding to the power access value is in power supply abnormality; If the abnormal device is a heterogeneous sensor, the heterogeneous sensor is fault-isolated and the backup acquisition mode associated with the heterogeneous sensor is enabled; If the abnormal device is a wireless communication module, switch to a backup communication link, or adjust the backup communication mode of the wireless communication module.

[0032] In this embodiment, cross-verifying the plurality of first sensing information includes: Acquire multiple pieces of first sensor information, divide the multiple pieces of first sensor information into a first verification group and a first operation group according to a preset verification mode, record the first sensor information of the first verification group as first verification information, and record the first sensor information of the first operation group as first operation information; Performing data fusion on the first operation information to obtain a first stress calculation value, and converting the first verification information to obtain a first stress actual value; Determine whether a deviation between a calculated value of the first stress and an actual value of the first stress is within a range of a first preset threshold; If not, it means that the heterogeneous sensor corresponding to the first stress actual value is in acquisition abnormality; If so, it means that the heterogeneous sensor corresponding to the first stress actual value operates normally.

[0033] The preset verification mode is a dynamic rotation mechanism. Preferably, 30% of the first sensing information of the sensors is randomly selected as the first verification group each time the verification is performed, and the remaining 70% is selected as the first operation group. The rotation cycle is synchronized with the data acquisition cycle. Optionally, data fusion is achieved by weighted averaging, and weight coefficients (such as strain gauge weight 0.6, optical fiber sensor weight 0.4) are assigned to heterogeneous sensor data in the same monitoring area in the operation group, and finally the first stress calculation value is generated by fusion. The actual value of the first stress is directly converted from the sensor data in the first verification group (i.e., the first verification information) through the calibration formula. The calibration formula is the strain-voltage linear relationship model established when the sensor leaves the factory. The first preset threshold is set according to engineering experience. When the first preset threshold is exceeded, the corresponding heterogeneous sensor acquisition is judged to be abnormal.

[0034] The link bit error rate is the ratio of the number of error bits to the total number of transmitted bits during the communication process. For communication link anomaly detection, the second preset threshold is set based on the communication protocol standard. The fault self-diagnosis module continuously counts the bit error rate of the wireless communication module, and triggers a communication anomaly alarm when the average bit error rate exceeds the threshold in three consecutive communication cycles.

[0035] The power access value and calibrated power value of the heterogeneous sensor are used to determine whether there is a power supply abnormality. Specifically, the third preset threshold is defined as a ±10% deviation range of the calibrated power value for power supply abnormality judgment. The calibrated power value is determined by the output voltage of the energy collection module under rated conditions. When it is monitored that the power access value of a heterogeneous sensor is lower than the calibrated power value by 10% for 5 consecutive minutes, it is determined to be a power supply abnormality. When the heterogeneous sensor is determined to have a power supply abnormality, the fault self-diagnosis module performs the following steps: Starting a backup power supply, which is a pre-configured redundant energy harvesting module or energy storage device; If the backup power supply is not available, adjust the working mode of the heterogeneous sensor, including reducing the sampling frequency or entering a low power mode; Record power supply abnormalities and transmit energy shortage signals to the edge computing module and the server.

[0036] In power supply abnormality processing, preferably, the backup power supply uses a supercapacitor energy storage device, and its capacity is designed to maintain low-power operation of the abnormal node for 12 hours. If the backup power supply is unavailable, the edge computing module sends instructions to the adjacent nodes to reduce the sampling frequency of the abnormal node from 1Hz to 0.2Hz.

[0037] For each heterogeneous sensor, there is a corresponding backup acquisition mode. The backup acquisition mode is implemented by activating multiple adjacent redundant heterogeneous sensors around the target location. When an abnormality occurs in a heterogeneous sensor, multiple heterogeneous sensors are divided around the heterogeneous sensor to detect the information of the location together and increase the acquisition frequency. The specific content is described below.

[0038] The backup communication link can be understood as a separate communication hardware configuration. Starting the backup communication link means selecting another communication hardware for communication. For example, the backup communication link switches to the LoRa communication module in the 433MHz frequency band, forming heterogeneous redundancy with the 2.4GHz ZigBee module of the main communication link. The backup communication mode refers to the backup software communication mode under the current communication hardware configuration state, that is, another communication method is selected for communication without replacing the communication hardware. All state change records generated by the exception handling process are generated through the server to generate an exception log, and are automatically synchronized to the central database after the communication is restored for subsequent reference and call. It should be noted that all abnormal states are reported to the server immediately after the judgment, and the backup mode is only temporarily enabled during the duration of the abnormality, and the original working mode is automatically restored after the fault is eliminated.

[0039] The fault self-diagnosis method provided in this embodiment significantly improves the reliability of the high-temperature steam pipeline monitoring system through multi-dimensional anomaly detection and dynamic fault tolerance mechanism. Based on the dynamic rotation mechanism, the heterogeneous sensors are divided into the first verification group and the first operation group. The first stress calculation value is generated by fusing the operation group data through the weighted average method, and compared with the first verification group to achieve accurate identification of sensor acquisition anomalies; at the same time, the communication link bit error rate is monitored, and the instantaneous interference is eliminated in combination with the over-limit judgment condition lasting 5 minutes. For heterogeneous sensor anomalies, a backup acquisition mode is used, and for wireless communication module anomalies, a backup communication link or backup communication mode is used to achieve fault isolation and function replacement. The abnormal status is reported to the server in real time and a log is generated. After the fault is repaired, the initial working mode is automatically restored. Through the dynamic rotation verification mechanism and heterogeneous sensor data fusion, the integrity and consistency of key area monitoring data are ensured to avoid data loss caused by the failure of a single sensor; the second preset threshold and continuous judgment cycle can accurately identify communication link anomalies, and the switching of the main and standby communication modules can ensure the continuity of data transmission; the power supply deviation detection mechanism based on the calibrated electric energy value, combined with the supercapacitor backup power supply and sampling frequency adaptive adjustment, maintains the basic monitoring capability of abnormal nodes; the collaborative collection mode of adjacent redundant nodes compensates for abnormal area data through spatial distribution to ensure that there are no blind spots in monitoring coverage. All backup mechanisms serve as temporary transition solutions to reduce resource usage while maintaining system functions. The real-time synchronization and automatic recovery mechanism of abnormal logs provide traceability support for operation and maintenance, and ultimately achieve high-robustness continuous monitoring of the system in extreme environments.

[0040] See also Figure 1 In some embodiments, the alternate acquisition mode is configured as: S101, obtaining location information of a heterogeneous sensor in an abnormal state, recording it as abnormal location information, and recording the heterogeneous sensor in the abnormal state as an abnormal sensor; S102, dividing a spare collection area with the abnormal position information as the center and a preset length as the radius, and recording other heterogeneous sensors in the spare collection area except the abnormal sensor as spare sensors; and, obtaining a predetermined collection frequency of the abnormal sensor, recorded as a first collection frequency; S103, generating a second acquisition frequency according to the first acquisition frequency; S104, controlling the standby sensor to collect standby sensor information according to the second collection frequency; S105, fusing multiple backup sensor information to obtain a second calculated stress value; S106. Using the second calculated stress value as the stress value corresponding to the abnormal position information.

[0041] In step S101 and step S102, the preset length is determined according to the attenuation characteristics of the pipeline stress field, and is usually set to 3 times the diameter of the pipe section where the abnormal position is located (for example, DN300 pipeline corresponds to 0.9 meters). This range can cover more than 90% of the impact range of the stress concentration area. When dividing the backup acquisition area, the adjacent nodes in the same annular array as the abnormal sensor are preferentially selected to ensure the continuity of the spatial distribution.

[0042] In step S103, the second acquisition frequency is generated using the linear compensation principle, increasing the original first acquisition frequency (such as 1 time / hour) to 1.5 times (i.e. 1.5 times / hour), and requiring the acquisition timestamp of the backup sensor group to be synchronized with the original sensor. , then the second acquisition frequency is set to ,The specific coefficient is dynamically adjusted according to the pipeline conditions and is sent to the backup sensor through the edge computing module.

[0043] In step S105, data fusion can use the inverse distance weighted spatial interpolation method (IDW) to calculate the contribution value of the backup sensing information collected by the backup sensor to the abnormal position. The weight coefficient of the backup sensor is ,in is the straight-line distance between the sensor and the abnormal position, To prevent division by zero, a small constant (usually The second calculation of stress value is through the formula get, is the measurement value of each backup sensor. If the backup sensor types include strain gauges and optical fiber sensors, the data of the same type of sensors are first averaged within the group and then participate in the cross-type fusion calculation.

[0044] Furthermore, the final determination of the stress value at the abnormal location needs to be combined with historical data verification: when the deviation between the second calculated stress value of the backup sensor group and the recent (e.g., within 24 hours) stress mean value of the location stored in the edge computing module exceeds ±3%, the manual review process on the server is triggered. During the operation of the backup acquisition mode, the original data of the abnormal sensor is still retained at a sampling rate of 10% for data consistency comparison after fault repair. The spatiotemporal labels of all backup sensor information are strictly aligned with the original data stream to ensure the integrity of the server-side time series analysis.

[0045] It should be noted that the number of spare sensors needs to be And it contains at least two sensor types, otherwise it will automatically upgrade to the cross-regional collaborative collection mode; the increase in the second collection frequency must not cause the total energy consumption of the backup sensor group to exceed 80% of the energy collection module's supply capacity; the data fusion result submits a confidence assessment report to the server once an hour, and when the confidence is lower than 85%, the backup communication link retransmission mechanism is activated.

[0046] The backup acquisition mode provided in this embodiment realizes the continuity and reliability improvement of pipeline stress monitoring through a systematic abnormal data processing mechanism. The preset length parameters set based on the attenuation characteristics of the pipeline stress field ensure that the backup acquisition area can cover more than 90% of the influence range of the abnormal position on the stress concentration area. At the same time, by giving priority to the spatial distribution strategy of adjacent nodes of the same ring array, the spatial continuity of the sensor network is maintained, avoiding the generation of monitoring blind spots. The linear compensation principle is adopted to dynamically adjust the acquisition frequency, which not only ensures the temporal consistency of data acquisition density and historical monitoring data, but also adapts to different pipeline working conditions through the dynamic adjustment capability of the edge computing module, effectively balancing the monitoring accuracy and equipment energy consumption. Through the multi-source data fusion mechanism of the inverse distance weighted spatial interpolation method, the geometric relationship between the backup sensor and the abnormal position is fully considered, and the stress value is reconstructed with the inverse square of the distance as the weight coefficient, which significantly improves the spatial correlation accuracy of the stress value estimation of the abnormal position. At the same time, the hierarchical fusion strategy set for the differences in heterogeneous sensor types effectively eliminates the system errors caused by different sensing principles through the collaborative processing of intra-group average and cross-type calculation. In addition, the acquisition timestamp synchronization mechanism and the mathematical processing to prevent zero-based tiny constants further ensure the timing alignment and calculation stability of the data fusion process. This mode realizes the dynamic replacement and compensation of abnormal sensor functions without adding new hardware equipment through the technical collaboration of spatial coverage optimization, acquisition timing enhancement, and data fusion algorithm, providing multiple guarantees for the robustness of the pipeline stress monitoring system.

[0047] In some embodiments, if the abnormal device is a wireless communication module, switching to a backup communication link, or adjusting the backup communication mode of the wireless communication module includes: The backup communication link is a pre-configured redundant communication path; If the backup communication link is unavailable, the backup communication mode of the wireless communication module is enabled, and the backup communication mode includes reducing the communication rate and switching the communication protocol; And, record abnormal communication events and transmit them to the edge computing module and the server.

[0048] In this embodiment, the redundant communication path is a pre-deployed independent communication channel, whose physical link has no overlap with the main communication path. Path redundancy can be achieved through multi-hop relay nodes or different frequency bands, and basic communication capabilities can be maintained when the main link is interrupted.

[0049] Reducing the communication rate can be achieved by adjusting the modulation method or extending the transmission interval, thereby reducing the channel load and improving the signal's anti-interference ability, so that the communication module can still maintain basic data transmission functions in a weak signal environment; switching communication protocols means switching to a communication standard that is more suitable for current channel conditions under the same hardware support, such as switching from the long-distance, low-power (LoRa) protocol to the narrowband Internet of Things (NB-IoT) protocol, or from the TCP protocol to the UDP protocol, and matching different service quality requirements through protocol stack reconstruction. The former focuses on reducing transmission delays, and the latter focuses on ensuring the arrival rate of data packets.

[0050] Communication anomaly events are transmitted to the edge computing module and the server to achieve two-level collaborative processing. Specifically, the edge computing module optimizes the local strategy in real time based on event triggering, including dynamically adjusting the channel scanning cycle or the number of retransmissions; the server establishes a communication link health assessment model through historical anomaly data aggregation and analysis to provide a decision-making basis for subsequent maintenance. The record of communication anomaly events includes the anomaly type, occurrence time, switching operation log, and communication quality indicators after switching, forming a complete chain of evidence for anomaly handling, supporting fault tracing and reliability verification. If the backup communication link and backup communication mode cannot restore the communication function, the hierarchical alarm mechanism is triggered, and local caching and delayed upload are performed through the edge computing module first, and data replenishment is performed after communication is restored to ensure the continuity of monitoring data.

[0051] This mechanism uses a three-layer fault-tolerant design of path redundancy, mode degradation, and event coordination to prioritize the accessibility of key data when communication is abnormal. At the same time, through dynamic adaptation of protocols and rates, it maximizes the use of existing hardware resources to maintain basic services and avoid overall system failure due to a single module failure.

[0052] In some embodiments, the wireless communication module includes multiple sensor nodes, which are distributed on the pipeline in a second preset manner to form a multi-hop network. Each sensor node is configured to have data receiving and relay forwarding functions. Each sensor node establishes a communication connection with at least one neighbor node, and the neighbor nodes are configured as other sensor nodes arranged adjacent to the sensor node.

[0053] In this embodiment, the second preset method is a node spatial distribution rule designed according to the geometric characteristics of the pipeline and the communication coverage requirements. The sensor nodes are evenly deployed along the axial and circumferential directions of the pipeline through a ring array or a spiral arrangement. The spacing between neighbor nodes is set according to the effective transmission distance of the wireless signal, which is usually 1.5-2 times the diameter of the pipeline to ensure that the signal strength between adjacent nodes is higher than the communication threshold.

[0054] The construction of a multi-hop network relies on the relay forwarding function between nodes. While receiving its own collected data, each sensor node can decode, verify and enhance the signal of the data transmitted by the upstream neighbor node, and then forward it to the next-hop neighbor node through time division multiplexing or frequency division multiplexing mechanism, and finally converge to the edge computing module.

[0055] Neighbor nodes are defined as other nodes that are directly adjacent to the current sensor node in physical space. Their connection relationships are automatically identified through wireless signal strength thresholds or statically bound through a preset topology table.

[0056] This embodiment expands the network coverage under limited power consumption constraints through the spatial layout optimization and multi-hop cooperation mechanism of the second preset method, and at the same time uses the redundant links between neighboring nodes to improve the reliability of data transmission. It is particularly suitable for compensating for signal attenuation and occlusion problems in long-distance pipeline monitoring scenarios, and cooperates with the abnormal sensor replacement mechanism in the aforementioned backup acquisition mode to jointly enhance the fault tolerance capability of the monitoring system.

[0057] See also Figure 2 In some embodiments, the multi-hop network communication mode is configured to include the following steps: S201, when a sensor node needs to send data, select the nearest neighbor node as the next hop node according to the preset routing protocol; S202, after receiving the data, the neighbor node forwards the data to the next relay node according to the routing protocol until the data reaches the edge computing module, and the relay node is the neighbor node adjacent to the neighbor node; S203, the edge computing module receives data from multiple sensor nodes, and aggregates and processes the data; S204, monitor the communication status of each sensor node in the multi-hop network in real time. If a fault is detected, the routing protocol automatically adjusts the network topology and selects an alternative path for data transmission.

[0058] In step S201, the preset routing protocol can be a dynamic source routing based on a distance vector (such as AODV) or a gradient routing protocol (such as RPL), and the basis for selecting the next-hop neighbor node includes but is not limited to the remaining power of the neighbor node, the signal receiving strength (RSSI) or the minimum number of hops to the edge computing module, where the nearest neighbor node can be understood as the node with the least number of hops to the edge computing module among the nodes that meet the communication link quality threshold.

[0059] In step S202, the relay node can be understood as the next-level forwarding node in the adjacent node set of the current neighbor node that meets the routing protocol's preferred conditions, such as giving priority to nodes with smaller level numbers in gradient routing. The data forwarding process follows a hop-by-hop confirmation mechanism, that is, after each hop forwarding, a confirmation signal from the next node must be received. If no confirmation is received within a timeout, retransmission or path switching is triggered.

[0060] In step S203, the edge computing module receives data from multiple sensor nodes and aggregates and processes them, including deduplication verification of multi-source data, timestamp alignment, and spatial interpolation fusion of stress values. For example, the data of multiple sensor nodes in the same circular array are superimposed and calculated according to preset weights.

[0061] In step S204, when the sensor node fails to respond to the heartbeat detection for a preset number of consecutive times or the cyclic redundancy check (CRC) error rate of the data packet exceeds a threshold (such as 10%), it indicates that a communication failure has occurred. The network topology is a logical structure composed of all nodes and their communication connection relationships in a multi-hop network. The backup path refers to an alternative transmission link that bypasses the faulty node, and its construction depends on the list of candidate neighbor nodes maintained by the routing protocol. For example, when a sensor node fails, its upstream neighbor node forwards the data to the suboptimal neighbor node according to the routing table, and notifies the entire network of topology changes through flooding update messages to ensure that subsequent data is transmitted along the new path.

[0062] The multi-hop network communication mode provided in this embodiment significantly improves the communication reliability of the pipeline monitoring system through dynamic path optimization and fault tolerance mechanism. Based on the path selection strategy of the preset routing protocol, it comprehensively evaluates the remaining power of neighboring nodes, signal reception strength and number of path hops to ensure that data forwarding is always carried out in the direction of optimal energy efficiency and stable link, avoiding communication interruption caused by excessive load or signal attenuation of a single node. The hop-by-hop confirmation mechanism is combined with the hierarchical optimization rules of the relay nodes. In the gradient routing, the forwarding priority is dynamically adjusted by the hierarchical number, and the timeout retransmission and path switching mechanism are combined to effectively reduce the data transmission packet loss rate. The edge computing module performs deduplication verification and timestamp alignment processing on multi-source data to eliminate data redundancy or timing disorder that may be caused by multi-hop transmission, and the spatial interpolation fusion of stress values ​​further ensures the spatial continuity of the monitoring data. The fault perception mechanism uses the dual threshold judgment of the number of heartbeat detection response failures and the cyclic redundancy check error rate to accurately identify abnormal communication nodes, trigger the routing protocol to automatically reconstruct the network topology, use the candidate neighbor node list to quickly establish an alternative path to bypass the faulty node, and achieve full network topology synchronization through flooding updates to ensure that the data transmission link can still maintain end-to-end connectivity in the case of node failure. This mode builds a low-power, highly robust closed-loop communication architecture through the synergy of dynamic routing optimization, data integrity assurance, and network self-healing capabilities, providing a stable multi-hop transmission foundation for long-distance pipeline monitoring.

[0063] See also Figure 3 In some embodiments, the energy harvesting module includes a vibration energy harvester, a wind speed energy harvester, a power storage unit, and a power management circuit. The energy harvesting module is used to collect energy from the pipeline surface and convert it into electrical energy to be transmitted to the heterogeneous sensor. S301. Setting a vibration energy collector and a wind speed energy collector at key positions of the pipeline, including the pipeline elbow area, the weld area, the gas flow port and the high stress concentration area. The vibration energy collector is used to convert the mechanical vibration energy on the pipeline surface into electrical energy, and the wind speed energy collector is used to convert the air flow velocity around the pipeline into electrical energy. S302, storing the electric energy generated by the vibration energy harvester and the wind speed energy harvester in a power storage unit; S303, the power management circuit monitors the reserve power value of the power reserve unit and the power access value of the heterogeneous sensor in real time; S304, when the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, calculating a deviation between the power access value and the calibrated power value, and recording it as a second deviation value; S305, determining whether the reserve electric energy value is greater than the second deviation value; S306, if yes, connecting the power reserve unit and the heterogeneous sensor; S307: If not, do not connect.

[0064] In step S301, vibration energy harvesters are deployed at high stress concentration locations such as pipeline elbow areas and weld areas, and the periodic deformation caused by the mechanical vibration of the pipeline is used to trigger piezoelectric materials or electromagnetic induction devices to generate electricity. Wind speed energy harvesters are set in areas with significant airflow disturbances such as gas flow ports, and the kinetic energy of the airflow is converted into electrical energy through micro turbines or piezoelectric cantilever beams, so that the energy collection density is positively correlated with the pipeline working condition intensity, thereby improving the energy capture efficiency.

[0065] In step S302, the power reserve unit may be a high cycle life energy storage device, such as a supercapacitor or a lithium thionyl chloride battery pack, which is used to temporarily store and smooth the output of the intermittent electrical energy generated by the vibration energy harvester and the wind speed energy harvester to avoid power interruption due to environmental energy fluctuations.

[0066] In step S303, the power management circuit is composed of a voltage monitoring chip, a DC-DC conversion module and a microcontroller. The terminal voltage and output current of the power reserve unit are periodically sampled through an analog-to-digital converter (ADC), and the real-time reserve power value is calculated in combination with a preset reserve power-voltage mapping relationship. At the same time, the voltage and current product of the power supply port of the heterogeneous sensor is monitored, and its power access value is dynamically calculated and compared with the calibrated power value.

[0067] In step S305 to step S307, when the available energy of the power reserve unit is sufficient to cover the second deviation value (i.e., the current energy consumption gap of the sensor), the power management circuit closes the relay to replenish power to the sensor; if the reserve power is lower than the required threshold, the disconnected state is maintained to prevent the energy storage device from being damaged by over-discharge. This mechanism not only ensures the minimum working energy consumption of the sensor, but also gives priority to maintaining the basic energy storage level of the power reserve unit to avoid complete system downtime due to intermittent environmental energy.

[0068] The energy collection module provided in this embodiment realizes the self-sustaining power supply of heterogeneous sensors through environmental energy capture and intelligent power distribution mechanism. Vibration energy collectors are deployed in high stress concentration areas such as pipeline elbows and welds, and the mechanical vibration of the pipeline is used to trigger piezoelectric materials or electromagnetic induction devices to generate electricity; wind speed energy collectors are set in areas with significant airflow such as gas flow ports, and the kinetic energy of airflow is converted into electrical energy through micro turbines or piezoelectric cantilever beams, so that the energy collection density matches the pipeline working condition intensity and maximizes the environmental energy utilization rate. The power reserve unit uses supercapacitors or lithium thionyl chloride battery packs to store intermittent electrical energy, and realizes energy temporary storage and smooth output through high cycle life characteristics to avoid power interruption caused by vibration or wind speed fluctuations. The power management circuit monitors the reserve power value and the sensor power access value in real time through the voltage monitoring chip and the microcontroller. When the sensor access value is lower than the calibration value, the second deviation value is calculated and the power supply decision is triggered: if the reserve value is greater than the deviation value, the relay is closed to supplement the power; if it is insufficient, it is maintained disconnected to prevent the power reserve unit from being over-discharged and damaged. This mechanism prioritizes maintaining the basic level of energy storage through dynamic threshold control, while ensuring the minimum energy consumption demand of the sensor, avoiding the system from completely shutting down due to energy discontinuity. This embodiment converts the pipeline's own vibration and surrounding airflow into a stable power supply through the coordinated design of directional acquisition at key locations, multi-modal energy storage, and dynamic power distribution control, significantly reducing dependence on external batteries. It is especially suitable for long-term monitoring scenarios in unmanned or harsh environments, and forms an energy-data transmission collaborative optimization system with the aforementioned multi-hop network communication mode, jointly extending the overall life cycle of the monitoring system.

[0069] In some embodiments, the data processing module is used to receive and process the first sensor information and extract the characteristic safety parameter, including: Generate a data processing task according to the first sensor information, decompose the data processing task into multiple processing subtasks, and assign the multiple processing subtasks to a multi-core CPU for parallel calculation; Multi-core CPU parallel computing includes the following steps: Using wavelet transform or Fourier transform to compress and reduce noise of the first sensor information, so as to reduce the data volume of the first sensor information; Using a Kalman filter algorithm to eliminate sensor noise and environmental interference noise in the first sensor information to obtain second sensor information; The second sensor information is fused by using a data fusion algorithm to obtain characteristic safety parameters; Send characteristic security parameters to the edge computing module.

[0070] In this embodiment, the data processing task is decomposed into multiple processing subtasks and assigned to multi-core CPUs for parallel computing, which can achieve load balancing of computing resources and improve processing efficiency, shorten the overall processing delay, and is suitable for the real-time requirements in high sampling rate pipeline monitoring scenarios.

[0071] Wavelet transform or Fourier transform is used to compress and reduce noise of the first sensing information, and high-frequency noise components and redundant data are eliminated through time-frequency domain conversion, thereby reducing the computational load and storage pressure of subsequent processing.

[0072] The Kalman filter algorithm dynamically estimates the true measurement value of the sensor and suppresses noise interference through the state space model and recursive prediction-correction mechanism. It can distinguish between the inherent noise of the sensor (such as thermal noise and quantization error) and the environmental interference noise (such as electromagnetic radiation and mechanical vibration crosstalk), and adaptively adjust the filtering strength through the covariance matrix to improve the signal-to-noise ratio while retaining the dynamic characteristics of the signal.

[0073] The data fusion algorithm fuses the second sensor information through weighted aggregation of multi-source heterogeneous data, and assigns different weight coefficients according to the sensor type, spatial position and historical reliability. For example, for the data of multiple vibration sensors in the same annular array, the local stress distribution map is first generated by spatial interpolation, and then linearly superimposed with the thermal expansion compensation value of the temperature sensor, and finally the normalized characteristic safety parameter is output. If the fusion of optical fiber sensor and strain gauge data is involved, principal component analysis (PCA) is used to extract common feature vectors to eliminate the dimensional differences and coupling interference of cross-type sensors.

[0074] This embodiment achieves accurate extraction of high-dimensional sensor information into key safety indicators under limited computing resources through progressive processing of task parallelization, signal purification, and multi-source fusion, and provides low-noise, compact, and physically meaningful input data for the decision-making analysis of the edge computing module, thereby forming a computing-energy consumption collaborative optimization closed loop with the sustainable power supply capability of the aforementioned energy harvesting module.

[0075] In some embodiments, the edge computing module is used to process the characteristic security parameter to obtain the first processing information, including: The characteristic safety parameters are processed by incremental calculation, and the data processing includes the following steps: Performing Huffman coding on the characteristic security parameter, and recording the processed characteristic security parameter as the first packaged data; and, constructing a pipeline operation status feature vector based on the feature safety parameter; Performing status evaluation on the operating status feature vector to obtain evaluation results, the evaluation results including warning status, maintenance status, overhaul status and normal status; Performing Huffman coding on the evaluation result, and recording the processed evaluation result as second packaged data; Integrate the second packaged data with the first packaged data to form first processed information, and transmit the first processed information to the server; And, store the characteristic safety parameters and evaluation results in a local database.

[0076] In this embodiment, the incremental calculation method refers to only local processing of newly added or updated feature security parameters, rather than recalculating the entire data. For example, encoding and vector construction operations are only performed on the feature security parameters of the latest acquisition cycle each time, thereby reducing computing resource consumption and improving real-time response speed.

[0077] Huffman coding is a variable-length lossless compression algorithm based on the frequency of character occurrence. It converts characteristic safety parameters into compact first-package data by assigning short code elements to high-frequency eigenvalues ​​and long code elements to low-frequency values. For example, if the axial stress gradient value has a high repetition rate in historical data, its corresponding code length is significantly shorter than the sparsely occurring abnormal value, thereby reducing data volume.

[0078] Preferably, the operating state characteristic vector includes the pipeline axial stress gradient, annular strain fluctuation rate, temperature-stress coupling coefficient, steam pressure change entropy value and vibration spectrum distortion. The construction of the operating state characteristic vector is realized by extracting multidimensional characteristic safety parameters, including: the pipeline axial stress gradient is calculated by dividing the stress difference between adjacent monitoring nodes by the axial spacing, the annular strain fluctuation rate is determined by statistically analyzing the standard deviation of the strain values ​​of the same annular array nodes, the temperature-stress coupling coefficient uses linear regression to analyze the correlation coefficient of temperature and stress data, the steam pressure change entropy value quantifies the fluctuation complexity through the Shannon entropy of the pressure time series, and the vibration spectrum distortion is calculated based on the mean square error between the FFT spectrum and the reference spectrum. These parameters together constitute a multidimensional vector that describes the health status of the pipeline.

[0079] Preferably, the operating state feature vector can be evaluated through a multi-level state classification model, and the operating state feature vector can be mapped to a warning state, a maintenance state, an overhaul state or a normal state. The specific contents are described below.

[0080] Furthermore, the warning state corresponds to a single parameter exceeding the first-level threshold but not reaching a dangerous level, the maintenance state corresponds to multiple parameters continuously exceeding the limit and the trend is deteriorating, and the inspection state is triggered by sudden parameter anomalies or combination pattern matching historical fault characteristics.

[0081] The evaluation results are Huffman encoded to generate the second packaged data, which is integrated with the first packaged data through message encapsulation into the first processing information. Its structure contains the compressed original features and diagnostic conclusions, which not only meets the low-bandwidth transmission requirements, but also retains the basic data required for in-depth analysis on the server side. The local database synchronously stores the uncompressed feature security parameters and evaluation results to form a complete historical state record chain, supporting offline backtracking and model optimization. This process optimizes edge computing and communication efficiency while ensuring data validity through the collaborative design of incremental processing and hierarchical compression.

[0082] In some embodiments, the operating state feature vector is evaluated to obtain an evaluation result including: Inputting the operating state feature vector into the multi-level state classification model, the operating state feature vector includes the pipeline axial stress gradient, the hoop strain fluctuation rate, the temperature-stress coupling coefficient, the steam pressure change entropy value and the vibration spectrum distortion degree; The multi-level state classification model performs the following classification judgments: First-level judgment: When the temperature-stress coupling coefficient exceeds the preset dynamic threshold and the duration exceeds the range of the preset duration threshold, the warning state is triggered; Second level judgment: If the product of the axial stress gradient and the hoop strain fluctuation rate exceeds the material yield critical value, the maintenance state is triggered; The third level judgment: when the vibration spectrum distortion degree and the vibration spectrum distortion degree under the preset fault mode are placed within the same cosine similarity threshold, the maintenance state is triggered; Fourth level judgment: If the operating state feature vector is within the range of the preset operating threshold, the normal state is triggered; Establish a decision fusion mechanism based on fuzzy logic to perform weighted fusion on the judgment results output by the multi-level state classification model; A sliding time window algorithm is used to perform trend analysis on the evaluation results of a preset number of consecutive sampling cycles, and the evaluation result output is triggered when the same operating state appears for a preset number of consecutive times; And, the evaluation results are matched with historical failure cases in the local database for similarity, and the credibility level of the evaluation results is corrected.

[0083] In this embodiment, the multi-level state classification model refers to a hierarchical judgment logic constructed based on the physical failure mechanism. The first to third levels correspond to thermal-mechanical coupling anomalies, composite stress exceeding limits, and vibration failure mode identification, respectively, and the fourth level is the normal state baseline judgment.

[0084] The preset dynamic threshold is determined based on the regression analysis of the thermal expansion coefficient of the pipeline material and the historical operation data. For example, the temperature-stress coupling coefficient threshold of the carbon steel pipeline is set to 0.85. Preferably, the preset time threshold is set to 10 minutes through the pipeline thermal inertia experiment to avoid false triggering of short-term fluctuations.

[0085] The product of the axial stress gradient and the hoop strain fluctuation rate represents the composite stress level. The material yield critical value is obtained through a standard tensile test. For example, the corresponding value for X80 pipeline steel is .

[0086] The vibration spectrum distortion refers to the root mean square error between the current spectrum and the benchmark healthy spectrum. When the vibration spectrum distortion and the vibration spectrum distortion under the preset fault mode (such as weld cracks and corrosion thinning) are within the same cosine similarity threshold, it indicates that the vibration characteristics are highly matched with the typical fault.

[0087] The preset operating threshold is set through design specifications and historical statistics, and includes the normal fluctuation range of each characteristic parameter. For example, the steam pressure change entropy threshold is [0.2, 1.5].

[0088] The decision fusion mechanism based on fuzzy logic quantifies the credibility of the judgment results at each level through the membership function. The whole process can be carried out through the following steps: first, define triangular or Gaussian membership functions for the warning state, maintenance state, overhaul state and normal state respectively, and quantify the judgment results of the multi-level classification model into confidence values ​​of 0-1; secondly, set weights according to the state priority (such as the maintenance state has the highest weight), and perform weighted summation on the confidence of each state; finally, use the maximum membership principle or weighted average method to output the final evaluation result.

[0089] The sliding time window algorithm uses a queue of fixed length (such as 5 sampling cycles) to store continuous evaluation results. When the number of occurrences of the same state in the window exceeds the set ratio (such as 3 / 5), the output is triggered to avoid occasional abnormal interference. The similarity matching between the evaluation results and historical fault cases is achieved through the cosine similarity calculation of the feature vector. If the matching degree is higher than 0.85, the credibility level is increased by one level.

[0090] The pipeline operation status assessment method provided in this embodiment significantly improves the accuracy and reliability of abnormal identification through hierarchical diagnosis and multi-dimensional verification mechanism. The multi-level state classification model realizes accurate positioning of fault types through hierarchical judgment logic, in which the first-level judgment is based on the combination of the preset dynamic threshold and the preset time threshold of the temperature-stress coupling coefficient, effectively distinguishing short-term fluctuations from continuous thermal anomalies; the second-level judgment directly associates the critical characteristics of material yield through the composite stress index of the product of the axial stress gradient and the hoop strain fluctuation rate, ensuring the physical meaning of the maintenance status triggering; the third-level judgment realizes the feature identification of typical faults such as weld cracks by matching the vibration spectrum distortion with the cosine similarity threshold of the preset fault mode. The fuzzy logic decision fusion mechanism quantifies the state confidence by defining the triangle / Gaussian membership function, and combines the priority weight for weighted fusion to solve the conflict problem of multi-level judgment results and reduce the risk of misjudgment. In addition, the sliding time window algorithm filters occasional interference signals through continuous state frequency statistics to enhance the temporal continuity of the evaluation results; the historical fault case similarity matching dynamically corrects the credibility level of the current result by comparing the fault feature vector in the local database, and improves the historical interpretability of the diagnostic conclusion. This embodiment uses hierarchical criteria to lock the fault type, fuzzy fusion balance judgment conflicts, time window filtering false alarms, and historical case correction confidence to form a closed-loop evaluation system from parameter extraction to decision output. It not only ensures a rapid response to sudden anomalies, but also improves diagnostic accuracy through multi-dimensional verification, forming a complete state perception chain with the feature extraction of the aforementioned data processing module.

[0091] Different from the prior art, the above technical solution has the following beneficial effects: This technical solution provides a high-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters, and builds a full-dimensional intelligent monitoring system for the stress-strain state of high-temperature steam pipelines. Through the organic integration of heterogeneous sensor collaborative acquisition, multi-level data processing and autonomous fault-tolerant mechanism, the accuracy, reliability and continuous operation capability of the monitoring system are significantly improved. The system adopts a heterogeneous combination layout of strain gauges, optical fiber sensors and vibration sensors, combined with multi-core parallel processing and data fusion algorithms, to eliminate the monitoring blind spots of a single sensing mode, accurately extract multi-dimensional characteristic parameters such as stress concentration factor and strain rate, and realize comprehensive perception of pipeline stress-strain state. The adaptive multi-hop network communication mode cooperates with the dynamic routing protocol to effectively respond to local communication failures and maintain the continuity of monitoring data through node relay and path automatic switching mechanism while ensuring data transmission efficiency. The vibration and wind energy composite acquisition system breaks through the traditional power supply limitations, combines intelligent power management strategies to achieve equipment self-power supply, and provides stable energy guarantee for long-term monitoring. The fault self-diagnosis module uses cross-validation and link error analysis technology to accurately locate sensor anomalies, communication interruptions and power supply failures, and ensures the overall function of the system is complete under local failures through fault-tolerant strategies such as spare acquisition area reconstruction and redundant communication path switching. Incremental computing and Huffman coding technology are used on the edge side to optimize the data processing process. Combined with a multi-level state classification model and a fuzzy decision-making mechanism, real-time intelligent hierarchical assessment of the pipeline health status is achieved, forming a closed-loop monitoring system from data collection, transmission, processing to diagnostic decision-making, providing accurate and reliable technical support for the preventive maintenance of high-temperature steam pipelines.

[0092] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A high-temperature steam pipeline stress-strain state monitoring system based on characteristic safety parameters, characterized in that: include: a sensor acquisition module, comprising a plurality of heterogeneous sensors distributed on the pipeline in a first preset manner, wherein the heterogeneous sensors are configured as at least two of strain gauges, optical fiber sensors, and vibration sensors, and the sensor acquisition module is used to acquire first sensing information; A data processing module, used for receiving and processing the first sensing information and extracting characteristic safety parameters, wherein the characteristic safety parameters include stress concentration factor, strain rate, temperature gradient and vibration frequency; A wireless communication module, configured to use a multi-hop network communication mode to transmit the first sensing information and / or the characteristic security parameter to an edge computing module; An energy collection module is arranged on the surface of the pipeline, the energy collection module is electrically connected to the sensor collection module, and the energy collection module is used to collect energy from the surface of the pipeline and convert it into electrical energy to be transmitted to the heterogeneous sensor; an edge computing module, configured to perform data processing on the characteristic security parameter to obtain first processing information, and transmit the first processing information to a server, wherein the first processing information is operation information of the pipeline; A fault self-diagnosis module, used for detecting an abnormal state, wherein the abnormal state is configured as any one of an acquisition abnormality, a communication abnormality, and a power supply abnormality, and the fault self-diagnosis module is used for locating the fault and isolating the abnormal device through cross-validation and link bit error rate analysis; The service end is used to receive the first sensing information and / or the first processing information and / or the characteristic safety parameter and continuously monitor the working status of the pipeline.

2. The high-temperature steam pipeline stress-strain state monitoring system with characteristic safety parameters as claimed in claim 1 is characterized in that: The fault self-diagnosis module is used to realize fault location and isolation of abnormal devices through cross-validation and link bit error rate analysis, including: Cross-validate the plurality of first sensing information to obtain a plurality of first stress calculation values, synchronously obtain the first stress actual value associated with the first sensing information corresponding to each of the first stress calculation values, and determine whether a deviation between the first stress calculation value and the first stress actual value is within a range of a first preset threshold value, if not, indicating that the heterogeneous sensor corresponding to the first stress actual value is in acquisition abnormality; and, monitoring the communication link status of the wireless communication module and calculating the link bit error rate, and determining whether the link bit error rate is within a second preset threshold, if not, indicating that the wireless communication module is in a communication abnormality; and, monitoring the power access value of each of the heterogeneous sensors, and obtaining the calibrated power value of the heterogeneous sensors; When the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, calculating a deviation between the power access value and the calibrated power value, and recording the deviation as a first deviation value; Determine whether the first deviation value is within a range of a third preset threshold value, and if not, it indicates that the heterogeneous sensor corresponding to the power access value is in power supply abnormality; If the abnormal device is a heterogeneous sensor, isolating the fault of the heterogeneous sensor and enabling a backup acquisition mode associated with the heterogeneous sensor; If the abnormal device is a wireless communication module, switch to a backup communication link, or adjust the backup communication mode of the wireless communication module.

3. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 2 is characterized in that: The alternate acquisition mode is configured as: Acquire the position information of the heterogeneous sensor in an abnormal state, record it as abnormal position information, and record the heterogeneous sensor in the abnormal state as an abnormal sensor; Taking the abnormal position information as the center and a preset length as the radius, a spare collection area is divided, and other heterogeneous sensors in the spare collection area except the abnormal sensor are recorded as spare sensors; and obtaining a predetermined collection frequency of the abnormal sensor, recorded as a first collection frequency; generating a second acquisition frequency according to the first acquisition frequency; controlling the backup sensor to collect backup sensor information according to the second collection frequency; Performing data fusion on the plurality of the backup sensor information to obtain a second calculated stress value; The second calculated stress value is used as the stress value corresponding to the abnormal position information.

4. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 2 is characterized in that: If the abnormal device is a wireless communication module, switching to a backup communication link, or adjusting the backup communication mode of the wireless communication module includes: The backup communication link is a pre-configured redundant communication path; If the backup communication link is unavailable, enabling the backup communication mode of the wireless communication module, wherein the backup communication mode includes reducing the communication rate and switching the communication protocol; And, record abnormal communication events and transmit the abnormal communication events to the edge computing module and the server.

5. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 1 is characterized in that: The wireless communication module includes multiple sensor nodes, which are distributed on the pipeline in a second preset manner to form a multi-hop network. Each of the sensor nodes is configured to have data receiving and relay forwarding functions. Each of the sensor nodes establishes a communication connection with at least one neighbor node, and the neighbor nodes are configured to be other sensor nodes arranged adjacent to the sensor node.

6. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 5 is characterized in that: The multi-hop network communication mode is configured to include the following steps: When a sensor node needs to send data, it selects the nearest neighbor node as the next hop node according to the preset routing protocol; After receiving the data, the neighbor node forwards the data to the next relay node according to the routing protocol until the data reaches the edge computing module, and the relay node is the neighbor node adjacent to the neighbor node; The edge computing module receives data from multiple sensor nodes and aggregates and processes them; The communication status of each sensor node in the multi-hop network is monitored in real time. If a fault is detected, the routing protocol automatically adjusts the network topology and selects an alternate path for data transmission.

7. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 1 is characterized in that: The energy harvesting module includes a vibration energy harvester, a wind speed energy harvester, a power storage unit and a power management circuit. The energy harvesting module is used to collect energy from the surface of the pipeline and convert it into electrical energy to be transmitted to the heterogeneous sensor. A vibration energy collector and a wind speed energy collector are arranged at key positions of the pipeline, the key positions including the pipeline elbow area, the weld area, the gas flow port and the high stress concentration area, the vibration energy collector is used to convert the mechanical vibration energy of the pipeline surface into electrical energy, and the wind speed energy collector is used to convert the air flow velocity around the pipeline into electrical energy; storing the electric energy generated by the vibration energy harvester and the wind speed energy harvester in the power storage unit; The power management circuit monitors the reserve power value of the power reserve unit and the power access value of the heterogeneous sensor in real time; When the power access value of the heterogeneous sensor is lower than the calibrated power value of the heterogeneous sensor, calculating a deviation between the power access value and the calibrated power value, and recording it as a second deviation value; determining whether the reserve power value is greater than the second deviation value, and if so, connecting the power reserve unit and the heterogeneous sensor; If not, do not connect.

8. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 1 is characterized in that: The data processing module is used to receive and process the first sensing information and extract characteristic safety parameters, including: Generate a data processing task according to the first sensing information, decompose the data processing task into multiple processing subtasks, and assign the multiple processing subtasks to a multi-core CPU for parallel calculation; The multi-core CPU parallel computing comprises the following steps: Using wavelet transform or Fourier transform to compress and reduce noise of the first sensor information, so as to reduce the data volume of the first sensor information; Using a Kalman filter algorithm to eliminate sensor noise and environmental interference noise in the first sensing information to obtain second sensing information; Using a data fusion algorithm to fuse the second sensor information to obtain the characteristic safety parameter; The characteristic security parameters are sent to the edge computing module.

9. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 1, characterized in that the edge The calculation module is used to process the characteristic safety parameter to obtain the first processing information, including: The characteristic safety parameter is processed by using an incremental calculation method, and the data processing includes the following steps: Performing Huffman coding on the characteristic security parameter, and recording the processed characteristic security parameter as first packaged data; and, constructing a running state characteristic vector of the pipeline according to the characteristic safety parameter; Performing a state evaluation on the operating state feature vector to obtain an evaluation result, wherein the evaluation result includes a warning state, a maintenance state, an overhaul state, and a normal state; Performing Huffman coding on the evaluation result, and recording the processed evaluation result as second packaged data; Integrate the second packaged data with the first packaged data to form the first processing information, and transmit the first processing information to the server; And, the characteristic safety parameters and evaluation results are stored in a local database.

10. The stress-strain state monitoring system for high-temperature steam pipelines with characteristic safety parameters as claimed in claim 9, characterized in that: The running state feature vector is evaluated to obtain an evaluation result including: Inputting the operating state feature vector into a multi-level state classification model, the operating state feature vector including pipeline axial stress gradient, hoop strain fluctuation rate, temperature-stress coupling coefficient, steam pressure change entropy value and vibration spectrum distortion; The multi-level state classification model performs the following classification judgments: First-level judgment: When the temperature-stress coupling coefficient exceeds the preset dynamic threshold and the duration exceeds the range of the preset duration threshold, the warning state is triggered; Second level judgment: If the product of the axial stress gradient and the hoop strain fluctuation rate exceeds the material yield critical value, the maintenance state is triggered; The third level judgment: when the vibration spectrum distortion degree and the vibration spectrum distortion degree under the preset fault mode are placed within the same cosine similarity threshold, the maintenance state is triggered; Fourth level judgment: If the operating state feature vector is within the range of the preset operating threshold, the normal state is triggered; Establishing a decision fusion mechanism based on fuzzy logic to perform weighted fusion on the judgment results output by the multi-level state classification model; A sliding time window algorithm is used to perform trend analysis on a preset number of evaluation results of consecutive sampling periods, and when the same operating state occurs for a preset number of consecutive times, the output of the evaluation result is triggered; And, the evaluation result is matched with the historical failure cases in the local database for similarity, and the credibility level of the evaluation result is corrected.

Images