Intelligent valve actuator remote monitoring and fault early warning system based on Internet of Things

Abstract

The invention discloses an intelligent valve actuator remote monitoring and fault early warning system based on the Internet of Things, which relates to the field of valve actuator monitoring and comprises a data acquisition module, a data transmission module, a data storage and management module, an analysis and fault diagnosis module, an early warning module, a remote control module, a user interaction module, a safety protection module, a log recording and auditing module, an environment perception module and an intelligent prediction module. A plurality of sensors collect data, a hybrid communication architecture and quantum encryption transmission are used, distributed storage and cloud computing are combined, deep learning and reinforcement learning are fused to diagnose faults, early warning is performed based on a dynamic threshold model, remote control is performed by using digital twinning and a block chain, an immersive interface and voice interaction are supported, and system configuration is adaptively adjusted. A multi-level security protection system is adopted, and logs are analyzed and recorded by means of a block chain and big data. The valve actuator is monitored in real time in an omnibearing mode, data are accurately collected, transmission is stable and safe, faults are accurately diagnosed, early warning is conducted in time, remote control is supported, interaction is convenient and safe, and industrial operation is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of valve actuator monitoring, and particularly to an intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things. Background Art

[0002] In many fields such as industrial production, energy supply, and urban infrastructure, valve actuators are crucial devices, and their stable operation plays a key role in ensuring production safety, improving energy utilization efficiency, and maintaining the normal operation of the system. Traditional valve actuators usually rely on manual regular inspections to master their operating status. This method is not only inefficient, consuming a large amount of manpower and material resources, but also unable to achieve real-time monitoring, making it difficult to detect potential faults in a timely manner.

[0003] With the development of industrial automation and informatization, some preliminary remote monitoring systems have been applied to valve actuators. However, these systems have many deficiencies. In terms of data acquisition, the types of sensors are limited, and only some basic operating parameters can be obtained, making it difficult to detect some minor changes and potential faults. Moreover, the accuracy and reliability of the sensors are insufficient, and the collected data has errors, affecting the judgment of the true state of the valve actuator.

[0004] The data transmission link also faces challenges. Traditional wired transmission methods are limited by wiring costs and distances, making it difficult to be widely laid in complex environments and large-scale applications; wireless transmission has problems such as unstable signals, susceptibility to interference, and poor data security, which may lead to data loss or tampering, affecting the normal operation of the monitoring system.

[0005] In terms of fault diagnosis and warning functions, existing systems mostly use simple threshold judgment methods and cannot accurately identify complex fault modes. For early faults and potential risks, effective warnings cannot be issued in a timely manner, easily leading to equipment failures and even production accidents, causing huge economic losses and safety hazards.

[0006] In addition, existing remote monitoring systems lack intelligent and user-friendly designs. The user interface is not friendly enough, and the operation is complex, which is not conducive to the use by management personnel; the scalability and compatibility of the system are poor, making it difficult to integrate with other systems and unable to meet the growing demand for industrial intelligence. Therefore, it is of great practical significance to develop an efficient, intelligent, and safe intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things. Summary of the Invention

[0007] The intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things proposed by the present invention aims to solve the problems mentioned in the above prior art.

[0008] To achieve the above object, the present invention adopts the following technical solutions: An intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things, including:

[0009] Data acquisition module: Deploy multiple types of sensors at key parts of the intelligent valve actuator, and add a microelectromechanical gyroscope and an acoustic emission sensor;

[0010] Data transmission module: Adopt a hybrid communication architecture combining wide area network LPWAN and satellite communication technology, and use quantum encryption technology to generate encryption keys through the quantum key distribution QKD protocol to encrypt data;

[0011] Data storage and management module: Build an architecture combining distributed storage and cloud computing, store data with a distributed file system, process and analyze data with cloud computing, and introduce a data lake for unified storage and management;

[0012] Data analysis and fault diagnosis module: Apply a combination of deep learning and reinforcement learning, build a multi-modal deep neural network MDNN to extract features, and optimize the fault diagnosis strategy in combination with the reinforcement learning algorithm;

[0013] Fault warning module: Establish a dynamic threshold warning model based on the fault severity index FSI, automatically adjust the warning threshold by analyzing data through machine learning algorithms, and push warning information and processing suggestions when the threshold is exceeded;

[0014] Remote control module: Build a virtual model of the valve actuator using digital twin technology, synchronize the operation of the virtual model to the real device and feedback the results, and introduce blockchain smart contract technology to authenticate and authorize remote control operations;

[0015] User interaction module: Create an immersive interaction interface, combine virtual reality VR and tactile feedback, use natural language processing NLP technology to achieve voice interaction, and query the device status and issue control commands through voice instructions;

[0016] System configuration module: Use an adaptive configuration algorithm to optimize parameters according to the device operating environment and user requirements, dynamically adjust parameters, and encrypt and store configuration information in a distributed database;

[0017] Security protection module: Build a multi-level security protection system, integrate the zero-trust architecture and software-defined perimeter SDP technology, and use an intrusion detection system AIDS combined with deep learning algorithms to identify attack patterns;

[0018] Log recording and auditing module: Use blockchain and distributed ledger technology to record system logs and mine data using big data analysis.

[0019] Furthermore, it further includes:

[0020] Environmental perception module: Equipped with a micro weather station and harmful gas sensors, it monitors the wind speed v, wind direction d, atmospheric pressure p and other meteorological parameters and the concentrations of harmful gases such as sulfur dioxide SO2 and hydrogen sulfide H2S around the valve actuator. It fuses and analyzes the environmental data and the operation data of the valve actuator, uses the Bayesian network to establish an environment-fault correlation model, and evaluates the influence probability of environmental factors on valve failures.

[0021] Furthermore, it also includes:

[0022] Intelligent prediction module: It uses the Generative Adversarial Network (GAN) combined with the Long Short-Term Memory Network (LSTM) to predict faults. The generator in the GAN learns the normal operation data distribution to generate virtual normal data, the discriminator distinguishes between real data and generated data, and the LSTM network learns the long-term dependence relationship of the data to predict the operation status and potential faults of the valve actuator.

[0023] Furthermore, the sensors in the data acquisition module have the functions of self-calibration and adaptive acquisition frequency adjustment. They dynamically adjust the acquisition frequency f according to the operation status of the actuator. The formula is f = f0 + k×Δx, where f0 is the initial acquisition frequency, k is the adjustment coefficient, and Δx is the change amount of the operation parameters;

[0024] The sensors are integrated with energy harvesting devices, which use the thermoelectric effect and electromagnetic induction technology to collect the waste heat and vibration energy during the operation of the valve actuator, convert it into electrical energy to power the sensors, and use edge computing technology to perform preliminary processing and analysis on the collected data at the sensor nodes.

[0025] Furthermore, in the data transmission module, quantum encryption technology is used to encrypt key data during the transmission process. The quantum key distribution (QKD) protocol is used to generate the encryption key K. The encryption formula is E = Encrypt(D, K), where D is the original data and E is the encrypted data;

[0026] The Software-Defined Network (SDN) technology is used to dynamically optimize the network routing. The central controller monitors the network traffic and node status in real time. According to the data priority and the real-time network conditions, the Dijkstra algorithm or genetic algorithm is used to dynamically calculate the optimal routing path.

[0027] Furthermore, in the data analysis and fault diagnosis module, the fault severity index (FSI) is defined. The calculation formula is where w i is the weight of each operation parameter, and x i is the normalized anomaly value of the corresponding parameter;

[0028] The knowledge graph technology is introduced to integrate the equipment operation knowledge, fault cases and maintenance experience. Various types of knowledge are associated in the form of a graph. When detecting anomalies, the knowledge graph is used to locate the fault causes and solutions.

[0029] Furthermore, the calculation formula for the warning threshold T in the fault warning module is where T0 is the initial threshold, α is the adjustment factor, is the historical average fault severity index;

[0030] Adopt a multi-agent collaborative warning strategy. Each valve actuator acts as an agent to cooperate with each other and share fault information. When an agent detects an anomaly, the surrounding agents make a collaborative judgment based on their own status and shared information to avoid false alarms. The warning release strategy and countermeasures are determined through multi-agent negotiation.

[0031] Furthermore, the remote control module introduces the augmented reality remote assistance (ARRA) function. On-site maintenance personnel wear AR devices, and remote experts can see the on-site situation in real time in the AR scenario through the system and mark and guide operations on the virtual interface.

[0032] Furthermore, the user interaction module uses emotional computing technology to analyze the emotional state of the user during the interaction with the system. By monitoring the voice intonation, speech rate, word usage, and the frequency and rhythm of operation behaviors, the user's emotion is judged, and the display content and prompt information of the interaction interface are automatically adjusted according to the user's emotional state.

[0033] Furthermore, the security protection module uses homomorphic encryption technology to implement ciphertext data calculation and analysis, performs statistical analysis and fault diagnosis on encrypted operation data without decrypting the data, and uses biometric technology for user identity authentication.

[0034] Compared with the existing technologies, the beneficial effects of the present invention are:

[0035] In terms of monitoring, the system realizes all-round and real-time data collection. By deploying a variety of high-precision sensors, various operation parameters of the valve actuator and the surrounding environment information can be obtained, providing a rich data basis for accurately judging the equipment status. Whether it is a tiny angular deviation or a faint abnormal sound, it can be captured in time, greatly improving the accuracy and comprehensiveness of monitoring.

[0036] The data transmission adopts a hybrid communication architecture and quantum encryption technology, ensuring that data can be stably and securely transmitted in various environments. Even in remote areas or complex network environments, data loss can be guaranteed, providing reliable support for subsequent analysis and decision-making.

[0037] The fault diagnosis and early warning functions are powerful. By integrating algorithms of deep learning and reinforcement learning and combining with a dynamic threshold early warning model, it can accurately identify complex fault patterns, detect potential faults in advance and issue early warnings in a timely manner. At the same time, by precisely pushing early warning information through multiple channels, managers can master the situation in a timely manner, take effective countermeasures, avoid equipment failures and production accidents, and reduce economic losses and safety risks.

[0038] The remote control module utilizes digital twin and blockchain smart contract technologies to achieve safe and efficient remote operation. Managers can control the valve actuator in a virtual environment and obtain real-time feedback to ensure the accuracy and traceability of the operation.

[0039] The user interaction module adopts an immersive interaction interface and natural language processing technology, making the operation more convenient and user-friendly. Users can interact with the system through VR devices, joysticks and voice commands, enhancing the usage experience and work efficiency.

[0040] In addition, functions such as the system's adaptive configuration, multi-level security protection and intelligent log auditing improve the stability, security and maintainability of the system, providing strong guarantees for industrial production and infrastructure operation. Brief Description of the Drawings

[0041] Figure 1 It is a schematic block diagram of an Internet of Things-based intelligent valve actuator remote monitoring and fault early warning system proposed by the present invention;

[0042] Figure 2 It is a schematic diagram of the comparison of the timely fault discovery rate before and after the application of the system;

[0043] Figure 3 It is a schematic diagram of the proportion of different types of faults;

[0044] Figure 4 It is a schematic diagram of the change in the remote control response time;

[0045] Figure 5 It is a schematic diagram of the results of the user satisfaction survey. Detailed Embodiment

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0048] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, the meaning of "a plurality" is two or more unless otherwise specifically defined. In addition, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further introduced in detail below with reference to the drawings.

[0049] Refer to Figures 1 to 5 : An intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things, comprising:

[0050] Data acquisition module: Install various high-precision sensors at key parts of the intelligent valve actuator. The position sensor selects a high-precision photoelectric encoder, which can accurately obtain the valve opening P, with a range of 0-100%; the temperature sensor uses a thermocouple sensor to accurately measure the internal temperature T of the actuator; the pressure sensor selects a piezoresistive pressure sensor to monitor the inlet and outlet pressures P in and P out ; the current sensor uses a Hall current sensor to record the working current I of the actuator motor. A new microelectromechanical gyroscope is added to monitor the small angular deviation θ of the actuator operation, and an acoustic emission sensor captures the internal weak abnormal sound signal S. The sensor has a self-calibration function and automatically calibrates at regular intervals to ensure the measurement accuracy. The acquisition frequency f is dynamically adjusted according to the operating state of the actuator, and the formula is f = f0 + k × Δx, where f0 is the initial acquisition frequency, k is the adjustment coefficient, and Δx is the change amount of the operating parameters (such as temperature, pressure, etc.). For example, when the temperature change exceeds a certain threshold, the acquisition frequency is increased to capture data changes more timely.

[0051] Data Transmission Module: Adopts a hybrid communication architecture. In areas with good network coverage, it preferentially uses low-power wide-area networks such as LoRa or NB-IoT for data transmission to ensure data real-time performance; in remote areas or areas with poor network signals, it automatically switches to satellite communication. During the transmission process, quantum encryption technology is used. The quantum key distribution (QKD) protocol is utilized to generate an encryption key K, and the collected data D is encrypted. The encryption formula is E = Encrypt(D, K) to ensure the security of data during transmission. For example, at the data sending end, the key K is generated by the QKD device, and after encrypting the data D to obtain E, it is sent; at the receiving end, the same key K is used for decryption to obtain the original data D.

[0052] Data Storage and Management Module: Builds an architecture that combines distributed storage and cloud computing. The distributed file system selects Ceph to disperse the data storage across multiple nodes, improving storage reliability and scalability. The cloud computing platform adopts Alibaba Cloud or Huawei Cloud, etc., and utilizes their powerful computing capabilities for data processing and analysis. The concept of a data lake is introduced to uniformly store and manage structured operation parameter data, semi-structured device logs, and unstructured maintenance records, etc. For example, through the data lake, different formats of data can be correlated and analyzed to discover potential fault patterns.

[0053] Data Analysis and Fault Diagnosis Module: Uses an algorithm that combines deep learning and reinforcement learning for fault diagnosis. A multi-modal deep neural network (MDNN) is constructed, and various types of data such as position, temperature, pressure, current, angle deviation, and sound signals are used as different modalities of input to automatically extract complex features. Combining with a reinforcement learning algorithm (such as DQN), enables the system to optimize the fault diagnosis strategy through continuous attempts and feedback. Define a fault severity index FSI, and the calculation formula is where w i is the weight of each operation parameter, and x i is the normalized abnormal value of the corresponding parameter. Through the analysis of historical fault data, the weight w i of each parameter is determined. For example, when the abnormality of the temperature parameter has a greater impact on the fault, a higher weight is assigned to it.

[0054] Fault Warning Module: Establishes a dynamic threshold warning model based on the fault severity index FSI. Through machine learning algorithms to analyze historical fault data and real-time operation data, the warning threshold T is automatically adjusted. The formula is where T0 is the initial threshold, and α is the adjustment factor. is the historical average failure severity index. When the FSI exceeds T, the system accurately pushes warning information through multiple channels such as 5G messages and enterprise WeChat robots, including the type of failure, the possible affected range, and emergency handling suggestions. For example, when the warning is a valve leakage failure, it is recommended to immediately close the relevant valve and arrange maintenance personnel to go for handling.

[0055] Remote control module: Build a virtual model of the valve actuator using digital twin technology. In the remote monitoring center, the management personnel operate the virtual model, and the system synchronizes the operation instructions to the real device through real-time mapping technology and provides real-time feedback on the execution results of the device. Introduce blockchain smart contract technology to authenticate and authorize remote control operations. Only the instructions verified by the smart contract can be executed to ensure the security and traceability of control operations. For example, when the management personnel send a control instruction, the smart contract verifies their identity and permissions, and after verification, encrypts and sends the instruction to the device.

[0056] User interaction module: Create an immersive interaction interface, combining virtual reality (VR) and haptic feedback technology. When the user wears a VR device, they can enter the virtual factory scenario, view the operating status of the valve actuator from the first-person perspective, and achieve remote control through handle operations; the haptic feedback device enables the user to feel the resistance, vibration, etc. of the virtual device during operation, enhancing the realism and accuracy of the operation. Use natural language processing (NLP) technology to achieve voice interaction, and the user can query the device status and issue control commands through voice instructions. For example, when the user says "Query the current opening of valve 1", the system will reply with the opening information of valve 1 through voice.

[0057] System configuration module: Use an adaptive configuration algorithm to automatically optimize system parameters according to the device operating environment and user requirements. By collecting information such as network conditions and device performance indicators, dynamically adjust parameters such as data collection frequency, transmission protocol, and warning threshold. For example, when the network latency is high, automatically reduce the data collection frequency and switch to a more stable transmission protocol to ensure the stable operation of the system. The configuration information is stored in a distributed database through an encrypted channel for easy synchronization and management by multiple users.

[0058] Security protection module: Build a multi-level security protection system, integrating the zero-trust architecture and software-defined perimeter (SDP) technology. At the network boundary, the SDP technology hides system services, and only users who have passed identity authentication and authorization can access; internally, adopt the zero-trust strategy to strictly verify and continuously monitor each access request. Use an artificial intelligence-driven intrusion detection system (AIDS) to analyze network traffic and system behavior in real time, and identify new attack patterns through deep learning algorithms. For example, when an abnormal network traffic pattern is detected, AIDS will issue an alarm in a timely manner and take corresponding protection measures.

[0059] Logging and Auditing Module: The system logs are recorded using blockchain and distributed ledger technologies. Every operation, data transmission, fault event, etc. is encrypted and recorded in the distributed ledger, forming an immutable audit trail. Big data analysis techniques are used to mine the log data. For example, potential security threats and system performance bottlenecks can be discovered through correlation analysis. For instance, if it is found through log analysis that data transmission failures occur frequently during a certain period, network faults or equipment problems can be further investigated.

[0060] In the present invention, the following modules are further included:

[0061] Environmental Sensing Module: Equipped with a micro meteorological station and harmful gas sensors, it monitors the meteorological parameters (such as wind speed v, wind direction d, atmospheric pressure p) and harmful gas concentrations (such as sulfur dioxide SO2, hydrogen sulfide H2S concentration) around the valve actuator. The environmental data is fused and analyzed with the valve actuator operation data, and a Bayesian network is used to establish an environment - fault correlation model to evaluate the probability of environmental factors affecting valve failures and take preventive measures in advance.

[0062] In the present invention, the following modules are further included:

[0063] Intelligent Prediction Module: A method combining a Generative Adversarial Network (GAN) and a Long Short - Term Memory Network (LSTM) is used for fault prediction. The generator in the GAN learns the normal operation data distribution and generates virtual normal data; the discriminator distinguishes between real data and generated data, enhancing the model's sensitivity to abnormal data. The LSTM network learns the long - term dependencies in the data to predict the future operating state and potential faults of the valve actuator, providing an accurate basis for the maintenance plan in advance.

[0064] In the present invention, the sensors in the data acquisition module are integrated with energy harvesting devices. Specifically, based on the Seebeck effect, a thermoelectric effect principle, a thermoelectric potential is generated through a loop composed of two different conductors or semiconductors when there is a temperature gradient, thereby harvesting the waste heat generated during the operation of the valve actuator. With the help of Faraday's law of electromagnetic induction, that is, an induced electromotive force is generated when a conductor moves in a magnetic field to cut the magnetic induction lines, the vibration energy is captured. The harvested energy is processed by an energy conversion circuit and converted into stable electrical energy to continuously power the sensors, greatly reducing the system energy consumption. In terms of data processing, edge computing technology is adopted. Lightweight algorithms, such as anomaly detection algorithms based on machine learning, are deployed at the sensor nodes to perform real - time preliminary processing and analysis of the collected data such as pressure, temperature, vibration frequency, etc. locally, quickly identifying abnormal data and only transmitting key information to the cloud, significantly reducing the data transmission volume and remarkably improving the system response speed.

[0065] In the present invention, the data transmission module adopts software-defined network (SDN) technology, which realizes centralized management and flexible configuration of the network by separating the control plane and data plane of the network. As the core component of SDN, the centralized controller continuously monitors the bandwidth occupancy, flow rate and other traffic indicators of the network link in real time, as well as the load and operating status of each node. When there is data to be transmitted, the centralized controller uses the classic Dijkstra algorithm based on the priority of the data (for example, the priority of fault warning data is higher than that of regular operating status data) and the real-time network status. Starting from the source node, the centralized controller continuously searches for the node closest to the source node and has not been visited, and gradually constructs the shortest path to each node to calculate the optimal routing path; or uses a genetic algorithm to simulate the selection, crossover, mutation and other operations in biological evolution, iteratively optimizes various possible combinations of network routing paths, and screens out the optimal solution. In this way, data is ensured to be transmitted quickly and stably in the network, network congestion is avoided, and the data transmission efficiency and reliability of the entire remote monitoring and fault warning system are improved.

[0066] In this invention, the data analysis and fault diagnosis module incorporates knowledge graph technology. Through steps such as knowledge extraction and knowledge fusion, it structures operational knowledge such as equipment operating principles and operating specifications, past failure scenarios and phenomena, and maintenance personnel's troubleshooting methods and repair methods, all in the form of entity-relationship-entity triples. For example, the valve actuator "motor overheating" fault is treated as an entity and connected through relationships to possible fault cause entities such as "cooling fan failure" and "excessive load," as well as solution entities such as "check fan operation" and "adjust load," forming a knowledge graph network. When the system detects a valve actuator anomaly, such as a temperature sensor reporting an overly high temperature, the system leverages the semantic understanding and reasoning capabilities of the knowledge graph to rapidly traverse and match relevant knowledge along the graph's relationships, accurately locate the possible fault cause, and recommend corresponding solutions. This significantly improves the efficiency and accuracy of fault diagnosis, reduces equipment downtime, and ensures stable system operation.

[0067] In the present invention, the fault warning module adopts a warning strategy of multi-agent collaboration, and each valve actuator is regarded as an agent with sensing and decision-making capabilities. These agents share fault information with each other in real time through Internet of Things communication technologies, such as Low Power Wide Area Network (LPWAN) or industrial Ethernet. When the sensor of a certain agent (valve actuator) detects situations such as abnormal vibration or sudden temperature rise, it will immediately broadcast the abnormal data and its own status information to the surrounding agents. After receiving the information, the surrounding agents will combine the real-time data such as pressure and flow rate collected by themselves and the historical operation data, and use the preset data analysis algorithm (such as Bayesian network algorithm) for collaborative judgment. By analyzing the relevance, trend of the abnormal data and its own operation status, the authenticity of the abnormality is evaluated to avoid false alarms caused by single sensor error or local interference. After determining that the abnormality really exists, each agent will then determine the best warning release strategy according to factors such as the severity of the fault and the affected range through a distributed negotiation mechanism, such as selecting the appropriate warning level, notification object, etc., and discuss the optimal countermeasures, such as whether it is necessary to adjust the operation parameters, start standby equipment, etc., to ensure the stable operation of the entire system.

[0068] In the present invention, the remote control module incorporates an advanced Augmented Reality Remote Assistance (ARRA) function. When on-site maintenance personnel face complex faults that are difficult to solve, they need to wear an AR device with a high-definition camera, sensors, and display functions. This device is connected to the system server through a high-speed wireless network, and transmits the actual scene of the on-site valve actuator to the remote expert side in the form of a real-time video stream. With the help of the system interface, the remote expert can clearly observe the details on-site in the AR scene, such as the appearance of the valve, the connecting pipeline, the instrument readings, etc. The expert can use special marking tools to highlight key components, suspected fault points, etc. in the virtual interface, draw arrows or add text annotations, making it clear at a glance for on-site maintenance personnel. At the same time, the expert can also use the voice or text chat function, combined with the marked content, to guide on-site personnel to operate in real time, such as indicating how to disassemble specific components, adjust parameter settings, etc. According to the expert's guidance, on-site personnel accurately execute the operations under the prompt of the AR device. This method breaks through the spatial limitation, realizes the efficient collaboration between remote experts and on-site personnel, and greatly improves the efficiency and accuracy of valve actuator fault handling.

[0069] In the present invention, the user interaction module utilizes cutting-edge emotion computing technology. When a user interacts with the system, the system first collects the user's voice and operation behavior data through devices such as microphones and cameras. In terms of voice analysis, acoustic models and natural language processing technologies are used to accurately monitor the intonation, speech rate, and word usage of the voice. For example, when the user's intonation rises, the speech rate speeds up, and urgent words are frequently used, the system can determine that the user is in an anxious mood; if the voice is steady and the words are gentle, the user may be in a satisfied or calm state. For operation behaviors, the system records the frequency and rhythm of the user's operations such as clicking buttons and swiping the screen. For instance, frequently and quickly clicking the query button may imply the user's eagerness and anxiety. Based on this data, the system uses deep learning algorithms to model and classify the user's emotions. Once the user's emotional state is determined, the interaction interface is automatically adjusted. If the user is detected to be anxious, the interface will prominently display key fault solutions and simplify the operation process prompts; if the user is satisfied, appropriate product function introductions, usage skill sharing, etc. will be added. In this way, a more user-friendly service that meets the user's emotional needs is provided, enhancing the user experience.

[0070] In the present invention, the security protection module integrates advanced security technologies. As one of the core protection means, homomorphic encryption technology allows various calculations and analyses to be performed on data in the ciphertext state. Specifically, the system first encrypts the operation data of the valve actuator, such as numerical values of pressure, temperature, flow rate, etc., using the homomorphic encryption algorithm. Without decrypting, through specific ciphertext operation rules, statistical analyses are performed on the encrypted data, such as calculating the average value, standard deviation, etc., and logical judgments related to fault diagnosis can also be made, such as determining whether the valve operation deviates from the normal parameter range based on the encrypted data. This effectively prevents data from being leaked during the processing process and ensures data privacy and security. In terms of user identity authentication, biometric technologies are adopted. Taking fingerprint recognition as an example, when a user logs in to the system, the fingerprint acquisition device reads the fingerprint pattern features of the user, converts them into digital signals, and compares them with the fingerprint templates pre-stored in the system. Iris recognition uses optical devices to collect the unique texture information of the user's iris and verifies the user's identity through complex feature extraction and matching algorithms. Through biometric technologies, only legitimate users can access the system, significantly improving the security of system access and preventing unauthorized personnel from intruding.

[0071] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, should be covered by the protection scope of the present invention.

Claims

1. An intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things, characterized in that, It includes the following modules: Data acquisition module: Deploy multiple types of sensors at key parts of the intelligent valve actuator, and add a microelectromechanical gyroscope and an acoustic emission sensor; Data transmission module: Adopt a hybrid communication architecture combining wide area network LPWAN and satellite communication technology, and use quantum encryption technology to generate encryption keys through the quantum key distribution QKD protocol to encrypt data; Data storage and management module: Build an architecture combining distributed storage and cloud computing, store data using a distributed file system, process and analyze data through cloud computing, and introduce a data lake for unified storage and management; Data analysis and fault diagnosis module: Use a combination of deep learning and reinforcement learning to build a multi-modal deep neural network MDNN to extract features, and combine reinforcement learning algorithms to optimize fault diagnosis strategies; Fault warning module: Establish a dynamic threshold warning model based on the Fault Severity Index FSI, automatically adjust the warning threshold by analyzing data through machine learning algorithms, and push warning information and processing suggestions when the threshold is exceeded; Remote control module: Use digital twin technology to build a virtual model of the valve actuator, synchronize the operation of the virtual model to the real device and feedback the results, and introduce blockchain smart contract technology to authenticate and authorize remote control operations; User interaction module: Create an immersive interaction interface, combine virtual reality VR and tactile feedback, use natural language processing NLP technology to achieve voice interaction, and query the device status and issue control commands through voice instructions; System configuration module: Use an adaptive configuration algorithm to optimize parameters according to the device operating environment and user requirements, dynamically adjust parameters, and encrypt and store configuration information in a distributed database; Security protection module: Build a multi-level security protection system, integrate the zero-trust architecture and software-defined perimeter SDP technology, and use the intrusion detection system AIDS combined with deep learning algorithms to identify attack patterns; Log recording and auditing module: Use blockchain and distributed ledger technology to record system logs and mine data using big data analysis.

2. The intelligent valve actuator remote monitoring and fault warning system based on the Internet of Things according to claim 1, characterized in that, It also includes: Environmental perception module: Equip with a micro meteorological station and harmful gas sensors to monitor the meteorological parameters of wind speed v, wind direction d, and atmospheric pressure p and the concentrations of harmful gases sulfur dioxide SO2 and hydrogen sulfide H2S around the valve actuator. Integrate and analyze environmental data and valve actuator operation data, and use a Bayesian network to establish an environment-fault correlation model to evaluate the influence probability of environmental factors on valve failures.

3. The remote monitoring and fault warning system for an intelligent valve actuator based on the Internet of Things according to claim 1, wherein, It also includes: Intelligent prediction module: Use a generative adversarial network GAN combined with a long short-term memory network LSTM to predict faults. The generator learns the normal operation data distribution in the GAN to generate virtual normal data, the discriminator distinguishes between real data and generated data, and the LSTM network learns the long-term dependence relationship of the data to predict the operation state and potential faults of the valve actuator.

4. The remote monitoring and fault warning system for intelligent valve actuators based on the Internet of Things according to claim 1, characterized in that The sensors in the data acquisition module have self-calibration and adaptive acquisition frequency adjustment functions, and dynamically adjust the acquisition frequency f according to the actuator operation state. The formula is f = f0 + k × Δx, where f0 is the initial acquisition frequency, k is the adjustment coefficient, and Δx is the change amount of the operation parameter; The sensor integrated energy harvesting device utilizes the thermoelectric effect and electromagnetic induction technology to collect waste heat and vibration energy during the operation of the valve actuator, convert it into electrical energy to power the sensor, and adopts edge computing technology to preliminarily process and analyze the collected data at the sensor node.

5. The remote monitoring and fault warning system for the intelligent valve actuator based on the Internet of Things according to claim 1, wherein In the data transmission module, quantum encryption technology is used to encrypt key data during the transmission process. The quantum key distribution QKD protocol is used to generate the encryption key K, and the encryption formula is E = Encrypt(D, K), where D is the original data and E is the encrypted data. The software-defined network SDN technology is adopted to dynamically optimize the network routing. The central controller monitors the network traffic and node status in real time, and according to the data priority and real-time network conditions, the Dijkstra algorithm or genetic algorithm is used to dynamically calculate the optimal routing path.

6. The remote monitoring and fault warning system for the intelligent valve actuator based on the Internet of Things according to claim 1, characterized in that, Define the fault severity index FSI in the data analysis and fault diagnosis module. The calculation formula is where w i is the weight of each operating parameter, and x i is the normalized abnormal value of the corresponding parameter; The knowledge graph technology is introduced to integrate device operation knowledge, fault cases, and maintenance experience. Various types of knowledge are associated in the form of a graph, and when an anomaly is detected, the knowledge graph is used to locate the fault cause and solution.

7. The remote monitoring and fault warning system for the intelligent valve actuator based on the Internet of Things according to claim 1, characterized in that The calculation formula for the warning threshold T in the fault warning module is where T0 is the initial threshold and α is the adjustment factor, which is the historical average fault severity index; The multi-agent collaborative early warning strategy is adopted. Each valve actuator acts as an agent to cooperate with each other and share fault information. When an agent detects an anomaly, the surrounding agents make a collaborative judgment based on their own status and shared information to avoid false alarms, and the early warning release strategy and countermeasures are determined through multi-agent negotiation.

8. The remote monitoring and fault warning system for intelligent valve actuators based on the Internet of Things according to claim 1, characterized in that The remote control module introduces the augmented reality remote assistance ARRA function. The on-site maintenance personnel wear AR devices, and the remote experts can see the on-site situation in real time in the AR scene through the system and mark and guide the operation on the virtual interface.

9. The remote monitoring and fault warning system for the intelligent valve actuator based on the Internet of Things according to claim 1, characterized in that, The user interaction module uses affective computing technology to analyze the user's emotional state during the interaction with the system. The user's emotion is judged by monitoring the voice intonation, speech rate, word usage, and the frequency and rhythm of operation behaviors, and the display content and prompt information of the interaction interface are automatically adjusted according to the user's emotional state.

10. The remote monitoring and fault warning system for intelligent valve actuators based on the Internet of Things according to claim 1, characterized in that, The security protection module uses homomorphic encryption technology to realize the calculation and analysis of ciphertext data, conducts statistical analysis and fault diagnosis on the encrypted operation data without decrypting the data, and uses biometric technology for user identity authentication.

Images