Intelligent power transmission and transformation monitoring and fault early warning system based on Internet of Things

Abstract

The invention discloses an intelligent power transmission and transformation monitoring and fault early warning system based on Internet of Things, which relates to the technical field of power transmission and transformation monitoring and Internet of Things and comprises a data acquisition layer, a network transmission layer, a data processing layer and an early warning display layer. The functions of quantum encryption communication and self-diagnosis repair are achieved; multi-element networking is adopted for network transmission, quantum key distribution and a block chain are combined, an SDN and SD-WAN fusion architecture is used, a three-layer architecture is used for data processing, a quantum neural network and knowledge graph assistance is used, an MR technology and a brain-computer interface are used for early warning display, and all layers collaboratively guarantee efficient operation of the system. The system has obvious advantages, data acquisition is comprehensive and safe, and the sensor can be self-diagnosed and repaired; network transmission is stable and reliable, and data security is guaranteed; data processing is accurate and efficient, and early warning accuracy is improved; the early warning display interactivity is high, the equipment can be scientifically evaluated, the maintenance decision is optimized, the cost is reduced, and the stable operation of the power transmission and transformation system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of power transmission and transformation monitoring and the technical field of the Internet of Things, and in particular to an intelligent power transmission and transformation monitoring and fault early warning system based on the Internet of Things. Background Art

[0002] In modern society, the stability and reliability of power supply are crucial for economic development and people's daily lives. As a key link in power transmission, the safe operation of the power transmission and transformation system is of paramount importance. However, current power transmission and transformation monitoring and fault warning systems face many challenges.

[0003] Traditional power transmission and distribution monitoring methods rely primarily on manual inspections and a small number of fixed sensors. Manual inspections suffer from long inspection cycles, low efficiency, and difficulty detecting potential equipment failures in real time. Furthermore, due to limited manpower and environmental factors, equipment inspections in remote or hazardous areas are difficult and risky. The data collected by these few fixed sensors is limited, unable to fully reflect the operating status of power transmission and distribution equipment, making it difficult to provide timely warnings for early-stage, hidden failures.

[0004] Traditional network transmission methods suffer from unstable signals, significant transmission delays, and limited bandwidth. In remote areas, inadequate signal coverage can lead to data interruptions or loss, compromising the real-time and accuracy of monitoring systems. Furthermore, data security is also threatened. Data theft or tampering can lead to misjudgments and serious power outages.

[0005] In terms of data processing, existing monitoring systems mostly rely on simple data analysis methods, which are unable to deeply mine and analyze massive and complex operational data. Equipment failure predictions are mainly based on experience and simple threshold judgments, lacking the precise extraction of fault characteristics and probability prediction, resulting in poor accuracy and timeliness of fault warnings.

[0006] There is a lack of a scientific, comprehensive assessment system and optimization strategy for equipment health assessment and maintenance decision-making. Current assessment methods often only consider a single factor and fail to integrate multiple factors, such as the equipment's operating status, failure probability, and load conditions. Maintenance decisions are also relatively crude, making it difficult to select the optimal maintenance strategy based on the actual equipment conditions, resulting in high maintenance costs and low efficiency.

[0007] The development of emerging technologies such as the Internet of Things, artificial intelligence, and quantum technology has provided new ideas and methods for solving these problems. By building an intelligent power transmission and distribution monitoring and fault warning system based on the Internet of Things, using advanced sensor technology to comprehensively collect equipment operating data, employing high-speed and secure network transmission technology to ensure real-time and accurate data transmission, and applying powerful data processing and analysis technologies to deeply explore the value of data, and establishing a scientific equipment health assessment and intelligent maintenance decision-making system, we can effectively improve the safety, reliability, and economy of the power transmission and distribution system and ensure a stable power supply. Summary of the Invention

[0008] The present invention proposes an intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things to solve the problems mentioned in the above-mentioned prior art.

[0009] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things, comprising:

[0010] Data collection layer: There are multiple types of sensors in various locations of power transmission and transformation equipment. Conventional data collection includes current I, voltage U, and temperature T. New local discharge photon sensors are added to capture internal weak discharge photon signals P. The sensors use an integrated multi-energy collection micro-nano system that integrates electromagnetic induction, piezoelectric effect, thermoelectric effect, and friction nano-power generation technology, and uses an improved data validity judgment formula. Filter data, where N valid is the number of valid data, N total is the total amount of data, α is the correction coefficient considering the characteristics of the newly added sensor data;

[0011] Network transmission layer: 5G, LoRa, and satellite communication are used in a multi-hybrid network. In areas without 5G and LoRa signals, satellite communication is automatically switched. Quantum key distribution technology is introduced to encrypt data. The improved signal strength and transmission reliability formula is R = k × S × (1 + β), where k is a constant, S is the signal strength, and β is an enhancement coefficient that takes into account the advantages of quantum encryption and multi-networking. At the same time, distributed network ledger technology based on blockchain is used to transmit information.

[0012] Data processing layer: Adopting a three-layer architecture of edge computing, fog computing, and cloud computing, edge computing nodes screen data and extract features; the fog computing layer performs processing and analysis, and the cloud computing center uses a deep convolution algorithm based on quantum neural networks to extract fault features using the formula F = f(I, U, T, P). The improved fault probability prediction formula P = g(F) × (1 + γ), where g(F) is a function based on the fault feature F and γ is the boost coefficient, is used. Knowledge graph technology is also used to integrate professional knowledge and historical equipment data in the power transmission and transformation field.

[0013] Early warning display layer: Displays device status and early warning information through a visual interface, supports multi-terminal access, and adopts holographic projection and brain-computer interface interaction technology. Users control the device status information displayed by holographic projection through brain thinking instructions. The improved early warning level formula L = h(P) × (1 + δ) divides the early warning level. h(P) is a function based on the probability of failure P, and δ is an adjustment coefficient considering the user interaction experience and information importance.

[0014] Furthermore, it also includes an equipment health assessment module, which uses an improved equipment health index formula Calculate the device health index, where n is the number of parameters involved in calculating the device health index, and w i is the weight of the i-th parameter, x i is the actual measured value of the i-th parameter, ∈ i It is a dynamic correction coefficient for each parameter that changes with the equipment operating environment and time. The index is updated in real time with the help of synchronous computing technology based on quantum entanglement. The health level is divided according to the index to provide a basis for equipment maintenance, and the historical changes in health status are recorded using blockchain technology.

[0015] Furthermore, it also includes an intelligent maintenance decision module, which combines the equipment failure probability P, health index H and the real-time load condition L of the equipment load The improved maintenance benefit evaluation formula is B = m × P × (1-H) × (1 + ζ × L load )+n×C, where ζ is the load influence coefficient. Then, through the algorithm optimization combining genetic and simulated annealing, the maintenance strategy is selected according to the benefit.

[0016] Furthermore, the sensors in the data acquisition layer have intelligent self-diagnosis function, and the improved sensor performance evaluation formula Evaluate its own performance in real time, with p, q, and r as coefficients, where r is the coefficient of photon signal change, ΔV is the voltage change, ΔI is the current change, ΔP is the photon signal change, and Δt is the time interval. When performance degrades, the sensor automatically adjusts the acquisition frequency and range, and sends maintenance reminders to the system through quantum encryption communication, while using the built-in micro-repair device for self-repair.

[0017] Furthermore, the network transport layer adopts the software-defined network (SDN) technology and the software-defined wide area network (SD-WAN) fusion architecture. The network topology is adjusted according to the network traffic, signal strength, device importance and data real-time requirements through the SDN controller and SD-WAN orchestrator. The improved network optimization formula is: T throughput is the network throughput, T delayis the network delay, η is the performance improvement coefficient brought by the fusion architecture, r and s are coefficients, and quantum repeater technology is introduced to extend the transmission distance of quantum key distribution.

[0018] Furthermore, the data processing layer uses a reinforcement learning algorithm combined with a quantum annealing algorithm to optimize the fault prediction model, and uses an improved reward function R learn =t×(1-P error )+u×E×(1+θ) motivates model learning, P error is the error probability of fault prediction, θ is the optimization coefficient brought by the quantum annealing algorithm, and the federated learning technology is used to combine the data of multiple power transmission and transformation systems for model training without sharing the original data.

[0019] Furthermore, the warning display layer adopts mixed reality MR technology. Users can immersively experience the operating status of the power transmission and transformation equipment through MR devices, and use the improved AR positioning formula A=f(x, y, z)×(1+λ) to locate the equipment position. λ is the positioning accuracy improvement coefficient brought by MR technology. At the same time, the system uses artificial intelligence algorithms to provide users with personalized information display and interaction methods based on the user's operating habits and historical data.

[0020] Further, the following steps are included:

[0021] Data collection steps: Sensors in the data collection layer collect real-time operating data from power transmission and transformation equipment, including newly added photon signals. Effective data is filtered using improved formulas. Sensors self-diagnose and attempt self-repair, and quantum encryption communication ensures data security.

[0022] Data transmission steps: The network transmission layer uses multi-hybrid networking, quantum key distribution, and blockchain technology, combined with SDN and SD-WAN architectures, and uses improved formulas to optimize transmission performance and evaluate reliability;

[0023] Data processing steps: A three-layer architecture is used, assisted by quantum neural networks and knowledge graphs. Improved formulas are used to extract features and predict probabilities. The model is optimized by combining it with the quantum annealing algorithm, and federated learning improves versatility.

[0024] Warning display steps: The warning display layer uses MR technology and brain-computer interface interaction, divides warning levels according to the improved formula, and artificial intelligence provides a personalized experience.

[0025] Furthermore, this step uses an improved formula to calculate the equipment health index, quantum entanglement is updated synchronously, blockchain records history, and health levels are divided to provide a reference for maintenance.

[0026] Furthermore, an improved formula is used to evaluate the effectiveness of strategies by combining failure probability, health index and load conditions. Genetic and simulated annealing algorithms are combined to select the optimal strategy and optimize resource allocation.

[0027] Compared with the existing technology, the beneficial effects of the present invention are:

[0028] In terms of data collection, the addition of a partial discharge photon sensor and an integrated multi-energy harvesting micro-nanosystem not only enables more comprehensive capture of equipment operating data, enabling early warning of insulation failures, but also solves the sensor's self-power supply issue and improves power supply stability. Quantum encryption communication ensures the security of data collection, and the sensor's intelligent self-diagnosis and self-repair capabilities reduce maintenance costs and workload.

[0029] In terms of network transmission, a multi-hybrid networking approach ensures uninterrupted data transmission in any environment. Quantum key distribution and blockchain technology guarantee the security and traceability of data transmission. The SDN and SD-WAN converged architecture and quantum repeater technology optimize network performance and improve the real-time and reliability of data transmission.

[0030] Data processing adopts a three-layer architecture, quantum neural network and knowledge graph technology, combined with reinforcement learning, quantum annealing algorithm and federated learning, which can more accurately extract fault characteristics and predict fault probability, improve the accuracy and generalization ability of fault warning, and at the same time enhance the versatility of the model.

[0031] The MR technology and brain-computer interface interaction of the warning display layer, as well as the personalized information display, provide users with an immersive and convenient interactive experience, allowing users to understand the device status more intuitively.

[0032] By improving formulas and optimizing algorithms, the Equipment Health Assessment Module and the Intelligent Maintenance Decision Module comprehensively consider multiple factors. These modules can scientifically assess equipment health, select optimal maintenance strategies, optimize resource allocation, reduce maintenance costs, and improve the reliability and economic efficiency of the power transmission and transformation system. Overall, this patented system and method comprehensively enhances power transmission and transformation monitoring and fault warning capabilities, ensuring the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic block diagram of an intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things proposed by the present invention;

[0034] Figure 2 This is a schematic block diagram of an intelligent power transmission and transformation monitoring and fault early warning method based on the Internet of Things proposed by the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are 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 understood as limiting the present invention.

[0037] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "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 "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below with reference to the accompanying drawings.

[0038] Reference Figure 1-2 : An intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things, including a data acquisition layer, a network transmission layer, a data processing layer and a warning display layer.

[0039] Data acquisition layer: In addition to the conventional current I, voltage U, and temperature T, the multi-type sensors distributed throughout the power transmission and transformation equipment also include local discharge photon sensors that can capture the photon signal P generated by the extremely weak local discharge inside the equipment for early warning of insulation faults. The sensor uses an integrated multi-energy collection micro-nano system that not only utilizes electromagnetic induction and piezoelectric effects, but also integrates thermoelectric effects and friction nano-power generation technology to collect energy from multiple environmental factors such as magnetic fields, vibrations, temperature differences, and breezes during the operation of power transmission and transformation equipment, achieving self-powered power and significantly improving power supply stability. Use the improved data validity judgment formula (N valid Indicates the number of valid data collected, N total (This refers to the total amount of data collected, with α being a correction factor to account for the characteristics of newly added sensor data) to filter valid data. The sensor is equipped with quantum encryption communication capabilities to ensure the security of collected data before transmission.

[0040] The network transmission layer innovatively utilizes a hybrid networking approach combining 5G, LoRa, and satellite communications. 5G technology, with its high speed and low latency, enables rapid transmission of large amounts of monitoring data. LoRa, with its superior long-distance transmission and low power consumption, is suitable for data communication within a certain range. In remote areas, when 5G and LoRa signals are out of reach, the system automatically and seamlessly switches to satellite communication mode, ensuring continuous, uninterrupted data transmission. To ensure data security during transmission, this layer incorporates quantum key distribution (QKD). This advanced technology, based on the principles of quantum mechanics, provides theoretically absolutely secure encryption for data transmission, effectively preventing data theft and tampering. To assess transmission reliability, an improved signal strength and transmission reliability formula (R = k × S × (1 + β)) is used (k is a constant, S represents signal strength, and β is an enhancement factor that accounts for the advantages of quantum encryption and multi-networking). This formula enables more accurate assessment of transmission reliability, enabling timely optimization measures.

[0041] Furthermore, to ensure transparency and security during data transmission, the network transport layer utilizes distributed ledger technology based on blockchain. Detailed information about each data transmission, including transmission time, source address, and destination address, is fully recorded. This approach not only ensures traceability, enabling rapid identification and troubleshooting of any issues, but also leverages the unique characteristics of blockchain technology to ensure data immutability, further enhancing the security and reliability of the entire system.

[0042] Data processing layer: A three-layer architecture of edge computing, fog computing, and cloud computing is employed. Edge computing nodes perform preliminary data screening and simple feature extraction; the fog computing layer further processes and analyzes the data, alleviating pressure on the cloud computing. The cloud computing center utilizes a deep convolution algorithm based on quantum neural networks. Using an improved fault feature extraction formula F = f(I, U, T, P), where I, U, T, and P represent current, voltage, temperature, and photon signals, respectively, this method more comprehensively and accurately extracts fault features. The improved fault probability prediction formula P = g(F) × (1 + γ) (g(F) is a function based on the fault feature F, and γ is a boost factor to account for the advantages of quantum algorithms) is then used to predict the probability of fault occurrence. Knowledge graph technology is used to integrate professional knowledge in the power transmission and transformation field and historical equipment data to assist in fault diagnosis and prediction.

[0043] Early warning display layer: With the help of a visual interface, the real-time status and early warning information of the equipment are presented in an intuitive and clear manner. It also supports access from multiple terminals such as computers, mobile phones, and tablets, making it convenient for users to obtain relevant information at any time in different scenarios. In terms of technical applications, this layer introduces cutting-edge holographic projection technology and brain-computer interface interaction technology. Holographic projection technology can vividly display device status information in a three-dimensional form, allowing users to observe the device status as if they were there. Brain-computer interface interaction technology can achieve this. Users do not need to wear complex control devices. They can rely on the instructions issued by their brain to accurately control the device status information displayed by the holographic projection, realize information switching, zooming in, zooming out, and other operations, and greatly improve the convenience and fun of interaction. In terms of warning level classification, the warning display layer makes scientific judgments based on the improved warning level formula L = h(P) × (1 + δ). (h(P) is a function based on the probability of failure P, and δ is an adjustment coefficient that considers user interaction experience and information importance.) After different warning levels are divided according to this formula, the system will adopt a variety of reminder methods, using different colors of light and shadow flashing, sound alarms of different frequencies and tones, and unique holographic projection effects to attract users' attention for different levels, ensuring that users can quickly and accurately understand the degree of failure risk of the equipment and take corresponding measures in a timely manner.

[0044] The present invention also includes an equipment health assessment module. This module uses the improved equipment health index formula (n represents the number of parameters involved in calculating the device health index, w i is the weight of the i-th parameter, x i is the actual measured value of the i-th parameter, ∈ iThe device health index is calculated using dynamic correction coefficients (which reflect changes in each parameter over time and in the device's operating environment). This system uses quantum entanglement-based synchronous computing technology to update the device health index in real time. The health index is used to categorize device health levels, such as healthy, sub-healthy, fault warning, and faulty, providing a basis for device maintenance. Blockchain technology is also used to record historical changes in device health status, ensuring data authenticity and traceability.

[0045] The present invention also includes an intelligent maintenance decision module. During actual operation, the intelligent maintenance decision module will comprehensively consider multiple key factors. The equipment failure probability P, which reflects the possibility of equipment failure in the current state; the health index H, which intuitively reflects the current health status of the equipment; and the real-time load condition L of the equipment. load This parameter reflects the working intensity of the equipment during operation. In order to accurately evaluate the benefits of different maintenance strategies, the module uses the improved maintenance benefit evaluation formula B = m × P × (1-H) × (1 + ζ × L load )+n×C (ζ is the load influence coefficient) By substituting the key factors mentioned above into the formula for calculation, the benefit values corresponding to different maintenance strategies can be obtained.

[0046] In its decision-making process, the module employs an optimization strategy that combines genetic algorithms and simulated annealing. Genetic algorithms mimic biological evolution, searching for potential optimal solutions within the solution space through operations such as selection, crossover, and mutation. Simulated annealing, based on the principles of the physical annealing process, prevents the algorithm from becoming trapped in local optima, thereby enabling it to find the global optimal solution over a wider range. These two algorithms work together to select the optimal solution from a variety of maintenance strategies based on calculated benefits. These include preventive maintenance, which involves proactive equipment maintenance and inspection to prevent potential problems, and corrective maintenance, which involves timely repairs after equipment failures. Furthermore, when making decisions, the intelligent maintenance decision-making module not only considers the benefits of the maintenance strategy itself but also fully considers the optimal allocation and scheduling of maintenance resources. This means comprehensively weighing various resources, including human, material, and financial resources, to ensure the most rational and efficient use of resources when executing the maintenance strategy. This minimizes maintenance costs while ensuring normal equipment operation, thereby improving overall economic benefits and operational efficiency.

[0047] In the present invention, the sensor of the data acquisition layer has an intelligent self-diagnosis function. (p, q, and r are coefficients, where r is the coefficient of photon signal variation, ΔV represents voltage variation, ΔI represents current variation, ΔP represents photon signal variation, and Δt represents time interval.) The sensor evaluates its performance in real time. When performance degrades, it automatically adjusts the acquisition frequency and range, sends maintenance alerts to the system via quantum encrypted communication, and simultaneously initiates a simple self-repair attempt using its built-in micro-repair device.

[0048] In the present invention, the network transport layer adopts the software defined network (SDN) technology and software defined wide area network (SD-WAN) fusion architecture. The SDN controller and SD-WAN orchestrator dynamically adjust the network topology according to the network traffic, signal strength, device importance and data real-time requirements, and use the improved network optimization formula (T throughput represents the network throughput, T delay (where λ represents network latency, r and s represent performance improvements brought by the converged architecture, and r and s represent coefficients) to optimize network transmission performance. Quantum repeater technology is introduced to extend the transmission distance of quantum key distribution and ensure the security of long-distance data transmission.

[0049] In the present invention, the data processing layer combines the reinforcement learning algorithm with the quantum annealing algorithm, providing a strong technical support for the optimization of the fault prediction model. The reinforcement learning algorithm simulates the process of the intelligent agent learning the optimal behavior strategy through continuous trial and error in the environment, while the quantum annealing algorithm uses the characteristics of the quantum system to more efficiently find the optimal solution in the complex solution space. The organic combination of these two algorithms enables the fault prediction model to better adapt to the complex and changeable operating conditions in the power transmission and transformation system. In order to motivate the model to learn effectively, the data processing layer adopts an improved reward R learn =t×(1-P error )+u×E×(1+θ)(P error (where θ represents the error probability of fault prediction and θ is the optimization coefficient brought by the quantum annealing algorithm) Through this reward function, the model can obtain corresponding rewards according to the accuracy of the prediction results and the optimization effect of the quantum annealing algorithm during the learning process, thereby prompting the model to continuously adjust its own parameters and improve the accuracy and generalization ability of fault prediction. In other words, it can not only perform well on existing data, but also accurately predict new data.

[0050] Furthermore, to further enhance the model's practicality, federated learning technology is employed at the data processing layer. In power transmission and transformation systems, data is often dispersed across multiple systems, raising concerns about data privacy and security. Federated learning technology allows these systems to jointly train models without sharing raw data. Each system processes and trains data locally, uploading only model parameters or gradient information from the training process to a central server for aggregation. The central server then distributes the updated model to each system. This fully utilizes the data resources of multiple power transmission and transformation systems while protecting data privacy and security. This makes the trained model more versatile and adaptable, enabling it to better address the characteristics and needs of diverse power transmission and transformation systems.

[0051] In this invention, the warning display layer utilizes mixed reality (MR) technology, a fusion of augmented reality (AR) and virtual reality (VR). Users experience the operating status of power transmission and transformation equipment through MR devices, and the improved AR positioning formula A = f(x, y, z) × (1 + λ) (λ is the positioning accuracy improvement factor brought by MR technology) is used to accurately locate the equipment position, enhancing the interactive experience. Simultaneously, the system uses artificial intelligence algorithms to provide users with personalized information display and interaction methods based on their operating habits and historical interaction data.

[0052] The present invention includes the following steps: data acquisition step: the data acquisition layer sensor collects the operating data of the power transmission and transformation equipment in real time, covering the newly added photon signals, uses the improved formula to screen the effective data, the sensor self-diagnoses and attempts self-repair, and quantum encryption communication ensures data security.

[0053] Data transmission steps: The network transmission layer adopts multi-hybrid networking, quantum key distribution and blockchain technology, combined with SDN and SD-WAN architecture, and uses improved formulas to optimize transmission performance and evaluate reliability.

[0054] Data processing steps: A three-tier architecture of edge computing, fog computing, and cloud computing is employed. Edge computing nodes screen data and extract key features, the fog computing layer further analyzes the data, and the cloud computing center performs in-depth processing. Data processing utilizes quantum neural networks and knowledge graph technologies. Quantum neural networks can process complex data patterns and uncover hidden information. Knowledge graphs integrate specialized knowledge in the power transmission and distribution field and historical equipment data to provide background knowledge for data processing. Federated learning improves versatility by improving formulas for feature extraction and prediction probabilities, and strengthening the optimization model with quantum annealing algorithms.

[0055] Warning display steps: The warning display layer incorporates advanced mixed reality (MR) technology and brain-computer interface (BCI) interaction technology. MR technology integrates virtual device status information with real-world scenarios, presenting it to users in a more intuitive and three-dimensional manner. This allows users to immerse themselves in the actual operating environment of the device and clearly understand the real-time status of the device. BCI interaction technology breaks through traditional operation methods. Users can interact naturally with the display interface through their brains, eliminating the need for complex external devices and conveniently accessing and manipulating relevant information through simple mental instructions. The warning display layer uses an improved formula to classify warning levels. This formula comprehensively considers the probability of failure and other relevant factors to scientifically and accurately determine different warning levels. For each warning level, the system implements differentiated alerts to ensure users can quickly perceive the severity of potential equipment risks. Furthermore, the warning display layer incorporates artificial intelligence technology. By analyzing and learning from user usage habits, focus areas, and other data, AI can provide a personalized user experience. For example, it can tailor the information display method and content to user preferences, prioritizing device status and warning information that users are most concerned about. This improves user information acquisition efficiency and helps users make more effective decisions and management decisions.

[0056] The present invention also includes an equipment health assessment step. This step uses an improved formula to calculate the equipment health index, quantum entanglement is updated synchronously, and blockchain technology is used to record historical changes in the equipment health status. Blockchain has the characteristics of being tamper-proof and traceable. Every change in the equipment health index, key events during the equipment operation process, and other information are recorded securely and permanently. Different equipment health levels are divided according to the calculated equipment health index. These levels clearly and intuitively show the health of the equipment and provide a clear reference for equipment maintenance. Operation and maintenance personnel can reasonably arrange maintenance plans based on the health level of the equipment, and promptly inspect and maintain equipment in poor health to prevent problems before they occur, thereby improving the reliability and service life of the equipment and reducing overall operation and maintenance costs.

[0057] The present invention also includes an intelligent maintenance decision-making step. By comprehensively considering the probability of equipment failure, health index, and real-time load conditions, a set of scientific evaluation methods is used to comprehensively analyze the benefits that can be generated by different maintenance strategies, among which the impact of load conditions on benefits is quantified. Subsequently, a combination of genetic algorithms and simulated annealing algorithms is used to screen out the best solution from a variety of maintenance strategies, such as preventive maintenance, which inspects and maintains equipment in advance; or corrective maintenance, which repairs equipment in a timely manner after a failure occurs. At the same time, this step will also optimize the allocation of maintenance resources such as manpower and material resources, striving to effectively reduce maintenance costs while ensuring the normal operation of the equipment.

[0058] The above are only preferred specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things, characterized by: include: Data collection layer: There are multiple types of sensors in various locations of power transmission and transformation equipment. Conventional data collection includes current I, voltage U, and temperature T. New local discharge photon sensors are added to capture internal weak discharge photon signals P. The sensors use an integrated multi-energy collection micro-nano system that integrates electromagnetic induction, piezoelectric effect, thermoelectric effect, and friction nano-power generation technology, and uses an improved data validity judgment formula. Filter data, where N valid is the number of valid data, N total is the total amount of data, α is the correction coefficient considering the characteristics of the newly added sensor data; Network transmission layer: 5G, LoRa, and satellite communication are used in a multi-hybrid network. In areas without 5G and LoRa signals, satellite communication is automatically switched. Quantum key distribution technology is introduced to encrypt data. The improved signal strength and transmission reliability formula is R = k × S × (1 + β), where k is a constant, S is the signal strength, and β is an enhancement coefficient that takes into account the advantages of quantum encryption and multi-networking. At the same time, distributed network ledger technology based on blockchain is used to transmit information. Data processing layer: Adopting a three-layer architecture of edge computing, fog computing, and cloud computing, edge computing nodes screen data and extract features; the fog computing layer performs processing and analysis, and the cloud computing center uses a deep convolution algorithm based on quantum neural networks to extract fault features using the formula F = f(I, U, T, P). The improved fault probability prediction formula P = g(F) × (1 + γ), where g(F) is a function based on the fault feature F and γ is the boost coefficient, is used. Knowledge graph technology is also used to integrate professional knowledge and historical equipment data in the power transmission and transformation field. Early warning display layer: Displays device status and early warning information through a visual interface, supports multi-terminal access, and adopts holographic projection and brain-computer interface interaction technology. Users control the device status information displayed by holographic projection through brain thinking instructions. The improved early warning level formula L = h(P) × (1 + δ) divides the early warning level. h(P) is a function based on the probability of failure P, and δ is an adjustment coefficient considering the user interaction experience and information importance.

2. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: It also includes a device health assessment module that uses an improved device health index formula Calculate the device health index, where n is the number of parameters involved in calculating the device health index, and w i is the weight of the i-th parameter, x i is the actual measured value of the i-th parameter, ∈ i It is a dynamic correction coefficient for each parameter that changes with the equipment operating environment and time. The index is updated in real time with the help of synchronous computing technology based on quantum entanglement. The health level is divided according to the index to provide a basis for equipment maintenance, and the historical changes in health status are recorded using blockchain technology.

3. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: It also includes an intelligent maintenance decision module, which combines the equipment failure probability P, health index H and the real-time load condition L of the equipment load The improved maintenance benefit evaluation formula is B = m × P × (1-H) × (1 + ζ × L load )+n×C, where ζ is the load influence coefficient. Then, the maintenance strategy is selected according to the benefit through the algorithm optimization combining genetic and simulated annealing.

4. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: The sensors in the data acquisition layer have intelligent self-diagnosis function, and the improved sensor performance evaluation formula Evaluate its own performance in real time, with p, q, and r as coefficients, where r is the coefficient of photon signal change, ΔV is the voltage change, ΔI is the current change, ΔP is the photon signal change, and Δt is the time interval. When performance degrades, the sensor automatically adjusts the acquisition frequency and range, and sends maintenance reminders to the system through quantum encryption communication, while using the built-in micro-repair device for self-repair.

5. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: The network transport layer adopts the software-defined network (SDN) technology and the software-defined wide area network (SD-WAN) fusion architecture. The network topology is adjusted according to the network traffic, signal strength, device importance and data real-time requirements through the SDN controller and SD-WAN orchestrator. The improved network optimization formula is: T throughput is the network throughput, T delay is the network delay, η is the performance improvement coefficient brought by the fusion architecture, r and s are coefficients, and quantum repeater technology is introduced to extend the transmission distance of quantum key distribution.

6. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: The data processing layer uses reinforcement learning algorithm combined with quantum annealing algorithm to optimize the fault prediction model, and improves the reward function R learn =t×(1-P error )+u×E×(1+θ) motivates model learning, P error is the error probability of fault prediction, θ is the optimization coefficient brought by the quantum annealing algorithm, and the federated learning technology is used to combine the data of multiple power transmission and transformation systems for model training without sharing the original data.

7. The intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to claim 1 is characterized in that: The warning display layer adopts mixed reality MR technology. Users can immersively experience the operating status of power transmission and transformation equipment through MR devices. The improved AR positioning formula A=f(x, y, z)×(1+λ) is used to locate the equipment position. λ is the positioning accuracy improvement coefficient brought by MR technology. At the same time, the system uses artificial intelligence algorithms to provide users with personalized information display and interaction methods based on the user's operating habits and historical data.

8. A method for applying the intelligent power transmission and transformation monitoring and fault warning system based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The following steps are involved: Data collection steps: Sensors in the data collection layer collect real-time operating data from power transmission and transformation equipment, including newly added photon signals. Effective data is filtered using improved formulas. Sensors self-diagnose and attempt self-repair, and quantum encryption communication ensures data security. Data transmission steps: The network transmission layer uses multi-hybrid networking, quantum key distribution, and blockchain technology, combined with SDN and SD-WAN architectures, and uses improved formulas to optimize transmission performance and evaluate reliability; Data processing steps: A three-layer architecture is used, assisted by quantum neural networks and knowledge graphs. Improved formulas are used to extract features and predict probabilities. The model is optimized by combining it with the quantum annealing algorithm, and federated learning improves versatility. Warning display steps: The warning display layer uses MR technology and brain-computer interface interaction, divides warning levels according to the improved formula, and artificial intelligence provides a personalized experience.

9. The intelligent power transmission and transformation monitoring and fault warning method according to claim 8, characterized in that: It also includes an equipment health assessment step, which uses an improved formula to calculate the equipment health index, synchronizes quantum entanglement updates, records history on the blockchain, and divides health levels to provide a reference for maintenance.

10. The intelligent power transmission and transformation monitoring and fault warning method according to claim 8, characterized in that: It also includes intelligent maintenance decision-making steps, combining failure probability, health index and load conditions, using improved formulas to evaluate strategy benefits, combining genetic and simulated annealing algorithms to select the optimal strategy and optimize resource allocation.

Images