Real-time monitoring and guiding system for operation and maintenance personnel of wind power plant and use method
Through the end-edge-cloud collaborative architecture and cutting-edge technology, multi-source data fusion, professional knowledge management and security problems in wind farm operation and maintenance are solved, and the automation, refined management and data security sharing of wind farms are realized, reducing operation Maintenance costs and improve power generation efficiency.
Patent Information
- Application Number
- CN202411202669.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
AI Technical Summary
There are problems in wind farm operation and maintenance, which are difficult to integrate heterogeneous data, difficult to systematically manage wind power professional knowledge, single human-computer interaction methods, and difficult to ensure safety and privacy, resulting in low maintenance efficiency, slow fault response, and high operation and maintenance costs.
Adopting an operation and maintenance architecture with end-edge-cloud collaboration, the key components of wind turbines are realized through AR glasses, multi-modal sensors, drones, edge computing devices and central servers, combined with the Internet of Things, artificial intelligence, and blockchain technology. Real-time monitoring and health assessment, build fault diagnosis, residual life prediction and risk assessment models to ensure safe sharing of data.
It realizes automation, refinement and visualization of the full life cycle management of wind farms, reduces operation and maintenance costs, improves power generation efficiency and data security, reduces labor waste and spare parts backlog, and extends the service life of the equipment.
Smart Images

Figure CN119090488A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of wind power generation equipment operation and maintenance, and in particular relates to a real-time monitoring and guidance system for wind farm operation and maintenance personnel and a use method thereof. Background Art
[0002] With the rapid development of the global wind power industry, the scale of wind farms continues to expand, and operation and maintenance management faces many challenges such as frequent equipment failures, high labor costs, and low data utilization. Traditional wind farm operation and maintenance mainly rely on manual regular inspections and post-maintenance, which have problems such as low maintenance efficiency, slow fault response, and high operation and maintenance costs. However, the existing technology still has the following shortcomings in practical applications: First, it is difficult to effectively integrate multi-source heterogeneous data, and the equipment, environment, and operation data within the wind farm have not yet been interconnected; second, it is difficult to systematically manage wind power expertise, and there is a lack of fault diagnosis and predictive maintenance experience converted into a computable knowledge base; third, the human-computer interaction method is single, and it is difficult to achieve coordinated optimization of operation and maintenance personnel and intelligent systems; fourth, security and privacy are difficult to guarantee, and multi-party data sharing faces the risk of data theft and tampering.
[0003] The Chinese patent publication number is CN106295992A, and the name is a patent application for a wind turbine status monitoring and operation and maintenance guidance system based on holographic images, which includes N field workstations, a monitoring center workstation and a communication network group, where N is a natural number and N≥1. The field workstation set up at the on-site operation and maintenance end sends the status information of the wind turbine and the holographic image of the operation and maintenance site to the monitoring center workstation set up at the remote operation and maintenance end. The monitoring center workstation generates holographic operation and maintenance guidance information and sends the guidance information back to the field workstation to guide the on-site operation and maintenance personnel to perform on-site operation and maintenance. The system also includes information exchange between N field workstations. Although this patent application can monitor the status of wind turbines and provide operation and maintenance guidance, the data type collected on the end side is single, and there is no edge side involved in the calculation. It is difficult to monitor in real time when a large amount of data is collected on the end side. Summary of the invention
[0004] The purpose of the present invention is to provide a real-time monitoring and guidance system for wind farm operation and maintenance personnel and a method of use. By constructing an end-edge-cloud collaborative operation and maintenance architecture, the automation, refinement and visualization of the full life cycle management of the wind farm are realized. The real-time monitoring and health assessment of key components of wind turbines through collaborative computing can reduce the operation and maintenance costs of wind farms.
[0005] To achieve the above object, the technical solution adopted by the present invention is:
[0006] A real-time monitoring and guidance system for wind farm operation and maintenance personnel, comprising terminal-side devices, edge-side devices and cloud-side devices; the terminal-side devices communicate with cloud-side devices through edge-side devices; the terminal-side devices include AR glasses, multimodal sensors and drones, the edge-side devices include edge computing devices, and the cloud-side devices include a central server; the AR glasses communicate with the multimodal sensors, drones, edge computing devices and central servers respectively; wherein the edge computing device includes an industrial computer for preprocessing, local modeling and real-time decision-making of collected data; the industrial computer includes a data acquisition module, a data preprocessing module, a local diagnosis module and an AR interaction engine; the central server includes a GPU cluster, performs cloud storage through a knowledge graph module, and performs cloud training through a machine learning module.
[0007] Optionally, the AR glasses are equipped with a built-in camera, microphone, speaker, display screen and brain-computer interface sensor; the multimodal sensor is installed on the key components of the wind turbine to collect vibration, oil quality, temperature and humidity information of the key components; the drone is equipped with a camera and an infrared thermal imager to detect the surface and thermal defects of the wind turbine.
[0008] Optionally, the data acquisition module supports industrial bus protocols including PLC and MODBUS and Internet of Things protocols including MQTT and COAP, and is used to collect multi-source heterogeneous data.
[0009] Optionally, the data preprocessing module is used to perform data processing including data noise reduction, feature extraction and data compression.
[0010] Optionally, the machine learning module is used to build fault diagnosis, remaining life prediction and risk assessment models.
[0011] Optionally, the knowledge graph module uses an ontology construction method to fuse structured data and unstructured data to construct a wind turbine and operation and maintenance knowledge graph.
[0012] Optionally, the cloud side also includes a blockchain module, which uses Hyperledger Fabric to deploy smart contracts to achieve operation and maintenance data storage, audit tracking and multi-party trust collaboration.
[0013] Optionally, the AR glasses are communicatively connected to an eeg helmet, an EEG acquisition module and a vibration vest.
[0014] Optionally, the AR interaction engine adopts the unity3d game engine.
[0015] The method for using the real-time monitoring and guidance system for wind farm operation and maintenance personnel comprises the following steps:
[0016] Realize real-time monitoring and initial fault screening of key components through end-side devices;
[0017] The edge computing device on the side device uses an improved Rul prediction algorithm, gated recurrent units and multi-task learning to predict the remaining life of key components;
[0018] The deep learning model is trained through the machine learning module of the cloud-side device, and a multi-scale one-dimensional convolutional neural network is used to integrate time domain and frequency domain features to analyze the degradation patterns in timing signals including vibration.
[0019] Compared with the prior art, the present invention has the following beneficial effects:
[0020] A real-time monitoring and guidance system for wind farm operation and maintenance personnel of the present invention integrates cutting-edge technologies of the Internet of Things, artificial intelligence, AR, and blockchain, and constructs an end-edge-cloud collaborative operation and maintenance architecture from the aspects of multimodal data acquisition, intelligent diagnosis and prediction, AR interactive guidance, and federated learning optimization. It realizes the automation, refinement and visualization of the entire life cycle management of wind farms, and can improve the intelligence level of wind farm operation and maintenance.
[0021] Through real-time monitoring and health assessment of key components of wind turbines, the system can timely detect early signs of failure and reduce the occurrence of serious failures; through intelligent scheduling and optimization of operation and maintenance tasks and resources, the system can reduce manpower waste and spare parts backlog, extend the service life of equipment, and thus significantly reduce maintenance costs and spare parts costs. The present invention can reduce the operation and maintenance costs of wind farms.
[0022] The present invention can improve the power generation efficiency of wind farms. By tracking and analyzing the performance degradation trend of the units, the system can optimize the control strategy of wind turbines and maximize the power generation under the premise of ensuring the safety of the units; by comparing and mining the operating data between different wind farms, the system can identify the key factors affecting the power generation efficiency and provide a basis for the refined management and technical transformation of wind farms.
[0023] The present invention can ensure the secure sharing of multi-party data in wind farms. The present invention uses blockchain to build a trusted data sharing network in the wind power industry, which not only ensures that the data cannot be tampered with and can be traced, but also realizes data privacy protection and authority management through cryptographic technology, and promotes collaborative innovation among wind power equipment manufacturing, operation and maintenance services, technical supervision, and financial insurance.
[0024] The present invention can provide a demonstration for the intelligent development of the wind power industry. Aiming at the pain points in wind farm management, the present invention proposes a set of solutions with advanced technology, reasonable architecture and practical application, which has important demonstration significance and promotion value for promoting the digitalization, networking and intelligent development of the wind power industry and accelerating the intelligent upgrading of the energy industry.
[0025] The real-time monitoring and guidance system for wind farm operation and maintenance personnel of the present invention has significant technical advantages and application value in improving the level of intelligent operation and maintenance of wind farms, reducing operation and maintenance costs, improving power generation efficiency, and ensuring data security, and is of great significance for promoting the high-quality development of the wind power industry. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The drawings described herein are for explanation purposes only and are not intended to limit the scope of the present invention in any way. In addition, the shapes and proportional dimensions of the components in the drawings are only for illustration purposes to help understand the present invention, and are not intended to specifically limit the shapes and proportional dimensions of the components of the present invention. In the drawings:
[0027] Figure 1 This is an architecture diagram of the real-time monitoring and guidance system for wind farm operation and maintenance personnel of the present invention;
[0028] Figure 2 It is a schematic diagram of the arrangement of the vibration sensor of the present invention;
[0029] Figure 3 This is a diagram of the end-edge-cloud collaborative diagnosis architecture of the present invention;
[0030] Figure 4 This is the wind power field ontology definition diagram of the present invention;
[0031] Figure 5 This is a diagram of the blockchain architecture of the present invention;
[0032] Figure 6 This is a schematic diagram of blockchain storage optimization of the present invention. DETAILED DESCRIPTION
[0033] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work should fall within the scope of protection of the present invention.
[0034] It should be noted that when an element is referred to as being "disposed on" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only embodiment.
[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.
[0036] The present invention is described in detail below with reference to the accompanying drawings.
[0037] like Figure 1 As shown, the real-time monitoring and guidance system for wind farm operation and maintenance personnel of the present invention includes terminal-side equipment, edge-side equipment and cloud-side equipment; the terminal-side equipment communicates with the cloud-side equipment through the edge-side equipment.
[0038] The terminal devices include AR glasses, multimodal sensors and drones, the edge devices include edge computing devices, and the cloud side devices include central servers.
[0039] The AR glasses have built-in cameras, microphones, speakers, display screens and brain-computer interface sensors; the AR glasses communicate with multimodal sensors, drones, edge computing devices and central servers respectively.
[0040] The multimodal sensor is installed on the key components of the wind turbine generator set to collect vibration, oil quality, temperature and humidity information of the key components; the drone is equipped with a camera and an infrared thermal imager to detect the surface and thermal defects of the wind turbine generator set; the edge computing device includes an industrial computer, which is used to preprocess the collected data, perform local modeling and real-time decision-making; the industrial computer includes a data acquisition module, a data preprocessing module, a local diagnosis module and an AR interaction engine.
[0041] The data acquisition module supports industrial bus protocols including PLC and MODBUS and Internet of Things protocols including MQTT and COAP, and is used to collect multi-source heterogeneous data.
[0042] The data preprocessing module uses Kalman filtering or wavelet transform algorithm to process data.
[0043] The AR interaction engine uses the unity3d game engine. The unity3d game engine of the AR interaction engine supports 3d model loading, animation control, physical collision and gesture interaction.
[0044] The central server includes a GPU cluster, providing large-scale data storage, deep learning training and remote expert guidance services.
[0045] The machine learning module uses a support vector machine algorithm or a random forest algorithm or a recurrent neural network algorithm or a long short-term memory network algorithm to build a fault diagnosis, remaining life prediction and risk assessment model.
[0046] The knowledge graph module uses an ontology construction method to fuse structured data and unstructured data to construct a wind turbine and operation and maintenance knowledge graph. The structured data includes equipment files, fault cases, and maintenance manuals.
[0047] The cloud side also includes a blockchain module, which uses Hyperledger Fabric to deploy smart contracts to achieve operation and maintenance data storage, audit tracking and multi-party trust collaboration.
[0048] The AR glasses are connected to the eeg helmet, EEG acquisition module and vibration vest.
[0049] When a wind farm operation and maintenance personnel uses a real-time monitoring and guidance system, an intelligent fault diagnosis method using device-edge-cloud collaboration is used:
[0050] The AR glasses, multimodal sensors and drones on the end devices all use the STM32 MCU and the tensorflowlite learning framework to achieve real-time monitoring of key components and preliminary fault screening;
[0051] The edge computing device of the side equipment predicts the remaining life of key components through an improved Rul prediction algorithm, using gated recurrent units and multi-task learning;
[0052] The machine learning module of the cloud-side device trains a deep learning model, uses a multi-scale one-dimensional convolutional neural network, integrates time domain and frequency domain features, and analyzes the degradation patterns in timing signals including vibrations.
[0053] Adopting the AR remote collaboration method of brain-computer fusion, the EEG signals of the operation and maintenance personnel are collected through AR glasses, and the EEG is collected through the EEG helmet and EEG acquisition module. The EEG signal classification model is constructed, the common space pattern algorithm is used to extract features, and the support vector machine is used to distinguish between the concentration state and the fatigue state; according to the EEG state, the complexity and presentation method of the AR glasses guidance content are adaptively adjusted, and tactile feedback is provided through the vibration vest to optimize the human-computer interaction experience;
[0054] The central server adopts a task planning and resource optimization method driven by reinforcement learning, applies a multi-agent reinforcement learning algorithm, models the status of wind turbines, weather forecasts, and spare parts inventory information as environmental states, and models the generated operation and maintenance task sequences and personnel and spare parts resource allocation as actions. The reward function is used to balance the power generation benefits and operation and maintenance costs to solve the optimal strategy; heuristic rules and constraints are designed, and the learning model of the machine learning module is embedded to achieve adaptive optimization of the operation and maintenance strategy.
[0055] Example 1
[0056] This embodiment provides a real-time monitoring and guidance system for wind farm operation and maintenance personnel, such as Figure 1 As shown, the system includes: AR glasses, multimodal sensors, drones, edge computing devices and central servers.
[0057] AR glasses have built-in cameras, microphones, speakers, displays and brain-computer interface sensors.
[0058] The camera is used to capture the first-person perspective video of the operation and maintenance personnel for real-time viewing by remote experts.
[0059] Microphones and speakers are used to enable voice communication between operation and maintenance personnel and remote experts.
[0060] The display screen is used to superimpose AR information to achieve information enhancement. The brain-computer interface sensor is used to collect the EEG signals of the operation and maintenance personnel to achieve human-computer interaction based on EEG.
[0061] Multimodal sensors are installed on key components of wind turbines, including gearboxes, generators, and converters, to collect vibration, oil quality, temperature, and humidity information from key components to achieve comprehensive perception of equipment status. Taking the gearbox as an example, the vibration sensor layout of the multimodal sensor is as follows: Figure 2 As shown, the sensor sampling frequency f sa satisfy:
[0062] f≥2.56×f
[0063] max
[0064] Among them, f max is the highest order frequency of the gear meshing frequency.
[0065] The drone is equipped with a camera and an infrared thermal imager. The camera is used to detect surface defects of wind turbines, such as blade cracks and rust; the infrared thermal imager is used to detect thermal defects of key components of wind turbines, such as abnormal temperature rise of the gearbox.
[0066] Edge computing devices include industrial computers, data acquisition modules, data preprocessing modules, local diagnostic models, and AR interaction engines. The data acquisition module is responsible for the collection and synchronization of multi-source heterogeneous data, and supports a variety of industrial bus protocols and IoT protocols. The data preprocessing module uses Kalman filtering and wavelet transform algorithms to reduce noise, extract features, and compress the collected data. The local diagnostic model uses the classic machine learning algorithm of support vector machines to perform preliminary diagnosis of common faults. The AR interaction engine uses the mature game engine of unity3d, which is responsible for AR scene construction and human-computer interaction control.
[0067] The central server includes a GPU cluster, providing cloud storage, cloud training, and cloud services. Cloud storage is responsible for the persistent storage management of massive historical data and knowledge bases. Cloud training is responsible for offline training of deep learning models, such as Figure 3 The end-edge-cloud collaborative diagnosis architecture shown in the figure analyzes the degradation rules in time series signals including vibration, and continuously optimizes fault diagnosis and life prediction performance. The cloud service is responsible for knowledge graph query, AR remote collaboration and global optimization, providing intelligent enhancement for the edge. The knowledge graph adopts the ontology construction method to define the core concepts of components, faults, symptoms, causes, solutions, and the logical relationships between concepts, such as Figure 4 shown.
[0068] The workflow of the system is as follows: First, multimodal sensors and drones collect wind turbine operation data in real time and aggregate it to the edge computing device through the data acquisition module. Then, the data preprocessing module preprocesses the collected data and inputs it into the local diagnostic model for preliminary diagnosis. When the local diagnostic model diagnoses a fault, the AR interaction engine pushes fault information and disposal suggestions to the AR glasses. Next, the operation and maintenance personnel wear AR glasses, check the faulty parts on site, and establish an audio and video connection with the remote expert. The remote expert uses AR glasses to view the on-site situation, retrieve knowledge graphs and historical cases, and guide on-site disposal. Finally, the edge computing device uploads the on-site data to the central server for big data analysis and model optimization, and feeds back the analysis results to the operation and maintenance personnel.
[0069] This embodiment uses multimodal sensors to achieve all-round state perception of wind turbines, achieves low latency and high reliability of data processing through end-edge-cloud layered deployment, and realizes intelligent operation and maintenance decision-making in human-machine collaboration through AR interaction technology, ultimately significantly improving the operation and maintenance efficiency, safety, and economy of wind farms.
[0070] Example 2 Based on Example 1, this embodiment further adopts reinforcement learning technology to optimize global resource scheduling. The multi-agent reinforcement learning algorithm proximal policy optimization (PPO) is applied in the machine learning module, and the wind turbine status, task list, personnel skills, and spare parts inventory are modeled as environmental state S, and different task allocation schemes and spare parts procurement strategies are modeled as actions A. The task completion rate, personnel load, and spare parts cost indicators are balanced through the reward function R. The PPO algorithm alternates between policy evaluation and policy improvement, continuously updates the policy network of the agent, and obtains the optimal scheduling strategy. The objective function of the PPO algorithm is as follows:
[0071] Among them, r t (θ) is the probability ratio, is the advantage function, is a hyperparameter.
[0072] When training reinforcement learning models, heterogeneous features are uniformly mapped to the semantic space through the embedding layer to enhance generalization; the solution space is constrained by heuristic rules to accelerate convergence; and the robustness of the strategy is improved through a large number of simulation experiments.
[0073] This embodiment achieves global dynamic scheduling from equipment to system through end-edge-cloud collaborative optimization, thereby improving the overall operation and maintenance efficiency and economy of the wind farm.
[0074] Example 3
[0075] In this embodiment, the cloud side also includes a blockchain module. Based on Example 1, blockchain technology is further introduced to establish a trusted data chain and value chain covering the entire life cycle of wind power. Design a consortium chain architecture, such as Figure 5 As shown in the figure, the equipment parameters, operating conditions, and health status data of the production, installation and commissioning, preventive maintenance, fault diagnosis, life prediction, and spare parts management links are stored on the blockchain module to achieve full data traceability. The responsibility definition and benefit distribution between links are automatically triggered and executed through smart contracts to establish a new collaboration mechanism.
[0076] The blockchain architecture is oriented to the complex system of wind farms, and a lightweight consensus mechanism is designed to ensure the real-time performance of the business while taking into account the trusted integration of distributed nodes. For multi-source heterogeneous data, a privacy protection method based on zero-knowledge proof is proposed to avoid the leakage of sensitive information while sharing modeling, and the proof process meets the completeness, reliability and zero-knowledge. For massive time series data, a hybrid storage optimization method based on merkle tree and bloom filter is proposed to balance data credibility and space efficiency. The merkle tree ensures data integrity through encrypted hashing, and the bloom filter accelerates indexing speed through probabilistic query, such as Figure 6 shown.
[0077] This embodiment uses blockchain technology to establish a collaborative innovation network for the entire life cycle of wind power, break data silos, stimulate data value, and accelerate the digital transformation of the wind power industry.
[0078] Unless otherwise specified, the device elements involved in the above embodiments are all conventional device elements, and the structural settings, working modes or control modes involved are all conventional settings, working modes or control modes in the art unless otherwise specified.
[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in the field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.
Claims
1. A real-time monitoring and guidance system for wind farm operation and maintenance personnel, characterized in that: It includes terminal devices, edge devices and cloud devices; the terminal devices communicate with the cloud devices through the edge devices; the terminal devices include AR glasses, multimodal sensors and drones, the edge devices include edge computing devices, and the cloud devices include a central server; the AR glasses communicate with the multimodal sensors, drones, edge computing devices and central servers respectively; wherein the edge computing device includes an industrial computer for preprocessing, local modeling and real-time decision-making of the collected data; the industrial computer includes a data acquisition module, a data preprocessing module, a local diagnosis module and an AR interaction engine; the central server includes a GPU cluster, performs cloud storage through a knowledge graph module, and performs cloud training through a machine learning module.
2. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The AR glasses are equipped with a camera, a microphone, a speaker, a display screen and a brain-computer interface sensor; the multimodal sensor is installed on the key components of the wind turbine to collect vibration, oil quality, temperature and humidity information of the key components; the drone is equipped with a camera and an infrared thermal imager to detect the surface and thermal defects of the wind turbine.
3. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The data acquisition module supports industrial bus protocols including PLC and MODBUS and Internet of Things protocols including MQTT and COAP, and is used to collect multi-source heterogeneous data.
4. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The data preprocessing module is used to perform data processing including data noise reduction, feature extraction and data compression.
5. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The machine learning module is used to build fault diagnosis, remaining life prediction and risk assessment models.
6. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The knowledge graph module adopts an ontology construction method to fuse structured data and unstructured data to construct a wind turbine and operation and maintenance knowledge graph.
7. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The cloud side also includes a blockchain module, which uses Hyperledger Fabric to deploy smart contracts to achieve operation and maintenance data storage, audit tracking and multi-party trust collaboration.
8. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The AR glasses are communicatively connected to an eeg helmet, an EEG acquisition module and a vibration vest.
9. A real-time monitoring and guidance system for wind farm operation and maintenance personnel according to claim 1, characterized in that: The AR interaction engine adopts the unity3d game engine.
10. A method for using a real-time monitoring and guidance system for wind farm operation and maintenance personnel according to any one of claims 1 to 9, characterized in that: The following steps are involved: Realize real-time monitoring and initial fault screening of key components through end-side devices; The edge computing device on the side device uses an improved Rul prediction algorithm, gated recurrent units and multi-task learning to predict the remaining life of key components; The deep learning model is trained through the machine learning module of the cloud-side device, and a multi-scale one-dimensional convolutional neural network is used to integrate time domain and frequency domain features to analyze the degradation patterns in timing signals including vibration.
Citation Information
Patent Citations
State monitoring and operation and maintenance guiding system of wind turbine generator set based on holographic image
CN106295992A
