54 results about "Adaptive learning algorithm" patented technology

The invention relates to the technical field of data processing, and discloses a multi-protocol fusion Internet of Things equipment intelligent gateway data conversion method and system. The method comprises the following steps: collecting a multi-protocol equipment data packet, and extracting protocol features to construct a vector library; protocol types are identified based on the vector library, data are analyzed, and a data object set containing semantic tags is constructed; semantic correlation is analyzed through an adaptive learning algorithm, and a dynamic protocol semantic mapping matrix is established; converting the data into a standard format according to the mapping matrix and recording a matching degree to form a target data pool; and extracting fusion data from the data pool, recoding according to a target protocol format, and outputting a data frame. The problem that an existing multi-protocol fusion data conversion method lacks protocol semantic understanding and self-adaptive learning ability is solved, and semantic consistency and conversion quality of data conversion among multi-protocol equipment are improved.

The invention provides a rail transit equipment fault prediction method and system, and the system comprises a data perception and fusion layer which is used for collecting and fusing multi-source heterogeneous data; the digital twinning and intelligent prediction layer is used for realizing accurate prediction and early fault early warning of the health state of the equipment by constructing a lightweight digital twinning model of the equipment and combining a space-time diagram attention network and a self-adaptive learning algorithm; the interpretable analysis and decision support layer is used for analyzing the root cause of the prediction result and providing visual analysis; and the maintenance linkage and execution layer is used for automatically generating a maintenance strategy and scheduling resources according to a prediction result, relates to the technical field of rail transit operation and maintenance, and overcomes the defects of single data, static model, weak early warning capability, poor interpretability and disjunction between prediction and maintenance in the prior art. And the full-life-cycle, self-adaptive and intelligent management of the fault prediction of the rail transit equipment is realized.

The invention provides a multi-device automatic switching method and system for an intelligent mouse, and the method comprises the steps: collecting the connection signal strength of a plurality of external computing devices through a built-in wireless signal receiver of the intelligent mouse, and constructing a dynamically updated signal strength matrix; calculating the optimal probability of switching the mouse to each device by combining the device feature vector, the spatial position relationship, the use scene similarity and the historical use frequency; constructing a switching cost function based on a dynamic programming algorithm, and solving an optimal equipment switching path; through a switching pre-connection mechanism, a self-adaptive learning algorithm, a switching rollback mechanism and a mistaken touch prevention mechanism, efficient, stable and low-delay automatic switching of the intelligent mouse is realized. According to the method, the connection strategy can be dynamically adjusted according to the real-time scene, the mouse parameter configuration is optimized, cross-device switching is more intelligent and seamlessly connected, and the user operation experience is improved.

The invention provides an employee health risk monitoring method and system based on big data, and relates to the technical field of health management and data analysis, and the method comprises the steps: S1, collecting the multi-modal health data of an employee, including but not limited to physiological data, behavior data, working environment data, social interaction data and genome data, and S2, fusing and analyzing the collected multi-modal health data by adopting an integrated neural network model and an adaptive learning algorithm. According to the big data-based staff health risk monitoring method and system, through the combination of the integrated neural network and the deep causal inference model, the multi-modal health data of the staff can be deeply analyzed, and the complex causal relationship between the health data can be effectively identified. Through the dynamic analysis of the historical health data, the current health state and the working environment of the employees, the model can achieve the precise health risk prediction, and provides personalized health intervention suggestions according to the individual differences of the employees.

The invention relates to the technical field of power grid information system fault positioning, and particularly discloses a power grid information system fault positioning system based on adaptive learning, and the system comprises a data collection module which is used for collecting electrical quantity data and state quantity data in the operation process of a power grid; the data preprocessing module is connected with the data acquisition module and is used for carrying out preprocessing operations such as filtering, denoising and normalization on the acquired data and removing interference and invalid information in the data; and the fault feature extraction module is connected with the data preprocessing module and is used for extracting feature parameters related to the power grid fault based on the preprocessed data. According to the power grid information system fault positioning system based on adaptive learning, a dynamic multi-scale adaptive learning algorithm is fused with reinforcement learning and transfer learning mechanisms, model parameters and structures are dynamically adjusted according to the real-time operation state of a power grid, similar scene experience is migrated, and the fault positioning accuracy and adaptability are remarkably improved.

The invention relates to the technical field of power grid exception handling, and discloses a power grid exception event handling method and system based on a knowledge graph. The method comprises the following steps: collecting time sequence data flow and space coordinate information of a power grid abnormal event in real time through multi-source sensing equipment, and fusing equipment operation parameters to construct a dynamic event data pool; performing graph structure conversion on the dynamic event data pool based on a knowledge graph topological connection relationship, calculating event node propagation path intensity and generating an event propagation network model; key abnormal indexes are separated out from the model by adopting a multi-modal feature extraction technology, risk probability calculation is completed in combination with an adaptive learning algorithm, and an abnormal risk distribution diagram is output; and classifying event levels according to the graph, and automatically generating a processing instruction sequence. According to the method, omnibearing data perception and accurate analysis of the abnormal events of the power grid are realized, an event propagation rule is clearly presented, risk assessment is enabled to be closer to an actual operation state, and accurate guidance is provided for abnormal disposal.

The invention relates to the technical field of artificial intelligence, in particular to an energy AI agent decision-making method and system based on adaptive learning and loopback control. The method comprises the following specific steps: collecting energy data and environment data in real time, and performing data fusion processing; generating an original strategy of the energy AI intelligent agent according to the fused data based on an adaptive learning algorithm; correcting the original strategy in real time based on a preset loopback loss function, and outputting a preliminary strategy instruction; receiving the preliminary strategy instruction, and optimizing the preliminary strategy instruction to generate a final execution instruction under the condition of meeting physical constraints and security constraints of the system; and executing the final execution instruction. By adopting the method, the self-adaptive optimization capability can be realized, the execution safety can be ensured, and the method has the characteristic of supporting continuous optimization.

The invention discloses an intelligent power consumption management system for Internet of Things equipment, which relates to the technical field of intelligent power consumption management systems and comprises a behavior acquisition module, a dynamic adjustment module, an energy consumption optimization module, an energy prediction module, an energy supply switching module and a system feedback module. The behavior acquisition module is used for monitoring the running state of equipment to obtain equipment activity feature data; the dynamic adjusting module is used for processing the equipment activity characteristic data by adopting a self-adaptive learning algorithm to obtain a dynamic dormancy threshold parameter; the energy consumption optimization module is used for applying the dynamic dormancy threshold parameter by adopting a multi-objective optimization method to obtain a power consumption distribution scheme of each functional module; the energy prediction module is used for analyzing the power consumption distribution scheme based on a neural network model in combination with environmental parameters to obtain an energy supply prediction result; and the energy supply switching module is used for responding to the energy supply prediction result by adopting a priority strategy.

The invention discloses a full-life-cycle health management method for enteritis patients, a medium and equipment, and the method comprises the steps: extracting a key lever factor through a lever point recognition algorithm based on obtained full-life-cycle health data, and generating a lever point intervention priority sequence; generating an individualized toughness development path plan in combination with a calculation result of the toughness evaluation model, and designing a structured self-verification experiment scheme according to the individualized toughness development path plan; continuously updating the leverage point recognition algorithm and the toughness evaluation model by using an adaptive learning algorithm according to a scheme execution result until the optimal parameter configuration and the individualized health management strategy are locked; and when the sorting stability of the key lever factors exceeds the standard, starting a grading response mechanism to generate a precise intervention scheme, and finally outputting a full-life-cycle health management comprehensive scheme. According to the method, a dynamic optimization closed loop is constructed, so that a management strategy is converted from static matching to dynamic self-adaption, and the defects of an existing method in the aspects of intervention target spot recognition, adaptive capacity quantification and strategy continuous optimization are overcome.

The invention relates to the technical field of green building environment monitoring, and discloses a green building environment monitoring system and method and a storage medium. The method comprises the steps that environmental parameters such as thermodynamic parameters, humidity parameters and gas concentration parameters are continuously collected through intelligent sensing nodes at multiple positions in a green building; the environment parameters are transmitted to a central processing unit, and the central processing unit combines a pre-stored environment standard value and a real-time data stream and generates an environment control command by adopting a self-adaptive learning algorithm; the environment execution device carries out an environment regulation activity according to the command; and monitoring and adjusting an activity execution sequence in real time, calculating a performance evaluation index, generating a normal or abnormal performance state signal, and automatically triggering an alarm process when the performance state signal is abnormal. According to the method, a complete environment management and control closed loop is constructed, all-directional dynamic monitoring and accurate adjustment of the environment of the green building are achieved, the core requirements for environment protection and comfort of the green building are met, and it is guaranteed that the internal environment of the building is in a proper state.

The invention discloses a flight simulation training auxiliary system and method based on intelligent co-pilot, and the system comprises a data collection module which is used for collecting flight data and carrying out the operation monitoring of a college; the voice interaction interface is used for multi-mode state analysis voice interaction; the student model module is used for skill level evaluation and learning style identification; the emotion perception module is used for flight experience identification and risk prediction analysis; the personalized training module is used for training process monitoring, training result analysis and personalized training adjustment; and the decision engine module is used for deeply reinforcing a learning model and assisting a strategy generator. And intelligent and personalized auxiliary support is provided for pilot training. Through real-time data analysis and an adaptive learning algorithm, functions and behaviors of a real copilot are simulated, and targeted guidance is provided for flight trainees. And a complete training ecosystem is formed. And the flexibility and expandability of the system are ensured, and each functional component can be independently optimized and upgraded.

The invention relates to the technical field of vehicle engineering, and discloses a vehicle-mounted magneto-rheological active suspension damping matching control system which comprises a sensing module, a central control module, a magneto-rheological execution module and a power supply module. The signal output end of the central control module is electrically connected with the signal input end of the magneto-rheological execution module, and the power supply module is electrically connected with the sensing module, the central control module and the magneto-rheological execution module and provides working electric energy. All-dimensional parameters such as road surface states, vehicle body postures and vehicle operation are collected through the multi-source sensing module, signal interference and measurement errors are eliminated through weighted fusion processing of the central control module, and accurate decision of damping adjustment is achieved in combination with a pre-stored damping matching strategy library and a self-adaptive learning algorithm. And in cooperation with the stepless regulation characteristic of the magneto-rheological execution module, the driving state change can be followed in real time to dynamically optimize the damping force.

The embodiment of the invention discloses a control method and device for linkage of an air purifier and outdoor air quality information, and the scheme can comprise the steps that the outdoor air quality information is obtained in real time, and the outdoor air quality information at least comprises the outdoor air quality index AQI and the PM2.5 concentration; collecting indoor air quality parameters in real time, wherein the indoor air quality parameters at least comprise indoor PM2.5 concentration, VOC concentration and temperature; based on the outdoor air quality information and the indoor air quality parameters, an air purification demand index AQDI is calculated; the AQDI is compared with a preset first threshold value and a preset second threshold value, and the operation mode of the air purifier is automatically switched according to the comparison result; wherein the numerical value of the first threshold value is larger than that of the second threshold value, and the operation modes comprise an inner circulation mode, an outer circulation mode and a pre-purification mode; historical operation data and user feedback are recorded, and weight parameters in AQDI calculation, the first threshold value and the second threshold value are dynamically adjusted through an adaptive learning algorithm.

The invention provides a self-adaptive early warning system for overload of electrical equipment of a thermal power plant. The self-adaptive early warning system comprises a data acquisition and fusion module, a dynamic threshold calculation module, a risk probability evaluation module, a graded early warning decision module and a feedback learning and model updating module. The data acquisition and fusion module acquires multi-dimensional operation parameters of the electrical equipment in real time and forms an equipment state vector; the dynamic threshold calculation module generates a dynamic early warning threshold through an adaptive learning algorithm based on historical data and real-time working conditions; the risk probability evaluation module calculates a quantitative risk probability in combination with the real-time parameter deviation and the equipment health degree; the grading early warning decision module executes grading response from visual prompt to load control according to the risk grade; and the feedback learning module continuously optimizes algorithm parameters. According to the method, the limitation of traditional fixed threshold early warning is broken through, dynamic threshold self-adaption, accurate risk quantification, early warning grading response and continuous model optimization are realized, the early warning accuracy is remarkably improved, and the false alarm rate is effectively reduced.

The invention relates to the technical field of intelligent buildings, and discloses intelligent control equipment for a central air-conditioning system, and the equipment comprises a distributed sensor network which is used for collecting indoor and outdoor environment data in real time; the low-power-consumption edge computing unit is connected with the distributed sensor network and is used for primarily processing the environment data; the environment self-adaptive energy management system is provided with a solar energy collection panel and an energy storage unit and is connected with the edge computing unit through a converter; the cross-device cooperative control network is integrated with a wireless communication module; a self-adaptive learning algorithm is adopted, and a recurrent neural network model is adopted to process the time sequence data; and the multi-modal user feedback optimization mechanism is used for detecting temperature distribution and triggering control parameter adjustment based on a vision and thermal imaging feedback system. Multi-dimensional environment data are collected in a grid layout mode through the distributed sensor network, the real-time processing and caching functions of the low-power-consumption edge computing unit are combined, the system response speed is increased, and data collection uniformity and processing efficiency are guaranteed.

The application provides a two-material double-sided edge sealing processing method, system and equipment for producing bath towels, physical characteristic parameter and surface state data of two bath towel materials to be compounded are collected, and the data is preprocessed and feature extracted and then pushed to corresponding digital twin virtual models; based on historical qualified processing data associated with the models, an adaptive learning algorithm is used to determine the ultrasonic welding and hot pressing composite parameters corresponding to each material combination; the material edges are pre-positioned and welded by an ultrasonic welding unit, and then synchronously fused, compounded and shaped by a double-sided hot pressing composite unit to form an integrated edge sealing structure without pinholes and seams; key process parameters are monitored in real time, and when the parameters deviate from the preset threshold, automatic adjustment or a warning signal is generated. The scheme does not require a sewing machine, the edge sealing can withstand long-term soaking of bath milk, has high bonding strength and good water resistance.

The invention discloses a circulating water monitoring method based on an adaptive learning algorithm and a related device. The circulating water monitoring method comprises the following steps: acquiring detection data of each detection position in a circulating water system; the detection data of the detection positions in the circulating water system are input into the trained corrosion prediction model to predict the corrosion of the circulating water in the circulating water system, the corrosion prediction model is constructed based on a long short-term memory network, and the method and the related device can accurately detect the corrosion of the circulating water.

This invention relates to the field of green building environmental monitoring technology, and discloses a green building environmental monitoring system, method, and storage medium. The method includes continuously collecting environmental parameters such as thermodynamic parameters, humidity parameters, and gas concentration parameters through intelligent sensing nodes at multiple locations within the green building; transmitting these environmental parameters to a central processing unit, which combines pre-stored environmental standard values ​​with real-time data streams and uses an adaptive learning algorithm to generate environmental control commands; environmental execution devices carrying out environmental adjustment activities based on these commands; real-time monitoring of the execution sequence of adjustment activities, calculation of performance evaluation indicators, and generation of normal or abnormal performance status signals, automatically triggering an alarm process in case of an anomaly. This method constructs a complete environmental management closed loop, realizing comprehensive dynamic monitoring and precise adjustment of the green building environment, adapting to the core requirements of environmental protection and comfort in green buildings, and ensuring that the building's internal environment is in a suitable state.

The invention relates to the technical field of vehicles, in particular to a vehicle window anti-pinch method and device, electronic equipment, a storage medium and a program product.The method comprises the steps that the motor rotating speed when a vehicle window ascends is collected; determining a target rotating speed according to the motor rotating speed, and matching an anti-pinch monitoring data window and current filtering time according to the target rotating speed; and based on a preset anti-pinch force, performing anti-pinch control according to the target rotating speed, the anti-pinch monitoring data window and the current filtering time. Therefore, by adding the car window self-adaptive learning algorithm, correcting the current filtering window in real time based on the rotating speed of the motor and dynamically adjusting the anti-pinch monitoring response time, the problems of deviation between the actual anti-pinch force and the target, wrong anti-pinch or non-anti-pinch and the like caused by aging of a mechanical structure in the related technology are solved, and the safety and reliability of the car window anti-pinch system are improved.

The invention relates to the technical field of intelligent instrument data interaction, in particular to a kitchen safety cooperative control system based on multi-mode interaction, and is characterized in that an intelligent screen in the system is in communication connection with a system server, and the system server is in communication connection with a gas meter; the intelligent screen is in communication connection with the door and window control system, the safety valve, the alarm, the sensor and the range hood, more humanized operation experience is provided for a user by integrating multiple interaction modes such as visual sense, auditory sense and tactile sense, and the multi-mode interaction function is achieved. Through a hybrid architecture of edge computing and cloud computing, real-time performance and expansibility are both considered, the local quick response requirement is met, and strong data analysis capability is achieved. Through an adaptive learning algorithm of the system server, a decision model of the system server can be continuously optimized according to historical data, and performance and reliability are gradually improved.

The invention relates to the technical field of two-component spraying, and discloses a two-component spraying independent temperature control heating hose system and a balancing method. A dual-channel independent heating hose group; an electric delivery pump unit; and an intelligent control module. The method comprises the following steps: step S01, an independent temperature control stage; s02, a dynamic balance stage; and step S03, a matching verification stage. A multi-channel PID temperature controller is combined with a self-adaptive learning algorithm, so that the heating power can be automatically adjusted according to the environment temperature change; meanwhile, the elliptical gear flow meter monitors flow in real time and feeds back data to the intelligent control module, and when the flow deviation exceeds + / -3%, a corresponding compensation mechanism is triggered, so that accurate temperature control and flow stability of the components A and B in the spraying process are ensured, the problem that in the prior art, accurate temperature control cannot be conducted on the components A and B respectively is solved, and the spraying quality is improved. And the stability and the reliability of the spraying quality are improved.

The application discloses a power distribution network voltage optimization dynamic partition method based on an improved adaptive PSO algorithm, a comprehensive index system of power distribution network region division is established, the power distribution network region is set as a particle swarm, inertia weight in a particle swarm algorithm is improved by adopting a nonlinear decreasing strategy based on the comprehensive index system, an initial region division result of the power distribution network is obtained based on the processed particle swarm position and in combination with an adaptive learning PSO algorithm, a dynamic region division result changing with the state of the power distribution network is obtained based on the initial region division result and by combining a difference trigger mechanism in the comprehensive index system, the dynamic partition of the rural intelligent power distribution network of the integrated heterogeneous distributed resource group is realized by establishing the comprehensive index system, combining the nonlinear decreasing inertia weight and the adaptive learning factor, optimizing the K-means clustering center by using the adaptive learning PSO algorithm and combining the dynamic threshold trigger mechanism.

According to the automatic cutting system and control method for the valve sealing weld joints, the system integrates digital twin positioning, self-adaptive clamping, dual-mode cutting, multi-dimensional monitoring and block chain tracing technologies, and high cutting precision is achieved; through a three-level safety response mechanism, the safety accident rate is greatly reduced, the scrap recovery rate is high, and dust explosion and high-temperature burning risks are effectively prevented; the system adapts to a full-size valve, the universality is improved, and the requirement for customizing tools is reduced; the block chain platform realizes tampering-free storage of cut data in a full life cycle, and generates a traceable report in combination with machine vision quality evaluation, so that the maintenance traceability requirement of nuclear power equipment is met; a self-adaptive learning algorithm dynamically optimizes a cutting path and process parameters based on historical data, and a'data driving-intelligent optimization 'closed-loop ecology is formed. According to the method, multi-dimensional breakthrough of precision, efficiency, safety and universality is achieved through technical innovation, and remarkable economic benefits and social values are achieved.

The invention discloses a gravity measurement and calculation system, and relates to the technical field of geophysical measurement and precise instruments. The system comprises a gravity measurement module, a dynamic correction module, a calculation module and a result output and early warning module. The method comprises the following steps: acquiring 0.1 nGal-level gravity data through an atomic interference type quantum gravimeter array; dynamically updating an energy component correction term epsilon (g) in the empirical equation by using an adaptive learning algorithm based on a Lyapunov stability criterion, and ensuring asymptotic stability of the system under high-frequency data flow; combining a real-time density value of a CRUST1.0 density model after Bouge correction, and accurately calculating the earth radius variation; and finally, through 5G and satellite double-link redundant communication, triggering early warning when severe conditions that delta g is greater than or equal to 2 mu Gal for continuous 30 minutes, and SNR is greater than or equal to 6 dB are met. According to the invention, high-precision quantum sensing, a stability control algorithm and a real-time geophysical model are deeply fused, reliable monitoring of micron-sized change of the earth shape and effective early warning of geophysical events are realized, and the method has high precision, high stability and high engineering practicability.

The invention discloses a cylindrical lithium battery internal temperature field real-time estimation method and system, and the method comprises the steps: building a temperature space distribution model based on a heat conduction equation, normalizing the space-time quantity through scaling transformation, and converting a non-homogeneous boundary condition into a homogeneous boundary condition through variable replacement; decoupling a space-time relationship between the temperature distribution quantity and a heat production item by adopting a double decomposition technology, and regarding a heat production time variable as a virtual source; and establishing a finite-dimensional ordinary differential equation model by using a Galerkin method. Designing a self-adaptive observer, and estimating a low-order state variable and a virtual source time sequence on line by combining a self-adaptive learning algorithm so as to measure and estimate a temperature error driving update rate; and reconstructing a temperature distribution quantity and a virtual source estimation value through space-time synthesis of the estimation sequence and a preset space basis function. Real-time estimation of the internal temperature field and the heat production amount of the cylindrical lithium battery can be effectively realized by means of a small number of thermocouples only through temperature measurement data without voltage and current sensors.

The invention relates to the technical field of hot roll bending forming. The invention provides an integrated closed-loop cooling system for hot roll bending forming, which comprises a multi-dimensional temperature sensing module, a partition self-adaptive cooling execution module, a heating-cooling linkage control module, an intelligent algorithm center and an online performance closed-loop module, a multi-dimensional temperature sensing module is used for synchronously collecting the surface temperature and the internal temperature of a high-strength steel plate and constructing a zoning temperature field model, a zoning self-adaptive cooling execution module is matched to independently regulate and control the water flow and the atomization granularity of a cooling spray head according to part structure zoning, and a heating-cooling linkage control module and an intelligent algorithm center cooperate. And in combination with an adaptive learning algorithm, real-time and historical data are integrated to optimize cooling parameters, and the online performance closed-loop module detects the microstructure and hardness of the part in real time and reversely optimizes the parameters. In this way, the problems that a traditional open type water spraying system is inconsistent in cooling rate and uneven in temperature distribution are solved.

The invention provides an SUMO road network coordinate conversion method and device based on an adaptive learning algorithm, electronic equipment and a storage medium, and belongs to the technical field of data processing, and the method comprises the steps: extracting node information, edge information and lane information from road network data; generating a point geometric object based on the node information; generating a line geometric object of the road edge based on the edge information; generating a surface geometric object based on the lane information; converting the two-dimensional coordinates of the geometric object into WGS84 space coordinates by using an integrated learning model fused with various heterogeneous machine learning algorithms; if the WGS84 space coordinates obtained through conversion are abnormal, interpolation restoration is carried out, restoration is carried out based on preset geometric constraints, or restoration is carried out based on network topology connectivity; and updating road network data based on the WGS84 space coordinates. The non-linear deformation of the complex road network can be captured, and the conversion precision is improved.

The application provides a SUMO road network coordinate conversion method and device based on an adaptive learning algorithm, electronic equipment and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: extracting node information, edge information and lane information from road network data; generating a point geometric object based on the node information; generating a line geometric object of a road edge based on the edge information; generating a surface geometric object based on the lane information; converting two-dimensional coordinates of the geometric object into WGS84 space coordinates by using an integrated learning model that integrates multiple heterogeneous machine learning algorithms; if the converted WGS84 space coordinates are abnormal, interpolation repair, repair based on a preset geometric constraint, or repair based on network topology connectivity is performed; and updating the road network data based on the WGS84 space coordinates. The application can capture the nonlinear deformation of a complex road network and improve the conversion accuracy.

The invention relates to the technical field of intelligent equipment control, in particular to a single-live-wire multi-dimensional chopping phase-cut fan lamp intelligent control system, which comprises a single-live-wire input, a main control processor, a load driver, a multi-dimensional sensor and a communication module, and is characterized in that the multi-dimensional sensor is used for acquiring temperature, humidity, human body existence state and ambient illuminance data. According to the system, the target rotating speed of the fan and the target brightness of the lamp are calculated through a multi-dimensional weighted decision algorithm, chopping and phase cutting control signals are generated, and fan PWM chopping stepless speed regulation and lamp phase cutting stepless dimming are achieved through a load driving module; a dynamic smooth transition mechanism is provided to avoid sudden change of rotating speed and brightness; an adaptive learning algorithm is also included, and weight coefficients are optimized to fit user habits; the communication module supports Wi-Fi, Bluetooth or Zigbee protocols and can be in butt joint with an intelligent home cloud platform, a mobile terminal APP and the like, intelligent and convenient control is achieved, and the use comfort and compatibility are improved.

The invention provides a wind power prediction method, system, medium and equipment based on self-adaptive verification, and belongs to the technical field of wind power prediction, and the method comprises the steps: collecting historical data and real-time data in an area where a wind power plant is located, and carrying out the preprocessing; constructing a multi-scale prediction model, and performing initial prediction based on the preprocessed historical data and real-time data to obtain a power prediction result; real-time verification is carried out, and an abnormal fan is identified; for the abnormal fan, adopting a self-adaptive learning algorithm to adjust the multi-scale prediction model of the abnormal fan; and using the adjusted multi-scale prediction model to enter a next cycle prediction period, and continuously performing prediction and cross validation on the wind power airport. Through mutual verification and fusion of fan-level and station-level prediction, microscopic and macroscopic information is effectively utilized, the limitation of single-scale prediction is overcome, the prediction precision is greatly improved, and the effect is particularly obvious when the wake effect drastically changes due to wind direction changes.