Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1137results about How to "Reduce instability" patented technology

Natural gas odorant concentration detection system based on multi-sensor fusion

The invention provides a natural gas odorant concentration detection system based on multi-sensor fusion, and the system comprises a multi-sensor array which comprises at least three different types of sensors; the data acquisition module is used for respectively acquiring detection signals of each type of sensor in the multi-sensor array; the signal preprocessing module is used for preprocessing the collected detection signal of each type of sensor to obtain a preprocessing signal corresponding to each type of sensor; the feature extraction module is used for extracting a corresponding feature vector from the preprocessed signal of each type of sensor through a wavelet transform and principal component analysis method; the multi-modal fusion module is used for fusing the feature vectors of all sensors in the multi-sensor array by adopting a deep neural network algorithm to obtain fusion features; and the concentration estimation module is used for carrying out parallel prediction on the fusion features through various machine learning regression algorithms so as to determine the concentration of the odorant. According to the invention, high-precision, real-time and reliable detection of the concentration of the natural gas odorant is realized.
Owner:PRELITE (TIANJIN) GAS EQUIP CO LTD +1

Servo hydraulic system optimization control method and system for press machine test platform

The invention provides a servo hydraulic system optimization control method and system for a press machine test platform, and relates to the technical field of press machines, and the method comprises the steps: building a state space expression and building a mathematical model of a servo hydraulic system based on dynamic characteristics by deducing mathematical expressions of all components of the system; building a predictive control algorithm based on the mathematical model, solving a quadratic programming problem by adopting a rolling optimization strategy through building a state space predictive model and determining a multi-objective optimization function to obtain an optimal control sequence, and taking a first element of the optimal control sequence as control input at the current moment; feedforward compensation and pressure feedback compensation are introduced, the feedforward compensation constructs a compensation model based on an inverse system of a press transfer function and pre-corrects a control signal, and the pressure feedback compensation designs a digital filter based on a pressure error, fuses a feedforward compensation signal with a pressure feedback compensation signal and superposes the fused signal with the control signal; and obtaining a final control signal.
Owner:TIANJIN HANYANG METAL EQUIP

Real-time river water level monitoring and early warning method and system based on deep learning

The invention relates to a real-time river water level monitoring and early warning method and system based on deep learning. The method comprises the following steps: acquiring a target watershed remote sensing image and real-time hydrological data of multiple monitoring points; performing water flow direction topology analysis on the remote sensing image of the target watershed, and constructing a water flow topology network; performing basin structure dynamic change feature analysis on the target basin remote sensing image to generate basin structure dynamic change data; carrying out topology situation evolution fitting on the water flow topology network based on the basin structure dynamic change data to obtain a dynamic topology evolution network; performing multi-scale time sequence trend evolution analysis on the multi-monitoring-point real-time hydrological data to generate water flow time sequence evolution characteristics; and evolution characteristic space position mapping is performed on the dynamic topology evolution network based on water flow time sequence evolution characteristics, and a three-dimensional hydrological evolution model is constructed. According to the invention, timely and accurate river water level monitoring and early warning are realized.
Owner:CHANGJIANG RIVER SCI RES INST CHANGJIANG WATER RESOURCES COMMISSION

Light spot real-time monitoring and feedback focusing system and method for laser processing

The invention discloses a light spot real-time monitoring and feedback focusing system and method for laser processing. The system comprises a laser processing module, an emission light source module, a power monitoring module, a light spot monitoring module and an automatic control module. The emitting light source module is used for emitting laser beams; the power monitoring module is used for monitoring the laser power emitted by the emitting light source module; the light spot monitoring module is used for monitoring light spots of diffuse reflection light after the laser is emitted to the surface of the workpiece; the automatic control module sets reference signals of the following parameters: processing laser power and shape, position and size of a processing light spot; and according to the reference signal and the corresponding feedback signal, the laser emission parameter and the laser incident workpiece surface parameter are automatically adjusted, so that the error between the reference signal and the corresponding feedback signal is within a set precision range. According to the method, the light spot form and the light intensity in the machining process are dynamically monitored, and the light spot form and the energy in the laser machining process are adjusted in real time through feedback.
Owner:FUJIAN HITRONICS TECH INC

Charging pile dynamic power scheduling method

The invention discloses a charging pile dynamic power scheduling method, and relates to the technical field of charging pile power scheduling, and the method specifically comprises the following steps: obtaining node state information of each remaining normal node in real time, and generating a remaining bearing capability index and a load balancing index of each normal node; and constructing a power distribution evaluation model for the generated residual bearing capacity index and the load balancing index of each normal node, generating a power distribution evaluation coefficient of each normal node, analyzing the power distribution evaluation coefficient after generation, and evaluating the power bearing capacity of each normal node. Dividing each normal node into a high-bearing node, a middle-bearing node and a low-bearing node according to an evaluation result; and respectively adopting a corresponding power scheduling strategy according to a division result of each normal node. According to the invention, the problem that the power resource cannot be quickly and efficiently allocated after the fault node exits is solved, and efficient and stable dynamic balanced power scheduling and system operation are realized.
Owner:江西驴充充物联网科技有限公司

Wind power prediction method based on improved LSTM and FA-KELM

The invention discloses a wind power prediction method based on improved LSTM and FA-KELM, and the method comprises the steps: obtaining the wind power data of a wind power plant, carrying out the normalization of the wind power data, and carrying out the decomposition of the wind power data through employing CEEMDAN; calculating the fuzzy entropy of the obtained subsequences, performing secondary decomposition on the subsequence with the maximum fuzzy entropy by using a PSO-VMD algorithm, and dividing other sequences into a high-entropy sequence and a low-entropy sequence according to the fuzzy entropy; the method comprises the following steps: improving an LSTM network, and replacing an input gate, a forgetting gate and an output gate in the LSTM network with a gate control structure with a cross coupling structure to obtain ConvsLSTM; mIC is adopted to screen out meteorological factors with large correlation with wind power in the meteorological factors of the wind power plant; and in combination with the obtained meteorological factor data, predicting the obtained high-entropy sequence by using ConvsLSTM, and predicting the low-entropy sequence by using FA-KELM. And superposing the predicted values of all the components, and carrying out reverse normalization to obtain a final ultra-short-term wind power prediction result. According to the method, the appropriate prediction model can be selected for the power subsequences with different complexities, and the overall wind power prediction precision is improved.
Owner:GD POWER DEVELOPMENT CO LTD +4

Sea ice target detection method based on multi-dimensional feature extraction

The invention discloses a sea ice target detection method based on multi-dimensional feature extraction, and the method specifically comprises the following steps: S1, data preprocessing: carrying out the denoising of an original sea ice image through a Gaussian filter, carrying out the multi-scale analysis of the sea ice image through an image pyramid, and obtaining sea ice images under different scales; s2, local feature extraction: extracting texture features of each local region by using a gray-level co-occurrence matrix; s3, performing enhanced texture feature processing on the extracted texture features through a directional filter and an enhancement algorithm to obtain final texture feature data; and S4, performing feature fusion on the obtained multi-dimensional features and the texture features to form a comprehensive feature image, and obtaining a classification result of the sea ice target. According to the sea ice target detection method, through multi-scale analysis, image representation is obtained under different scales by using an image pyramid transformation method, changes and expressions of texture features under different scales are captured, and the stability of sea ice target detection is improved.
Owner:CSSC MARINE TECH CO LTD

Alternating current charging pile ordered charging power regulation and control method

The invention discloses an alternating current charging pile ordered charging power regulation and control method, and relates to the technical field of alternating current charging pile charging power regulation and control, and the method specifically comprises the following steps: obtaining the operation state information of each alternating current charging pile in real time, and generating a voltage fluctuation influence index and a load dynamic response index of each alternating current charging pile; constructing a power influence evaluation model for the generated voltage fluctuation influence index and the load dynamic response index of each alternating current charging pile, generating a power influence evaluation coefficient of each alternating current charging pile, performing analysis after generation, and evaluating the influence degree of the three-phase voltage phase difference fluctuation on the charging power of each alternating current charging pile. And the alternating current charging piles are divided into low-influence charging piles, medium-influence charging piles and high-influence charging piles according to the evaluation result. According to the method, the problem that the charging power is influenced by three-phase voltage phase difference fluctuation is solved, and the efficient and stable effects of dynamic evaluation and accurate regulation and control of the power of the charging pile are achieved.
Owner:江西驴充充物联网科技有限公司

Shrimp population health condition assessment method based on deep clustering analysis

The invention relates to the technical field of data processing, in particular to a shrimp group health condition assessment method based on deep clustering analysis, and the method comprises the steps: monitoring health parameters; determining a shrimp group dispersion grid; determining a temporary grid; identifying a non-shrimp group abnormal grid; calculating an actual health index; and adjusting the grid step length and evaluating health. According to the method, the health condition of the shrimp group can be accurately monitored and evaluated by combining physiological and behavior data such as real-time density, saturation and activeness, abnormal grids are eliminated step by step, more representative grids are screened out, evaluation deviation caused by environmental fluctuation or measurement errors is avoided, and the evaluation accuracy is improved. The dynamic monitoring of the health condition of the prawn group is realized, and the grid step length is automatically adjusted by comparing the ideal health index with the actual health index, so that the health assessment precision and reliability are improved, and the problem of inaccurate health assessment result caused by unstable environmental parameters is effectively solved.
Owner:GUANGZHOU JIESHENG INFORMATION TECH

Intelligent electrical cabinet with stable heat dissipation function and heat dissipation control method thereof

The invention relates to the technical field of electrical cabinet heat dissipation control, in particular to an intelligent electrical cabinet with a stable heat dissipation function and a heat dissipation control method thereof. The method comprises the steps of firstly obtaining load power data, temperature data and heat dissipation power; further predicting future power change trend parameters according to the change characteristics of the historical load power data; further obtaining heat dissipation effect parameters according to the fluctuation characteristics of the historical temperature data; further obtaining predicted heat dissipation power according to the power change trend parameter and the heat dissipation effect parameter at the current moment in combination with the heat dissipation power at the current moment; and finally, controlling the heat dissipation of the intelligent electrical cabinet based on the predicted heat dissipation power. According to the method, the change trend of the load power possibly borne by the electrical cabinet is predicted, the heat dissipation effect of the current electrical cabinet is evaluated, the predicted heat dissipation power is obtained, heat dissipation of the intelligent electrical cabinet is controlled, the heat dissipation power is adjusted in time, the heat dissipation stability is improved, and stable and safe operation of the electrical cabinet is guaranteed.
Owner:TAIYUAN SILIAN INTELLIGENT ELECTRICAL TECH CO LTD

Garbage truck real-time monitoring and remote scheduling method based on Internet of Things

The invention discloses a garbage truck real-time monitoring and remote scheduling method based on the Internet of Things, and the method comprises the following steps: S1, collecting the real-time data of the operation state of a garbage truck, and carrying out the preprocessing of the real-time data; s2, constructing a task prediction model based on an improved adaptive graph neural network, and generating a preliminary task distribution matrix and a path planning scheme; s3, optimizing the preliminary task allocation matrix and the path planning scheme by adopting an improved PPO algorithm; s4, the optimized task allocation matrix and the path planning scheme are sent to a garbage truck vehicle-mounted terminal, and the task completion rate and the path deviation value are calculated; s5, the operation state of the garbage truck is monitored in real time, and the monitoring result and the operation state data are transmitted to the cloud Internet of Things platform; and S6, dynamically updating the scheduling instruction. According to the method, the Internet of Things, the adaptive graph neural network and the improved PPO algorithm are fused, intelligent scheduling and real-time optimization of the garbage truck are realized, and the method has the advantages of high efficiency, stability and low-cost operation.
Owner:ANKANG XINYEFENG ENVIRONMENTAL TECH CO LTD

Semi-supervised seismic wave impedance inversion method and system based on Swin Transform iterative gradient correction

The invention discloses a semi-supervised seismic wave impedance inversion method and system based on Swin Transform iterative gradient correction, and belongs to the technical field of earthquakes in geophysical exploration. According to the method, the impedance gradient is iteratively corrected in the model space through the deep neural network, and complex nonlinear prior information is captured; and each anisotropic structure direction regularization item is established, and constraint is carried out along the direction of the stratum structure, so that the space consistency of the prediction result is ensured. Meanwhile, the USTNet network designed by the invention combines the advantages of the local feature capture capability of the convolutional neural network and the global modeling capability of Transform, and reduces the non-uniqueness of solutions. The network is used for inverting synthetic data and actual data, and the effectiveness of the method is verified.
Owner:XI AN JIAOTONG UNIV

Systems and related methods for producing fluid mixtures in microfluidic channels, in particular for formulating liposomal-based drugs by alternating injection of two fluid phases

The invention relates to a system (10) for producing a fluid mixture, comprising: a pressure source (11); a pressure regulator (12); at least a first container (16.1) and a second container (16.2), the first container (16.1) containing the first fluid (15.1) and the second container (16.2) containing the second fluid (15.2); a microfluidic mixer (20); and a control unit (40) capable of controlling the pressure level of the first fluid (15.1) and the pressure level of the second fluid (15.2) and the opening and closing of the first valve (23.1) and the second valve (23.2) in order to inject the first fluid and the second fluid successively into the microfluidic mixer (20) in order to create a profile of stripes (F1, F2) of the first fluid (15.1) and the second fluid (15.2) within the common outlet channel (34).
Owner:INSIDE HEALTH CORP

Broadband wide frequency spectrum analysis method and system based on deep learning

The invention discloses a broadband wide frequency spectrum analysis method and system based on deep learning. The method comprises the steps of spectrum signal acquisition, spectrum preprocessing, abnormal interference detection, spectrum trend prediction and spectrum scheduling management. The invention relates to the technical field of wide-frequency spectrum analysis, in particular to a broadband wide-frequency spectrum analysis method and system based on deep learning, which adopts a three-step method of abnormal interference detection, spectrum trend prediction and spectrum scheduling management, and adopts a layer-by-layer progressive deep learning and reinforcement learning technology. The real-time detection of spectrum abnormity, the accurate prediction of future trend and the optimal allocation of dynamic resources can be realized; carrying out abnormal interference detection by adopting a joint improvement multi-classification support vector machine method combined with feature enhancement; performing spectrum trend prediction by adopting a time sequence integrated network combined with one-dimensional convolution feature extraction; and performing spectrum scheduling management by adopting a reinforcement learning method enhanced by a near-end strategy optimization algorithm.
Owner:HEFEI INNOVATION RES INST BEIHANG UNIV

Spine rehabilitation training device, equipment and rehabilitation method thereof

The invention discloses a spine rehabilitation training device, comprising: a rehabilitation training assembly comprising a head and neck supporting mechanism, a thoracolumbar supporting mechanism and a caudal vertebra supporting mechanism which are arranged at intervals from top to bottom and are connected with each other through a flexible connecting piece I, the head and neck supporting mechanism, the thoracolumbar supporting mechanism and the caudal vertebra supporting mechanism each comprise a plurality of air bag supporting pieces arranged at intervals. The plurality of air pumps are respectively used for supplying air to the plurality of air bag supporting pieces so as to adjust the pressure on each part of the body; and the control unit is connected with the plurality of air pumps and can independently control the start and stop of each air pump so as to control the pressure of each air bag supporting piece. Bed-in-bed, physical or exercise rehabilitation treatment methods can be selected according to different periods, and the application range is wide.
Owner:ANHUI SANLIAN UNIV

Self-adaptive switching method and system of current transformer

The invention relates to the technical field of equipment control, in particular to a self-adaptive switching method and system of a current transformer. The method comprises the following steps: collecting primary side parameters and secondary side parameters of a current transformer to obtain primary side collection parameters of the current transformer and secondary side collection parameters of the current transformer; performing current transformer state segmentation initialization according to the current transformer primary side acquisition parameters and the current transformer secondary side acquisition parameters so as to generate a current transformer operation state classification result; switching result judgment is conducted on the current transformers according to the current transformer operation state classification result, and when the current transformer operation state classification result is a current transformer critical state section, parallel buffering is conducted on the current transformers, and critical current transformer switching data are generated. According to the invention, through accurate state classification, a dynamic switching mechanism, time sequence optimization and visual display, the switching sensitivity and stability of the current transformer are improved.
Owner:SHENZHEN RUIQIZHENG TECH CO LTD

Natural gas load prediction method based on improved Transform network

The invention discloses a natural gas load prediction method based on an improved Transform network, and the method comprises the steps: carrying out the preprocessing of collected natural gas load data and meteorological data, decomposing the preprocessed natural gas load data into a plurality of intrinsic mode functions IMF through employing a variational mode decomposition method VMD, and carrying out the prediction of the natural gas load data through employing the IMF; the method comprises the following steps of: preprocessing meteorological data, selecting a proper K value by using a minimum envelope entropy as a judgment basis, then independently splicing each IMF and the preprocessed meteorological data to form a plurality of pieces of data to be measured, normalizing the data to be measured, and matching each piece of data to be measured with a trained improved Transformer network to obtain a plurality of pieces of data to be measured; and inputting the plurality of normalized data to be measured into the respective corresponding improved Transform networks for prediction to obtain corresponding prediction results, and finally performing superposition reconstruction on all the prediction results to serve as a final prediction result to be output. According to the method, the problems of data non-stationarity and complex time sequence dependency relationship in natural gas load prediction are solved, and the prediction accuracy and reliability are improved.
Owner:BEIFANG UNIV OF NATITIES

Intelligent alkaline water electrolysis device and low-load stable operation method

The invention relates to an intelligent alkaline water electrolysis device and a low-load stable operation method.The intelligent alkaline water electrolysis device comprises an electrolytic bath, a sensor system, an electrolyte adjusting system and a control system, and the electrolyte adjusting system comprises an electrolyte storage tank, a pump and a mixing device; the sensor system comprises a temperature sensor, a pressure sensor, an electrolyte concentration sensor, a current sensor, a voltage sensor and a gas sensor, the control system comprises a controller, and the output ends of the temperature sensor, the pressure sensor, the electrolyte concentration sensor, the current sensor, the voltage sensor and the gas sensor are connected with the input end of the controller. And the controller is electrically connected with the electrolyte storage tank, the pump and the mixing device. The running state of the electrolytic cell is monitored in real time, and the concentration of the electrolyte is dynamically adjusted, so that the electrolysis process is optimized, the stability of the cell voltage and the gas generation amount is ensured when the alkaline water electrolysis device runs at a low load, especially an ultra-low load, and the rapid rising of the hydrogen content in oxygen is effectively prevented.
Owner:HUADIAN CAOFEIDIAN HEAVY IND

Intelligent parking lock remote management method and system based on Bluetooth communication

The invention relates to the field of remote management of parking locks, in particular to an intelligent parking lock remote management method and system based on Bluetooth communication. The method comprises the following steps: acquiring an intelligent parking lock operation log and an intelligent parking lock real-time Bluetooth connection state parameter; according to the intelligent parking lock operation log, user personalized behavior habit evolution is carried out, user portrait modeling is carried out, and an unlocking behavior portrait of each user is constructed; based on the unlocking behavior portrait of each user, real-time user behavior abnormal deviation quantification and abnormal parking lock use decision making are carried out on the intelligent parking lock real-time Bluetooth connection state parameters, and an abnormal parking lock early warning strategy is generated; when the real-time user behavior abnormal deviation value does not exceed a preset behavior deviation threshold value, triangulation positioning distance measurement and user accurate positioning calculation are conducted on the intelligent parking lock real-time Bluetooth connection state parameters, and real-time position coordinates of the user are obtained. According to the invention, safe and efficient remote management of the parking lock is realized.
Owner:SHENZHEN MUSMOON TECH CO LTD

Photovoltaic power station power generation prediction method based on multi-model fusion

The invention relates to the technical field of power generation prediction data processing, and discloses a photovoltaic power station power generation prediction method based on multi-model fusion, which combines a photovoltaic physical model, a power generation statistical model and a power generation prediction model, not only considers a physical rule, but also combines statistical learning and machine learning to improve the stability and accuracy of prediction, and improves the prediction efficiency. And predicting the generating capacity of the photovoltaic power station by using environmental meteorological data, electrical parameters of the photovoltaic power station and historical power generation data. Accurate photovoltaic power generation power prediction is beneficial to better arrangement of power generation plans and resource scheduling of the power grid. The prediction precision and stability are improved through multi-model fusion, so that power grid dispatching is more accurate and efficient, and power grid instability factors caused by photovoltaic power generation fluctuation are reduced. Therefore, photovoltaic power generation can be connected to a power grid more stably, the power demand is met, and wide application and development of clean energy are promoted.
Owner:HUANENG QINMEI RUIJIN POWER GENERATION CO LTD

Method for positioning memory leak

The invention discloses a method for positioning memory leak, which relates to the field of computer science and technology, and comprises the following steps of: initializing a memory use monitoring module, setting an initial memory use rate threshold, and defining a threshold adjustment parameter; the CPU utilization rate and the memory use condition are monitored in real time, historical data are recorded, and a memory use trend model is established. When the CPU utilization rate exceeds the set threshold value, reducing the first preset threshold value, adjusting the second preset threshold value according to the memory use trend, and comprehensively adjusting the memory utilization rate threshold value. And when the memory utilization rate exceeds a first preset threshold value, starting memory leak detection, recording memory allocation and release information by using a hash table, and searching the unreleased memory. And analyzing logs and behavior records of the system before and after memory leak, constructing a causal relationship model, adjusting a memory utilization rate threshold value, and generating a report containing memory leak position and reason analysis thereof. According to the method, the predictability and the accuracy of memory management are better improved, and the self-adaptive capability of the system is enhanced.
Owner:深圳市云希谷科技有限公司

Steel wire ring winding main machine

The utility model discloses a steel wire ring winding main machine, which belongs to the technical field of steel wire ring production, and comprises an operation table, a mounting plate and two groups of mounting racks are fixedly mounted at the top of the operation table, a winding assembly is arranged on one side of the mounting plate, and the winding assembly comprises a rotating shaft and a moving rod, the rotating shaft is rotatably mounted in the mounting plate, a cross-shaped frame is fixedly mounted at one end of the rotating shaft, a first motor is fixedly mounted at the bottom of the cross-shaped frame, and a lead screw is fixedly mounted on an output shaft of the first motor. According to the steel wire winding device, the steel wire rings with different diameters can be conveniently wound by the winding drum, the universality and the flexibility of equipment are improved, the steel wire rings are uniformly wound in the winding process, the conditions of knotting and non-uniform winding in the winding process are avoided, and the wound steel wires are prevented from being stacked at a certain position.
Owner:JIANGYIN AOCHI MECHANICAL EQUIP CO LTD

Surface water quality parameter detection method, device, equipment, medium and product

The invention discloses a surface water quality parameter detection method, device and equipment, a medium and a product, and relates to the technical field of water quality monitoring. The method comprises the following steps: constructing sample data of each selected water quality parameter index according to ultraviolet-visible absorption spectrum data and water quality detection data of different surface water samples, sequentially determining a plurality of corresponding optimal water quality parameter estimation models and an optimal model fusion method on the basis of the corresponding sample data for each index, and calculating the optimal water quality parameter estimation model according to the optimal water quality parameter estimation model and the optimal model fusion method. Finally, the ultraviolet-visible absorption spectrum data, collected in real time, of the field surface water are imported into the optimal water quality parameter estimation models of all the indexes in real time, and the final index values of all the indexes of the field surface water are obtained by applying the optimal model fusion method of all the indexes. Therefore, the purpose of quickly, accurately and real-timely monitoring multiple parameters of the surface water quality can be achieved, and the method has the advantages of no reagent, no secondary pollution, real-time performance, high efficiency, multi-parameter monitoring capability and high robustness.
Owner:BO RUI SI SHU ZHI KE JI (SHEN ZHEN) YOU XIAN GONG SI

Plasma gun automatic spraying equipment

The invention relates to plasma gun automatic spraying equipment which comprises a workbench, an X-axis moving assembly, a Y-axis moving assembly and a rotating shaft assembly, the X-axis moving assembly, the Y-axis moving assembly and the rotating shaft assembly are located above the workbench, the rotating shaft assembly is connected with an ion gun fixing support, and the X-axis moving assembly, the Y-axis moving assembly and the rotating shaft assembly move independently or cooperatively. And the plasma gun on the ion gun fixing bracket is driven to spray the workpiece according to the set motion path. Through an advanced automatic control system and an intelligent adjusting function, the spraying process can be accurately controlled without manual intervention, the consistency of the production efficiency and the spraying quality is remarkably improved, meanwhile, the dependence on manual operation is reduced, and the equipment maintenance cost is reduced. The equipment disclosed by the invention has higher adaptability, can be automatically adjusted to adapt to different types of workpieces, has a fully automatic spraying process, has higher application and popularization values and is suitable for large-scale production.
Owner:DALIAN UNIV OF TECH

Regional power grid wind power generation power prediction optimization method

The invention discloses a regional power grid wind power generation power prediction optimization method which comprises the following specific steps: firstly, collecting data such as wind speed and wind direction through meteorological sensors arranged in a wind power plant and around the wind power plant, and carrying out cleaning and de-noising preprocessing; secondly, decomposing the meteorological data into intrinsic mode function components with different frequencies by adopting variational mode decomposition, constructing a convolutional neural network to perform feature extraction on each component, and adaptively adjusting the size of a convolution kernel according to the periodic characteristics of the data; then, a bidirectional long-short-term memory network based on an attention mechanism is used for fusing features, time sequence information is captured, power prediction is achieved through a full-connection neural network, and the weight of the FCNN is initialized through a random forest regression model to improve the initial performance of the model; according to the method, the prediction precision is improved through multi-level characteristic decomposition and a self-adaptive mechanism, the real-time response capability is good, and the requirements of the regional power grid for the precision and timeliness of wind power generation power prediction are met.
Owner:CHUXIONG POWER SUPPLY BUREAU OF YUNNAN POWER GRID CO LTD

GIS partial discharge type identification method and device, terminal and medium

PendingCN119106368Aaccurate identificationPreserve local structureBiological modelsReal-time dataData set
The invention discloses a GIS partial discharge type identification method and device, a terminal and a medium. The method comprises the following steps: acquiring a statistical characteristic quantity data set of a historical PRPD atlas of partial discharge under each defect type of a GIS; preprocessing the obtained statistical characteristic quantity data set to obtain a sample set after dimension reduction; training a constructed deep residual shrinkage network DRSN recognition model by using the sample set, and optimizing network parameters of the model by taking the minimum SLoss loss function as a target; and loading the obtained statistical characteristic quantity real-time data of the GIS partial discharge PRPD atlas into the trained and optimized DRSN identification model to obtain an identification result of the GIS partial discharge type. According to the method, the type of GIS partial discharge can be quickly and accurately identified, and a powerful guarantee is provided for safe operation of GIS equipment.
Owner:WUXI POWER SUPPLY BRANCH OF STATE GRID JIANGSU ELECTRIC POWER CO LTD

Bottle blowing forming production device for large infusion bottle

The invention discloses a bottle blowing forming production device for a large infusion bottle. The bottle blowing forming production device comprises an installation machine cover and a four-station index plate, a five-station index plate, a transfer assembly and a driving assembly which are assembled in the installation machine cover. A transfer station A, a discharging station, a mold closing station and a feeding station are arranged on the four-station index plate, a transfer station B, a heating station, a bottle blowing station, a cooling station and a polishing station are arranged on the five-station index plate, and the transfer station A and the transfer station B are vertically and oppositely arranged. In addition, the device further comprises a mold assembly, and the mold assembly can be accurately fixed through the four-station index plate and the five-station index plate. The transfer assembly is vertically opposite to the transfer stations A and B, and the driving assembly is in power connection with the four-station index plate, the five-station index plate and the transfer assembly. According to the invention, the production efficiency is improved, the production cost is reduced, the coordination and matching effect among equipment are improved, and the method has remarkable economic benefits and practical values.
Owner:HUNAN KANGYUAN PHARM CO LTD

New energy electric quantity demand prediction model construction method, prediction method and device

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a new energy electric quantity demand prediction model construction method, a new energy electric quantity demand prediction method and a new energy electric quantity demand prediction device. Wherein the multivariable historical time series data set comprises weather data, multi-subject market transaction logic data and user electricity demand historical data; performing stabilization processing on time series data in the multivariate historical time series data set to obtain a stable multivariate historical time series data set; a new energy electric quantity demand prediction model is constructed based on a destabilization attention mechanism and Transform; and training the new energy electric quantity demand prediction model by using the stationary multivariable historical time series data set to obtain a trained new energy electric quantity demand prediction model. Through the embodiment of the invention, the new energy electric quantity demand prediction accuracy can be improved.
Owner:INFORMATION & COMMUNICATION BRANCH STATE GRID JIBEI ELECTRIC POWER CO LTD +1

New energy station management system and method based on smart power grid

The invention discloses a new energy station management system and method based on an intelligent power grid, and the system comprises a real-time monitoring module which is used for predicting the charging load fluctuation of an electric vehicle based on real-time monitoring data, a scheduling module which is used for adjusting the output of new energy power generation equipment according to the predicted load fluctuation, and an optimization module. The power distribution network management module is used for optimizing charging scheduling in a charging station and avoiding overload caused by peak charging at the same time, the dynamic adjustment module is used for dynamically adjusting the voltage and frequency of a power distribution network, and the real-time monitoring module is used for monitoring the state of the power distribution network in real time and dynamically updating a management strategy; according to the new energy station management system and method based on the smart power grid, the problems that in the prior art, due to instability and rapid change characteristics of electric vehicle charging loads, severe fluctuation of the loads can bring extra pressure to a power distribution network, the overload problem of the power distribution network is caused, and then the reliability and safety of the power grid are affected are solved.
Owner:HUANENG FUXIN WIND POWER GENERATION CO LTD

Multi-modal control method, system and equipment for lower limb exoskeleton and medium

PendingCN118963399AAdapt promptly to changes in walking patternsimprove accuracyWalking aidsVehicle position/course/altitude controlBacksteppingMachine
The invention provides a multi-modal control method for a lower limb exoskeleton, and the method comprises the steps: selecting a gait track from a gait track library as an initial track according to the body feature parameters of a wearer, and carrying out the gait phase estimation through combining with a phase estimation model; using a CPG model to obtain an exoskeleton expected trajectory; inputting the exoskeleton expected trajectory and a lower limb motion trajectory in the exoskeleton model into a variable parameter admittance controller, performing modulation factor adjustment in combination with a man-machine interaction torque, and outputting a reference trajectory; and based on the reference trajectory, performing multi-modal control of the lower limb exoskeleton through a position controller based on adaptive RBF backstepping control. According to the method, in an admittance controller, a modulation factor is introduced to realize smooth transition among different control modes, so that an exoskeleton can be flexibly switched among different operation modes, accurate control of an exoskeleton system is realized through the synergistic effect of the steps, and the adaptability of the system and the comfort of a wearer are improved.
Owner:BEIHANG UNIV