42results about How to "Reduce non-stationarity" patented technology

The invention discloses an EMD based fiber-optic gyroscope temperature drift multi-scale extreme learning machine training method. The EMD based fiber-optic gyroscope temperature drift multi-scale extreme learning machine training method comprise the following steps of (1) adopting a bounded ensemble empirical mode decomposition (EEMD) method to respectively decompose drifting output data of a fiber-optic gyroscope in different temperature-changing-rate environments into a series of intrinsic mode functions; (2) adopting a sample entropy (SE) measurement theory to calculate SE values of the intrinsic mode functions (IMF) in the step (1); (3) determining an IMF set led by noise and an IMF set having different self-similarity features according to the fluctuation trend and sizes of the SE values; (4) superposing the IMF sets determined in the step (3) and having the similar self-similarity features to serve as ELM model training inputs, using temperature gradients at the temperature change rates corresponding to the group of output data as another input training ELM model, similarly, using different superposed self-similarity IMF and corresponding temperature gradients to generate different ELM models through training; (5) accumulating the multiple ELM models generated in the step (4) to obtain a final integrated multi-scale model.

The invention discloses a short-term impulse load forecasting model building method based on an signal decomposition and intelligent optimization algorithm, comprising the following steps: S1, according to the non-stationarity of load data, adopting complementary set empirical mode decomposition (CEEMD) to decompose the time series of the original load into several intrinsic mode functions (IMFs);complementary empirical mode decomposition (CEEMD) adding positive and negative white noise to the original time series, which not only guarantees the same decomposition effect as empirical mode decomposition (EEMD), but also reduces the reconstruction error caused by adding white noise. The invention adopts the decomposition technology to decompose the sequence into a plurality of modal components, optimizes the parameters of the prediction model combined with the optimization algorithm, and finally superimposes the prediction results of each component as the final prediction value. Comparedwith other models, the combined model can obtain higher prediction accuracy in the short-term impact load prediction.

The invention discloses an optimal power flow calculation method for a multi-period electricity-gas interconnection system based on wind speed prediction and is applicable to the field of power system optimization control. According to the method, firstly, a wind speed prediction method based on variational mode decomposition and gaussian process regression is proposed, and accordingly a probability distribution curve for currently predicating the wind speed is obtained; an electricity-gas interconnection system multi-period optimal power flow model is established, the minimum total operation cost serves as the target, and the model relates to operation constraint of an power system and a natural gas system; punishment cost and standby cost are adopted to describe influences caused by wind power overestimation and wind power underestimation respectively. It is indicated through the embodiment that the power system and the natural gas system restrict each other, comprehensive optimization is beneficial for obtaining of a globally optimal solution, and safety and reliability of the systems are further guaranteed. Besides, the wind power punishment cost and wind power standby cost have great influences on a regulation scheme, a reference is provided for optimized operation of the systems under the background that new energy is introduced, and decision support is provided for scheduling personnel.

The invention discloses a power distribution transformer area electricity sales accurate prediction method based on a modal GRU learning network, which comprises the following steps of: S1, obtaininghistorical data of electricity sales of a power distribution transformer area, and dividing the historical data into a test set and a training set; S2, preprocessing the data, complementing the sampling time points to ensure continuity of the sampling time points, and filling up missing data of the sampling points by utilizing an average interpolation method; S3, determining an optimal modal number K of variational mode decomposition (VMD) according to the center frequency of each modal component by using an experimental method; S4, carrying out VMD decomposition on the historical data of theelectricity sales of the transformer area, and respectively extracting a decomposed low-frequency modal component and a decomposed high-frequency modal component; S5, predicting a low-frequency mode and a high-frequency mode respectively by using a Prophet prediction model and a GRU learning network; and S6, reconstructing the prediction result of each mode, and obtaining a predicted value of theelectricity sales of the transformer area. The method can improve the prediction precision of the electricity sales of the transformer area, and can provide theoretical and practical support for the precise prediction and management of the electricity sales of the transformer area.

The invention discloses an intelligent tomato greenhouse temperature early-warning system based on a minimum vector machine. The early-warning system is characterized by being composed of a tomato greenhouse environmental parameter acquisition and intelligent prediction platform based on a CAN field bus and an intelligent tomato greenhouse temperature early-warning system. By means of the intelligent tomato greenhouse temperature early-warning system based on the minimum vector machine in the invention, many problems still in the environment in a closed tomato greenhouse due to the reasons ofunreasonable design, backward equipment, incomplete control system and the like in the traditional tomato greenhouse environment can be effectively solved; and furthermore, the control problem that the tomato greenhouse environment temperature is greatly influenced due to the fact that the existing tomato greenhouse environment monitoring system does not monitor and predict the temperature in thetomato greenhouse environment according to the characteristics of nonlinearity and large lag of tomato greenhouse environmental temperature change, large tomato greenhouse area, complex temperature change and the like can be effectively solved.

The invention discloses a short-period wind power interval predicating method which comprises the steps of decomposing a wind power sequence by means of VMD, calculating the sample entropy of each subsequence after decomposing, performing regrouping of the subsequences with approximate sample entropy for forming a new subsequence, respectively establishing a GPR model for each re-grouped subsequence, predicating the probability interval of the wind power sequence, and finally overlapping the prediction results of the subsequences for obtaining a final short-period wind power interval predicating result. The method according to the invention is a scientific and effective method for predicating the short-period wind power interval, and further has advantages of good interval coverage range,high predication accuracy and relatively narrow interval width. The short-period wind power interval predicating method facilitates scheduling and operation of a power system.

The present invention discloses a tomato greenhouse environmental parameter intelligent monitoring device based on an ANFIS neural network. The intelligent monitoring device is composed of a wirelesssensor network-based tomato greenhouse environmental parameter intelligent detection platform and a tomato greenhouse yield intelligent early warning system. According to the tomato greenhouse environmental parameter monitoring and regulation platform established by the present invention, the problem that the tomato greenhouse yield cannot be predicted and early warned according to the impact of tomato soil moisture on the tomato greenhouse yield in the prior art is effectively solved.

The invention discloses a green pepper greenhouse environment intelligent monitoring system based on a subtractive clustering classifier. The intelligent monitoring system is characterized by comprising a green pepper greenhouse environment parameter detection platform based on a wireless sensor network and a green pepper greenhouse yield intelligent early warning system. In the prior art, only adevice is adopted for monitoring the green pepper greenhouse environment parameter, and green pepper greenhouse yield cannot be warned according to green pepper greenhouse environment temperature andsunlight. The green pepper greenhouse environment intelligent monitoring system solve the above problem.

The invention discloses an agricultural product price prediction method based on SHD-ELM. The method comprises the following steps: firstly, collecting agricultural product price time series data; decomposing the original agricultural product price time sequence into a plurality of intrinsic mode functions (IMF) and remainders by utilizing empirical mode decomposition; secondly, performing secondary hybrid decomposition on the influence of the irregularity of the IMF1 component with the strongest fluctuation on prediction, namely performing wavelet transform on IMF1 to decompose the IMF1 intoan approximate sequence and a detail sequence; predicting all components obtained after decomposition by using an extreme learning machine; and finally, combining the prediction results of the components to obtain a prediction value of the original agricultural product price time sequence. The agricultural product price is accurately predicted, and the prediction error is very small. Compared withprediction methods such as a BP neural network, the prediction method combining empirical mode decomposition, wavelet transform and an extreme learning machine has good agricultural product price prediction performance and can be suitable for prediction of agricultural product price fluctuation rules.

The invention relates to a method for reconstructing a vehicle interior noise signal, comprising the following steps: 1) decomposing and analyzing a signal; decomposing and analyzing the source signalto obtain three stable signal component categories, namely, a high-frequency component, an intermediate-frequency component and a low-frequency component; 2) component fitness calculation: respectively train that BP neural network model and taking the performing weight and the threshold value of the BP neural network model as component fitness value to obtain the optimal component fitness value;3) performing Signal reconstruction model: According to the categories of input signal components, the BP network is trained by assigning the fitness value of the optimal component to the noise reconstruction as the initial weight and threshold. After convergence, the corresponding reconstruction algorithm model of each signal component is obtained, and the noise signal of the occupant's ear sideis reconstructed by reconstruction superposition according to the reconstruction algorithm model. Compared with the prior art, the invention has the advantages of reducing the non-stationarity of thesignal and the difficulty of modeling, improving the reconstruction accuracy and the like.

The invention discloses a cucumber greenhouse temperature intelligent detection device based on an LVQ neural network. The cucumber greenhouse temperature intelligent detection device is characterizedby comprising a cucumber greenhouse environment parameter acquisition platform based on a CAN bus and a cucumber greenhouse temperature intelligent monitoring system. The device effectively solves the problem that the existing cucumber greenhouse monitoring system does not intelligently monitor and predict the temperature of the cucumber greenhouse environment according to the characteristics ofnonlinearity and large lag of the temperature change of the cucumber greenhouse environment, large area and complex temperature change of the cucumber greenhouse and the like, so that the regulation and control of the temperature of the cucumber greenhouse environment are greatly influenced.

The invention discloses an optimal power flow calculation method for a multi-period electricity-gas interconnection system based on wind speed prediction and is applicable to the field of power system optimization control. According to the method, firstly, a wind speed prediction method based on variational mode decomposition and gaussian process regression is proposed, and accordingly a probability distribution curve for currently predicating the wind speed is obtained; an electricity-gas interconnection system multi-period optimal power flow model is established, the minimum total operation cost serves as the target, and the model relates to operation constraint of an power system and a natural gas system; punishment cost and standby cost are adopted to describe influences caused by wind power overestimation and wind power underestimation respectively. It is indicated through the embodiment that the power system and the natural gas system restrict each other, comprehensive optimization is beneficial for obtaining of a globally optimal solution, and safety and reliability of the systems are further guaranteed. Besides, the wind power punishment cost and wind power standby cost have great influences on a regulation scheme, a reference is provided for optimized operation of the systems under the background that new energy is introduced, and decision support is provided for scheduling personnel.

The invention relates to the technical field of discharge fault identification, and discloses a GIS partial discharge fault identification method, which comprises the following steps: signal acquisition: acquiring multiple groups of various defect discharge signals to form original signals; data processing: performing variational mode decomposition on the original signals to obtain a series of intrinsic mode components; feature extraction: performing feature extraction on the intrinsic mode component to obtain a multi-scale permutation entropy; and identification and diagnosis: inputting the multi-scale permutation entropy as a high-dimensional feature vector into the partial discharge fault classifier model, and outputting a fault result. The variational mode decomposition overcomes the problems of endpoint effect and mode component aliasing of an EMD method, can reduce the time sequence non-stationarity with high complexity and strong nonlinearity, and obtains a relatively stable sub-sequence containing a plurality of different frequency scales through decomposition; the multi-scale permutation entropy is calculated by the intrinsic mode component, and the complexity change of the time sequence under multiple scales can be detected.

The invention discloses a big data detection system for livestock and poultry activity information. The big data detection system is composed of a livestock and poultry sign parameter acquisition and intelligent prediction platform based on a cloud platform and a livestock and poultry activity big data prediction subsystem. The livestock and poultry physical sign parameter acquisition and intelligent prediction platform based on the cloud platform is used for detecting and processing temperature and activity information parameters of livestock and poultry physical signs; the livestock and poultry activity big data prediction subsystem is used for predicting the activity state of livestock and poultry and providing data and early warning for preventing livestock and poultry diseases; the invention aims to provide the big data detection system for the livestock and poultry activity information, and the system monitors the livestock and poultry body temperature and activity information in real time, so that data and early warning are provided for preventing livestock and poultry diseases.

The invention discloses a human body motion intention recognition method for a lower limb exoskeleton, and particularly relates to the technical field of human body exoskeleton control, and the method comprises the steps: obtaining a signal set of lower limb electromyographic signals and inertial signals during human body gait motion; noise reduction processing is conducted on the electromyographic signals in the signal set in sequence through a Butterworth filter and variational mode decomposition; sequentially carrying out noise reduction processing on the inertial signals in the signal set through a Butterworth filter and wavelet denoising; extracting time-frequency information of each signal in the signal set after noise reduction through continuous wavelet transform, and obtaining a three-dimensional color image of the corresponding signal based on the time-frequency information; performing off-line classification training on the double-flow convolutional neural network through the three-dimensional color image with the preset proportion; and carrying out human body motion intention identification verification on the three-dimensional color image of the remaining proportion through the trained double-flow convolutional neural network. According to the method, the human body motion intention is identified from two aspects of myoelectricity and inertia, so that a more accurate motion intention classification effect is obtained.

The invention discloses a structural mode identification method based on computer vision and variational mode decomposition, and the method comprises the steps of collecting a vibration video of a structural object, and selecting pixel points meeting a preset pixel level in the vibration video as feature points; calculating the speed of each selected feature point by using a Farneback dense optical flow algorithm; calculating the speed and acceleration of each feature point in a real ground coordinate system by using a scale transformation mode to obtain an acceleration signal of a non-stationary sequence; performing noise reduction processing on the acceleration signal by using a variational mode decomposition method; and recognizing the acceleration signal after noise reduction processing by using a frequency domain decomposition method to obtain the vibration characteristics of the structure in each order mode. According to the invention, the vibration video of the structure is calculated and multi-modal extracted by using the improved optical flow algorithm in a non-contact manner, so that the real-time, efficient and low-cost detection of the dynamic characteristics of the structure is realized.

The invention discloses an environment big data Internet of Things intelligent detection system, which comprises an environment parameter acquisition platform and a formaldehyde big data intelligent prediction subsystem, realizes accurate detection and grade classification of formaldehyde concentration, and improves the reliability and accuracy of formaldehyde concentration detection. The system effectively solves the problems that an existing environment parameter detection system has no influence on the accuracy and reliability of measured environment parameters according to complex changes such as large environment area, nonlinearity of environment parameter changes, large lag and the like, and does not accurately detect and predict the environment parameters, so that the monitoring and management of the environment parameters are greatly influenced.

The invention relates to a building energy consumption prediction method and system. The method comprises the following steps of firstly, extracting the characteristic values of all influence factorsof the energy consumption; solving the building energy consumption similarities of the historical days and the prediction days, and selecting the historical day with the highest building energy consumption similarity as a similar day; carrying out wavelet decomposition on the building energy consumption data of the selected similar day to obtain a low-frequency sequence and a high-frequency sequence; then simulating the low-frequency sequence by adopting LSSVM-GSA, and processing the high-frequency sequence by adopting a mean square weighting method; and finally, carrying out the wavelet reconstruction based on the processing results of the low-frequency sequence and the high-frequency sequence, so that the wavelet reconstruction result is the building energy consumption prediction value of the prediction day. The method and the system can be effectively applied to the building energy consumption prediction, and have the good prediction precision and robustness.

The invention discloses a livestock and poultry health sign big data Internet of Things detection system which is characterized in that the detection system comprises a parameter acquisition and control platform and a livestock and poultry body temperature big data intelligent prediction subsystem, and accurate detection and prediction of the measured livestock and poultry body temperature are achieved; the system effectively solves the problems that an existing livestock and poultry sign parameter detection system does not accurately detect and predict livestock and poultry sign parameters according to the influence on the livestock and poultry sign parameters due to the fact that the livestock and poultry environment area is large, and the livestock and poultry environment parameters and complex changes such as nonlinearity and large lag of livestock and poultry sign parameter changes are complex; the livestock and poultry health and the livestock and poultry management are greatly influenced.

The invention discloses a product design process staging method based on EEG signals, relates to a product design thinking process staging method based on EEG signals, and belongs to the fields of product aided design, knowledge engineering, and intelligent manufacturing. The implementation method of the present invention is as follows: select the basic rhythm wave applicable to the EEG signal in the thinking process of product design, obtain the frequency range corresponding to the basic rhythm wave, collect the EEG signal in the design process of the designer, and decompose the EEG signal by wavelet. Decompose the results and select the frequency range of the basic rhythm wave of the EEG signal to obtain the basic rhythm wave of the EEG; calculate the EEG characteristic parameters of each time window in turn to obtain the characteristic parameter points; perform aggregation based on the density peak value of the characteristic parameters of each window Class analysis to obtain the clustering results of design thinking states based on EEG signals; EEG signal staging based on the clustering results of design thinking states based on EEG signals; use EEG signal staging results to solve engineering problems.

The invention discloses an agricultural product price prediction method based on EMD-ELM, and the method builds an agricultural product price combination prediction model based on empirical mode decomposition (EMD) and an extreme learning machine (ELM) method, and comprises the following steps: firstly collecting agricultural product price time series data; decomposing the original agricultural product price time sequence into a plurality of intrinsic mode functions (IMF) and remainders by utilizing empirical mode decomposition, then respectively predicting the components by using an extreme learning machine, and finally combining prediction results of the components to obtain a prediction value of the original agricultural product price time sequence. According to the invention, prediction is carried out in practical application and the prediction result is evaluated and analyzed, so that the prediction error is extremely small; and compared with prediction methods such as a BP neuralnetwork, the prediction method combining empirical mode decomposition and an extreme learning machine has good agricultural product price prediction performance and can be suitable for prediction ofagricultural product price fluctuation rules.

The oil gas concentration big data intelligent detection system is composed of a measurement parameter acquisition platform and a multi-point oil gas concentration prediction subsystem, the measurement parameter acquisition platform achieves accurate detection of measurement parameters, and the multi-point oil gas concentration prediction subsystem achieves processing of the measurement parameters and oil gas concentration prediction. The accuracy and reliability of oil gas concentration detection are improved; the method effectively solves the problem that the reliable operation and intelligent management of safe production of oil and gas enterprises are greatly influenced due to the fact that the existing oil and gas concentration is not influenced by nonlinearity, large lag, coupling and the like of oil and gas concentration change and the oil and gas concentration is not accurately predicted.

The invention provides a subband ANMF (Adaptive Normalized Matched Filter) based method for detecting a moving object in sea clutter, which comprises the following steps of: (1) processing sea surface pulse echo signals received by a radar by a discrete Fourier transform modulated filter bank to realize subband decomposition; (2) carrying out down-sampling extraction on signals subjected to subband decomposition to obtain decomposed and down-sampled subband signals; (3) constructing the detection statistics of all subbands of a subband ANMF detector based on the decomposed and downsampled subband signals, and independently determining the detection threshold of each subband; and (4) comparing the detection statistics of each subband with the detection threshold of a corresponding subband, and judging whether the object exists. The method reduces the non-stationarity of the speckle component of subband sea clutter, overcomes the difficulty of limited available reference samples, eliminates the trouble of limited pre-supposed conditions, and is applicable to moving object detection in various sea conditions.

The invention discloses a green pepper greenhouse environment intelligent monitoring system based on a subtractive clustering classifier, which is characterized in that: the intelligent monitoring system consists of two parts: a green pepper greenhouse environment parameter detection platform based on a wireless sensor network and a green pepper greenhouse output intelligent early warning system Composition; the present invention provides a green pepper greenhouse environment intelligent monitoring system based on a subtractive clustering classifier. Early warning of green pepper greenhouse yield by environmental temperature and light in green pepper greenhouse.

The invention discloses an intelligent forecasting device for cucumber greenhouse output based on a recursive neural network. Networked cucumber greenhouse parameter detection platform and greenhouse cucumber output intelligent prediction system; the purpose of the invention is to provide a cucumber greenhouse output intelligent prediction device based on recursive neural network, and the intelligent early warning system detects the environmental parameters, soil parameters and parameters of cucumber greenhouse in real time. Cucumber greenhouse production information, so as to improve the production management of cucumber greenhouse and improve economic benefits.

The invention discloses a seawater quality three-dimensional space-time sequence multi-parameter accurate prediction method and system, and the method comprises the steps: obtaining key parameters of seawater quality, and processing the key parameters to obtain target key parameters; obtaining spatio-temporal feature information among the target key parameters based on spatial attention; obtaining predicted future data sequence information based on time attention and the spatio-temporal feature information; and predicting the future water quality multi-parameter content based on the spatial-temporal characteristic information and the predicted future data sequence information to obtain a prediction result. According to the seawater quality three-dimensional space-time sequence multi-parameter accurate prediction method, the extraction rate of seawater quality multi-parameter feature information of a time sequence and a space sequence can be improved; the non-stationarity of seawater quality multi-parameter data is reduced; and the prediction precision of the water quality time sequence and three-dimensional space multiple parameters is improved.

The invention discloses an intelligent early warning system for oil and gas leakage speed of a tanker based on a wireless sensor network. Tank truck oil and gas leakage state parameter collection and intelligent early warning platform, tank truck oil and gas leakage speed intelligent early warning model; the purpose of the invention is to provide a tank truck oil and gas leakage speed intelligent early warning system based on wireless sensor network, the intelligent early warning system real-time Monitor the safety information such as temperature, humidity, pressure, and whether the tanker is leaking during driving, so as to avoid accidents.