946 results about "Non linear mapping" patented technology

The invention relates to the technical field of equipment health state prediction, in particular to a multi-source sensing driven equipment health prediction method and system. The method comprises the following steps: synchronously acquiring equipment temperature, vibration, current and acoustic data through a multi-source sensor, carrying out denoising and standardization processing, dynamically distributing each signal weight to adapt to an equipment operation stage, generating a high-dimensional dynamic feature vector, and embedding a historical smoothing mechanism to realize continuous updating; performing standardization and nonlinear mapping on the features, constructing a dynamic coupling factor matrix to quantify a cooperative relationship between the features, fusing interaction information and adaptively enhancing abnormal features; three-layer progressive health prediction from a local part, a middle-layer subsystem to global equipment is implemented based on coupling characteristics, a trend consistency verification mechanism is introduced, global and middle-layer prediction differences are quantified through residual errors, weights are adaptively corrected, and the equipment health state evolution trend and the risk level are output. According to the method, the multi-working-condition adaptability, the feature coupling sensitivity and the prediction result reliability are remarkably improved.

The invention discloses an HPLCamp (High Performance Liquid Chromatography) based on deep learning. The invention discloses an HRF dual-mode communication adaptive coding modulation and anti-noise method. The method comprises the following steps: acquiring an optical radio frequency signal amplitude-phase change rate and synchronously sampling and normalizing; calculating a node amplitude-phase residual error to generate a nonlinear mapping coefficient; monitoring coherent change to solve a drift trend, adjusting a modulation coding optimization scheme, compensating distortion and outputting an anti-noise result. According to the method, the instantaneous amplitude and phase of the optical radio frequency dual-mode signal are extracted, a multi-dimensional amplitude-phase characteristic matrix is formed in combination with time domain synchronization and a normalization template, differential residual modeling and nonlinear mapping coefficient calculation are carried out between impedance nodes, and dynamic compensation of amplitude-phase mismatch and envelope offset is achieved. A drift trend quantity is generated based on coherent offset parameter differentiation, feedback is provided for modulation format and coding strategy optimization, amplitude equalization and phase correction are completed, the signal synchronization degree and amplitude-phase consistency are improved, and the steady-state response and anti-disturbance performance of a transmission link are enhanced.

The invention discloses a commercial building energy monitoring and intelligent control method and device and a storage medium, and belongs to the technical field of building intelligent control, and the method comprises the steps: collecting data, building a nonlinear mapping relation, and generating an energy consumption demand prediction tensor; injecting an adversarial disturbance sample, and evaluating the robustness of the prediction model; in combination with the energy consumption baseline, performing cross confirmation and correction on the prediction data exceeding the threshold value; performing attribution analysis on the corrected energy consumption sequence to generate an energy consumption attribution map; adjusting the solution of a multi-objective optimization function according to the atlas, and generating an optimal cooperative control strategy; and the comprehensive efficiency is used as a reinforcement learning reward, strategy parameters are iteratively updated, and a control knowledge base is formed. According to the method, a closed-loop control framework integrating robust demand prediction, dynamic attribution analysis, collaborative optimization decision and a self-evolution strategy is adopted, intelligent regulation and control of building energy consumption can be realized, and the long-term adaptive optimization capability is improved.

The invention discloses a fruit and vegetable juice production line equipment fault tracing method, which comprises the following steps of: acquiring parameters such as temperature, pressure, vibration, rotating speed and motor current in real time through a multi-channel sensor, and establishing a working condition characteristic database by combining filtering, normalization, statistics and frequency domain characteristic extraction; based on a support vector regression algorithm, a nonlinear mapping model of working condition features and anomaly detection thresholds is constructed, and dynamic threshold adaptive output and real-time anomaly judgment for different working conditions are realized; according to a detection result, a fault signal is automatically triggered, a model is continuously incremented and trained, the adaptability to new working conditions is improved, the accuracy, intelligence and stability of equipment anomaly detection are effectively improved, misinformation and missing information can be reduced, and the automatic operation and maintenance level of a production line is enhanced.

The invention relates to the technical field of numerical control programming, in particular to a five-axis machining path planning method and system based on data driving, and the method comprises the following steps: obtaining real-time coordinates of each axis of a machine tool, calculating linear velocity and angular velocity components to construct a Jacobian matrix, executing singular value decomposition, and calculating a conditional number ratio by using maximum and minimum singular values; and inputting a nonlinear mapping function to calculate a dynamic penalty factor, generating a rotating shaft weighted item in combination with a rotating shaft identifier, constructing a weighted damping least square objective function, calculating a five-axis motion increment, and accumulating the five-axis motion increment with a real-time coordinate to generate a target absolute position coordinate. According to the method, the pose singularity degree is quantified by monitoring the machine tool pose condition number ratio and converted into the dynamic penalty factor to apply the self-adaptive constraint to the rotating shaft, the severe sudden change of the rotating shaft in the singularity area is inhibited, the tool nose track following error is minimized, and meanwhile smooth distribution of the motion increment is achieved; and the dynamic stability and the surface quality of five-axis linkage machining are improved.

The invention discloses a self-adaptive visual admittance control method fusing fluid characteristics and multi-modal perception, which comprises the following steps: designing a self-adaptive Bingham-shear thickening fluid virtual damping coefficient through nonlinear mapping based on sigmoid, and combining a threshold triggering behavior of a Bingham fluid and a sudden stiffening characteristic under the impact of the shear thickening fluid; the flexibility is enhanced under the action of small force, and the anti-interference capability is improved under impact. Besides, a force auxiliary function based on force amplitude is introduced, an anisotropic compliance strategy is combined, rigidity and damping are dynamically adjusted by identifying the main force direction, and the mechanism can reduce sensitivity to noise of a micro sensor and ensure stability and accuracy in the task execution process. Meanwhile, an environment attraction domain model is established in a feature space, Lyapunov analysis shows that the system has consistent final boundaries, stable convergence is ensured, and secondary correction is supported.

The invention relates to the technical field of ship design optimization, and discloses a hull shape optimization method based on neural network modeling. In the data acquisition stage of the method, initial appearance parameters and hydrodynamic performance data of a ship body are obtained, the appearance parameters comprise geometric dimensions and shape features, and the performance data comprise resistance coefficients and wave-making resistance values. In the neural network construction stage, a neural network model with a multi-layer perceptron structure is trained by using collected data, weights are updated through a back propagation algorithm, and a nonlinear mapping relation between appearance parameters and hydrodynamic performance indexes is established. In the shape optimization stage, the trained neural network model is used for carrying out iterative adjustment on the shape of the ship body, fluid dynamic performance indexes are recalculated through the model after each adjustment until preset convergence conditions are met, and finally optimized ship body shape data are output. According to the method, partial complex calculation is replaced by the neural network, and intelligent optimization of the hull appearance is realized.

The invention relates to the technical field of motor control and sensors, and discloses a displacement error dynamic compensation method, device and equipment and a medium, and the method comprises the steps: obtaining the temperature data and original displacement data of a plurality of temperature measurement points in a moving part and an environment, calling a pre-built nonlinear mapping relation between a temperature gradient and a displacement deviation, and calculating the displacement error of the moving part; based on the nonlinear mapping relation, adaptive filtering is carried out on the temperature data and the original displacement data, a trend component representing temperature drift is separated out, displacement data without the trend component is obtained, and a dynamic compensation instruction is generated based on the trend component and the nonlinear mapping relation; and adjusting the displacement data of which the trend component is removed and outputting compensation displacement data. According to the method, the nonlinear mapping model of the temperature gradient and the displacement deviation is constructed, the drift trend is extracted in combination with multi-point temperature sensing and self-adaptive filtering, the compensation instruction is dynamically generated, accurate real-time correction of the displacement error is achieved, and the responsiveness and accuracy of compensation are improved.

The invention discloses a flow field prediction-oriented full-process automatic joint reduced-order modeling method, which comprises the following steps of: specifying a target physical field parameter space, and randomly generating a sample space according to a Latin hypercube sampling method; constructing a full-process automatic simulation tool chain, driving target physical field numerical calculation and generating a training data set; carrying out singular value decomposition-based intrinsic orthogonal decomposition on the output physical field data, and only retaining first r main feature components to construct a reduced-order data set; constructing a multi-input multi-output full-connection feedforward neural network, and modeling and training a nonlinear mapping relation between input parameters and reduced-order features; new working condition parameters are input, reduced-order features are predicted through the trained neural network, distribution of a target physical field is reconstructed according to a singular value decomposition reduction matrix, and more flexible and reliable technical support is provided for reducing the training cost of a reduced-order model and improving simulation efficiency.

The invention provides a laser remelting process parameter optimization method and system based on a multi-objective optimization algorithm. The method comprises the steps that the range of laser remelting process parameters on the surface of a cladding layer is limited; designing a process parameter combination by using an ELHS method, carrying out a laser remelting experiment by using different process parameter combinations on the premise of keeping the surface quality of the cladding layer consistent, and collecting performance index data after remelting; establishing a nonlinear mapping model between the process parameters and the performance indexes by using a PSO-XGBoost model; a Pareto optimal solution set is obtained through population and individual initialization, non-dominated sorting, congestion degree calculation, optimal solution calculation and global optimization of process parameters by adopting an MOEDO algorithm based on a nonlinear mapping model; and a CRITIC-TOPSIS decision system is utilized to carry out evaluation sorting on the Pareto optimal solution set, and an optimal process parameter combination is screened out. According to the method, the influence of the laser power, the scanning speed and the lap joint rate on the quality and performance of the laser remelting surface can be considered at the same time, and the limitation of traditional single process parameter optimization is broken through.

The invention provides a multi-scale pyramid weighted fusion underwater image enhancement method based on double prior, and the method comprises the steps: obtaining a degraded underwater image, and carrying out the global and local cooperation body color calibration of the degraded underwater image; decomposing the color correction image into a base layer, a detail layer and a noise layer by adopting a variational decomposition algorithm; performing spectral prior and transmissivity loss constraint on the base layer image to obtain a defogged image; fusing the detail layer image and the noise layer image to obtain a filtered image; performing enhancement processing on the filtered image by adopting a nonlinear mapping and contrast enhancement strategy to obtain an enhanced image; performing multi-level feature integration and reconstruction on the defogged image and the enhanced image by adopting a multi-scale pyramid adaptive weighted fusion method to obtain an underwater image with natural color and high visual definition; according to the method, the traditional image processing and variational optimization thought is combined to effectively correct the color deviation of the degraded underwater image, the image contrast and the detail definition are improved, and the visualization effect of the underwater image is improved.

The invention discloses a lithium battery SOH prediction method fusing data driving and empirical model physical constraint. The lithium battery SOH prediction method comprises the steps of extracting a health feature vector based on current data in a constant-voltage charging stage from battery operation data; constructing a data driving model to establish nonlinear mapping between the health feature vector and the SOH, and outputting an SOH estimated value; constructing an empirical model to represent the physical decline trend of the SOH along with the number of cycles; in the online operation process, the deviation between an SOH estimated value and an SOH predicted value output by the empirical model is monitored, and when the deviation exceeds a preset threshold value, an SOH estimated value sequence in a historical time window serves as a target, and empirical model parameters are updated through an optimization algorithm to enable the empirical model parameters to approach the actual aging rate of the battery; on the basis of the SOH change rate represented by the updated empirical model, constructing a physical constraint item, fusing a training loss function of the data-driven model, and carrying out secondary training on the data-driven model to correct parameters; and utilizing the corrected data to drive the model, and outputting an SOH prediction result.

The invention provides a lithium ion battery safety valve opening and failure early warning method based on expansive force, and belongs to the technical field of lithium ion batteries. Battery expansive force and cycle data under different pre-tightening force conditions are collected, statistical features are extracted to construct a state feature set, health state groups are divided by adopting a fuzzy clustering algorithm, and the early warning result is obtained. Establishing a segmented nonlinear mapping model of the expansive force and the internal pressure, performing wavelet denoising and robust differential calculation on expansive force signals, and optimizing an initial expansive force derivative threshold value by analyzing time dispersion at different heating rates; a multi-scale feature fusion algorithm based on hierarchical attention aggregation is utilized to construct a state self-adaptive early warning model to correct a threshold value, and a four-stage early warning mechanism is set to monitor the opening and failure states of the safety valve. The technical problem that the opening time of the safety valve cannot be accurately predicted and self-adaptive early warning cannot be realized under different battery health states and pretightening force working conditions is solved.

The invention relates to the technical field of data fusion, in particular to a multi-source electrocardiosignal correction method and system based on adaptive fusion, and the method comprises the following steps: constructing a multi-channel input tensor, extracting local features through a weight calculation network, carrying out the adaptive weight fusion and dimension reduction of multiple paths of signals, and carrying out the correction of the multi-source electrocardiosignal. A nonlinear mapping relation is established through a deep reconstruction network, a standard waveform is reconstructed, and network parameters are optimized based on reconstruction error reverse iteration. According to the method, local neighborhood features of multichannel signals are extracted by constructing a weight calculation network, a dynamic channel weight sequence reflecting the real-time contribution degree of a signal source is constructed, the amplitude intensity is adaptively adjusted according to the signal quality, unstable channel noise interference is effectively inhibited, and high-quality signal components are enhanced; a deep reconstruction network is used for carrying out nonlinear feature transformation on a fusion sequence, accurate mapping from non-standard input to standard lead waveforms is established, and weight distribution and optimization of signal reconstruction parameters are achieved in combination with an error back propagation mechanism.

The invention relates to the technical field of industrial equipment state monitoring and fault diagnosis, in particular to a trend fault prediction method based on cooperation of a dynamic mode and a threshold value. According to the method, a theoretical prediction interval dynamically changing along with a load is generated in real time by establishing nonlinear mapping between working conditions and key parameters, parameter drift interference caused by working condition fluctuation is effectively eliminated, a real-time health baseline of equipment is quantified in combination with maintenance records, and the width of an early warning threshold value is cooperatively adjusted according to feature similarity and the health level. Self-adaptive monitoring of different aging stages of the whole life cycle is realized, mode matching is performed by utilizing multi-dimensional feature vectors and fusing physical field information, deviation severity and form similarity are comprehensively evaluated through fuzzy reasoning, abnormity is locked in advance according to high feature goodness of fit when a numerical value does not seriously exceed a limit, and a real-time monitoring result is obtained. Early weak symptoms are accurately captured, abnormal sources are output, and the diagnosis precision under variable working conditions is remarkably improved.

The invention discloses a glacier change prediction method and system, and belongs to the technical field of glacier monitoring. According to the method, on the basis of the glacier material balance model based on data driving, the feedback mechanism of glacier form evolution on the glacier material balance and dynamic process is considered at the same time, and the uncertainty of the glacier change prediction result is reduced through iterative processing, so that the accuracy of predicting the future change of the glacier is improved. On the basis, the glacier material balance model adopted by the invention comprises a dimension reduction module, an attention mechanism module and a mapping module; a dimension reduction module and an attention mechanism module are combined to learn a nonlinear mapping relation between a glacier meteorological parameter sequence and glacier morphological parameters and glacier material balance data, multi-scale features of time sequence data can be fully mined, and errors of glacier material balance estimation are further reduced.

The invention provides a gear peeling time-varying meshing stiffness prediction method and system based on a back propagation neural network, and the method comprises the steps: considering a tooth surface peeling fault based on a gear tooth bearing contact analysis method, and constructing a helical gear pair time-varying meshing stiffness calculation model; a real irregular tooth surface peeling area is fitted by adopting a least square ellipse fitting method to obtain an ellipse appearance representation, any peeling position is completely described through six key geometric parameters, the geometric parameters of the ellipse appearance are systematically traversed and fitted, and diversified peeling appearance samples are generated. Introducing a tooth profile deviation matrix corresponding to the peeling morphology sample into a tooth surface bearing contact analysis model, and constructing a training data set; and constructing a back propagation neural network model of multiple hidden layers, and performing end-to-end training by using the training data set, so that the back propagation neural network model learns a nonlinear mapping relationship from geometric parameters to a time-varying meshing stiffness curve, thereby predicting the time-varying meshing stiffness under any peeling morphology.

A power transmission tower grounding resistance non-contact measurement method based on the electromagnetic coupling principle comprises the following steps that transmitting and receiving electromagnetic coupling coils are arranged around an iron tower grounding body, and geometric calibration and spatial positioning of a measurement area are completed by combining grounding grid structure parameters and soil conduction characteristics; injecting a high-frequency alternating-current excitation signal into the transmitting coil, and synchronously acquiring the amplitude and phase response of the induced voltage at a receiving coil end; carrying out filtering processing on the induction signal by adopting a time-frequency analysis and phase decoupling algorithm, and solving a function relationship between electromagnetic response and grounding impedance by combining a coupling equivalent model; based on experimental calibration data and scene parameters, a nonlinear mapping model of induction response and grounding resistance is constructed, and real-time inversion calculation is carried out by combining a solving result obtained in the third step. According to the invention, the real-time accurate measurement of the grounding resistance under the conditions of no power failure and no wire breakage is realized, and the safety, the operation convenience and the anti-interference capability in a complex environment in the measurement process are obviously improved.

The invention discloses a laser scanning system, and belongs to the technical field of laser signal processing. The system comprises a laser emission and control module, a scanning device, a receiving device, a signal processing module and a self-adaptive learning module. And the signal processing module extracts the instantaneous frequency of the beat signal through Fourier transform and Hilbert transform, and dynamically adjusts the input voltage based on an iterative algorithm optimized by the adaptive learning module to realize linearization correction of the beat signal frequency and a nonlinear mapping linearization interpolation scheme. The adaptive learning module stores historical correction data, dynamically optimizes parameters such as step length and convergence conditions of an iterative algorithm by using a machine learning method, and improves the adaptability and correction precision of the system in a complex environment. According to the method, full-closed-loop intelligent control from signal acquisition and processing to parameter optimization is realized, and the method has the characteristics of high precision, strong robustness and low manual intervention, and is suitable for the fields of laser radar, three-dimensional scanning, precise distance measurement and the like.

The invention discloses a single image defogging method based on block-by-block nonlinear brightness prior, which belongs to the technical field of image processing, and comprises the following steps of: dividing a fog-containing image into local blocks, calculating the average brightness of the blocks, and constructing prior block-by-block monotone increasing nonlinear mapping to represent the corresponding relationship between the brightness of fog-containing blocks and the brightness of clear blocks; an atmospheric scattering model is combined, an atmospheric light vector is modeled into a vector, the vector and a PPWF form a parameterized recovery model, three scalar parameters are taken as a core, an optimal parameter is obtained through multi-target joint optimization, alternate optimization and golden section search, and finally a defogged image is generated. The method has the advantages of few parameters, low complexity and no need of training data, the definition and global contrast of far and near scenery can be remarkably improved while the image structure is maintained, and halo, excessive enhancement and color cast are effectively inhibited; the method has good robustness for different fog densities and illumination conditions, and is suitable for real-time and embedded defogging application of single-channel or multi-channel images.

The invention relates to an energy efficiency model establishing and dynamic updating method based on mechanism and data driving fusion. The method comprises the following steps: establishing an equipment mechanism energy efficiency model; collecting real-time operation data of the equipment and preprocessing the real-time operation data; extracting actual measurement energy efficiency of the equipment from the preprocessed real-time operation data, and obtaining mechanism prediction energy efficiency based on an equipment mechanism energy efficiency model; calculating a difference value between the actual measurement energy efficiency and the mechanism prediction energy efficiency as an energy efficiency deviation; extracting and screening performance degradation characteristics from the historical operation data; establishing a nonlinear mapping relation between the energy efficiency deviation and the screened performance degradation characteristics by adopting a machine learning algorithm, namely an equipment data driving correction model; and fusing the initial mechanism energy efficiency model and the data driving model to obtain an equipment energy efficiency fusion model, and training and optimizing the equipment energy efficiency fusion model. According to the method, self-adaption and automatic establishment and updating of the energy efficiency model can be achieved, and it is ensured that the energy efficiency model keeps high precision and high robustness in the whole life cycle.

The invention provides three-dimensional vehicle-mounted navigation equipment and a navigation method based on the equipment. The method comprises the following steps: carrying out equipment initialization and reference calibration, arranging communication equipment on a vehicle roof, arranging acquisition equipment on a vehicle head grid, and arranging a calibration and calculation module in a vehicle cabin; synchronously acquiring multi-source scene and body state data by using hardware; identifying an operation scene through a CNN-LSTM hybrid model, and dynamically allocating a sensor fusion weight based on a reinforcement learning algorithm; a BP neural network is utilized to construct nonlinear mapping of the vibration frequency and the positioning error, and a dynamic error value is calculated; the dynamic error is substituted into extended Kalman filtering for real-time correction, and vibration influence is eliminated; the method comprises the following steps: pre-judging a GNSS signal trend by using an LSTM model, and initializing a backup module in advance to realize multi-mode seamless switching; dynamically adjusting map updating frequency according to environment change and compressing data by using an octree; and outputting a three-dimensional navigation instruction on the display screen. The problems of high-precision positioning and smooth switching of the engineering vehicle under strong vibration and complex scenes are effectively solved.

The invention provides a user behavior intention recognition method and device based on multi-modal data fusion, and relates to the technical field of data processing.The method comprises the steps that a multi-modal observation sequence is obtained, initial features are formed through time synchronization and mutual information screening, a cross-space initial offset vector is generated in combination with virtual space offset parameters, and the cross-space initial offset vector is obtained; establishing an association relationship between a real action and a virtual action through nonlinear mapping to obtain a cross-space registration feature; generating a correction coefficient according to the proportion of the real action amplitude and the virtual action amplitude, and performing amplitude correction to obtain a cross-space correction feature sequence; compensating rendering delay and synchronous drift by using weighted fusion of the current feature and the lag feature to obtain a time sequence correction feature; outputting cross-space fusion features through a unified embedding space and a cross-modal attention mechanism; and non-linear intention mapping is constructed based on the fusion features, and a user behavior intention result is inferred and output in combination with time smoothing. According to the invention, the accuracy of user behavior intention analysis in a virtual field scene can be improved.

The invention relates to the field of space-time missing signal reconstruction, in particular to a modal parameter identification method, device and equipment for a space-time missing vibration signal, and the method comprises the following steps: 1, extracting modal parameters, giving a two-dimensional missing signal X, carrying out the PCA initialization of the missing signal through PCA modal decomposition, obtaining initial data, carrying out the dimension reduction of the signal, and extracting a principal component; 2, performing SRCNN and PCA joint optimization, taking a modal parameter space modal matrix U and a time coefficient matrix V of the PCA as constraint conditions of the SRCNN, and reconstructing missing data by utilizing the nonlinear mapping capability of the SRCNN and combining the global features of the PCA; and step 3, alternately optimizing the SRCNN parameter and the PCA parameter, and reconstructing a signal and a modal parameter. A vibration signal can be effectively reconstructed from the space-time field, the noise of the signal can be reduced, and the signal reconstruction precision can be improved.

The invention discloses a multivariable time sequence feature extraction and grade prediction method and system for a flotation process and a storage medium. The method comprises the steps that S1, original data are input and coded; carrying out coding and structured input on time sequence data formed by various process variables; s2, extracting dynamic characteristics; s3, modeling based on condition guidance coding; s4, enhancing the significance of the key variable and the important time slice; a multi-head attention mechanism is adopted, and a query vector based on target guidance is matched with a key value pair generated by multi-scale features; s5, outputting a prediction module; and carrying out feature fusion and nonlinear mapping on an attention mechanism output result, and outputting a concentrate grade and recovery rate prediction result at a future moment. The system and the storage medium are both realized based on the method. The method has the advantages of being higher in intelligent degree, better in controllability, capable of improving prediction accuracy and model adaptability of key indexes in the flotation process and the like.

The invention discloses a data asset visualization and collaborative governance method and system based on an AI agent, and the method comprises the steps: carrying out the mapping of attribute parameters, such as the type, scale, value and the like, of data assets, building a feature space, completing the nonlinear mapping from high dimension to low dimension through a t-SNE model, and achieving the visualization feature presentation of the data assets. Initializing a deep Q network agent, setting a reward function by taking visual features as a state space, governance operation as an action space and parameter change, selecting actions by the agent according to the reward function to execute collaborative governance, and storing empirical data into a buffer region to train the network; and training is repeated until network convergence, and a visual and cooperative treatment strategy is generated. The system is composed of a data asset feature mapping unit, a t-SNE conversion unit, an agent initialization unit and the like, all the units are mutually connected and cooperatively operate, data asset visualization and intellectualization and automation of cooperative governance are achieved, and the data asset management efficiency and the value mining capacity are effectively improved.

The invention discloses a wind field yaw wake flow hybrid modeling method and device fusing simulation and deep learning. The method comprises the following steps: firstly, introducing a yaw-corrected actuating disc model, constructing a volume force source item under the yaw action of each fan, performing steady-state computational fluid mechanics simulation on the yaw wake flow of the wind field by combining a Reynolds average Navier Stokes method and a k-epsilon turbulence model, and constructing a yaw wake flow database of the wind field; and then, training the yaw wake flow database by using a deep neural network, and learning a nonlinear mapping relationship between a wind field input wind speed and a multi-fan yaw angle combination and an incoming flow wind speed of each fan, so that a wind field yaw wake flow data driving model is established, and real-time prediction of wake flow characteristics under non-consistent yaw configuration is realized. Compared with an existing yaw wake flow model, the method has the advantages that the technical difficulty of wake flow modeling of multi-fan non-consistent yaw is effectively solved, the prediction speed is remarkably increased while the modeling precision is improved, and the method has high engineering application value.

The invention discloses a new energy truck carbon emission model adaptive optimization method and system, and belongs to the technical field of model optimization, and the method specifically comprises the steps: obtaining the related data of a new energy truck in the operation process, generating a working condition feature vector corresponding to the parameters of a carbon emission model through nonlinear mapping, and carrying out the adaptive optimization of the carbon emission model based on the working condition feature vector, a layered reinforcement learning reward function is established, the reward function takes the minimum deviation between the predicted emission amount and the actual emission amount as a first-layer target and takes the energy consumption efficiency and the operation stability as a second-layer target, and in the reinforcement learning iteration process, a nonlinear correction factor is generated according to the feedback of the reward function; dynamically adjusting the coefficient of the carbon emission model by using the nonlinear correction factor, and performing adaptive optimization under multiple working conditions and extreme working conditions; according to the carbon emission model, continuous self-learning and self-optimization under multiple working conditions and extreme working conditions can be realized, and the adaptability, generalization and operation stability of the model are remarkably improved.

The invention discloses a lightweight multi-mode lower limb motion intention recognition method and system, and relates to the technical field of biomedicine. The method comprises the steps that multi-channel surface electromyogram signals sEMG of a target lower limb and joint angle signals and joint torque signals of lower limbs on the same side are synchronously collected; performing feature extraction by using a double-branch structure to obtain muscle-related deep time sequence features and joint-related high-level semantic features; performing feature fusion through a bidirectional cross attention mechanism to obtain cross attention fusion features; and performing flattening, nonlinear mapping, regularization and Softmax classification on the cross attention fusion features, and outputting the motion intention of the target lower limb. Through double-branch input, depth feature extraction and a bidirectional cross attention mechanism, on the premise of ensuring recognition precision, a lightweight attention module, a residual structure and a cross-modal interaction mechanism are introduced, and the parameter quantity and calculation overhead are reduced.

The invention relates to the technical field of photovoltaic power generation power prediction and artificial intelligence, and discloses a SparseKAN photovoltaic power prediction system fusing multi-time scale characteristics, which divides meteorological and time characteristics related to photovoltaic power into instantaneous characteristics, short-term characteristics and long-term characteristics based on a multi-scale characteristic decomposition thought. The method comprises the following steps: respectively inputting to corresponding KAN sub-networks for modeling, fully extracting a nonlinear mapping relationship under different time scales, performing adaptive weighting on output results of each sub-network through a gating fusion mechanism, dynamically adjusting contribution proportions of instantaneous, short-term and long-term characteristics in prediction, and performing prediction to obtain a prediction result. Therefore, a photovoltaic power prediction result which is more robust to complex time sequence changes is obtained, so that the system not only can capture instantaneous fluctuation and continuous trend of meteorological conditions, but also can identify time periodic characteristics, and finally multi-scale collaborative modeling and fusion prediction of photovoltaic power are realized.