709 results about "Energy based" patented technology

The invention discloses a multi-mode pet health monitoring and motion artifact elimination method and system based on a millimeter wave radar, and relates to the technical field of pet health monitoring, and the method comprises the following steps: S001, building a unified time baseline and an energy fingerprint auditing surface, constructing an energy distribution model from a chest to a tail, and taking the model as a reference for artifact evolution, identifying a signal spectrum coupling trend in a time-frequency domain; and S002, based on the energy distribution model, performing causal playback on continuous time sequence signals acquired by the millimeter-wave radar, extracting a pseudo-motion energy nucleus caused by tail or limb movement, and calibrating a phase anchor point and a space observation area of a respiratory signal. According to the method, multi-source physiological data are fused, pure respiratory signals are extracted through energy distribution modeling, causal playback, phase anchor point calibration and three-dimensional resampling, risk assessment is achieved based on physiological credibility tensor, and the accuracy and anti-interference capacity of health monitoring are improved by combining phase conjugate traction and a space-time regulation strategy.

At least one example embodiment provides a system for controlling a heater in a non-combustible aerosol-generating device, the system comprising a memory storing computer-readable instructions and a controller configured to execute the computer-readable instructions to cause the non-combustible aerosol-generating device to apply a first power to the heater based on a first preheat temperature determine an estimated energy applied to the heater during application of the first power, and apply a second power to the heater based on the estimated energy, an energy threshold and a second preheat temperature, the second power being less than the first power.

The present invention relates to the technical field of intelligent out-of-distribution fault detection for construction machinery, and discloses an out-of-distribution fault detection method and system based on energy propagation and graph learning, and the method includes: acquiring vibration acceleration signals in typical fault states, carrying out similarity calculation to obtain an adjacency matrix composed of the maximum mutual information coefficients, and taking the adjacency matrix as input in a graph neural network; carrying out feature extraction on the adjacency matrix through adopting a GraphSage graph convolution method, and generating each node representation; calculating an energy score of each node, and distinguishing between in-distribution data and out-of-distribution data; and enhancing out-of-distribution data confidence estimation for each node, and carrying out out-of-distribution data identification and out-of-distribution data detection under different working conditions of a rolling bearing.

The invention discloses a vibration signal denoising reconstruction method and device based on machine learning and a medium, and relates to the technical field of data processing. The method comprises the following steps: firstly, carrying out adaptive time-frequency decomposition on an original signal, and then identifying a noisy dominant component based on energy entropy and kurtosis; then, a generative adversarial network is constructed, denoising is carried out through joint optimization of adversarial loss and frequency domain perception loss, high-level semantic features of the frequency domain perception loss are extracted through a convolutional network pre-trained on bearing fault data, and it is ensured that high-frequency impact and modulation features related to a bearing structure and a defect type are reserved; and finally, reconstructing the de-noised component and other components, and outputting a high-quality signal. The method does not need a clean label, effectively inhibits complex noise, and improves the fault diagnosis reliability.

The invention relates to the technical field of geodetic survey and structural health monitoring, and discloses a GNSS-RTK coordinate domain error correction method, which comprises the following steps: acquiring GNSS-RTK dynamic observation data to form a mixed signal time sequence; executing an improved adaptive noise complete empirical mode decomposition algorithm on the sequence to obtain an intrinsic mode function component; identifying and eliminating high-frequency components representing Gaussian white noise based on an energy coefficient, and reconstructing residual components into a signal sequence after primary noise reduction; inputting the noise reduction sequence into a rapid independent component analysis model for blind source separation; and finally, carrying out sorting and phase and amplitude uncertainty correction on the separated independent components, and outputting a multi-path error model and a structure dynamic deformation signal. According to the method, the problem of blind source separation failure or low precision caused by strong noise covering source signal statistical characteristics is solved through a strategy of first noise reduction and then separation, and an effective physical signal can be accurately extracted from a strong noise background.

The invention relates to the technical field of industrial automation control and dynamic simulation, and discloses a centralized control console and 3D model linkage virtual-real simulation system, which comprises a control signal sampling interface, a load response modulation unit, a dynamic model evolution unit and a virtual-real closed-loop feedback unit, the load response modulation unit performs energy consumption weight accumulation on all the virtual controlled objects in transient action to generate a global time scaling factor so as to correct an inertia time constant of the system in real time; the dynamic model evolution unit introduces a hard limiting boundary by using an amplitude limiting link and calculates a process variable; the virtual-real closed-loop feedback unit extracts a control deviation signal and drives a physical instrument to generate a nonlinear damping action, and by establishing a global load modulation model based on energy constraint, a discrete control system spontaneously emerges a nonlinear hysteresis characteristic conforming to physical energy conservation under the low calculation power condition without complex fluid network solution.

Systems and methods are provided for modeling and for providing a graphical representation of tissue heating and electric field distributions for medical treatment devices that apply electrical treatment energy through one or a plurality of electrodes. In embodiments, methods comprise: providing one or more parameters of a treatment protocol for delivering one or more electrical pulses to tissue through a plurality of electrodes; modeling electric and heat distribution in the tissue based on the parameters; and displaying a graphical representation of the modeled electric and heat distribution. In another embodiment, a treatment planning module is adapted to generate an estimated target ablation zone based on a combination of one or more parameters for an irreversible electroporation protocol and one or more tissue-specific conductivity parameters.

The technology described herein is directed towards a reconfigurable intelligent surface (RIS) that harvests RF energy from incoming signals based on energy harvesting antennas and associated energy harvesting circuitry. At the same time RIS elements (unit cells) redirect the incoming signals towards a predetermined direction. The harvested energy is combined and converted to DC power using a harvesting circuit. In one implementation, a dual-mode energy harvesting circuit employs a higher power rectifier subcircuit and a lower power rectifier subcircuit, with a multiport circulator and switch that self-actuates to use one or the other rectifier subcircuit based on the combined RF input power captured by the energy harvesting antennas. A multiple battery approach is described, in which one battery is charging based on the converted DC power, another, previously-charged battery is powering the reconfigurable intelligent surface components.

The invention discloses a device and a method for simulating heat exchange and friction resistance measurement of an aviation high-speed motor under different working conditions, and relates to the field of heat management of high-speed rotating equipment. An additional heating sheet is attached to the outer surface of the inner rotor, and different surface structures are detachably assembled on the outer rotor to form a stator and rotor slit flow channel boundary; cooling liquid forms one-inlet and one-outlet forced convection through the radial through hole of the end cover. The rotating speed larger than or equal to 20,000 rpm, runner pressure drop and temperature data are synchronously collected through an axle load type sensor, and the heat exchange coefficient, the flow resistance coefficient and the friction resistance coefficient are calculated in real time based on energy conservation, a Darcy formula and a torque empirical formula. A real rotor surface structure is reproduced under the condition of high-speed rotation, working medium leakage is restrained through mechanical sealing, and runner blockage caused by centrifugal deformation of the surface structure is prevented through the outer rotor designed in an integrally-formed mode; the obtained convective heat transfer-resistance coefficient-friction resistance coefficient all-parameter curved surface database can guide optimization of the cooling flow channel of the aviation motor.

The invention relates to an ancient building green repair cost optimization method combined with carbon footprint analysis, and relates to the technical field of green buildings, and the method comprises the steps: obtaining the structural damage and functional decline problems of a to-be-repaired ancient building; based on the structural damage and functional decline problems of the to-be-repaired ancient building, a repair project of the to-be-repaired ancient building is determined; based on the repair project of the to-be-repaired ancient building, determining multiple repair schemes of the to-be-repaired ancient building; for each repairing scheme, determining a production carbon emission factor, a transportation carbon emission factor and a carbon emission factor of construction energy of each repairing material of the repairing scheme, and determining the carbon emission factor of the construction energy based on the production carbon emission factor, the transportation carbon emission factor and the carbon emission factor of the construction energy of each repairing material of the repairing scheme; performing carbon footprint analysis on the repairing scheme, and calculating the total carbon emission of the repairing scheme; the optimal repairing scheme is determined based on the total carbon emission of the repairing scheme, and the method has the advantage of reducing the carbon emission of ancient building repairing.

The invention discloses a new energy automobile endurance mileage increasing system and method based on multi-mode energy collaborative management. The system comprises a multi-mode energy input module which is used for converting solar energy into direct current electric energy through a photovoltaic array and integrating power battery energy and hub motor kinetic energy recovery energy; the predictive management module is used for acquiring front road condition information through a V2X technology and predicting an energy consumption curve based on a deep learning model; the dynamic weight distribution module is used for calculating photovoltaic, battery and kinetic energy recovery weight coefficients through a dynamic weight distribution algorithm according to the real-time vehicle environment information and the prediction result; and the energy distribution control module is used for carrying out weighted distribution on the multi-modal energy based on the weight coefficient and outputting total available energy and a control signal so as to drive electric equipment or charge a battery. According to the invention, the problem of dynamic energy distribution during multi-energy coupling is solved, and the purposes of improving the endurance of urban roads, improving the endurance of expressways, reducing the increment cost of the system and being compatible with a 400V / 800V platform are achieved.

The invention discloses a multi-energy complementary optimal configuration method and system for a new energy base, and belongs to the technical field of power system planning. The method comprises the following steps: acquiring energy base system operation parameters, power generation equipment parameters, delivery channel capacity and power market electricity price data; constructing an optimal configuration model taking a receiving end time-of-use electricity price signal as input and aiming at stabilizing new energy output fluctuation and meeting delivery channel constraint; solving the model to obtain a thermal power, wind power, photovoltaic and energy storage capacity configuration scheme and a time sequence output plan; and determining a final optimal configuration scheme by analyzing the operation stability and delivery power volatility of the configuration scheme in different pricing modes. According to the method, the technical problem that the influence of the receiving end electricity price market is not fully considered during optimal configuration of the existing new energy base is solved, an optimal configuration scheme which meets the technical constraint and adapts to the market environment can be generated, and the operation economy and stability of the new energy base are remarkably improved.

A distributed system and method for compressing and restoring data across edge computing devices and cloud infrastructure is disclosed. The system dynamically adjusts compression based on available computing resources, network conditions, and now energy constraints. Edge devices monitor power consumption and battery levels, optimizing compression parameters to extend battery life while maintaining data quality. A workload scheduler prioritizes tasks based on energy availability, offloading intensive processing to cloud infrastructure when necessary. The system utilizes an energy-aware coordination layer to balance workloads across multiple devices, ensuring efficient data flow and long-term operational stability. Homomorphic operations allow secure distributed processing on compressed data, while an adaptive neural upsampler enhances reconstructed outputs. By integrating energy optimization, the system improves performance and longevity of edge devices in power-limited environments.

The invention discloses a data management system and method based on artificial intelligence, and relates to the technical field of data intelligent processing, and the method comprises the steps: carrying out the frequency spectrum transformation of an encrypted feature vector, calculating the energy density of each frequency spectrum coefficient, constructing a cumulative distribution function, determining an effective frequency spectrum interval based on the energy distribution function, and constructing a projection matrix. Compressing the spectrum vector to a low-dimensional space by using a projection matrix to generate a compressed feature vector; and constructing a neural network model to calculate an abnormal score, setting a detection threshold, performing label detection on the abnormal score, forming a label vector, performing homomorphic decryption on the label vector, and generating a plaintext feature vector. According to the method, a frequency spectrum energy distribution function is introduced on the basis of homomorphic encryption, safe dimensionality reduction and rearrangement of feature vectors are realized by combining periodic mapping and an integer mechanism, the structural identifiability of the feature vectors in a finite field is enhanced, an offset period is optimized through a fluctuation potential function, and the sensitivity to abnormal changes is improved.

The invention discloses a greenhouse climate multi-target intelligent control method fusing rule constraint and reinforcement learning, and relates to the technical field of agricultural environment control, and the method comprises the following steps: building a temperature and humidity dynamic model based on an energy conservation law, and coupling an external environment disturbance term to obtain a temperature and humidity dynamic model; establishing a mapping relation among the temperature, the relative humidity and actuator input data, generating multiple groups of interval training data based on the mapping relation, constructing an intelligent decision model, and screening out an optimal actuator state vector by taking the deviation degree of an environment target value and an interval range as an evaluation criterion; and setting a difference mediation threshold value of mutual exclusion operation for safety correction, adopting environment adjustment difference and energy consumption minimization as optimization objectives, designing a multi-objective reward function, and determining an optimal control instruction, thereby updating an intelligent decision-making model, realizing accurate and efficient greenhouse climate control, enabling the comprehensive control of temperature and humidity to be more accurate and reasonable, and improving the reliability of the greenhouse climate control. And the energy consumption is reduced.

The invention relates to the crossing field of artificial intelligence and material science, and provides an automatic generation method and system for a hydrogel formula for an ultrathin lens based on energy guidance, and the method comprises the steps: constructing a component feature space; establishing a free energy density function fusing a Flory-Hugins theory and elastic network correction, wherein the free energy density function is used for predicting a swelling ratio, a modulus and a diffusion coefficient; deploying a generative adversarial network, and introducing an energy guide item formed by a mean square error of prediction performance and target performance into generator loss; and enabling the generator to output a feasible formula meeting triple performance constraints through iterative training. The system supports Monte Carlo sampling screening, diversity enhancement, cross-scene migration adaptation, real-time error feedback correction, manufacturable hard constraint filtering and multi-target Pareto frontier exploration. An AI frame is deeply embedded through a physical model, the realizability of formula thermodynamics is ensured, the design precision, generalization ability and industrial applicability are remarkably improved, and automatic closed-loop evolution of hydrogel intelligent design is achieved.

The invention discloses a large-section tunnel blasting control method and system based on an energy dissipation mechanism, and the method comprises the steps: constructing a blasting region three-dimensional geomechanical model of rock mass mechanical parameters, and mapping the energy demand distribution of each point; based on the model, establishing a stress wave field propagation and interference prediction model for predicting a space-time stress field under any microsecond-level delay sequence; constructing a multi-target fitness function, and solving through intelligent optimization algorithms such as a non-dominated sorting genetic algorithm and the like to obtain an optimal microsecond-level delay sequence; the sequence is issued to a plurality of electronic detonators through a high-precision synchronization and safety protocol to execute detonation; and collecting actual blasting monitoring data, comparing the actual blasting monitoring data with a model prediction result, and carrying out adaptive correction on geologic model parameters by applying extended Kalman filtering. According to the method, the stress wave field interference is actively constructed to realize distribution of energy according to needs, multiple blasting targets are considered, and continuous optimization is performed through feedback, so that the blasting precision, safety and economical efficiency are improved.

The invention belongs to the technical field of lattice tower structure health detection, and relates to a lattice tower rod piece missing intelligent detection method based on multi-view three-dimensional reconstruction. According to the method, an adaptive feature matching algorithm fusing geometric features and texture descriptors is provided, camera pose estimation is optimized by constructing a global depth consistency scoring mechanism, and high-precision sparse point cloud reconstruction is realized; designing a depth map optimization strategy based on energy minimization, and effectively overcoming the interference of complex illumination and a low-texture environment on three-dimensional reconstruction in combination with density threshold filtering and geometric structure feature analysis; an ordered / disordered point cloud adaptive noise reduction method is innovatively provided, and noise robustness processing is realized through gradient constraint and covariance matrix eigenvalue analysis; and finally, an improved neighborhood radius adaptive registration algorithm is adopted, and a rod piece missing region is accurately identified through a significance scoring mechanism. The method remarkably improves the automation level and reliability of rod piece missing detection, and can be widely applied to structural health detection of the lattice tower.

The invention discloses an energy management method and system for a fuel cell vehicle. The method comprises the steps of obtaining vehicle driving parameters and power battery parameters; identifying a current driving condition according to the vehicle driving parameters; evaluating the working intensity of the power battery based on the power battery parameters to obtain a working intensity index of the power battery; determining target output power of the fuel cell by adopting a fuzzy control rule according to the driving working condition, the SOC of the power cell, the working intensity index and the required power of the whole vehicle; and managing the energy of the fuel cell vehicle based on the target output power of the fuel cell. The method has the advantages of dynamically adapting to complex working conditions, optimizing the energy distribution efficiency and prolonging the service life of the fuel cell and the power cell.

The invention discloses an energy recovery control method and system for a vehicle, the vehicle, a computer readable storage medium and a computer program product, and the method comprises the steps: obtaining the road condition information and traffic information around the vehicle in the driving process of the vehicle; wherein the road condition information comprises road condition information of the vehicle before the current driving moment and road condition information of the current driving moment; based on the road condition information and the traffic information, predicting a braking demand level in a preset period to determine corresponding energy recovery intensity; and outputting an energy recovery instruction based on the energy recovery intensity to control the vehicle to perform energy recovery at the starting moment of the preset period. By means of the technical scheme, the problems that an existing vehicle is single in energy recovery strategy and lack of pre-judgment capacity can be solved, energy recovery control in advance is achieved by actively predicting the braking requirement, the energy recovery efficiency is remarkably improved, and the braking comfort is improved.

The invention discloses a power distribution network fault accurate positioning method based on a graph convolutional neural network, and relates to the technical field of power distribution network intelligent fault diagnosis, and the method comprises the steps: collecting multi-source operation data in the operation process of a power distribution network, and generating a multi-source synchronous operation data set through time synchronization, format unification, abnormity elimination and dimension standardization processing; performing node association analysis and electrical connection relation calculation on the multi-source synchronous operation data set, and outputting a power distribution network topology feature graph; constructing an energy topology joint embedding expression through energy feature extraction and structural feature fusion mapping of the power distribution network topology feature map, and outputting a fusion feature matrix through feature space mapping and high-dimensional vector coding based on the energy topology joint embedding expression; and performing fault feature analysis and node classification judgment on the fused convolution feature matrix, and outputting a fault positioning result. And high-precision perception and identification of a complex fault mode are realized.

The invention relates to the technical field of signal processing, and discloses a periodic abnormal sound adaptive identification method, which comprises the steps of dividing a time domain detection signal of equipment to be detected based on a frequency domain and a time domain, obtaining corresponding sub-signals in candidate frequency bands, calculating a comprehensive score based on various frequency spectrum characteristics of the sub-signals, and obtaining a periodic abnormal sound adaptive identification result. Obtaining a final score of each candidate frequency band, and taking the candidate frequency band with the highest final score as a target frequency band; and constructing a self-adaptive threshold value based on the median of the sliding window and the absolute deviation of the median, and judging whether the periodic abnormal sound exists or not based on the energy curve and the self-adaptive threshold value through an equal interval condition that the interval range is not greater than a preset tolerance and a persistence condition that the number of peak values is not less than a preset minimum peak number. According to the method, the target frequency band is accurately obtained by integrating multiple frequency spectrum features, the missing detection rate and the false detection rate are reduced from the source, the detection robustness is guaranteed through the self-adaptive threshold value, and meanwhile accurate recognition of the periodic abnormal sound is achieved based on the equal-interval and continuous conditions.

The invention relates to the field of laser processing, and particularly discloses a fillet structure laser shock peening residual stress control method based on energy compensation, which comprises the following steps: accurately measuring and quantifying residual stress fluctuation and a tensile stress area caused at a fillet in the prior art, and setting a peening target according to the residual stress fluctuation and the tensile stress area; laser parameters and geometric parameters are systematically identified, and a database covering the combination of the laser parameters, the geometric parameters and material parameters and corresponding residual stress results is constructed through experiments and simulation; and based on the constructed database, establishing a relationship between parameters and stress, and obtaining a simplified empirical formula for laser energy compensation from the relationship. The energy control formula extracted by the control method can accurately guide processing parameters with different geometrical characteristics, so that the uniformity of residual stress distribution is fundamentally ensured, and harmful tensile stress at the fillet is effectively eliminated. Through accurate control of an empirical formula, raw materials and working hours consumed by repeated trial and error in a traditional process are avoided.

The invention discloses an impact-outburst hybrid dynamic disaster prediction method based on energy chain type evolution, and relates to the technical field of coal mine underground dynamic disaster prediction. According to the method, roadway impact-outburst hybrid dynamic disaster energy under different surrounding rock mechanical parameters, gas parameters and impact load parameters is solved through automatic numerical simulation, and an impact-outburst hybrid dynamic disaster energy data set under various working conditions is automatically constructed. The invention provides a CNN-LSTM-Attention roadway impact-outburst hybrid dynamic disaster energy prediction model with energy and spatial feature constraints, the CNN model extracts roadway spatial features, the LSTM model obtains an energy sequential sequence, Attention automatically allocates space-time double-region attention mechanism weights, the three models are cooperatively fused, and the energy prediction efficiency of the roadway impact-outburst hybrid dynamic disaster energy prediction model is improved. And the energy prediction accuracy of the roadway impact-outburst hybrid dynamic disaster is improved.

Optimized backscatter energy harvesting using a Reconfigurable Intelligent Surface (RIS) may be provided. Energy parameters may be received from a backscatter communication device. Then an energy critical message may be received from the backscatter communication device. The backscatter communication device may then be instructed to send frequent messages in response to receiving the energy critical message from the backscatter communication device. Next, a configuration for a Reconfigurable Intelligent Surface (RIS) cluster may be determined to supply energy to the backscatter communication device based on the energy parameters and the frequent messages. The RIS may be caused to supply energy to the backscatter communication device based on the configuration.

The invention discloses an under-water flow tumble detection system based on multi-scale fusion and decision, which comprises the following steps of: acquiring radar signals in a detection area by utilizing a millimeter wave radar, constructing a distance Doppler spectrum, calculating a water flow dynamic clutter index based on energy distribution statistical characteristics, identifying a background noise type and dynamically generating a detection threshold; target point cloud extraction under a complex dynamic water flow background is realized; the method comprises the following steps: performing track initialization and state updating by constructing a two-stage gating and evidence judgment framework, executing online parameter self-adaption and target physical size estimation, extracting time sequence characteristics such as a centroid position and Doppler velocity, and constructing a characteristic vector; and establishing a finite state machine model based on the feature vectors, identifying state transition, fall confirmation and state rollback conditions, and outputting a fall judgment result or a rollback result. According to the invention, accurate identification and dynamic determination of a fall event in a wet, slippery and water flow complex environment are realized.

The invention discloses a load control method and system for mobile energy storage equipment, a medium and a product, and the method comprises the steps: obtaining the motion state data and environment state data of target mobile energy storage equipment; performing second-order differential operation on the real-time speed to obtain a jerk value; generating a power demand impact sequence; based on the real-time polarization impedance and the real-time open-circuit voltage, calculating a maximum pulse discharge power threshold value under the condition that a preset under-voltage protection threshold value is not triggered; when the maximum power demand value in the power demand impact sequence is greater than the maximum pulse discharge power threshold, determining that the target mobile energy storage equipment has a power supply drop risk in a preset load prediction time window; calculating an energy gap prediction sequence based on waveform integration of the power demand impact sequence; and generating a feed-forward compensation instruction based on the energy gap prediction sequence, and controlling an auxiliary power conversion unit in the target mobile energy storage equipment to execute the feed-forward compensation instruction. And the accuracy of load control is improved.

The invention relates to the technical field of wireless communication, in particular to a lightweight multi-device communication protocol intelligent adaptation conversion system for emergency rescue, which comprises a broadband signal segment acquisition step: segmenting a broadband IQ data stream into discrete signal segments based on an energy threshold and an instantaneous bandwidth parameter, extracting physical layer characteristics and packaging to generate a unified protocol data frame; a conversion scheduling control step: analyzing the metadata label to judge a source protocol type, and performing hash matching on the source protocol type and a support protocol list; a heterogeneous protocol streaming translation step: in response to known protocol determination, executing load isolation mapping or ciphertext shell reconstruction based on a protocol parameter mapping table, and generating a target protocol baseband data stream; a dynamic spectrum fingerprint routing step: in response to unknown protocol determination, establishing a transparent bridging channel, and executing digital spectrum shifting and resampling on the original IQ slice; the problems that heterogeneous protocol conversion is high in delay, large in computing power consumption and difficult to give consideration to safety are solved.

The invention discloses a geometric consistency guided deep manifold network parameter initialization method and system, and relates to the technical field of manifold learning in machine learning, and the method comprises the steps: dividing an input feature into a plurality of independent modals, and building a feature-level modal energy distribution model; deriving a geometric consistency constraint formula of learnable parameters based on the energy distribution consistency constraint; the parameters are mapped to a high-degree-of-freedom fixed rank manifold for optimization, and updating of the parameters on the manifold and geometric structure maintaining are achieved through a designed Riemannian projection operator and a pull-back operator; and combining a geometric consistency constraint formula and a manifold optimization strategy, and carrying out iterative training until the model is converged. According to the method, the geometric consistency in the network training process can be effectively maintained under different manifold structures and data distribution, and the convergence speed, the stability and the cross-scene generalization ability of the deep manifold network are remarkably improved.