460 results about "Nonlinear coupling" patented technology

The invention discloses a charge and discharge controllable system and method for a decommissioned battery, and relates to the technical field of intelligent charge control. By collecting the capacity fading rate, the internal resistance value, the cycle index and the environment temperature data of the decommissioned battery in real time, a health degree parameter is calculated by adopting a nonlinear coupling algorithm; and the future health degree evolution trend is predicted in combination with the LSTM neural network. And dynamically generating a grading label according to a preset scene threshold matrix, and matching the charging demand thermodynamic diagram with the battery grading label through a dynamic scheduling algorithm to realize intelligent distribution of charging and discharging power. And introducing a photovoltaic-battery-power grid cooperative power supply model, predicting and dynamically adjusting the power supply proportion based on the environment temperature and the photovoltaic output, and deploying to a target scene. And through a dynamic health degree evaluation and scene adaptive matching mechanism, the utilization rate of the retired battery is improved, the deployment cost of charging facilities is reduced, and the power supply reliability under multiple scenes is remarkably improved.

The invention relates to the field of tunnel engineering geology and support design, and discloses a weak surrounding rock tunnel deformation risk discrimination method based on shear expansion-shear constitutive, which comprises the following steps: constructing a nonlinear coupling model between a shear expansion angle and shear stress, normal stress and joint parameters, and obtaining the shear expansion angle; establishing a volumetric strain rate discrimination formula; inverting an initial crustal stress tensor field; reconstructing an irregular tunnel boundary; constructing a risk level discrimination model, and outputting a risk level; supporting schemes such as supporting rigidity, anchor rod parameters and spraying layer thickness are matched according to the risk grades; establishing a model to predict a risk trend; a support adjustment suggestion is generated; collecting monitoring data to dynamically correct model parameters; and all the modules are integrated in a deployment system. According to the method, the coupling relation between the shear expansion angle and the shear strength is introduced, the coupling type constitutive discrimination model is established, the risk grading system and the support correction strategy associated with the support response are constructed, and active early warning of the high-risk section and dynamic adjustment of the support rigidity are achieved.

The invention relates to a source-containing power distribution network multi-target collaborative voltage optimization control method based on an FACMAC algorithm, and belongs to the technical field of photovoltaic inversion control. According to the technical scheme, a power distribution network physical system is composed of a plurality of feeder lines, a transformer, a line and a plurality of grid-connected photovoltaic inverters, and each inverter can measure operation information such as local voltage and current in real time; the data acquisition and communication system is used for acquiring node operation data and realizing low-delay communication; the multi-agent reinforcement learning control system is composed of a plurality of distributed agents and factorization centralized Critic modules, and whole-network voltage optimization decision can be carried out in training and execution stages. And the execution unit adjusts the reactive power output of the inverter in real time according to the control instruction. According to the method, the whole-network cooperative regulation and control capability is improved, the training efficiency bottleneck in a high-dimensional scene is relieved, the expression capability on a complex nonlinear coupling relationship is enhanced, and efficient, stable and extensible power distribution network voltage optimization control is realized.

The invention discloses a partial discharge detection method based on multi-source data fusion, and particularly relates to the technical field of discharge detection. Multi-mode partial discharge signals of partial discharge target equipment are collected, unified time reference alignment and multi-mode data structure normalization processing are carried out, and multi-source partial discharge observation data are generated; constructing a cross-modal discharge event response sequence, identifying response time delays and amplitude differences among modal signals, and extracting inter-modal response coupling feature data; constructing a non-linear feature alignment mapping function, performing time domain and frequency domain joint mapping on the multi-source observation data to obtain discharge feature multi-dimensional tensor data after non-linear coupling compensation, and performing inter-modal weight reconstruction and feature redistribution to generate a partial discharge fusion feature map; accurate identification of the partial discharge type and the spatial position is realized through the classification discrimination model, and a partial discharge detection result is output; and the accuracy of partial discharge detection is effectively improved.

The invention discloses a shield tunnel muck improvement parameter prediction method and system, and relates to the technical field of tunnel engineering construction.The method comprises the steps that a multi-modal sensor is arranged at a key part of a shield tunneling machine, and tunneling parameters, stratum parameters, multi-modal sensor signals, muck physical properties and modifier injection parameters are collected; then, extracting change characteristics, calculating mutation sensitive factors and carrying out working condition judgment; constructing a normal prediction sub-model library and a sudden change quick response model, calculating a stratum model adaptation index and performing model suitability judgment; establishing a working condition coupling prediction model by using a graph neural network, extracting nonlinear coupling characteristics, calculating a working condition coupling index and judging prediction stability; actual construction performance data are collected and compared with a model prediction result, a prediction correction index is calculated, deviation analysis is carried out, and a corresponding correction strategy is triggered. According to the method, intelligent prediction and dynamic correction of shield tunnel muck improvement parameters can be achieved, and the safety and stability of the construction process are improved.

The invention relates to the technical field of electrical digital data processing, and discloses a train ice melting simulation optimization method of an electromagnetic thermal coupling model fused with a deep learning method, which comprises the following steps of: inputting a geometric representation tensor and a physical working condition parameter vector containing an electromagnetic excitation frequency and a reference environment temperature into a feature mapping neural network; outputting a dual-channel space source item tensor containing basic heat source power density and a heat source to temperature change sensitivity distribution matrix through nonlinear convolution operation; constructing a heat conduction discrete numerical value evolution operator configured with an active item linear correction interface; time stepping operation is executed according to the heat conduction time scale, a basic heat source is corrected in real time through the Hadamard product of a sensitivity distribution matrix and temperature deviation, and an operator is substituted for solution. On the premise that electromagnetic-thermal nonlinear coupling characteristics are reserved, decoupling of the time scale is achieved, and the calculation efficiency in high-frequency physical field simulation is effectively improved.

The invention relates to the technical field of spectral analysis and concentration quantitative detection, and discloses an LIBS quantitative analysis method, device and system based on a thin plate spline regression algorithm. The method comprises the steps that multiple sets of sample data are obtained, and each set of sample data comprises corresponding target sample concentration, laser energy and spectral intensity; constructing a concentration quantitative model about the concentration, the laser energy and the spectral intensity based on a spline function; determining an optimal penalty parameter by adopting a cross validation method; based on the optimal penalty parameter, solving parameters of the concentration quantitative model through a minimization objective function to obtain a constructed concentration quantitative model; and performing quantitative analysis on a sample with unknown concentration by using the constructed concentration quantitative model. Thus, the output energy of the laser is incorporated into the core model, and an I-E-C nonlinear coupling relationship is constructed, so that the problem of calibration deviation caused by laser energy fluctuation is reduced, and the precision improvement of concentration quantification in a complex scene is realized.

The invention discloses a bimodal adaptive immersion phase change charging station thermal management system, and relates to the technical field of charging station thermal management, and the system comprises a circulation management module which carries out the circulation mapping and optimization operation of a phase change temperature result, and generates a circulation scheme; the immersion cooling module is used for intelligently regulating and controlling the nanometer phase change slurry to flow in an immersion cooling tank in a self-adaptive manner by utilizing a circulation scheme, and dynamically switching between a single-phase liquid cooling mode and a phase change boiling mode to generate heat absorption data; the heat exchange module is used for inputting the heat absorption data into a plate heat exchanger for heat exchange to generate cooling liquid temperature data, and carrying out heat dissipation and waste heat recovery operation of a dry cooler to generate backflow heat data; feature extraction and multi-dimensional nonlinear coupling analysis are carried out on the initial working condition data of the charging station, and iterative optimization is carried out in combination with a pre-training model, so that high-precision prediction of dynamic and multi-modal temperature changes is realized, and a reliable basis is provided for circulation management and cooling mode selection.

The invention provides a simulation test key factor screening-oriented method and system and a computer program product. The method comprises the following steps: generating a structured configuration file; constructing a supervised learning data set based on the structured configuration file; based on the supervised learning data set, training a machine learning classification model to obtain a current key factor set; and repeating the steps, judging whether the current key factor set is converged or not, and if the current key factor set is converged, stopping simulation and outputting the current key factor set of the last round as a final key factor. According to the technical scheme of the invention, a high-dimensional, nonlinear and high-coupling complex system can be automatically processed; key factors are objectively recognized through machine learning, a small-batch iteration verification mechanism is adopted, and the screening accuracy and efficiency are improved while the number of times of simulation is remarkably reduced.

The invention discloses a wide temperature range compensation method for resistive current of a lightning arrester, which belongs to the technical field of online monitoring of power equipment, and comprises the following steps: acquiring waveform data under a reference low-temperature working condition, and establishing an initial capacitive harmonic base; acquiring working condition data at any temperature in real time, performing harmonic decomposition, and analyzing to generate a nonlinear distortion feature vector; dynamically correcting the initial base by using the feature vector, and carrying out subtraction operation on the total current harmonic wave to obtain a final resistive current harmonic wave vector; and reconstructing an instantaneous resistive current waveform through inverse transformation and calculating a characteristic value. According to the technical scheme, the initial capacitive harmonic wave base is established, the nonlinear distortion feature vector is generated based on the harmonic distortion of the real-time working condition quantification temperature and valve plate nonlinear coupling, and dynamic feedback correction is conducted on the base, so that the real resistive current waveform in the wide temperature range can be accurately separated and reconstructed, and the accuracy of the real resistive current waveform in the wide temperature range is improved. And the accuracy and reliability of lightning arrester state evaluation are improved.

The invention discloses an industrial multi-source heterogeneous data feature fusion and dynamic modeling method and system, and relates to the technical field of industrial multi-source heterogeneous data processing, and the system comprises a data collection module, an event triggering type local space-time alignment module, a time sequence data set generation module, a feature fusion module and an industrial equipment state model generation module. According to the method, an event-triggered local space-time alignment module is arranged, an event-driven dynamic space-time anchoring mechanism is adopted, and in a preset tolerant time window, an image feature time sequence is constructed through industrial camera superframe sampling to be matched with sensor time sequence data, so that feature dislocation caused by sampling frequency difference is avoided; compared with an existing interpolation method, the non-linear coupling relation between the process parameter data and the sensor time sequence data is obtained, and the problem of feature fusion distortion caused by the time granularity difference is solved by performing non-linear interpolation on the process parameter data through Gaussian process regression and generating a continuous proxy curve synchronous with the sensor time sequence data.

The invention relates to an energy efficiency optimization method for a dynamic load of a central air conditioner, which comprises the following steps of: establishing a response relationship among a cold and heat source, a transmission and distribution system and end equipment, identifying a nonlinear decoupling characteristic of a cold and heat response behavior by monitoring operation deflection of each level of equipment under a low-load working condition, and defining and updating a cooling capacity response deviation threshold in real time; on the basis of the cooling capacity response deviation threshold, delay compression control is conducted on response actions of the refrigerant side and the air medium side, and by adjusting the air side response time sequence in advance, dynamic thermodynamic equilibrium is formed between refrigerant transfer delay and air medium response in advance; by establishing the response relationship among the cold and heat source, the transmission and distribution system and the end equipment and introducing a cold capacity response deviation threshold dynamic updating mechanism, nonlinear coupling mismatch in a cold and heat transmission chain can be accurately identified, so that the system is more flexible to operate under low-load and variable-load conditions, frequent start and stop or redundant operation of the cold and heat source is avoided, and the system reliability is improved. And therefore, the overall COP value of the system is remarkably increased, and unit cooling capacity consumption is reduced.

The invention provides a coastal water level prediction method based on multi-modal observation data, and belongs to the technical field of coastal water level prediction.The coastal water level prediction method comprises the steps that multi-modal ocean observation data of different sensors are collected, and a multi-scale space-time registration matrix is established to achieve space-time alignment of heterogeneous data; an ocean dynamic process feature extractor is constructed to recognize astronomical storm surge and wave features and calculate nonlinear coupling parameters, an adaptive space-time fusion algorithm is adopted to dynamically adjust weights according to data quality to generate a space-time consistency data set, and an ocean dynamic coupling strength discrimination model is established to determine a modeling strategy. And finally generating a coastal water level prediction product containing a predicted value confidence interval and risk early warning. The technical problem of insufficient coastal water level prediction precision caused by difficult effective fusion of multi-modal ocean observation data under the condition of spatial-temporal scale mismatching is solved.

The invention belongs to the field of artificial intelligence, particularly relates to a power plant infrastructure multi-target intelligent scheduling optimization method, and aims to solve the problems of static weight imbalance, disturbance response hysteresis and process coupling effect modeling insufficiency of traditional scheduling. According to the method, a multi-dimensional space-time semantic model is constructed, BIM, sensor and environment data are integrated, construction period, cost, resource and safety four-dimensional target weights are dynamically set, and an improved non-dominated sorting genetic algorithm is adopted to generate an initial Pareto optimal schedule; and then inferring an inter-process nonlinear coupling delay factor through a graph neural network, embedding a disturbance response module, starting local rolling re-optimization when a progress deviation or an external event is detected, limiting an influence subnet and freezing a stable region. According to the scheme, stage self-adaptive target focusing, chain risk pre-buffering and minute-level robust adjustment are achieved, the stability of a critical path is improved by 45%, the secondary optimization frequency is reduced by 60%, the calculation efficiency and the execution toughness are both considered, and efficient and accurate landing of a large power plant infrastructure project is supported.

The invention relates to the technical field of computers, and discloses a rock creep model construction method and device and a rock failure mode determination method. The method comprises the steps of obtaining a data set; samples in the data set comprise input data and output data, the input data comprise creep load holding time, sample rock stress data, initial macroscopic damage data, initial microscopic damage data, long-term strength and a creep starting threshold value, and the output data is a strain true value; fitting the initial rock creep model by using the data set to obtain a final rock creep model; wherein the initial rock creep model comprises at least one of a damaged elastomer strain item, a damaged viscoelastomer strain item and a damaged viscoplastic body strain item; each strain item comprises a macro-micro nonlinear coupling damage item, and the macro-micro nonlinear coupling damage item is generated based on the initial micro damage data and the initial macro damage data. The model constructed by the method can truly reflect the nonlinear mechanical response of the rock mass under the combined action of the multi-scale initial defects.

The invention relates to the crossing field of mechanical engineering and intelligent prediction technologies, particularly discloses a coal mill efficiency and service life prediction method and device, and aims to solve the problem that a traditional model is difficult to deal with nonlinear coupling prediction of equipment performance degradation under variable load and coal quality fluctuation. The method comprises the following steps: receiving a multi-source sensing data stream and constructing a structured feature matrix with aligned time sequences; efficiency degradation implicit features are extracted through a nonlinear dynamic encoder, and the interaction influence of grinding roller abrasion, lining plate fatigue and bearing degradation is quantified in combination with a multi-failure-mode coupling analysis module; and cooperatively predicting a network output efficiency attenuation curve and residual life probability distribution through a bidirectional attention mechanism. According to the method, through fusion of multi-source time sequence characteristics and multi-failure coupling modeling, limitation of a static threshold value and linear extrapolation is broken through, prediction precision and timeliness are remarkably improved, intelligent maintenance decision support is provided for a coal-fired power plant, non-planned shutdown risks are reduced, and operation economy and system reliability are optimized.

The invention relates to the technical field of ecological environment monitoring and intelligent information processing, and discloses an intelligent monitoring method and system for ecological restoration of a small and micro wetland. The method comprises the following steps: synchronously collecting multi-dimensional parameters of water, soil, gas and growth through a multi-source sensor array, and constructing ecological state vectors with time-space alignment; carrying out cross-medium nonlinear coupling modeling by utilizing a graph attention space-time fusion network; predicting key water quality and biological indexes by adopting an LSTM (Long Short Term Memory) and GRU mixed framework; and generating graded early warning and self-adaptive repair suggestions in combination with the three-level health threshold and the rule base. The system comprises a multi-source sensing module, a data preprocessing module, a graph structure construction module, a feature fusion module, a time sequence prediction module and an intelligent decision module. According to the system, global sensing, early warning and intervention of the ecological state of the small and micro wetlands are realized, and the restoration timeliness and scientificity are improved.

The invention discloses a voltage transformer state influence factor analysis method, system and device and a medium, and belongs to the technical field of voltage fault analysis, and the method comprises the steps: collecting state parameters of a voltage transformer, carrying out the preprocessing of the state parameters, and constructing a nonlinear coupling relation between multidimensional feature tensor capture features; analyzing voltage fluctuation characteristics of the voltage transformer, and automatically correcting the insulation state evaluation model; and inputting abnormal feature vectors obtained by monitoring into a recursive attribution decision tree model, carrying out multi-dimensional abnormal clustering and causal analysis, generating a tracing report, and carrying out multi-dimensional evaluation and verification on an analysis result. According to the invention, continuous dynamic full-coverage monitoring of the equipment insulation health condition is realized, the accuracy and robustness of anomaly detection are improved, the phenomena of missing detection and false alarm are reduced, the scientificity of anomaly tracing analysis and the interpretation of early warning decision are improved, and the reliability of the system is improved. And the intelligent level of the monitoring and early warning system is improved by continuously adapting to new abnormal types and complex operation environments.

The invention belongs to the technical field of textile, and discloses a reinforcement learning and physical modeling combined broken end dynamic capturing method and system. The method comprises the following steps: constructing a yarn microstructure evolution model; inputting real-time environment parameters of the textile workshop into the microstructure evolution model, and predicting to obtain real-time microstructure parameters of the yarn; performing nonlinear coupling feature extraction on the real-time environment parameters, and calculating an environment coupling feature vector; inputting the real-time microstructure parameters as material attributes into a yarn tension dynamical equation, and solving to obtain a predicted yarn macroscopic stress state; splicing the macroscopic stress state of the yarn and the environment coupling feature vector to form a state observation value; the reinforcement learning agent outputs a broken end risk probability value according to the state observation value; and when the broken end risk probability value exceeds a preset threshold value, generating and outputting a broken end early warning signal. According to the invention, early and accurate early warning of yarn breakage in a complex dynamic environment can be realized.

The invention provides a tunnel surrounding rock deformation rolling time sequence prediction method and system considering excavation disturbance, and the method comprises the steps: obtaining a geometrical relationship from a tunnel face to a monitoring point, an excavation area and an excavation footage in a tunnel excavation process, and calculating a construction disturbance factor according to the obtained data; constructing and training a surrounding rock deformation prediction model, wherein the surrounding rock deformation prediction model is obtained by fusing a convolutional neural network, a bidirectional long-short term memory neural network and an attention mechanism layer; acquiring tunnel surrounding rock monitoring data, and preprocessing the monitoring data; and taking the preprocessed monitoring data and the calculated construction disturbance factor as input data of the trained surrounding rock deformation prediction model to obtain a final deformation prediction result. According to the method, the dynamic disturbance characteristics of stress redistribution in the tunnel excavation process are quantified into the construction disturbance factors, the nonlinear coupling relation between surrounding rock deformation and construction disturbance is analyzed through the hybrid model, and the tunnel surrounding rock deformation prediction accuracy is improved.

The invention discloses a new energy power grid frequency voltage collaborative support method, which comprises the following steps: acquiring electrical quantity signals of a plurality of units, and constructing multi-unit power angle trajectory data; regarding the instantaneous nonlinear coupling characteristic as a space curve in differential geometry, calculating a local curvature and a torsion rate of the instantaneous nonlinear coupling characteristic, establishing a three-dimensional dynamic coupling model capable of quantifying the instantaneous nonlinear coupling characteristic, and forming a three-dimensional coupling state matrix; dynamically evaluating the supporting capacity of the unit by using the matrix and combining a Lyapunov index to obtain a dynamic supporting capacity matrix; according to the dynamic support capability matrix, modeling a cooperative control problem as a non-cooperative game model and solving Nash equilibrium, performing conflict decoupling of a multi-machine cooperative strategy, and determining a cooperative control weight matrix; and performing multi-objective collaborative optimization based on the weight matrix to generate a collaborative support control instruction sequence. Transient coupling can be accurately quantified, dynamic self-adaption of a control strategy is achieved, and the frequency and voltage stability of a high-proportion new energy power grid is improved.

The invention discloses an inertial navigation temperature drift compensation method based on multi-dimensional modeling, and relates to the field of inertial navigation. Comprising the following steps: S1, collecting temperature, three-axis acceleration and three-axis angular velocity data through a constant temperature control system in a range of-40 DEG C to 80 DEG C, and constructing a time-aligned multivariable characteristic matrix; s2, after standardization and rotation transformation, a Chebyshev polynomial is utilized to construct a five-order nonlinear coupling function group, an orthogonal tensor model is established, and L1 constraint is applied; s3, constructing a drift response curve group based on the heating and cooling experiment data to obtain a 6 * 1 drift sensitivity matrix; s4, removing abnormal samples through mahalanobis distance analysis, and extracting a high-confidence training subset; s5, constructing a multi-channel modeling network containing a thermal coding module, a convolution channel and an attention mechanism, and carrying out cross-axis modeling; s6, training the network and generating a steady-state compensation tensor; s7, new data are input into the model, regular six-axis output is maintained one by one, and temperature drift active compensation is completed. The method has the beneficial effects that the cross-temperature-zone navigation precision and the compensation robustness are improved.

The invention relates to the technical field of mining engineering and geotechnical engineering support design, and discloses a roadway anchor rod group support parameter intelligent optimization method based on unbalanced force, and the method comprises the steps: building a surrounding rock finite element model, calculating a plastic stress increment through employing a minimum plastic complementary energy principle, and mapping the plastic stress increment into a node unbalanced force vector; an unbalanced force field reflecting reinforcement requirements is constructed, and an initial scheme is generated according to the unbalanced force field. Then, a virtual anchor rod unit is introduced to establish a nonlinear coupling model, an incremental balance equation is solved, and whether the unbalanced force is smaller than a threshold value or not is judged; if so, outputting an optimal parameter; otherwise, a comprehensive objective function containing safety and economy is constructed, new parameters are obtained through searching and decoding by means of the particle swarm algorithm, and the virtual anchor rod unit is re-entered for calculation to form a closed loop until convergence is achieved. According to the method, intelligent optimization is driven through a physical mechanism, the problem that a traditional design lacks a mechanical basis is solved, and accurate optimization of support parameters is achieved.

The invention belongs to the technical field of tool wear measurement, and particularly relates to a machining center tool wear state early warning method based on multi-source data fusion, and the method comprises the steps: calculating a cutting power consumption characteristic through a main shaft load energy mapping model according to the original sampling current and the real-time feeding speed of a main shaft; sliding window sampling is carried out on the cutting power consumption characteristics, and the cutting state disorder degree is calculated; performing nonlinear coupling on the power consumption gradient item and the cutting state disorder degree to obtain a grinding loss stability coefficient; and establishing a dynamic statistical reference surface, and performing cutter state early warning according to the deviation degree of the grinding loss stability coefficient monitored in real time. Instantaneous interference caused by uneven material hardness is effectively recognized and eliminated, meanwhile, signal structure disorder at the initial stage of tool failure is captured, the technical problems that in die steel machining, due to material structure segregation and variable working conditions, the false alarm rate is high, and failure precursor capturing is difficult are solved, and the machining precision is improved. And the monitoring accuracy of the precision machining process is obviously improved.

The invention relates to the technical field of modeling prediction, and discloses a DSP integrated degradation and LSTM model optical module life prediction method, and the method comprises the steps: enabling a multi-parameter coupling degradation model and a Kalman filtering algorithm to be embedded into an optical module DSP at a calculation level through a DSP embedded mechanism model filtering LSTM network time sequence calibration collaborative architecture, and achieving the prediction of the life of an optical module. The in-situ, real-time and safe evaluation of the life state is realized, and the traditional mode of relying on external computing resources is changed; on the model level, the interpretability of a physical mechanism and the adaptive capacity of data driving are fused, fundamental degradation dynamics is described through a nonlinear coupling model, and a specific degradation rule is learned from individual historical data by using an LSTM network; finally, real-time, accurate and self-adaptive evaluation and prediction of the service life state of the optical module are realized.

The invention belongs to the technical field of electronic digital control, and particularly relates to a digital loop control method and device for rapidly exiting circuit hardware clamping, and the method comprises the following steps: S1, carrying out the real-time monitoring and precise recognition of a clamping state; s2, digital loop feedback source switching; s3, clamping quit grading evaluation and strategy selection are carried out; s4, loop regulation under virtual current feedback; after hardware clamping occurs, the virtual current quickly replaces a current ADC measured value to serve as a feedback source, nonlinear coupling of DAC output and the current ADC measured value is effectively weakened, reference parameters and dynamically-adjusted loop control logic are matched, exit time is shortened by 90% or above compared with the prior art, and the overshoot rate is controlled to be a rated value smaller than or equal to 3%; meanwhile, in the feedback source switching process, loop state freezing is avoided, control continuity is high, switching impact is avoided, and rapid and stable quit of the hardware clamp is achieved.

The invention relates to the technical field of industrial automation, and particularly discloses a remote liquid level transmitter system based on HART (Highway Addressable Remote Transducer) communication, which constructs a multi-scale state interaction tensor by synchronously acquiring original sensing signals and communication carrier quality parameters of a transmitter, respectively extracting high-order feature sets of the transmitter and analyzing a nonlinear coupling relationship between the original sensing signals and the communication carrier quality parameters; quantifying the physical health state of the sensor through tensor decomposition and manifold learning, generating a progressive quantification factor representing the integrity degradation of the sensor, predicting a failure mode and residual life based on the change track of the factor, and packaging into an enhanced diagnosis frame for returning; according to the method, the problem that early physical damage and communication interference of the sensor are difficult to distinguish is solved, and accurate early warning and predictive maintenance of hidden faults are achieved.

The invention relates to the technical field of charging switching control, in particular to a dynamic switching system for cooperative work of wireless charging and wired charging, which performs node modeling and edge weight propagation on multiple parameters such as magnetic field intensity, current fluctuation ratio, contact resistance and temperature threshold through a graph neural network. Structured expression and dynamic updating of a nonlinear coupling relation among parameters are achieved, abnormal feature aggregation and channel state characterization are more refined, fuzzy reasoning and weight adjustment are conducted on multiple variables such as power output, the heat growth rate, the voltage drop rate and the energy efficiency ratio through fuzzy logic control, the stability of a channel priority sequence is enhanced, and the stability of the channel priority sequence is improved. Through dynamic detection of power curve intersection points and transition section time sequence calculation, continuous power distribution is converted into a smooth function interval, instantaneous energy abrupt change during switching is reduced, closed-loop correction of multi-period signals is achieved, and the system keeps stable operation and energy efficiency output consistency under high-dimensional parameter disturbance.

The invention relates to the technical field of laser processing control, in particular to a laser energy and light spot swing cooperative control method and system for laser welding, and aims to solve the problems that in the prior art, when parameters are linearly adjusted, the hysteresis effect of heat input and the nonlinear coupling relation of energy density are ignored; therefore, incomplete fusion, over-burning and non-uniform fusion depth of a welding seam are easily caused. The method comprises the following steps: acquiring a weld gap width estimation value and a gap change rate at the current moment; determining the target swing amplitude of the light spot at the current moment; calculating a laser power instruction value at the current moment; and a swing frequency instruction at the current moment is calculated, and closed-loop control is conducted on the welding process in cooperation with the laser power instruction value and the target swing amplitude. According to the method, no matter how the swing amplitude changes, the effective heat flux density acting on the unit area of the weld joint is kept constant, and therefore the consistency of the penetration depth is guaranteed.

The invention relates to the technical field of financial transactions, and discloses an artificial intelligence-based transaction execution and risk control management system, which comprises a heterogeneous data acquisition module, a conduction prediction module, a collaborative execution strategy module, a risk coupling and evaluation module, a signal monitoring and compensation module and a risk control collaborative optimization module. According to the method, heterogeneous data such as an order book, time sequence transactions, macroeconomy and news texts are fused through a multi-modal neural network, a dynamic asset association graph is constructed by adopting a graph neural network to predict a market impact conduction path, and a cross-market multi-leg transaction execution problem is modeled by applying Actor-Critic deep reinforcement learning; a Copula function and a Bayesian network are utilized to capture a nonlinear coupling relation of multi-dimensional risks, strategy signal attenuation is monitored in real time and dynamically compensated based on an LSTM neural network, and cooperative balance of execution efficiency and risk control is realized through a method of combining multi-objective optimization with a game theory.