1259 results about "Network output" patented technology

The invention discloses a power transmission line inspection unmanned aerial vehicle obstacle intelligent detection and obstacle avoidance method. The method comprises the steps that multi-source sensing data is acquired, and alignment is completed through calibration and timestamp matching; heterogeneous data preprocessing and feature enhancement; constructing a high-precision environment fusing a geometric structure and a semantic tag, mapping a two-dimensional target detection result output by the recognition network to a three-dimensional coordinate system through spatial transformation, and fusing the two-dimensional target detection result with a point cloud structure to construct a semantic occupation grid map; performing preliminary route planning according to a preset power grid topological structure and task coverage requirements, and generating a barrier-free flight path covering the whole inspection area; reinforcing learning of a dynamic obstacle avoidance strategy; track dynamic reconstruction and energy consumption optimization scheduling are carried out; the technical problems that an existing technical system has defects in the aspects of obstacle recognition accuracy, complex environment adaptability, data fusion capacity and obstacle avoidance strategy intelligence, and the requirements for high-reliability, low-energy-consumption and high-efficiency unmanned aerial vehicle power transmission line inspection are difficult to meet are solved.

The invention relates to the cross technical field of artificial intelligence and environment monitoring, and discloses an algal community structure change prediction algorithm and system based on multi-source data fusion, and the algorithm comprises the steps: obtaining water quality, weather and plankton multi-source time sequence data; performing time alignment and missing value interpolation; eliminating and screening key environment factors through recursive features; performing dynamic weighted fusion on the multi-modal features by using a space-time attention mechanism; inputting a three-layer stacked LSTM network to output future algae dominant species abundance prediction; and model parameters are corrected on line based on measured data. The system comprises a multi-source data acquisition module, a preprocessing module, a key factor extraction module, a space-time attention fusion module, a dynamic prediction module and an adaptive correction module. According to the method, the prediction accuracy and stability are remarkably improved, and algal bloom early warning and ecological regulation are effectively supported.

The embodiment of the invention provides a dynamic flexible workshop scheduling method and related equipment, and belongs to the technical field of industrial intelligent manufacturing and production scheduling. The method comprises the steps of obtaining current state information of a workshop in response to a scheduling event; inputting the state information into a pre-trained scheduling decision model for processing; the model outputs state feature embedding through a two-stage feature extraction network: in the first stage, feature extraction is performed on a heterogeneous disjunction graph by using a graph attention network, and in the second stage, expert output is dynamically fused through a hybrid expert model; and finally, outputting and executing a process-machine pairing decision by the actor network. Wherein the model is trained by adopting a near-end strategy optimization algorithm based on multiple commentators; and a meta-learning framework is integrated during training, so that the model obtains strong generalization ability. According to the method, the defects of an existing scheduling method in the aspects of state characterization, multi-target tradeoff and environmental adaptability are effectively overcome, and the efficiency, quality and robustness of dynamic flexible workshop scheduling are remarkably improved.

The invention provides a robot motion control model training method, device and equipment based on deep reinforcement learning, a robot and a medium, and relates to the technical field of robots. The method comprises the following steps: acquiring a first potential vector obtained after a student encoder encodes robot body observation data, and a second potential vector obtained after a teacher encoder encodes privilege observation data; based on the current training step number and a preset probability function, calculating a sampling probability for controlling a fusion proportion of the first potential vector and the second potential vector; fusing the first potential vector and the second potential vector based on the sampling probability to generate a third potential vector, and inputting the third potential vector into a strategy network; and updating the parameters of the policy network based on the value estimation of the current state output by the value network and the action policy output by the policy network. According to the method, updating oscillation caused by sudden change of input distribution in the training process of the strategy network can be avoided, the training efficiency is improved, and the training cost is reduced.

The invention relates to an unmanned aerial vehicle path planning method and system based on GNN and high-order security constraints. The method comprises the steps that a navigation scene where an unmanned aerial vehicle is located is represented as a heterogeneous directed graph, message passing and feature updating are conducted through the GNN, a risk-aware attention mechanism is introduced, and an interpretable decision result is output; a differentiable HoCBF-QP optimization layer is introduced, an original control command output by a strategy network is used as input, quadratic programming with high-order control barrier function constraints is solved online, minimum-amplitude safety correction is carried out on the control command, and an actuator control command meeting safety constraints is output; starting a HoCBF safety shield during operation so as to strictly ensure that all safety constraints are met before execution; a calculation task of the whole control cycle is modeled into a directed acyclic graph form, and parallel execution is carried out on heterogeneous multiple cores by utilizing a real-time scheduling strategy. The problem that unmanned aerial vehicle navigation control is not effective and unified in three aspects of structure, safety and scheduling is solved.

The invention discloses an electromagnetic field simulation grid adaptive generation method based on a neural network. The method comprises the following steps: performing mesh generation on a semiconductor device simulation model to obtain original generation data, and constructing node features; an undirected graph is constructed, graph nodes of the undirected graph adopt node features of grid points, and connecting edges adopt Euclidean distances between the grid points and adjacent grid points; inputting the undirected graph into a double-branch neural network, and outputting a predicted node position; and correcting each node of the original subdivision data by using the predicted node position obtained by the double-branch neural network to form new subdivision data for electromagnetic field simulation. According to the method, physical field information can be fused to efficiently adjust the node density, and the geometric boundary and topological structure characteristics of the device can be strictly kept.

The invention relates to the field of robot vision positioning, and discloses an intelligent hand-eye calibration and self-adaptive correction system and method. According to the method, a mechanical arm is controlled to drive a camera to collect multi-modal calibration data, a convolutional neural network is utilized to identify a calibration plate mark point, and a three-dimensional coordinate under a camera coordinate system is calculated in combination with depth information; meanwhile, on the basis of an encoder and torque data, flexible deformation of the mechanical arm is compensated through a kinematic model and a self-adaptive rigidity model, and three-dimensional coordinates under a base coordinate system are obtained. And obtaining a hand-eye transformation matrix by solving a transformation relation between the two point sets. And repeatedly calibrating before and after operation, inputting the difference of the two transformation matrixes into the fault diagnosis neural network, outputting fault type probability distribution, and generating a maintenance strategy. According to the invention, high-precision hand-eye calibration, automatic compensation of flexible deformation and intelligent diagnosis of system state change can be realized, so that the long-term precision and reliability of a visual positioning system are improved.

The invention relates to the technical field of computers, and discloses an interaction control method of intelligent glasses. The method comprises the following steps: synchronously acquiring multi-modal data such as eye movement, voice, gestures and head postures and environment and application context information; carrying out independent time sequence feature coding on each modal data; generating a modulation vector in combination with the context, and outputting probability distribution of user intentions through a cross-modal attention fusion network; and a unique execution instruction is determined through an instruction arbitration module based on rules and a state machine. The system comprises corresponding function modules. According to the method, the accuracy, robustness and naturalness of interaction are improved through multi-modal synchronous fusion and a context self-adaption mechanism.

The invention provides a self-supervised continuous 3D hand posture tracking method based on a lightweight inertial measurement unit, and the method specifically comprises the following steps: firstly, obtaining a hand motion signal by using a lightweight consumer-level IMU, and extracting features by using a multi-stage neural network containing a bidirectional long-short term memory (Bi-LSTM) module; the global displacement and orientation of the hand are processed through a wrist posture estimation module, and three-dimensional coordinates of hand skeleton points are solved and calculated by means of a finger motion chain; secondly, a self-supervised completion network is realized by combining a random mask and dual loss, and the features are processed to complete complete attitude reconstruction; and finally, combining network output with kinematics prior, generating a three-dimensional grid with reasonable anatomy, solving the problem that joint deformation is inconsistent with torque, and realizing accurate acquisition of a three-dimensional hand posture. For a dynamic hand motion tracking task, the method can adapt to a sparse IMU deployment scene and realize continuous high-precision tracking; the real-time performance demand of daily interaction can be met, and a low-cost solution can be provided for the fields such as medical rehabilitation and virtual interaction which have strict requirements on attitude precision.

The invention discloses an adaptive evaluation method for the health degree of an electrolytic cell, and the method comprises the following steps: collecting the multi-dimensional operation parameters of the electrolytic cell in real time, and carrying out the preprocessing of the collected time series data, so as to construct a training sample with a time window; extracting a multi-scale time sequence feature from the training sample to form a feature vector; inputting the feature vector into a weight adjustment network, and outputting a dynamic weight vector; weighting the feature vector by using the dynamic weight vector to generate a weighted feature vector; inputting the weighted feature vector into a performance prediction model, and outputting a short-term performance prediction value of the electrolytic cell at a future moment; after the corresponding real performance value is obtained, calculating a prediction error of the short-term performance prediction value, and constructing a reinforcement learning reward signal based on the prediction error; updating a strategy of the weight adjustment network through a reinforcement learning algorithm by utilizing a reward signal, thereby optimizing dynamic weight vector generation at a subsequent moment; based on the dynamic weight vector and the feature vector at the current moment, a comprehensive health degree index of the electrolytic bath is obtained through calculation; according to the method, main factors influencing the equipment health degree in different stages are intuitively revealed, and a basis is provided for operation and maintenance decision making.

The invention discloses a deep reinforcement learning-based valve flow anomaly detection method. The method comprises the following steps of: obtaining a marked space-time synchronization industrial valve operation data set; generating an enhanced industrial valve image; inputting the enhanced industrial valve image into the improved YOLOv9 detection network, and outputting a candidate micro abnormal region set and corresponding time sequence anchor point information; forming a visual feature set and a time sequence feature set; inputting the visual feature set and the time sequence feature set into an improved coupling convolution sparse coding model to obtain a visual domain reconstruction residual error, a time sequence domain reconstruction residual error and a sparse coefficient consistency deviation; obtaining a normalized abnormal score; and comparing the normalized abnormal score with an abnormal threshold dynamically updated according to the valve flow physical prior constraint, and when the normalized abnormal score exceeds the abnormal threshold, generating micro-abnormal alarm information and an abnormal level. According to the method, false alarm and missing alarm caused by working condition change can be remarkably reduced in practical application, and the reliability of abnormal judgment is improved.

The invention discloses a photovoltaic module construction quality identification method based on computer vision and three-dimensional modeling. The method comprises the following steps: S1, collecting an original image sequence of a photovoltaic construction site and carrying out image preprocessing; s2, outputting a semantic tag graph and a two-dimensional space boundary graph through an improved BiSeNet network; s3, using a mask constraint SIFT algorithm to extract cross-view key point features, generating a dense three-dimensional point cloud according to multi-view stereo reconstruction, and outputting a structure three-dimensional geometric model; s4, mapping the semantic tag graph and the two-dimensional space boundary to the structure three-dimensional geometric model to obtain a semantic three-dimensional model; s5, performing spatial registration on the semantic three-dimensional model and the reference model, and calculating spatial error parameters of the photovoltaic module; s6, performing compliance discrimination on the spatial error parameters, and outputting a quality discrimination result; and S7, generating a construction quality evaluation report. According to the invention, automatic identification and accurate evaluation of the photovoltaic construction quality are realized, and the detection efficiency and the discrimination accuracy are improved.

The embodiment of the invention provides an unmanned ship cooperative hunting control method, and belongs to the technical field of control, and the method specifically comprises the steps: distributing a main hunting target for each chasing unmanned ship; for each chasing unmanned ship, an original observation vector containing a variable-length interaction sequence is formed according to the distributed main hunting target of the chasing unmanned ship; a variable-length interaction sequence in the original observation vector is converted into a standardized state vector of a fixed dimension through a two-stage attention mechanism; inputting the standardized state vector into a strategy network of the unmanned ship, and outputting a continuous action control instruction; and calculating an instant reward based on empirical data obtained after executing an action control instruction, and performing iterative updating on a strategy neural network and a corresponding value neural network by adopting a centralized training and decentralized execution mode based on a multi-agent depth deterministic strategy gradient framework to obtain a control model to generate a cooperative control scheme. Through the scheme disclosed by the invention, the control precision and adaptability are improved.

The invention discloses a mobile robot accurate docking method based on edge calculation, and aims to solve the problems that the dynamic docking precision is reduced and the collision risk is increased due to micro-motion or drifting of a target station. According to the method, unified time reference alignment is carried out on data of a camera, a laser radar, an inertial measurement unit, an ultra-wideband range finder, a station encoder and a programmable logic controller at an edge node, and a three-dimensional special Euclidean group equivariant multi-source fusion network is used for outputting relative pose estimation and covariance; the estimation in the time window is further used as a condition to be input into a conditional diffusion short-time prediction model to obtain a time-varying mean value and a time-varying covariance, an anisotropic probability tube is constructed, and prediction-measurement joint correction is carried out based on a score function; scenarized opportunity constraints are constructed under correction probability tube constraints, a tubular nonlinear model is adopted to predict, control and solve a reference trajectory, an actuator command is generated in combination with depth visual servo and compliance control, and the technical effects of high precision, robustness and safe docking under the station dynamic disturbance condition are achieved.

The invention relates to the technical field of unmanned aerial vehicles and unmanned vehicles, in particular to an air-ground unmanned cluster conflict resolution method based on multi-agent reinforcement learning, which comprises the following steps of: establishing an air-ground unmanned cluster navigation environment, determining obstacles and a plurality of air-ground subgroups, and determining that routes from each air-ground subgroup to a target navigation point have conflict positions; determining a state space and an action space of an air space subgroup and a reward and punishment function of an air space subgroup action based on the air space unmanned cluster navigation environment; establishing strategy networks including a local Q network, a local strategy network, a hybrid network and an attention network; determining a network loss function; performing reinforcement learning training on the strategy network to obtain a trained strategy network; controlling the air-ground subgroup to navigate by a decision action output by the trained strategy network; according to the invention, the conflict of multiple groups of clusters can be resolved.

The invention belongs to the technical field of wireless communication, and particularly relates to an OFDM (Orthogonal Frequency Division Multiplexing) semantic signal detection device and method integrating deep learning and energy detection. The method comprises the following steps: firstly, acquiring I / Q sampling data of an OFDM signal to be detected, wherein a data subcarrier of the I / Q sampling data bears a continuous value complex symbol generated by a semantic encoder; then parallel features are extracted and fused; a signal energy value of I / Q sampling data is calculated to obtain energy features; inputting the I / Q data into a one-dimensional convolutional neural network, and extracting deep semantic features; and performing normalization processing on the energy features, splicing the energy features with the preliminary detection probability output by the deep semantic features and the deep learning branches to form a fusion feature vector, inputting the fusion feature vector into a fusion network, and outputting a detection result that the signal exists or does not exist. According to the invention, through a parallel feature extraction-fusion decision-making architecture, in combination with the sensitivity of a traditional energy detection method to strong signals and the extraction capability of deep learning to weak signals and complex features, the method is specially aimed at the detection requirements of noise-like OFDM semantic signals.

The invention relates to the technical field of industrial communication protocol analysis, in particular to a protocol semantic matching analysis method based on reinforcement learning, and the method comprises the steps: constructing an industrial interaction environment containing industrial control equipment, a communication module and a protocol simulation assembly, defining a state space containing a flow attribute and a communication state, field processing, semantic annotation and dependency configuration related action space are carried out; calculating a reward value through a multi-level reward function of dynamic weight adjustment; based on the preprocessed multi-source protocol data set, adopting a Transform and graph neural network dual model to pre-train and generate a template library, and embedding an intelligent agent state processor; the intelligent agent updates the strategy after state processing, action distribution output by the strategy network, verification and execution of the action executor and interaction with the environment; and storing the interaction experience for iteration, and finally outputting protocol structure analysis, field classification and abnormity prompt information. According to the method, low-manual-dependence automatic analysis, unknown protocol self-adaptive adaptation and high-precision semantic matching can be realized.

The invention provides a deep learning-based junction point relation network training and cell occlusion judgment method, which comprises the following steps of: performing instance segmentation on a cell microscopic image to obtain a cell instance mask, and extracting a cell boundary based on the cell instance mask; performing junction point detection on the cell boundary to obtain cell shielding junction points, and classifying the cell shielding junction points into cell T-shaped shielding points, cell Y-shaped convergent points or cell X-shaped cross points; cutting the local image patch by taking the cell shielding junction point as a center, and constructing a multi-channel sample containing the local image patch; adopting a unified relationship label to label the multichannel sample, wherein the unified relationship label comprises a shielding relationship, a same-layer relationship and an unjudgeable relationship; training a deep learning network by using the labeled multi-channel sample, wherein the deep learning network outputs probability distribution of a junction point relationship category; and inputting a multi-channel sample of a to-be-detected cell microscopic image into the trained deep learning network, and outputting a junction point relationship category and a confidence coefficient thereof.

The invention discloses a CFD calculation method and system based on a neural network and adaptive parameter optimization, and belongs to the technical field of computational fluid dynamics. Initializing a flow field by reading calculation parameters and a grid file; solving the N-S equation, recording solving parameters and outputting an intermediate flow field; inputting the intermediate flow field into a pre-trained physical constraint neural network, sequentially applying boundary condition hard constraint and soft constraint based on control equation residual error, and outputting a corrected flow field; based on the convergence dynamic characteristics and the solving parameters, outputting a parameter adjustment amount through a strategy network of reinforcement learning training, and dynamically optimizing the solving parameters; and taking the corrected flow field as an initial flow field of the next iteration step, updating solving parameters, and circularly executing until convergence. According to the method, the physical prior is embedded into the neural network, intelligent self-adaptive regulation and control of solving parameters are realized through reinforcement learning, and the prediction precision and convergence efficiency of complex flow simulation are remarkably improved.

The invention relates to the technical field of belt conveyor auscultation, and discloses a belt conveyor auscultation abnormity management method based on comparative learning and time sequence modeling, comprising the following steps: step 1, acquiring operation sound and equipment parameters, extracting frame features and acquiring a voiceprint baseline; 2, the carrier roller synchronization frequency is calculated, and period and sideband fingerprint prototype vectors are constructed; step 3, inputting the frame feature and the fingerprint prototype vector into a contrast learning network to obtain a contrast embedded vector and a time sequence feature vector; 4, the time sequence modeling network outputs three types of probabilities and classification original output values; step 5, calculating an abnormal score, generating an abnormal event and determining a grade; step 6, calculating a priority score and distributing a work order; and 7, backfilling the disposal information, calculating the total cost and storing the total cost. According to the invention, accurate detection, hierarchical management and operation and maintenance closed-loop processing of abnormal operation of the belt conveyor are realized.

The invention discloses an end-to-end obstacle avoidance method considering flight dynamics of a fixed-wing unmanned aerial vehicle, and the method comprises the steps: constructing a multi-source data synchronous collection module, and obtaining a monocular depth image and inertial navigation state data which are aligned in time sequence; an enhanced visual perception coding module is designed, and spatial position information of a tiny obstacle is reserved at the tail end of feature extraction through an asymmetric convolution strategy and a parallel spatial attention mechanism; constructing a state fusion and time sequence reasoning module, performing long and short time sequence modeling on the multi-modal features by using an encoder with a causal mask mechanism, and outputting potential decision variables; and constructing a kinematics constraint trajectory generation module, and mapping the neural network output into a three-dimensional control trajectory conforming to flight mechanics limitation. The problems that spatial information of a traditional convolutional neural network is seriously lost, an end-to-end model easily generates an illusion trajectory exceeding a physical limit and the like are solved, and the flight safety and robustness of the fixed-wing unmanned aerial vehicle in a complex low-altitude environment are remarkably improved.

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 a speech recognition technology, discloses a speech recognition model training method and device, equipment and a medium, and aims to improve the speech recognition rate in a noise environment. The method comprises the following steps: firstly, training an automatic speech recognition network to obtain a pre-trained network; a noise reduction module is introduced in front of an output classification layer, the noise reduction module is trained by taking embedded features output by the pre-trained automatic speech recognition network as a reference, and parameters of the pre-trained automatic speech recognition network are fixed during training to form an initial speech recognition model; and finally, noise reduction module parameters are fixed, the pre-trained automatic speech recognition network is retrained, and a final model is obtained. Through staged training and a parameter fixing strategy, training target conflicts among modules are avoided, and the training stability and the convergence speed are improved; the noise reduction module focuses on feature denoising required by recognition, is high in adaptability, has the characteristics of light weight and low delay, and can be widely applied to low-resource real-time scenes such as embedded equipment and edge computing.

The invention discloses a power transmission line engineering quality defect acceptance method based on generative adversarial and reinforcement learning, and relates to the technical field of power engineering quality detection and intelligent image recognition, and the method comprises the steps: carrying out the sample amplification of original image data of a power transmission line tower through a generative adversarial network module, and obtaining an amplified training data set; constructing a PaFPN feature extraction network according to the amplification training data set, extracting multi-scale defect feature vectors and generating a coding feature matrix; establishing a reinforcement learning agent module, taking the coding feature matrix as state input, learning an optimal defect detection strategy through a Q-learning algorithm, and outputting a defect detection parameter combination; and performing feature fusion on the coding feature matrix to generate a fusion feature vector, inputting the fusion feature vector into a classifier network, and outputting a defect category label and a confidence score of the power transmission line project quality. According to the invention, the automation level and the detection precision of power transmission line project quality defect acceptance are improved.

The invention provides a multi-agent reinforcement learning regional energy collaborative scheduling method and system, and belongs to the field of regional energy system scheduling. Coupling degrees and a coupling degree matrix between agents are constructed; inputting the observation vector into a strategy network to obtain a decision action; individual basic rewards and system economic rewards are calculated, and constraint reference rewards are constructed; individual differentiation basic rewards are calculated, and rewards are distributed; inputting the decision action into a physical quantity prediction network, calculating a physical consistency reward, obtaining a final reward and a global reward, and calculating a target return; splicing observation vectors and decision actions of all agents, splicing global joint observation vectors and joint action vectors, inputting the spliced vectors into a value network, and training; inputting the local state set into the trained strategy network, outputting a scheduling instruction, inputting the scheduling instruction into the trained value network, and outputting an evaluation result; the problems of depiction rigidness of an intelligent agent coupling relation, lack of a cooperative benefit distribution mechanism and insufficient decision physical consistency are solved.

The invention discloses an information processing system and method for improving the reachable rate of atmospheric channel information, belongs to the technical field of atmospheric laser communication, and solves the technical problems that in the prior art, due to the fact that fixed probability distribution is usually used in traditional probability shaping, sending signal probability distribution cannot be adaptively changed according to actually measured turbulent channel conditions, and the probability distribution cannot be changed. And therefore, the quality of received signals is reduced, and the communication performance is influenced. A temperature pulsator is arranged at a transmitting end, a real-time signal-to-noise ratio of a turbulent channel is obtained by calculating an actually measured temperature structure constant, the signal-to-noise ratio serves as an input value and is sent to a neural network module for training, optimal distribution of transmitted signals is output, and the maximum information reachable rate is achieved under the actually measured turbulent channel condition. And then the neural network output value is used as sending signal probability distribution, and is sent to a turbulent flow channel for signal transmission after modulation mapping. The method is used for realizing high-efficiency and high-anti-interference wireless laser communication under an atmospheric turbulence channel.

The invention relates to the technical field of three-dimensional map recognition, and discloses a semantic segmentation-based low-altitude three-dimensional map element autonomous recognition method and system. The method comprises the following steps: acquiring a low-altitude remote sensing image and preprocessing to generate a multi-channel image matrix containing geographic coordinates and spectral characteristics; extracting multi-scale features through a pyramid feature extraction network in combination with cavity convolution, and obtaining an adaptive weighted feature tensor through a cascade attention mechanism fusion channel and a spatial weight; adopting a bidirectional feature fusion strategy to generate fusion features, and outputting an initial category probability distribution diagram by a semantic segmentation header network; obtaining a refined mask through edge perception optimization and superpixel segmentation correction, and mapping the refined mask to a three-dimensional coordinate system to generate a vector layer with a semantic tag; a constraint rule is deduced through a topological relation inference engine, logic conflicts are eliminated through rule-driven post-processing, finally, a standardized three-dimensional map element database meeting the geographic information standard is generated, and efficient, accurate and autonomous recognition of low-altitude three-dimensional map elements is achieved.

The invention relates to the technical field of power equipment monitoring, and discloses a low-voltage power distribution cabinet fault monitoring system and method. According to the system, multiple paths of original operation signals are collected and preprocessed in real time to form a standard time sequence data stream, frequency domain feature extraction, transient feature capture and load fluctuation analysis are carried out, and a dynamic multi-dimensional feature reference library is constructed; iteratively calculating a feature-fault association weight based on the feature library and a pre-stored fault case graph, and establishing a dynamic mapping relation network which can be corrected in real time; according to the fault probability distribution output by the mapping network, the sampling frequency, the feature priority and the diagnosis threshold are adaptively adjusted, and an optimal monitoring strategy is formed; and finally, generating a standardized diagnosis report containing fault types, positions and severity levels through online analysis. According to the invention, comprehensive perception of fault features, autonomous optimization of a diagnosis strategy and accurate output of a fault report are realized, and the intelligent level and reliability of fault monitoring of the low-voltage power distribution cabinet are significantly improved.

The invention discloses a gas sensor multi-mode adaptive preprocessing method based on a Mama state space model, and relates to the field of gas detection, and the method comprises the following steps: synchronously collecting original signals, environmental parameters and historical time sequence data of a sensor; performing feature extraction on the three types of data to generate a sensor feature vector, an environment feature vector and a historical feature vector; the method comprises the following steps of: obtaining a final fusion feature through processing, mapping the final fusion feature to a 128-dimensional embedding space through a contrast learning encoder, inputting a three-layer residual error connection Mamba time sequence prediction network to output a zero offset, dynamically predicting process noise and observation noise through a neural network, executing adaptive Kalman filtering to output a smooth signal, and outputting a final fusion signal. Adopting a learnable piecewise linear network to carry out nonlinear correction on the filtering signal; the gas concentration value is calculated by integrating the correction signal and the zero offset, and finally a confidence score and a data quality mark are provided; according to the method, high-precision, real-time and robust pretreatment of various gas sensors in a complex environment is realized.

The invention provides a power transmission line fault type reasoning method based on multi-modal data fusion, relates to the technical field of electrics, and adopts a special encoder and a bidirectional cross attention module to realize deep fusion of high-frequency electrical characteristics and low-frequency visual information in combination with an asynchronous time alignment mechanism. The core reasoning module uses a parallel graph neural network and a sequential network to carry out space-time modeling on fusion features and output fault types and positioning probabilities, in order to ensure physical rationality of diagnosis results, a self-adaptive physical guiding module is introduced, and by learning environmental adaptability physical parameters and taking an electrical transmission rule as a constraint, a fault diagnosis result is obtained. And finally, the knowledge enhancement reasoning module corrects the output of the deep network by combining a knowledge graph, Bayesian correction and neural symbolic logic, and generates a structured interpretable report, and the model can quickly adapt to a new line through a meta-learning strategy, so that a new line can be quickly constructed. And high-precision and high-confidence intelligent reasoning and early warning of faults are realized.