996 results about "Rapid response" patented technology

The invention provides a perception collaborative decision-making method and system based on multi-modal heterogeneous data fusion, and relates to the technical field of artificial intelligence, and the method comprises the steps: inputting a global environment situation perception graph into a pre-trained multi-target collaborative decision-making model; the multi-target collaborative decision-making model forms a multi-target decision-making feature set by analyzing the resource entities and the incidence relation in the graph; based on the multi-target decision feature set, decision optimization is carried out to obtain a comprehensive collaborative scheduling scheme; performing instruction analysis and packaging on the comprehensive collaborative scheduling scheme to obtain an executable instruction sequence; and issuing the executable instruction sequence to a corresponding decision node and a control terminal in parallel through a distributed communication architecture to complete real-time scheduling of resources and collaborative issuing of control instructions. According to the invention, by constructing a linkage mechanism of multi-modal data fusion, dynamic environment perception and collaborative decision execution, intelligent perception and quick response to a complex environment are realized.

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 field of artificial intelligence and computer science, in particular to a causal structure and latent variable-based adaptive reinforcement learning reasoning migration method, which comprises the following steps of: constructing a causal world model fused with multi-modal observation and a decoupling latent variable space; establishing a hierarchical inference engine comprising an intuition layer, a conventional layer and a planning layer; pre-training a quick response and judicial planning dual-mode strategy and generating an interpretable fuzzy rule base; performing calculation level coarse tuning based on task identification and causal complexity; evaluating the real-time state criticality through an adaptive neural fuzzy system and dynamically switching a decision mode; after the action is executed, the threshold and the rule are subjected to closed-loop optimization, and cross-environment efficient migration is realized by utilizing a causal modularization characteristic. According to the technical scheme, consumption of computing resources is remarkably reduced on the premise that decision precision and safety are guaranteed, and the response speed and cross-scene adaptive capacity of a system on edge equipment are improved.

The invention discloses an intelligent fire detection and quick response method based on image recognition. The method comprises the following steps: S1, synchronously acquiring and preprocessing multi-source image data; s2, carrying out multi-modal feature fusion and early fire identification; s3, intelligent grading response based on deep reinforcement learning: constructing a fire behavior grade dynamic evaluation network, inputting fused multi-modal features, outputting fire behavior grade probability distribution and a crisis index, judging a fire behavior grade according to a dynamic threshold value, and triggering a predefined grading response strategy; s4, performing cross-scene adaptive transfer learning; and S5, carrying out system self-diagnosis and dynamic optimization. According to the invention, through time-space synchronous acquisition and deep fusion of visible light, infrared and smoke multi-mode data, vision, thermal radiation and smoke characteristics of flames are integrated, and common interferences such as real fire behavior and lamplight, light reflection, a moving heat source, water mist and dust are effectively distinguished by using an improved lightweight CNN, a self-adaptive background temperature model and an environment airflow model.

The invention relates to the technical field of industrial network control, in particular to a side-cloud collaborative software-defined industrial control system, which comprises a side control action configuration module, a multi-source signal collection module, a state mutation recognition module, a cloud scheduling module and a collaborative control generation module. In the invention, through decoupling control action configuration, multi-channel signal acquisition, data label construction, sudden change state identification and a remote scheduling execution process and realizing standardized processing, an edge control basic instruction structure body can be quickly constructed based on an equipment state and a unified time sequence data label mechanism is established; in combination with the dynamic sensing ability of a sudden change state and a feedback point identification mode, efficient discrimination and rapid classification of key control points can be realized, task chain execution can be rapidly mapped to a key path and real-time regulation and control are implemented, rapid response to industrial field multi-source change and accurate issuing of a control instruction are realized, and the task chain execution efficiency is improved. And the real-time performance and the collaboration of the control process are greatly improved.

The invention provides a heterogeneous building air conditioner group quick response control method based on physical information deep learning, and the method comprises the steps: 1, obtaining a real-time discrete step scheduling instruction issued by a power grid, obtaining the thermodynamic parameters and equipment inertia time constants of all building units in a heterogeneous building group, obtaining the outdoor temperature, and carrying out the real-time discrete step scheduling instruction; the solar radiation intensity and the indoor air temperature of each building unit; step 2, extracting spatial-temporal characteristics of each building unit based on a multi-head self-attention mechanism, and generating initial distribution target power of the air conditioner; 3, inputting the initial allocation target power into a pre-trained cascaded physical information neural network (PINN), and predicting power and temperature evolution tracks in a future scheduling period; 4, calculating an out-of-limit risk index of each unit, judging whether to execute a quantile risk migration strategy or not, and generating a final distribution target power of the air conditioner; and 5, calculating the transient climbing deviation between the actual aggregation power and the target power of the power grid, and carrying out deviation compensation.

The invention relates to the technical field of fault positioning, in particular to a power distribution network line fault positioning method and system based on a fault indicator, and the method comprises the following steps: obtaining node current data, calculating a jump rate, screening an early warning node, recognizing an intersection section, determining a fault position, and generating a recognition result. According to the invention, through collecting periodic current data of each node fault indicator, combining node numbers and topological structure mapping, systematically establishing a current sequence table and calculating a current increment difference value in unit time, and through grade division and periodic stability identification of a jump rate, key nodes with early warning characteristics can be accurately screened. The method comprises the following steps of: acquiring a path intersection area, positioning a fault centralized distribution section by virtue of jump intensity trend change analysis of the path intersection area, and determining a fault initial position and a grade identifier in combination with a comparison relationship between a sampling time point and trigger delay between nodes, so that accurate identification and quick response of a multi-path fault are realized under a complex topological structure of a power distribution network.

The invention relates to the technical field of smart traffic, and discloses a smart traffic monitoring system and method based on multi-source data fusion, and the system comprises a multi-source data collection module, a spatial-temporal feature fusion engine, a hierarchical decision core, a decision execution module, and an online learning module. The method corresponds to the system. According to the method, heterogeneous traffic data are unified under the same time-space reference through a multi-modal fusion technology, and comprehensive and accurate road network state feature representation is constructed; the hierarchical decision-making core forms a closed-loop decision-making link from event identification to control strategy generation through close cooperation of an event sensing layer and a regional optimization layer, and realizes rapid response and accurate control of traffic abnormity; on-line learning continuously optimizes decision logic based on complete historical operation data so as to adapt to a continuously changing traffic environment; finally, the accuracy of traffic state perception and the timeliness of decision response are improved, and reliable technical guarantee is provided for efficient management and control of intelligent traffic.

The invention discloses a method for monitoring and identifying dangerous behaviors of a smart park, and relates to the field of intelligent security and protection. The method comprises the following steps: acquiring an environment data stream through a sensing device deployed at a key point location of a park and carrying out standardization processing on the environment data stream; the data stream is sent to an edge computing node, a target is recognized through a lightweight target detection model, the detection confidence coefficient is obtained, a motion track is generated through a multi-target tracking algorithm, the rule matching degree is calculated according to a predefined rule base, and dangerous behaviors are preliminarily recognized; calculating a comprehensive model prediction credibility based on the detection credibility and the rule matching degree, and generating a final comprehensive credibility through a multi-dimensional credibility fusion model in combination with the time sequence consistency credibility and the scene matching credibility; and dangerous behavior trend prediction is carried out according to the comprehensive confidence, and an alarm instruction is generated to trigger disposal linkage, so that advanced prevention and quick response of dangerous behaviors are realized, and the intelligent level and operation and maintenance efficiency of park security and protection are greatly improved.

The invention relates to the technical field of resource scheduling, in particular to a resource scheduling method and system based on multi-modal collaboration and deep reinforcement learning, and the method comprises the steps: constructing a digital twin environment, fusing the collected visual passenger flow density and auditory environment noise in real time, and generating a multi-modal state matrix; predicting a passenger flow diffusion trend and fusing the passenger flow diffusion trend with the multi-modal state matrix to generate a composite feature vector; inputting the composite feature vector into a deep collaborative scheduling model, and generating a primary collaborative strategy containing broadcast volume gain and guide screen path pointing by using a strategy network with double constraints of evacuation efficiency maximization and energy consumption minimization; performing secondary constraint verification on the primary cooperation strategy to determine an optimal resource scheduling instruction; and issuing an optimal resource scheduling instruction to drive the field broadcast and the guide screen to execute actions. According to the method, quick response can be realized, the grooming efficiency and the operation energy consumption can be dynamically balanced, and instruction discretization caused by independent decision is effectively eliminated, so that the decision consistency of resource scheduling is improved.

The invention provides a vehicle track generation method and system capable of quickly responding to sudden interaction in automatic driving, and belongs to the technical field of track generation and motion control in automatic driving. Comprising the following steps: performing feature extraction on aerial view point cloud data, vehicle surrounding image data, high-precision map data and vehicle historical trajectory data to obtain a continuous environment information feature sequence in a time sequence; generating a dynamic self-adaptive anchor point representing the real-time driving environment information of the vehicle based on a continuous environment information feature sequence in a time sequence; modeling a de-noising process of a diffusion model generation track into an evolution process of a track latent variable in a de-noising network by using a Shenchang differential equation, and modulating the evolution process of the track latent variable at an activation level and an operator level of the de-noising network by a dynamic adaptive anchor point; and an ordinary differential equation decoder constructed by adopting an explicit Euler numerical integration method is adopted to carry out gradual reverse reconstruction on the evolution process of the latent variables of the track, and a future track of the vehicle is generated.

The invention relates to the technical field of line fault analysis, in particular to a high-voltage line fault identification method based on phasor analysis, which comprises the following steps of: performing multi-time window nesting decomposition on voltage phasors and current phasors acquired in the operation process of a high-voltage line, extracting a phasor dynamic response sequence, and calculating the phasor dynamic response sequence; identifying a main disturbance mechanism characteristic triggered by a fault, and constructing a main disturbance mechanism type label; a driving response dominant phasor disturbance factor is identified, a phasor factor mapping graph is constructed, factor stripping operation is executed, and a dominant purification phasor set is generated; and performing phase evolution analysis on the dominant purification phasor set, and determining a fault initial phase transition boundary and a cross-phase offset trend. According to the method, the stability and the physical consistency of identification are ensured, and the finally output fault type and phase structured result not only has clear logic traceability, but also highly meets the requirements of dispatching automation and quick response of a protection system.

The invention discloses a distributed ducted unmanned aerial vehicle monitoring and fire fighting integrated system and a control method, and belongs to the technical field of fire fighting. The system comprises a fire monitoring network deployed on the outer wall of the roof of the high-rise building, a fire-fighting unmanned aerial vehicle storeroom arranged correspondingly, a fire-fighting unmanned aerial vehicle with an anti-collision structure and a fire-fighting management platform. The method comprises the steps that a fire monitoring network or an original system triggers alarm, and an unmanned aerial vehicle library is activated; the unmanned aerial vehicle automatically takes off, infrared guidance and image acquisition approach reconnaissance are carried out, and information is returned; after the platform confirms the fire behavior, a window breaking fire extinguishing bomb is instructed to be launched, and a fire extinguishing matrix is built in cooperation with multiple mechanisms as needed; after fire extinguishing, environmental parameters are monitored, and the unmanned aerial vehicle automatically returns and resets. Through distributed monitoring, automatic quick response and multi-machine cooperation, second-level sensing and handling of fire of the high-rise building are achieved, the problems that traditional fire fighting is slow in response, difficult to arrive and poor in single-machine capacity are solved, and the fire is controlled within the golden time of 3-5 minutes.

The invention relates to the technical field of intelligent illumination control, and discloses an intelligent enhancement method and system for the brightness of an LED light-emitting module, and the method comprises the steps: collecting environment illumination data and LED module operation state data, and carrying out the preprocessing; acquiring cultural relic material information, performing exhibit change detection, determining an illumination constraint threshold, calculating effective illumination and tracking accumulated exposure; determining an illumination safety boundary and dynamically modulating an LED spectrum; performing hierarchical coordination by adopting a three-layer game decision framework; a three-dimensional light field representation framework is constructed through audience behavior perception and visual attention prediction, and space illumination optimization is carried out; environment sudden changes and audience behaviors are detected, and quick response adjustment is executed; analyzing lighting space-time distribution characteristics, performing dynamic power distribution and generating an intelligent dimming curve; according to the invention, environmental perception, cultural relic protection constraint, light attenuation compensation, multi-module cooperation and intelligent decision can be comprehensively considered.

The invention relates to the technical field of industrial automation and control systems, in particular to a heat dissipation fault early warning and monitoring system based on edge computing, which is characterized by comprising an edge computing node and a remote monitoring center which are deployed on an equipment site, an edge node collects state parameters of heat dissipation equipment in real time, generates first fault early warning and health assessment through a built-in algorithm, performs local adaptive control according to the first fault early warning and health assessment, monitors execution feedback at the same time, forms an independent'sensing-analysis-control-verification 'closed loop, and realizes millisecond-level quick response; the monitoring center carries out deep analysis and diagnosis on the received key data, generates second fault early warning, and carries out intelligent cooperation and conflict arbitration with edge early warning; and the central early warning module uniformly issues alarms. Through fusion of edge real-time closed loop and center depth cooperation, network and cloud pressure is reduced, and the reliability, decision consistency and operation and maintenance intelligence level of the system are improved.

The invention discloses a high-speed target continuous tracking system and method based on inter-satellite cooperative computing. The system comprises a distributed architecture management module, an inter-satellite communication module, a double-satellite cooperative tracking module and a distributed computing coordination module. The system provided by the invention adopts a distributed hierarchical management structure, and through a hierarchical management mechanism of intra-cluster local management and inter-cluster global coordination, not only are the quick response and autonomy of a distributed system reserved, but also the global management capability of a centralized layer is introduced, and the communication overhead is effectively reduced. In addition, a multi-type missile trajectory prediction method based on deep learning is designed, a prediction-driven tracking switching mechanism is achieved, the next round of prediction task is triggered through an adaptive threshold value, and missing of a visibility window is avoided. In the aspect of computing resource scheduling, the time delay of task scheduling can be reduced, the communication overhead is remarkably reduced while the tracking precision is ensured, the high timeliness of the tracked target is ensured, and the global continuous tracking of the target is realized.

The invention provides a smart building environment adaptive regulation and control method based on digital twinning and AI, and relates to the technical field of artificial intelligence, and the method comprises the following steps: extracting dynamic features based on multi-source system data after time alignment, so as to construct a dynamic feature set; inputting multi-source system data into the digital twin, performing iterative simulation on key environment parameters of a plurality of time steps in the future by taking a current building equipment state as a boundary condition, and outputting a multi-step prediction sequence; inputting into a model prediction controller, and solving to obtain an equipment regulation and control instruction sequence in a future first preset duration by taking the lowest total energy consumption in a prediction period as an optimization target and taking the condition that the key environment parameters do not exceed a comfort interval as a constraint condition; and the first equipment regulation and control instruction in the equipment regulation and control instruction sequence is issued to the field execution mechanism, so that self-adaptive regulation and control of the building environment are realized, the defect that passive response is performed after environmental parameters exceed the standard is overcome, and the quick response capability of the system to sudden environmental changes is remarkably improved.

The invention discloses a color consistency control method in a bamboo kitchen ware carbonization process, and belongs to the technical field of bamboo processing. The method comprises the following steps: acquiring a multi-dimensional spectral data vector of the surface of the bamboo kitchen ware; determining a multi-dimensional change rate vector of the spectral data; respectively generating a first candidate control signal and a second candidate control signal based on the spectral data and the change rate vector; determining a system dynamic state index based on the change rate vector; generating a dynamic weighting coefficient according to the dynamic state index of the system; and performing weighted fusion on the first candidate control signal and the second candidate control signal by using a dynamic weighting coefficient to generate a final heat regulation control signal. According to the invention, the method achieves the self-adaptive optimal control of all working conditions through the construction of a dual-mode decision fusion composite control system, guarantees the quick response in a dynamic stage, guarantees the smooth convergence in a steady-state stage, and fundamentally improves the thermal inertia problem of the system.

The invention provides a rockfall slope geology early warning device and method based on digital twinning, and relates to the technical field of slope geology early warning. According to the invention, slope multi-dimensional physical parameters are obtained through the perception acquisition module, standardized processing and multi-protocol transmission are completed nearby through the edge transmission module, and the cloud load is reduced. The digital twinborn module constructs a mechanical twinborn model, dynamically updates and forms a digital twinborn body in combination with standard data, and accurately copies the slope state; and the early warning decision module realizes graded early warning through a risk assessment system. A full-link closed loop of sensing, transmission, modeling and early warning is integrally formed, the problems that traditional early warning data are fragmented, manual dependence is high, and static modeling is disjointed with reality are solved, conversion from passive response to active pre-judgment is achieved, on-site rapid response and global accurate analysis are balanced, and the accuracy, real-time performance and actual combat performance of early warning of the rockfall slope are improved.

According to the intelligent operation monitoring system based on multi-source sensing, through cooperative work of the sensing terminal, the positioning base station, the intelligent video monitoring device and the back-end control system, combined monitoring of the operation environment, the personnel state and behavior violation is achieved. The system realizes indoor and outdoor seamless positioning through cooperation of UWB positioning and GPS positioning, and constructs a multi-dimensional security monitoring network in combination with environment sensor data and a video behavior recognition result. Through automatic processing of the alarm module and the video linkage module, rapid response of alarm triggering and video linkage is realized. The system supports historical data backtracking analysis to generate an operation risk thermodynamic diagram, and provides data support for safety management. The system improves the real-time performance and accuracy of operation safety monitoring, reduces the manual inspection cost, improves the emergency response efficiency, achieves the precise early warning of safety risks through multi-source data fusion, and improves the scientificity and refinement level of operation safety management.

The invention provides a coordination control method and device for an energy storage power station, electronic equipment and a storage medium, and belongs to the field of energy storage. Under the condition that the difference between the current frequency of the grid-connected point and the system frequency dead zone of the energy storage power station is greater than or equal to a preset frequency deviation threshold value, superimposing a primary frequency modulation instruction and a virtual inertia support instruction so as to doubly suppress the frequency change amplitude and the frequency change rate; the primary frequency modulation power is determined according to the SOC of the energy storage power station; when the system frequency fluctuates and deviates from the rated frequency, and the difference value between the current frequency of the grid connection point and the system frequency dead zone is smaller than a preset frequency deviation threshold value, or when the system frequency gradually approaches the rated frequency, a primary frequency modulation instruction is executed. The method can solve the problems that the energy storage power station is poor in frequency quick response performance and large in frequency steady-state deviation, and the service life of a battery is prolonged.

The invention discloses a micro-grid hierarchical coordination control method and system based on multi-time scale optimization, and relates to the field of micro-grid control, and the method comprises the steps: achieving the collaborative operation through distributed communication; on the basis of a multi-time scale dynamic coordination mechanism of hour-level rolling optimization, minute-level edge correction and millisecond-level quick response, closed-loop management from long-term scheduling to instantaneous control is realized in combination with a cross-layer linkage strategy triggered by a threshold value; the global layer makes a plan through multi-objective optimization, the regional layer dynamically allocates power by using a consistency algorithm, and the equipment layer quickly stabilizes the system by means of energy storage; an event-driven mechanism is introduced to realize cross-scale collaborative response in an abnormal state, a physical model and machine learning are fused to improve prediction precision, and parameter adaptive adjustment is realized through periodic evaluation. The method has the advantages that through cross-scale collaboration, edge calculation enabling and hybrid prediction and adaptive adjustment, micro-grid full-chain efficient management and control are achieved, and stability, economical efficiency and intelligence are considered.

The invention discloses a new energy intelligent operation and maintenance system based on AI and digital twinning, and relates to the technical field of photovoltaic power generation and energy storage, and the system comprises a sensing and control layer which is disposed at the site of an optical storage power station. Power station equipment and environment data are collected in real time through the sensing and control layer, the data collection and edge calculation layer completes preliminary analysis and quick response locally, the timeliness of fault processing is effectively improved, the cloud platform conducts deep mining and model training on mass data through an AI analysis engine, the system performance is continuously optimized, and the fault processing efficiency is improved. And the digital twinning and decision visualization module realizes holographic mirroring and dynamic deduction of the operation state of the power station and assists management personnel in accurate decision making and predictive maintenance, and the system finally forms a continuously evolved closed-loop intelligent operation and maintenance system, so that the operation and maintenance efficiency of the power station is improved. And the energy utilization efficiency, the equipment reliability and the operation and maintenance automation level are obviously improved.

The invention provides a multi-sensor fire early warning method and device, computer equipment and a medium, and belongs to the field of fire early warning, and the method comprises the steps: collecting environmental parameters in real time through a plurality of heterogeneous sensors, the environmental parameters at least comprising temperature, smoke concentration and humidity; preprocessing and normalizing the acquired environmental parameters to unify dimensions and compensate environmental interference, and outputting standardized data; organizing the standardized data into time series data, inputting the time series data into a convolutional neural network for deep feature extraction to capture a space-time evolution mode related to the fire, and outputting a fusion feature vector; and inputting the fusion feature vector into a decision model based on fuzzy logic and Bayesian reasoning, calculating a comprehensive fire risk value, and outputting a corresponding alarm grade according to a preset grading threshold. Through multi-source data fusion and deep feature extraction, the data fusion capability is improved, computing resource consumption is reduced, and accurate recognition and quick response of fire risks are realized.

The invention provides a self-adaptive ripple suppression circuit based on an MOSFET, and relates to the technical field of electronic circuits. The circuit comprises an input alternating current end EMC filtering surge protection circuit, a rectification circuit, an absorption protection filtering circuit, a clamping absorption circuit, a detection protection circuit, a control circuit, a power follow current circuit, an output filtering circuit, a stroboflash removing circuit and an LED load circuit which are connected in sequence. Under the condition that the MOSFET self-adaptive ripple suppression circuit is in a working state, voltage at the two ends of the sampling resistor is fed back to a grid electrode and a source electrode of the MOS tube, on-resistance of the MOS tube is adjusted through change of the sampling voltage on the basis of the characteristic that the MOS tube works in a variable resistance area, and output current ripples are dynamically suppressed. The circuit has excellent adaptive capacity, can dynamically suppress output current ripples in a wide load range through a simple simulation negative feedback loop, and is quick in response.

The invention discloses a method for generating a post-earthquake seismic oscillation parameter field in a peripheral area of a railway by considering a topographic site, which can consider the influence of topographic features on seismic oscillation, improve the estimation precision of the post-earthquake seismic oscillation parameter field and provide technical support for post-earthquake inspection and driving order recovery. Meanwhile, railway workers can carry out targeted field inspection according to the mileage range, the inspection range is reduced, the emergency disposal time is shortened, the road network post-earthquake emergency disposal capacity is improved, the post-earthquake loss is reduced, and the railway transportation safety is guaranteed; moreover, the calculation work can be completed before the earthquake occurs, the calculation amount is relatively small after the earthquake occurs, and the actual demand of quick response after the earthquake of the railway can be met; besides, earthquake rapid report and station observation data from an earthquake station network center are comprehensively applied, information of a railway self-built station is fused, information utilization is comprehensive, and meanwhile, earthquake oscillation around the railway is better reflected.

The application provides a kind of intelligent building environment adaptive regulation and control method based on digital twinning and AI, it is related to artificial intelligence technical field, including the following steps: based on time alignment after multi-source system data, extract dynamic characteristics to construct dynamic feature set;Multi-source system data is input to digital twinning, with the current building equipment state as boundary condition, iteratively simulates the key environmental parameters of multiple time steps in the future, and outputs multi-step prediction sequence;Again input model predictive controller, with the minimum overall energy consumption in the prediction period as the optimization goal, with the key environmental parameters not exceeding the comfort interval as the constraint condition, the equipment control instruction sequence in the first preset time in the future is solved;The first equipment control instruction in the equipment control instruction sequence is issued to the on-site actuator to realize the adaptive regulation and control of building environment, solve the disadvantage that the environment parameter is over-standard and then responds passively, significantly improve the rapid response capability of the system to sudden environmental changes.

The utility model relates to an electric control cabinet intelligent safety alarm device, which comprises an electric control cabinet main body, an ultrasonic ranging module, an alarm module and a communication module, and is characterized in that the ultrasonic ranging module measures the time difference of transmitting and receiving ultrasonic waves to determine the actual distance between an obstacle and the electric control cabinet main body, so that non-contact ranging is realized; the timeliness of alarm triggering is ensured, and accurate measurement can be carried out even in a severe environment full of dust, smog or corrosive substances and the like; the multi-mode alarm module and the ultrasonic ranging module are combined for use, multi-mode alarm is carried out when the ultrasonic ranging module triggers the alarm function, a multi-level verification and confirmation mechanism is realized, the possibility of false alarm is reduced, diversified alarm signals are provided, and the alarm can be carried out even in a noisy or poor-sight environment. Normal receiving of alarm information can also be ensured; by means of the communication module, the intelligent safety alarm device of the electric control cabinet has remote monitoring and management functions, and the quick response capability is remarkably enhanced.

The invention provides an underwater target positioning method and system based on acoustic-magnetic combined detection, belongs to the technical field of underwater target detection, and aims at solving the problems of an existing method and system in the aspects of combined detection, accurate positioning, quick response and the like. The method comprises the following steps that sonar data and magnetic field data of a target water area are obtained, the sonar data are obtained through a plurality of sonar nodes, and the magnetic field data are obtained through a plurality of aircrafts; preprocessing the sonar data and the magnetic field data, and respectively generating a sonar response parameter and a magnetic compensation coefficient of the target water area; a plurality of sonar nodes are used for monitoring a target water area, and early warning signals of candidate targets are determined according to sonar response parameters; and determining a response aircraft from the plurality of aircrafts according to the early warning signal, collecting the current magnetic field data of the candidate target according to the position information through the response aircraft, processing the current magnetic field data based on the magnetic compensation coefficient, and determining the underwater target according to the processing result.

The invention provides a real-time feature point extraction and matching method based on star operation and GateMLP, and the method comprises the following steps: S1, carrying out the preprocessing of an input image, and sending the image into a lightweight convolutional network to extract an initial feature; s2, on the basis of the output feature map, deep feature modeling is carried out by fusing the structure of a convolution branch and a star operation module, and a dense descriptor and a feature point thermodynamic diagram are output; s3, non-maximum suppression is performed on the thermodynamic diagram, and key point coordinates are screened in combination with confidence score; s4, performing rough matching on the key points of the left view and the right view by adopting cosine similarity and a mutual nearest neighbor strategy to obtain an initial matching pair; and S5, inputting the paired descriptors obtained by rough matching into the gated multilayer perceptron for fine-grained matching, and outputting accurate matching point pairs. The method provided by the invention realizes end-to-end efficient reasoning while ensuring high extraction and matching precision, has good real-time performance and robustness, and is suitable for unmanned aerial vehicle navigation, SLAM (Simultaneous Localization and Mapping) and other actual scenes needing quick response.