86 results about "Edge analytics" patented technology

The invention discloses an underground mine operation state analysis system and method based on video monitoring data, and the system comprises a data collection module which is used for collecting mine video and environment parameter data through a distributed sensor network, and generating a multi-dimensional data fusion set based on a space-time label technology; the edge analysis module is used for extracting feature parameters through a convolutional neural network algorithm based on the multi-dimensional data fusion set and generating a mine operation state recognition result; the fence construction module is used for constructing a three-dimensional digital model and a dynamic safety boundary based on the mine operation state recognition result to form a real-time monitoring reference framework; and the decision execution module is used for performing hierarchical risk assessment on the monitoring data in the security boundary based on the real-time monitoring reference framework, and generating a security early warning and disposal scheme with a tracing identifier. Each piece of early warning and disposal information is attached with a unique tracing identification code, so that follow-up event backtracking analysis is facilitated, and the risk management and control capability is continuously improved.

The invention discloses an intelligent pipe network leakage detection method based on edge calculation, and relates to the technical field of pipe network monitoring and leakage detection, and the method comprises the steps: carrying out the feature extraction of a preprocessing data set through an edge analysis terminal, and obtaining a pressure stability coefficient, a sound wave correlation coefficient and a flow mutation coefficient; inputting the pressure stability coefficient, the sound wave correlation coefficient and the flow abrupt change coefficient into a leakage probability evaluation model, and outputting a leakage risk index; and the edge decision terminal generates a leakage level signal according to the leakage risk index and triggers a positioning instruction. The pressure stability coefficient, the sound wave correlation coefficient and the flow abrupt change coefficient are extracted through the edge analysis terminal and input into the leakage probability evaluation model, the leakage risk index is output, accurate quantitative evaluation of the leakage risk is achieved, the model can adapt to changes of different working conditions through introduction of the dynamic weight, and the reliability of the model is improved. And the adaptability and accuracy of evaluation are improved.

The invention discloses a detection method and device for intelligent visual detection of parts and a storage medium, belongs to the technical field of industrial quality detection, and aims to solve the problems that surface and internal defects of complex parts are difficult to identify synchronously and the identification precision is low. The method comprises the following steps: acquiring multi-modal image data obtained through structured light three-dimensional imaging and laser ultrasonic scanning; performing geometric registration and scale normalization on the image to generate a fused image; carrying out image preprocessing and edge analysis, and extracting a region of interest; dividing the candidate region of interest into a plurality of image blocks, and inputting the image blocks into an anomaly detection network; calculating a reconstruction error between the original image block and the reconstructed image block, and generating an abnormal scoring graph; and finally, extracting a defect area through image post-processing, and outputting information such as a defect type, a spatial position, a geometric dimension and a severity level. According to the method, the robustness and accuracy of multi-modal defect identification are improved, and the method is suitable for an online visual inspection task of an industrial production line.

The invention is suitable for the technical field of distribution network detection, and provides a distribution network overhead line partial discharge integrated live detection system based on a ubiquitous Internet of Things architecture, which comprises a pulse signal detection end, an edge gateway and a cloud monitoring platform, the pulse signal detection end is used for detecting a partial discharge pulse signal of the overhead line and transmitting the partial discharge pulse signal to the edge gateway; the edge gateway comprises a synchronization pulse trigger module, a time calibration module and an edge analysis module. The generation module is used for generating a positioning distribution diagram of partial discharge points; the cloud monitoring platform comprises a multi-terminal data fusion module, a risk assessment module and a result feedback module; the server is used for fusing the positioning distribution map and the pulse characteristics, outputting a global discharge point correction distribution map, identifying a discharge type based on a discharge characteristic spectrogram, generating an insulation state evaluation result and feeding back the evaluation result to a terminal user; and a high-reliability, high-efficiency and low-cost solution is provided for the management and control of the insulation state of the distribution network.

The invention discloses a traffic incident detector system based on a domestic intelligent DSP and a detection method. The system comprises a video acquisition unit, a data exchange and storage unit, an intelligent processing core and a communication interaction unit. The intelligent processing core adopts a heterogeneous SoC chip integrating a multi-core DSP, an NPU and an FFT hardware acceleration module, the FFT module is responsible for video frame frequency domain enhancement, the NPU runs a deep learning model to carry out target detection, and the multi-core DSP executes multi-target parallel tracking and event judgment. And the data exchange and storage unit supports direct carrying of data among the modules through a unified physical address space and a DMA mechanism. The method comprises the following steps: carrying out NPU target detection on a video subjected to environment self-adaptive preprocessing; a multi-core DSP is used for tracking a target in parallel and judging an event; and finally, alarm information is generated and reported. Through heterogeneous hardware division and software and hardware cooperation, high-real-time and high-precision edge analysis is realized, and the detection reliability is improved.

The invention discloses an intelligent home control system, which relates to the technical field of intelligent home and comprises an illumination sensor, an infrared human body sensor, an auxiliary sensor, an edge analysis module, an illumination controller and an illumination strategy optimization module. The multi-source sensing data is subjected to fusion analysis through an edge analysis module, so that accurate light control based on multi-condition judgment is realized; and the lighting strategy optimization module dynamically adjusts a logic weight or a threshold value based on the abnormal behavior characteristics of the user, so that the control strategy has an adaptive optimization capability, and the response accuracy, stability and individuation level of the system are remarkably improved.

An anthropomorphic AI control system including a plurality of sensors configured to collect industrial input data. The control system also includes an artificial intelligence-enabled edge-deployed computing device configured to analyze and fuse multimodal input data and generate an output through anthropomorphic computing. The computing device includes a cognitive module performing real-time decision-making at the sensor edge and a controller to manage industrial process actuators across operational domains. In management of industrial fluid flow, the control system may include AI-enabled fluid characterization modules to calculate the Reynolds number and incorporate compliance with AGA3 and AGA8 standards.

The invention relates to a distribution line power factor real-time monitoring and collaborative optimization system and method, and belongs to the technical field of distribution line energy efficiency management systems and methods. According to the technical scheme, the system comprises a multi-source data acquisition and preprocessing module, an edge node calculation and edge analysis module, a power factor real-time analysis and state evaluation module, a multi-subject collaborative optimization decision module and a dynamic reactive compensation control execution module. An edge and cloud data interaction and full life cycle management module; and an abnormity early warning and fault diagnosis module. The method has the beneficial effects that the line network loss and the operation and maintenance cost are reduced at the same time, the fault-tolerant capability is achieved, the modular design supports multi-scene expansion, the method not only adapts to the process requirements of vanadium-titanium steel rolling, smelting and the like, but also can be flexibly applied to other high-load industrial 11kV lines, and the power factor regulation and control effectiveness and the system full-life-cycle benefits are improved.

The invention relates to the technical field of atmospheric environment monitoring, and discloses a sand and dust path monitoring system, which is characterized by comprising a data acquisition module, an image processing module, a feature extraction module, a path fitting module, a path fusion module and a geographic mapping module which are sequentially cascaded, the data acquisition module is used for receiving remote sensing data of a stationary meteorological satellite and generating a multi-time sand and dust monitoring binary image; the image processing module performs edge detection and morphological operation on the sand and dust monitoring binary image to realize accurate segmentation of a sand and dust region; the feature extraction module comprises a minimum enclosing rectangle calculation unit and an edge analysis unit and is used for extracting four types of feature points of the sand and dust area, and the four types of feature points comprise the lower right corner, the upper right corner, the right side line and the lower side line. According to the invention, by fusing edge detection, morphological operation and multi-feature endpoint identification, precise segmentation of a complex dust region and stable capture of motion features are realized, and the problem that feature points are easy to drift in a traditional method is effectively solved.

The invention discloses an intelligent bus duct and cable online monitoring system for wireless dual-mode collaborative networking, and the system comprises a data collection and preprocessing module which is used for collecting and preprocessing the monitoring data of a bus duct and a cable; the feature extraction module is used for performing normalization and feature cascade processing on the preprocessed monitoring data to generate monitoring feature data; the data encapsulation and communication module is used for encapsulating the monitoring characteristic data into a standardized data frame and transmitting the standardized data frame through a main communication link; the gateway convergence module is used for generating gateway convergence data; the edge analysis module is used for receiving gateway aggregation data, inputting the gateway aggregation data into an improved MFDFA-XGBoost fusion model for state judgment and outputting a state result; the cloud diagnosis module is used for receiving the state result and the monitoring feature data and generating and storing event records; and the alarm and operation and maintenance module is used for generating alarm information and realizing real-time monitoring and active early warning of the bus duct and the cable.

The invention relates to the field of intelligent inspection of substation equipment, discloses a substation equipment inspection path planning system based on an unmanned aerial vehicle, and aims to solve the problems that high-definition images are difficult to return in real time in low-frequency transmission under strong electromagnetic interference of a substation, and path planning is single. The system comprises five core modules, an equipment three-dimensional digital reference and feature library is constructed, new equipment is adapted in combination with operator similarity migration, and the observation pose is accurately reproduced to guarantee the image comparison precision; after airborne edge analysis, selectively returning data, and adapting to a low-frequency transmission link; and according to equipment similarity in batches, planning a global optimal path by fusing the path length and the flight risk. The system realizes efficient transmission of inspection data, is accurate and reliable in detection, balances the inspection efficiency and the flight safety, and meets the core requirements of safe, efficient and accurate inspection of the transformer substation.

The invention relates to the technical field of power system equipment monitoring, in particular to a substation equipment state monitoring embedded edge analysis system, which comprises a monitoring front-end module for acquiring and transmitting substation equipment operation state data; the edge processing module comprises a multi-scale wavelet transform unit, a topology continuity analysis unit and a manifold learning unit, wherein the multi-scale wavelet transform unit decomposes data and separates signals and noise through a self-adaptive threshold mechanism; the topological persistence analysis unit maps the de-noised signal to a high-dimensional feature space, calculates a persistent coherence group, and extracts a topological feature vector; and the manifold learning unit constructs a nonlinear manifold structure, calculates a geodesic distance, and executes discharge type identification and anomaly evaluation, and the FPGA and ARM heterogeneous calculation architecture is adopted, and through the synergistic effect of multi-scale wavelet transform, topology persistence analysis and manifold learning, high-precision extraction of weak discharge signals and accurate identification of fault modes are realized.

The invention specifically relates to the technical field of real-time fault diagnosis, and discloses an intelligent ship equipment state monitoring and fault diagnosis system, which comprises a data acquisition processing module, an edge analysis reasoning module, a local decision execution module, a cloud edge comprehensive analysis module, an optimization strategy making module and a man-machine interaction feedback module, the data acquisition and processing module is used for constructing a ship equipment state feature set; the edge analysis reasoning module is used for outputting a ship equipment state analysis result; the local decision execution module is used for generating a preliminary decision instruction; the cloud edge comprehensive analysis module is used for judging the ship equipment health level; the optimization strategy making module is used for making a global equipment optimization strategy; the man-machine interaction feedback module is used for providing an equipment state panel; by constructing a cloud edge collaborative model optimization mechanism, a global ship equipment health state evaluation model is continuously trained and optimized based on real-time feature data and historical data, and the real-time performance of fault response and the dynamic adaptability of state real-time perception are improved.

The invention discloses an intelligent garden irrigation control method, and relates to the technical field of garden irrigation, and the technical scheme is characterized in that the method comprises the following steps: collecting soil humidity, temperature and net radiation through a soil parameter detection module; acquiring wind speed, illumination intensity and future rainfall prediction through a meteorological data acquisition module; calculating and outputting a dynamic irrigation demand index based on an edge analysis module; the pressure compensation module generates a valve control instruction based on pipe network position analysis. According to the system, the dynamic irrigation demand index is calculated and output through diversified collection and the edge analysis module, so that precise irrigation can be carried out on the garden according to the actual demand; by arranging the pressure compensation module, the actual flow of each position of the pipe network can be dynamically calculated, and the flow of the pipe network is adjusted, so that the flow difference of each position of the pipe network can be reduced, and irrigation of each position of the garden is more comprehensive and accurate.

The invention discloses a tea fermentation degree identification method, system and device and a storage medium, and the method comprises the steps: inputting a to-be-identified tea fermentation image into a tea fermentation identification network, carrying out the feature extraction of the to-be-identified tea fermentation image through a first processing layer, and obtaining a first semantic feature map; performing multi-scale processing and edge enhancement processing on the to-be-identified tea fermentation image through an edge analysis and enhancement module layer to obtain a detail feature map; performing global dependency modeling processing through a second processing layer according to the first semantic feature map and the detail feature map to obtain a second semantic feature map; and performing classification identification on the second semantic feature map through a classification decision layer to obtain a fermentation degree identification result of the to-be-identified tea leaf fermentation image, thereby enhancing identification of image edge and texture detail features and establishing a cross-regional global context dependency relationship. Cooperative perception of local microscopic change and overall uniformity in the fermentation process is achieved, and then the identification accuracy of the tea fermentation degree is improved.

The invention belongs to the technical field of power system intelligent operation and maintenance, and discloses a power distribution operation and maintenance intelligent inspection system fused with edge calculation. A terminal data preprocessing unit; distributed edge analysis nodes; the nodes are interconnected with a communication link; an inspection task scheduling platform; a defect alarm generator; and a work order distribution and maintenance guide center. The surface temperature and partial discharge pulse signals of the power distribution equipment are obtained through the field inspection sensing device, time sequence alignment of multi-source data is achieved through time stamps in a unified format, normalization processing and trend modeling analysis are carried out in the terminal data preprocessing unit, and the system adopts a temperature change rate formula and a data normalization formula, so that the accuracy of the system is improved. Standardized conversion and dynamic index extraction are carried out on continuous time domain data, so that the recognition capability of early-stage heating hidden dangers and abnormal discharge symptoms is remarkably improved, and the misjudgment risk caused by data scale inconsistency or time dislocation is reduced.

The invention discloses a traffic video edge analysis system based on Yolov5-Edge and Prewitt algorithms, and the system achieves the real-time collection, intelligent recognition and encrypted transmission of a vehicle-mounted video through the construction of a layered architecture of an object-side equipment layer, an edge calculation layer and a cloud service layer. According to the system, a lightweight Yolov5-Edge model and a Prewitt edge detection algorithm are fused in edge equipment, multi-channel video parallel processing is realized under finite computing power, and the video inspection efficiency is effectively improved; the frame rate and the number of processing paths are dynamically adjusted through the resource monitoring and load control module, and the real-time performance and stability of AI reasoning are guaranteed; a data management and encryption mechanism is adopted, only abnormal data are stored at an edge end and clouded through RSA and AES encryption modes, and security and compliance of sensitive behavior information in the transmission and storage process are ensured. The system can identify and classify abnormal behaviors of drivers and passengers without depending on a high-performance server.

The invention relates to an edge analysis system supporting remote operation and maintenance of a charging station. The system comprises a core main process control module, a communication module, a database module, an electrical internet of things data alarm event analysis module, a video AI image analysis module and a camera agent registration module. The core main process control module is used for connecting the working logic of each module in series; the control module is also used for controlling sensor data, charging pile electrical Internet of Things state data, video stream data and state operation data to be stored in the database module, uploading an alarm event, monitoring a monitoring retrieval action of a superior master station and pushing the corresponding video stream data; and the controller is also used for monitoring a remote control instruction issued by the superior master station and controlling the external data acquisition device according to the remote control instruction. Data of various sensors for remote operation and maintenance of an external charging station are received and gathered, hidden danger information is found, and an alarm is given, so that full-coverage intelligent monitoring of remote operation and maintenance equipment can be realized, the cost is reduced, and the loss is reduced.

Systems and methods described herein provide an application function and interface for a Network Data Analytics Function (NWDAF) to receive, from User Equipment (UE) devices, user data for edge applications. An NWDAF receives an analytics request for user analytics for an edge application and sends, to an Edge Analytics Engine (EAE) associated with an edge location, a data request based on the analytics request. The EAE receives user data from an Edge Enabler Client (EEC) on the UE device that is connected to the edge location. The EAE forwards the user data to the network device. The NWDAF receives the user data responsive to the analytics request and generates an analytics report based on the user data.

The invention provides an edge position determination method, an edge position determination device and an edge analysis method. In the edge position determination method, an average edge position is determined by summing up intensity values in the direction of extension of lines and lines in spaced SEM images, and a first intensity distribution is fitted using a weighting function in which the weight at the average edge position is maximum and a fitting function determined from the first intensity distribution, and a second intensity distribution is fitted using a fitting function determined from the second intensity distribution. The first intensity distribution represents a distribution of intensity values along a direction perpendicular to the extension direction at coordinates representing each position in the extension direction of the SEM image, and the edge position at the coordinates is determined on the basis of a second intensity distribution obtained by fitting.

The invention relates to the technical field of bridge structure health monitoring, and discloses an urban bridge sidewalk multi-mode vibration monitoring and early warning system, which comprises a vibration sensing execution unit, an MEMS (Micro Electro Mechanical System) three-axis acceleration sensor with a built-in temperature compensation sheet, and a vibration detection unit, and is characterized in that the MEMS three-axis acceleration sensor is packaged in a 304 stainless steel base with a rubber damping pad; the self-adaptive data acquisition and transmission unit is connected with a LoRa wireless node of the vibration sensing execution unit; the edge analysis execution unit is used for receiving an embedded AI chip of data of the acquisition and transmission unit and executing vibration spectrum fingerprint matching and comfort level rating operation; and the early warning output execution unit is connected with an audible and visual alarm and a 4G communication module of the edge analysis unit. Through an embedded AI chip of the edge analysis unit, a 1 / 3 octave frequency spectrum is generated in real time and is matched with a fingerprint database, progressive early warning is realized through sound-light alarm and 4G communication, digital mapping of sidewalk vibration characteristics and pedestrian perception is established for the first time, and the defect of lack of a correlation model in the prior art is overcome.

The application provides a conference picture abnormality processing method and system based on video semantic understanding, and relates to the technical field of video processing. The method comprises the following steps: dynamically grouping a plurality of edge analysis nodes to obtain P high-availability backup groups; taking a dynamic semantic vector as a semantic matching benchmark to position a first video acquisition device to perform gradual switching from an initial display picture to a semantic adaptive picture; starting a signal layer pixel-level monitoring function to perform group internal multi-node collaborative disaster recovery; performing frame-level semantic incremental analysis to obtain a plurality of incremental semantic feature vectors to perform signal content bimodal health closed loop until a conference termination instruction is triggered. The technical problem that in the prior art, video scheduling modes are mostly based on fixed round patrol strategies or manual experience to perform picture scheduling, lack semantic understanding ability for video content itself, and cause obvious misalignment between conference semantic content and on-site display pictures, thereby reducing information presentation accuracy in the process of emergency command is solved.

The invention discloses a mining pipeline leakage positioning and intelligent valve closing system based on 5G + AI. The mining pipeline leakage positioning and intelligent valve closing system comprises a multi-mode sensor deployed at a pipeline key node, a mining 5G communication network, a cloud edge collaborative analysis platform and an intelligent execution unit. The sensor collects vibration and pressure waveform data, and the vibration and pressure waveform data are synchronously transmitted through a 5G network in a low-delay manner; the edge analysis unit is internally provided with a lightweight AI model for leakage initial judgment and triggering; the cloud analysis unit performs fusion analysis on multi-node synchronous data by adopting a space-time convolutional neural network to realize sub-wavelength level accurate positioning and intensity evaluation of a leakage point; and the decision engine generates an intelligent instruction containing a dynamic valve closing strategy according to the positioning and evaluation result, and issues the intelligent instruction to the intelligent valve for execution through the 5G network. The problems that a traditional method is poor in positioning precision, lagged in response and high in false alarm rate are solved, rapid sensing, accurate positioning, intelligent decision making and self-adaptive optimization of leakage events are achieved, and the safety and reliability of the mining liquid supply pipeline are remarkably improved.

This invention discloses a high-precision detection method for concave and convex feature points based on multi-segment straight line edge analysis, comprising the following steps: S10, image acquisition; S20, preprocessing and edge detection; S30, straight line segment extraction and filtering; S40, line segment relationship analysis and concave / convex hypothesis generation; S50, hypothesis verification and precise positioning; S60, outputting the coordinates of concave and convex points. This invention overcomes the dependence on continuous and complete contours by directly detecting and filtering multi-segment straight line edges related to potential concave and convex features from the image. Based on this, it robustly and accurately locates the coordinates of convex and concave points by analyzing the spatial topological relationships and geometric constraints between these straight line segments.

The invention provides a functionality for providing edge load analytics at an edge analytics producer as well as functionality for utilizing this edge load analytics for optimizing edge service performance. An edge analytics producer is configured to collect data and to perform edge load analytics considering data producers from different domains, to allow for edge analytics enablement. Further, based on the derived edge load analytics by the edge analytics producer, an analytics consumer is configured to generate a trigger event that indicates a predicted overload and a specific action to be performed.

The invention relates to the technical field of intelligent safety monitoring, and discloses a wireless intelligent smoke sensing and power utilization safety cooperative monitoring network system, which comprises a plurality of multi-mode sensing units configured by intelligent sensing nodes in a distributed manner and used for synchronously acquiring chemical fingerprints, electromagnetic acoustics and environmental data; an edge processor performs edge analysis through a preset AI model, generates and broadcasts a local event vector after identifying a persistent or mutable risk, performs multi-source information cross validation by calculating a regional evidence factor, and evaluates a quantized regional threat level in combination with local confidence. The gateway device may also perform hierarchical intervention according to threat levels, and predict a risk propagation path based on an architectural space environment map model. Through combination of edge intelligence and center cooperation, high-precision identification of early-stage hidden fire disasters is realized, the false alarm rate is significantly reduced through multi-source information cross validation, and the reliability of early warning and the accuracy of intervention are improved.

The invention discloses a clock production quality detection method and system based on machine vision, and the method comprises the steps: fusing the two-channel data of a visible light image and an infrared image in an input layer through a YOLOv5s convolutional neural network model, adding an SPP-F spatial pyramid pooling layer in a network structure, inputting an initial feature image into the improved YOLOv5s convolutional neural network model, and carrying out the detection of the clock production quality. Outputting a part positioning area; performing sub-pixel edge analysis on the part positioning area based on an edge positioning algorithm of a Zernike moment, acquiring a movement track of a clock pointer through a sensor, and analyzing the movement track of the clock pointer in combination with an optical flow method and a Kalman filter to obtain a track analysis result; and generating a detection report according to the trajectory analysis result and the clock defect detection result, marking defect positions and recommending polishing process parameters. Automatic detection is realized in the whole process, the dependence on artificial experience is greatly reduced, and the detection efficiency is improved.

The present invention discloses a switch jam diagnosis method, system and storage medium based on a single-chip microcomputer. The method is applied to a switch jam diagnosis system based on a single-chip microcomputer, and the system includes: a single-chip microcomputer and an edge analysis module. The method includes: obtaining a switch status signal after the target switch is closed according to the single-chip microcomputer, and transmitting the switch status signal to the edge analysis module; performing impact detection on the received switch status signal according to the edge analysis module, and determining the jam diagnosis result of the target switch according to the signal impact of the impact detection. The present invention avoids the problems of high computing power resource requirements and insufficient application scenarios in the existing switch jam diagnosis method based on deep learning, and can achieve efficient and accurate diagnosis of the jam fault of the switch in the switch cabinet, with low computing power resource requirements. At the same time, the solution has strong interpretability, can quickly adapt to the switch jam diagnosis scenarios of various switch cabinets, and has better rapid implementation capabilities.

The application discloses a kind of based on cloud edge collaborative processing's internet of things information management system, belong to internet of things information management technical field, by real-time collection internet of things data to sensing terminal, and transmit internet of things data to edge end;Edge end is preprocessed to the internet of things data received, obtains standardized internet of things data;Real-time determination edge analysis task, according to edge analysis task call corresponding built-in task analysis mode is analyzed to standardized internet of things data, obtains edge task analysis result;Standardized internet of things data and edge task analysis result are screened, obtain high-value data, abnormal data and data abstract, and high-value data, abnormal data and data abstract are sent to cloud end;Cloud end is according to the high-value data, abnormal data and data abstract received task analysis processing;And sensing terminal is collected parameter management.

The invention discloses an edge gateway service dynamic control system, which belongs to the technical field of edge gateways and comprises a cloud management platform and an edge end. The cloud management platform comprises a target analysis module; the edge end comprises a monitoring module, an edge analysis module and a control module; the target analysis module is used for carrying out real-time analysis on the control equipment to obtain edge analysis targets of the control equipment, carrying out strategy analysis according to the edge analysis targets to obtain target control strategies of the edge analysis targets, and sending the edge analysis targets and the target control strategies to the edge analysis module; the monitoring module is used for monitoring the control equipment in real time to obtain monitoring data; the edge analysis module is used for performing control analysis, analyzing the monitoring data according to a target control strategy and edge analysis targets, obtaining control information of each edge analysis target, and sending the control information to the control module; and the control module is used for controlling the control equipment according to the received control information.