Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

61results about How to "Solve the low detection accuracy" patented technology

Knowledge distillation-based target detection model training method

The invention relates to a training method of a target detection model based on knowledge distillation, and belongs to the field of target detection. Comprising the following steps: constructing a training data set and a target detection model, and training the target detection model based on the training data set to output an inference graph; calculating a first loss function to obtain a trained target detection model, and taking the trained target detection model as a teacher model; simplifying parameters of the teacher model to obtain a student model; obtaining a second training data set based on the training data set, training the teacher model and the student model based on the second training data set, and respectively outputting prediction labels; and calculating a second loss function to obtain a trained student model as a trained target detection model. According to the method, the optimal distillation temperature and loss coefficient are obtained by adopting the differential mutation algorithm, and the trained target detection model is obtained by training the student model through knowledge distillation, so that the problem of low detection precision caused by the fact that the existing target detection model is trained by a small amount of samples is solved.
Owner:BEIJING JINGHANG COMPUTING & COMM RES INST

Multi-data fusion lithium battery thermal runaway detector and detection method

The invention relates to a multi-data fusion lithium battery thermal runaway detector and detection method.The lithium battery thermal runaway detector comprises a hollow shell, a microprocessor and multiple sensors, the microprocessor and the multiple sensors are installed in the shell, and one sensor is a dual-waveband dual-light-path smoke sensor; the dual-band dual-optical-path smoke sensor comprises two detection light sources, a first full-band photodiode and a second full-band photodiode, the two detection light sources are arranged in parallel and are a 940nm red light emitting diode and a 450nm blue light emitting diode respectively, and the included angle between the first full-band photodiode and the detection light source is 135 degrees. The included angle between the second full-wave band photodiode and the detection light source is 66.5 degrees; and the microprocessor is configured to perform thermal runaway detection on the lithium battery through a thermal runaway detection model based on deep learning based on various detection data acquired by the various sensors. The problem that an existing lithium battery thermal runaway detector is low in detection accuracy is solved.
Owner:ANHUI ELECTRIC POWER DESIGN INST CEEC

Intelligent low-altitude unmanned aerial vehicle cluster air-ground cooperative detection fire extinguishing system and method

The invention discloses an intelligent low-altitude unmanned aerial vehicle cluster air-ground cooperative detection fire extinguishing system and method, a patrol plan is made by determining the patrol time interval of a patrol area of an unmanned aerial vehicle and the density of patrol routes, the system can dynamically adapt to the change of seasons and human activities, and the system and method are more accurate and more efficient. Fire missing detection can be effectively avoided; identifying a fire source by adopting a multi-source data fusion technology, determining whether the fire source exists in the forest region through the infrared image and the actual image of the forest region, and determining the intensity and the position of the fire source according to the smoke concentration when determining that the fire source exists in the forest region. The problem that the accuracy of infrared thermal imaging is affected and the detection precision is low due to the temperature difference of different vegetation, the change of the sunlight irradiation angle, water vapor in the atmosphere and the like can be solved. The fire trend prediction module and the fire extinguishing scheme generation module are adopted to automatically realize fire extinguishing of the forest area, the prediction result is efficient and accurate, and missing of the optimal fire extinguishing opportunity can be avoided.
Owner:BEIJING HUALU CHUANGZHI TECH CO LTD

Gas infrared cross detection system and detection method

The invention provides a gas infrared cross detection system and a detection method, and belongs to the technical field of gas detection. A first detection channel and a second detection channel are arranged in a cavity in parallel at an interval. The first photoacoustic receiving module converts a first photoacoustic signal generated in the first detection channel into a first electric signal. The second photoacoustic receiving module converts a second photoacoustic signal generated in the second detection channel into a second electric signal. The first signal processing module filters and amplifies the first electric signal to obtain a first detection signal. The second signal processing module filters and amplifies the second electric signal to obtain a second detection signal. And the differential amplification module performs differential amplification on the first detection signal and the second detection signal to obtain a concentration detection signal, so that the purpose of differential noise reduction is achieved, and a target signal is enhanced. The main control module determines the concentration of the detected gas according to the concentration detection signal, so that the concentration detection precision is improved, and the problem of low detection accuracy in the traditional technology is solved.
Owner:CHINA GENERAL NUCLEAR POWER OPERATION

Soil monitoring method, soil monitoring device and computer readable storage medium

The invention provides a soil monitoring method, a soil monitoring device and a computer readable storage medium. The method comprises the following steps: acquiring initial multi-source sensor data and a spectral image of soil; performing real-time calibration on the multi-source sensor data by using a self-calibration technology to obtain target multi-source sensor data; inputting the spectral image into a soil image recognition model to obtain target soil data; and analyzing the target multi-source sensor data and the target soil data to obtain soil abnormal data, and sending out early warning information according to the soil abnormal data. The method solves the problem that the traditional soil monitoring method depends on manual sampling and laboratory analysis, so that the soil detection precision is low.
Owner:GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1

Bubble identification method, application and system based on machine vision

The invention relates to a bubble recognition method based on machine vision, and the method comprises the steps: obtaining an image sequence of a test liquid environment, enabling the upstream side of a target object to be provided with a gas cavity, enabling the image sequence to be obtained when gas pressure is applied to the upstream side of the target object, and enabling a focal plane corresponding to the imaging of the image sequence to form an included angle larger than 0 degree with a vertical plane, and performing bubble recognition on the image sequence based on an image recognition algorithm, judging whether the image sequence contains bubbles according to a recognition result so as to obtain a first bubble-containing image, and determining the gas pressure applied to the upstream side of the target object at the collection moment according to the collection moment of the first bubble-containing image. According to the invention, the problem of low first bubble point detection accuracy is solved. The first bubble point is detected by obtaining the image sequence, large manual detection errors are avoided, and the detection accuracy is improved. Meanwhile, an included angle is formed between the focal plane and the vertical plane, so that a single image acquisition device can obtain clear images of the bubbles.
Owner:HANGZHOU COBETTER FILTRATION EQUIPMENT CO LTD

Multi-mode energy storage power station fire detection system based on image and time sequence analysis

The invention provides a multi-mode energy storage power station fire detection system based on image and time sequence analysis. The system comprises a feature extraction module, a short-term fire decision module and a long-term fire decision module. Meanwhile, the invention provides a multi-modal energy storage power station fire detection method based on image and time sequence analysis, and the method comprises the following sub-steps: S1, obtaining a video image of a fire region, and extracting a feature vector in each frame of image; s2, making a short-term fire decision; s3, making a long-term fire decision; according to the method provided by the invention, image feature extraction and time sequence analysis technologies are combined, and early detection and early warning of the fire of the energy storage power station are realized through multi-modal fusion; dynamic behaviors of continuous video frames are analyzed through a long short-term memory (LSTM) network, short-term fire decision making and long-term fire decision making are combined, and the accuracy and response speed of fire detection are remarkably improved.
Owner:KUNYUE INTERNET ENVIRONMENTAL TECH (JIANGSU) CO LTD

Information determination method, device and equipment, computer storage medium and computer program product

The embodiment of the invention discloses an information determination method. The method comprises the steps of obtaining historical operation data of assets in a network system, first data of the assets for historical access requests and second data of the assets for target access requests; based on the historical operation data, the first data and the second data, generating target detection information of services provided for the assets; and obtaining target data of the asset for the to-be-processed access request, and determining a target service of the asset for the to-be-processed access request from a target database based on the target data and the target detection information. The embodiment of the invention further discloses an information determination device and equipment, a computer storage medium and a computer program product.
Owner:CHINA MOBILE COMM GRP CO LTD +1

High-voltage interlocking detection method, high-voltage interlocking detection system and computer equipment

The invention relates to a high-voltage interlocking detection method, a high-voltage interlocking detection system and computer equipment. The high-voltage interlocking detection system comprises a controller of a vehicle and all high-voltage components. The controller and the low-voltage interlocking wire harness form a low-voltage interlocking loop; the high-voltage components are connected in series in the low-voltage interlocking loop through low-voltage interlocking wire harnesses; and the controller is respectively connected with each high-voltage component. The method comprises the following steps: performing low-voltage detection on a low-voltage interlocking loop to obtain a first detection state; and acquiring a voltage state corresponding to each high-voltage component, and determining a high-voltage interlocking detection result according to the voltage state and the first detection state. Through the method and the device, the problem of low detection accuracy caused by false alarm in related technologies is solved, the robustness of high-voltage interlocking detection is enhanced by combining the voltage state corresponding to each high-voltage component with the first detection state of low-voltage detection, and the driving safety is improved.
Owner:ZHEJIANG ZEEKR INTELLIGENT TECH CO LTD +2

A multi-modal fake news detection method and device

The application discloses a multi-modal false news detection method and device, and relates to the field of multi-modal cognitive computing. The method is used for providing in-depth mining and analysis of news information, realizing semantic enhancement of multi-modal information, and mining and application of news sentiment features. According to the BERT model, the first image caption information is subjected to feature coding to obtain a first caption representation and a first empirical representation. A first text representation is subjected to a self-attention mechanism, a full connection layer and averaging to obtain a sentiment representation of comprehensive analysis of the first text representation by all experts and a sentiment tendency evaluation value of comprehensive analysis of the first text representation by all experts. According to the attention weights of a plurality of different sentiment news processors and the first news processing features, news aggregation features for true or false classification are obtained. According to the news aggregation features for true or false classification and a false news detector, a prediction label of the first news is obtained.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Water immersion identification method and device, computer equipment and storage medium

The invention belongs to the technical field of artificial intelligence, and relates to a water immersion identification method and device, computer equipment and a storage medium, the method comprises the following steps: receiving real-time water immersion data collected by water immersion data collection equipment, the real-time water immersion data comprising real-time sensor data and real-time image data; performing state estimation processing on the real-time sensor data according to a Kalman filtering algorithm to obtain a water immersion state estimation value; performing visual verification processing on the real-time image data according to an image recognition technology to obtain visual water immersion confidence; performing fuzzy reasoning processing according to a fuzzy rule, the water immersion state estimation value and the visual water immersion confidence to obtain a fuzzy reasoning result; performing defuzzification processing on the fuzzy reasoning result to obtain an accurate alarm confidence coefficient; and confirming a water immersion identification result according to the accurate alarm confidence coefficient. According to the invention, through fusion analysis and intelligent reasoning of multi-source information, accurate identification and reliable early warning of the water immersion state are realized.
Owner:QINGDAO WEIZHIHUI INFORMATION

Optical meter axis movement detection device for constructing concave lens based on microfluidics

The utility model relates to an optical meter axis movement detection device for constructing a concave lens based on microfluidics, and relates to the field of microfluidics. The device comprises a microfluidic array, liquid drops, an image sensor and a control assembly, the micro-fluidic array comprises each micro-fluidic unit; the micro-fluidic unit comprises a first micro-fluidic chip and a second micro-fluidic chip; the bottom surfaces of the first micro-fluidic chip and the second micro-fluidic chip are coplanar, and the top surfaces of the first micro-fluidic chip and the second micro-fluidic chip form a convex shape; the lower surface of the liquid drop is in contact with the convex shape; the micro-fluidic array is arranged between the optical meter shaft and the image sensor; the direction of light rays diffracted by the laser irradiation optical surface axis points to the liquid drop from the convex shape; the control assembly is used for controlling the first micro-fluidic chip and the second micro-fluidic chip to apply voltage, so that the liquid drop is in a concave lens shape, and light rays diffracted by the laser irradiation optical surface axis penetrate through the liquid drop. The objective of the utility model is to solve the problem of low detection precision of optical watch axis movement detection at present.
Owner:MAXIC TECHNOLOGY CORPORATION

Wafer inspection method and device

This invention discloses a method and apparatus for inspecting wafers. The inspection method includes: acquiring grain registration marks contained in the wafer and the wafer to be inspected; determining a grain registration path based on the wafer to be inspected and the grain registration marks; determining a detection path based on the wafer to be inspected; acquiring a grain registration image of the grain row while the wafer moves along the grain registration path; acquiring a grain registration mark template image; determining the deviation between the actual position and the theoretical position of the grain registration mark in each wafer row based on the grain registration image and the grain registration mark template image; when the wafer moves along the detection path and the wafer to be inspected image of the grain row is acquired, determining the region of interest image of each wafer based on the deviation; and determining the defect detection result of the wafer based on the region of interest image. The accuracy of wafer inspection can be improved by using the above inspection method.
Owner:SHANGHAI JINGJI SEMICON TECH CO LTD

Anti-poisoning federated privacy leakage detection method based on local personalized learning

The present application provides a method for detecting federal privacy leakage with anti-poisoning based on local personalized learning, which includes: the IoT device determines the logical adjustment loss value based on the total number of categories supported by the initial detection model, the weight of each category supported by the initial detection model, the correction vector of each category, the predicted label and the true label; the network parameters of the initial detection model are adjusted based on the logical adjustment loss value to obtain a candidate detection model; the reference model parameters are obtained from the candidate detection model, and the reference model parameters are sent to the central server; the central server determines the initial global model parameters based on multiple reference model parameters; the central server determines the target global model parameters based on the initial global model parameters, and sends the target global model parameters to the IoT device, so that the IoT device obtains the target detection model based on the target global model parameters. Through the technical solution of the present application, it is possible to accurately know whether the privacy data is leaked.
Owner:HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD

Component porosity lossless prediction method and device, storage medium and electronic equipment

The invention discloses a component porosity lossless prediction method and device, a storage medium and electronic equipment. The method comprises the steps that a to-be-detected target component is placed in a detection platform to be subjected to frequency detection, a frequency detection result is obtained, and a laser excitation probe and a three-dimensional laser vibration meter are placed on the two sides of the detection platform; determining a highest frequency signal in the frequency detection result; determining an ultrasonic signal corresponding to the highest frequency signal through a laser excitation probe, and receiving the ultrasonic signal through a three-dimensional laser vibration meter; and processing the ultrasonic signal to obtain a non-linear zero-frequency wave signal, determining a target deep learning network model based on the non-linear zero-frequency wave signal, and predicting the porosity of the target component through the target deep learning network model. The problem that in the prior art, the detection accuracy of the porosity of the additive manufacturing component is low is solved.
Owner:XIAMEN UNIV +1

A catenary wear detection device

This utility model provides a contact wire wear detection device, relating to the field of wear detection technology. It includes a busbar with a cleaning mechanism at its bottom. The cleaning mechanism includes a detection housing, a cleaning box fixedly connected to the outer surface of the detection housing, a cleaning rod rotatably connected to the inner surface of the cleaning box via a bearing, a cleaning brush fixedly connected to the outer surface of the cleaning rod, and two limiting rods fixedly connected to the outer surface of the cleaning box. Sliding blocks are slidably connected to the outer surfaces of the two limiting rods. This utility model achieves automatic cleaning of the contact wire inside the busbar before detection. Through the coordinated action of the cleaning brush and scraper, it can efficiently wipe away stains on the wire surface and promptly clean the dirt attached to the cleaning brush, avoiding secondary contamination. This solves the problem of low detection accuracy caused by stains on the wire surface in existing detection devices, significantly improving the reliability of wear detection data.
Owner:TIEKE DIGITAL INTELLIGENT TRANSPORTATION TECHNOLOGY (CHENGDU) CO LTD

Optical meter axis movement detection device for constructing convex lens based on microfluidics

The utility model relates to an optical meter axis movement detection device for constructing a convex lens based on microfluidics, and relates to the field of microfluidics. The optical surface axis movement detection device for constructing the convex lens based on microfluidics comprises a microfluidics array, liquid drops and an image sensor, the micro-fluidic array comprises each micro-fluidic unit; the micro-fluidic unit comprises a first micro-fluidic chip; the liquid drop is located on the surface of the first micro-fluidic chip and is in a convex lens shape; the micro-fluidic array is arranged between the optical meter shaft and the image sensor; the direction of light rays diffracted by the laser irradiation optical surface axis points to the liquid drop from the first micro-fluidic chip; the image sensor is used for collecting a first gray level image before the optical meter shaft moves and a second gray level image after the optical meter shaft moves, and the first gray level image and the second gray level image are used for detecting movement information of the optical meter shaft. The objective of the utility model is to solve the problem of low detection precision of optical watch axis movement detection at present.
Owner:MAXIC TECHNOLOGY CORPORATION

Strain sensor and electric vehicle

The utility model discloses a strain sensor and an electric vehicle. The strain sensor comprises a metal substrate, an induction chip and a signal processing chip which are sequentially stacked. A first fixing part is arranged between the metal substrate and the sensing chip, and the first fixing part is used for fixing the sensing chip above the metal substrate; the sensing chip is electrically connected with the signal processing chip, a second fixing part is arranged between the sensing chip and the signal processing chip, and the second fixing part is used for fixing the signal processing chip above the sensing chip. By adopting the scheme, the problem of low detection precision of the strain sensor is solved.
Owner:GUANGDONG GOBAO INTELLIGENT TECHNOLOGY CO LTD

Equipment for detecting quality of inner wall of metal tank on production line

The invention relates to the field of metal can quality inspection, and provides production line metal can inner wall quality detection equipment which comprises a first visual detection assembly, a second visual detection assembly and a third visual detection assembly which are arranged in the conveying direction of a production line. The first visual inspection assembly is used for acquiring an image of the inner bottom wall of the metal can from the position over the metal can; the second visual detection assembly is used for obtaining an image of a first area of the inner side wall of the metal can from the position over the metal can; the third visual detection assembly comprises a plurality of visual detection parts which are uniformly arranged at intervals in the circumferential direction and are used for acquiring images of a second area of the inner side wall of the metal can from the inclined upper part of the metal can in different directions; the second region is located below the first region. The problem that the detection precision of the inner side wall of the metal can is low is solved.
Owner:BEIJING MIAOXIANG SCIENCE & TECHNOLOGY CO LTD

Odometer detection method and device, electronic equipment and storage medium

Embodiments of the present application disclose a kind of odometer detection method, device, electronic equipment and storage medium, method includes: the odometer associated data of odometer and the measurement source associated data of measurement source are acquired;Wherein, the odometer associated data includes odometer data and odometer state;The measurement source associated data includes measurement source data and measurement source state;In the case where it is determined that the odometer state is odometer delay effective and the measurement source state is measurement source effective, the deviation data of the odometer data and the measurement source data is calculated;According to the deviation data, the detection state of the odometer is determined.The technical scheme of the present application embodiment can improve the accuracy of odometer state detection.
Owner:UISEE TECH BEIJING LTD

Defect detection method, system, terminal and medium based on base paper graphitization equipment

The present application is applicable to the technical field of carbon paper production detection, and provides a defect detection method, system, terminal and medium based on base paper graphitization equipment. The method includes first acquiring real-time acquisition image set information, and simultaneously acquiring real-time voltage information, historical voltage information and nominal voltage information, and then comprehensively generating voltage fluctuation amplitude information based on the real-time voltage information, historical voltage information and nominal voltage information. If the voltage fluctuation amplitude information is greater than the fluctuation amplitude threshold, the current moment information and the retrospective moment information are acquired, and then based on the real-time acquisition image set information, the first target image information and the second target image information are determined, and finally the detection result information of the first target image information is determined. The present application can effectively reduce the subjective deviation of manual detection, significantly improve the accuracy and reliability of the detection results, effectively improve the overall accuracy of the detection, and improve the intelligence of the base paper graphitization equipment.
Owner:湖南隆深氢能科技有限公司

Radar adaptive detection method based on improved large-dimensional precision matrix estimation

The invention relates to the technical field of radar signal processing, in particular to a radar adaptive detection method based on improved large-dimensional precision matrix estimation. The problem that existing radar detection is low in accuracy is solved. The method comprises the steps of collecting radar data and preprocessing the radar data to obtain preprocessed radar data; determining a to-be-detected unit and a reference unit according to the preprocessed radar data; constructing a sample covariance matrix according to the reference unit, and then inversing the sample covariance matrix to obtain a sample precision matrix; obtaining an improved precision estimation matrix according to the sample precision matrix; and judging whether a target exists in the distance unit of the place where the unit to be detected is located according to the improved precision estimation matrix. By using the method, the detection performance of a radar system under the condition that the dimension N and the sample size K are in the same order of magnitude can be remarkably improved. The problem of low radar detection accuracy caused by poor detection performance of a self-adaptive detector in a large-dimensional asymptotic system in the existing method is solved.
Owner:HARBIN INST OF TECH

Driving fatigue detection system based on abnormal actions of driver

The invention discloses a driving fatigue detection system based on abnormal actions of a driver, and relates to the technical field of driving fatigue detection, the system comprises a video acquisition unit, a video preprocessing unit, a feature extraction unit, a fatigue detection algorithm unit and a fusion detection unit; the video preprocessing unit is used for preprocessing each hand and head action image to obtain preprocessed hand and head action images; the feature extraction unit is used for carrying out key feature extraction on the preprocessed hand and head action images to obtain hand and head action features, and the fatigue detection algorithm unit is used for carrying out fatigue detection according to all the hand and head action features to obtain an action recognition result; and the fusion detection unit determines a final fatigue detection result of the driver according to the action recognition result. The driving fatigue detection precision is improved.
Owner:FUZHOU UNIV

Lithium battery hot pressboard flatness and parallelism detection device and system

The utility model provides a lithium battery hot pressboard flatness and parallelism detection device and system, and belongs to the field of lithium batteries. The device comprises an upper pressing plate, a lower pressing plate and a detection device, the upper pressing plate and the lower pressing plate are arranged in parallel in a spaced mode, the detection device is arranged between the upper pressing plate and the lower pressing plate and comprises a sliding rail mechanism, a sliding rod and a displacement sensor, the sliding rail mechanism comprises two stand columns and a first sliding rail, the stand columns are arranged perpendicular to the lower pressing plate, and the two stand columns are arranged in a spaced mode; the first sliding rail is erected on the two stand columns and is parallel to the lower pressing plate, the sliding rod is arranged on the first sliding rail in a sliding mode, and the displacement sensor is arranged on the sliding rod and enables the probe direction of the displacement sensor to be perpendicular to the lower pressing plate. By adopting the lithium battery hot pressboard flatness and parallelism detection device and system provided by the embodiment of the utility model, the problem of low detection precision in the prior art can be solved.
Owner:XIAOGAN CORNEX NEW ENERGY INNOVATION TECHNOLOGY CO LTD

Obstacle avoidance scene detection method, device, equipment and storage medium

The present invention relates to the field of automatic driving detection technology, and in particular to a detection method, device, equipment and storage medium for obstacle avoidance scenes. By acquiring the driving data of the main vehicle during driving, the target obstacles in the surrounding environment and the position information of the target obstacles, the predicted driving trajectory of the main vehicle in the next time period in the current driving direction is calculated based on the driving data, and the first distance of the predicted driving trajectory relative to the target obstacle and the second distance of the main vehicle relative to the target obstacle are calculated based on the driving data, the position information of the target obstacle and the predicted driving trajectory. Based on the first distance and the second distance, it is determined whether the scene corresponding to the road test data is an obstacle avoidance scene. The problem that obstacles cannot be effectively screened accurately and the accuracy of obstacle avoidance scene detection is low in the prior art is solved.
Owner:GUANGZHOU WERIDE TECH LTD CO

Text image direction detection method based on deep learning

The invention provides a text image direction detection method based on deep learning, and belongs to the field of computer vision, and the method comprises the steps: cutting an original text image according to a preset size, and obtaining a preprocessed text image; inputting the preprocessed text image into an image direction detection model to obtain a direction confidence data set; detecting whether the maximum confidence data in the direction confidence data set meets the confidence threshold requirement, and when the confidence threshold requirement is met, taking the direction corresponding to the maximum confidence data as the text detection direction; and when the confidence coefficient threshold requirement is not met, height-width ratio data of the original text image is adjusted, and re-detection is performed through the image direction detection model. The method is based on the image direction detection model, the detection precision of the character direction in the image is improved, and the attention of the model on the character content characteristics in the image is improved by adjusting the aspect ratio of the original text image, so that the method can be suitable for complex image scenes to meet the requirements of downstream task processing.
Owner:BEIJING BAIGEFEICHI TECH LLC

Data processing method and device for unmanned aerial vehicle detection

The invention discloses a data processing method and device for unmanned aerial vehicle detection. The method is applied to an unmanned aerial vehicle sound wave detection system so as to detect an unmanned aerial vehicle, and comprises the steps that to-be-processed sound wave data are obtained, and the to-be-processed sound wave data are data used for representing to-be-detected sound waves collected by a sound wave collection device of the unmanned aerial vehicle sound wave detection system; sound wave enhancement processing is carried out on the to-be-processed sound wave data, enhanced to-be-detected sound wave data are obtained, and the enhanced to-be-detected sound wave data are used for representing data obtained after sound wave enhancement of to-be-detected sound waves; and performing identification processing based on sound wave parameters on the enhanced to-be-detected sound wave data to obtain detection result data. By enhancing the sound wave, the accuracy of detecting the unmanned aerial vehicle by the sound wave is improved, the problem that the accuracy of detecting the unmanned aerial vehicle based on the sound wave is low is solved, and the technical effect of improving the accuracy of detecting the unmanned aerial vehicle by the sound wave is achieved.
Owner:BEIJING INST OF TECH QUANSHENG TECH CO LTD

Abnormal cover opening intelligent alarm system for under-mine maintenance

The invention relates to the technical field of abnormal alarm, and particularly discloses an abnormal cover opening intelligent alarm system for under-mine maintenance, and the system comprises a live detection module which is responsible for detecting the electrical state of equipment and judging whether the equipment is live; the deviation determination module is used for setting a standard dust concentration value and acquiring a critical value of the electrified detection module under the concentration value; setting a plurality of different dust concentration values, collecting critical value data of the electrified detection module under the dust concentration values, and establishing a data set; training a neural network model by using the data set to obtain a simulation measurement model; the calibration module is used for monitoring the dust concentration of the current environment in real time and calculating a simulation critical value by using a simulation measurement model; calibrating the standard critical value by comparing the difference between the current simulation critical value and the standard critical value to obtain a calibration critical value; and the alarm module is used for monitoring whether the equipment has an abnormal cover opening condition or not by combining the electrification condition and the cover opening state of the equipment.
Owner:YUEQING BADA VACUUM ELECTRICAL APPLIANCE SWITCHGEAR PLANT

Outlier detection method based on data acquisition and knowledge filtering and related device

The invention belongs to the technical field of outlier detection / abnormal point detection of industrial production data, and discloses an outlier detection method based on data acquisition and knowledge filtering and a related device. The outlier detection method based on data acquisition and knowledge filtering comprises the following steps: acquiring industrial production data; based on the collected industrial production data, performing classification detection by using an outlier detection model based on knowledge filtering to obtain an outlier detection result; wherein the outlier detection model based on knowledge filtering comprises an encoder, a decoder and a knowledge filter. According to the technical scheme provided by the invention, the problem of low outlier detection precision caused by lack of priori knowledge utilization in the prior art can be solved, and compared with the prior art, the outlier detection precision can be remarkably improved.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI