33results about How to "Realize automatic interpretation" patented technology

The invention aims to provide a method and device for automatic interpretation of remote sensing images. The method includes the steps of acquiring the land information in a remote sensing image, acquiring the grid image data corresponding to the land information, extracting image features in the grid image data, and finally determining the earth surface type corresponding to the land informationaccording to the image features. Compared with the prior art, the method realizes automatic interpretation of remote sensing images, the calculation amount is reduced, and the interpretation accuracyis improved.

The invention discloses an underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion, and the method comprises the steps: collecting and obtaining comprehensive pipe gallery monitoring related data in real time, wherein the monitoring related data comprises structural data and unstructural data; preprocessing the monitoring related data; carrying out feature value extraction on the preprocessed structural data; taking the preprocessed unstructured data as the input of a pre-constructed first deep learning neural network, and taking the extracted structured data feature value and the output of the first deep learning neural network as the input of a pre-constructed second deep learning neural network; determining whether the comprehensive pipe gallery is abnormal or not according to the output of the second deep learning neural network; and outputting abnormal judgment result information in real time. According to the invention, fusion processing and anomaly analysis and identification of images, videos, operation states and other related service data of power cabin channel section monitoring can be realized.

The invention discloses a device for detecting the one-way reliability of a carrier rocket two-out-of-three ignition circuit. The device comprises a testing microcomputer, an instruction simulator and a timing sequence receiving unit, wherein the testing microcomputer is connected with the instruction simulator and the timing sequence receiving unit. The instruction simulator is used for sending a simulated ignition instruction to an ignition PLC. The timing sequence receiving unit is used for receiving a PLC timing sequence signal output by a three-way ignition PLC and an ignition timing sequence signal output by a contactor circuit. The testing microcomputer is used for controlling work of the instruction simulator and work of the ignition PLC, and further used for reading the PLC timing sequence signal and the ignition timing sequence signal from the timing sequence receiving unit and judging whether the timing sequence requirement is met according to a preset judgment method. The device for detecting the one-way reliability of the carrier rocket two-out-of-three ignition circuit has the advantages that the one-way reliability of the two-out-of-three ignition circuit is examined, the timing sequence of the ignition circuit is automatically interpreted, and the use reliability of the two-out-of-three ignition circuit is improved.

The invention relates to a polyhedral probe for in situ nondestructive testing of nucleic acid molecules in extracellular vesicles and a preparation method and application thereof. The polyhedral probe comprises a nucleic acid polyhedral skeleton and a probe structure which is used for identifying a target gene and located at a vertex angle of a polyhedron, the probe structure is modified with a quenching group, and the nucleic acid polyhedral skeleton is modified with a luminescent group. The probe can rapidly, sensitively and specifically detect a plurality of nucleic acid molecules in the extracellular vesicles, and can perform design application on the specific target nucleic acid molecules according to the clinical or research detection needs.

The invention relates to an aviation big data intelligent analysis method based on remote embedded data collection. According to the method, aviation big data is utilized to analyze and monitor the health condition of an aircraft and carry out fault diagnosis. Through the method, on the one hand, integration of multiple monitoring means such as onboard videos, audio, a warning system and a flightparameter system is realized, and a system can record and store more flight data; and on the other hand, aviation big data application software is embedded into an airborne computer system to realizereal-time monitoring of the aircraft, meanwhile, the application software is continuously upgraded according to the latest research achievement, and the data stored in the system also can be subjectedto trend analysis on the ground in combination with historical data and can be utilized again in teaching and scientific research work.

The invention provides a model training and data analysis method, device and equipmen for time series data and a storage medium. The method comprises the steps of constructing a training sample, the training sample comprising one or more pieces of time series data, different pieces of time series data corresponding to different feature dimensions, and each piece of time series data comprising a plurality of pieces of data arranged according to a time sequence; and training a time series data analysis model by using the one or more training samples, wherein the time series data analysis model is used for analyzing the category to which the sample comprising the one or more time series data belongs. Therefore, the automatic interpretation of the time sequence data can be realized by using the trained model.

The invention provides a pavement crack disease detection method. The method comprises the following steps: laser generators emitting laser beams to lanes to form a series-connected bending marking line on the to-be-detected pavement; an image acquisition device, based on a preset collection period, acquiring a series-connected bending marking line image to obtain marking line images; carrying out high-pass filtering on the marking line images to obtain pulse elevation numerical images of the pavement crack disease; and processing the pulse elevation numerical images to obtain a result of the pavement crack disease. According to the pavement crack disease detection method, automatic and intelligent treatment of the pavement disease is realized, the problem that pseudo-cracks generated by water traces and oil traces, existing in an image photography method generally adopted at home and abroad, is solved, so that the automatic interpretation of complex grey-scale patterns is realized, relevant information of the pavement disease is directly obtained through processing, manual interpretation is not needed, and safety is guaranteed.

The invention relates to the technical field of aero-engine blade detection, and particularly discloses an aero-engine blade intake and exhaust edge shape detection method, which comprises the steps of obtaining blade profile contour theoretical point cloud data, blade profile contour actual measurement point cloud data and a deviation value of a blade; performing curve fitting according to the theoretical point cloud data of the blade profile to obtain a theoretical blade profile curve and a theoretical blade profile mean camber line, and performing curve fitting according to the actually measured point cloud data of the blade profile to obtain an actually measured blade profile curve and an actually measured blade profile mean camber line; performing calculating according to the theoretical blade profile curve and the theoretical mean camber line to obtain a front edge theoretical vertex and a rear edge theoretical vertex; performing calculating according to the actually measured blade profile curve and the actually measured mean camber line to obtain a front edge actually measured vertex and a rear edge actually measured vertex; calculating a front edge actual measurement vertex curvature radius and a rear edge actual measurement vertex curvature radius; and comparing and judging the front edge shape and the rear edge shape of the blade. According to the aero-engine blade intake and exhaust edge shape detection method provided by the invention, the defect detection efficiency of the blade is improved.

The invention provides a method for detecting pavement crack diseases. The method includes steps of emitting laser light beams towards lanes by a laser generator and forming series bent marked lines on to-be-detected pavements; acquiring the series bent marked lines by a laser marked line image acquisition device under the control of image acquisition control signals on the basis of preset acquisition cycles to obtain light spot images and carrying out low-pass filter processing on the light spot images by an information processing system to obtain low-pass filtered continuous cross-section numerical images; carrying out full-spectrum fidelity processing on the light spot images obtained by the information processing system to obtain full-spectrum cross-section numerical images; carrying out difference on the full-spectrum cross-section numerical images obtained by means of full-spectrum fidelity processing and the low-pass filtered continuous cross-section numerical images obtained by means of low-pass filter processing to obtain pulse elevation numerical images of the pavement crack diseases. Filter parameters for low-pass filter are related to light spots formed by the series bent marked lines. Filter parameters for the full-spectrum fidelity processing are related to the light spots formed by the series bent marked lines. The method has the advantage that the work efficiency can be improved.

The invention provides a super-pixel-based remote sensing image semantic segmentation method under a known sample imbalance condition, and the method comprises the steps: firstly carrying out the over-segmentation preprocessing of image data, obtaining a super-pixel segmentation result, cutting a rectangular image through employing the gravity center of each super-pixel as a central point, and constructing a super-pixel rectangular image data set; training an ensemble classification model, under the condition that the known samples are unbalanced, combining the small samples into one class, carrying out primary classification, carrying out secondary classification on the small samples after the primary classification is completed, and integrating the network models of the two classifications to obtain the ensemble classification model; inputting a to-be-predicted super-pixel rectangular image data set into the integrated classification network model to obtain a super-pixel rectangularimage category; and mapping the category of the super-pixel rectangular image to the original image to obtain a semantic segmentation result. According to the method, the semantic segmentation precision of the small sample under the condition that the known sample is unbalanced can be effectively improved finally.

The invention relates to an aviation big data intelligent analysis system based on remote embedded data collection. Aviation big data is utilized to analyze and monitor the health condition of an aircraft and carry out fault diagnosis. Through the system, on the one hand, integration of multiple monitoring means, such as onboard videos and audio, an alarm system and a flight parameter system, is realized, and the system can record and store more flight data; and on the other hand, aviation big data application software is embedded into an airborne computer system to realize real-time monitoring of the aircraft, meanwhile, the application software is continuously upgraded according to the latest research achievement, and the data stored in the system can be subjected to trend analysis in combination with historical data on the ground and also can be utilized again in teaching and scientific research work.

The invention relates to an automatic zero adjustment device for an electric steering engine. The automatic zero adjustment device comprises a controller, a proximity switch, a proximity switch support and an extension clamping device; the controller is respectively connected with the proximity switch and the electric steering engine; the extension clamping device comprises a base and a lengthenedrod body, the base is clamped on an output shaft of the electric steering engine, and the lengthened rod body is fixedly connected with the base; when the output shaft of the electric steering enginerotates and drives the base to rotate and the lengthened rod body reaches a triggering range of the proximity switch, output level of the proximity switch turns over, the controller controls the output shaft of the electric steering engine to stop rotating, and mechanical zero adjustment is completed; and the controller is used for acquiring an output voltage value of a sensor, rotating the sensor and stopping rotation of the sensor when an alarm gives an alarm, thus electrical zero adjustment is completed. By using the proximity switch, the extension clamping device, the controller and the alarm, automatic mechanical zero adjustment of the electric steering engine as well as automatic interpretation and hint when a zero position of the sensor is adjusted into position are realized, and efficient and precise zero adjustment of the electric steering engine is improved.

The invention relates to an embedded control surface gap and skewness automatic detection method and equipment, an upper computer controls an electric cylinder to apply continuous loading force to a control surface through an RS232 serial port, an embedded controller acquires a force sensor and a gap displacement sensor in real time, and the force sensor and the gap displacement sensor are sent to the upper computer through an RS422 serial port after low-pass filtering. A force-displacement curve is drawn in real time after analysis of an upper computer, a control surface gap value is calculated, the upper computer sends a control surface deflection control instruction to an onboard maintenance assembly through an RS422 serial port and drives a control surface to deflect, and an embedded controller collects skewness displacement sensor signals in real time and sends the skewness displacement sensor signals to the upper computer through the RS422 serial port. The control surface skewness value is analyzed and calculated by the upper computer, and the motor power supply supplies power to the electric cylinder. According to the method, equipment self-detection, automatic test, automatic test data acquisition and interpretation and high control surface skewness displacement measurement precision of control surface gap displacement measurement are realized, and the reliability, maintainability and safety are good.

The invention provides a test data interpretation method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining an association relationship description file and a test data set of a carrier rocket; determining test data corresponding to each incidence relation from the test data set based on each incidence relation in the incidence relation description file; and based on each association relationship, interpreting the test data corresponding to each association relationship, and determining an interpretation result of the test data corresponding to each association relationship. According to the method, the device, the electronic equipment and the storage medium provided by the invention, automatic interpretation of the test data of the carrier rocket is realized, the interpretation efficiency of the test data of the carrier rocket is improved, and the interpretation accuracy of the test data of the carrier rocket is improved.

The invention discloses a device for measuring the relative aperture of a photographic objective. The device comprises an optical bench, a collimator, a diffusion screen, a holder, a camera assembly,a displacement table and a computer. The collimator is arranged on the optical bench, and the diffusion screen, a to-be-measured objective lens and the camera assembly are sequentially located in theoptical axis direction of the collimator; the diffusion screen is arranged on the optical bench through a fixing frame; a to-be-measured photographic objective lens is arranged on the clamp holder andis arranged on the optical bench through the clamp holder; and the camera shooting assembly is arranged on the displacement table, is arranged on the optical bench through the displacement table, andis connected with the computer. The invention further discloses a measuring method by using the photographic objective relative aperture measuring device. The measuring method comprises the followingsteps: assembling the device; measuring a focal length; measuring the entrance pupil diameter; deriving aperture values. By means of the mode, the entrance pupil diameter and the focal length can bemeasured, two kinds of equipment do not need to be used for measurement respectively, measurement steps are simplified, and the measurement accuracy can be improved.

The invention discloses a formalized description-based carrier rocket test data interpretation method and system. The method comprises the following steps: (1) classifying criteria of test parameters;(2) defining composition elements of a test parameter criterion; (3) according to the defined composition elements, carrying out formalized description on the classified criteria; (4) reading formalized description of the criterion, and converting an interpretation rule represented by the formalized description into a target program code which can be identified by a computer; And (5) operating the target program code by taking the carrier rocket test data as a data source, and giving an interpretation conclusion about whether the carrier rocket test data is normal or not, thereby completing interpretation of the carrier rocket test data. Through the formalized description method, the problem that the criteria of the test data of the carrier rocket are difficult to accurately describe anddefine is solved, automatic test data interpretation is realized on the basis, and the test data interpretation efficiency and accuracy are greatly improved.