110results about How to "Realize accurate judgment" patented technology

The invention relates to a Fourier descriptor and gait energy image fusion feature-based gait identification method. The method comprises the steps of performing graying preprocessing on a single frame of image, updating a background in real time by using a Gaussian mixture model, and obtaining a foreground through a background subtraction method; performing binarization and morphological processing on each frame, obtaining a minimum enclosing rectangle of a moving human body, performing normalization to a same height, and obtaining a gait cycle and key 5 frames according to cyclic variation of a height-width ratio of the minimum enclosing rectangle; extracting low-frequency parts of Fourier descriptors of the key 5 frames to serve as features I; centralizing all frames in the cycle to obtain a gait energy image, and performing dimension reduction through principal component analysis to serve as features II; and fusing the features I and II and performing identification by adopting a support vector machine. According to the method, the judgment whether a current human behavior is abnormal or not can be realized; the background is accurately modeled by using the Gaussian mixture model, and relatively good real-time property is achieved; and the used fused feature has strong representability and robustness, so that the abnormal gait identification rate can be effectively increased.

The invention discloses a numerical control machine tool cutter state monitoring and control system and control method. The control method is characterized in that abnormal vibration signals in the cutter machining process are collected in real time; state pre-judgment is carried out on an abnormal condition by using a cutter state pre-judgment model, and a time point when a cutter is abnormal isdetermined; and after the state is pre-judged and under the condition of not influencing the cutter machining continuity, cutter image acquisition is completed, so that accurate judgment on the abnormal state of the cutter is realized. The system is divided into state pre-judgment and accurate judgment of the cutter in terms of cutter state judgment, and the system occupies short equipment normaloperation time in the working process, so that the working efficiency of a machine tool is effectively improved; and the cutter state pre-judgment in the system is based on the machine learning theoryprinciple, and the accurate judgment of the cutter state is based on the image comparison and analysis processing method.

A method for detecting crude defect image of a printed circuit board based on FPGA comprises the following steps of: subjecting preprocessed template image data and the image data of the scanned printed circuit board to be detected to information extraction at the same proportion by using a field programmable gate array collection card; comparing the two image data after information extraction to obtain the difference, subjecting the difference image data and the template image data to binary morphologic operation corrosion, dividing grids, and removing fine characteristics of image data and keeping the larger characteristics; counting foreground pixels in each grid and respectively outputting data streams larger than, equal to and small than the template image data; and determining the desired characteristics and coordinates according to the output result, reducing the original coordinates of the large characteristics and determining large defect characteristics and coordinates of the printed circuit board. The invention can rapidly detect large defects of the printed circuit board in real time.

The invention discloses a transparent encryption and decryption method for a database based on a multi-level view and a trigger, which is used for encrypting and protecting data in a relational database and preventing information from being stolen illegally. Based on the view and the trigger, which are universal to the relational database, an aim of being correspondingly transparent is achieved by implementing automatic encryption and decryption of sensitive data through implementing the multi-level view and using the trigger based on a row identifier, and an application system is not needed to be modified; precise judgment on query actions to the database is implemented through the multi-level view, so that a special ciphertext and plaintext data caching strategy based on an LRU cache management mechanism is established for different types of query actions, a strategy of pre-decrypting the ciphertext data in batches is established, and efficient ciphertext query is implemented.

The invention belongs to the technical field of image processing, discloses a medical image processing method, device, equipment and system. The method comprises steps of obtaining a lesion area blockin the original medical image and a lesion contour in the lesion area block through the segmentation model, recognizing lesion grade indication information of the lesion area block through the recognition model, synthesizing the lesion grade indication information of the lesion area block and the lesion contour on the original medical image, and outputting a lesion diagnosis image. Thus, the accurate boundary of the lesion contour can be determined, the lesion position is accurately positioned, the false alarm rate of lesion recognition is reduced, and accurate judgment of lesion recognitionis achieved.

The invention discloses a natural language semantic matching method for sequence global attention and local dynamic attention. Global understanding and representation of sentence semantics are achieved through a stacked gating recurrent neural network and a self-attention mechanism; dynamic analysis of important information of the sentences is achieved through a local dynamic attention mechanism,and dynamic local representation of sentence semantics is obtained. According to the method, more comprehensive understanding of sentence semantics is achieved through global attention and local dynamic attention of the sentence sequence, then semantic interaction between two sentences is accurately modeled, finally accurate judgment of the sentence semantic matching relation is achieved, and thedefects of an existing method in the aspect of attention mechanism use are overcome.

The invention relates to the technical field of automobile braking and aims to provide an electric automobile brake pedal signal analytic method. The analytic method comprises the steps that when a signal output by a brake switch is invalid, a complete vehicle control unit judges that an automobile is in a non-braking state, meanwhile, a voltage value output by an analog quantity sensor is detected to be in a zero potential value range, the complete vehicle control unit judges that the automobile is in a zero potential state, and a received voltage signal is calibrated as a zero potential value; when the signal output by the brake switch is valid, the complete vehicle control unit judges that the automobile is in a braking state, and distributes electric braking torque values to an energy recovery system according to the voltage value output by the analog quantity sensor; and when the signal output by the brake switch is invalid, the voltage value output by the analog quantity sensor is not in the zero potential value range, the complete vehicle control unit judges that a braking system is in a failure state, and the complete vehicle is controlled to start a parking mode. By adopting the method, the energy recovery efficiency is improved, and accurate determining of output failures is achieved.

The invention relates to a method for detecting a malicious code which is applied to a client program operating on a terminal. The method comprises the steps of responding to an operation request received by the client program, and carrying out one or more steps selected from the following groups to determine whether or not there is a malicious code: detecting whether or not a system application file of an operation system starting the terminal is legal; detecting whether or not there is an illegal program package name in an installation package manager provided by the operation system; detecting whether or not there is a file name in a preset blacklist in a file loaded in a process space of the operation system; transversing a key application program interface API in a current running process on the terminal, and detecting whether or not method type identification of the key API is legal.

The invention provides a method for predicting the technical condition of a bridge, which mainly comprises the following steps: (1) obtaining the distribution law of the technical condition of the bridge through on-site investigation, data collection and data analysis; 2) according to that distribution rule, finding the correspond bridge, determining the influencing factors of the bridge technicalcondition and calculating and generating the eigenvector of the prediction model; (3) according to the influencing factors and influence degree parameters, the construction, training and reliabilityanalysis of the bridge technical condition prediction model based on the long-term and short-term memory cycle depth network being carried out; (4) inputting the bridge data into the model establishedin the step (3) for calculation, and obtaining the prediction result of the bridge technical condition. Through the use of long-term and short-term memory depth network, the bridge technical status prediction model which can automatically revise the weight of influencing factors is constructed to solve the problem of inaccurate prediction results caused by the indeterminacy of influencing factorsand influencing degree parameters in the current bridge technical status prediction method.

The invention discloses a copper converter converting control system which comprises a slag forming end point detection unit and a copper forming end point detection unit, wherein the slag forming end point detection unit is used for online collecting characteristic spectrum emission intensity signals of PbO and PbS of the melt in a copper converter in the slag forming period; the copper forming end point detection unit is used for online collecting gas concentration signals of SO2 in flue gas in a copper converter gas duct A in the copper smelting period; a data processing unit is used for analyzing and processing the signals collected by the slag forming end point detection unit and the copper forming end point detection unit to judge whether the converting reaches the slag forming end point and the copper forming end point, and performs regulation and control to determine whether the blowing out is performed. The control system can accurately judge the slag forming end point and the copper forming end point, so that the phenomena including over-blowing, under blowing and the like can be avoided, the safety production of copper converter converting is ensured, and the efficiency of copper smelting is improved.

Using real-time mode, the invention enables reconfiguration signaling of synchronization wireless link. Based on time point when data of each frame reach corresponding process module, enabling signaling solves issue thoroughly that loss of data occurs in procedure for submitting reconfiguration of synchronization wireless link.

The invention discloses a crane telescopic boom control device and method and a crane. The device comprises a displacement sensor and a controller, wherein the displacement sensor is arranged at the tail part of a telescopic boom, and used for acquiring the current extension length of a telescopic oil cylinder and the initial length of the telescopic oil cylinder during last extension, the controller is connected with the displacement sensor and used for acquiring the current extension length of the telescopic oil cylinder and the initial length of the telescopic oil cylinder during last extension, which are sent by the displacement sensor, when the preset conditions are met, and triggering an oil cylinder electromagnetic valve for turning on the telescopic oil cylinder when a first difference between the initial length and the current extension length is greater than or equal to a first preset value, so that a rod-less cavity of the telescopic oil cylinder is pressurized, and the pressurization judgment error problem of a single-cylinder bolt type telescopic boom during an oil charging and pressurizing process in the prior art can be solved.

The invention provides a wireless local area network (WLAN) access method and a multi-mode terminal. The method comprises the following steps that A. The multi-mode terminal acquires cellular network coverage information and WLAN coverage information from a service desk and associates the acquired cellular network coverage information and the WLAN coverage information; B. The multi-mode terminal determines whether a current position is covered by a cellular-network indoor station; if the current position is covered by the cellular-network indoor station, a step C is executed; C. The multi-mode terminal determines whether the current position is in a WLAN effective coverage scope according to an association relation of the cellular network coverage information and the WLAN coverage information; if the current position is in the WLAN effective coverage scope, a step D is executed; D. A service set identification SSID and / or a MAC address of a site which is in the WLAN effective coverage information is acquired from the WLAN coverage information, a configured WLAN switch is opened and the opened WLAN switch is used to identify and access the site possessing the SSID and / or the MAC address.

The invention provides an event pre-warning and classifying method by an external safety pre-warning and positioning system of photoelectric composite cables, which comprises the following steps: obtaining event signals occurred within the range monitored by the system obtained through the continuous acquisition performed by the external safety pre-warning and positioning system of the photoelectric composite cables through high-speed data acquisition card; and performing pre-warning and classification of invasion events on the acquired event signals by using a loose coupling wavelet radial basis neural network algorithm described in the following text. The event pre-warning and classifying method by the external safety pre-warning and positioning system of the photoelectric composite cables provides a practical basis for the event occurrence position calculation and pre-warning so that the external safety pre-warning and positioning system of the photoelectric composite cables can conveniently detect the occurrence of warning events for the convenience that monitoring staffs can arrive at the occurrence positions of the events in time and perform corresponding protection and maintenance on the photoelectric composite cables; besides, the method saves the investigation time of event precaution and provides time allowance for the precautionary measures of the events.

The invention discloses a CT disconnection detection method and system based on sequence current phase comparison and a medium. The method comprises the steps: acquiring the positive sequence currents, negative sequence currents and positive sequence currents of the A phase, the B phase and the C phase of a line respectively; for any one of A, B and C phases of a line, judging whether the phase difference between the positive sequence current and the negative sequence current is within a first preset angle range and the phase difference between the negative sequence current and the zero sequence current is within a second preset angle range: if so, judging that the auxiliary criterion result of the CT disconnection state of the phase is true, otherwise, judging that the auxiliary criterionresult of the CT disconnection state of the phase is false; or performing OR operation on the auxiliary criterion result of the CT disconnection state of each phase to obtain an auxiliary criterion result of line CT disconnection, and if the auxiliary criterion result is true, indicating that CT disconnection occurs in the line. According to the invention, CT disconnection can be accurately judged, the judgment is accurate, the anti-interference performance is strong, and the action criterion of the CT disconnection criterion is more strict and more reliable.

The invention, which belongs to the field of fault monitoring of a wind turbine generator system, relates to a fault recording method and recorder of a wind variable-pitch system. The recording methodcomprises: collecting operation data of a wind variable-pitch system and caching wind variable-pitch system data within latest T0 time; monitoring a wind variable-pitch system safety chain signal anddetermining whether the wind variable-pitch system has a fault based on the signal; and if so, integrating wind variable-pitch system data within T2 after the wind variable-pitch system fault and wind variable-pitch system data within T1 time before the wind variable-pitch system fault into one fault recording record and storing the record. The sum of the T1 and T2 is equal to T0; and the T1 andthe T2 are larger than 0. According to the invention, relative less data information before and after the wind variable-pitch system fault can be recorded effectively and timely at the sudden occurrence of the fault of the variable-pitch system; the small storage space is occupied; the high-efficiency recording of the key information of the wind variable-pitch system is realized; and the technicalstaff member can inquire the fault information subsequently conveniently.

The invention discloses a method for detecting the incomplete root penetration of a butt weld of a thick-walled pipe in ferrite, and belongs to the field of ultrasonic flaw detection nondestructive testing. The method for detecting the incomplete root penetration comprises the steps that firstly, a transverse wave high-frequency angle probe is utilized for carrying out qualitative analysis on incomplete penetration reflected waves; then excess weld metal of the weld at the horizontal flaw locating position is ground and polished to be in the same horizontal plane with a base metal; finally, a high-frequency longitudinal wave normal probe is used for carrying out qualitative and quantitative analysis determination on the incomplete root penetration. According to the method, the incomplete root penetration of the butt weld of the thick-walled pipe in the ferrite is precisely judged, and meanwhile the method can be used for the incomplete root penetration of a thick plate, a pressure container and the like in the ferrite in a reference mode.

The invention provides a multi-source information fusion dairy cow behavior monitoring system and method. The method comprises the steps of performing data fusion on collected body temperature parameters, pulse parameters and exercise amount parameters to obtain body temperature data, pulse data and exercise amount data; collecting video frames in dairy cow monitoring videos, and performing normalization conversion on the collected video frames to obtain image data; on the basis of the body temperature data, the pulse data, the exercise amount data and the image data, constructing a sample data matrix; on the basis of the sample matrix, adopting a density clustering algorithm for determining whether an outlier exists or not; if the outlier exists, indicating that dairy cow is in the heat state at an outlier corresponding moment. By means of complementarity among multi-dimensional data, the problem that single data is poor in anti-jamming capability is avoided, accurate judgment of thedairy cow behavior state is achieved, and the effects of high reliability and good fault tolerance are achieved.

The invention discloses an automatic control system for copper converter converting, which comprises a slag forming end point detection unit and a copper forming end point detection unit, wherein the slag forming end point detection unit is used for online collecting characteristic spectrum emission intensity signals of PbO and PbS of the melt in the copper converter in the slag forming period; the copper forming end point detection unit is used for online collecting gas concentration signals of SO2 in flue gas in a copper converter gas duct in the copper forming period; a data processing unit is used for analyzing and processing the signals collected by the slag forming end point detection unit and the copper forming end point detection unit to judge whether converting reaches the slag forming end point and the copper forming end point, and performs regulation and control to determine whether blowing out is performed. The control system can accurately judge the slag forming end point and the copper forming end point, so that the phenomena such as over-blowing and under blowing can be avoided, the safety production of copper converter converting is ensured, and the efficiency of copper smelting is improved.

The invention discloses a device and a method for reducing a temperature error of a test adopting an electric field fingerprint method, and belongs to the technical field of non-destructive tests for pipelines. The device comprises a pipeline (1) to be tested and a reference plate, and is characterized in that a running compensation device (2) is arranged on the surface of the pipeline (1) to be tested, and the reference plate is fixed on the surface of the running compensation device (2); and a medium circulation unit and a temperature compensation unit are arranged on the running compensation device (2). The method comprises a data acquisition process of signal acquisition for capture electrodes on the pipeline (1) to be tested, and the reference plate, and a data analysis and processing process after the data acquisition, during running of the medium circulation unit and the temperature compensation unit. According to the device and the method for reducing the temperature error of the test adopting the electric field fingerprint method, influence of a temperature on the pipeline to be tested, is completely embodied through the reference plate, thus the corrosion condition of the pipeline to be tested is accurately judged through the electric field fingerprint method.

The invention discloses a composite material defect detection method and system based on infrared and ultrasonic signal fusion, and the method comprises the steps: collecting a data set containing a composite material infrared signal and an ultrasonic signal, and dividing the data set into a training data set and a verification data set; constructing a signal feature learning and fusion classification model based on deep learning, and inputting the training data set into the signal feature learning and fusion classification model for training; and inputting the verification data set into the trained signal feature learning and fusion classification model to obtain a composite material defect detection result. The method and system effectively solves the problems of great influence of human factors on defect type judgment and difficulty in defect qualitative analysis in ultrasonic detection and the problems of low defect type classification accuracy and incapability of reflecting defect positions well in infrared thermal imaging detection, and realizes objective judgment on the defect types and positions of the composite material; and the accuracy of defect type classification is improved.

The embodiment of the invention discloses a collision identification method and device, equipment and a storage medium. The method comprises the following steps that if the motion state of a moving object is detected to abruptly change according to speed information of the moving object, the abrupt changing speed, the abrupt changing acceleration and the abrupt changing time are determined, whether the moving object collides or not is determined according to the abrupt changing speed, the abrupt changing acceleration, a collision speed threshold and a collision acceleration threshold, if the collision occurs, the collision duration span is determined according to speed change information after the sudden change time, and the collision degree of the moving object is determined according tothe collision duration span. According to the method of the embodiment, by acquiring the abrupt changing speed of the moving object, whether the moving object collides or not is determined, the collision degree of the moving object is determined according to the speed change information after collision, hardware equipment for acquiring acceleration information is reduced, the requirement on hardware is reduced, accurate judgment on the collision degree is realized at the same time, and the processing efficiency of a collision accident is improved.

The present application provides an alarm method and a system for preventing life in a vehicle from being left behind, and relates to the technical field of automobile safety protection. The method comprises the following steps: judging whether to activate the alarm system according to the first measurement information from the sensor; when the alarm system is activated, judging whether to send analarm instruction or not according to the acquired information for judging whether the in-vehicle living body such as the infant completes the off-vehicle operation or not and the second measurementinformation. The present application is based on measurement information for judging whether or not a living body exists on a non-driver seat and information for judging whether or not an in-vehicle living body completes an off-vehicle operation, multi-dimensional judgment of the driver will be stranded in the living things to achieve the accurate judgment of the stranded living things, while avoiding the misjudgment of the driver caused by the troubles to improve the practicability of the alarm system left behind by the living things.

The invention discloses a touch recognition device and method based on the Doppler effect and a touch screen. The touch recognition device comprises a first receiving and sending module, a second receiving and sending module and a calculating module, and the first receiving and sending module is used for emitting a first detecting wave in the first direction and receiving a first feedback wave formed after the first detecting wave is reflected by a touch body. The second receiving and sending module is used for emitting a second detecting wave in the second direction, and receiving a second feedback wave formed after the second detecting wave is reflected by the touch body. The calculating module is used for calculating the moving speed and moving direction of the touch body at a touch point according to the first detecting wave, the first feedback wave, the second detecting wave and the second feedback wave. According to the technical scheme, one set of (two) receiving and sending devices is arranged, the moving speed and moving direction of the touch body of the touch point are solved based on the formula of the Doppler effect, and therefore the touch action of the touch body can be judged precisely.

The invention provides a three-phase alternating current voltage drop state judgment method and system. The judgment method comprises the steps that sampling voltage is converted from a three-phase stationary coordinate system to a two-phase rotating coordinate system; in the two-phase rotating coordinate system, a d-axis direct current voltage component Ud and a q-axis direct current voltage component Uq are decoupled and separated; and the d-axis direct current voltage component Ud and the q-axis direct current voltage component Uq are filtered to acquire a d-axis direct current voltage component Ud flt and a q-axis direct current voltage component Uq flt, and the d-axis direct current voltage component Ud flt and the q-axis direct current voltage component Uq flt are used to judge whether the power grid voltage drops. According to the invention, the system is rapidly controlled and protected by improving the rapidity and accuracy of the system to judge the states of voltage drop and recovery.

The invention provides an interference detection method and terminal, and relates to the technical field of communication. The method comprises the steps: determining a first interference cell of a current service cell of a terminal; obtaining the data power of a PDSCH (physical downstream shared channel) on a PRB (physical resource block) occupied by the first interference cell at the current service cell of the terminal and the pilot frequency power of a CRS (common reference signal); obtaining a first power distribution value of the first interference cell according to the data power of the PDSCH and the pilot frequency power of the CRS; determining whether the PRB has the interference from the first interference cell or not according to the first power distribution value. According to the technical scheme of the invention, the method achieves the precise judgment of the cell interference on the basis of the PRB, and improves the interference detection accuracy.

The invention discloses a method for calculating occurrence positions of pre-warning events in an external safety pre-warning and positioning system of photoelectric composite cables, which comprises the following two steps: step one, selecting a typical data field, and then calculating the occurrence positions of the events; and step two, performing a wavelet generalized mutual correlation positioning method. Through the two steps of calculations, the external safety pre-warning and positioning system of the photoelectric composite cables detects position information of the pre-warning events. The method for calculating the occurrence positions of the pre-warning events in the external safety pre-warning and positioning system of the photoelectric composite cables saves the investigationtime of event precaution and provides time allowance for the precautionary measures of the events so that correlative personnel can get to the site from nearby and the use efficiency of the personnelis improved; and the method provides a fact basis for the detection of data stealing events from the technical aspects. The implementation process of the method needs no constructions on the prior fiber network but only needs to mount a bidirectional common-path distributed fiber optic interferometer at two ends of a node of a communication optical fiber to achieve the designed functions of the system, thus the method not only is suitable for terrestrial environments but also is suitable for underwater environments, is simple to use, and has wide suitable environments.

The invention relates to an image-based defect detection method and a computer readable storage medium. The method is suitable for detecting appearance defects of an object to be detected. The image defect detection method comprises the following steps: acquiring at least one image of a to-be-detected object; extracting a plurality of target defect sub-regions from the image; judging defect typesof the plurality of target defect sub-regions by utilizing a first processing method; generating at least one target defect area from the plurality of target defect sub-areas by using a second processing method; judging a first defect level of the target defect area according to a first criterion; and storing the first defect level. According to the invention, a first processing method is used todetermine defect types of a plurality of target defect subareas extracted from an image of a to-be-detected object; and at least one target defect area is generated from the plurality of target defectsubareas by using a second processing method, and the first defect level of the target defect area is judged according to a first criterion, so as to judge the defects of the to-be-detected object.