1470results about How to "Fast test" patented technology

A welding visual detection method based on a convolutional neural network includes the following steps that firstly, at the training stage, a training sample is input into the convolutional neural network, and the connection weight and offset value of the convolutional neural network are obtained; secondly, at the testing state, a welding picture is read in and preprocessed with the digital picture processing technology, and a region of interest is extracted and then subjected to picture size normalization processing to serve as input of the convolutional neural network. The invention further provides a welding visual detection device based on the convolutional neural network. The welding visual detection device based on the convolutional neural network comprises a crawling mechanism, a power transmission mechanism, visual detection equipment and a weld defect detection and analysis system. By means of the welding visual detection method and device based on the convolutional neural network, the automaton and intelligence level is improved, the detection precision is effectively improved, and the detection speed is effectively increased.

The invention relates to a device and a method for testing the LED light source intensity space distribution characteristic. The device comprises a base, a testing sample seat, a light intensity detecting unit, a detector bracket, a testing circuit, a computer and testing software. A multi-path synchronous testing method of a plurality of light intensity detecting units is adopted to replace one light intensity detector to sequentially test a plurality of points so as to realize the quick testing of the LED light source intensity space distribution characteristic. Compared with a conventional light distribution curve measuring method adopting one light intensity detector, if N light intensity detectors are used, the testing speed can be improved by more than N times. The device has the advantages of high testing speed and precision, abundant information content and real time and visualization.

The method for genome analysis translates the clinical findings in the patient into a comprehensive test order for genes that can be causative of the patient's illness, delimits analysis of variants identified in the patient's genome to those that are “on target” for the patient's illness, and provides clinical annotation of the likely causative variants for inclusion in a variant warehouse that is updated as a result of each sample that is analyzed and that, in turn, provides a source of additional annotation for variants. The method uses a genome sequence having the steps of entering at least one clinical feature of a patient by an end-user, assigning a weighted value to the term based on the probability of the presence of the term, mapping the term to at least one disease by accessing a knowledge base containing a plurality of data sets, wherein the data sets are made up of associations between (i) clinical features and diseases, (ii) diseases and genes, (iii) genes and genetic variants, and (iv) diseases and gene variants, assigning a truth value to each of the mapped terms based on the associated data sets and the weighted value, to provide a list of results of possible diagnoses prioritized based on the truth values, with continuous adjustment of the weightings of associations in the knowledge base based on updating of each discovered diagnosis and attendant clinical features, genes and gene variants. This method can be performed in fifty hours or twenty-four hours or less.

The invention discloses a Web testing method comprising: calling a test case to be executed; sending inquiring data to a Web server according to the test case; analyzing the received response data of the Web server to generate final testing results. The invention further provides a Web testing device which utilizes an extensible Markup Language (XML) to allocate the test case of Web, and executes the testing operation to the Web page by analyzing the test case and realizes the test which can arrange pressure by combining simultaneous multi-threading. The test case of the invention is arranged easily, and has high testing speed, and can imitate high-pressure test and has better adaptability to the testing environment.

The invention discloses a panoramic image CNN based tunnel disease automatic identification device. According to the device, firstly, a panoramic image of a tunnel inner wall is quickly acquired with a panoramic vision sensor; then the panoramic image is processed mainly by panorama unrolling, image preprocessing, binarization processing and the like to extract suspected disease region; and finally, the disease is subjected to automatic detection and classification identification by adopting a convolutional neural network. According to the scheme, the structure of the detection device in extracting a tunnel inner wall panoramic image is greatly simplified, and various tunnel disease characteristics can be automatically extracted, detected and identified by the end-to-end convolutional neural network, and an effective technical support is provided to tunnel maintenance and completion acceptance.

The invention discloses a face detection method based on a convolutional neural network. The face detection method comprises a training stage and a testing stage, wherein the training stage comprises the following steps: inputting a training sample into the convolutional neural network, and obtaining a connection weight and an offset value of the convolutional neural network. The testing stage comprises the following steps: reading a video image; when a moving object is detected, extracting an interested area, moving for one pixel each time by utilizing a block with a n*n pixel size, and carrying out partitioning processing to the interested area to obtain a plurality of pictures; zooming the partitioned pictures to a size which is the same with the size of the training sample; and inputting the pictures into the convolutional neural network which finishes training for classification, wherein n is greater than or equal to 50 and less than or equal to 70. The convolutional neural network is used as a classifier, so that detection precision and speed can be improved.

The invention discloses a traffic sign classification method based on a deep neural network. The traffic sign classification method comprises the following steps: A, detecting a read-in video based on a moving object detection method of a light stream method, and when a moving object is detected, extracting a region of interest; B, utilizing blocks with fixed sizes to carry out blocked processing on the extracted region of interest; C, carrying out zooming processing on pictures after the blocked processing, and converting into pictures with the same size; D, inputting the converted pictures, and utilizing a convolutional neural network for classification. According to the method, the region of interest is extracted for the pictures after motion detection and then the blocked processing is carried out, and after the obtained pictures are converted into the pictures with the same size, processing is carried out by utilizing the convolutional neural network, so that the problems caused by an artificially assumed class conditional density function are avoided, the testing speed is greatly quickened, and the precision is greatly improved. The traffic sign classification method based on the deep neural network disclosed by the invention can be widely applied to the traffic field.

The invention discloses a method and a device for regression testing of Web application programs. The method includes acquiring webpage addresses corresponding to various functions in a first Web application program and a second Web application programs; using the acquired webpage addresses in the same testing environment and requesting for the first Web application program and the second Web application; and comparing a first result object fed back by the first Web application program responding to the request with a second result object fed back by the second Web application program responding to the request, and obtaining comparison results; wherein the first Web application program and the second Web application program are different versions of the same Web application program. By the method and the device for regression testing of the Web application programs, the problem of high testing burden in the prior art is solved, the finding number of potential errors in the application programs is obviously superior to that of the prior art, testing load is reduced and testing speed is increased.

The invention belongs to the technical field of image processing, and specifically discloses a block-based shielded face recognition algorithm. The algorithm comprises the following steps of: in an offline training stage, carrying out preprocessing operations such as face detection, geometric face normalization, illumination normalization, extracting four blocks such as a left eye, a right eye, anose and a mouth from a face image on the basis of the preprocessing result, training a network model of each block, extracting corresponding features, training a shielding judgement network of each block to obtain a shielding judgement result, finally fusing the features according to the shielding judgement result of each block, and constructing a K-D tree feature index; and in an online recognition stage, extracting face image features by adoption of a method same as the offline training stage, and carrying out feature query through a K-D tree index manner so as to obtain a recognition result. Experiment results prove that the algorithm has better correctness.

The invention discloses a device for measuring the sample thermo-physical property in situ, comprising a reaction kettle internally provided with a tested sample, a gas supply system for providing a gas source for the reaction kettle, a temperature control system for maintaining the reaction temperature in the reaction kettle, a hydraulic driving system connected with the reaction kettle and a measurement and control acquisition system connected with the reaction kettle and used for testing the thermo-physical property of the sample, wherein a background material of which the thermal conductivity is less than that of the tested sample is arranged at the bottom inside a barrel of the reaction kettle, and the measurement and control acquisition system comprises a thermo-physical test probe which is inserted between the tested sample and the background material. By adopting a single-side test structure of the thermo-physical test probe, the thermo-physical property test to different samples can be carried out, and the test speed is fast; the thermo-physical property parameters of the sample under different temperatures and pressures can be measured as the temperature and the pressure are respectively regulated; the reaction extent test is carried out according to the change of the thermo-physical property parameters during the chemical reaction; and the system has definite functions of all parts, favorable upgradability and expandability as well as wide adaptability.

The invention discloses an active reflection coefficient test system and method of a phased array antenna. The test system comprises a vector network analyzer, a multichannel amplitude phase control auxiliary unit, a signal extraction auxiliary unit, a master control computer, a calibration member and an amplitude-stabilizing phase-stabilizing cable, wherein the vector network analyzer is configured to generate test excitation signals and receive reference, reflection and monitoring signals; the multichannel amplitude phase control auxiliary unit is configured to convert one path of excitation signals into M paths, control the amplitudes and phases of the M paths of signals independently, and output M paths of amplitude and phase controllable excitation signals; and the signal extraction auxiliary unit is configured to realize straight-through output of the M paths of amplitude and phase controllable excitation signals, carry out reference coupling, monitoring coupling and reflection coupling extraction on the M paths of amplitude and phase controllable excitation signals, and implement switching control and selective output. The test system can directly test the active reflection coefficient of the antenna unit needless of calculation, the test process is concise, manual operation is less, and the test result is highly correct.

The invention relates to a ship intelligent control system test platform with virtual and real fusion. The ship intelligent control system test platform with virtual and real fusion comprises a real navigation database, a real-time simulation system for generating a numerical twinning fused traffic scene according to data in the real navigation database, a ship simulation system for simulating a ship in the test scene, and a tested intelligent control system for controlling and simulating the ship according to the data provided by the ship simulation system. The experimental environment constructed by the ship intelligent control system test platform with virtual and real fusion disclosed by the invention comes from real data collection, which ensures the validity of the test; and the based object experimental ship and experimental process are still based on numerical simulation, which reduces the risk and cost of the test; that is, the experimental object ship is based on numerical simulation, and the experimental scene completely comes from the perception fusion of the real world.

The invention discloses a fluid system of a flow cytometer and a flow cytometric detection method. The fluid system comprises a sampling needle, a sampling needle cleaning device, a flowing chamber, a reaction tank, a hemolytic agent syringe, a sample syringe, a diluent syringe, a diluent bottle, a hemolytic agent bottle and a motor, wherein the sample syringe is respectively communicated with the sampling needle, the reaction tank, the flowing chamber, the sampling needle cleaning device and the diluent syringe, the diluent syringe is respectively communicated with the diluent bottle, the flowing chamber and the reaction tank, the hemolytic agent syringe is respectively communicated with the hemolytic agent bottle and the reaction tank, and the hemolytic agent syringe, the sample syringe and the diluent syringe are all driven and controlled by the motor. According to the invention, driving motors for a plurality of syringes are integrated into one, arrangement of the syringes satisfies moment balance, integral rigidity and inertia are improved, gap instability of the driving motor can be buffered, a more stationary sample flow can be obtained, and thus, detection precision of the flow cytometer is improved.

The invention provides a stress measuring device with higher precision, which can measure the size, direction and distribution of the stress of optical glass. The stress measuring device of the optical glass comprises a communicated light path interferometer and a stander, wherein the stander comprises a frame and a plane scanning test platform arranged on the frame; and a laser receiving unit and a laser emitting unit of the communicated light path interferometer are arranged on the stander, and can synchronously move front and back, and up and down. The stress measuring device achieves the quantitive measurement of the stress size and the stress uniformity of the optical glass; in addition, the precision is greatly improved, the resolution reaches 0.01nm, and the size of the measurable optical glass is greatly widened. The stress measuring device can better measure the stress optical coefficient of the optical glass; and compared with the other polarized stress meter measuring devices with weight application, the measuring precisions of the pressure and the stress of load are obviously improved, and the measuring precision of the stress optical coefficient can reach 0.03*10<-12> / Pa.

An ophthalmic lens design and modeling system comprises a user interface providing functionality for generating a template associated with a desired lens design to be manufactured, the template comprising design information sufficient for generating three-dimensional (3D) models of lens, and 3D models of associated components required for lens manufacture in an ophthalmic lens manufacturing system. The system further includes functionality for generating and / or specifying linking information, via the user interface, that governs the physical behavior of lens design features included in said template in accordance with one or more process parameters affecting lens manufacture and manufacture of associated components in an ophthalmic lens manufacturing system. The use of the template and design and linking information therein thus facilitates rapid lens modeling and lens manufacturing operations with greater accuracy, thereby reducing lens design build and test (DBT) cycle time.

The invention discloses a microwave scattering property test system based on a vector network analyzer. The microwave scattering property test system comprises the vector network analyzer, an antenna and a main control computer, wherein the vector network analyzer is used for generating a pulse radio frequency signal of a designated parameter under the control of the main control computer; the pulse radio frequency signal is transmitted by the antenna; and the vector network analyzer is also used for carrying out strobe treatment on a target echo signal received by the antenna to obtain microwave scattering property data within a designated area range. The vector network analyzer can be used for generating a narrowband pulse radio frequency signal with the frequency range covering wavebands of L, S, C, X, Ku and Ka; and the position of a strobe gate of a receiver is set by adopting a mode of fixed point test in pulse according to a test object. The microwave scattering property test system disclosed by the invention is convenient for field work and stable in performance and can be used for scattering property test of the ground background and a large-area camouflage net or the target scattering property test.

Plural crRNA for detecting RSPO2 gene in body fluid with CRISPR-Cas13a specificity and applications thereof are disclosed. The crRNA is able to construct the CRISPR-Cas13a system and specifically detect micro-RSPO2 gene in the body fluid. The present invention is non-invasive and able to test rapidly, frequently and repeatedly. Compared to the conventional liquid biopsy, the present invention detects the micro-RSPO2 in the body fluid through the fluorescence units. The present invention has the advantages of no need for high-throughput sequencing, low cost and rapid testing speed, which is able to be adopted by large scale clinical applications.

The invention relates to automatic test control system and method in the production of a POS machine, which belongs to the technical field of computer tests, reduces the human misjudgment rate of a function test, enhances the test speed and ensures the test quality. The automatic test control system in the production of the POS machine comprises a tooling test jig, an automatic test control circuit and corresponding control software, wherein the tooling test jig is provided with an automatic test control circuit board and a device elastically connected with a tested single board; and the tooling test jig is also provided with a device used for controlling the electrification of the tested single board and the automatic test control circuit so as to supply electricity for the tested single board and the automatic test control circuit. The invention also provides the automatic test method in the production of the POS machine. The invention is mainly suitable for the function test in the production of the POS machine.

The invention discloses time sequence control method and system for a chemiluminescence immunoassay device. The system includes an input pipe module, a detection module, a sample module, a reagent module, a reaction plate module, a transfer pipe module, a cleaning disk module, and a liquid path control module. The control method includes flow line control to the units in the device according to time stamps and timing triggering, wherein a time sequence control part includes several key threads, which are completed in parallel in different zones simultaneously. In the method, actions of the device within 16 sec are defined as a time sequence period T, each 0.5 s defined as a timer t. The method, via reasonable hardware system arrangement in the CLIA device and systemic and complete time sequence control method design on the hardware layer, functional demands such as parallel control, seamless connection and abnormity treatment among different executing mechanisms in a bottom layer are achieved. The method achieves accurate control in a uniform period according to optimum time sequence flow, thus increasing test speed.

The invention discloses a software test system. The system collects access records of users having access to a first server through a log transmitting and receiving server and sends the access records to a log processing server, wherein target software runs on the first server; the log processing server generates a log message list according to the received access records and generates a test case according to the log message list, wherein the test case corresponds to the access record in the log message list; the test server sends a first test request and a second test request to a second server and a third server respectively according to the obtained test case, makes response to a first test result received from the second server and a second test result received from the third server, compares the first test result and the second test result and generates a test report, wherein the same target software runs on the first server and the second server, and a modified version of the target software runs on the third server. The invention further discloses a corresponding software test method.

The invention relates to an EIS rapid measuring method of a lithium-ion battery, and provides an EIS rapid measuring method based on square wave current excitation and Fourier transform. The method includes: selecting a square wave excitation frequency based on an electrochemical reaction characteristic of the lithium-ion battery, determining that the lithium-ion battery is in an appropriate polarized voltage amplitude range, and selecting a sinusoidal alternating current amplitude according to the range; applying a square wave current of a selected frequency point and with a specific amplitude to the lithium-ion battery, performing Fourier transform on the square wave current and a response voltage obtained by sampling, and obtaining the impedance of a specific frequency point; and screening the impedance with a specific frequency based on a frequency spectrum amplitude of Fourier decomposition of the response voltage and an impedance change rule to form the electrochemical impedance spectroscopy of the lithium-ion battery, namely EIS. According to the EIS rapid measuring method, the electrode reaction characteristic of the lithium-ion battery can be accurately described, the EIS of the lithium-ion battery is accurately obtained, the EIS test speed of the lithium-ion battery is fast, the test time is short, and the project is easy to realize.

The invention relates to an automatic wafer testing machine used for fixing and testing a chip located on a wafer. The automatic wafer testing machine comprises a machine, an angle adjustment mechanism, a wafer test positioning device, a test component and a controller. The machine is provided with a test station. The angle adjustment mechanism comprises a rotation component and a translation component. The wafer test positioning device is installed on the surface of the angle adjustment mechanism, wherein the surface faces away from an installation surface. The angle adjustment mechanism candrive the wafer test positioning device to rotate or translate so as to drive the chip to move to the test station. The test component is used for carrying out performance detection on the chip located at the test station. The controller, the angle adjustment mechanism and the test component are connected in a communication connection mode. The controller is used for sending trigger signals to theangle adjustment mechanism and the test component respectively so as to trigger the angle adjustment mechanism and the test component. The automatic wafer testing machine has characteristics that a test speed is fast and test efficiency is high.

The invention relates to a field crop phenotypic information high-pass peer monitoring device. An electric mobile trolley (4) carrying a sensor / camera / measurer moves on a test area (3) for testing, and test data is processed and analyzed. The invention further relates to a monitoring method for the field crop phenotypic information high-pass peer monitoring device. Phenotypic information of field crops can be quickly acquired, and tested crops do not need to be moved during testing, so that the natural growth state of the crops is kept, and the influence on the crops in the test process is greatly reduced. Thus, on the one hand, the designed field crop phenotypic information high-pass peer monitoring device can remarkably promote molecular breeding of crops and development of plant functional genomics; and on the other hand, the device can guide people to optimize field management measures and crop planting structures.

The invention particularly relates to a double-channel optical performance testing device of an integrated waveguide modulator and a polarization crosstalk identification and processing method thereof and belongs to the technical field of measurement of optical devices. The double-channel optical performance testing device of the integrated waveguide modulator comprises a high-polarization stability wide spectrum light source, an integrated waveguide modulator to be detected, an optical distance demodulating device and a polarization crosstalk detecting and recording device. According to the device, the system structure is simplified and the testing function is enriched; the cost is reduced and the testing efficiency is improved; the double-channel optical performance testing device can be widely applied to a quantitative test of the optical performance of integrated waveguide devices with an extinction ratio greater than 80dB.

The invention relates to a test system which is used for testing a semiconductor laser chip. The test system comprises a loading and unloading device, a probe assembly and an integrating sphere assembly; wherein the loading and unloading device comprises a plurality of stations for placing a to-be-tested chip; the probe assembly comprises a plurality of probes arranged above the to-be-tested chip;and the integrating sphere assembly comprises an integrating sphere with an opening which is close to the to-be-tested chip. When the current flows through the pin of the to-be-tested chip through the probes, the opening receives an optical signal sent by the to-be-tested chip. The probe assembly and the integrating sphere assembly are respectively arranged to be capable of moving in the verticaldirection and the horizontal direction, so that the detection element is protected, and the service life is prolonged. The test speed is further improved through orderly movement.

The invention provides an automatic test platform and a test method for a blade type server. The test platform comprises a plurality of types of test equipments, a monitoring computer, a controller, aclient and a computer product under test. The devices are connected with each other through local area network. The corresponding tested modules of the tested computer products are respectively connected with the corresponding interfaces of the corresponding test equipments of various types; The controller controls the testing process of all computer products under test, and executes test flow instructions edited by the user, The instructions arrive at the monitoring computer through the network, the corresponding test equipment is parsed and controlled, the corresponding test items are executed, the instruction information is recorded in the database, the test data fed back by the test equipment is forwarded to the monitoring computer through the network, the monitoring source code is parsed by loading different parsing files, and the test data is stored; users use clients to log on to query the corresponding working status and test information status, and carry out query, return visits and analysis on the data as required.

The invention relates to an intelligent testing system for a motor controller of an electric vehicle. The system comprises a low-voltage program-controlled power supply, a high-voltage program-controlled power supply, an oscilloscope, a probe, a rotary transformer, a servo motor system, a temperature sensor simulation device, a motor controller test bench, a test motor and a personal computer (PC) machine. The testing system and a testing method have the advantages of reduction in human testing interference factors, high testing accuracy, high testing speed and high efficiency, are simple in operation, and meet the requirement for batch production of motor controllers.

The invention discloses a full-automatic coagulate blood analytical instrument and a using method thereof. The instrument comprises a sample position module, a reagent position module, an incubation detection module, a gripper module, a cupping module, a needle movement module, a light source module, a pump station module, a consumable module, a power source module and a cuboid-shaped frame body composed of six faces of a front face, back face, left side face, right side face, top face and bottom face, wherein the center in the frame body is provided with a main cavity, the sample position module, the reagent position module, the incubation detection module, the gripper module and the needle movement module are all located in the main cavity, the left side face of the frame body is provided with a left side cavity, the pump station module is located in the left side cavity, the right side face of the frame body is provided with a right side cavity, the consumable module and the light source module are located in the right cavity, the cupping module is located in the right side cavity and penetrates into the main cavity, the back face of the frame body is provided with a back cavity, the power source module is located in the back cavity, and through the synergy of the modules, the full-automatic coagulation analysis is achieved.

The invention is concerned with the fixing equipment for testing sample, which is used for test semiconductor chip, it includes: the fixing part, the compacted part and the base; the fixing part sets on the base that is with the fixing wall plumbing with the base, the compacted part consists of the active wall that plumbs with the base; forms the space between the fixing wall, the active wall ad the base that is used for fixing the testing sample. The invention is: improving the SEM imaging quality because the sample fixes on the fixing equipment and will not appearing vibrate during the scanning; improving the productivity and testing speed because the width of the sample is adjustable, which provides a multiple production.