130results about How to "Realize online real-time detection" patented technology

The invention discloses a multi-vision defect detecting equipment and a multi-vision defect detecting method for a large-size LCD glass substrate in a production line. For the equipment, a linear scanning imaging detection system is adopted for acquiring the high-definition gray image of an LCD glass substrate to be detected, and the equipment is simple in structure and convenient to operate; according to the method disclosed by the invention, the acquired image is processed, a kmeans clustering method is adopted to carry out defect existence judgment on the processed image of the LCD glass substrate, and by making the defect regions, the defect category is judged by a classification method of a support vector machine (SVM), and the defect quantity is counted. Processed image and detection results are transmitted to an office in real time by a filed bus control system for operators on duty to check, and the field production parameters are transmitted, so that remote monitoring of the system is realized.

The invention provides a method which uses transient online diagnosis coupling frequency response to position the leakage of natural gas pipeline, and relates to a natural gas pipeline failure detection and positioning method which can solve the problems that the existing method for detecting and positioning the leakage of the natural gas pipeline can not detect in real time, has long detection period, low positioning precision and high error report rate; real-time pressure value and real-time flux value are respectively collected at the upstream and downstream of the pipeline; the real-time downstream pressure value and the real-time flux value when the pipeline runs stably are reduced by the practical real-time pressure value and the practical real-time flux value at the downstream; if both of the two differences exceed the valve value, the leakage is considered to occur, otherwise the values are collected again; an excitation pressure wave is generated at the downstream end of the pipeline and the wave speed of the response wave of the excitation pressure wave is gained; according to the wave speed of the excitation pressure response wave and the time difference when the excitation pressure response wave is transmitted to the upstream and the downstream, the position of the leakage point is gained. The measurement and collection of the values are completed by normal equipments and the method can be used both in the built pipeline or pipelines under construction.

The invention relates to the technology of photovoltaic grid-connected inverter, in particular to an online detection method of insulating resistance to ground of a photovoltaic grid-connected inverter. The method comprises the following steps of: by sampling an output voltage VPV of a photovoltaic cell and enabling a switch S1 in a resistance switch circuit to be in opening or closing state, disconnecting or connecting a resistor R5 from or to an upper bridge arm, and then sampling a voltage signal of a dividing voltage output end of a lower bridge arm to obtain a voltage ratio equation of anode to ground of photovoltaic cell and cathode to ground of the photovoltaic cell, thereby online calculating a insulating resistance R+ of anode to ground of the photovoltaic cell and an insulating resistance R- of cathode to ground of the photovoltaic cell in real-time and accurately. The method has simple calculation process and high detecting precision; by adopting the method, the online and real-time detection of anode-to-ground resistance of the photovoltaic cell and the cathode-to-ground resistance of the photovoltaic cell is achieved, the photovoltaic grid-connected inverter is guaranteed to work safely and reliably.

The invention belongs to the technical field of atmospheric environment detection and spectral measurement and particularly relates to a portable multi-component gas infrared spectrum detection system. The system comprises a portable case, an infrared source, an infrared interferometer, a sample cell, a gas pump, an infrared detector, a data acquisition card, a computer and a power supply module, and the infrared source, the infrared interferometer, the sample cell, the gas pump, the infrared detector, the data acquisition card, the computer and the power supply module are mounted in the portable case. The portable multi-component gas infrared spectrum detection system which is capable of realizing online real-time detection of multi-component gas concentration can be applied to various fields of atmospheric environment detection, such as fields of emergency monitoring of emergency atmosphere accident sites, pollution source emission monitoring, atmospheric environmental monitoring of chemical industrial parks, gas detection in a catalytic conversion process and the like, and reliable equipment is provided for atmospheric environmental monitoring.

The invention discloses a D-S-evidence-theory-based distribution automation terminal state diagnosis method. The method comprises: statistics of designated state characteristic quantities is carried out from operating information uploaded to a main distribution station from a distribution automation terminal; distribution automation terminal states are graded and a fuzzy membership function, corresponding to different distribution automation terminal states, of the state characteristic quantities is constructed; various membership parameters of the fuzzy membership function are determined; with the distribution automation terminal state grading result as a single element proposition, a basic probability assignment function and an evidence fusion result are calculated for the single element proposition and an identification frame; and matching is carried out on the evidence fusion result and a preset terminal state diagnosis decision-making criterion, so that a current state of the distribution automation terminal is obtained. According to the invention, the state of the distribution automation terminal can be determined accurately based on the operating information; the detection result is accurate and reliable; the diagnosis becomes convenient and rapid; and the operability is high.

The invention relates to an X-ray on-line detection probe of a steel wire rope core conveyor belt and a signal acquisition and processing method. The X-ray on-line detection probe of the steel wire rope core conveyor belt belongs to the field of non-destructive X-ray on-line probing equipment. Hardware design of the X-ray on-line detection probe of the steel wire rope core conveyor belt is as follows: a photoelectric conversion module is used for realizing conversion from X-ray signals to electrical signals; four lines of A/D (analog/digital) modules are used for realizing sampling from analog signals to digital signals; and a signal acquisition and processing module in the structure of an ARM (advanced RICS (reduced instruction set computing) machine and an FPGA (field programmable gate array) is used for realizing the control of the A/D modules and the processing of image element data. The signal acquisition and processing method comprises the following steps: using the FPGA to adopt a state machine to realize the sampling control of the four lines of the A/D modules; adopting a three-point sectional image element non-homogenization correction algorithm based on a response model to realize homogenization processing of the image element data in the FPGA; and figuring out a coefficient of the correction algorithm through the ARM and performing median filtering processing on the image element data after completing the correction. By adopting the probe in the invention, the high-precision dynamic real-time detection of the conveyor belt can be realized, thereby facilitating diagnosis of elongation, rust, fracture and other situations of a joint of a steel rope core.

The invention discloses a method for evaluating the bonding strength of a mechanical composite tube. The method comprises the following steps: 1, selecting a standard component mechanical composite tube; 2, applying excitation onto the standard component mechanical composite tube, recording the exciting force signal, acquiring acceleration signals in a real time mode, and carrying out analytic processing to obtain the value of a modal parameter of the standard component mechanical composite tube; 3, applying same excitation onto the mechanical composite tube to be tested, and acquiring the acceleration signals of corresponding points in a real time mode, and carrying out analytic processing to obtain the value of a same modal parameter of the mechanical composite tube to be tested; and 4, comparing the two values of the modal parameter, and determining whether the bonding strength of the mechanical composite tube to be tested is qualified according to the comparison result. The method solves problems of large detection error, high cost, low efficiency and online detection unableness of destructive detection needed by present methods.

The invention discloses an automatic transmission tower scanning method based on hovering state of an aircraft. The method comprises steps of offline deep learning, online automatic scanning and online automatic high-definition imaging, wherein for offline deep learning, a transmission tower is positioned online in real time with a deep learning method, a pod is controlled through feedback of areainformation and POS information of the tower, automatic scanning of the transmission tower is realized, multistage internal features of various electric components are learned and described automatically and step-by-step abstraction is performed with a deep convolutional neural network, feature learning and classified detection are realized simultaneously, the problems that the optimal detectioneffects of feature learning and classified detection cannot be realized simultaneously with the traditional feature extraction method and the like are solved effectively, and online real-time detection of multiple targets is realized; the information feedback mechanism is introduced on the basis of multi-target recognition, load is controlled automatically, a test field of imaging equipment is adjusted, high-definition imaging of the electric components is realized, and imaging quality is improved effectively.

The invention discloses a visual detection method for foreign body particles in bottled solution, which comprises the following steps: S1, continuously collecting T frame sequence images of bottled solution movement; S2, performing sub-pixel precision registration on the acquired sequence images to obtain the registered sequence images; S3, extracting ROI effective detection region sub-images in each frame sequence image and performing image enhancement processing respectively to obtain enhanced images of each frame sequence image; 4, respectively calculatinga difference image between two adjacent enhanced image based on that enhanced images correspond to each frame of the sequence images, and performing gray threshold segmentation on each difference image to obtain a new image; S5, extracting contour regions in each new image, and discriminating whether the contour regions are foreign objects or not based on the size features of the contour regions; S6: Identifying whether the foreignobject target is a bubble interference. On the basis of recognizing the foreign object, the method can identify whether the foreign object is a bubble or not, which improves the reliability of foreign object detection results.

The invention relates to a method for estimating the capacity of a lithium ion battery in real time. The initial electric quantity and voltage data are processed into data with certain voltage intervals, and then differential operation is carried out to obtain an IC curve. A nonlinear minimum square law is used for fitting an IC curve by using a gaussian function, and the parameter value of the gaussian function is obtained. The correlation between the parameters of the gaussian function and the capacity of the battery is analyzed, and a capacity estimation model is established. When the on-line capacity is estimated, the acquired charging data is processed, the parameter value of the gaussian function obtained by fitting is used as a model input to estimate the capacity of the real-timebattery. According to the method, the problem of online application of the capacity increment method is solved, and the problem of online estimating the battery capacity is broken through. In one embodiment of the invention, the real-time estimation error of the algorithm is less than 3%.

The invention discloses a near-infrared spectrum fruit quality online detection system achieving automatic placement of references. The system comprises a light source system, a spectrum acquisition system, a conveying system and an automatic reference feeding system; the light source system comprises halogen tungsten lamps and lamp tubes which are symmetrically arranged on the two sides of a conveyor belt; the spectrum acquisition system comprises a collimating lens, an optical fiber, a spectrometer, a position sensor and a computer; when a fruit tray loading fruit to be detected is conveyed to the portion above the collimating lens through the conveying system, and the position sensor is triggered, the spectrometer gives a response, and spectrum acquisition is conducted; the automatic reference feeding system is composed of an electric telescopic rod, a reference clamping device, a reference ball and a PLC, the PLC controls the electric telescopic rod to drive the reference clamping device to move up and down, and automatic acquisition of a reference spectrum is conducted. According to the near-infrared spectrum fruit quality online detection system achieving automatic placement of the references, real-time detection of a fruit spectrum is achieved, automatic placement of the references and automatic acquisition of the reference spectrum are achieved, man-made interference is reduced, and the accuracy and automation degree of fruit quality detection are improved.

The invention discloses a stator bar sectional dimension detection system based on machine vision. The system is used for detecting the length and width of the cross section of a line segment of a stator bar. The system comprises an image collecting transmission module, an image preprocessing module, a calibration module and a measurement module, wherein the image collecting transmission module is used for collecting, converting and transmitting a wide face image and a narrow face image of the stator bar; the image preprocessing module is used for processing a digital image and generating a target sectional dimension model and a standard sectional dimension model; the calibration module is used for performing camera calibration; and the measurement module is used for performing image matching on the target sectional dimension model and the standard sectional dimension model and obtaining an actually measured sectional dimension of a stator bar measured piece through a pixel difference method and error correction. The system can automatically and simultaneously detect the cross section length and the cross section width of each stator bar measured piece and can perform production line type detection on the sectional dimension of stator bar measured pieces of the same model produced in batches, and on-line real-time detection of the sectional dimension of the stator bar is achieved.

The invention provides a medium and low speed magnetic levitation train air gas detection system and method. The medium and low speed magnetic levitation train air gas detection system comprises a measurement unit used for detecting the gap between the train rail and a medium and low speed magnetic levitation train suspension frame. The measurement unit comprises a standard detection rail F. The standard detection rail F is arranged in the middle of the medium and low speed magnetic levitation train rail and fixed to rail sleepers through fastening pieces. At least one sensor is arranged in the magnetic pole of the standard detection rail F. The gap between the standard detection rail F and the medium and low speed magnetic levitation train suspension frame is detected through the sensors, and the gap between the magnetic levitation train rail and the train suspension frame can be detected when a train runs. The medium and low speed magnetic levitation train air gas detection system and method have the advantages of being high in detection accuracy, simple in structure, convenient to operate and high in automation degree, the measurement accuracy is further improved, and safe running of the train is effectively ensured. Operators can conduct control through a man-machine interaction unit, and can know the state of the train when being far away from the train.

The invention relates to a comprehensive partial discharge monitoring device and method. The comprehensive partial discharge monitoring device comprises an internal signal detection coil (1), an external high-configuration current transformer (3) and an external signal processing unit (2), wherein the internal signal detection coil (1) is located between a rubber insulation layer (4) and cable armor (5), and the internal signal detection coil (1) and the external high-configuration current transformer (3) are connected with the external signal processing unit (2); the internal signal detection coil (1) is used for judging whether a high-voltage cable has partial discharge; the high-configuration current transformer (3) is used for detecting the discharge capacity; the external signal processing unit (2) is used for receiving a transmission signal of the internal signal detection coil (1) and a signal of the external high-configuration current transformer (3) and computing the discharge charge quantity and judging background noise, and accurate partial discharge is realized. Compared with a relatively traditional partial discharge detection technology, the comprehensive partial discharge monitoring device and method realize new technological breakthroughs, and multiple problems of difficulty in measuring the partial discharge capacity of the internal coil and multiple interference signals of the external current transformer are solved.

The embodiment of the invention provides a communication capability opening anomaly detection method and device, and the method comprises the steps: inputting an operation parameter of a to-be-detected communication capability opening platform into an anomaly detection model, and outputting an anomaly detection result of the to-be-detected communication capability opening platform, wherein the operation parameters comprise at least one of API calling data, concurrent transaction data and module time delay data, and the anomaly detection model is obtained by training based on sample operation parameters. According to the method and device, operation parameters are input into an anomaly detection model; the anomaly detection result is obtained, online real-time detection of the communicationcapability open platform is realized; abnormity detection precision is improved, early detection and early warning of abnormity are realized, precious time is gained for coping with abnormal events,the risk prevention level of operator communication capability opening is improved, and conditions are provided for coping with instantaneous change mobile Internet application demands.

The invention discloses a device and method for detecting a high-speed tiny target online in real time by simulating fly vision. The method comprises the following steps of: acquiring scene video information by using a binocular camera, transmitting the scene video information into a DSP (digital signal processor) chip, and performing primary vision processing; performing large scene and small scene integration and target detection on primary motional information by using an FPGA (field programmable gate array) chip; and tracking a tiny target moving at high speed by taking an integration result of a large scene and a small scene as a target detection evidence. The device and method disclosed by the invention have the advantages that: the target detection is realized by virtue of a biological principle; the device and method have relatively strong antijamming capability and are applicable to the target detection under the condition of a low signal-to-noise ratio in various severe natural environments; a neuron integrating mechanism of a fly vision system has the characteristics of simple computing principle, high real-time performance and the like; the fly vision neuron is simple in tissue structure and can be easily realized by hardware; and the device can be installed on an automobile, panzer, airplane and other appliances which move at high speed, and has the capability of accurately detecting the high-speed tiny target on line in real time in a dynamically changing background.

The invention discloses a small-size sample dielectric property detection device based on micro-flow channel electric field enhancement. The small-size sample dielectric property detection device includes a vector network analyzer and a sensor, wherein the sensor is composed of a metal layer and a dielectric substrate which are arranged vertically, a coplanar waveguide transmission line is etchedon the metal layer, and the coplanar waveguide transmission line comprises two signal transmission gaps, a middle conduction band and a metal ground, and a test area composed of a rectangular capacitor and slot line branch nodes is loaded on the middle conduction band in series, the slot line branch nodes are vertically connected to the two sides of the rectangular capacitor, and the groove line branch node is vertically connected with the two signal transmission gaps. The testing device is simple in structure and high in sensitivity, the measuring area on the sensor, namely the rectangular capacitor and the groove line branch nodes at the two ends, is processed by adopting a traditional etching process, the cost is low, the processing difficulty is low, batch production is facilitated, and on-line real-time detection can be realized.

The invention relates to a method for detecting sizing percentage of slashing by applying the near-infrared spectrum technology, in particular to the Fourier-based near-infrared spectrum analysis technology. Slashing test specimen is prepared by special sample collection preparation method, and a slashing sizing percentage calibration model is established by combining with chemo-metrics methods, thus detecting the sizing percentage of slashing on line rapidly without any loss.

The invention relates to a real-time detection and fine-adjustment device for easily-open-cap nicks and a detection and fine-adjustment method. The defects that in existing easily-open-cap processing, off-line detection is carried out, the detection time is long, and detection is prone to being influenced by human factors are overcome. The real-time detection and fine-adjustment device comprises a detection device and a fine-adjustment device, wherein the detection device is arranged on an upper mold of an easily-open-cap nicking device, and the fine-adjustment device is arranged on a lower mold of the easily-open-cap nicking device. The detection device comprises an imaging source, an imaging screen and an imaging data collector, wherein the imaging source is arranged on the upper mold of the nicking device, and the imaging screen is arranged on the periphery of the upper mold. The fine-adjustment device comprises an induction heating expansion body and a heating control device, wherein the induction heating expansion body is fixed on the lower mold, the heating control device is connected with the expansion body, the induction heating expansion body is circumferentially arranged along the center line of the lower mold and corresponds to a cutter mold body on the upper mold in position, and the heating control device is connected with the imaging data collector. The cutting edge of the cutter mold body is imaged on the imaging screen so that changes of the size of the cutting edge of the cutter mold body in the axial direction can be calculated to determine changes of the depths of the easily-open-cap nicks, and detection is conveniently carried out; on-line real-time detection can be achieved, halting is not required, the detection speed is high, efficiency is high, and influences of the human detection factors are avoided.

The invention relates to a fuel on-line detection method of a gasoline and diesel oil mixing flexible fuel engine. The fuel on-line detection method is characterized in that power equipment is used, and the power equipment comprises an engine electronic control unit, a flexible fuel compression ignition engine, a piezoresistive cylinder pressure sensor and a fuel recognition electronic control unit; the fuel recognition electronic control unit comprises a circulating fuel-injection quantity calculating module, an accumulative heat release calculating module, a fuel volume calorific value calculating module and a fuel recognition module; the engine electronic control unit collects the fuel temperature, the rail pressure and the injection time, and the piezoresistive cylinder pressure sensor collects cylinder pressure and sends the cylinder pressure to the fuel recognition electronic control unit; the circulating fuel-injection quantity calculating module calculates the circulating fuel-injection quantity and sends the circulating fuel-injection quantity to the fuel volume calorific value calculating module; the accumulative heat release calculating module calculates the circulating accumulative heat release and sends the circulating accumulative heat release the fuel volume calorific value calculating module; the fuel volume calorific value calculating module calculates the volume calorific value of mixing fuel and sends the volume calorific value of the mixing fuel to the fuel recognition module; the fuel recognition module calculates the mixing ratio and feeds back the mixing ratio to the engine electronic control unit to perform closed-loop control. The fuel on-line detection method can be widely applied to the on-line detection of engine fuel.