17results about How to "Accurate and effective detection" patented technology

The invention discloses a motor deflection abnormal sound detection method and device, test equipment and a storage medium, and the method comprises the steps: starting a target motor, collecting a sound signal transmitted by the target motor, and obtaining an audio sampling signal; based on a preset framing duration, performing short-time Fourier transform on the audio sampling signal to obtain first sound pressure frequency domain data of a plurality of audio clips; combining equivalent sound pressure level data obtained by carrying out equivalent sound pressure calculation and sound pressure level conversion on the first sound pressure frequency domain data of the plurality of audio clips based on a time sequence to obtain sound pressure level time domain data of which the sound pressure level changes along with time; fourier transform is carried out on the sound pressure level time domain data to obtain sound pressure level frequency domain data with the sound pressure level changing along with the modulation frequency; according to the sound pressure level frequency domain data and a preset deflection abnormal sound threshold, whether deflection abnormal sound exists in the target motor or not is determined. According to the invention, whether the motor has abnormal deflection noise or not can be accurately and effectively detected.

The present application discloses a method and system for detecting pollutants after sewage treatment, which relates to the technical field of sewage treatment. According to the type of sewage treatment strategy corresponding to the treated sewage and the influence relationship between the preset sewage treatment strategy type and the pollutant detection strategy type, the target pollutant detection strategy type suitable for the treated sewage is determined. Then, according to this type, combined with the evaluation value of the pollutant detection ability of the sewage detection strategy adapted to the treated sewage, the target pollutant detection strategy is determined from multiple pollutant detection strategies respectively corresponding to multiple preset pollutant detection strategy types, so as to detect pollutants based on the target pollutant detection strategy. Since the influence of the sewage treatment strategy on sewage detection is considered, as well as the sewage detection strategy adapted to the characteristics of the sewage, the finally determined target pollutant detection strategy can achieve effective and accurate pollutant detection of the treated sewage.

The present invention discloses a quality inspection device for cold-drawn seamless steel pipes, which belongs to the field of mechanical stress testing devices, and includes a pressure collar assembly and a tension collar assembly. One end of the tension collar assembly is plugged into the interior of the pressure collar assembly, and a driving ring is plugged into the interior of the pressure collar assembly. A wave slope plate is fixed to the inner wall of the driving ring. The present invention arranges the wave slope plate and the tension plate. When the driving motor is running, the wave slope plate can be driven to rotate, and then the lower pressure seat can move up and down in coordination with the opening and closing of the tension plate. Pressure and tension can be applied to the steel pipe at the same time, so that the wound on the steel pipe is quickly exposed, providing favorable conditions for ensuring the reliability of quality inspection. At the same time, applying pressure and tension to the steel pipe can extend the circumference of the steel pipe, so that the wound can be expanded and extended, so that the probe device can accurately detect the more hidden wound, so that the accuracy of the inspection is guaranteed.

The invention discloses a method for detecting an initiator and a degradation product thereof in a polymer, a chromatographic column is an octadecyl bonded silica gel column, a gradient elution mode is adopted, and a detector is a diode array detector (DAD). The result shows that under the chromatographic condition, various impurities generated by degradation of the sevelamer carbonate catalyst can be well separated; the precision, repeatability and stability results are good. The method is simple and convenient to operate, high in repeatability and stable and reliable in result, and can be used for detecting the sevelamer carbonate initiator and the degradation product thereof.

This invention discloses a device for inspecting bulge defects in cover glass, belonging to the field of cover glass defect detection technology. The technical solution includes a water tank with an inlet pipe, a glass fixing platform below the water outlet, and the glass being fixed at an angle on the glass fixing platform. A weighing platform is located below the glass fixing platform, and several electronic scales are spaced apart along the length of the glass fixing platform. This invention, by employing the principle of blocking water flow due to bulge defects in the cover glass, can accurately and effectively detect the location and defect level of the bulge defects.

The boiler coal metering auxiliary device comprises a coal plough, a coal layer detection assembly and a controller, the coal plough comprises a door frame, a swing frame, a V-shaped plowshare and an electric-hydraulic push rod, the coal layer detection assembly comprises a supporting plate, an angle adjusting plate and a plurality of diffuse reflection optoelectronic switches, the supporting plate is fixedly arranged on the upper side of the front portion of the V-shaped plowshare, and the angle adjusting plate is fixedly arranged on the lower side of the V-shaped plowshare. The angle adjusting plate is arranged on the supporting plate in the left-right direction and can swing up and down and be positioned relative to the supporting plate, and the diffuse reflection optoelectronic switches are arranged on the angle adjusting plate in the left-right direction and used for detecting coal seams distributed on the conveying belt below the V-shaped plowshare; and the diffuse reflection photoelectric switch is electrically connected with the controller. By means of the auxiliary device, the amount of coal unloaded into a coal bunker of a corresponding single boiler through a coal plough can be calculated, and therefore further research on power supply coal consumption, boiler combustion indexes and economic benefits can be conveniently achieved according to the data.

The embodiment of the invention provides a touch area detection method and device, electronic equipment, a storage medium and a program product. The touch area detection method comprises the steps that first touch data obtained when a user conducts touch operation on a touch screen are obtained, and the first touch data at least comprise touch data of an intention touch area of the touch screen; based on the first touch data, touch area detection is conducted through a machine learning model, and coordinate information of an intention touch area corresponding to the first touch data is obtained. According to the scheme, the detection effect on the touch area of the touch screen is good.

A display device includes: a substrate including a display area and a non-display area disposed near the display area; a plurality of pixels disposed in the display area; a plurality of signal lines disposed on the substrate and connected to the plurality of pixels; and a pad portion disposed in the non-display area and including a plurality of pads. The plurality of signal lines include: a first crack detection line connected to a first test voltage pad and a first pad at a first node, connected to a second pad at a second node, and extending along the non-display area between the first node and the second node; and a first data line including one end connected to a first transistor connected to the first crack detection line at the second node and the other end connected to a corresponding pixel among the plurality of pixels.

The present application relates to the technical field of target detection, and specifically provides a target detection method, system, device and medium, aiming to solve the problem of how to accurately detect and obtain the human body, face and the correlation between the human body and face in the image during the target detection process. To this end, the present application respectively performs face detection, human body detection and face-human body correlation detection on the image to be detected, and obtains the final target detection result of the image to be detected according to the above detection results, comprehensively considers the influence of face detection, human body detection and face-human body correlation detection on the final target detection result, can more accurately and effectively detect the human body, face and the correlation between the human body and face in the image to be detected, and can also achieve good detection effect for the case that the face is blocked or only the face is exposed.

This invention discloses a method, apparatus, equipment, and medium for controlling cigarette packaging quality based on the sensing range of a tobacco packaging machine sensor. The method includes: determining a sensing range acquisition strategy based on the theoretical sensing range of the target cigarette pack material sensed by the packaging quality sensor; reading the real-time sensing signal of the packaging quality sensor and acquiring the actual sensing phase range when the packaging quality sensor senses the target cigarette pack material based on the real-time sensing signal and the sensing range acquisition strategy; the actual sensing phase range being the main axis phase range of the cigarette packaging machine when the quality sensor actually senses the target cigarette pack material; and controlling the packaging quality of the cigarette packaging machine based on the cigarette pack identification information corresponding to the packaged cigarette pack and the actual sensing phase range. This invention can improve the overall control capability of cigarette packaging quality.

The present invention relates to the technical field of dual-channel communication, and discloses a module adaptive identification control method and system for dual-channel communication. During the communication process, inspection items are confirmed, and corresponding communication data are obtained according to the inspection items; judgment and analysis are performed according to the communication data, and inspection item signals are generated, and then the communication data is analyzed based on the running time; wherein the inspection item signals include normal transmission item signals or abnormal transmission item signals, normal equipment item signals or abnormal equipment item signals; based on the transmission fluctuation value and the equipment fluctuation value, signal cross-analysis is performed to judge the problem of slow communication interaction rate; based on the dual-item detection signal, the inspection items are optimized and judged, and specific inspection items are output; the present invention performs modular analysis according to the detection items, so as to identify the cause of the slow communication interaction rate, facilitate rapid inspection and recovery, and ensure the normal operation of communication.

The invention discloses a micro-fluidic immune quantitative analysis system, which comprises a micro-fluidic chip and immune colloidal gold, and a preparation method of the micro-fluidic chip comprises the following steps: carrying out corona activation on a polydimethylsiloxane chip with a channel and a glass slide together for 30-60 s, attaching the polydimethylsiloxane chip and the glass slide, and sequentially carrying out amination treatment and formylation treatment on the channel; adding a cTN I monoclonal capture antibody into the treated chip for modification; carrying out vacuum degassing and sealing on the modified chip; the immune colloidal gold is obtained by marking a cTNI detection antibody with colloidal gold. The microfluidic immune quantitative analysis system disclosed by the invention can realize rapid and quantitative detection of cTNI, can quantitatively detect 0.5 ng / ml-60ng / ml of cTNI through strip length without depending on instruments and equipment, and is good in specificity.

The invention provides a pedestrian detection method and system based on deep learning, and the method comprises the steps: obtaining scene image data in a to-be-detected scene, and carrying out the preprocessing of the scene image data; performing object shape recognition on the preprocessed scene image data based on a pre-training model, and performing feature extraction on an object shape recognition result based on an attention mechanism; and analyzing a feature extraction result, judging whether a pedestrian exists or not, and identifying and positioning the pedestrian when the pedestrian exists. According to the invention, whether the pedestrian exists or not is accurately and effectively judged, and when the pedestrian exists, the pedestrian is effectively identified and positioned, so that the reliability and the accuracy of pedestrian detection are ensured.

The present invention belongs to the field of biological detection and diagnosis, and relates to the diagnosis of AFB1 poisoning in broilers, and particularly refers to a plasma biomarker and its application for the diagnosis of AFB1 poisoning in broilers. The plasma biomarker is erythrinain. Its structural formula is:. The above-mentioned plasma biomarker is used in the preparation of a reagent, a kit or a detection instrument for the diagnosis of AFB1 poisoning in broilers. The reagent, the kit or the detection instrument is used to detect the content of erythrinain in the plasma of the broiler to be tested, and the content is compared with the content in the plasma of normal broilers, so as to judge whether the broiler is AFB1 poisoned. The present invention screens out a plasma metabolite erythrinain, which has extremely high specificity for AFB1 poisoned broilers and normal broilers, and is superior to serum liver function markers. It has high sensitivity for the diagnosis of AFB1 poisoning, which is conducive to the rapid and effective detection and screening of AFB1 poisoned broilers, and the preliminary evaluation and analysis of the degree of AFB1 exposure of animals.

This invention discloses a support device, specifically a support device for X-ray inspection of narrow weld seams in aero-engine casing support plates, belonging to the field of aero-engine maintenance and repair process equipment design and manufacturing technology. It provides a support device for X-ray inspection of narrow weld seams in aero-engine casing support plates that ensures an effective radiographic angle for in-situ replacement support plates and accurately and effectively detects defects in these weld seams. The support device includes a base frame, an adjustment assembly, and a support fixing structure, with the support fixing structure arranged on the base frame. During X-ray inspection of narrow weld seams in aero-engine casing support plates, the radiographic angle of the aero-engine casing support plate fixed to the support fixing structure in the horizontal and / or vertical directions is adjusted to a specified position by the adjustment assembly.

The invention relates to a single tomato flower dynamic counting method based on target tracking counting, and relates to the field of agricultural yield prediction.The method comprises the steps that single tomato flowers on tomato vines are recognized through a depth camera and a tomato flower target detection algorithm; obtaining a single tomato flower target frame through the target detection model, extracting appearance characteristics and motion characteristics of a single tomato flower in combination with a tracking counting algorithm, and matching the appearance characteristics and the motion characteristics with the target frame; the tomato flower ID jump in the tracing process is slowed down through a multi-section region area method; according to the method, the tomato flowers can be accurately and effectively detected by using the target detection algorithm, tracking counting of the single tomato flowers can be realized by combining the target detection model and the tracking counting model, dynamic counting of the single tomato flowers is effectively completed, and a reference is provided for yield estimation of a planter.

The invention discloses a repetitive defect detection method, device and system and a readable storage medium. The method comprises the following steps: acquiring first position information of a defect on the surface of a machined part by taking the machined part as a position reference; taking one of the plurality of processed areas on the surface of the processed workpiece as a reference area, and determining second position information of the defect on the surface of the processed workpiece by taking the reference area as a position reference; determining a defect density peak point taking the reference area as a position reference according to the second position information of the defects on all the processed areas; and if the number of the defects in the preset range of a certain defect density peak point is greater than or equal to a repetitive defect threshold value, judging that the processed workpiece has repetitive defects. As the repetitive defects are densely distributed in a certain area when mapped into the reference area, the repetitive defects are detected through the defect density, and the repetitive defects in the machined workpiece can be accurately and effectively detected.