82results about How to "Achieve culling" patented technology

The invention discloses an acoustic emission effective signal extraction method, device and equipment and a storage medium, and the method comprises the steps: collecting an initial acoustic emission signal, and carrying out the frequency band decomposition of the initial acoustic emission signal through wavelet packet transformation, and obtaining a plurality of frequency band waveforms; inputting each frequency band waveform into a preset auto-encoder model for reconstruction feature filtering to obtain an initial filtering signal; the initial filtering signal is input into a preset feature extraction model for time sequence feature filtering, an acoustic emission effective signal is obtained, and the preset feature extraction model is used for conducting time sequence feature analysis on the initial filtering signal. Compared with the prior art, the method has the advantages that the initial acoustic emission signals are subjected to frequency band decomposition by adopting wavelet packet transformation, then different frequency band waveforms are input into the preset auto-encoder model for reconstruction feature filtering, and then the filtered signals are subjected to time sequence feature analysis, so that background noise is effectively eliminated, and the accuracy of the acoustic emission signals is improved. The extraction of the sound emission effective signal in the strong background noise environment is realized.

The invention discloses beverage bottle sealing performance detection equipment, and belongs to the technical field of beverage bottle sealing performance detection. A beverage bottle sealing performance detection device comprises a base and a detection cylinder fixedly installed on the inner bottom face of the base, and a sealing opening is formed in the middle of the surface of the top end of the detection cylinder. According to the sealing performance detection equipment of the beverage bottle, when the beverage bottle body is put into the detection cylinder through the sealing opening and is immersed in water, the sealing plug and the sealing opening are matched and sealed, the pressure is detected according to the sealing performance of the beverage bottle body, and air in the detection cylinder is exhausted through work of the air extracting pump; the detector works to detect the sealing performance of the beverage bottle body, the overall sealing performance of the beverage bottle body is judged according to whether bubbles are generated in water in the detection cylinder or not of the beverage bottle body, compared with the prior art, the equipment enables the sealing performance detection process of the beverage bottle body to be simple and convenient, and then the efficiency of beverage bottle sealing performance detection is improved.

The invention relates to the technical field of intelligent manufacturing, in particular to a checking and rejecting device and method under the high-speed condition, and the device comprises a conveying belt, a code reading triggering photoelectric sensor, a depth camera, a code reader, a rejecting assembly, a rejecting detection photoelectric sensor, an encoder and a PLC. The accurate position of the bottle cap is obtained through the depth camera, and the code reader is controlled to be aligned with the bottle cap, so that the accuracy of two-dimensional code reading is ensured; the vibration sensor and the light sensor are introduced to detect the change of environment vibration and illumination intensity, and the sensitivity of the photoelectric sensor and the trigger delay of the rejecting device are dynamically adjusted through the PLC, so that high-precision two-dimensional code verification and accurate rejecting of unqualified products under a high-speed condition are realized, and the production efficiency and the product quality are remarkably improved.

The invention relates to the field of automatic conveying, in particular to C-shaped lining conveying and detecting equipment which comprises a friction type self-adaptive rotating device, a T-shaped screening and conveying device and a first flexible internal expansion material moving mechanical arm. The friction type self-adaptive turning device drives the C-shaped bushing to rotate by utilizing friction force, and uniformly adjusts the opening direction of the C-shaped bushing to a preset angle; the first flexible internal expansion material moving manipulator is used for transferring the C-shaped bushings between the friction type self-adaptive rotating device and the T-shaped screening and conveying device and grabbing the inner walls of the C-shaped bushings in an internal expansion manner; and the T-shaped screening and conveying device is used for receiving the C-shaped bushings and removing the C-shaped bushings with incorrect opening directions by utilizing a profiling structure of the T-shaped screening and conveying device. The friction type self-adaptive turning device is used for replacing expensive machine vision equipment, the cost is low, interference of greasy dirt and light rays is avoided, and the adaptability is high; and meanwhile, by means of the physical profiling design of the T-shaped screening and conveying device, error correction and rejection of wrong opening directions are achieved, and accurate feeding is ensured.

The utility model relates to the technical field of visual inspection, and discloses a defective package rejecting device with visual inspection, which comprises a support component, a conveying component is mounted at the top of the support component, and a height adjusting and detecting component is mounted on the rear side of the top of the conveying component. And the rear side of the height adjusting and detecting assembly is correspondingly provided with the flow dividing control assembly, the rear side of the flow dividing control assembly is correspondingly provided with the flow dividing rail assembly, and the flow dividing rail assembly, the flow dividing control assembly and the height adjusting and detecting assembly are fixedly installed at the top of the support assembly. According to the utility model, the control shunting assembly is arranged on the device, so that when the device is used, defective products or unqualified products captured in the detection process can be shunted and guided out through the arranged control shunting assembly, and then the working effect of removing is realized; and the work complexity of subsequent manual independent sorting is avoided.

The application discloses a full-angle image recognition sugarcane seed selecting device, and relates to the technical field of sugarcane seed selection, which comprises a sugarcane loading frame, sliding seats are slidingly connected to slide rods fixed to one end of the sugarcane loading frame, two sliding seats are connected through a cross rod, the cross rod is fixedly connected to a lifting cylinder at the middle position of the bottom, the lifting cylinder is fixed to the sugarcane loading frame, in the process that the sugarcane is lifted by the sugarcane supporting frame, the two ends of the sugarcane will push the swing rods to deflect to one side until the sugarcane is lifted above the swing rods, after the sugarcane is no longer pushed, the swing rods will droop according to their own gravity, the sugarcane falls on the two swing rods, then a cutting saw, which is electrically mounted on a cutting support through a linear module, moves downwards, so that the rhizome of the sugarcane is cut, the cut sugarcane no longer lifted by the swing rods will fall on multiple inclined guide conveying rods, under the guidance of the inclined guide conveying rods, the sugarcane falls on double-sided conveyors, so that subsequent sugarcane seeds can be selected.

The present invention relates to an analysis method, system, equipment and storage medium for the main controlling factors of oil well productivity. The method comprises the following steps: respectively cleaning the production dynamic factors and static geological factors in the acquired oil well data; using the control variable method to independently analyze the cleaned production dynamic and static geological data, respectively designing their application methods, and using a machine learning algorithm to sort the main controlling factors of oil well productivity, and obtain the importance ranking of each production dynamic factor and static geological factor. The present invention can improve the applicability and accuracy of the machine learning algorithm in the field of research on the main controlling factors of oil well productivity by efficiently cleaning the production dynamic and static geological data and using a data usage method suitable for the characteristics of the production dynamic and static geological data. Therefore, the present invention can be widely used in the field of oil and gas field development.

The invention provides a belt inspection robot control method and system, and relates to a data processing technology, the method comprises the following steps: obtaining an oblique detection zone located at a belt mechanism, and collecting magnetic flux data of static induction units obliquely arranged in the oblique detection zone at intervals; according to the magnetic flux data and the distribution positions of the static induction units, verification areas are generated, and based on the magnetic flux data of the change induction units corresponding to the verification areas, estimated contours corresponding to the verification areas are constructed; when it is determined that the verification area is located in the treatment area, a robot in the treatment area is controlled to sort and recognize the verification area, and the recognition contour of the to-be-sorted object is obtained; on the basis of the comparison result of the estimated contour and the recognized contour, the mobile sensing unit is controlled to move to the re-checking area for verification, a re-checking result is obtained, shape estimation can be conducted on the metal foreign matter buried below the coal, therefore, a robot is effectively guided, and the efficiency and reliability of removing the metal foreign matter are improved.

The adaptive tailings pond remote sensing deep learning detection method provided by the present invention is used for large-scale tailings pond identification and extraction. The present invention proposes a new tailings pond remote sensing extraction framework, namely: first, a feature pyramid network is used to perform deep feature learning of tailings ponds of different sizes based on a tailings pond remote sensing image data set; second, a cascade positioning optimization module is used to locate the tailings pond according to the characteristic value and use a multi-level detector to optimize the positioning coordinates; third, candidate detection objects are obtained according to the positioning optimization value, and multi-dimensional features are extracted and fused based on the deep learning algorithm and the traditional feature extraction algorithm to generate feature vectors; finally, an adaptive feature learning classifier is used to perform integrated learning and classification based on the feature vector, eliminate false alarm targets and extract tailings ponds. The present invention has the advantages of high positioning accuracy, low false alarm rate, and wide application range, and can provide an important basis for dynamic updating of tailings pond distribution information and safety management.

The utility model discloses a long, short, thick and thin material mixing prevention mechanism of a thread rolling machine, and relates to the technical field of fastener machining. The device structurally comprises a conveying frame, a belt conveyor, an impact rejector, a first U-shaped mounting seat and a second U-shaped mounting seat, the conveying frame comprises a first flat plate; an L-shaped panel is fixed on one side of the lower surface of the first panel; a flow guide side plate is fixed on the side surface of the first plate adjacent to the L-shaped plate; the belt conveyor is mounted on the L-shaped flat plate; the first flat plate and the L-shaped flat plate are jointly mounted on the base; and the first U-shaped mounting seat is mounted on the first flat plate. Through the combination of the material conveying frame and the belt conveyor, over-thick bolt blanks are removed from the front end, and over-thin bolt blanks are removed under the action of gravity; through cooperation of the first correlation switch, the second correlation switch, the inductive switch and the impact rejector, overlong and overshort bolts can be detected and rejected, the consistency of product sizes is guaranteed, and unqualified products are effectively reduced.

The present invention relates to the field of optical technology, and in particular to a backlight detection system and a pixel-level light field modulation method thereof, wherein the system comprises a main optical system, a polarization beam splitter, a relay lens group, a visible light detector, a pixel-level polarization light field modulator, a polarization detector and a high-dynamic fusion component, wherein the radiation energy collected by the main optical system is incident on the polarization detector and the pixel-level polarization light field modulator respectively through the polarization beam splitter, the polarization detector acquires a polarization image, the radiation energy output by the pixel-level polarization light field modulator is imaged to the visible light detector in turn through the polarization beam splitter and the relay lens group to obtain a visible light image, the polarized visible light image is sent to the high-dynamic fusion component for detection target recognition and motion trajectory prediction, the pixel-level polarization light field modulator is modulated according to the detection target recognition and motion trajectory prediction results, so that the background radiation energy is reflected out of the backlight detection system along the original path. The present invention realizes high-precision target recognition of the detection target.

The waste kicking device for the boxing machine comprises two guide plates which are symmetrically arranged, the two guide plates are arranged on the front sides of baffles on the two sides of a conveying belt of the boxing machine respectively, a finished product conveying belt is arranged at the front end of the conveying belt of the boxing machine, and the ends, away from the finished product conveying belt, of the two guide plates are obliquely arranged towards the opposite baffle sides respectively. Adjusting assemblies capable of adjusting the distance between the guide plates are arranged on the outer sides of the two baffles correspondingly, a blocking assembly for blocking packaging boxes from advancing is arranged between the two baffles on the front side of the boxing machine conveying belt, the baffle on one side of the blocking assembly communicates with a waste discharging groove, and a waste pushing assembly is arranged on the side, away from the finished product conveying belt, of the blocking assembly. An infrared detector is arranged on a guide plate on the side, away from the blocking assembly, of the waste pushing assembly. The infrared detector, a control element of the blocking assembly and a control element of the waste pushing assembly are connected with a control system. The device can realize automatic detection and removal of the packaging box sealing cover, and manpower resources are saved.

The utility model discloses a waste kicking device of a web press to solve the technical problems that an existing waste kicking mode is not accurate enough, and arrangement of paper is easily affected. The conveying device comprises a first conveying belt located at the rear portion and a second conveying belt located at the front portion, the tail end of the first conveying belt is higher than the head end of the second conveying belt, or the tail end of the first conveying belt and the head end of the second conveying belt are equal in height or coincide, and an included angle is formed between the first conveying belt and the second conveying belt. The time and space for waste kicking can occur when the book paste is transited between the first conveying belt and the second conveying belt, a waste kicking mechanism is arranged at the tail end of the first conveying belt, and the waste kicking mechanism can be a pneumatic suction nozzle, a mechanical arm or a belt clamp. The device has the beneficial technical effects that waste book stickers in the book stickers arranged in a fish scale mode can be removed, stable operation of the front book stickers and the rear book stickers is not affected, the waste book stickers are grabbed and positioned accurately, and continuous waste products or a plurality of waste products with very small intervals can also be kicked smoothly.

The utility model discloses an automatic cleaning machine for fiber carding, which comprises a bearing frame and a control bin, the bearing frame is of a U-shaped structure, the control bin is arranged at the top of the bearing frame, a dehairing fence is movably arranged on the control bin, and the control bin controls the dehairing fence to move horizontally. The steel needles and the dehairing rods are staggered, the dehairing rods are used for dehairing down batting or fibers on the rotating steel needles, removal is achieved, and the problems that in the background technology, a method for manually removing batting or fibers in the steel needles is time-consuming, labor-consuming and poor in effect are solved.

The present invention discloses a battery pack information acquisition system based on terminal control; the system comprises a main control module, the main control module is electrically connected to a data processing module, the data processing module is electrically connected to a BMS management system and a communication module, the BMS management system is electrically connected to a battery module, the main control module is electrically connected to an electric power device, and the communication module is communicatively connected to a remote terminal module. The present invention manages and controls the battery module through the BMS management system, and then calculates and processes the data information through the data processing module, calculates and processes the power supply mode of the battery module through a greedy algorithm to achieve a balanced and stable power supply mode, and evaluates the power supply mode through a neural network algorithm to prevent calculation errors. Finally, when errors occur in the data information, the data information is corrected and eliminated to improve the accuracy and validity of the data.

The utility model relates to the technical field of batteries, and discloses a battery cell fusing control structure and a battery, and the battery cell fusing control structure comprises a first plate body; the pole column and the first plate body are arranged at an interval along the second direction; the fusing piece is suitable for electrically connecting the pole with the battery cell main body; a first groove is formed in the pole; the conductive part is arranged in the first groove, one end of the conductive part in the second direction is suitable for being electrically connected with the pole, and the other end of the conductive part tends to be close to and abut against the first plate body; the insulating part has a first state for locking the conductive part in the first groove and a second state for unlocking the conductive part; when the insulating part is switched from the first state to the second state, the other end of the conductive part abuts against the first plate body, and the fusing part is fused. According to the battery cell fusing control structure provided by the utility model, the isolation and elimination of abnormal battery cells and the continuous use of normal battery cells are realized, so that a battery pack can be continuously and normally used.

The invention provides an intelligent coal gangue sorting and removing method and system, and relates to the technical field of coal sorting, and the method comprises the following steps: carrying out the semantic segmentation of an obtained coal flow image, and obtaining a coal region; calculating a real hue value of each pixel point in the image based on the illumination distribution function, and identifying and marking coal gangue in the coal flow image through a preset classification model; performing feature tensor analysis by using the neural network model, and determining position information of the coal gangue according to an analysis result; and rejecting the identified coal gangue from the coal flow by using a coal gangue rejecting device. According to the method, automatic recognition and removal of the coal gangue are achieved, manual intervention is reduced, the sorting efficiency is remarkably improved, feature extraction and position determination are conducted through the neural network model, accurate removal is conducted through the coal gangue removal device, and automation and high efficiency of coal sorting are achieved.

The invention relates to the technical field of government affair informatization, in particular to a government affair knowledge graph construction method and system based on artificial intelligence, and the method comprises the steps: obtaining multiple pieces of multi-source government affair data, carrying out the format unification of the multiple pieces of multi-source government affair data, obtaining multiple unified texts, carrying out the cleaning segmentation of the multiple unified texts, obtaining multiple text segments, and carrying out the segmentation of the multiple text segments; performing subject recognition on the plurality of text segments to obtain a plurality of government affair entities, performing normalized alignment on the plurality of government affair entities to obtain a plurality of unique entities, obtaining a plurality of semantic relationships of the plurality of unique entities, and constructing a triple set by using the plurality of unique entities and the plurality of semantic relationships, and constructing a government affair knowledge graph by utilizing a plurality of triads in the triad set, and automatically generating a rule required by the rule engine by the government affair knowledge graph. The method can solve the problem that intelligent application of government affair knowledge is difficult due to dispersion of multi-source government affair data and low manual integration efficiency.

The invention discloses a parameter optimization method for an anti-impact double-phase structure. The method comprises the steps of obtaining a to-be-optimized parameter index numerical value set and an anti-impact double-phase structure performance test result set; the to-be-optimized parameter index numerical value set comprises a plurality of to-be-optimized parameter index numerical values; the impact-resistant biphase structure performance test result set comprises a performance test result under each to-be-optimized parameter index value; performing modeling processing on the to-be-optimized parameter index value set and the impact-resistant biphase structure performance test result set to obtain a multi-index optimization model; and performing calculation processing on parameter indexes to be optimized by utilizing the multi-index optimization model to obtain an optimal index set. According to the method, the accurate construction of the performance index function is realized, the overall optimization of the multi-type parameters of the biphase structure is realized based on the function set, and finally the optimization of the performance of the biphase structure is realized.

A detecting and magnetizing device used after magnet magnetizing comprises a conveying rotary disc, positioning grooves are evenly machined in the position, close to the circumference, of the conveying rotary disc, positioning seats are arranged in the positioning grooves, array type machining material grooves are formed in the positioning seats and used for containing magnet blocks, and the conveying rotary disc is sequentially provided with a feeding station, a detecting station and a discharging station in the anticlockwise rotation direction. A magnetic force detection mechanism is arranged above the detection station; the magnetic detection mechanism comprises magnetic detectors which are uniformly mounted at the bottom of the positioning sleeve, and a push block is slidably mounted at the center of the positioning sleeve; a limiting plate is arranged at the bottom of the trough to support the magnet, one side of the limiting plate is hinged to a support through a pin shaft, the support is fixedly arranged at the bottom of the positioning base and on the pin shaft, and a torsional spring is installed between the limiting plate and the support. According to the device, a mechanical structure is adopted to replace manual operation, magnetic force detection of the magnet blocks is automatically completed, unqualified products are removed, and the working efficiency is effectively improved.

This application provides a method, equipment, medium, and product for testing power line signals, relating to the field of signal processing technology. The method includes: dividing the power frequency cycle into N test time cycles using a voltage zero-crossing detection unit and generating corresponding N wideband test data packets; sequentially sending the wideband test data packets within M consecutive power frequency cycles to obtain M test signals, which are then collected to form N sub-signal sets; calculating the fluctuation variance of each sub-signal set and generating a confidence coefficient; synthesizing N reference sub-signals and dividing them into high-confidence sub-signals and sub-signals to be repaired based on the confidence coefficients; reconstructing and repairing the sub-signals to be repaired using the channel response characteristics of the high-confidence sub-signals to generate repaired sub-signals; and finally concatenating the high-confidence sub-signals and repaired sub-signals in time sequence to obtain the final test signal. This solution solves the technical problem of how to obtain high-precision power line test signals throughout the entire power frequency cycle.

This invention provides a cigarette rejection device, comprising a mounting cover, a horizontal drive assembly, a vertical drive assembly, a linear motor, a blank cigarette detector, and a controller. The mounting cover and the blank cigarette detector are respectively disposed on the right side of the conveying channel of a cigarette storage and conveying device. The horizontal drive assembly and the vertical drive assembly are respectively disposed inside the mounting cover. The linear motor is disposed on the horizontal drive assembly, which drives the linear motor to move horizontally. The horizontal drive assembly is disposed on the vertical drive assembly, which drives the horizontal drive assembly and the linear motor to move vertically. The movement direction of the mover of the linear motor is parallel to the axis of the cigarettes on the conveying channel. The blank cigarette detector, the linear motor, the horizontal drive assembly, and the vertical drive assembly are all electrically connected to the controller. This invention can reject blank cigarettes one by one as they pass through the cigarette storage and conveying device, avoiding excessive rejection.

The invention relates to the technical field of radar survey, in particular to a ground-based synthetic aperture slope radar atmospheric disturbance correction method and system, and the method comprises the steps: collecting a radar image, and carrying out the phase unwrapping of the radar image, and obtaining a PS point; eliminating the PS points by using an improved morphological opening operation to obtain stable PS point distribution, and completing deformation monitoring and realizing deformation inversion according to the stable PS point distribution; the improved morphological opening operation comprises the following steps: obtaining an outlier of a PS point by using an outlier detection algorithm, and correcting the outlier through a distance value between the PS point and a nearest PS point. According to the method, the data distribution of the PS points is analyzed, the core radiuses of morphological processing corresponding to different PS points are obtained, self-adaptive morphological processing is achieved, the isolated PS points are removed, the more stable PS points are obtained, and the accuracy of deformation inversion is improved.

The application discloses a data processing method and device, a storage medium and an electronic device. The method comprises the following steps: collecting target data reported by a target device; calling a data cleaning rule mapping, and obtaining a target cleaning rule corresponding to the target data according to the identification of the target device and the data cleaning rule mapping, wherein the data cleaning rule mapping is used at least for indicating the mapping relationship between the device identification and the cleaning rule; determining the attribute type of the target data according to the target cleaning rule; and executing different data processing strategies according to the attribute type. The application solves the technical problem that accurate data cannot be obtained, subsequent reasonable and timely early warning cannot be performed, and accurate prediction analysis cannot be performed due to the fact that, in the related art, a third-party IOT monitoring tool can only store data and cannot eliminate error data.

The utility model relates to the technical field of coal mine conveyors, and discloses an impurity blocking device for a coal mine belt conveyor, which comprises a conveying mechanism main body, the top of the conveying mechanism main body is sequentially provided with a blocking component, a cleaning component and an adsorption component from left to right, and the front surface of the inner wall of a fixing frame is fixedly connected with a mounting block. The top of the supporting plate is fixedly connected with a fixing frame, the front face of the fixing frame is fixedly connected with a translation motor, an output shaft of the translation motor is fixedly connected with a screw rod, and the outer side of the screw rod is in threaded connection with a moving plate in a sleeved mode. The top of the moving plate is fixedly connected with a fixing block, and the right side of the connecting block is fixedly connected with a scraper. By arranging the blocking assembly, the cleaning assembly and the adsorption assembly, blocking and removing of long sundries mixed in a coal mine and adsorption and cleaning of ironware sundries are achieved.

The invention provides a text data denoising method for a mining industry large model. The method comprises the following steps: determining a typesetting state of a home page in a knowledge document; wherein the knowledge document is a document in a mine industry knowledge base; determining page header coordinates of the knowledge document, page footer coordinates of a home page and page footer coordinates of a non-home page in the knowledge document; cutting the home page according to the header coordinates and the footer coordinates of the home page in combination with the typesetting state of the home page, so that the cut home page only contains the text; and cutting the non-home page according to the header coordinates and the footer coordinates of the non-home page, so that the cut non-home page only contains the text. According to the method, noise data in the mine industry knowledge base can be eliminated, the quality and accuracy of the coal industry knowledge base are improved, the quality of the coal industry high-quality text data set is improved, and the influence of the noise data on the model performance is reduced.

The present invention provides a cigarette rejection device for a splicing drum of a cigarette making machine, which comprises an air blowing block, an electromagnetic valve, a controller, and an air supply device, wherein the air blowing block is provided with a first protrusion and a second protrusion opposite to each other; the first protrusion is provided with a first air blowing hole, and the second protrusion is provided with a second air blowing hole; the first air blowing hole and the second air blowing hole are connected to two air suction holes one by one; the air blowing block is provided with a connecting hole connecting the first air blowing hole and the second air blowing hole; one end of the electromagnetic valve is connected to the air supply device, and the other end of the electromagnetic valve is connected to a first pipeline and a second pipeline, and the first pipeline and the second pipeline are connected to the connecting hole respectively; a round block is provided in the second pipeline, and a vent hole coaxial with the second pipeline is provided on the round block; the controller is used to be electrically connected to the V-valve opening and closing control system of the cigarette making machine, and the electromagnetic valve is electrically connected to the controller. The present invention can better reject cigarettes at the splicing drum when the cigarette making machine is started and stopped.

The invention relates to a non-woven fabric defective product removing device and an identification method, and belongs to the technical field of identification or measurement which is not specially used for specific variables, and the identification method comprises the following steps: step 1), taking a piece of non-woven fabric, spreading the non-woven fabric, and tensioning the non-woven fabric; step 2), acquiring a first plane deformation image of the non-woven fabric; step 3), acquiring a second plane deformation image of the non-woven fabric; step 4), evaluating the tearing condition of the non-woven fabric based on the first plane deformation condition of the non-woven fabric and the second plane deformation condition of the non-woven fabric; (5) the non-woven fabric is stopped from being tensioned, and whether the non-woven fabric has torn cracks or not is checked; the method has the beneficial effects that by evaluating the tearing condition of the non-woven fabric, tensioning of the non-woven fabric is stopped, whether the non-woven fabric has torn cracks or not is checked, and if the non-woven fabric does not have the torn cracks, the non-woven fabric is a good product; if the non-woven fabric has torn cracks, the non-woven fabric is a defective product, so that the rejection and identification of the defective non-woven fabric products are realized.

The present invention provides a drum-type stem cutting and screening device, which includes a frame, a drum screen arranged in the frame, rolling rings mounted on both ends of the drum screen, and a driving device. The drum screen is tilted so that it is lower on the left and higher on the right. The drum screen includes a material leveling section, a screening section, and a material discharging section that are sequentially connected from right to left; the screening section includes a plurality of wedge-shaped bars arranged in parallel, and each of the wedge-shaped bars is equally spaced and distributed around the axis of the drum screen; the cross-section of the wedge-shaped bar is an isosceles triangle structure, and the tip of the wedge-shaped bar faces the axis of the drum screen; the bottoms of the two ends of the wedge-shaped bar are respectively connected to the rolling rings through screws, and the screws are provided with a top fixing nut and a bottom fixing nut; a material receiving device is provided below the screening section. The present invention can conveniently adjust the spacing between two adjacent wedge-shaped bars according to the shape of the stem and the screening specification requirements, and can better meet different process requirements.

The utility model discloses a vibration screening device which comprises a screening assembly, the screening assembly comprises a first blanking area and a screening area, the screening area is located above the first blanking area, a second blanking area is arranged at the discharging end of the screening area, and the screening area screens materials in a vibration mode so that part of the materials can fall into the first blanking area; the other part of the material is conveyed to the second blanking area in the screening area in a vibrating manner; the second blanking area comprises a blanking guide groove and a blanking port, and the blanking port is located at one end of the blanking guide groove. Products and metal balls in the materials fall into the first blanking area in the screening area, and ceramic balls in the materials are conveyed to the second blanking area in a vibration mode, so that the ceramic balls are removed. The device can be widely applied to the technical field of material screening.