132results about How to "Accurate sorting" patented technology

The invention discloses an automatic fine ore sorting method and system based on XRT (X ray tomography) and hyperspectrum, which are used for realizing comprehensive fusion of ore surface and internal information by combining X-ray tomography and hyperspectral imaging technologies so as to improve the recognition precision and the sorting efficiency. XRT is used for extracting the internal structure and density characteristics of the ore, hyperspectral imaging is used for identifying the mineral composition characteristics of the ore surface, and information complementation is achieved. The system adopts a multi-modal convolutional neural network to perform independent feature extraction on XRT and hyperspectral data, and the extracted features are fused through a deep residual network. And the fused features are processed by a cross-modal attention mechanism to ensure that key features of different modals are fully integrated and optimized, and finally high-precision ore classification and sorting are realized. According to the method, the limitation of a single data source on feature extraction is overcome, the ore recognition and sorting precision is greatly improved, and the refined and intelligent development of ore sorting is promoted.

The invention belongs to the technical field of coal processing, and particularly discloses an intelligent coal gangue and coal quality sorting method and system based on an image hyperspectral technology, and the method comprises the steps: obtaining a hyperspectral image on a to-be-detected sample transmission line, converting the hyperspectral image into a grayscale image, and extracting the edge information of a to-be-detected sample; segmenting a spectral image of each to-be-detected sample, and extracting position information of each to-be-detected sample at the same time; determining the dynamic position of each sample to be detected; transmitting sound waves to each to-be-tested sample, and receiving sound wave signals passing through each to-be-tested sample; preprocessing the spectral image and the sound wave signal of each to-be-detected sample, and respectively extracting spectral features, texture features, spatial features and sound wave features to form a comprehensive feature vector; and inputting the comprehensive feature vector into a trained coal gangue recognition model to obtain a coal gangue and coal recognition result. According to the method, the sorting precision of the coal gangue and the coal quality is remarkably improved, so that the model can still keep relatively high recognition precision in a complex environment.

The invention discloses a high-precision metering and weighing system based on PLC control, relates to the technical field of metering and weighing, and realizes precise product weight measurement and sorting by combining a pressure sensor, a weighing module and a fuzzy PID control algorithm. The system can quickly convert the weight information of the product to be detected into a voltage signal, and after amplification and analog-to-digital conversion, an accurate digital signal is provided for the PLC. And the PLC performs error analysis and parameter adaptive adjustment by using a fuzzy PID algorithm, so that the control precision and the response speed are improved. In addition, through quantitative processing and use of a membership function, the system can effectively reduce errors and perform self-correction, and therefore the accuracy and reliability of overall weighing and sorting are improved. According to the invention, the weighing system can realize high-efficiency automatic control in industrial application, and can meet the weighing requirements of different products.

The invention discloses an intelligent coal gangue sorting method and system based on image deep learning, and belongs to the technical field of coal rock recognition. Global images and local images of coal gangue are obtained; preprocessing the global image and the local image to obtain a preprocessed global image and a preprocessed local image; fusing the preprocessed local image to the global image to obtain a fused image; and inputting the fused image into a target detection model based on a color feature attention mechanism, and carrying out detection and identification on coal and gangue to obtain an identification result. An image fusion technology is adopted to fuse a global image and a local image of coal gangue, so that coal gangue image information with rich details can be provided, a deep learning target detection model based on a color feature attention mechanism is adopted, coal and gangue can be accurately recognized, the recognition accuracy is improved by using color features, and the recognition efficiency is improved. And it is ensured that the sorting process is more accurate.

The invention discloses a position recommendation method, model and device based on a deep neural network model. The method comprises the steps that features and IDs are input into a shared embedding layer, the shared embedding layer carries out embedding operation on the input features and IDs, obtained public feature vectors are input into a public feature layer, and private feature vectors are input into a private feature layer; obtaining a common feature vector matrix based on the common feature layer; obtaining a private feature vector matrix based on the private feature layer; inputting the public feature vector matrix and the private feature vector matrix into an expert layer to obtain a predicted click probability and a transformation probability of the target position; inputting the public feature vector matrix and the private feature vector matrix into a gating layer to obtain a weight; and based on the click probability, the conversion probability and the weight of the target position, obtaining a target click probability and a target conversion probability of the target position, and further obtaining a sorting score of the target position. The position recommendation method and device are beneficial for improving the position recommendation accuracy and meeting personalized requirements of different scenes.

The invention discloses a coal gangue grading and sorting method and system based on LIBS (laser-induced breakdown spectroscopy) and image analysis, and relates to the technical field of coal gangue sorting, the method comprises the following steps: acquiring spectral data of each sample in a mixed coal flow comprising coal briquettes and coal gangue by using an LIBS technology; comparing the obtained spectral data with a pre-established coal briquette spectral database, preliminarily identifying coal briquettes and coal gangue according to a comparison result, and completing preliminary sorting; obtaining a visible light image of the separated mixed coal flow, preprocessing the image, inputting the preprocessed image into a coal gangue detection model based on an improved Mask RCNN, identifying and segmenting all coal gangues in the image, and obtaining the equivalent particle size of each coal gangue; and according to a preset particle size range, the coal gangue is divided into different grades, and the coal gangue in the mixed coal flow is classified and sorted. According to the invention, accurate identification of the coal gangue and grading sorting of the coal gangue can be realized.

The invention discloses a tray turning and sorting machine, a tray turning and sorting system and a sorting method.The tray turning and sorting machine comprises a tray turning and sorting trolley and an overturning driving assembly for driving a tray assembly of the tray turning and sorting trolley to overturn relative to a tray support; the tray bracket is arranged on a frame of the tray dumping and sorting trolley in a manner of rotating around an axis extending along the vertical direction; and the tray bracket is connected with a driving part and a resetting part, wherein the driving part is used for being matched with an autorotation driving mechanism outside the tray overturning and sorting trolley to drive the tray bracket to autorotate relative to the frame, and the resetting part is used for resetting the tray bracket after autorotation. The discharging direction of the tray overturning assembly can be adjusted, driving force generated by a sorting loop line on goods in the running direction can be overcome to a certain extent by adjusting the discharging direction, accurate sorting of the goods in a smaller grid opening size is facilitated, and meanwhile the speed of the loop line is increased so as to improve the sorting efficiency.

The automatic sorting and warehousing device comprises a conveying mechanism, a sorting mechanism, a stacking container, a stacking mechanism, a warehousing mechanism, a PLC and an upper computer, the conveying mechanism comprises a conveying belt, a gravity sensor is arranged below the conveying belt, the gravity sensor is connected with the PLC, the sorting mechanism comprises a sorting mechanical arm, and the sorting mechanical arm is connected with the upper computer. The sorting mechanical arm is located above the conveying belt, the sorting mechanical arm is connected with the PLC and controlled by the PLC, a photoelectric sensor and a camera client are arranged on the sorting mechanical arm, the stacking container is located between the sorting mechanical arm and the stacking mechanical arm, the stacking mechanism comprises a stacking mechanical arm, and the storage mechanism comprises a goods shelf. According to the corn cob sorting device, rapid and accurate sorting and storage of corn cobs can be achieved, compared with a traditional manual sorting mode, a large number of corn cobs can be processed within a short time, the labor cost is effectively reduced, and meanwhile sorting errors caused by human factors are reduced.

The invention discloses a commodity recommendation system based on artificial intelligence, and the system comprises a user behavior tracking module which is used for collecting and processing the multi-source behavior data of a user; the commodity feature extraction and fusion module is used for acquiring and analyzing multi-modal information of commodities; the dynamic updating module is used for adjusting a recommendation list in real time according to instant user behaviors and long-term preferences in combination with short-term memory and long-term memory; the situation awareness module takes external factors such as time, place and weather as input; the explanatory enhancement module is used for adding an explanatory layer for a black box model by using an explanatory machine learning model; the personalized sorting optimization module is used for dynamically adjusting the feature weight and improving the click rate and the conversion rate; and the privacy protection module is used for protecting user privacy by adopting a differential privacy technology. According to the commodity recommendation system and method provided by the invention, many problems existing in a traditional recommendation system are overcome, and a more efficient, more intelligent and safer commodity recommendation service is realized.

The invention belongs to the technical field of automatic sorting, and particularly relates to building waste reclaimed material automatic sorting equipment and method.The equipment comprises a vibrating feeder, a plurality of funnel-shaped material distribution grooves are formed below an ultrasonic atomization spraying device side by side, a belt conveyor is used for conveying building waste crushed materials, and the vibrating feeder is used for feeding the building waste crushed materials; a fluorescence detection box is arranged above the belt conveyor, connecting columns in one-to-one correspondence with the funnel-shaped material distribution grooves are arranged in the fluorescence detection box, ultraviolet lamps are arranged on the connecting columns, and photosensitive sensors are arranged on the rear sides of the ultraviolet lamps. According to the invention, through cooperation of fluorescence recognition feedback and high-pressure gas, building waste crushed materials are automatically sorted, building waste materials of different substances with similar density, size, color, shape and the like can be finely sorted, and the device has the characteristics of sensitive reaction, accurate distinguishing, high precision and the like.

The utility model provides a bagged chemical fertilizer conveying and warehousing device special for greenhouse crop special fertilizer, and aims to solve the problems that the loading quality of bagged chemical fertilizer does not meet the standard and the chemical fertilizer is not uniformly distributed. The device comprises a weighing conveyor, a roller floating type sorting machine, a first correcting conveyor, a second correcting conveyor and a control system. The weighing conveyor is used for weighing the bagged chemical fertilizer and sending weight information to the control system. If the weight is within a normal range, passing through a good product branch; otherwise, passing through the inferior product branch. The first correcting conveyor is provided with a plurality of check blocks used for correcting distribution of the chemical fertilizer in the packaging bag. The second straightening conveyor is a roller conveyor and is provided with two groups of staggered rollers, so that the stability of the chemical fertilizer in the conveying process is ensured. According to the device, the sorting efficiency and weighing accuracy of the chemical fertilizer are improved, manpower resources and time cost are saved, human errors are reduced, and the quality and competitiveness of products are improved.

The invention discloses a cross-belt sorting machine, a lifting sorting machine, a cross-belt sorting system and a sorting method.The cross-belt sorting machine comprises a circle of lifting sorting machine moving along a track, the lifting sorting machine comprises a lifting mechanism and a conveying assembly driven by the lifting mechanism to ascend and descend, and a rotation driving assembly is arranged on the lifting mechanism; the rotary driving assembly is provided with a conveying assembly so that the conveying assembly can horizontally rotate around the longitudinal axis perpendicular to the conveying face of the conveying assembly. The conveying direction of the conveying assembly can be adjusted during sorting, so that the parcels output by the conveying assembly can overcome inertia force borne by the parcels in the moving direction of the lifting sorting machine, and the moving direction of the parcels is closer to be perpendicular to the moving direction of the lifting sorting machine; in this way, the parcels can be accurately sorted under the smaller sorting grid openings, more sorting grid openings can be arranged under the same size, and / or on the basis of the sorting grid openings of the same size, the higher loop line running speed is adopted.

The invention relates to the technical field of coal mining, and particularly discloses an X-ray-based coal mine fine separation system which comprises a vibration feeding mechanism, a conveying mechanism, an imaging analysis module, an intelligent control module and a mechanical separation module, the imaging analysis module comprises an X-ray emission source and a detector, the vibration feeding mechanism comprises a vibrator, and the vibrator is connected with the conveying mechanism. The intelligent control module comprises a data acquisition module and an image processing and analyzing module, and the mechanical separation module comprises an execution mechanism. By arranging the X-ray technology, tiny differences between materials such as coal and gangue can be accurately recognized, and therefore high-precision sorting is achieved. The technology has the remarkable advantages that the materials do not need to be in direct contact, material pollution and damage possibly caused in a traditional sorting method are avoided, the integrity and quality of the materials can be kept in the sorting process, and the sorting efficiency and the resource utilization rate can be improved.

The utility model belongs to the technical field of sorting equipment, and particularly relates to an intelligent infusion bag sorting machine which comprises a rack, two transmission rollers are arranged on the rack, a belt is in transmission connection between the two transmission rollers, one end of one transmission roller is fixedly connected with an auxiliary fluted disc, the auxiliary fluted disc is meshed with a transmission chain belt, and the other end of the transmission chain belt is fixedly connected with a conveying belt. The chain belt is in transmission connection with a driving fluted disc, the driving fluted disc is connected to the output end of a servo motor, a portal frame is fixedly installed at the top of the rack, and an intelligent recognition camera is fixedly connected to one end of the portal frame. The infusion bag sorting device can quickly and accurately sort infusion bags, manpower and time are greatly saved, misjudgment caused by human factors is reduced due to the application of the intelligent recognition technology, sorting precision is improved, automation of infusion bag sorting is achieved, manual operation is reduced, labor intensity is lowered, and the production efficiency is improved. And the sorting work of the infusion bags is more orderly and efficient, and the overall working quality is improved.

The invention discloses an artificial intelligence sorting method and device based on multi-image fusion, and relates to the field of ore sorting. Acquiring a first wave band image, a second wave band image and an X-ray image of the target ore; the first waveband image is a visible light image; the second wave band image is a near-infrared image; scaling the first wave band image, the second wave band image and the X-ray image to obtain a multi-channel feature map; the multi-channel feature map serves as input of a pre-trained classification model, and the type of the target ore is obtained; and according to the type of the target ore, the target ore is conveyed to the corresponding receiving area. According to the method, the visible light image, the near-infrared image and the X-ray image are comprehensively analyzed and processed through the artificial intelligence classification model, multi-dimensional information can be fused, and therefore tiny differences of ores can be accurately distinguished, accurate sorting can be achieved even under the condition that the ore components are highly similar, and the ore sorting efficiency is improved. And the ore sorting accuracy and efficiency are remarkably improved.

The invention provides a character string identifier sorting method and system, and the method comprises the steps: obtaining the sortable content in a to-be-sorted character string identifier, and obtaining a sortable character string; sequencing the sequenced character strings according to a digital sequence; and taking a sorting result of the sortable character strings as a sorting result of the corresponding to-be-sorted character string identifiers. The method has the advantages that after the sorting method is applied, sorting of the file names or the webpage list identifications conforms to the habit of people for number sorting, and the reading efficiency is improved. When the sorting method is applied to the field of online education, teaching content can be accurately sorted, teaching resources can be optimized and organized, the discoverability of the resources can be improved, learning outline generation is supported, and the content organization and utilization efficiency of the education industry is integrally improved.

The utility model provides a kind of for coke coal pre-arrangement gangue intelligent dry method sorting equipment, it belongs to coal sorting technical field, wherein upper layer X-ray generator, upper layer beating device, lower layer X-ray generator and lower layer beating device are all installed on equipment rack, unified dust collector and control terminal are equipped;Upper layer X-ray receiver and lower layer X-ray receiver are respectively arranged in the inner cavity of upper layer sorting conveying device and lower layer sorting conveying device;Upper layer sorting conveying device and lower layer sorting conveying device all include transmission belt, transmission roller and driving motor, transmission roller is fixedly connected in the inner cavity of equipment rack by bearing.Compared with traditional single-layer photoelectric sorting equipment, the utility model uses upper and lower double-layer sorting structure, a single device can process two layers of coal simultaneously, greatly improves the processing capacity of coal, when facing a large number of coal sorting tasks, multiple devices do not need to be used simultaneously, saves sorting time, improves overall production efficiency.

The invention relates to the technical field of value evaluation, and discloses a high-performance multi-factor commodity value evaluation sorting method and system, and the method comprises the steps: obtaining transaction data recorded during commodity circulation; the commodities are classified, after first-level classification is obtained, re-classification is carried out, and second-level classification is obtained; respectively carrying out single-thread processing on each category in the first-level classification and the second-level classification; after each thread processes the respective batch, results are summarized to a central processing unit, final data fusion is carried out, and the commodity value is comprehensively evaluated; and generating a value sequence of the commodities according to a comprehensive evaluation result. And the performance bottleneck of traditional single-thread processing is overcome. By introducing a comprehensive scoring model and combining multi-dimensional factors such as sales volume, gross profit contribution and sales promotion activities, more comprehensive and accurate commodity sorting is realized.

The present invention discloses a glass sorting device and method, and a computer-readable storage medium, wherein the glass sorting device includes an AOI detection device, a material discharge position, and a controller, wherein the AOI detection device is provided with a discharge port, and the discharge port is connected to a conveyor belt; the outlet of the conveyor belt is connected to a uniformly driven docking line, and docking platforms are fixed on both sides of the docking line; the discharge port and the outlet of the conveyor belt are distributed around the docking platform; the docking line is connected to the conveyor belt and the corresponding docking platform, and the position where the material discharge position is connected to the docking platform is provided with sensors; the controller is electrically connected to the AOI detection device, the docking line, and the sensor, respectively. The present invention controls the AOI detection device, the docking line, and the sensor through the controller, and the sensor detects whether the glass product exists, so as to realize the classification of the glass from first to last according to the corresponding category, effectively replacing manual sorting, improving production capacity, and only requiring manual contactless production throughout the process, greatly improving the product yield rate.

The utility model discloses an automatic detection stacking conveyor line, and relates to the technical field of stacking conveyor lines, the automatic detection stacking conveyor line comprises a feeding guide rail, one side of the feeding guide rail is provided with an opening, the opening is fixedly connected with a detection sorting reversing arc table, the input end of the detection sorting reversing arc table is in butt joint with the opening, and the output end of the detection sorting reversing arc table is in butt joint with the opening. The output end of the detecting, sorting and reversing arc table is fixedly connected with a material returning guide rail, the material returning guide rail and the feeding guide rail are arranged in parallel, one side of the detecting, sorting and reversing arc table is fixedly connected with a supporting plate, the supporting plate is located between the material returning guide rail and the feeding guide rail, and the supporting plate is rotationally connected with a rotating shaft; according to the utility model, the servo motor is used for accurately controlling the rotation of the material shifting hand, unqualified materials can be accurately shifted from the feeding guide rail to the material returning guide rail, the sorting accuracy and reliability are improved, the unqualified materials are transferred to a reinspection area through the material returning guide rail, the further confirmation of the product quality is facilitated, the misjudgment is reduced, and the production efficiency is improved. And the product quality control level is improved.

The invention belongs to the technical field of wine brewing, and relates to a method for improving single-cell Raman sorting efficiency of grease microorganisms in fermented grains, which comprises the following steps: fermented grain microorganism extraction: taking fermented grains to prepare a plate bacterial colony; a plate bacterial colony is collected and subjected to fermentation culture in a culture medium, the culture medium is formed by mixing an IM culture medium and a JP culture medium, and the mixing volume ratio of the IM culture medium to the JP culture medium is 1: (3-5); and performing Raman spectrum detection. Fermentation culture is carried out through a culture medium formed by mixing an IM culture medium and a JP culture medium, fermented grain microbial oil performance expression is increased, fermented grain microbial single-cell groups tend to show oil production characteristics, target bacteria are rapidly and accurately screened out from a large number of microorganisms with complex varieties in fermented grains, and the yield of the fermented grains is improved. Interference of non-target microorganisms in the fermented grains is reduced, the sorting accuracy is improved, and rapid and accurate detection and sorting of grease microorganism single cells in the fermented grains are achieved.

The invention provides an intelligent logistics sorting system, and relates to the technical field of logistics sorting. The intelligent logistics sorting system comprises an article recognition system, a data processing system, an automatic sorting system, a conveying system, a monitoring system and a user interaction system. According to the article identification system, the advanced identification technology is adopted, and the information of the article can be rapidly and accurately identified; the data processing system analyzes the data provided by the article identification system based on a machine learning algorithm to realize automatic classification of articles; the automatic sorting system realizes automatic sorting according to the information of the articles; the conveying system is used for automatically conveying articles; and the monitoring system. By combining the advanced article recognition technology, the machine learning algorithm, the automatic mechanical arm and other modules, efficient and accurate sorting of logistics articles is achieved, the sorting efficiency is remarkably improved, the error rate of manual sorting is reduced, and huge economic benefits are brought to the logistics industry.

The automatic ballstone sorting and cleaning device comprises a conveying device, a sorting device in butt joint with the conveying device and a collecting device located under the sorting device, and further comprises a spraying and cleaning device arranged above the sorting device. Starting and stopping of the spraying cleaning device are synchronous with starting and stopping of the transmission motor; the sorting device comprises a transmission motor, a transmission connection structure and a drum screen which are in transmission connection in sequence; the drum screen is obliquely arranged from top to bottom; a cavity formed above the drum screen is a feed port for screening ballstones, and a cavity formed below the drum screen is a ballstone discharge port for sorting ballstones with corresponding particle sizes; according to the automatic ballstone sorting and cleaning device of the multiple rotary screens with the screen holes with the different hole diameters, grading conveying, butt joint and matching of ballstones are achieved through the conveying device according to the sequence of the screen holes from small to large, finally the ballstones sorted and cleaned through the recycling and collecting device are recycled, and the labor intensity is greatly reduced.

The invention relates to the field of ammeter detection, and discloses an intelligent ammeter quality detection system for a sorting platform, and the system comprises the steps: preliminarily screening out qualified returned ammeters, unqualified returned ammeters and to-be-detected returned ammeters from returned ammeters conveyed into a detection region; the power data of the to-be-detected returned ammeter and the historical power data are combined for comparative analysis, the difference change trend in the power transmission process is detected, the unqualified to-be-detected returned ammeter is screened out, analysis is carried out according to the energy efficiency data of the to-be-detected returned ammeter and the historical energy efficiency data, and whether the to-be-detected returned ammeter is qualified or not is judged. The qualified and unqualified returned ammeters are automatically sorted to the qualified area and the unqualified area, and the sorting result is fed back to the management personnel terminal, so that the energy efficiency and state of the ammeters are comprehensively analyzed and compared, the returned ammeters are more accurately screened and sorted, and the sorting efficiency and the sorting accuracy of the ammeters are improved.

A material arranging device is fixed to a workbench and arranged at the output end of a conveying part and comprises a channel assembly, a sorting sensor set and at least one distribution mechanism, and the channel assembly is communicated with the conveying part and extends in the advancing direction of workpieces; the distribution mechanism is fixed above the transmission part and is movably arranged relative to the transmission part; the conveyed workpieces are divided through the channel assembly arranged at the output end of the conveying part, so that the requirement that the multiple overturning parts work at the same time is met; by means of the distributing mechanism arranged above the conveying part, the workpieces in the conveying process can be distributed, then conveying channels and parallel conveying of the multiple workpieces are achieved, parallel operation of multiple operation procedures is achieved, and the efficiency of the machining equipment is remarkably improved.

The invention relates to the technical field of goods identification, in particular to a hanging channel machine for identifying hanging type goods in a three-dimensional warehouse in a streamlined mode and an identification method, and provides the following scheme that based on a hanging track system, radio frequency labels of the goods are read through a radio frequency scanner to generate a goods list, and appearance images of the goods are collected in combination with a main camera; and determining cargo sorting information and a storage position. A multi-camera system is used for collecting transportation images in real time, sorting information of goods and correctness of track distribution are verified, and if deviation occurs, track distribution is dynamically adjusted, and a conveying path is corrected. Goods storage and distribution are optimized through image segmentation, feature extraction, feature completion and a genetic algorithm, and logistics efficiency is improved. The hanging channel machine is integrated with a multi-sensor system, and efficient identification, sorting, sorting and path adjustment of goods are achieved.

The present invention discloses a flow group scheduling method in an optoelectronic hybrid data center network, and belongs to the field of network transmission technology. The method first divides the input traffic into flow groups according to business semantics, and then inputs the network topology structure. Secondly, based on the flow group information, the order of the flow groups is solved in combination with the characteristics of the optical circuit switch and the electrical packet switch port bandwidth to obtain an ordered flow group sequence. Finally, the flow groups and the sub-flows contained therein are scheduled according to the flow group sequence to optimize the transmission of the traffic in the optoelectronic hybrid network structure, reduce the completion time of the flow group transmission, and achieve the purpose of comprehensive optimization of the overall transmission. The present invention can optimize the scheduling and transmission process of the traffic in the optoelectronic hybrid structure, and can be applied to the scenarios of integrated services in data centers, etc.

This utility model provides a coin conveying mechanism for a high-speed coin sorting machine, including a support plate. The support plate has, sequentially, a central rotating wheel, a coin inlet wheel assembly, a cross-arm pressure wheel assembly, multiple single-swing arm pressure wheel assemblies, multiple double-swing arm pressure wheel assemblies, and a main drive wheel on its side, all connected in series via a synchronous belt to form a closed transmission chain. A coin sorting plate is located at the bottom of the support plate, with coin sorting slots on the plate. Guide rails are mounted on the sides of the coin sorting slots, and these guide rails are positioned opposite to the lower part of the synchronous belt. This utility model achieves high-speed, stable coin conveying and efficient sorting by optimizing the transmission and pressure wheel structure and combining it with the coin sorting plate guide rail design.

The invention discloses a DSE-YOLO v3-based fruit target identification method, and belongs to the technical field of artificial intelligence. The method comprises the following steps: step 1, constructing a data set of a fruit target; step 2, establishing a DSE-YOLO v3 network model; step 3, constructing a DSE-YOLO v3 network model; step 4, identifying fruit targets of large, medium and small scales; step 5, a DSE-YOLO v3 network model is trained; 6, determining an evaluation index of the fruit target recognition model; and step 7, testing effect verification. The DSE-YOLO v3 network disclosed by the invention compresses the network parameter calculation amount on the whole, pays more attention to different types of fruit target features in the process of generating the feature map, enhances the semantic information of the fruit features, effectively inhibits complex background information, and can solve the problem that the recognition precision is poor when the fruits are overlapped, shielded and densely distributed.

The invention belongs to the field of aviation part repair, and particularly relates to an intelligent screening and sorting method for aviation repair screw type small parts based on image recognition. The top camera, the side camera and the mechanical arm are used in cooperation, the bolts are dynamically recognized in a multi-angle mode, the top camera collects images when the bolts transversely fall on the working face, the images of the sizes and threads of the bolts can be effectively collected, and then the mechanical arm is used for clamping the bolts to the recognition area of the side camera; images of bolt head shapes, groove shapes and bolt tail marks can be effectively collected, so that the bolts can be recognized at multiple angles, and the problem of inaccurate recognition caused by bolt stacking and posture inclination is solved.