40results about How to "Low artificial dependence" patented technology

The invention discloses automatic fruit picking equipment. The automatic fruit picking equipment comprises a mechanical device, wherein the mechanical device comprises a machine seat and a picking device, and further comprises a collecting device and a discharging device; the picking device comprises a lifting rack, a lifting driving mechanism, a base frame, a translating driving mechanism, a clamping jaw assembly and a scissors assembly; the lifting rack is arranged on the machine seat; the base frame is arranged on the lifting rack; the clamping jaw assembly and the scissors assembly are arranged at the front end of the base frame; the collecting device comprises a guiding table and collecting mechanisms; the collecting mechanisms are separately arranged below two ends of the guiding table; each collecting mechanism comprises a table seat, a rotating plate and a rotary driving piece; each rotary driving piece is used for driving the corresponding rotating plate to rotate; and the discharging device is provided with a feeding opening and a discharging opening. The automatic fruit picking equipment is high in degree of automation, and can adapt to fruit picking in various environments; and a basket can be automatically changed when the collected fruits are arranged uniformly and the basket is filled with the fruits.

The invention discloses a live pig abnormal sound intelligent monitoring system and method. The system comprises a data acquisition layer, a data transmission layer and an intelligent monitoring layer. The data acquisition layer includes a pickup and an audio acquisition and encoding processor for collecting sounds in a pig house in real time and encoding collected signals; the data transmission layer transmits the collected sound signals to the intelligent monitoring layer through a wireless transceiver device; the intelligent monitoring layer includes a monitoring computer and an alarm device for processing, identifying and alarming the collected sound. The system has reasonable design, friendly human-computer interaction and high stability, improves the intelligent level of abnormal live pig monitoring, and reduces the degree of artificial dependence.

The invention relates to the field of electronic technology, and particularly relates to a video editing method and device. The method comprises the following steps: identifying audio frames included in a video file or a video stream to obtain a target audio frame of which the volume and / or voiceprint meets preset conditions, wherein the video file or the video stream also includes video frames corresponding to each audio frame; determining a display object for enhancing effects corresponding to the target audio frame; determining a corresponding target video frame according to the target audio frame; and adding the display object to an image of the target video frame. According to the video editing method and device disclosed by the invention, the technical effects of reducing the dependence degree of video editing on manual work and automatically editing the video file or the video stream can be achieved.

The invention provides a webpage data structured analytic method. The webpage data structured analytic method comprises the steps that a program which fetches information according to rules is written according to template webpages, and a training corpus is obtained; possible names of possible items to be structured are acquired through IDFs; a hidden markov model is trained through the training corpus, and parameters are determined; hidden markov model decoding is conducted on a webpage to be analyzed through a correlation algorithm, so that final structured data are acquired. The invention further provides a webpage data structured analytic device. The webpage data structured analytic device comprises a collection module, an acquisition module, a training module and a decoding module. According to the webpage data structured analytic method and device, operation is accomplished according to the intelligent analysis feature and the self learning feature of the model, domain experts do not need to pay more attention to the operation, the manual dependence degree is low, and the accuracy, the performance and the efficiency of analysis are greatly improved.

The invention discloses a video editing method for artificial intelligence education based on speech recognition. The method comprises the following steps: (1) inputting a teaching document and converting the teaching document into a script file which can be recognized by a system; (2) inputting an original teaching video material file, identifying an audio frame contained in the original teachingvideo material file, and identifying a target audio frame of which the voiceprint satisfies a preset condition; (3) comparing the video file subjected to voice recognition with a script file, and determining a video clip which does not conform to the teaching document and contains a target audio; (4) finding out and automatically deleting video clips which do not conform to the teaching documentin the video file subjected to voice recognition; (5) automatically rendering video clips including audio conforming to the teaching document, and synthesizing the video clips into a complete video; and (6) outputting the synthesized complete video. The invention also discloses a video editing system for artificial intelligence education based on speech recognition.

The invention discloses a train number automatic identification method and identification system. The system includes a camera, a light source, a wheel sensor and a processing unit, the wheel sensor transmits a triggering signal to the camera and the light source, and the camera transmits image information to the processing unit. The method provided by the invention includes the following steps: 1. image acquisition: after passing a line, wheels trigger the sensor to generate a signal, and the camera and the light source receives the signal to complete image acquisition; 2. train number positioning: the acquired image is preprocessed, coarse positioning and accurate positioning of the train number are performed, and thus train number positioning is completed; 3. train number identification: train number character segmentation is performed, the segmentation number (number) is recorded, and thus train number identification is completed; and 4. data transmission: train number positioning and identification results are transmitted to a terminal device to be stored and displayed. The train number automatic identification method and system can dynamically identify a moving train number, greatly reduce the manual work amount and a measuring error brought by manual work, and improve the accuracy rate and efficiency of train number identification.

The invention relates to a plastic part surface polishing automatic processing robot. The plastic part surface polishing automatic processing robot comprises a base plate, a top frame, a polishing device, a clamping device and a conveying device. The top frame is installed on the base plate, the polishing device is installed at the lower end of the top frame, the clamping device is arranged at thelower end of the polishing device, the conveying device is arranged on the inner side of the clamping device, and the clamping device and the conveying device are installed on the base plate. The polishing device comprises an installation frame, a rotating motor, a gear, a gear ring, polishing rings, connecting columns, supporting ring frames and supporting frames. The conveying device comprisesa connecting frame, a driving motor, a conveying disc, supporting columns and material placement bases. The plastic part surface polishing automatic processing robot can overcome the defects that in the existing cylindrical plastic part polishing process, the working efficiency is low, the manual dependence degree is high, the working cost is high, and the application range is small, and can fulfill the function of automatically polishing cylindrical plastic parts.

The invention discloses a wave recording fixed value remote online modification and check method and relates to the technical field of power systems. The method includes a protection working terminal operates and upload fixed value information to an operation working terminal; the operation working terminal operates and confirms the fixed value information uploaded by the protection working terminal; a server sends a fixed value list to a fixed value list system; the fixed values of wave recording devices in different areas are updated and sent back remotely to the server; a fixed value list sent back to the server is compared with the fixed value list sent by the server and modification and check of the wave recording fixed values are implemented. The method provided by the invention has characteristics of simple procedures, good time effectiveness, low human dependence degree and high efficiency.

The invention relates to traditional Chinese medicine decoction piece slicing equipment for air-drying lucid ganoderma. The traditional Chinese medicine decoction piece slicing equipment comprises a bottom plate, an infiltration device, an auxiliary device, a slicing device and a collecting device; the infiltrating device is sequentially installed on the bottom plate from left to right, an auxiliary device is installed at the lower end of the infiltration device, and the infiltrating device is installed in the middle of the bottom plate; the auxiliary device comprises a fixing frame, a liftingair cylinder, a water storage tank, a sponge and a cleaning mechanism; the auxiliary device comprises a moving mechanism, a connecting rod, a moving frame, a linear guide rail, a supporting mechanismand a limiting mechanism; and the slicing device comprises a supporting air cylinder, a mounting plate, a slicing mechanism and a cutting mechanism. The equipment can solve the problems that in the existing air-drying lucid ganoderma slicing process, the slicing difficulty is high, the manual dependence degree is high, and potential safety hazards exist, the working efficiency is low, the work cleaning degree is not ideal, and the like; and the function of automatic slicing of the air-dried lucid ganoderma can be realized.

The invention discloses a following type intelligent crack detection system for train wheels. The intelligent crack detection system consists of a data acquisition module, a communication module, a comprehensive control module and a cloud data transmission module. The invention also discloses a following type intelligent crack detection method for the train wheels. The following type intelligent crack detection method comprises the following steps that the data acquisition module completes the mapping of wheel inner information to operable data; the communication module completes the transmitting of the data; the comprehensive control module completes the sending of an instruction, and the processing and the storing of the data; and the cloud data transmission module completes the backdating of initial data and the sharing of alarming data. Compared with the prior art, the following type intelligent crack detection system disclosed by the invention has the beneficial effects that the efficiency and the accuracy of detecting cracks in an online and real-time manner are improved, data sharing and informationization management are facilitated, and the following type intelligent crack detection system conforms to the developing trend of big data, and is convenient to quickly mount.

The invention relates to a surface treatment device and treatment method for PVC plastic parts. The surface treatment device comprises a bottom plate, a top frame, a grinding device, a clamping deviceand a conveying device. The bottom plate is provided with the top frame, the grinding device is installed at the lower end of the top frame, the clamping device is arranged at the lower end of the grinding device, the conveying device is arranged on the inner side of the clamping device, and the clamping device and the conveying device are both installed on the bottom plate. The conveying devicecomprises connecting frames, a driving motor, a conveying plate, a supporting column, placing seats, blocking plates, a pushing frame and receiving boxes. The surface treatment device for the PVC plastic parts can solve the problems that existing PVC cylindrical plastic parts have low working efficiency, high manual dependence degree, high working cost, small use range and the like in the grindingprocess, can realize the function of automatic grinding of the PVC cylindrical plastic parts, and has the advantages of improving the work efficiency, reducing the manual dependence degree, reducingthe work cost, expanding the use range and the like.

The invention relates to the technical field of cable arrangement, and discloses an automatic cable arrangement device and method based on image recognition. The device comprises a driving mechanism, a main installation frame, a camera, a cable arrangement mechanism, and a control module, wherein the driving mechanism and the cable arrangement mechanism are arranged on the main installation frame, the main installation frame is located on one side of a main cable storage disc, the cable arrangement mechanism is used for reversing and guiding an introduced umbilical cable and winding the umbilical cable around the main cable storage disc, the camera is used for collecting video data of a cable outlet of the cable arrangement mechanism and video data of the main cable storage disc and transmitting the video data to the control module, the control module conducts image processing on the received video data to obtain control information and outputs the control information to the driving mechanism, and the driving mechanism drives the cable arrangement mechanism to move in parallel in an axial direction of the main cable storage disc according to the control information. According to the device, uniform arrangement of the cable can be automatically realized, the arrangement quality of the cable is greatly improved, the loss of the cable caused by uneven arrangement is avoided, and the service life of the cable is effectively prolonged.

The invention relates to the field of automatic spraying, in particular to a BMC line spraying system and spraying process. The system comprises a feeding station used for feeding of products obtainedafter injection molding, a preliminary trimming station used for carrying out preliminary trimming on the products, a fine trimming station used for carrying out secondary trimming on the products, adust removal station used for carrying out dust removal on the products obtained after trimming, a UV pretreatment station used for carrying out UV pretreatment on the products obtained after dust removal, a paint spraying station used for carrying out paint spraying on the products obtained after UV pretreatment, a buffer leveling station used for carrying out buffer leveling on the products obtained after paint spraying, a UV curing station used for carrying out UV curing on the products obtained after buffer leveling and a discharging station used for cooling and discharging the products obtained after UV curing. The system further comprises a control station used for control. The BMC line spraying system and spraying process are low in manpower dependency degree, high in automation degree and working efficiency, good in spraying quality, high in product percent of pass and small in occupied area.

The invention discloses a train wheel tread defect and out-of-roundness three-dimensional image pass-type detection system. The system comprises an acquisition module, a speed measurement control module, a motor moving module and a data processing module, the motor moving module is fixed on track beds on two sides of a track, and the acquisition module and the speed measurement control module aremounted on the motor moving module. The acquisition module acquires a wheel tread profile in a process of synchronously moving with a wheel, and acquires one profile at a minimum interval of 1 mm through speed measurement detection control, and an image is compressed through a preprocessing module in the acquisition process, and then is transmitted to the image processing module in time; the speedmeasurement control module measures the wheel speed and provides the wheel speed for the motor moving module; the motor moving module drives a motor to work in time according to the signal of the speed measurement control module, so that the acquisition module moves in time and keeps consistent with the wheel advancing speed; and the data processing module processes the image data compressed by the acquisition module, synthesizes the image data into a three-dimensional image of the wheel tread, and calculates out-of-roundness and tread defects.

The invention discloses a live pig diet abnormity intelligent monitoring method and a live pig diet abnormity intelligent monitoring system. The system comprises a live pig diet data acquisition layer, a live pig diet data transmission layer and a live pig diet abnormity intelligent monitoring layer. The live pig diet data is uploaded to the live pig diet abnormity intelligent monitoring layer through the Ethernet of the live pig diet data transmission layer. The live pig diet abnormity intelligent monitoring layer processes, judges, displays and alarms the acquired diet data. The system is reasonable in design, low in cost, simple in structure, small in size, high in stability, not prone to being influenced by environmental factors and friendly in man-machine interaction. The intelligentlevel of live pig diet abnormity monitoring is improved. The manual dependence degree is reduced, and the live pig diet abnormity monitoring efficiency is improved.

The invention relates to the technical field of mask production, and in particular, relates to a mask detection mechanism. A mask detection mechanism in the prior art is complex in structure, and a qualified mask can be damaged to a certain extent when the mask detection mechanism is used. For solving the problem, the following technical scheme is adopted: the mask detection mechanism comprises aconveying belt and a mask detection assembly, the mask detection assembly comprises a detector and a data processing device which are arranged above the conveying belt, the detector is in communication connection with the data processing device, and the data processing device can identify a defective mask through the signal transmitted by the detector. According to the technical scheme, the detection mechanism can be smoothly connected with a production line, automatic defective mask screening can be achieved, the structure is simple, and the manual dependence degree is low.

The invention discloses a girth welding device and girth welding method for tubeless engineering rims. The girth welding device comprises a base and four electric welding devices, each electric welding device comprises a welding gun, a rim supporting seat is arranged on the base, a welding position is arranged on the rim supporting seat, a liftable electric conduction pressing wheel is arranged above the welding position, and the electric conduction pressing wheel is electrically connected with all the electric welding devices. The girth welding method comprises the steps of pre-welding, feeding, welding gun in-place, girth welding and discharging. According to the girth welding device and girth welding method for the tubeless engineering rim, a simultaneous staggered girth welding mode is adopted for welding, the welding efficiency of the tubeless engineering rim is improved, the problem of the simultaneous welding process of multi-section workpieces is solved, and the welding quality of the rim can be effectively ensured. Feeding and discharging of the girth welding device are convenient and fast, and the manual dependence degree in the welding process is further reduced.

The invention discloses a target guide approaching control method and system for an underwater autonomous vehicle, relates to the technical field of underwater autonomous vehicle control, and the method and the system can improve the online recognition capability of the vehicle, perform task re-planning after finding a suspected target, and ensure the underwater autonomous path planning and target guide approaching functions of the underwater vehicle. According to the technical scheme of the invention, the method and the system are used for achieving the recognition, processing and guided approaching of an underwater target by the autonomous underwater vehicle. The method comprises the following steps: the autonomous underwater vehicle autonomously sails underwater according to a pre-planned route; a forward-looking sonar detects the navigation area of the autonomous underwater vehicle to obtain a sonar image; and the image processor performs online processing on the sonar image and outputs the position information of the underwater target to the control unit in real time; the control unit carries out task re-planning according to the position information of the underwater target, and the autonomous underwater vehicle sails according to an air route obtained through re-planning and is guided to approach the target.

The invention discloses a digital television front-end platform operation and maintenance monitoring and analysis system, which comprises a server, an acquisition end and a display end, and is characterized in that the server comprises short message alarm equipment and a server carrying a database and a service platform system, and can store, monitor, alarm and statistically analyze data of digital television platform equipment; the acquisition end monitors monitored equipment and acquires data information through an acquisition probe, and a management host of the display end monitors the operation state of platform equipment and acquires acquired data by displaying and checking a service platform system, so that intensive management of the front-end platform equipment of the digital television is realized, and the equipment maintenance efficiency is improved. The system is low in manual dependence degree and high in timeliness, alarm information can be obtained through the management host and the short message alarm device when the device breaks down or is abnormal, the fault device can be found in the first time, operation and maintenance work can be rapidly carried out, meanwhile, data of the collection device can be managed and analyzed, and the use efficiency of the data is effectively improved.

The invention provides a novel grinding part. The grinding part is of a cylindrical structure, a abrasive particle layer, a flexible base material layer and a hollow shaft structure are sequentially arranged from outside to inside, the abrasive particle layer is arranged on the flexible base material layer, the hollow shaft structure is wrapped by the flexible base material layer, and the grindingpart is arranged on the corresponding grinding device through the hollow shaft structure. According to the grinding part, the cylindrical side surface serves as a grinding contact surface, so that the linear speed of abrasive grains during grinding is relatively consistent, and the abrasive grain layer is in matched contact with the curved surface of a product to be machined through the flexiblebase material layer, so that uniform grinding is realized, and the grinding effect is ideal. The invention further provides the automatic grinding device. The grinding device comprises a machine frame, a power part and the grinding part, wherein the power part and the grinding part are installed on the machine frame, the power part is in driving connection with the grinding part so that the grinding part can rotate at the set rotating speed, cleaning cooling water can be applied to one side of the grinding part, the surface temperature of a ground workpiece is effectively reduced, and scraps are removed in time.

The invention discloses a tunnel detection method and device based on an unmanned aerial vehicle. The method comprises the following steps: receiving a video image of a tunnel acquired by the unmanned aerial vehicle; performing preprocessing and standardization processing on the video image; and inputting the preprocessed and standardized video image into a trained three-dimensional convolutional neural network (3D-CNN) model, wherein the three-dimensional convolutional neural network model outputs a tunnel disease detection result according to the video image. According to the method, the video image of the tunnel is acquired through the unmanned aerial vehicle, and the video image is input into the trained three-dimensional convolutional neural network model, so that the space and time features in the video can be better captured, the tunnel disease detection result is quickly output, the recognition rate, the detection frequency and the processing speed of the tunnel disease are improved, and the manual dependence degree is reduced.

The invention discloses a pig diet abnormal intelligent monitoring method and system, comprising a pig diet data acquisition layer, a pig diet data transmission layer, and a pig diet abnormal intelligent monitoring layer; the pig diet data is uploaded to the pig through the Ethernet of the pig diet data transmission layer Intelligent monitoring layer for abnormal diet; the intelligent monitoring layer for abnormal diet of pigs processes, judges, displays and alarms the collected dietary data. The invention is reasonable in design, low in cost, simple in structure, small in size, high in stability, not easily affected by environmental factors, friendly in human-computer interaction, improves the intelligence level of pig diet abnormality monitoring, reduces manual dependence, and improves pig diet Anomaly detection efficiency.

The invention discloses a tunnel detection method and device based on an unmanned aerial vehicle. The method includes: receiving a video image of a tunnel obtained by an unmanned aerial vehicle; performing preprocessing and standardization processing on the video image; The processed video image is input into a trained three-dimensional convolutional neural network (3D-CNN) model, and the three-dimensional convolutional neural network model outputs a tunnel defect detection result according to the video image. The invention obtains the video image of the tunnel through the drone, and inputs the video image into the trained three-dimensional convolutional neural network model, which can better capture the spatial and temporal characteristics of the video, and quickly output the tunnel defect detection result , improve the identification rate, detection frequency and processing speed of tunnel diseases, and reduce the degree of manual dependence.

The invention relates to the technical field of drilling machines, and provides an automatic drilling machine capable of feeding, which is low in degree of dependence on manpower in the feeding and discharging processes, can realize automatic positioning after feeding, is relatively good in universality of a positioning assembly, is relatively practical, can be automatically loosened after machining is completed, is relatively high in degree of automation, is convenient to form assembly line type production, and is suitable for large-scale production. The automatic drilling machine is high in overall machining efficiency and comprises an automatic drilling machine body, the automatic drilling machine body is provided with a workbench, the automatic drilling machine further comprises an assembly line conveying belt, the assembly line conveying belt is installed on the automatic drilling machine body through a driving roller assembly and a driven roller assembly, a plurality of pressing-in openings are formed in the assembly line conveying belt, and a tight supporting assembly is installed in the automatic drilling machine body. Four lifting rods are connected to the workbench, lifting electric rods are installed between the four lifting rods and the automatic drilling machine body, a front pressing roller is connected between the two lifting rods, close to the front side, of the four lifting rods, and a rear pressing roller is connected between the two lifting rods, close to the rear side, of the four lifting rods.

The invention provides a UUV deployment and recovery protection device, comprising: a boom installation interface plate, a hanging plate, a movable inner ring, a fixed outer ring, a horizontal vibration isolator, a support frame, an annular vibration isolator and a protective frame. The use of this protection device can effectively avoid the shaking and swinging of the UUV carrier during the UUV deployment and recovery operation, and at the same time, it can reliably absorb the impact caused by the swing and shaking belt on the UUV carrier, reducing the manual dependence of the deployment and recovery process. Reducing the demand for manpower can also improve the safety of deployment and recovery operations, reduce the risk of collision of UUV carriers, and achieve effective protection of UUV carriers during deployment and recovery under high sea conditions.

An ultrasonic detection system for a hollow axle of an EMU mainly includes: a probe rod module, a motor control module, a UT (ultrasonic flaw detection) module and user software. The working process of the system is as follows: After logging in the user software, configure the detection shaft type and detection parameters, and drive the two motor modules to run. The motor module drives the rotation motor and the feed motor, the rotation motor drives the rotation of the probe rod, and the feed motor drives the movement of the probe rod through the hinge. Multiple probes of different types are installed at different positions on the probe rod. The probe is controlled by the UT module, which receives the reflected ultrasonic waves after sending them, and uploads the ultrasonic flaw detection data to the user software. After the data processing and transformation of the user software, the system can display the A-scan and intuitively draw the B-scan and C-scan, so that it can quickly judge the existence of defects, the location and size of internal defects, and has storage, playback, View and other functions.

The invention discloses a device for dynamically measuring X-ray film density, and belong to the field of industrial X-ray film density measurement. The device overcomes the shortcomings that a traditional density measuring device is mainly used for single-point measurement and not applicable to density detection of large-scale films, and measurement processes are complicated. Illumination is collected based on multi-sensors, an ingenious structure is designed, multi-area, high-accuracy and high-speed dynamic measurement of a film density value is achieved by an automatic nondestructive transmission principle of a belt and signal processing of high-performance chips, rapid quality judgment of the large-scale films required by industrial film review occasions can be met, so that smooth implementing of subsequent processing of the films is ensured, and film processing efficiency is improved.

The invention discloses an automatic brocade spinning device and method, and aims to solve the technical problems that brocade cannot be automatically spun, the efficiency is low and the cost is high in the prior art. The device comprises a specially-made weft tube box and mechanical claw arms; the weft tube box is installed at the front end of a spinning rack, and the mechanical claw arms are installed on the two sides of the weft tube box; the weft tube box comprises an uncovered box body, weft tube clamping seat columns, weft tubes and sliding rail clamping grooves; the sliding rail clamping grooves are fixed to the bottom of the uncovered box body; the weft tube clamping seat columns are movably connected with the sliding rail clamping grooves; the weft tubes are installed on the weft tube clamping seat columns; the plurality of weft tubes can be installed in the weft tube box; and the weft tubes can move in the weft tube box through the sliding rail clamping grooves. The problem that the number of wefts is relatively large in brocade spinning can be solved, automatic brocade spinning is achieved, and the brocade spinning efficiency is improved.

The invention relates to an automatic slicing machine for traditional Chinese medicine decoction pieces of lucid ganoderma for medical rehabilitation and health care. The automatic slicing machine forthe traditional Chinese medicine decoction pieces of the lucid ganoderma for medical rehabilitation and health care comprises a bottom plate, an impregnating device, an auxiliary device and a slicingdevice, wherein the impregnating device and the slicing device are sequentially arranged on the bottom plate from left to right; the auxiliary device is arranged at the lower end of the impregnatingdevice and is arranged in the middle of the bottom plate; the impregnating device comprises a fixing frame, a lifting air cylinder, a water storage tank, a sponge and a cleaning mechanism; the auxiliary device comprises a moving mechanism, a connecting rod, a moving frame, a linear guideway, a bearing mechanism and a limiting mechanism; and the slicing device comprises a support air cylinder, an installation plate, a slicing mechanism and a dividing mechanism. The automatic slicing machine for the traditional Chinese medicine decoction pieces of the lucid ganoderma for medical rehabilitation and health care provided by the invention can solve the problems of big slicing difficulty, high artificial dependency level, potential safety hazard, ideal working cleanliness and the like, can realize a function of automatically slicing the lucid ganoderms, and has the advantages of small slicing difficulty, low artificial dependency level, high working safety, high cleanliness and the like.