专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明专利

GB2581669B Seakeeping unmanned ship with water surface self-adaptive stabilizer 未知
公开(公告)号：GB2581669B
公开(公告)日：2022-05-11
申请号：GB202006069
申请日：2019-07-15
申请人： UNIV HOHAI
发明人： PENGFEI XU , YANXU DING , YALIN SHEN , WENBIN CHENG , HONGXIA CHENG , JIACHENG LUO
IPC分类号： B63B39/00 , B63B35/00
摘要： A seakeeping unmanned boat provided with a water-surface self-adaptive stabilizer. The unmanned boat is of a catamaran type and comprises an upper deck (1), floating bodies (7) separated from the upper deck (1) and the self-adaptive stabilizer; the floating bodies (7) provide buoyancy for the unmanned boat and are provided with propelling devices (8); the floating bodies (7) are two floating bodies that are completely bilaterally symmetric; a tilt angle sensor, an accelerometer and a gyroscope are provided on the upper deck (1) and are used to acquire the rotating angle of the upper deck (1) and an angular acceleration prediction and tendency and to transmit the same to a control system in real time; and the self-adaptive stabilizer comprises a suspension system and a balance control mechanism (6).

12. 发明专利

LU500782B1 A BIG DATA MINING-BASED SHIP SPEED PREDICTION AND SAFETY SPEED CONTROL METHOD 未知
公开(公告)号：LU500782B1
公开(公告)日：2022-04-25
申请号：LU500782
申请日：2021-10-25
申请人： UNIV HOHAI
发明人： SHEN CAIHUA , ZHANG WEI , CHU MINGSHENG , WANG YEZHAO
IPC分类号： G06F30/20 , B63J99/00 , G06N3/04
摘要： The invention relates to a big data mining-based ship speed prediction and safety speed control method. According to the method, first a sample database of a plurality of influencing factors having influences on navigation of a ship in plain river network waterways is collected; then a fully connected deep learning neural network model is constructed, and by taking a prediction precision as a control target, initial parameters are optimized; comparative analysis is carried on prediction precisions of 10 the plurality of influencing factors under different combinations by means of the optimized fully connected deep learning neural network model, and an optimal combination of influencing factors is selected; based on the data sample of the optimal combination of influencing factors, by taking a prediction precision as a target.

13. 发明专利

GB2565931B Integrated sensing system and method for sensing seepage behavior of water engineering structures 未知
公开(公告)号：GB2565931B
公开(公告)日：2021-10-27
申请号：GB201818976
申请日：2016-10-25
申请人： UNIV HOHAI
发明人： HUAIZHI SU , MENG YANG , CHONGSHI GU
IPC分类号： G01M3/00 , G01M3/04 , G01M3/38
摘要： Provided are a water engineering seepage behavior fusing and sensing system and method. The system comprises a seepage-hidden optical fiber locating device, a seepage flow velocity distributed optical fiber monitoring device, an online seepage line diagnosis device and a seepage behavior optical fiber self-adaptive identification device, the location of a water engineering seepage point is realized by using the seepage-hidden optical fiber locating device, then, the seepage flow velocity of a water engineering is monitored by virtue of the seepage flow velocity distributed optical fiber monitoring device, the online diagnosis of a seepage line on a section of a whole water engineering structure can be realized by using the online seepage line diagnosis device, and finally, the current seepage behavior is integrally monitored and evaluated by using the seepage behavior optical fiber self-adaptive identification device, so that the water engineering seepage behavior fusing and sensing is completed. The optical information change of the optical fiber is acquired from multiple aspects and angles by using the four water engineering seepage monitoring devices, depending on the material and mechanical properties of the water engineering and relying on a distributed optical fiber monitoring technology, and furthermore, the monitoring and sensing of a seepage behavior of a water engineering are indirectly completed.

14. 发明专利

GB2593960A 3-D imaging apparatus and method for dynamically and finely detecting small underwater objects 未知
公开(公告)号：GB2593960A
公开(公告)日：2021-10-13
申请号：GB202020689
申请日：2020-12-29
申请人： UNIV HOHAI
发明人： PENGFEI XU , JIACHENG LUO , ZICHENG REN , YUE ZHANG , MAOFEI CHEN , HONGXIA CHENG
IPC分类号： G01B11/25
摘要： A three-dimensional imaging apparatus for dynamically and finely detecting an underwater small object, including a platform 3, where a laser emitting module and underwater cameras 1 are fixedly mounted on the platform, and the underwater cameras 1 are connected to a processing unit 5. The apparatus preferably being located on the underside of an underwater robot 8. The laser emitting module may be an array or a single line laser. There are preferably two cameras located on either side of the laser emitting unit. The three-dimensional imaging preferably comprises applying a difference colour to a range in the image.

15. 发明专利

ZA202007526B A COMPREHENSIVE INTERPOLATION METHOD FOR DAILY PRECIPITATION DATA 未知
公开(公告)号：ZA202007526B
公开(公告)日：2021-06-30
申请号：ZA202007526
申请日：2020-12-03
申请人： UNIV HOHAI
发明人： WEN WANG , RAN PANG , JINGJING SUN

16. 发明专利

AU2021102397A4 METHOD FOR TARGET DETECTION ORIENTED TO DAM DEFECT IMAGES 未知
公开(公告)号：AU2021102397A4
公开(公告)日：2021-06-24
申请号：AU2021102397
申请日：2021-05-07
申请人： UNIV HOHAI
发明人： MAO YINGCHI , QIAN JUN , LIU YI , PING PING , LI YUAN , XU SHUFANG , WANG LONGBAO
IPC分类号： G06T7/00 , G06K9/00 , G06K9/62
摘要： The present disclosure discloses a method for target detection oriented to dam defect images, comprising: applying deformable convolution to a VGG16 network, expanding the convolutional sensing range, and capturing deformation features of dam defects by learning convolution offset so as to obtain a feature map of defect images; during the multi-scale feature map detection, modifying the size proportion of a prior box in the anchor mechanism to improve the detection accuracy of strip-shaped defect features and the generalization capability of the model; adopting an improved non-maximum suppression algorithm to screen out redundant negative samples, so that the diversity of training samples is ensured as much as possible on the premise of balancing the ratio of positive and negative samples. According to the present disclosure, effective detection is performed for the dam defect images, so as to both realize the detection of multi-deformation defect features and further improve the generalization capability of strip-shaped defect detection. The present disclosure shows a higher detection precision and a better convergence performance in the target detection for the dam defect images.

17. 发明专利

GB202105078D0 Sluice gate testing apparatus and testing method based on phased array ultrasonic flaw detector 未知
公开(公告)号：GB202105078D0
公开(公告)日：2021-05-26
申请号：GB202105078
申请日：2018-11-09
申请人： UNIV HOHAI
摘要： Disclosed in the present invention are a sluice gate testing apparatus and a testing method based on a phased array ultrasonic flaw detector. The testing apparatus comprises a testing mechanism, the testing mechanism comprising a support frame. A guide wheel and two drive wheels are provided on the bottom of the support frame, the drive wheels being driven by means of a first electric motor, and a controller and a phased array ultrasonic flaw detector are provided on the support frame. During the testing process, a second electric motor drives a rotating platform to rotate, driving a rotating arm to rotate in an upper region of a fan-shaped through hole; simultaneously, a third electric motor drives a leadscrew to rotate, driving a sliding block and an ultrasonic phased array matrix probe to move along the leadscrew in the length direction; that is, while the ultrasonic phased array matrix probe moves in the width direction of a sluice gate, the probe also sweeps at a certain angle, and is thus able to perform testing on a large area of the sluice gate simultaneously; and a testing signal from the ultrasonic phased array flaw detector is passed to the controller. The present invention uses phased array ultrasonic technology, and features high testing efficiency and high testing accuracy.

18. 发明专利

GB202020689D0 3-D imaging apparatus and method for dynamically and finely detecting small underwater objects 未知
公开(公告)号：GB202020689D0
公开(公告)日：2021-02-10
申请号：GB202020689
申请日：2020-12-29
申请人： UNIV HOHAI
摘要： A three-dimensional imaging apparatus for dynamically and finely detecting an underwater small object, including a platform 3, where a laser emitting module and underwater cameras 1 are fixedly mounted on the platform, and the underwater cameras 1 are connected to a processing unit 5. The apparatus preferably being located on the underside of an underwater robot 8. The laser emitting module may be an array or a single line laser. There are preferably two cameras located on either side of the laser emitting unit. The three-dimensional imaging preferably comprises applying a difference colour to a range in the image.

19. 发明专利

CA3066668C ANNULAR MULTI-LEVEL FREE-FALL-TYPE ENERGY-DISSIPATING VERTICAL SHAFT 未知
公开(公告)号：CA3066668C
公开(公告)日：2020-10-13
申请号：CA3066668
申请日：2018-01-26
申请人： UNIV HOHAI
发明人： ZHANG RUI , XU HUI , CHEN YULING , FENG JIANGANG , WANG XIAOSHENG
IPC分类号： E02B8/06
摘要： An annular multi-level free-overfall-type energy-dissipating vertical shaft, comprising an inner shaft and an outer shaft that are arranged coaxially. A water inlet culvert is connected at top of the outer shaft. Two deep tunnel drainage pipes pass through bottoms of the outer shaft and the inner shaft. Between the inner shaft and the outer shaft, in a vertical direction, is provided a plurality of horizontal drop layers, arranged in an alternating manner, forming an annular, multi-level alternating discharge channel. Each horizontal drop layer, excluding the top layer, is provided with two curved drop plates, symmetrically distributed about a center of rotation along an axis of the energy-dissipating vertical shaft.

20. 发明专利

NZ750970A Memory-guide simulated pattern recognition method 未知
公开(公告)号：NZ750970A
公开(公告)日：2020-06-26
申请号：NZ75097016
申请日：2016-12-08
申请人： UNIV HOHAI
发明人： CHEN ZHE , WANG ZHIJIAN , HU WENCAI , WANG XIN
IPC分类号： G06T7/20 , G06K9/68
摘要： A memory mimicry guided pattern recognition method, wherein time series information in the memory prior to the current moment is introduced to detect motion information by means of pattern recognition using samples in the series as a reference. The memory invocation mechanism in a human brain is simulated, and different memory segments are used as elements to detect motion changes in multiple memory segments and their corresponding motion states. The memory attenuation mechanism is simulated, and the motion detection results in the multiple segments are combined to enhance motion change information in the current moment and to form a motion state in a continuous time series, so as to form a motion detection result of the current moment as a pattern recognition result. The method can be used stably and reliably for pattern recognition and motion detection under complicated conditions, has a better noise suppression effect and a higher computational efficiency.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式