69 results about "Sonar sensor" patented technology

The invention relates to the technical field of channel monitoring, and discloses an unmanned aerial vehicle water depth monitoring method for channel inspection. The method comprises the following steps: deploying an unmanned aerial vehicle to a target channel area, initializing a carried sonar sensor, a camera and a positioning module, and planning a flight path to cover a to-be-detected point according to a preset algorithm; water depth and image data are collected in real time during flight, position information is obtained, multi-modal monitoring data are formed through space-time alignment, a water depth fusion model is input to generate a channel water depth distribution diagram, an abnormal area is recognized through an abnormal detection model, and finally the position and water depth data of the abnormal area are encrypted and transmitted to a ground control terminal. The method improves the efficiency and accuracy of channel water depth monitoring, can timely discover the abnormality, guarantees the safety and smoothness of the channel, and provides an effective technical means for channel management.

The invention discloses a dredging method of a robot for a nuclear power seawater pump room, the robot, a storage medium and a program product, and the method comprises the steps: receiving a task instruction corresponding to a dredging task of the nuclear power seawater pump room, and collecting environment image data through an image collection device arranged on the robot, environmental sonar data are collected through a sonar sensor; according to the task instruction, the environment image data, the environment sonar data and a task planning model, determining a plurality of sub-tasks and environment feature data corresponding to the dredging task; and determining associated feature data according to the plurality of sub-tasks, the environment feature data and a feature fusion model, and determining a target dredging path corresponding to the dredging task according to the associated feature data, a preset constraint condition of the robot and a path planning model. According to the technical scheme, the safety, efficiency and intelligent level of the dredging operation of the robot in the nuclear power seawater pump room can be effectively improved.

The invention discloses a hydraulic structure superficial defect identification method for an underwater robot, and belongs to the technical field of underwater robots, and the method comprises the steps: respectively obtaining first distance information and second distance information, fed back by a sonar sensor and a laser sensor, between the underwater robot and a hydraulic structure superficial defect in the moving process, image information, fed back by the binocular camera, of superficial defects of the hydraulic structure is obtained; inputting the obtained first distance information, the second distance information and the image information into a pre-trained deep learning network model to obtain a superficial defect identification result of the hydraulic structure; on one hand, the problems that a traditional underwater robot is low in hydraulic structure defect recognition and evaluation efficiency and low in accuracy are solved; and on the other hand, the influence of the underwater complex environment on diagnosis is reduced, and the robustness and stability of the system are improved.

In various examples, associating object detections for sensor data processing for autonomous and semi-autonomous systems and applications is described herein. Systems and methods described herein may group object detections (e.g., echoes, etc.) that are detected using multiple sensors (e.g., ultrasonic sensors, sonar sensors, etc.) and then use the groupings to process the object detections to perform one or more tasks, such as object or feature detection. In some examples, the object detections are grouped using one or more configurations, such as an order associated with analyzing sensor data generated using the sensors and / or threshold distances associated with determining that object detections are associated with the same object. Additionally, a respective group may be generated for one or more (e.g., each) detected object such that the locations of the object surrounding the machine may be determined.

The invention relates to the technical field of image processing, and discloses a fish school target tracking and cruise calculation method based on a sonar image, and the method comprises the steps: obtaining a sonar video set and a parameter set collected by a sonar sensor array, and carrying out the equal-time-interval frame decoding processing, and obtaining a first video frame set; performing screening and denoising to obtain a second video frame set; based on the second video frame set, the parameter set and a pre-trained identification model, determining position data and fish school type data of a target fish school; performing identification frame labeling on each video frame image in the second video frame set; and extracting target data of the recognition frame, and calculating the swimming speed of the target fish school. Through the implementation of the method and the device, comprehensive and accurate data acquisition, high-quality image processing and accurate target identification and tracking are realized, and the problems that related technologies are not perfect, targets are easy to lose or misjudge when multi-target tracking is processed, and the requirement of accurate measurement of the fish school speed cannot be met are solved.

The invention relates to the technical field of underwater detection and monitoring, and discloses an intelligent form monitoring sonar device and system for an underwater net bag, and the device comprises a data collection module, a signal processing module, a state judgment module, a communication transmission module, and a regulation and control module. Morphological and biological behavior data are collected through a sonar sensor unit arranged on a net bag framework, parameters such as width variation and posture offset are generated, and the working mode is adjusted in a self-adaptive mode in combination with environment information. And when an abnormal state is detected, triggering a cleaning, flow reduction or alarm instruction. According to the invention, the form change and the internal biological distribution of the net bag can be monitored in real time, an intelligent regulation and control means is provided, the technical problem of lack of comprehensive monitoring in a complex underwater environment is solved, and the working efficiency and reliability of the underwater net bag are improved.

The invention relates to a fluid section scanning device and an application method, and belongs to the technical field of water flow detection. According to the technical scheme, a second magnet on a rotating disc is matched with a first magnet on a magnet support through magnetic coupling, the magnet support outside the front side wall of a waterproof shell and a sliding shaft sleeve are driven to rotate around a fixed shaft, and a sensor on the sliding shaft sleeve rotates along with the magnet support; the sensor comprises a sonar sensor which floats under the water surface, a stepping motor rotates in a forward and reverse alternating discontinuous mode within the range of larger than 180 degrees and smaller than 360 degrees, and the sensor conducts forward and reverse alternating rotating scanning in the range of larger than 180 degrees and smaller than 360 degrees within the water passing section. The device has the advantages that winding damage of a sensor cable is avoided, magnetic coupling is adopted to replace a conductive slip ring, only waterproof sealing needs to be carried out on the driving motor and the control module, the sensor does not need to be sealed, reliability is improved, and cost is reduced.

The invention relates to an unmanned aerial vehicle towed body positioning attitude measurement method based on binocular vision positioning, and relates to the technical field of computer processing, and the method comprises the following steps: S01, constructing a measurement system which comprises an unmanned aerial vehicle and a towed body connected with the unmanned aerial vehicle through a cable; the unmanned aerial vehicle carries a GNSS module, an IMU module and a binocular camera, and the upper surface of the towed body is provided with a coding pattern and carries a sonar sensor; s02, establishing a towed body coordinate system by taking the acoustic center of the sonar sensor as an original point, obtaining three-dimensional coordinates of feature points on the towed body in the towed body coordinate system, and generating a three-dimensional space model operation simulation model of the towed body; and S03, the binocular camera is calibrated. According to the invention, the problem of underwater topographic survey of a near-shore high-flow-velocity turbid water area is solved, and high-efficiency, low-cost and high-precision surveying and mapping operation is realized.

A maritime drone as uncrewed surface vessel is provided. The maritime drone has a control and a monohull. The control is configured such that a movement and / or an operation of the maritime drone is autonomously controlled by the control. The monohull has a casing which encloses an interior volume of the maritime drone. The maritime drone comprises at least one sonar sensor which is coupled to the control and is configured for detecting underwater objects. The at least one sonar sensor is arranged within the maritime drone. The maritime drone has furthermore compact dimensions, namely a maximum length of 200 cm, a maximum width of 60 cm, a maximum height of 60 cm and a maximum weight that the maritime drone can be transported by a single person. The maritime drone comprises a self-righting functionality, which is based at least on a shape of the monohull and a weight distribution of the maritime drone.

The application discloses a kind of autonomous operation methods of deep-sea mining car, and mining car is equipped with sonar sensor, camera sensor and control unit.Through sonar, three-dimensional point cloud information of seabed operation area is obtained, and synchronous positioning and map construction are carried out in combination with vehicle pose, to form global point cloud map;Based on the map, cubic surface fitting is carried out on seabed topography, to generate continuous three-dimensional curved surface model;Through camera, seabed image is collected and sulfide target is identified, in combination with camera calibration parameter, vehicle real-time pose and curved surface model, two-dimensional target information is mapped to global coordinate system, to obtain target three-dimensional space position;Construct the grid map containing sulfide target distribution and operation state mark, generate target-oriented mining operation path, and control mining car to execute mining operation;After operation is completed, detection and identification are carried out again using sonar and camera, and operation completion state is updated.The application improves target positioning accuracy, path planning efficiency and autonomous operation ability in deep-sea mining.

The disclosure relates to associating object detection for sensor data processing in autonomous systems and applications. In various examples, sensor data processing is described herein that associates object detection for autonomous and semi-autonomous systems and applications. Systems and methods described herein may group object detection (e.g., echo, etc.) detected using multiple sensors (e.g., ultrasonic sensors, sonar sensors, etc.), and then process the object detection using the grouping to perform one or more tasks, such as object or feature detection. In some examples, object detections are grouped using one or more configurations, such as an order associated with analyzing sensor data generated using sensors and / or a threshold distance associated with determining that object detections are associated with the same object. Further, respective groups may be generated for one or more (e.g., each) detected objects so that the locations of the objects around the machine may be determined.

The invention discloses a high-viscosity material experimental molding and rheological parameter measurement method considering both a supergravity environment and a constant gravity environment. Comprising the following steps: firstly, placing a high-viscosity material in a closed space provided with a sonar sensor, and enabling the closed space to be in a constant-gravity or supergravity environment; pressurizing the closed space to a preset high air pressure for a period of time, then releasing the pressure to a preset low air pressure for a period of time, repeating pressurizing and pressure releasing for preset times, and collecting the volumetric strain of the high-viscosity material at any preset high air pressure or preset low air pressure through a sonar sensor in the repeating process; and after the operation is repeated for preset times, bubbles in the high-viscosity material reach the preset discharge efficiency, and in-situ leveling and molding of the high-viscosity material are completed. The device and the method have the beneficial effects that the material bubbles of the high-viscosity material are efficiently discharged and the rheological parameters of the high-viscosity material are measured in a constant-gravity and supergravity experimental environment.

The application relates to the technical field of image processing, and discloses a fish school target tracking and swimming speed calculation method based on a sonar image, which comprises the following steps: acquiring a sonar video set and a parameter set collected by a sonar sensor array, performing isochronous interval frame processing to obtain a first video frame set, performing screening and denoising to obtain a second video frame set, determining position data and fish school type data of a target fish school based on the second video frame set, the parameter set, a pre-trained identification model, performing identification frame marking on each video frame image in the second video frame set, extracting target data of the identification frame, and calculating the swimming speed of the target fish school. Through implementation of the application, from comprehensive and accurate data collection to high-quality image processing, accurate target identification and tracking are realized, and the problems that related technologies are not perfect, target loss or misjudgment is prone to occurring when multiple targets are tracked, and the demand for accurate measurement of fish school speed cannot be met are solved.

The invention discloses a method for accurately identifying stratum rock soil by combining controllable rail directional drilling and comprehensive logging, belongs to the field of geological exploration and underground engineering construction, and solves the problems of low exploration precision and poor exploration and construction collaboration of an existing subway tunnel. The method comprises an earlier-stage exploration stage and a shield tunneling exploration stage: arranging traction pipes along a preset path in the earlier stage to form a space detection array, arranging a built-in mobile detection device for cooperative detection, and inverting stratum parameters and adjusting drilling parameters through data processing; in the tunneling-following stage, phased array sonar sensors are installed on a shield cutterhead, front strata are scanned by 360 degrees, after data are processed, a three-dimensional distribution diagram is generated by means of multi-sensor fusion and a geological interpretation model and is fed back to a shield main control system to adjust tunneling parameters, and a self-adaptive optimization step is further arranged to improve the recognition accuracy. The technology is high in exploration precision, high in construction collaboration, suitable for complex environments and capable of guaranteeing safety and high efficiency of subway tunnel shield construction.

The utility model provides an offshore oil platform settlement inclination monitoring device which comprises a base frame assembly and a winding mechanism, and the base frame assembly comprises a clamping frame, a machine shell and a sliding frame; wherein the machine shell is connected to the interior of the clamping frame in a sliding mode, and the sliding frame is connected to the outer side of the clamping frame in a sliding mode; according to the utility model, the housing is integrally limited on an offshore oil platform by using the clamping frame, then the monitoring mechanism is released by rotating the rolling mechanism, so that the storage box is integrally sunk into the sea, and the counterweight cone is matched with the traction rope to provide a downward traction force for the storage box in the sea water, so that the sonar sensor can directly face the seabed, and the detection accuracy is improved. In the monitoring process, the sonar sensor can send out a sound wave signal to detect the seabed, and the distance between the sonar sensor and the seabed is calculated according to the reflection time and the wave pattern, so that the overall vertical settlement of the offshore oil platform is effectively detected based on the distance, and the detection effect is ensured.

The invention provides an adaptive space calibration method and device, an underwater robot and electronic equipment, and the method comprises the steps: carrying out the multi-view image collection of a first feature of a target object through a visual sensor, obtaining a first feature image set, carrying out the point cloud extraction of a first feature image in the first feature image set, and generating a first point cloud; performing image acquisition on a second feature of the target object through a sonar sensor to obtain a second feature image set, and performing point cloud extraction on a second feature image in the second feature image set to generate a second point cloud; and performing dynamic matching on the first point cloud and the second point cloud according to the visibility of the water area so as to realize adaptive space calibration of the camera vision sensor and the sonar sensor. Through a three-dimensional reconstruction method, space coordinate calibration of a visual sensor and a sonar sensor is adaptively completed, and correct fusion of point cloud data of at least two sets of different sensors is guaranteed in multiple imaging modes.

This invention relates to a biomimetic brain-like synchronous localization and environmental perception method for underwater robots. The invention addresses the problems of poor visual odometry, insufficient robustness, and low accuracy in loop closure detection in existing underwater robot navigation systems. The robot first acquires environmental feature information through sonar sensors and its own motion information through navigation sensors. A local scene template is obtained by processing the sonar data using an acoustic-visual processing method. The sensor data undergoes pre-integration processing, and the processed data is used as input to a convolutional neural network to output motion displacement, thus forming the robot's perception of its own position. Finally, an empirical map integrates the above information, and loop closure detection updates the empirical map, reducing drift during robot movement and completing the construction of the empirical map. This invention belongs to the fields of bionics and motion navigation technology.

The invention belongs to the technical field of voltage type pre-amplifiers. The invention provides a fully differential rail-to-rail voltage type preamplifier for a sonar sensor. According to the embodiment of the invention, the two rail-to-rail input stages and the shared four-input dual-output node output stage are integrated, so that a unique signal processing structure is formed. By means of the flexibility of multiple input nodes, differential signal amplification and additional input common-mode control nodes can be achieved in the preamplifier, and therefore output common-mode level can be accurately adjusted, and the good active common-mode rejection capacity is achieved. Under the condition that the linearity is ensured, the input and output range of the circuit is remarkably widened, the common-mode rejection capability of the circuit is effectively improved, and a high-performance solution is provided for the multichannel sonar array.

A ground assembly for wireless charging of electric vehicles according to an embodiment of the present invention includes: a transmitting coil; a power supply unit capable of supplying power to the transmitting coil; a detection sensor unit capable of detecting foreign matter in an external matter detection area surrounding the transmitting coil; and a control unit for detecting foreign matter using the detection sensor unit, measuring the distance to the detected foreign matter, determining the presence of foreign matter in the foreign matter detection area based on the measured distance, and controlling the power supplied to the transmitting coil based on the determination result. The detection sensor unit includes at least one of a sonar sensor, a lidar, and a camera device. The foreign matter detection area can be within a predetermined distance from the edge of the transmitting coil in a direction parallel to the ground surface, and can be within a predetermined distance from the upper part of the transmitting coil in a direction perpendicular to the ground surface.

The invention discloses a full-simulation class volume accumulation and calculation integrated chip and a cross-medium multi-mode detection method thereof, and belongs to the field of computer vision. The optical sensor array is used for capturing an optical image signal and directly outputting a voltage signal through an analog circuit; the sonar sensor array is used for receiving acoustic signals and converting the acoustic signals into corresponding electric signals; and the shared and reusable convolution-like hybrid storage calculation unit is used for executing weight storage and analog calculation. The invention aims to solve the problems of high delay, high resource consumption and analog-to-digital conversion bottleneck in cross-media detection.

The utility model discloses a sonar temperature sensor and an electric kettle realizing water level measurement based on sonar technology, the sonar temperature sensor is integrated with a sonar sensor and a temperature sensor, the sonar temperature sensor comprises a T-shaped sensor housing, a sonar transduction sheet and a temperature measurement circuit board, and the sonar transduction sheet and the temperature measurement circuit board are both arranged in the sensor housing; wherein the sonar transduction sheet is glued at the upper part in the sensor shell by using epoxy resin glue, and the temperature measurement circuit board is arranged on the inner wall of the sensor shell, so that the temperature measurement circuit board is respectively connected with the sensor shell and then is encapsulated by epoxy resin; the sensor shell is made of 304 stainless steel, and the sensor shell is directly used for signal receiving and transmitting of the sonar sensor and the temperature sensor so that the water level height and the water temperature can be conveniently detected. According to the utility model, the sonar temperature sensor is integrated, the installation is convenient, and the water level measurement accuracy can be improved through the sonar sensor.

The invention discloses a pier scour prediction method and system based on a single-beam sonar and water tank experiment, and the method comprises the steps: carrying out the quantitative evaluation of a pier position in a navigable river channel, and selecting a pier with the highest comprehensive scour risk as a monitoring object; acquiring field flow field parameters; setting a pier model and a riverbed scene in the water tank, and carrying out a water tank scouring experiment; detecting the section of a scouring pit on the upstream side of the pier after the water tank scouring experiment, and obtaining a curve shape from the pit bottom to an edge transition area; extracting water tank scouring experiment data, and constructing a training data set; training a pre-established pier scouring curve prediction model by adopting the training data set; and acquiring field real-time data and inputting the field real-time data into the trained pier scour curve prediction model to obtain a pier scour prediction curve. According to the method, a small number of sonar sensors are installed on actual piers to monitor the depth of the scouring pit, and calculation and prediction of the section curve of the scouring pit of the multiple piers of the actual bridge are achieved in combination with a prediction model trained through a water tank model experiment and a data driving method.

A retainer installation tool can facilitate installation of a retainer onto a vehicle body structure. In some arrangements, the retainer can be for a vehicle sonar sensor, and the vehicle body structure can be a bumper. The retainer installation tool can help to ensure proper placement of retainer, sufficient adhesion time, and / or placement of an adhesive. The retainer installation tool can include a plunger that extends partially within a housing. The plunger can have a longitudinal axis. The plunger can be movable along its longitudinal axis within the housing. The retainer installation tool can be configured to retainably engage a retainer. The retainer installation tool can be configured to selectively disengage the retainer when the plunger is depressed downwardly along the longitudinal axis. In such case, the retainer is free to be separated from the retainer installation tool.

The ground assembly for wireless charging of an electric vehicle according to an embodiment of the present invention comprises: a transmission coil; a power supply unit capable of supplying power to the transmission coil; a detection sensor unit capable of detecting an external material in an external material detection area around the transmission coil; and a control unit for detecting the external material by using the detection sensor unit, measuring the distance to the detected external material, determining whether the external material exists within the external material detection area on the basis of the measured distance, and controlling power supplied to the transmission coil on the basis of the determination result. The detection sensor unit includes at least one of a sonar sensor, a lidar, and a camera. The external substance detection area may be within a predetermined distance from the edge of the transmission coil in a direction parallel to the ground surface, and may be within a predetermined distance from the upper portion of the transmission coil in a direction perpendicular to the ground surface.

The subject invention pertains to systems and methods for controlling an end-effector moving in three-dimensional space within long piles or shafts. Systems can include a fixed base platform, a cable-driven working platform, a cable-driven end-effector, a sensing system including draw wire sensors, gyroscopes, sonar sensors, and lidar, a control system in communication with the sensing system, and actuators for cables. The end-effector can be configurable to become a cable-driven parallel end-effector, a serially linked arm, a flexible end-effector or an air-lifting end-tool in cases of cleaning founding layers in bored pile shafts. The control system can be configurable to regulate the lengths of cables through actuators and modulate the positions and orientations of the working platform and the end-effector.

Techniques are described for calibrating a coordinate frame of a remote sensing sensor of a perception system of a machine with respect to a coordinate frame of the machine. An application of a mobile device, such as a smartphone, a tablet computing device, or a laptop, or a web service detects a visual fiducial tag and a feature of the machine in an image by using an optical sensor of a digital camera system. The fiducial tag detection provides the coordinate transformation between the mobile device and a housing of the remote sensing sensor, e.g., radar sensor, lidar sensor, sonar sensor, or camera. Detecting a feature of the machine, e.g., a traction component such as a wheel or track, a brake light, a headlight, a turn signal, or a logo, provided constraints for the transformation between the device and machine.

The utility model discloses an unmanned diving device. The unmanned diving device comprises a frame body; one end of the mounting assembly is fixedly connected with one end of the frame body; the sealing assembly is arranged at the other end of the frame body, a controller is arranged in the sealing assembly, and the controller is used for controlling movement of the unmanned diving device; the sampling assembly is arranged at the end, away from the frame body, of the sealing assembly, and the sampling assembly is electrically connected with the controller; and the sonar sensor is arranged on one side of the sealing assembly, and the sonar sensor is electrically connected with the controller. The unmanned diving device is small in size, simple in structure, high in working efficiency, convenient to transport and high in control precision.

The invention relates to the field of energy storage battery assembly, and discloses a battery box screw installation abnormity detection system based on an artificial intelligence large model, and the system comprises the steps: collecting echo signals of a battery box screw and a hole wall through a sonar sensor, and comprehensively judging the fastening state of the screw and whether a workpiece has a dark damage through a multi-mode fusion algorithm; performing joint modeling and semantic reasoning on the sonar signal features and the visual image features by using an artificial intelligence large model, and automatically generating specific reasons causing abnormity; based on the corresponding relationship between the abnormal reason and the repair knowledge graph, retrieving repair process parameters and operation steps related to the type of the dark injury or the fastening defect; the abnormal position is directly marked on the surface of the battery box through high-precision laser; and collecting process data and feedback information after repair execution of the operator, and outputting an updated anomaly detection and repair guidance result in combination with a historical repair result and a detection record. The method has the advantage of improving the detection accuracy.

The invention discloses a multi-mode water rescue robot cooperative control method and a related device, and relates to the technical field of robot cooperative control. The method comprises the following steps: acquiring a water area environment image acquired based on a visual sensor in a target water area, distance and depth information of an underwater target determined based on a sonar sensor, and position and speed information of the underwater target determined based on a radar sensor; determining a rescue target in the target water area according to the multi-modal data; determining a rescue task of each rescue robot according to the position information of the rescue target, the current position and the current state of each rescue robot and the current water area environment information; and determining an optimal path for each rescue robot to arrive at the matched rescue target position so as to execute a cooperative rescue action. Target detection is carried out through the multi-source sensing data, the accuracy of target detection is improved, task allocation and path planning are carried out on the multiple water rescue robots, and cooperative control over the multiple robots is achieved.

The utility model discloses depth measuring equipment for river channel construction, which comprises a base, the upper surface of the base is fixedly connected with an angle adjusting seat, the inner wall of the angle adjusting seat is hinged with a primary support frame, and the front surface of the angle adjusting seat is fixedly connected with a motor. According to the device, the laser distance measuring sensor is matched with the sonar sensor, the laser distance measuring sensor in a shallow water area quickly obtains accurate data by means of the high precision advantage, the sonar sensor in a deep water area effectively works, the limitation of a single sensor in different water areas is avoided, and the accuracy of measurement data of the whole water area is ensured; meanwhile, the first-stage supporting frame with the adjustable angle can flexibly adjust the measurement angle according to the actual conditions of different measurement sites, and the device adapts to diversified measurement environments; the electric hydraulic telescopic rod can adjust the measurement length according to the estimated river channel depth, the measurement requirements of river channels with different depths are met, and the application range of the device is greatly expanded.