41 results about "Unexploded ordnance" patented technology

This invention proposes a method for detecting unexploded ordnance using multi-source data fusion based on deep learning. This method primarily addresses the problems of low accuracy and excessive false alarms and missed alarms in existing unexploded ordnance detection technologies. The method comprises: a data processing module processes received magnetic detection data and image data and transmits them to a deep learning model, which then identifies unexploded ordnance; a data storage module records the input and output of the deep learning model; and a display module displays the acquired magnetic field, image, and location of the unexploded ordnance. This invention utilizes both the magnetic detection module and a camera to acquire information, and obtains unexploded ordnance detection results based on multi-source data fusion and deep learning. This effectively avoids the shortcomings of existing detection methods using a single magnetic detection module, resulting in more comprehensive and diverse information, reducing false alarms and missed alarms, further ensuring personal safety, and reducing resource consumption.

The invention belongs to the technical field of geophysical exploration, and particularly discloses a differential transient electromagnetic method device and an unexploded ordnance detection method thereof.The differential transient electromagnetic method device is characterized in that a transmitter injects emission current into an emission loop, and the emission loop generates a primary field excitation signal; the underground anomalous body target generates a secondary field excitation signal under the action of the primary field excitation signal; the receiving coil assembly is based on the structure of a differential coil, synchronously counteracts a primary field excitation signal and a uniform background signal in an induced voltage, and expands a local asymmetric differential signal generated by an underground anomalous body target; and the receiver carries out time sequence analysis on the local asymmetric differential signals and extracts differential signal features so as to realize positioning and identification of an underground anomalous body target. The device is suitable for detection of shallow-buried small bodies such as UXO, the overall arrangement range of the device is small, and rapid arrangement and mobile observation in the field are facilitated.

A system and processes detect, identify a Unexploded Ordnances (UXOs) and / or categorize UXOs in near real-time using Unmanned Aerial Vehicles (UAVs). In accordance with various disclosed embodiments, the equipment includes such UAVs (also referred to herein as “drones,”) that include a plurality of sensors for imaging the terrain of a geographic area to analyze the terrain and detect anomalies and / or changes that may be indicative location of UXOs, for example, soil moving activity performed in association with the burying the UXO. Additionally, the UAVs include processing equipment, e.g., one or more small form factor devices, e.g., Next Unit of Computing (NUC) compute elements or the like, that provide processing power to provide EDGE computing on the data gathered at the UAV.

The invention provides a three-dimensional magnetic anomaly feature extraction method and system applied to unexploded ordnance identification, and the method comprises the steps: rotating the angle of an unexploded ordnance, and adjusting the position of a first magnetometer relative to the unexploded ordnance; the data recording instrument records unexploded ordnance identification information and position data and angle data of the unexploded ordnance relative to the first magnetometer, and original magnetic anomaly data of the unexploded ordnance is obtained by combining the first magnetic data and a difference value of synchronously collected second magnetic data; performing inversion based on the original magnetic anomaly data and the position data of a plurality of positions corresponding to the same angle so as to form a three-dimensional point cloud model at the angle; and performing inversion based on the three-dimensional point cloud model of the multiple angles to form three-dimensional magnetic anomaly features. Multiple groups of original magnetic anomaly data of the unexploded ordnance are collected and inverted in the outdoor environment to form three-dimensional magnetic anomaly features capable of being compared and matched with actually measured data, and the efficiency, accuracy and convenience of unexploded ordnance detection are improved.

Exemplary embodiments of apparatus and methods for remotely and explosively cutting the casing of a UXO and separating the fuzing components from the main charge in the UXO. A remote explosive separation tool creates a Linear Explosively Formed Projectile (LEFP) charge to separate fuzing components from live explosive threats in UXO, for example only, a 155 mm artillery round. The tool functions by explosively deforming a copper liner into a linear projectile or penetrator which then impacts the UXO casing. The speed of impact enables the fuzing elements of the UXO to be removed from the main charge of the UXO either by directly cutting the fuze elements off or by imparting the fuze elements with enough momentum such that they break off. The process of dismembering the fuze elements occurs without detonating the main charge of the UXO. The tool may be remotely placed by an unmanned vehicle.

The invention discloses an unexploded ordnance classification and attitude resolving method based on planar array near-field detection. The resolving capability of magnetic vector field data on unexploded ordnance types and attitudes is remarkably improved. Fusion learning is carried out on multi-source data of the planar magnetic flux gate array by using a deep neural network model, so that the problem of failure of a magnetic dipole theoretical model under a near-field detection condition is solved, and rapid and accurate calculation of the type and attitude of an unexploded ordnance is realized; by combining the finite element high-fidelity simulation data and the live-action experiment data, the unexploded ordnance detection object-driven database is established, the generation cost of the data required by the neural network model is reduced, and the training efficiency of the neural network model is improved.

The invention discloses a device for dismantling a buried underwater unexploded ordnance, the device works based on an underwater robot, the device is composed of a shell, a connecting port, a sensor, a driving rod, a protection releasing element, a small motor, a telescopic rod, a shaped charge, a magnetic detection device, a telescopic sleeve and a supporting plate, and the shape of the buried unexploded ordnance is detected through the magnetic detection device; an explosive ordnance disposal scheme is determined after information is transmitted to the water operation platform, the telescopic rod controls the telescopic sleeve to ensure the position relation between the shaped charge and the unexploded ammunition, and the shaped charge is provided with an intelligent fuze which can be detonated after the robot is away from the unexploded ammunition. The device for destroying and burying the underwater unexploded ordnance has the advantage that the position relation between the shaped charge and the unexploded ordnance is fixed through the telescopic sleeve, the shaped charge can be accurately detonated, the unexploded ordnance can be detonated, the effect of accurately destroying and burying the underwater unexploded ordnance is achieved, meanwhile, the device can be produced in batches, and high economic benefits are achieved.

The utility model relates to the technical field of unmanned aerial vehicles, and discloses an unmanned aerial vehicle detection device which comprises a mounting plate, the outer wall of the mounting plate is provided with a stabilizing assembly used for stabilizing the detection device in the flight process of an unmanned aerial vehicle, the bottom of the mounting plate is fixedly connected with a connecting plate, and the bottom of the connecting plate is fixedly connected with a fixing plate. A middle shaft is rotatably connected to the inner wall of the fixing plate, a bearing is fixedly connected to the outer wall of the middle shaft, a control box is fixedly connected to the outer wall of the bearing, a second bevel gear is fixedly connected to the outer wall of the middle shaft, and a first bevel gear is rotatably connected to the inner wall of the bottom of the control box; the outer wall of the first bevel gear is connected with the outer wall of the second bevel gear in a meshed mode. According to the utility model, the angle of the detection device is adjusted by adding the angle adjusting assembly, so that the detection device can monitor unexploded ordnance of different models and earth surface thunders in different detection ranges, and the detection efficiency is better.

The invention provides a sub-meter buried unexploded ordnance detection and identification method based on correlation three-dimensional magnetic imaging, and the method comprises the steps: obtaining ground surface magnetic anomaly measured data and corresponding trajectory data of a detection region, and dividing a local anomaly region according to a magnetic anomaly change rate; dividing the underground space corresponding to the local abnormal region into three-dimensional grids based on the local abnormal region, calculating the theoretical magnetic anomaly of each grid node based on a magnetic dipole model, obtaining a normalized local correlation coefficient point by point with the measured data of the magnetic anomaly, and reserving nodes higher than a preset threshold as candidate nodes; taking error minimization between theoretical magnetic anomaly of the candidate node and magnetic anomaly measured data as a fitness function, and obtaining an optimal magnetization parameter and an optimal local correlation imaging coefficient based on particle swarm optimization iterative optimization; and based on the optimal local correlation imaging coefficient, carrying out integration according to a spatial position, generating a three-dimensional magnetic imaging result of the detection area, and obtaining a contour parameter and a spatial position of the sub-meter buried unexploded ordnance.

The invention discloses an unexploded ordnance laser destroying device, which belongs to the technical field of unexploded ordnance destroying, and comprises a laser destroying equipment body comprising a laser aiming and launching device; the protection component comprises a protection shell arranged on the laser aiming and transmitting device and is used for protecting the laser aiming and transmitting device, and a fixing assembly is arranged on the protection shell; the launching device protection mechanism is arranged on the protection shell; according to the laser aiming and launching device, through multiple protection structures such as the front end shielding mechanism and the launching device protection mechanism, the shielding plate can be rapidly triggered to shield the front end of the laser aiming and launching device when the unexploded ordnance explodes, and the protection shell is made of impact-resistant materials such as high-strength alloy steel or bulletproof ceramic composite materials; and fragments and shock waves generated by explosion can be resisted, core parts are prevented from being damaged, meanwhile, an operator remotely operates through the control panel, the risk of close-range contact is reduced, and the overall operation safety is greatly improved.

An aerial vehicle system for detecting magnetized objects comprises a propulsion system and sensor bar having magnetic field sensors at opposite ends to collect magnetic field data. In one example, the sensor bar extends at least one and a half times the propulsion system's length. The system further includes a positioning system, an altitude sensor, and an energy storage system. A processor executes flight instructions to navigate the aerial vehicle along a predefined path, collecting magnetic field and position data. A magnetic field information analyzer processes this data, generating expected magnetic signatures, comparing them to collected data, and predicting magnetized object locations. A user interface allows flight path customization and overlays detected objects onto a map of the surveyed area. The system can identify unexploded ordnance and landmines by comparing detected signals to predefined thresholds. The method includes controlling flight, collecting magnetic data, and analyzing signals to detect magnetized objects.

The present invention concerns a firearm (10) comprising at least one frame (11) defining a housing seat of a barrel group (12); and a barrel group (12) comprising at least one barrel with longitudinal development axis (A), the barrel group (12) being mounted in a tilting manner with respect to the frame (11) between a position in which the barrel group (12) engages the housing seat and a position in which the barrel group (12) is rotated with respect to the housing seat, wherein the barrel group (12) comprises at least one extractor device (60) associated with the at least one barrel of the barrel group (12) and configured to at least partially expel at least a portion of an ammunition from the at least one barrel, and is characterized in that the at least one extractor device (60) is configured to selectively operate in a first mode in which it integrally ejects a casing of an exploded ammunition and in a second mode in which it accompanies part of an unexploded ammunition in partial exited from the at least one barrel, and in that it comprises an ejection trigger device (70) configured to drive the at least one extractor device (60) so as to operate in the first ejection mode.

The present invention provides a sample target data enhancement processing method for transient electromagnetic surface detection, which relates to the technical field of sample target data enhancement processing. The method comprises the following steps: uniformly dividing a detection area into feature unit grids, using the center point of each grid as a monitoring point, and collecting transient electromagnetic signal data; judging whether a monitoring point signal is missing, and if missing, defining it as a data missing point and filling it based on a spatial distance attenuation law; using a multi-dimensional anomaly detection algorithm to identify noise interference monitoring points, setting a neighborhood search radius, and correcting it using the signal value of a non-noise monitoring point; constructing a BIM model of the target detection area, performing registration and real-time updating of monitoring point data, defining a dynamic risk threshold, and triggering an unexploded ordnance warning signal if the monitoring point signal exceeds the threshold. The present invention achieves comprehensive monitoring and risk assessment of the monitoring area.

The invention relates to the technical field of seafloor detection, in particular to a seafloor unexploded ordnance identification method and system based on multi-source data, and the method comprises the steps: obtaining seafloor surface multi-source detection data, and carrying out the preliminary screening of magnetic anomalies; suspected mine point magnetic anomaly screening based on mine magnetic moment modeling; pre-estimated burial depth screening of suspected thunder points; screening estimated weights of suspected thunder points; and performing refined verification on the suspected lightning point. According to the method, preliminary screening is carried out according to obtained unexploded ammunition magnetic anomaly data, and non-unexploded ammunition magnetic anomaly elimination is realized by combining geological information such as shallow stratum profile data, side-scan sonar data and synthetic aperture sonar data, a mine modeling and magnetic anomaly matching algorithm, a pre-estimated burial depth and pre-estimated weight screening method and the like. Finally, fine verification is carried out through a magnetic encryption detection method, and unexploded ordnance identification and positioning are achieved.

The utility model discloses an all-terrain crawler-type multifunctional unexploded ordnance destruction vehicle, and relates to the technical field of ordnance disposal devices. The system comprises a crawler-type chassis driving system, a vehicle-mounted pan-tilt camera system, a wireless transmission system, a vehicle-mounted controller and a remote control monitoring terminal, and further comprises a laser detonation device, and the laser detonation device is installed on the vehicle-mounted pan-tilt camera system; the laser detonation device and the vehicle-mounted pan-tilt camera system are both electrically connected with the vehicle-mounted controller and are both controlled by the remote monitoring terminal. The unexploded ordnance can be remotely detonated through laser irradiation so that the unexploded ordnance can be destroyed on site, an operator does not need to make close contact with or get close to the unexploded ordnance, the destroying operation can be completed through remote control operation, and use is safe.

This invention discloses a method and apparatus for magnetic detection of unexploded ordnance, comprising: acquiring three components of a magnetic field near the unexploded ordnance using an array sensor; sending the three components of the magnetic field to an information processing terminal; processing the three components of the magnetic field to obtain a magnetic gradient tensor; and determining the location of the unexploded ordnance based on the magnetic gradient tensor. This invention can achieve accurate detection of the location of unexploded ordnance.

The utility model provides a multifunctional working vehicle. The multifunctional operation vehicle comprises a chassis vehicle, a detection arm and an explosive ordnance disposal arm, and the detection arm comprises a first rotation mechanism arranged at one end of the chassis vehicle and a detection frame folded or unfolded relative to the first rotation mechanism. The explosive ordnance disposal arm comprises a second rotating mechanism arranged at the other end of the chassis truck and an explosive ordnance disposal hopper folded or unfolded relative to the second rotating mechanism, and after the detection arm and the explosive ordnance disposal arm are folded, the detection frame and the explosive ordnance disposal hopper are arranged on the top of the chassis truck at the same time. According to the utility model, detection and elimination are integrated, so that multiple functions are integrated, other extra equipment is not required to be used for detection, the unexploded object disposal operation process is improved, and the operation efficiency is improved.

The invention provides an intelligent detection method and device for unexploded ordnance, electronic equipment and a medium, and effectively solves the problem that an existing unexploded ordnance detection method is low in detection accuracy due to geological interference of iron ore and the like. The method comprises the following steps: acquiring original magnetic data, determining magnetic data based on the original magnetic data, controlling a detection model to preprocess the magnetic data to obtain target magnetic data, and respectively extracting features to obtain time sequence features and frequency spectrum features; fusing the time sequence features and the frequency spectrum features to obtain unexploded ordnance features, and constructing a pyramid feature map of the unexploded ordnance features to perform detection based on the pyramid feature map to obtain a plurality of candidate detection results; and screening out a target detection result from the plurality of candidate detection results according to a preset screening method, so as to detect the unexploded ordnance in the to-be-detected area based on target position information in the target detection result.

The invention provides a three-dimensional magnetic anomaly feature extraction method and system for identifying an unexploded ordnance, and the method comprises the steps: setting a near-end magnetometer and a far-end magnetometer corresponding to the unexploded ordnance; rotating the angle of the unexploded ordnance, and adjusting the position of the near-end magnetometer; the data recording instrument records unexploded ordnance identification information and position data and angle data of the unexploded ordnance relative to the near-end magnetometer, and original magnetic anomaly data of the unexploded ordnance are obtained through calculation; performing inversion based on the original magnetic anomaly data and the position data of a plurality of positions corresponding to the same angle so as to form a three-dimensional point cloud model at the angle; and performing inversion based on the three-dimensional point cloud model of the multiple angles to form three-dimensional magnetic anomaly features. According to the three-dimensional magnetic anomaly feature extraction method, multiple groups of original magnetic anomaly data of the unexploded ordnance are collected and inverted in the outdoor environment to form the three-dimensional magnetic anomaly features, and the efficiency, accuracy and convenience of unexploded ordnance detection are improved.

The utility model discloses an appearance structure of a movable laser destruction device, which belongs to the technical field of unexploded ammunition destruction, and comprises a base, a vertical support rod is arranged on the base, a top seat is arranged at the top end of the support rod, a holder is arranged on the top seat, and a laser transmitter is arranged on the holder. Comprising a first lantern ring and at least three sets of first supporting legs, and the ends of the first supporting legs are rotationally connected to the first lantern ring; and the transmission assembly comprises a motor and a first screw rod, the motor is installed at the bottom of the base, and an output shaft of the motor is provided with a rotating shaft. When the first supporting leg is in a folded state, the whole body can be pushed to move so as to reach a destroying site, so that the portable type mobile destroying device has better portability; and when the first supporting legs are in the folded state, the overall occupied space is small, and therefore the folding chair has the advantage of being convenient to store.

This invention relates to the field of seabed detection technology, specifically to a method and system for identifying unexploded ordnance (UFOs) based on multi-source data. The method includes: acquiring multi-source detection data from the seabed surface and initial screening of magnetic anomalies; screening of suspected mine points based on mine magnetic moment modeling; screening of suspected mine points based on estimated burial depth; screening of suspected mine points based on estimated weight; and refined verification of suspected mine points. The method performs initial screening based on the obtained unexploded ordnance magnetic anomaly data, and combines this with geological information such as shallow seismic profile data, side-scan sonar data, and synthetic aperture sonar data, mine modeling and magnetic anomaly matching algorithms, and methods for screening based on estimated burial depth and estimated weight to eliminate non-unexploded ordnance magnetic anomalies. Finally, refined verification is achieved through a magnetically encrypted detection method, enabling the identification and location of unexploded ordnance.

This application belongs to the field of geophysical exploration technology, specifically disclosing a differential transient electromagnetic method device and its unexploded ordnance detection method. In the differential transient electromagnetic method device, the transmitter injects a transmission current into the transmission loop, generating a primary field excitation signal. Under the influence of the primary field excitation signal, the subsurface anomaly target generates a secondary field excitation signal. The receiving coil assembly, based on a differential coil structure, synchronously cancels the primary field excitation signal and the uniform background signal in the induced voltage, amplifying the local asymmetric differential signal generated by the subsurface anomaly target. The receiver performs time-series analysis on the local asymmetric differential signal, extracts differential signal features, and achieves the location and identification of the subsurface anomaly target. This application is suitable for the detection of shallowly buried small bodies such as UXOs. The overall deployment range of the device is small, facilitating rapid deployment and mobile observation in the field.

The application provides a kind of intelligent detection method, device, electronic equipment and medium for unexploded bomb, effectively solve the problem of low detection accuracy caused by iron ore and other geological disturbances in the existing unexploded bomb detection method.The method comprises: obtaining original magnetic data, determining magnetic data based on the original magnetic data, controlling the detection model to preprocess the magnetic data to obtain target magnetic data, extracting features to obtain time sequence features and frequency spectrum features respectively;Fusion of the time sequence feature and the frequency spectrum feature obtains the unexploded bomb feature, and constructs the pyramid feature map of the unexploded bomb feature to detect based on the pyramid feature map to obtain multiple candidate detection results;According to the pre-set screening method, the target detection result is screened out from the multiple candidate detection results, to detect the unexploded bomb in the to-be-detected area based on the target position information in the target detection result.

The invention provides a multi-buried unexploded ordnance magnetic anomaly image recognition method based on a YOLO model, and the method comprises the steps: constructing a magnetic dipole simulation model, obtaining an unexploded ordnance magnetic anomaly data set which comprises a two-dimensional magnetic anomaly graph and corresponding bounding box coordinates through adjusting the magnetic moment, magnetic declination and position parameters of the magnetic dipole simulation model, and obtaining the unexploded ordnance magnetic anomaly image. Dividing the data set into a training data set and a verification data set in proportion; performing data enhancement preprocessing on the training data set; obtaining an optimal hyper-parameter combination of a YOLO model based on a genetic algorithm, carrying out YOLO model training based on the training data set after enhancement preprocessing, carrying out YOLO model verification based on the verification data set, and obtaining a multi-buried target magnetic anomaly image recognition YOLO model; based on aeromagnetic detection equipment, a two-dimensional magnetic anomaly distribution diagram of the to-be-detected area is obtained, the two-dimensional magnetic anomaly distribution diagram is input into the multi-buried-target magnetic anomaly image recognition YOLO model, and unexploded ordnance coordinates and confidence are obtained.

The present invention discloses an airborne surface mine and unexploded ordnance detection system and method based on image recognition, specifically relating to the technical field of image recognition. By monitoring the wireless signal strength in real time, analyzing the signal fluctuations and image transmission delay, evaluating the impact of the delay on the image resolution and detail retention, and then analyzing the compression quality of the image, according to the degree of image quality degradation, the images are classified into two categories: slightly degraded and severely degraded, and corresponding processing measures are taken: for slightly degraded images, the image quality is improved through local enhancement; for severely degraded images, by predicting and warning the accuracy of the image recognition algorithm, the algorithm is automatically adjusted to improve the detection accuracy, which can effectively improve the accuracy of surface mine and unexploded ordnance detection and ensure real-time and stable image recognition can still be achieved in complex environments.

The present invention is directed to improved precision in object detection, reducing the false positive rates. In particular, the present invention is directed to improved methods, tools and systems of detecting and identifying objects, such as explosives (e.g., landmines and unexploded ordnance) using an unmanned aerial vehicles. The present invention offers solutions to the problem of the high rate of false positives that take time and resources away from real objects, such as these landmines.

The invention provides an unmanned aerial vehicle optical image unexploded ordnance detection method and system based on pseudo label generation, and the system comprises a ground station processing module, an unmanned aerial vehicle and ground station communication module, an airborne calculation module, and an unmanned aerial vehicle platform. The operation route is transmitted to the airborne calculation module through the unmanned aerial vehicle and ground station communication module; the airborne calculation module uploads an operation route to the unmanned aerial vehicle platform, controls the unmanned aerial vehicle to execute a first search task, receives images acquired by the unmanned aerial vehicle in real time, and transmits the images acquired in real time to the ground station processing module through the unmanned aerial vehicle and ground station communication module; according to the invention, real-time target identification can be carried out on the image shot by the unmanned aerial vehicle, the target latitude and longitude are calculated, and the target latitude and longitude and the image are filed.

An aerial vehicle system for detecting magnetized objects comprises a propulsion system and sensor bar having magnetic field sensors at opposite ends to collect magnetic field data. In one example, the sensor bar extends at least one and a half times the propulsion system's length. The system further includes a positioning system, an altitude sensor, and an energy storage system. A processor executes flight instructions to navigate the aerial vehicle along a predefined path, collecting magnetic field and position data. A magnetic field information analyzer processes this data, generating expected magnetic signatures, comparing them to collected data, and predicting magnetized object locations. A user interface allows flight path customization and overlays detected objects onto a map of the surveyed area. The system can identify unexploded ordnance and landmines by comparing detected signals to predefined thresholds. The method includes controlling flight, collecting magnetic data, and analyzing signals to detect magnetized objects.

The application discloses a kind of based on neural network magnetic data inversion submarine cable efficient detection method, belong to the technical field of detection of submarine cable.The method includes: receiving magnetic anomaly time series signal, local time domain feature is extracted by one-dimensional convolution and obtains multi-channel one-dimensional convolution feature map by ReLU activation and normalization;Channel weight adaptive weighting is realized by SE channel attention module;Obtain double attention enhanced feature map by multi-head self-attention of lower triangular mask mechanism;After being compressed by global average pooling, respectively, output spatial position parameters by position parameter regression module, output magnetic anomaly detection probability by detection probability classification module.The application constructs end-to-end deep learning network, avoids the false solution and time-consuming problem caused by improper parameter selection of Euler deconvolution method, can accurately and efficiently identify and locate submarine cable magnetic anomaly, significantly improves detection accuracy and efficiency, and is suitable for fast detection of underwater magnetic targets such as submarine cable and unexploded ordnance.

This invention discloses a continuously fired unexploded ordnance incineration and destruction system and method, belonging to the field of unexploded ordnance destruction technology. It includes an incinerator loading mechanism, a stepper motor rotating mechanism, and a laser ranging and positioning mechanism. The incinerator loading mechanism is a cylindrical structure with multiple loading holes for loading the incinerator. These loading holes are evenly distributed around the axis of the loading mechanism. Between each adjacent loading hole is a laser ranging hole connecting the two bottom surfaces of the loading mechanism. These laser ranging holes are located on the same circle and are evenly distributed. The stepper motor rotating mechanism is connected to and controls the rotation of the incinerator loading mechanism. The laser ranging and positioning mechanism is fixedly connected to the stepper motor rotating mechanism and is used to coordinate with the laser ranging holes on both sides of the loading holes to achieve unexploded ordnance positioning. This invention can improve penetration effect and destruction efficiency.