Search results

The purpose of this study is to investigate the deformation characteristics and failure modes of the right bank slope of Xiluodu Hydropower Station after excavation.

Micro-seismic monitoring technology is applied to obtain the microfracture information and study the internal damage evolution law of the slope rock mass. A numerical model for discontinuous deformation analysis (DDA) is established to analyse the deformation characteristics and failure mode of the slope. Micro-seismic monitoring and DDA can verify and supplement each other's results in the investigation of slope failure.

The results show that the slope has a downhill displacement along the weathered zone under natural conditions; the maximum resultant displacement at the monitoring point is 380 mm. The micro-seismic events are concentrated in an area located 30–100 m horizontally away from the slope surface and at an elevation of 390–470 m. The distribution of these micro-seismic events is consistent with the location of the unloading and weathered zones; it is the same as the DDA simulation result.

The study is anticipated to be used as reference for the stability analysis of rock slopes. By combining the continuous (micro-seismic monitoring technology) and discontinuous (DDA) methods, the entire process starting from the gradual accumulation of internal rock micro-damage to the macroscopic discontinuous deformation and failure of the slope can be investigated.

This paper introduces normal systems and the normal sum of general systems. A system S=(M,R) is normal if and only if any two relations in R are not contained in the same Cartesian product Mⁿ for any ordinary number n. Normal sum is a new kind of decomposition (composition) of general systems. Given a normal system S=(M,R), and two subsets A₁⊆M and A₂⊆M. One of the main results is that the normal sum of the A₁‐related subsystem and the A₂‐related subsystem of S equals the (A₁∪A₂)‐related subsystem of S. This implies that every normal system is a normal sum of its subsystems which are non‐trivial and non‐discrete.

In this paper, we introduce the concept of a supporting set for a general system. We study basic properties of supporting sets for a general system, supporting sets for subsytems of a system, homomorphic images of supporting sets for a system, and supporting sets for free sums and direct sums of systems.

Presently, 6 Degree of Freedom (6DOF) visual pose measurement methods enjoy popularity in the industrial sector. However, challenges persist in accurately measuring the visual pose of blank and rough metal casts. Therefore, this paper introduces a 6DOF pose measurement method utilizing stereo vision, and aims to the 6DOF pose measurement of blank and rough metal casts.

This paper studies the 6DOF pose measurement of metal casts from three aspects: sample enhancement of industrial objects, optimization of detector and attention mechanism. Virtual reality technology is used for sample enhancement of metal casts, which solves the problem of large-scale sample sampling in industrial application. The method also includes a novel deep learning detector that uses multiple key points on the object surface as regression objects to detect industrial objects with rotation characteristics. By introducing a mixed paths attention module, the detection accuracy of the detector and the convergence speed of the training are improved.

The experimental results show that the proposed method has a better detection effect for metal casts with smaller size scaling and rotation characteristics.

A method for 6DOF pose measurement of industrial objects is proposed, which realizes the pose measurement and grasping of metal blanks and rough machined casts by industrial robots.

This paper aims to study six degrees-of-freedom (6DOF) pose measurement of reflective metal casts by machine vision, analyze the problems existing in the positioning of metal casts by stereo vision sensor in unstructured environment and put forward the visual positioning and grasping strategy that can be used in industrial robot cell.

A multikeypoints detection network Binocular Attention Hourglass Net is constructed, which can complete the two-dimensional positioning of the left and right cameras of the stereo vision system at the same time and provide reconstruction information for three-dimensional pose measurement. Generate adversarial networks is introduced to enhance the image of local feature area of object surface, and the three-dimensional pose measurement of object is completed by combining RANSAC ellipse fitting algorithm and triangulation method.

The proposed method realizes the high-precision 6DOF positioning and grasping of reflective metal casts by industrial robots; it has been applied in many fields and solves the problem of difficult visual measurement of reflective casts. The experimental results show that the system exhibits superior recognition performance, which meets the requirements of the grasping task.

Because of the chosen research approach, the research results may lack generalizability. The proposed method is more suitable for objects with plane positioning features.

This paper realizes the 6DOF pose measurement of reflective casts by vision system, and solves the problem of positioning and grasping such objects by industrial robot.

To address the issue of large visual measurement errors caused by insufficient information collected by monocular vision when performing six-degree-of-freedom (6DOF) position measurements on metal castings, which hinders the robot’s ability to visually guide grasping, this paper aims to propose a 6DOF position measurement method that integrates monocular vision with deep neural networks.

This method enhances the robot’s ability to visually grasp small-sample industrial objects with high accuracy. By establishing a mapping relationship between the two-dimensional (2D) position of the object’s image and its three-dimensional (3D) position in space, the proposed approach achieves 6DOF position measurement of the target workpiece using monocular vision. An image enhancement algorithm based on a generative adversarial network (GAN) is introduced to improve robustness in industrial environments by addressing the challenge of acquiring image data for small-sample objects. Additionally, the method combines single-phase object detection using deep neural networks with 2D-3D affine transformation to achieve accurate 3D position measurements.

The introduction of the GAN-based image enhancement algorithm significantly mitigates the robustness issues posed by the difficulties in obtaining image data for small-sample objects in industrial settings. The integration of single-phase object detection and 2D–3D affine transformation allows for precise 3D position measurement of the workpiece. Experimental results demonstrate that the proposed method provides high accuracy in 6DOF position measurements for industrial objects.

This approach overcomes the limitations of traditional vision algorithms for 3D position measurement of industrial objects, such as high cost and poor robustness. The experimental validation confirms that the proposed method achieves excellent 6DOF position measurement accuracy for industrial objects.