The proposed model of the neural network describes the task of planning the assembly sequence on the basis of predicting the optimal assembly time of mechanical parts. In the proposed neural approach, the k-means clustering algorithm is used. In order to find the most effective network, 10,000 network models were made using various training methods, including the steepest descent method, the conjugate gradients method, and Broyden–Fletcher–Goldfarb–Shanno algorithm. Changes to network parameters also included the following activation functions: linear, logistic, tanh, exponential, and sine. The simulation results suggest that the neural predictor would be used as a predictor for the assembly sequence planning system. This paper discusses a new modeling scheme known as artificial neural networks, taking into account selected criteria for the evaluation of assembly sequences based on data that can be automatically downloaded from CAx systems.

Analysis of the energy consumption of industrial robots during the implementation of a technological task can increase efficiency and minimize production costs, as well as extend the service life of robots, taking into account the rational use of energy sources. An important challenge in designing sustainable production processes is the selection of energy-saving technological equipment supporting the work of robots. Additionally, optimization of robot program codes, including parameters and robot movement paths, determines the energy efficiency of the robotic station. Welding is one of the most popular areas of process robotization due to its ability to increase production efficiency and improve the quality of part assembly compared to manual work. In these studies, an exemplary process of robotic welding of aluminum alloy parts was designed, analyzed, and optimized with an orientation towards sustainable development guidelines. This work also presents a review of current publications discussing the authors’ contribution to achieving energy efficiency in robotic welding processes. The purpose of this analysis is also to indicate directions for the development of future research work in order to minimize energy consumption in production processes with an appropriate level of product quality and increase production efficiency.

The purpose of the article was to build a low-cost system for identifying shapes in order to program industrial robots (on the base of the six-axis “ABB IRB 140” robot) for a welding process in 2D. The whole system consisted of several elements developed in individual stages. The first step was to identify the existing robot control systems, which analysed images from an attached low-cost digital camera. Then, a computer program, which handles communication with the digital camera capturing and processing, was written. In addition, the program’s task was to detect geometric shapes (contours) drawn by humans and to approximate them. This study also presents research on a binarization and contour recognition method for this application. Based on this, the robot is able to weld the same contours on a 2D plane.

In this paper, an assembly sequence planning system, based on artificial neural networks, is developed. The problem of artificial neural network itself is largely related to symmetry at every stage of its creation. A new modeling scheme, known as artificial neural networks, takes into account selected DFA (Design for Assembly) rating factors, which allow the evaluation of assembly sequences, what are the input data to the network learning and then estimate the assembly time. The input to the assembly neural network procedure is the sequences for assembling the parts, extended by the assembly’s connection graph that represents the parts and relations between these parts. The operation of a neural network is to predict the assembly time based on the training dataset and indicate it as an output value. The network inputs are data based on selected DFA factors influencing the assembly time. The proposed neural network model outperforms the available assembly sequence planning model in predicting the optimum assembly time for the mechanical parts. In the neural networks, the BFGS (the Broyden–Fletcher–Goldfarb–Shanno algorithm), steepest descent and gradient scaling algorithms are used. The network efficiency was checked from a set of 20,000 test networks with randomly selected parameters: activation functions (linear, logistic, tanh, exponential and sine), the number of hidden neurons, percentage set of training and test dataset. The novelty of the article is therefore the use of parts of the DFA methodology and the neural network to estimate assembly time, under specific production conditions. This approach allows, according to the authors, to estimate which mechanical assembly sequence is the most advantageous, because the simulation results suggest that the neural predictor can be used as a predictor for an assembly sequence planning system.

This paper aims to propose the method of automatic robotic assembly of two or more parts placed without fixing instrumentation and positioning on the pallet. Assembly tasks performed by industrial robots are usually based on a constant program, extensive tooling, fixing objects in a given place and a relatively limited sensory system. In this study, a different approach is presented. The industrial robot program is adjusted to the location of parts for assembly in the work space. This leads to a transition from a clearly defined assembly sequence realized by the industrial robot to the one in which the order of execution of the assembly operations can be determined by the mutual position of parts to be assembled. The method presented in this study combines many already known algorithms. The contribution of the authors is to test and select the appropriate combination of methods capable of supporting robotic assembly process based on data from optical 3D scanners. The sequence of operations from scanning to place the parts in the installation position by an industrial robot is developed. A set of parameters for selected methods is presented. The result is a universal procedure that determines the position of the preset models in partial measurements performed at a fixed relative position of the sensor, the measurement object. The developed procedure for determining the position of the parts is essential to develop a flexible robotic assembly system. It will be able to perform the task of assembly on the basis of appropriate search algorithms taking into account the selected and implemented sequence of assembly position and orientation of parts, particularly the base unit freely placed on an assembly pallete. It is also the basis of a system for testing different algorithms to optimize the flexible robotic assembly.

This article deals with the design of a methodology for vibration and noise measurement on a six-axis collaborative robotic arm. A vibration and noise measurement methodology is proposed for six robot positions. In each position, measurements were performed under defined equal boundary conditions. The boundary conditions were related to the velocities of the joints and the load on the robotic arm. The second part of the article is an evaluation of the initial experimental results. So far, only the acceleration of the sixth joint of the robotic arm—Wrist 3—has been measured. The aim of the measurements was to verify if the methodology presented can be used for vibration measurements. From the evaluation of the experimental measurements, it was determined that the given methodology can be used for vibration measurements. It was also found that the acceleration is transmitted in the axes other than the axis of motion of the robotic arm. In future experiments, the vibration at the other joints of the robotic arm will be measured and the noise of the robotic arm will be measured to confirm whether the proposed methodology is indeed functional.