Tool Path Generation Method for High-Quality Machining of Free-Form Surfaces

Machining data (NC program) is generated by a CAM system, which generates the tool path from the target shape as a plane approximation surface instead of a free-form surface. Owing to this plane approximation, machining accuracy is reduced. In this paper, we propose a method to process the shape with high accuracy by defining the areas where accuracy is not required as a plane approximation surface and defining the part where accuracy is required as free-form surfaces.

Identifying the Cyber-Incidents in Additive Manufacturing Systems via Multimedia Signals

Additive Manufacturing (AM) is an emerging manufacturing technology that plays a growing role in both industrial and consumer settings. However, security concerns of the AM have been raised among researchers. In this paper, we present an online detection mechanism for the malicious attempts on AM system, which taps into both audios and videos collected during the actual printing process. For audio signals, we propose to monitor the characteristics or patterns in the spectrogram via the Wasserstain metric. For video signals, we present a path reconstruction method which effectively monitors the motion of the printer extruder. We then show the effectiveness of our methods in a case study using Ender 3D printer, where the cyber-incidence of modifying the internal fill density can be easily identified in an online manner.

Smart Production System Modeling: Bernoulli Serial Line Case

The manufacturing industry has entered the era of Industry 4.0/Smart Manufacturing. New technologies have dramatically changed the way manufacturing activities are carried out on the factory floor. In addition to an enhanced level of equipment automation, automation of decision-making has been one of the key objectives of these new initiatives. On the other hand, a critical issue that has been overlooked is the construction of mathematical models in manufacturing research and studies, which are typically done manually. This manual, ad-hoc nature of mathematical modeling is quite problematic when modeling the job flow in a manufacturing process. As a result, the quality of the models obtained may heavily depend on the experience and personal preference of the modeler. The goal of this paper is to develop a method to standardize and automate the modeling process using standard manufacturing key performance indices in the framework of Bernoulli serial production line model.

3D Shape Prediction of a Paper Model for a Brassiere Cup Consisting of Multiple Polygonal Patterns

A general method is proposed to predict the shape of a paper model of a brassiere cup. A brassiere cup consists of several cloth and wire parts and the shapes of cloth parts are determined by repeating creation of a paper cup model, check of its 3D shape, and modification of 2D shapes of parts. For efficient design of a brassiere cup, prediction of its 3D shape with a simulation is required. The deformed shape of a paper part is represented as a single or multiple developable surfaces. So, a model that can represent a part both as a single surface and as multiple surfaces is proposed. Which case is selected depends on the magnitude of the potential energy of the part in each case. The potential energy of the part and geometric constraints imposed on the part are formulated based on the model. Minimizing the potential energy under geometric constraints derives the stable shape of the part in either case. Furthermore, our proposed method can be applied to prediction of the paper cup model consisting of parts with complex shapes.

A Conflict-Free Routing Method for Automated Guided Vehicles Using Reinforcement Learning

In a modern large-scale fabrication, hundreds of vehicles are used for transportation. Since traffic conditions are changing rapidly, the routing of automated guided vehicles (AGV) needs to be changed according to the change in traffic conditions. We propose a conflict-free routing method for AGVs using reinforcement learning in dynamic transportation. An advantage of the proposed method is that a change in the state can be obtained as an evaluation function. Therefore, the action can be selected according to the states. A deadlock avoidance method in bidirectional transport systems is developed using reinforcement learning. The effectiveness of the proposed method is demonstrated by comparing the performance with the conventional Q learning algorithm from computational results.

Machining Performance Evaluation of Robot Type Machine Tool Based on Forward Kinematics Model

Robot type machine tools with parallel link mechanism are characterized by the performance to change tool posture and machine wider range than conventional machine tools. It is realized by simultaneous multi-axis control of parallel link mechanism. However, there are some problems, it is difficult to identify and adjust alignment error. In addition, the machining performance is unidentified due to the rigidity is different from conventional machine tools. In this research, a geometric model is described and the forward kinematics model is derived based on the geometric model. Then, the machining tests were carried out to evaluate the machining accuracy by measured machined surface and the simulated motion of tool cutting edge based on proposed forward kinematics model.

Design of a Two-Piece Brassiere Cup From its Data Points Toward its Automation

A method to design the two-dimensional shapes of patterns of two piece brassiere cup is proposed when its target three-dimensional shape is given as a cloud of its data points. A brassiere cup consists of several patterns and their shapes are designed by repeatedly making a paper cup model and checking its three-dimensional shape. For improvement of design efficiency of brassieres, such trial and error must be reduced. As a cup model for check is made of paper not cloth, it is assumed that the surface of the model is composed of several developable surfaces. When two lines that consist in the developable surface are given, the surface can be determined. Then, the two-piece brassiere cup can be designed by minimizing the error between the surface and given data points. It was mathematically verified that the developable surface calculated by our propose method can reproduce the given data points which is developable surface.

Sensitivity Analysis of Error Motions and Geometric Errors in the Case of Sphere-Shaped Workpiece

Motion error of machine tool feed axes influences the machined workpiece accuracy. However, the influences of each error sources are not identical; some errors do not influence the machined surface although some error have significant influences. In addition, five-axis machine tools have more error source than conventional three-axis machine tools, and it is very tough to predict the geometric errors of the machined surface. This study proposes a method to analyze the relationships between the each error sources and the error of the machined surface. In this study, a kind of sphere-shaped workpiece is taken as a sample to explain how the sensitivity analysis makes sense in ball-end milling. The results show that the method can be applied for the axial errors, such as motion reversal errors, to make it clearer to obverse the extent of each errors. In addition, the results also show that the presented sensitivity analysis is useful to investigate that how the geometric errors influence the sphere surface accuracy. It can be proved that the presented method can help the five-axis machining center users to predict the machining errors on the designed surface of each axes error motions.

Combining Motion Primitives and Image-Based Visual Servo Control

Combining perception feedback control with learning-based open-loop motion generation for the robot’s end-effector control is an attractive solution for many robotic manufacturing tasks. For instance, while performing a peg-in-the-hole or an insertion task when the hole or the recipient part is not visible in the eye-in-the-hand camera, an open-loop learning-based motion primitive method can be used to generate end-effector path. Once the recipient part is in the field of view (FOV), visual servo control can be used to control the motion of the robot. Inspired by such applications, this paper presents a control scheme that switches between Dynamic Movement Primitives (DMPs) and Image-based Visual Servo (IBVS) control combining end-effector control with perception-based feedback control. A simulation result is performed that switches the controller between DMP and IBVS to verify the performance of the proposed control methodology.

Human-Robot Collaboration: A Predictive Collision Detection Approach for Operation Within Dynamic Environments

Robots and humans closely working together within dynamic environments must be able to continuously look ahead and identify potential collisions within their ever-changing environment. To enable the robot to act upon such situational awareness, its controller requires an iterative collision detection capability that will allow for computationally efficient Proactive Adaptive Collaboration Intelligence (PACI) to ensure safe interactions. In this paper, an algorithm is developed to evaluate a robot’s trajectory, evaluate the dynamic environment that the robot operates in, and predict collisions between the robot and dynamic obstacles in its environment. This algorithm takes as input the joint motion data of predefined robot execution plans and constructs a sweep of the robot’s instantaneous poses throughout time. The sweep models the trajectory as a point cloud containing all locations occupied by the robot and the time at which they will be occupied. To reduce the computational burden, Coons patches are leveraged to approximate the robot’s instantaneous poses. In parallel, the algorithm creates a similar sweep to model any human(s) and other obstacles being tracked in the operating environment. Overlaying temporal mapping of the sweeps reveals anticipated collisions that will occur if the robot-human do not proactively modify their motion. The algorithm is designed to feed into a segmentation and switching logic framework and provide real-time proactive-n-reactive behavior for different levels of human-robot interactions, while maintaining safety and production efficiency. To evaluate the predictive collision detection approach, multiple test cases are presented to quantify the computational speed and accuracy in predicting collisions.