The photogrammetry system has been widely used in industrial manufacturing applications, such as high-precision assembly, reverse engineering and additive manufacturing. In order to meet the demand of the product variety and short product lifecycle, the factory facilities including photogrammetry devices, should be relocated in response to rapid change in mechanical structure and hardware integration. Nevertheless, the camera position of the photogrammetry system is difficult to select to guarantee an optimal field of view (FoV) coverage of retro-reflective targets during the whole production horizon. Especially in a reconfigurable manufacturing work cell, scaling and calibration of a photogrammetry system requires professional skills and these would cost tremendous labour for rapid configuration each time. In this paper, we propose a novel deep optimisation framework for the photogrammetry camera position for the dynamic layout design based on digital twin. The optimisation framework follows an effective coarse-to-fine procedure to evaluate the FoV visibility over the target frame. In addition, the deep Q-learning algorithm is utilised to find the maximum FoV coverage and avoid collision. Three experiments are implemented to verify the application feasibility of the proposed deep camera position optimisation framework.Note to Practitioners—Large-volume in-process metrology is an essential element in flexible manufacturing systems. Quality of large-volume measurement relies heavily on target visibility within its field of view. In a compact industrial robotic cell, this is extremely challenging as the robot would take the primary position and causing view blockage throughout its operation. This makes the simultaneous monitoring of robot head and the work piece key feature extremely difficult. Manual trial-and-error positioning approach is lengthy and requires high level of expertise, due to both safety and spatial concerns. We approached this problem by simulating the camera’s view in a digital twin environment and maximising the target visibility throughout the full operation cycle. The generic framework can provide guidance in metrology setup within automated manufacturing environment, accelerate the system commissioning time, remove dependency of skill level and expand the capability for flexible/reconfigurable manufacturing systems. Although V-STARS camera are used in this application, the framework can be applied for other types of vision systems that requires field of view.

Industrial robots contribute to a considerable amount of energy consumption in manufacturing. However, modeling the energy consumption of industrial robots is a complex problem as it requires considering components such as the robot controller, fans for cooling, the motor, the friction of the joints, and confidential parameters, and it is difficult to consider them all in modeling. Many authors investigated the effect of operating parameters on the energy consumption of industrial robots. However, there is no prescriptive methodology to determine those parameter values because of the challenges in the modeling of industrial robots. This work investigates an industrial robot and the manufacturing process together and proposes a black-box model-based energy consumption optimization approach. Our contribution to the research is the new online and data-efficient methodology, prescriptive algorithm, and the analysis of operating parameters' effects on industrial robots' energy consumption. The proposed methodology was tested using two real FANUC industrial robots in three industrial settings.

Abstract This paper presents a novel probabilistic distributed framework based on movement primitives for flexible robot assembly. Since the modern advanced industrial cell usually deals with various scenarios that are not fixed via-point trajectories but highly reconfigurable tasks, the industrial robots used in these applications must be capable of adapting and learning new in-demand skills without programming experts. Therefore, we propose a probabilistic framework that could accommodate various learning abilities trained with different movement-primitive datasets, separately. Derived from the Bayesian Committee Machine, this framework could infer new adapting trajectories with weighted contributions of each training dataset. To verify the feasibility of our proposed imitation learning framework, the simulation comparison with the state-of-the-art movement learning framework task-parametrised GMM is conducted. Several key aspects, such as generalisation capability, learning accuracy and computation expense, are discussed and compared. Moreover, two real-world experiments, i.e. riveting picking and nutplate picking, are further tested with the YuMi collaborative robot to verify the application feasibility in industrial assembly manufacturing.

This paper presents a novel distributed probabilistic framework based on movement primitives for flexible robots assembly implementation. Since modern advanced industrial cell usually deals with various tasks that are not fixed via-point trajectories but highly reconfigurable application templates, the industrial robots used in these applications must be capable of adapting and learning new skills on-demand, without programming experts. Therefore, we propose a probabilistic framework that could accommodate various learning abilities trained with different movement-primitive datasets, separately. Thanks to the fusion theory of the Bayesian Committee Machine, this framework could infer new adapting trajectories with weighted contributions of every trained datasets. To verify the feasibility of our proposed imitation learning framework, state-of-the-art movement learning framework Task-parameterized GMM is compared from several crucial aspects, such as generalization capability, accuracy and robustness. Moreover. this framework is further tested on the YUMI collaborative robot with a rivet picking assembly scenario. Potential applications can be extended to more complicated industrial assembly manufacturing or service robotic applications.

With the current advances in the Internet of Things (IoT), smart sensors and Artificial Intelligence (AI), a new generation of condition monitoring solutions for smart manufacturing is starting to emerge. Computer Numerical Control (CNC) machines can now be sensorised and the vast amount of data generated can be processed using Machine Learning (ML) techniques. These can provide insights about the condition of the machine or tool in real-time, which can then be used by decision makers. This is fundamental in order to reach a new level of manufacturing capabilities in the context of Industry 4.0 (Lasi et al, 2014). Most current monitoring solutions rely on the off-line generation of models before they can be used online. This is not ideal when the data holds complex evolving features. There is a lack of approaches that are capable of determining what to learn and when to learn. This paper presents preliminary results on a new deep learning approach based on Bayesian Convolutional Neural Networks (BCNN) for online tool condition classification. Based on the uncertainty of the model, the proposed approach can determine using an entropy acquisition function if the incoming data cannot be classified, and therefore needs to be labelled and used for re-training. This constitutes the first step towards an online active learning tool condition monitoring approach. We demonstrate using a machine tool data set that the active learning approach can achieve similar accuracy of a deterministic Convolutional Neutral Network (CNN) with a smaller training data set.

An on-line trajectory generation algorithm with time-variant kinematic motion constraints is presented in this paper. The algorithm is an extension of a class of trajectory planning method which is applicable with constant kinematic motion constraints only. The extended approach allows the abrupt change in the value of the physical robot constraints(jerk, acceleration, and velocity) at any time instant and keeps these constraints bounded during the trajectory parameter adaptation. Short computation time enables the real-time usage of the proposed algorithm so that it can update the trajectory at any time taking into account the current robot motion limits. It allows sensor integration in low-level robot motion control, that is, making robots have the capability of reacting to unforeseen sensor events in real time. Simulation results are summarized in the paper.

Determining the most appropriate means of producing a given product, i.e., which manufacturing and assembly tasks need to be performed in which order and how, is termed process planning. In process planning, abstract manufacturing tasks in a process recipe are matched to available manufacturing resources, e.g., CNC machines and robots, to give an executable process plan. A process plan controller then delegates each operation in the plan to specific manufacturing resources. In this paper we present an approach to the automated computation of process plans and process plan controllers. We extend previous work to support both non-deterministic (i.e., partially controllable) resources, and to allow operations to be performed in parallel on the same part. We show how implicit fairness assumptions can be captured in this setting, and how this impacts the definition of process plans.

Industry 4.0 proposes the integration of the new generation of ICT solutions for the monitoring, adaptation, simulation, and optimisation of factories. With the democratization of sensors and actuators, factories and machine tools can now be sensorized and the data generated by these devices can be exploited, for instance, to optimize the utilization of the machines as well as their operation and maintenance. However, analysing the vast amount of data generated is resource demanding both in term of computing power and network bandwidth, thus requiring highly scalable solutions. This paper presents a novel big data platform for the management of machine generated data in the cloud. It brings together standard open source technologies which can be adapted to and deployed on different cloud infrastructures, hence reducing costs, minimising deployment difficulty and providing on-demand access to a virtually infinite set of computing, storage and network resources.

There is a rising demand for customised products with a high degree of complexity. To meet these demands, manufacturing lines are increasingly becoming autonomous, networked, and intelligent, with production lines being virtualised into a manufacturing cloud, and advertised either internally to a company, or externally in a public cloud. In this paper, we present a novel approach to two key problems in such future manufacturing systems: the realisability problem (whether a product can be manufactured by a set of manufacturing resources) and the control problem (how a particular product should be manufactured). We show how both production recipes specifying the steps necessary to manufacture a particular product, and manufacturing resources and their topology can be formalised as labelled transition systems, and define a novel simulation relation which captures what it means for a recipe to be realisable on a production topology. We show how a controller that can orchestrate the resources in order to manufacture the product on the topology can be extracted from the simulation relation, and give an algorithm to compute a simulation relation and a controller.

The new market trends are very different, so it is crucial to the companies improve the tools and capabilities that allow themselves readjust rapidly and effectively to the news market changes and to the new requirements. In order to facilitate this process, it is proposed in this paper an agent based implementation that can provide to the existent systems the capacity to quickly adapt and reconfigure using standard technology. The proposed framework provides an intelligent tool to autonomously help the configuration when a production operator pretends to introduce a new variant of product in runtime and consult important information provided by the system to monitor execution.