Zivana Jakovljevic

Fuzzy inference mechanism for recognition of contact states in intelligent robotic assembly

This paper presents a methodology for generating a fuzzy inference mechanism (FIM) for recognizing contact states within robotic part mating using active compliant motion. In the part mating process, significant uncertainties are inherently present. As a result it is pertinent that contact states recognition systems operating in such environment be able to make decisions on the contact state currently present in the process, based on data full of uncertainties and imprecision. In such conditions, implementation of fuzzy logic and interval inference brings significant robustness to the system. As a starting point for FIM generation, we use a quasi-static model of the mating force between objects. By applying Discrete Wavelet Transform to the signal generated using this model, we extract qualitative and representative features for classification into contact states. Thus, the obtained patterns are optimally classified using support vector machines (SVM). We exploit the equivalence of SVM and Takagi–Sugeno fuzzy rules based systems for generation of FIM for classification into contact states. In this way, crisp granulation of the feature space obtained using SVM is replaced by optimal fuzzy granulation and robustness of the recognition system is significantly increased. The information machine for contact states recognition that is designed using the given methodology simultaneously uses the advantages of creation of machine based on the process model and the advantages of application of FIM. Unlike the common methods, our approach for creating a knowledge base for the inference machine is neither heuristic, intuitive nor empirical. The proposed methodology was elaborated and experimentally tested using an example of a cylindrical peg in hole as a typical benchmark test.

Recognition of Planar Segments in Point Cloud Based on Wavelet Transform

Within industrial automation systems, three-dimensional (3-D) vision provides very useful feedback information in autonomous operation of various manufacturing equipment (e.g., industrial robots, material handling devices, assembly systems, and machine tools). The hardware performance in contemporary 3-D scanning devices is suitable for online utilization. However, the bottleneck is the lack of real-time algorithms for recognition of geometric primitives (e.g., planes and natural quadrics) from a scanned point cloud. One of the most important and the most frequent geometric primitive in various engineering tasks is plane. In this paper, we propose a new fast one-pass algorithm for recognition (segmentation and fitting) of planar segments from a point cloud. To effectively segment planar regions, we exploit the orthonormality of certain wavelets to polynomial function, as well as their sensitivity to abrupt changes. After segmentation of planar regions, we estimate the parameters of corresponding planes using standard fitting procedures. For point cloud structuring, a z-buffer algorithm with mesh triangles representation in barycentric coordinates is employed. The proposed recognition method is tested and experimentally validated in several real-world case studies.

Context sensitive recognition of abrupt changes in cutting process

This paper presents a new generic approach to real-time monitoring of abrupt changes in cutting process. Proposed method is based on hierarchical fuzzy clustering of patterns obtained from discrete wavelet transform (DWT) of acquired signals correlated with cutting force variation in time. Cutting process is naturally highly dynamical and normally consists of mixture of various dynamic phenomena related to the chip formation process and dynamical responses of machining system, workpiece and tool itself. These phenomena are characterized by different time duration. The class of phenomena related to abrupt changes during short time interval is of special importance since they correspond to the most dramatic changes in cutting process, such as various kinds of tool failure or workpiece damage or even breakage. Due to their short time duration, discovery and recognition of these phenomena is extremely difficult. To solve given problem we have chosen DWT, fuzzy clustering and finite state automata as a formal platform for its analysis. Beside its good time localization properties, DWT is, due to asymmetric and irregular shapes of wavelets, especially suitable for analysis of signals having sharp changes or even discontinuities. Given properties make DWT an efficient means for extraction of representative and reliable information contents, thus making good basis for extraction of discriminative and representative features (as DWT coefficients combinations) for classification that will follow. Robustness of specific pattern recognition and learning may be achieved only by taking into consideration wider context. Therefore, in tool condition pattern recognition we have considered the entire context of changes in cutting process state space that precedes and appears after the phenomenon which should be recognized. The cutting process behavior and its evolution in time are considered rather then momentary state which is represented as a point in adopted feature hyperspace of classification machine. Efficiency and practical applicability of developed method is evaluated by extensive experiments in laboratory conditions.

Towards Plug-n-Play numerical control for Reconfigurable Manufacturing Systems

Modern manufacturing systems require fast and effective adaptation to fluctuating market conditions and product diversification. This high level adaptability can be achieved through the utilization of Reconfigurable Manufacturing Systems (RMS), which should be based on modular equipment that is easily integrated, scalable, convertible in terms of functionality, and self diagnosable. RMS also necessitate the use of a dynamic controller architecture that is distributed, fully modular, and self configurable. In this paper, we present a control system design approach for reconfigurable machine tools through the use of modularized and decentralized CNC control. Specifically, we investigate design challenges for Plug-n-Play automation systems, where new system functionalities, such as adding new axes in existing CNC units, can be introduced without significant reconfiguration efforts and downtime costs. We propose a fully decentralized motion control architecture realized through a network of individual axis control modules. Reconfiguration of motion control systems based on this architecture can be achieved by only presenting the controller on each axis with information about machine configuration and the type of axis. This effectively enables modularity, reconfigurability, and interoperability of the machine control system. Finally, we present an implementation of the decentralized architecture based on the use of a real-time operating system, wireless networking, and low-cost ARM Cortex-M3 MCUs; we illustrate its effectiveness by considering machining of a standard test part defined in ISO 10791-7 using a software-in-the-loop testbed.

Recognition of Contact States in Robotized Assembly Using Qualitative Wavelet Based Features and Support Vector Machines

This paper presents a method for recognition of contact states in robotized assembly using an example of cylindrical peg into hole part mating. Starting from force quasi-static model, offline features extraction using Discrete Wavelet Transform and teaching (classification) using Support Vector Machines is carried out. Thus obtained class boundaries together with features extracted from signals of generated contact force vector are used for recognition of contact states on-line. Proposed method is tested using intensive real world experiments.

Cyber Physical Production Systems—An IEC 61499 Perspective

Recent developments in the field of cyber physical systems (CPS) and internet of things (IoT) open up new possibilities in manufacturing. CPS and IoT represent enabling means for facilitating the companies’ adaptation to the ever-changing market needs and adoption of individualized manufacturing paradigm. It is foreseen that implementation of CPS and IoT will lead to new industrial revolution known as Industry 4.0. The fourth industrial revolution will bring about the radical changes in manufacturing process control through distribution of control tasks to intelligent devices. On the other hand, over the last decades International Electrotechnical Commission invested significant efforts in generation of the standard IEC 61499 for distributed automation systems. In this paper we provide the outline of the interconnection of IEC 61499 standard and Reference Architecture Model Industrie 4.0 in cyber physical production systems. The findings of the paper are illustrated using a realistic case study—an example of pneumatic manipulator that is made of CPS devices.

Diagnosis of irregularities in the robotized part mating process based on contextual recognition of contact states transitions

Purpose – The purpose of this paper is to provide a method for the generation of information machines for part mating process diagnosis. Recognition of contact states between parts during robotized part mating represents a significant element of the system for active compliant robot motion. All proposed information machines for contact states recognition will recognize one of the possible contact states even when irregular events in the process occur, and the active motion planner will continue to send commands to robot controller according to the planned trajectory. Design/methodology/approach – The presented framework is based on the general theory of automata and formal languages. Starting from possible regular contact states transitions in part mating, the authors create an automaton for diagnostics, which, besides regular, accepts all irregular (observable and unobservable) process sequences. Findings – Contact states do not appear arbitrarily during regular processes, but in certain context. Theory ...

Intelligent Sensing Systems – Status of Research at KaProm

Within Industrie 4.0 intelligent sensing systems represent an indispensable asset with significant role in enabling shifting from automated to intelligent manufacturing. Instead of being simple transducers, intelligent sensors are able to retrieve useful information from raw signal. They represent systems with integrated computation and communication capabilities, that run sophisticated and real time applicable algorithms and communicate the necessary information to the other elements of the manufacturing facility.

Cyber-Physical Manufacturing Systems (CPMS)

Increased product variety that market needs impose to manufacturers, requires high level adaptability of manufacturing systems that can be achieved through introduction of reconfigurable manufacturing systems composed of interoperable devices with ever-changing architecture. Control and management of such a complex system of systems requires fast and reliable real-time virtualization of real world applications as well as real-time feedback from virtual (cyber) model to the real world. The border line between real-world manufacturing system and its cyber representation is characterized by extremely high information permeability thus composing these two systems into a unique system—Cyber-Physical Manufacturing System (CPMS). Recent advances in the fields of Cyber-Physical Systems (CPS) and Internet of Things (IoT) enable creation of CPMS. In this paper we provide an overview of the research works that are currently conducted in the field of CPMS, and we outline the interconnection between CPMS and Industry 4.0. The motivation of this overview is the identification of the R&D activities that are necessary for industry-wide application of CPMS.

Microcontroller based Control of Disc Brake Actuation Pressure

Monitoring, modeling, prediction, and control of the braking process is a difficult task due to a complex interaction between the brake contact surfaces (disc pads and brake disc). It is caused by different influences of braking regimes and brake operation conditions on its performance. Faster and better control of the braking process is extremely important in order to provide harmonization of the generated braking torque with the tire-road adhesion conditions. It has significant influence on the stopping distance. The control of the braking process should be based on monitoring of the previous and current values of parameters that have influence on the brake performance. Primarily, it is related to the disc brake actuation pressure, the vehicle speed, and the brake interface temperature. The functional relationship between braking regimes and braking torque has to be established and continuously adapted according to the change of mentioned influencing factors. In this paper dynamic neural networks have been used for the purpose of modeling and control of the disc brake actuation pressure. Parameters of the developed dynamic neural model were used to build a program for implementation in a microcontroller. Recurrent neural networks have been implemented in 8-bit CMOS microcontroller for control of the disc brake actuation pressure. Two different models have been developed and integrated into the microcontroller. The first model was used for modeling and prediction of the braking torque. Based on that, the second inverse neural model, has been developed able to predict the brake actuation pressure needed for achieving previously selected (desired) braking torque value.