Renato Ventura Bayan Henriques

A model-based approach for data integration to improve maintenance management by mixed reality

Facilitating interaction with maintenance systems through intuitive interfaces is a competitive advantage in terms of time and costs for industry. This work presents the CARMMI approach, which aims to integrate information coming from CAx tools, mixed/augmented reality tools and embedded intelligent maintenance systems. CARMMI aims to provide support to operators/technicians during maintenance tasks through mixed reality, providing an easier access, understanding and comprehension of information from different systems. Information about where, when and which data will be presented in interface are defined by CARMMI. The paper presents three test cases that were performed using the proposed concepts and infrastructure. The main benefit of the approach is to provide an extensive and generic model for the integration and management of maintenance data through the use of CARMMI.

Fault Detection, Diagnosis and Prediction in Electrical Valves Using Self-Organizing Maps

This paper presents a proactive maintenance scheme for fault detection, diagnosis and prediction in electrical valves. The proposed scheme is validated with a case study, considering a specific valve used for controlling the oil flow in a distribution network. The scheme is based in self-organizing maps, which perform fault detection and diagnosis, and temporal self-organizing maps for fault prediction. The adopted fault model considers deviations either in torque, in the valve’s gate position or in the opening or closing time. The map which performs the fault detection, diagnosis and prediction, is trained with the energy spectral density information, obtained from the torque and position signals by applying the wavelet packet transform. These signals are provided by a mathematical model devised for the electrical valve. The training is performed by fault injection based on parameter deviations over this same mathematical model. The proposed system is embedded into an FPGA-based platform. Experimental results demonstrate the effectiveness of the proposed approaches.

Using Mixed Reality in the Visualization of Maintenance Processes

Abstract The integration of the maintenance systems and mixed reality techniques discussed here focuses on the development of data visualization. The mixed visualization will allow assist the operator during maintenance tasks through the overlap of virtual components in real scene, making possible the operator to work in safe and accurately way in the mixed environment of industrial maintenance.

Embedded Systems Solutions for Fault Detection and Prediction in Electrical Valves

This paper proposes an embedded system architecture for fault detection and prediction in electrical actuators used in pipelines for oil and gas transportation. The proposed system incorporates a signal processing flow that requires low complex mathematical operations using ANSI-C language. However, when described in the hardware description language (HDL), it can be implemented in dedicated field-programmable gate array (FPGA) or ASIC. To prove its functionalities, a test bench was developed, which aims to reproduce in a laboratory some common faults and degradation processes that may occur in real-world field applications. A data acquisition equipment was used to collect the sensors information from specific points of the actuator. The sensor data collected and simulation were used to validate the propose fault detection methodology.

Fault prediction in electrical valves using temporal Kohonen maps

This paper presents a proactive maintenance scheme for the prediction of faults in electrical valves. In our case study, these valves are used for controlling the oil flow in a distribution network. A system implements temporal self-organizing maps for the prediction of faults. These faults lead to deviations either on torque, on the valve end position or on opening/closing time. For fault prediction, one map is trained using data from a mathematical model devised for the electrical valve. The training is performed by fault injection based on three parameter deviations over this same mathematical model. The map learns the energies of the torque and the position that are computed using the wavelet packet transform. Once the map is trained, the system is ready for on-line monitoring of the valve. During the on-line testing phase, the system computes the Euclidean distance and the activation of data series. The biggest activation determines which is the winner neuron of the map for one data series. The obtained results demonstrate a new solution for prediction behavior of these valves.

Blended Learning using GCAR-EAD Environment: Experiences and Application Results

Abstract This paper presents results and experiences of the application of an educational tool called GCAR-EAD Virtual Learning Environment in control systems lessons at the electrical engineering department of our University. The environment offers besides traditional organized educational material also remote experiments and a preliminary tutoring system that guide the student in order to maximize knowledge transfer and self-learning techniques. MOODLE as common virtual learning platform was employed as basis of the environment architecture and several developed tools were integrated to increase the added educational value of the system. Results and students feedback indicate good educational value associated with the system and further development is addressed to enhance the blended learning scenario and effectiveness of the system.

Polyurethane-Based Modular Series Elastic Upgrade to a Robotics Actuator

This article extends previous work, presenting a novel polyurethane based compliant spring system designed to be attached to a conventional robotics servo motor, turning it into a series elastic actuator SEA. The new system is composed by only two mechanical parts: a torsional polyurethane spring and a round aluminum support for link attachment. The polyurethane spring, had its design derived from a iterative FEM-based optimization process. We present also some system identification and practical results using a PID controller for robust position holding.

Design Space Exploration of Embedded Systems for Intelligent Maintenance

With the development of intelligent maintenance techniques, the embedded systems that will be used with such algorithms will need increasingly to present more flexibility, combined with high processing speed and low power consumption. Within this context, model based programming associated with automatic platform-specific code generation capabilities are of great interest. This work performs a design space exploration of some algorithms commonly used on intelligent maintenance applications, in this case wavelet package energies and logistic regression, by analyzing the performance and required footprint of different implementations for intelligent maintenance algorithms when executed in hardware and software. Starting point for the comparison was the so called Watchdog Agent™ IMS system, which is currently available both in MATLAB™ and LabVIEW™ environments. Using available code generation tools distinct hardware and software versions are deployed and both the performance of the generated systems as well as some energy and memory metrics of the resources used in FPGA implementations are compared For the validation tests, vibration data collected from a test bench composed by an electric mechanical actuator was used and obtained results confirmed a great variability of the generated solutions in terms of the assessed metrics, clearly indicating that best solution may vary depending on the application requirements.

Design of an embedded system for the proactive maintenance of electrical valves

This paper presents a proactive maintenance scheme for the detection and diagnosis of faults in electrical valves. In our case study, these actuators are used for controlling the flow in an oil distribution network. An embedded system implements selforganizing maps for the detection and classification of faults that lead to deviations either on torque, or on the valve opening position. For fault detection, the map is trained using a mathematical model devised for the electrical valve. For fault classification, training is performed by fault injection based on parameter deviations over this same mathematical model. In both cases, the maps store the energies of the torque and the opening position that are computed using the wavelet packet transform. Once the maps are trained, the embedded system is ready for online monitoring the actuator. During the on-line testing phase, the embedded system computes the best matching between an acquired input vector (current torque and position energies) and the synaptic weight vector of the trained map. This matching is quantified by computing the Euclidean distance between these vectors and guide the fault detection and classification steps. The complete scheme was prototyped using FPGAs. The results obtained for area, performance and memory requirements point out to a low cost, promising solution for embedding maintenance in electrical actuators.

Sensoring for Retrofitting of an Industrial Robot 1

Abstract Retrofitting of an industrial robot consists on verifying the usability conditions of each component of the robot, replacing obsolete ones, especially electronics and control. This work describes the replacement of the analog sensors (resolvers and tachometers) of a retrofitted ASEA IRB6 robot by digital sensors (incremental optical encoders). The advantages of such replacements are assessed through the use of tachometers and encoders for speed feedback. The control architecture based on a CAN-bus is also presented.