Remaining useful life estimation - A review on the statistical data driven approaches

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Tackling Climate Change with Machine Learning

https://research.birmingham.ac.uk/portal/files/53643809/APEN2017.pdf

Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review

On condition based maintenance policy

https://hal.archives-ouvertes.fr/hal-01050920/document

Proton exchange membrane fuel cell degradation prediction based on Adaptive Neuro-Fuzzy Inference Systems .

The article proposes an improvement tool, Petri Nets type, dedicated to hierarchical recurrent systems modeling. This tool can be implemented in manufacturing systems served by collaborative robots if the recurrent modeling function is structured on hierarchical levels. Each level is similar with previous ones, from superior hierarchical level, but has allocated different time intervals. In low hierarchical levels, those intervals are bigger, decreasing detection accuracy. Hierarchical levels are interfaced by LIFO module and OOPN (Object Oriented Petri Nets). This new approach base on temporal hierarchical structure, refined monitoring function modeling. On each horizontal level is proposed an elementary detection model, but transitions are associated with external events synchronized with fault occurrence, expected specific temporal windows. Not all the external events may occur in the assigned intervals so the model is designed to evolve to the next level, and to preserve / transferring its set of detected external events. The model evolution is made on every horizontal level, until the node where detection is finished, and moves to the next level.

Application for manufacturing systems served by collaborative robots monitoring

This article proposes an extended approach to assembly/disassembly mechatronics lines (A/DML) modelling, in terms of service system typologies: autonomous mobile robots, collaborative mobile robots versus mobile robots with parallel action. The A/DML systems served by mobile robots have a specific typology and are modelled by specialized hybrid instruments belonging to Petri Nets class: Timed Petri Nets (TPN), Synchronised Hybrid Petri Nets (SHPN). For the reasons imposed by the production manufacturing management, for transporting components, are used mobile robotic platforms equipped with manipulators, which are dedicated or shared status between production manufacturing lines. The collaborative transport systems meet the specific concepts of shared resources with avoiding collisions while the parallel transport systems are subordinated of synchronized actions concepts. This paper focuses on SHPN models and off-line simulation results for the state, boundedness, viability and possible deadlock of process analysis. Task planning is used to identify synchronous events of SHPN model, the last one being useful for implementing of real-time control.

Extended Approach for Modelling and simulation of Mechatronics Lines Served by Collaborative Mobile Robots

In this paper, we present a training technique of a Recurrent Radial Basis Function neural network for fault prediction. We use the Fuzzy Min‐Max technique to initialize the k‐center of the RRBF neural network. The k‐means algorithm is then applied to calculate the centers that minimize the mean square error of the prediction task. The performances of the k‐means algorithm are then boosted by the Fuzzy Min‐Max technique.

Training the Recurrent neural network by the Fuzzy Min‐Max algorithm for fault prediction

This paper aims to describe modeling and control in what concerns advanced manufacturing technology running on a flexible assembly, disassembly and repair on a mechatronic line (A/D/RML) assisted by an Autonomous Robotic System (ARS), two robotic manipulators (RM) and visual servoing system (VSS). The A/D/RML consists of a six workstations (WS) mechatronics line (ML) connected to a flexible cell (FC) equipped with a 6-DOF ABB industrial robotic manipulator (IRM) and an ARS used for manipulation and transport. A hybrid communication and control based on programmable logic controller (PLC) architecture is used, which consists of two interconnected systems that feature both distributed and centralized topology, with specific tasks for all the manufacturing stages. Profinet communication link is used to interconnect and control FC and A/D/RML. The paper also discusses how to synchronize data between different field equipment used in the industry and the control systems. Synchronization signals between the master PLC and ARS is performed by means of Modbus TCP protocol and OPC UA. The structure of the ARS consists of a wheeled mobile robot (WMR) with two driving wheels and one free wheel (2DW/1FW) equipped with a 7-DOF RM. Trajectory tracking sliding-mode control (TTSMC) is used to control WMR. The end effector of the ARS RM is equipped with a mobile eye-in-hand VSS technology for the precise positioning of RM to pick and place the workparts in the desired location. Technology operates synchronously with signals from sensors and from the VSS HD camera. If the workpiece does not pass the quality test, the process handles it by transporting back from the end storage unit to the flexible cell where it will be considered for reprocessing, repair or disassembling with the recovery of the dismantled parts. The recovered or replaced components are taken over by the ARS from disassembling location and transported back to the dedicated storage warehouses to be reused in the further assembly processes.

/pdf/communication-and-control-of-an-assembly-disassembly-and-1dvzd243.pdf

Communication and Control of an Assembly, Disassembly and Repair Flexible Manufacturing Technology on a Mechatronics Line Assisted by an Autonomous Robotic System

This article proposes a temporal recurrent approch of hierarchical systems modeling, symplifing prevoius tools in thies area of th authors. The states of the systems are supposed known for system functioning at every occurence moment. In addition to them, appear external events for nonautonomus system sysncronisation {s i }, with transitions in Temporised Recurrent Petri Nets (TRecPN) model. The sysncronised signals are defined on an assembly of subsets, conditioned by the moment of occurence and the temporal interval when are expected in network. This approch permits an hierarchical approch on levels of Petri Net model. The refining process of the model is made on horisontal. In each place is a PN model, each one is linked with a distinct temporal interval represented by a syncronised signals subset. In an explected syncronised signal doesn't appears, the model functioning will be stoped. Each level is linked with a LIFO object placed on a lower level dedicated to the transfer of the last state reache by the system. In this context, two type of applications are proposed: a) recurrent detection function modelling; b) manufacturing system served by colaborative robots support.

http://ieeexplore.ieee.org/iel5/5876182/5899042/05899165.pdf

Eugenia Minca

Papers

Application for manufacturing systems served by collaborative robots monitoring

Extended Approach for Modelling and simulation of Mechatronics Lines Served by Collaborative Mobile Robots

Training the Recurrent neural network by the Fuzzy Min‐Max algorithm for fault prediction

Communication and Control of an Assembly, Disassembly and Repair Flexible Manufacturing Technology on a Mechatronics Line Assisted by an Autonomous Robotic System

Temporal recurrent modelling appllied to manufacturing flexible lines served by collaborative robots