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 .

In this paper, two Petri Nets (PN) models of an assembly line and of an integrated mobile platform equipped with manipulator are proposed in order to perform disassembly. The first model is a discrete event model, where, both, the assembly/disassembly line and wheeled mobile robot (WMR) equipped with robotic manipulator (RM) are considered as discrete systems. The second model is a hybrid system in which the line is the discrete event system (DES) and the WMR together with the RM is the continuous system. To the first model, Temporized Petri Nets (TPN) are used in order to model assembly/disassembly tasks of the manufacturing line served by RM mounted on WMR. The WMR is involved only in disassembling operations in order to transport the work pieces from the disassembling locations to the storage locations. To the second model, the cycle performed by the WMR equipped with robotic manipulator is considered as a continuous system. Therefore, Hybrid Petri Nets (HPN) are used in modeling and control. This hybrid system takes into consideration the distribution of the necessary tasks to perform the hybrid disassembly of a component using robots synchronization with flexible line process. Therefore, assembling line becomes reversible.

http://ieeexplore.ieee.org/iel5/6365889/6379186/06379285.pdf

Two approaches in modeling of assembly/disassembly line with integrated manipulator mounted on mobile platform

Due to the complexity of modern distributed power generation, a conventional automation system is not always capable to provide sufficient information, so intelligent control approaches are requiring. This paper is concerned with intelligent control technologies applied to distributed power generation network. Precisely it presents a fuzzy controller based control solution, developed with Matlab that allows the implementation of different renewable energy resources (RES) in a distributed power energy network (PD) and ensures a greater stability.

A fuzzy approach to intelligent control of low voltage electrical networks with distributed power from renewable resources

In the flexible manufacturing environment some processes that until now did not need a close loop control need to be controlled so that the precision of the task permits the continuing of the manufacturing. As the processes are optimized and the manufacturing consists of multiple parallel processes, there is a need of assuring that a product is at a certain location at a certain time. In the control of a task, usually, the output of the system is measured in a timely manner at a certain sampling time. This is usually not possible in the manufacturing processes as a product position is given based on events, by sensors placed at certain locations. Certain event-based PID controllers were proposed and implemented in other control areas but in this controllers the event triggering is given by the error passing a certain level. This kind of controller cannot be implemented given the necessity of high frequency measurement of product position. In this paper we propose an PID event-base controller that uses as triggering event the activation of one of the manufacturing process sensors by the product. As the sensors are placed only in key positions the number of activations is limited. Based on these sensors the PID controller determines the necessary control signals between the key locations.

https://www.mdpi.com/2411-5134/7/4/86/pdf?version=1664194562

Event-based PID control in a flexible manufacturing process

This article proposes a Fuzzy Recurrent Synchronized Petri Networks (PNetSinFREC), dedicated to implementing the recurrent appearance of the functions of monitoring-decision. The proposed instrument improves a previous proposal because it proposes modeling the decision function in both autonomous and non-autonomous hierarchical systems. PNetSinFREC integrates fuzzy logic in modeling temporal aspects of the occurrence of monitored events. We propose two types of structural systems decision: hierarchical autonomous system and hierarchical distributed non-autonomous system. On each level there are events with equal probabilities of occurrence / detection. Proposed typology provides a recurrent behavior to the horizontal firing of the networks, which allows the detection of the occurrence / persistence of the external events monitored. It proposes an application for monitoring of the PNetSinFREC in a distributed system for production / consumption from renewable energy with photovoltaic solar panels.

https://ieeexplore.ieee.org/iel5/5256114/5276086/05276358.pdf

Advanced methods for recurrent hierarchical systems modeling. Application to producer-consumer distributed energy production systems

This paper presents hybrid model for an assembly/disassembly mechatronics line serviced by two mobile robotics systems, working in parallel. The aim is to reverse an assembly line using these mobile platforms. For this purpose, an assembly/disassembly line balancing (A/DLB) and synchronized hybrid Petri nets (SHPN) will be used to model and control an assembly/disassembly mechatronics line (A/DML), with a fixed number of workstations, served by two wheeled mobile robots (WMRs) one of them equipped with a robotic manipulators (RM). The WMR with RM is used for part manipulation and the other for transporting. Moreover, the model operates in synchronized mode with signals from sensors. The SHPN model is hybrid type, where A/DML is the discrete part, and WMRs are the continuous parts. Disassembly starts after the assembly process and after the assembled piece fails the quality test, for recovering the parts. The WMRs are used only during disassembly, to manipulate and transport the parts from the disassembling locations to the storage warehouse locations.

Eugenia Minca

Papers

Two approaches in modeling of assembly/disassembly line with integrated manipulator mounted on mobile platform

A fuzzy approach to intelligent control of low voltage electrical networks with distributed power from renewable resources

Event-based PID control in a flexible manufacturing process

Advanced methods for recurrent hierarchical systems modeling. Application to producer-consumer distributed energy production systems

Hybrid modeling, balancing and control of a mechatronics line served by two mobile robots