Industrial manufacturing environments are often characterized as being stochastic, dynamic and chaotic, being crucial the implementation of proper maintenance strategies to ensure the production efficiency, since the machines' breakdown leads to a degradation of the system performance, causing the loss of productivity and business opportunities. In this context, the use of emergent ICT technologies, such as Internet of Things (IoT), machine learning and augmented reality, allows to develop smart and predictive maintenance systems, contributing for the reduction of unplanned machines' downtime by predicting possible failures and recovering faster when they occur. This paper describes the deployment of a smart and predictive maintenance system in an industrial case study, that considers IoT and machine learning technologies to support the online and real-time data collection and analysis for the earlier detection of machine failures, allowing the visualization, monitoring and schedule of maintenance interventions to mitigate the occurrence of such failures. The deployed system also integrates machine learning and augmented reality technologies to support the technicians during the execution of maintenance interventions.
Home Health Care (HHC) services are growing worldwide and, usually, the home care visits are manually planned, being a time and effort consuming task that leads to a non optimized solution. The use of some optimization techniques can significantly improve the quality of the scheduling solutions, but lacks the achievement of solutions that face the fast reaction to condition changes. In such stochastic and very volatile environments, the fast rescheduling is crucial to maintain the system in operation. Taking advantage of the inherent distributed and intelligent characteristics of Multi-agent Systems (MAS), this paper introduces a methodology that combines the optimization features provided by centralized scheduling algorithms, e.g. genetic algorithms, with the responsiveness features provided by MAS solutions. The proposed approach was codified in Matlab and NetLogo and applied to a realworld HHC case study. The experimental results showed a significant improvement in the quality of scheduling solutions, as well as in the responsiveness to achieve those solutions.
A challenge is emerging in the design of scheduling support systems and facility layout planning, both for manufacturing environments where dynamic adaptation and optimization become increasingly important on the efficiency and productivity. Focusing on the interactions between these two problems, this work combines two paradigms in sequential manner, optimization techniques and multi-agent systems, to better reflect practical manufacturing scenarios. This approach, in addition to significantly improve the quality of the solutions, enables fast reaction to condition changes. In such stochastic and very volatile environments, the manufacturing industries, the fast rescheduling, or planning, are crucial to maintain the system in operation. The proposed architecture was codified in MatLab R and NetLogo and applied to a realworld job shop case study. The experimental results achieved optimized solutions, as well as in the responsiveness to achieve dynamic results for disruptions and simultaneously layout optimization.
Manufacturing activities and production control are constantly growing. Despite this, it is necessary to improve the increasing variety of scheduling and layout adjustments for dynamic and flexible responses in volatile environments with disruptions or failures. Faced with the lack of realistic and practical manufacturing scenarios, this approach allows simulating and solving the problem of job shop scheduling on a production system by taking advantage of genetic algorithm and particle swarm optimization algorithm combined with the flexibility and robustness of a multi-agent system and dynamic rescheduling alternatives. Therefore, this hybrid decision support system intends to obtain optimized solutions and enable humans to interact with the system to properly adjust priorities or refine setups or solutions, in an interactive and user-friendly way. The system allows to evaluate the optimization performance of each one of the algorithms proposed, as well as to obtain decentralization in responsiveness and dynamic decisions for rescheduling due to the occurance of unexpected events.
The increasing relevance of complex systems in dynamic environments has received special attention during the last decade from the researchers. Such systems need to satisfy products or clients desires, which, after accomplished might change, becoming a very dynamic situation. Currently, decentralized approaches could assist in the automation of dynamic scheduling, based on the distribution of control functions over a swarm network of decision-making entities. Distributed scheduling, in an automatic manner, can be answered by a service coordination architecture of the different schedule components. However, it is necessary to introduce the control layer in the solution, encapsulating an intelligent service that merge agents with optimization methods. Multi-agent systems (MAS) can be combined with several optimization methods to extract the best of the two worlds: the intelligent control, cooperation and autonomy provided by MAS solutions and the optimum offered by optimization methods. The proposal intends to test the intelligent management of the schedule composition quality, in two case studies namely, manufacturing and home health care.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.