Random forests for industrial device functioning diagnostics using wireless sensor networks

Elghazel, Wiem; Medjaher, Kamal; Zerhouni, Noureddine; Bahi, Jacques M.; Farhat, Ahmad; Guyeux, Christophe; Hakem, Mourad

doi:10.1109/aero.2015.7119275

Cited by 22 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of decision is not yet sufficiently developed in the literature. However, there are some works that were proposed in specific contexts, including production scheduling [1], sensors network management [16], battery management [31] and the management of autonomous vehicles [37].…”

Section: Missions Reconfigurationmentioning

confidence: 99%

Post-prognostics decision making in distributed MEMS-based systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

In this paper, the problem of using prognostics information of Micro-Electro-Mechanical Systems (MEMS) for post-prognostics decision in distributed MEMS-based systems is addressed. A strategy of postprognostics decision is proposed and then implemented in a distributed MEMS-based conveying surface. The surface is designed to convey fragile and tiny microobjects. The purpose is to use the prognostics results of the used MEMS in the form of Remaining Useful Life (RUL) to maintain as long as possible a good performance of the conveying surface. For that, a distributed algorithm for distributed decision making in dynamic conditions is proposed. In addition, a simulator to simulate the decision in the targeted system is developed. Simulation results show the importance of the postprognostics decision to optimize the utilization of the system and improve its performance.

show abstract

Section: Missions Reconfigurationmentioning

confidence: 99%

Post-prognostics decision making in distributed MEMS-based systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each point in this figure is an average of error rates of a given algorithm on 20 simulations (for a certain t). As shown in the figure, during t = 0 | t = 40 (if 0 ≤ t ≤ 40), each algorithm has a specific error interval (in %) as follows: [14,20] for SVM, [7,10] for NB, [7,12] for RF, [2,6] for GTB, [4,8] for TBFS, and [12,17] for NN. After that (if t > 40) the error rate for each algorithm increased significantly at these intervals to reach at t = 50, 40 % for SVM, 20 % for NB, 16 % for RF, 30 % for GTB, 18 % for TBFS, and 36 % for NN.…”

Section: B Simulation Resultsmentioning

confidence: 99%

“…In this case, in order to keep connectivity, each sensor will then communicate with the closest active node in the distribution layer as shown in Figure 6b. , each algorithm has a specific error interval (in %) as follows: [15,18] for SVM, [8,10] for NB, [8,12] for RF, [4,6] for GTB, [4,8] for TBFS, and [12,15] for NN. These intervals are approximately the same where the topology is distributed (where the whole network is active), and this is because in these two topologies, there is no data aggregation as the decentralized topology.…”

Section: B Simulation Resultsmentioning

confidence: 99%

“…Our study in this work focused on evaluating these six diagnostic algorithms with the variation of the topology of WSN. These algorithms are: Support Vector Machine (SVM) [5], Naive Bayes (NB) [16], [22], Random Forests (RF) [2], [4], Gradient Tree Boosting (GTB) [3], Tree-Based Feature Selection (TBFS) [19], and Nearest Neighbors (NN) [14].…”

Section: ) Machine Learning Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

On the Topology Effects in Wireless Sensor Networks Based Prognostics and Health Management

Farhat

Makhoul

Guyeux

et al. 2016

2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Co

Self Cite

View full text Add to dashboard Cite

Abstract-In this work, we consider the usage of wireless sensor networks (WSN) to monitor an area of interest, in order to diagnose on real time its state. Each sensor node forwards information about relevant features towards the sink where the data is processed. Nevertheless, energy conservation is a key issue in the design of such networks and once a sensor exhausts its resources, it will be dropped from the network. This will lead to broken links and data loss. It is therefore important to keep the network running for as long as possible by preserving the energy held by the nodes. Indeed, saving the quality of service (QoS) of a wireless sensor network for a long period is very important in order to ensure accurate data. Then, the area diagnosing will be more accurate. From another side, packet transmission is the phase that consumes the highest amount of energy comparing to other activities in the network. Therefore, we can see that the network topology has an important impact on energy efficiency, and thus on data and diagnosis accuracies. In this paper, we study and compare four network topologies: distributed, hierarchical, centralized, and decentralized topology and show their impact on the resulting estimation of diagnostics. We have used six diagnostic algorithms, to evaluate both prognostic and health management with the variation of type of topology in WSN.

show abstract

“…This general discussion emphasizes that Random Forests should be considered in the context of PHM based on wireless sensor networks data [10], and that, due to their robustness and accuracy, they are real alternatives to state-of-the-art PHM algorithms. To illustrate this point by an experimental comparison between random forests and algorithms usually used for diagnosis such as Adaboost and SVM, a new series of simulations will be conducted in the section below.…”

Section: General Comparisonmentioning

confidence: 99%

Reliable diagnostics using wireless sensor networks

Bahi

Elghazel

Guyeux

et al. 2019

Computers in Industry

Self Cite

View full text Add to dashboard Cite

Monitoring activities in industry may require the use of wireless sensor networks, for instance due to difficult access or hostile environment. But it is well known that this type of networks has various limitations like the amount of disposable energy. Indeed, once a sensor node exhausts its resources, it will be dropped from the network, stopping so to forward information about maybe relevant features towards the sink. This will result in broken links and data loss which impacts the diagnostic accuracy at the sink level. It is therefore important to keep the network's monitoring service as long as possible by preserving the energy held by the nodes. As packet transfer consumes the highest amount of energy comparing to other activities in the network, various topologies are usually implemented in wireless sensor networks to increase the network lifetime. In this paper, we emphasize that it is more difficult to perform a good diagnostic when data are gathered by a wireless sensor network instead of a wired one, due to broken links and data loss on the one hand, and deployed network topologies on the other hand. Three strategies are considered to reduce packet transfers: (1) sensor nodes send directly their data to the sink, (2) nodes are divided by clusters, and the cluster heads send the average of their clusters directly to the sink, and (3) averaged data are sent from cluster heads to cluster heads in a hop-by-hop mode, leading to an avalanche of averages. Their impact on the diagnostic accuracy is then evaluated. We show that the use of random forests is relevant for diagnostics when data are aggregated through the network and when sensors stop to transmit their values when their batteries are emptied. This relevance is discussed qualitatively and evaluated numerically by comparing the random forests performance to state-of-the-art PHM approaches, namely: basic bagging of decision trees, support vector machine, multinomial naive Bayes, AdaBoost, and Gradient Boosting. Finally, a way to couple the two best methods, namely the random forests and the gradient boosting, is proposed by finding the best hyperparameters of the former by using the latter.

show abstract

Random forests for industrial device functioning diagnostics using wireless sensor networks

Cited by 22 publications

References 13 publications

Post-prognostics decision making in distributed MEMS-based systems

Post-prognostics decision making in distributed MEMS-based systems

On the Topology Effects in Wireless Sensor Networks Based Prognostics and Health Management

Reliable diagnostics using wireless sensor networks

Contact Info

Product

Resources

About