Schematic diagram of multi-state diagnosis and prognosis framework (MDP) for tool condition monitoring. 

Schematic diagram of multi-state diagnosis and prognosis framework (MDP) for tool condition monitoring. 

Source publication
Preprint
Full-text available
In this paper, a multi-state diagnosis and prognosis (MDP) framework is proposed for tool condition monitoring via a deep belief network based multi-state approach (DBNMS). For fault diagnosis, a cost-sensitive deep belief network (namely ECS-DBN) is applied to deal with the imbalanced data problem for tool state estimation. An appropriate prognost...

Contexts in source publication

Context 1
... paper proposes a novel multi-state diagnosis and prog- nosis framework (MDP). The schematic diagram of the MDP for TCM decision making is shown in Fig. ...
Context 2
... state estimation is also called fault diagnosis in the MDP framework as shown in Fig. 1. It is naturally an imbalanced classification problem. In real-world applications, the fatal faulty cases are always much fewer than healthy cases. Therefore, we form an imbalanced gun drilling dataset and apply ECS-DBN [43] on this dataset to investigate how well the ECS-DBN could handle with imbalanced data on fault diagnosis. In the ...
Context 3
... wear estimation is the prognostic step in the MDP framework as shown in Fig. 1. In this section, the analysis of the results mainly consists of three parts. Firstly, we evaluate its performance under different signal states. Secondly, the performance of DBNMS approach is evaluated and compared with other single state approaches at algorithmic level. Finally, the comparison between MDP framework and other single ...
Context 4
... Fig. 1 at system level, namely, con- ventional data-driven based, deep learning based and MDP, we summarize the performance of these frameworks in Table. X. Since there is a lack of physical model for these specific gun drills, we do not compare MDP with physical-based [1] 118.7091 ± 9.20 0.8666 ± 0.01 Deep learning based framework (DBN) ...

Similar publications

Article
Full-text available
The collected bearing signals are easily interfered by strong ambient noise due to complex operating conditions. It's a challenge to identify faults accurately and to reduce dependence on model hyper-parameters for intelligent diagnostic methods. This paper proposes an improved ensemble method based on deep belief network (DBN) for fault diagnosis...