Thermal imaging and predictive maintenance: what the future has in store

Author(s):  
R. Salisbury
Semantic Web ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 927-948 ◽  
Author(s):  
Qiushi Cao ◽  
Ahmed Samet ◽  
Cecilia Zanni-Merk ◽  
François de Bertrand de Beuvron ◽  
Christoph Reich

Within manufacturing processes, faults and failures may cause severe economic loss. With the vision of Industry 4.0, artificial intelligence techniques such as data mining play a crucial role in automatic fault and failure prediction. However, due to the heterogeneous nature of industrial data, data mining results normally lack both machine and human-understandable representation and interpretation of knowledge. This may cause the semantic gap issue, which stands for the incoherence between the knowledge extracted from industrial data and the interpretation of the knowledge from a user. To address this issue, ontology-based approaches have been used to bridge the semantic gap between data mining results and users. However, only a few existing ontology-based approaches provide satisfactory knowledge modeling and representation for all the essential concepts in predictive maintenance. Moreover, most of the existing research works merely focus on the classification of operating conditions of machines, while lacking the extraction of specific temporal information of failure occurrence. This brings obstacles for users to perform maintenance actions with the consideration of temporal constraints. To tackle these challenges, in this paper we introduce a novel hybrid approach to facilitate predictive maintenance tasks in manufacturing processes. The proposed approach is a combination of data mining and semantics, within which chronicle mining is used to predict the future failures of the monitored industrial machinery, and a Manufacturing Predictive Maintenance Ontology (MPMO) with its rule-based extension is used to predict temporal constraints of failures and to represent the predictive results formally. As a result, Semantic Web Rule Language (SWRL) rules are constructed for predicting the occurrence time of machinery failures in the future. The proposed rules provide explicit knowledge representation and semantic enrichment of failure prediction results, thus easing the understanding of the inferred knowledge. A case study on a semi-conductor manufacturing process is used to demonstrate our approach in detail. The evaluation of results shows that the MPMO ontology is free of bad practices in the structural, functional, and usability-profiling dimensions. The constructed SWRL rules posses more than 80% of True Positive Rate, Precision, and F-measure, which shows promising performance in failure prediction.


Author(s):  
Joe Symmes

The main objective of predictive maintenance is to identify a small problem before it becomes a big problem. Thermal Imaging is one of the best tools for predictive maintenance. This technology allows us to see a small temperature increase before it becomes a catastrophic failure. Modern technology is able to more accurately evaluate potential problems. The technology allows for collecting better and more extensive data than was previously available — from which very detailed temperature analysis can be made. Thermal inspections of electrical and mechanical systems will show you the necessary areas in your company on which to concentrate your efforts. By focusing specifically on those areas that need to be maintained, you will be saving money several ways: avoiding downtime in production, non-productive wages, greater repair costs and lost time. By performing annual thermal inspections you will also benefit by maintaining the most favorable insurance rating. Paper published with permission.


Injury Extra ◽  
2005 ◽  
Vol 36 (9) ◽  
pp. 395-397 ◽  
Author(s):  
Ronald J Cook ◽  
Shobhan Thakore ◽  
Neil M Nichol
Keyword(s):  

Author(s):  
Yiwei Wang ◽  
Christian Gogu ◽  
Nicolas Binaud ◽  
Christian Bes ◽  
Raphael T Haftka ◽  
...  

Aircraft panel maintenance is typically based on scheduled inspections during which the panel damage size is compared to a repair threshold value, set to ensure a desirable reliability for the entire fleet. This policy is very conservative since it does not consider that damage size evolution can be very different on different panels, due to material variability and other factors. With the progress of sensor technology, data acquisition and storage techniques, and data processing algorithms, structural health monitoring systems are increasingly being considered by the aviation industry. Aiming at reducing the conservativeness of the current maintenance approaches, and, thus, at reducing the maintenance cost, we employ a model-based prognostics method developed in a previous work to predict the future damage growth of each aircraft panel. This allows deciding whether a given panel should be repaired considering the prediction of the future evolution of its damage, rather than its current health state. Two predictive maintenance strategies based on the developed prognostic model are proposed in this work and applied to fatigue damage propagation in fuselage panels. The parameters of the damage growth model are assumed to be unknown and the information on damage evolution is provided by noisy structural health monitoring measurements. We propose a numerical case study where the maintenance process of an entire fleet of aircraft is simulated, considering the variability of damage model parameters among the panel population as well as the uncertainty of pressure differential during the damage propagation process. The proposed predictive maintenance strategies are compared to other maintenance strategies using a cost model. The results show that the proposed predictive maintenance strategies significantly reduce the unnecessary repair interventions, and, thus, they lead to major cost savings.


Sign in / Sign up

Export Citation Format

Share Document