An integrated machine learning model for aircraft components rare failure prognostics with log-based dataset

Multi-modal LSTM network for anomaly prediction in piston engine aircraft

An aircraft is a highly intricate system that features numerous subsystems, assemblies, and individual components for which regular maintenance is inevitable. The operational efficiency of an aircraft can be maximised, and its maintenance needs can be reduced using an effective yet automatic AI-based health monitoring systems which are more efficient as compared to designing and constructing expensive and harder to operate engine testbeds. It has been observed that aircraft engine anomalies such as undergoing flameouts can occur due to the rapid change in the temperature of the engine. Engine oil temperature and cylinder head temperature, two measures connected to this issue, might be affected differently depending on flight modes and operational conditions which in turn hamper AI-based algorithms to yield accurate prediction on engine failures. In general, previous studies lack comprehensive analysis on anomaly prediction in piston engine aircraft using modern machine learning solutions. Furthermore, abrupt variation in aircraft sensors' data and noise result in either overfitting or unfavourable performance by such techniques. This work aims at studying conventional machine learning and deep learning models to foretell the possibility of engine flameout using engine oil and cylinder head temperatures of a widely used Textron Lycoming IO-540 six-cylinder piston engine. This is achieved through pre-processing the data extracted from the aircraft's real-time flight data recorder followed by prediction using specially designed multi-modal regularised Long Short-Term Memory network to enhance generalisation and avoid overfitting on highly variable data. The proposed architecture yields improved results with root mean square error of 0.55 and 3.20 on cylinder head and engine oil temperatures respectively averaged over three case studies of five different flights. These scores are significantly better i.e., up to 84% as compared to other popular machine learning predictive approaches including Random Forest, Decision Tree Regression, Artificial Neural Networks and vanilla Long Short-Term Memory networks. Through performance evaluation, it can be established that the proposed system is capable of predicting engine flameout 2 minutes ahead and is suitable for integration with the software system of aircraft's engine control unit.

Health prediction of partially observable failing systems under varying environments

The modern engineering systems often operate under varying environments and only partial information can be observed at discrete monitoring epochs. For such systems, few works have been done for the prognostics of health status using the available environment and monitoring information. Therefore, the aim of this article is to present a new health prediction method for modern engineering systems whose condition is partially observable under varying environments. A dynamic Gamma process is proposed to model the system degradation observations under changing environments. To describe the relation of system actual status to the observed information, a proportional hazard (PH) model integrating internal aging and external observations is presented for modeling the system hazard rate. To realize prediction of residual life of such systems, a matrix operation-based prognostic method is presented to calculate the closed-form solutions of health characteristics for the system. A case study of partially observable failing systems is demonstrated, and comparisons with other recent developed approaches are also given to show the effectiveness of the model.

Predicting compressive strength of high-performance concrete with high volume ground granulated blast-furnace slag replacement using boosting machine learning algorithms

Predicting the compressive strength of concrete is a complicated process due to the heterogeneous mixture of concrete and high variable materials. Researchers have predicted the compressive strength of concrete for various mixes using machine learning and deep learning models. In this research, compressive strength of high-performance concrete with high volume ground granulated blast-furnace slag replacement is predicted using boosting machine learning (BML) algorithms, namely, Light Gradient Boosting Machine, CatBoost Regressor, Gradient Boosting Regressor (GBR), Adaboost Regressor, and Extreme Gradient Boosting. In these studies, the BML model’s performance is evaluated based on prediction accuracy and prediction error rates, i.e., R², MSE, RMSE, MAE, RMSLE, and MAPE. Additionally, the BML models were further optimised with Random Search algorithms and compared to BML models with default hyperparameters. Comparing all 5 BML models, the GBR model shows the highest prediction accuracy with R² of 0.96 and lowest model error with MAE and RMSE of 2.73 and 3.40, respectively for test dataset. In conclusion, the GBR model are the best performing BML for predicting the compressive strength of concrete with the highest prediction accuracy, and lowest modelling error.

A rare failure detection model for aircraft predictive maintenance using a deep hybrid learning approach

The use of aircraft operation logs to develop a data-driven model to predict probable failures that could cause interruption poses many challenges and has yet to be fully explored. Given that aircraft is high-integrity assets, failures are exceedingly rare. Hence, the distribution of relevant log data containing prior signs will be heavily skewed towards the typical (healthy) scenario. Thus, this study presents a novel deep learning technique based on the auto-encoder and bidirectional gated recurrent unit networks to handle extremely rare failure predictions in aircraft predictive maintenance modelling. The auto-encoder is modified and trained to detect rare failures, and the result from the auto-encoder is fed into the convolutional bidirectional gated recurrent unit network to predict the next occurrence of failure. The proposed network architecture with the rescaled focal loss addresses the imbalance problem during model training. The effectiveness of the proposed method is evaluated using real-world test cases of log-based warning and failure messages obtained from the fleet database of aircraft central maintenance system records. The proposed model is compared to other similar deep learning approaches. The results indicated an 18% increase in precision, a 5% increase in recall, and a 10% increase in G-mean values. It also demonstrates reliability in anticipating rare failures within a predetermined, meaningful time frame.

Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0

Recently, with the emergence of Industry 4.0 (I4.0), smart systems, machine learning (ML) within artificial intelligence (AI), predictive maintenance (PdM) approaches have been extensively applied in industries for handling the health status of industrial equipment. Due to digital transformation towards I4.0, information techniques, computerized control, and communication networks, it is possible to collect massive amounts of operational and processes conditions data generated form several pieces of equipment and harvest data for making an automated fault detection and diagnosis with the aim to minimize downtime and increase utilization rate of the components and increase their remaining useful lives. PdM is inevitable for sustainable smart manufacturing in I4.0. Machine learning (ML) techniques have emerged as a promising tool in PdM applications for smart manufacturing in I4.0, thus it has increased attraction of authors during recent years. This paper aims to provide a comprehensive review of the recent advancements of ML techniques widely applied to PdM for smart manufacturing in I4.0 by classifying the research according to the ML algorithms, ML category, machinery, and equipment used, device used in data acquisition, classification of data, size and type, and highlight the key contributions of the researchers, and thus offers guidelines and foundation for further research.