Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies

: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.

Explainable Artificial Intelligence for Anomaly Detection and Prognostic of Gas Turbines using Uncertainty Quantification with Sensor-Related Data

Explainable artificial intelligence (XAI) is in its assimilation phase in the prognostic and health management (PHM). The literature on PHM-XAI is deficient with respect to metrics of uncertainty quantification and explanation evaluation. This paper proposes a new method of anomaly detection and prognostic for gas turbines using Bayesian deep learning and Shapley additive explanations (SHAP). The method explains the anomaly detection and prognostic and improves the performance of the prognostic, aspects that have not been considered in the literature of PHM-XAI. The uncertainty measures considered serve to broaden explanation scope and can also be exploited as anomaly indicators. Real-world gas turbine sensor-related data are tested for the anomaly detection, while NASA commercial modular aero-propulsion system simulation data, related to turbofan sensors, were used for prognostic. The generated explanation is evaluated using two metrics: consistency and local accuracy. All anomalies were successfully detected using the uncertainty indicators. Meanwhile, the turbofan prognostic results showed up to 9% improvement in root mean square error and 43% enhancement in early prognostic due to the SHAP, making it comparable to the best existing methods. The XAI and uncertainty quantification offer a comprehensive explanation for assisting decision-making. Additionally, the SHAP ability to increase PHM performance confirms its value in AI-based reliability research.

Application of Explainable AI (Xai) For Anomaly Detection and Prognostic of Gas Turbines with Uncertainty Quantification.

XAI is presently in its early assimilation phase in Prognostic and Health Management (PHM) domain. However, the handful of PHM-XAI articles suffer from various deficiencies, amongst others, lack of uncertainty quantification and explanation evaluation metric. This paper proposes an anomaly detection and prognostic of gas turbines using Bayesian deep learning (DL) model with SHapley Additive exPlanations (SHAP). SHAP was not only applied to explain both tasks, but also to improve the prognostic performance, the latter trait being left undocumented in the previous PHM-XAI works. Uncertainty measure serves to broaden explanation scope and was also exploited as anomaly indicator. Real gas turbine data was tested for the anomaly detection task while NASA CMAPSS turbofan datasets were used for prognostic. The generated explanation was evaluated using two metrics: Local Accuracy and Consistency. All anomalies were successfully detected thanks to the uncertainty indicator. Meanwhile, the turbofan prognostic results show up to 9% improvement in RMSE and 43% enhancement in early prognostic due to SHAP, making it comparable to the best published methods in the problem. XAI and uncertainty quantification offer a comprehensive explanation package, assisting decision making. Additionally, SHAP ability in boosting PHM performance solidifies its worth in AI-based reliability research.

Anomalous Amide Proton Chemical Shifts as Signatures of Hydrogen Bonding to Aromatic Sidechains

Hydrogen bonding between an amide group and the p-π cloud of an aromatic ring was first identified in a protein in the 1980s. Subsequent surveys of high-resolution X-ray crystal structures found multiple instances, but their preponderance was determined to be infrequent. Hydrogen atoms participating in a hydrogen bond to the p-π cloud of an aromatic ring are expected to experience an upfield chemical shift arising from a shielding ring current shift. We survey the Biological Magnetic Resonance Data Bank for amide hydrogens exhibiting unusual shifts as well as corroborating nuclear Overhauser effects between the amide protons and ring protons. We find evidence that Trp residues are more likely to be involved in p-π hydrogen bonds than other aromatic amino acids, whereas His residues are more likely to be involved in hydrogen bonds with a ring nitrogen acting as the hydrogen acceptor. The p-π hydrogen bonds may be more abundant than previously believed. The inclusion in NMR structure refinement protocols of shift effects in amide protons from aromatic side chains, or explicit hydrogen bond restraints between amides and aromatic rings, could improve the local accuracy of side-chain orientations in solution NMR protein structures, but their impact on global accuracy is likely be limited.

Integrating Land-Cover Products Based on Ontologies and Local Accuracy

Freely available satellite imagery improves the research and production of land-cover products at the global scale or over large areas. The integration of land-cover products is a process of combining the advantages or characteristics of several products to generate new products and meet the demand for special needs. This study presents an ontology-based semantic mapping approach for integration land-cover products using hybrid ontology with EAGLE (EIONET Action Group on Land monitoring in Europe) matrix elements as the shared vocabulary, linking and comparing concepts from multiple local ontologies. Ontology mapping based on term, attribute and instance is combined to obtain the semantic similarity between heterogeneous land-cover products and realise the integration on a schema level. Moreover, through the collection and interpretation of ground verification points, the local accuracy of the source product is evaluated using the index Kriging method. Two integration models are developed that combine semantic similarity and local accuracy. Taking NLCD (National Land Cover Database) and FROM-GLC-Seg (Finer Resolution Observation and Monitoring-Global Land Cover-Segmentation) as source products and the second-level class refinement of GlobeLand30 land-cover product as an example, the forest class is subdivided into broad-leaf, coniferous and mixed forest. Results show that the highest accuracies of the second class are 82.6%, 72.0% and 60.0%, respectively, for broad-leaf, coniferous and mixed forest.

Accessing Imbalance Learning Using Dynamic Selection Approach in Water Quality Anomaly Detection

Automatic anomaly detection monitoring plays a vital role in water utilities’ distribution systems to reduce the risk posed by unclean water to consumers. One of the major problems with anomaly detection is imbalanced datasets. Dynamic selection techniques combined with ensemble models have proven to be effective for imbalanced datasets classification tasks. In this paper, water quality anomaly detection is formulated as a classification problem in the presences of class imbalance. To tackle this problem, considering the asymmetry dataset distribution between the majority and minority classes, the performance of sixteen previously proposed single and static ensemble classification methods embedded with resampling strategies are first optimised and compared. After that, six dynamic selection techniques, namely, Modified Class Rank (Rank), Local Class Accuracy (LCA), Overall-Local Accuracy (OLA), K-Nearest Oracles Eliminate (KNORA-E), K-Nearest Oracles Union (KNORA-U) and Meta-Learning for Dynamic Ensemble Selection (META-DES) in combination with homogeneous and heterogeneous ensemble models and three SMOTE-based resampling algorithms (SMOTE, SMOTE+ENN and SMOTE+Tomek Links), and one missing data method (missForest) are proposed and evaluated. A binary real-world drinking-water quality anomaly detection dataset is utilised to evaluate the models. The experimental results obtained reveal all the models benefitting from the combined optimisation of both the classifiers and resampling methods. Considering the three performance measures (balanced accuracy, F-score and G-mean), the result also shows that the dynamic classifier selection (DCS) techniques, in particular, the missForest+SMOTE+RANK and missForest+SMOTE+OLA models based on homogeneous ensemble-bagging with decision tree as the base classifier, exhibited better performances in terms of balanced accuracy and G-mean, while the Bg+mF+SMENN+LCA model based on homogeneous ensemble-bagging with random forest has a better overall F1-measure in comparison to the other models.

Assessment of DSM Based on Radiometric Transformation of UAV Data

Unmanned Aerial Vehicle (UAV) is one of the latest technologies for high spatial resolution 3D modeling of the Earth. The objectives of this study are to assess low-cost UAV data using image radiometric transformation techniques and investigate its effects on global and local accuracy of the Digital Surface Model (DSM). This research uses UAV Light Detection and Ranging (LIDAR) data from 80 meters and UAV Drone data from 300 and 500 meters flying height. RAW UAV images acquired from 500 meters flying height are radiometrically transformed in Matrix Laboratory (MATLAB). UAV images from 300 meters flying height are processed for the generation of 3D point cloud and DSM in Pix4D Mapper. UAV LIDAR data are used for the acquisition of Ground Control Points (GCP) and accuracy assessment of UAV Image data products. Accuracy of enhanced DSM with DSM generated from 300 meters flight height were analyzed for point cloud number, density and distribution. Root Mean Square Error (RMSE) value of Z is enhanced from ±2.15 meters to 0.11 meters. For local accuracy assessment of DSM, four different types of land covers are statistically compared with UAV LIDAR resulting in compatibility of enhancement technique with UAV LIDAR accuracy.

Cartesian coordinate control for teleoperated construction machines

Despite the continuous development of the hardware, most construction machines are exclusively teleoperated limiting the control to a single paradigm. The operators usually have to move different joints of the machine in a coordinated way solely relied on their experiences leading to reduced local accuracy and work efficiency. Automation of construction machinery can open up new possibilities to improve efficiency and safety during the construction process. This work introduces a generic method that can adapt construction machines that have been already used in the field for decades, so that a more intuitive and versatile control paradigm can be allowed. We introduce the system architecture with the necessary hardware extension and the closed-loop inverse kinematic based motion controller implemented in a visual programming environment. In contrast to existing works, which are mostly based on developing entirely new systems, an autonomous machine suited for construction sites and other hazardous environments can be obtained at a reduced effort. Because of its low cost and generality, this approach can be widely utilized in construction industries opening possibilities for a combination of the advanced robotics technology with proven machines from construction sites. We present our first prototype system based on a BROKK 170 demolition machine and highlight its capabilities but also the inherent limitations of the proposed method.