Table A2.
Excluded articles according to the publication year.
| ID | Authors, Date | Title | Publisher, Publication Name | Exclusion Reason |
|---|---|---|---|---|
| 1 | [89] Kumar et al., 2016 |
Adaptive cluster tendency visualization and anomaly detection for streaming data | ACM, ACM Transactions on Knowledge Discovery from Data | Non-PHM-XAI implementation/case study |
| 2 | [90] Bao et al., 2016 |
Improved fault detection and diagnosis using sparse global-local preserving projections | Elsevier, Journal of Process Control |
Process monitoring and anomaly detection |
| 3 | [91] Kozjek et al., 2017 |
Interpretative identification of the faulty conditions in a cyclic manufacturing process | Elsevier, Journal of Manufacturing Systems |
Process monitoring and diagnosis |
| 4 | [92] Ragab et al., 2017 |
Fault diagnosis in industrial chemical processes using interpretable patterns based on logical analysis of data | Elsevier, Expert Systems with Applications |
Process monitoring and fault diagnosis |
| 5 | [93] Tang et al., 2018 |
Fisher discriminative sparse representation based on DBN for fault diagnosis of complex system | MDPI, Applied Science |
Process monitoring and fault diagnosis |
| 6 | [94] Luo et al., 2018 |
Knowledge-data-integrated sparse modeling for batch process monitoring | Elsevier, Chemical Engineering Science | Process anomaly detection and diagnosis |
| 7 | [95] Puggini et al., 2018 |
An enhanced variable selection and Isolation Forest based methodology for anomaly detection with OES data | Elsevier, Engineering Applications of Artificial Intelligence |
Process anomaly detection and diagnosis |
| 8 | [96] Cheng et al., 2018 |
Monitoring influent measurements at water resource recovery facility using data-driven soft sensor approach | IEEE, IEEE Sensors Journal |
Process anomaly detection |
| 9 | [97] Zhang et al., 2018 |
Weakly correlated profile monitoring based on sparse multi-channel functional principal component analysis | Taylor and Francis, IISE Transactions |
Process monitoring |
| 10 | [98] Luo et al., 2018 |
Industrial process monitoring based on knowledge-data integrated sparse model and two-level deviation magnitude plots | ACS, Industrial and Engineering Chemistry Research | Process monitoring, anomaly detection and diagnosis |
| 11 | [99] Vojíř et al., 2018 |
EasyMiner.eu: web framework for interpretable machine learning based on rules and frequent item sets | Elsevier, Knowledge-Based Systems |
Only development version offers anomaly detection |
| 12 | [100] Du et al., 2019 |
A condition change detection method for solar conversion efficiency in solar cell manufacturing processes | IEEE, IEEE Transactions on Semiconductor Manufacturing |
Process monitoring and anomaly detection |
| 13 | [101] Keneniet et al., 2019 |
Evolving rule-based explainable artificial intelligence for unmanned aerial vehicles | IEEE, IEEE Access |
Interpret why agent deviate from its mission, not because of system failure |
| 14 | [102] Wang et al., 2019 |
Dynamic soft sensor development based on convolutional neural networks | ACS, Industrial and Engineering Chemistry Research |
Process modelling |
| 15 | [103] Wang et al., 2019 |
Explicit and interpretable nonlinear soft sensor models for influent surveillance at a full-scale wastewater treatment plant | Elsevier, Journal of Process Control |
Process monitoring and variable prediction |
| 16 | [104] Liu et al., 2019 |
Intelligent online catastrophe assessment and preventive control via a stacked denoising autoencoder | Elsevier, Neurocomputing | Black-box |
| 17 | [105] Bukhsh et al., 2019 |
Predictive maintenance using tree-based classification techniques: a case of railway switches | Elsevier, Transportation Research Part C |
Predict maintenance need, activity type and maintenance trigger status |
| 18 | [106] Ragab et al., 2019 |
Deep understanding in industrial processes by complementing human expertise with interpretable patterns of machine learning | Elsevier, Expert Systems with Applications |
Process monitoring and fault diagnosis |
| 19 | [107] Luo et al., 2019 |
Sparse robust principal component analysis with applications to fault detection and diagnosis | ACS, Industrial and Engineering Chemistry Research | Process monitoring, fault detection and diagnosis |
| 20 | [108] Jie et al., 2020 |
Process abnormity identification by fuzzy logic rules and expert estimated thresholds derived certainty factor | Elsevier, Chemometrics and Intelligent Laboratory Systems | Process anomaly diagnosis |
| 21 | [109] Sajedi et al., 2020 |
Dual Bayesian inference for risk-informed vibration-based diagnosis | Wiley, Computer-Aided Civil and Infrastructure Engineering | Uncertainty interpretation, not model’s interpretation |
| 22 | [110] Sun et al., 2020 |
ALVEN: Algebraic learning via elastic net for static and dynamic nonlinear model identification | Elsevier, Computers and Chemical Engineering | Process monitoring and variable prediction |
| 23 | [111] Henriques et al., 2020 |
Combining k-means and XGBoost models for anomaly detection using log datasets | MDPI, Electronics |
Anomaly in project, not engineered system |
| 24 | [112] Gorzałczany et al., 2020 |
A modern data-mining approach based on genetically optimized fuzzy systems for interpretable and accurate smart-grid stability prediction | MDPI, Energies | Electrical grid demand stability in financial perspective |
| 25 | [113] Müller et al., 2020 |
Data or interpretations impacts of information presentation strategies on diagnostic processes | Wiley, Human Factors and Ergonomics in Manufacturing and Service Industries | Experiment with operator effectivity following quality of interpretability |
| 26 | [114] Shriram et al., 2020 |
Least squares sparse principal component analysis and parallel coordinates for real-time process monitoring | ACS, Industrial and Engineering Chemistry Research | Process monitoring and diagnosis |
| 27 | [115] Alshraideh et al., 2020 |
Process control via random forest classification of profile signals: an application to a tapping process | Elsevier, Journal of Manufacturing Processes |
Process monitoring and anomaly detection |
| 28 | [116] Minghua et al., 2020 |
Diagnosing root causes of intermittent slow queries in cloud databases | ACM, Proceedings of the VLDB Endowment |
Diagnosing slow query due to lack of resources, not failure |
| 29 | [117] Shaha et al., 2020 |
Performance prediction and interpretation of a refuse plastic fuel fired boiler | IEEE, IEEE Access |
Performance prediction |
| 30 | [118] Kovalev et al., 2020 |
SurvLIME: a method for explaining machine learning survival models | Elsevier, Knowledge-Based Systems |
Medical survival model |
| 31 | [119] Kovalev et al., 2020 |
A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov.Smirnov bounds | Elsevier, Neural Networks |
Medical survival model |
| 32 | [120] Karn et al., 2021 |
Cryptomining detection in container clouds using system calls and explainable machine learning | IEEE, IEEE Transactions on Parallel and Distributed Systems | Network attack |
| 33 | [121] Gyula et al., 2021 |
Decision trees for informative process alarm definition and alarm-based fault classification | Elsevier, Process Safety and Environmental Protection | Process monitoring and anomaly detection |
| 34 | [122] Zaman et al., 2021 |
Fuzzy heuristics and decision tree for classification of statistical feature-based control chart patterns | MDPI, Symmetry | Process monitoring and diagnosis |
| 35 | [123] Li et al., 2021 |
DTDR-ALSTM: Extracting dynamic time-delays to reconstruct multivariate data for improving attention-based LSTM industrial time series prediction models | Elsevier, Knowledge-Based Systems |
Process monitoring and variable prediction |