Anomaly Detection in WAAM Deposition of Nickel Alloys—Single-Material and Cross-Material Analysis
Abstract
:1. Introduction
2. Experimental Materials and Methods
3. Feature Extraction, Data Labeling and Model Architecture
3.1. Feature Extraction and Data Labeling
3.1.1. High Frequency Voltage/Current Feature Extraction
3.1.2. Audio Feature Extraction
3.1.3. Data Labeling
3.2. Model Architecture
3.2.1. Random Forests
3.2.2. Artificial Neural Networks
4. Results and Discussion
4.1. Class Balance Evaluation
4.2. Random Forest Classification
4.3. Artificial Neural Network Regression and Classification
4.4. Cross-Material Analysis
4.5. Discussion
4.6. Predictions between Inconel 718 and Invar 36
4.7. Predictions on Inconel 625
5. Conclusions
- 1.
- Out of the two supervised ML models used for predictions on the single-material defect status of WAAM deposits, for the most part, the random forest model is found to have better results compared to the ANN in terms of accuracy (91.1% vs. 89.4% for Inconel 718), F1 (92.6% vs. 90.3% for Inconel 718) and MCC (83.0% vs. 79.6% for Inconel 718) scores.
- 2.
- Even though welding speed as a parameter is not introduced to the supervised models at any stage of training, the trends seen in the predictive nature of these models show similarities to the energy/length values, which would theoretically require knowledge of the welding speed.
- 3.
- Cross-material predictions between Inconel 718 and Invar 36 are found to heavily depend on the nature of the defect in either material. Training with Inconel 718 is found to lead to overprediction of defects in Invar 36 (recall > 95% and precision < 20%) and Inconel 625 (false positive rate > 92%), whereas training with Invar 36 is found to lead to underprediction of defects in Inconel 718 (precision > 60% and recall < 15%) and Inconel 625 (false positive rate < 46%).
- 4.
- In both random forest and ANN models with a reduced amount of minority class datapoints in the training set (33.3% of total), the testing performance of Inconel 718 was found to be better than Invar 36 in terms of accuracy (91.1% vs. 61.1% for random forest), F1 (92.6% vs. 22.2% for random forest) and MCC (83.0% vs. 27.1% for random forest) scores.
- 5.
- The usage of welding current, welding voltage and audio signals is found to provide information about the stability of the arc. However, tracking additional details such as heat input, weld contaminants, etc. will require additional parameters or sensor responses. One possibility is to include spectroscopic sensing in order to gather arc temperature and arc plasma composition data. In addition, attempting to extract more parameters from the voltage, current and audio data can be helpful.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Chen, X.; Kong, F.; Fu, Y.; Zhao, X.; Li, R.; Wang, G.; Zhang, H. A review on wire-arc additive manufacturing: Typical defects, detection approaches, and multisensor data fusion-based model. Int. J. Adv. Manuf. Technol. 2021, 117, 707–727. [Google Scholar] [CrossRef]
- Zhang, T.; Liu, C.T. Design of titanium alloys by additive manufacturing: A critical review. Adv. Powder Mater. 2022, 1, 100014. [Google Scholar] [CrossRef]
- Workman, G.L. (Ed.) Nondestructive Testing Handbook, 3rd ed.; American Society for Nondestructive Testing: Columbus, OH, USA, 2012; Volume 10. [Google Scholar]
- Bhattacharya, S.; Pal, K.; Pal, S.K. Multi-sensor based prediction of metal deposition in pulsed gas metal arc welding using various soft computing models. Appl. Soft Comput. 2012, 12, 498–505. [Google Scholar] [CrossRef]
- Qiu, W.; Murphy, W.J.; Suter, A. Kurtosis: A New Tool for Noise Analysis. Acoust. Today 2020, 16, 39–47. [Google Scholar] [CrossRef]
- Alfaro, S.C.A.; Cayo, E.H. Sensoring Fusion Data from the Optic and Acoustic Emissions of Electric Arcs in the GMAW-S Process for Welding Quality Assessment. Sensors 2012, 12, 6953–6966. [Google Scholar] [CrossRef] [PubMed]
- Qin, J.; Hu, F.; Liu, Y.; Witherell, P.; Wang, C.C.; Rosen, D.W.; Simpson, T.W.; Lu, Y.; Tang, Q. Research and application of machine learning for additive manufacturing. Addit. Manuf. 2022, 52, 102691. [Google Scholar] [CrossRef]
- Ko, H.; Witherell, P.; Lu, Y.; Kim, S.; Rosen, D.W. Machine learning and knowledge graph based design rule construction for additive manufacturing. Addit. Manuf. 2021, 37, 101620. [Google Scholar] [CrossRef]
- He, F.; Yuan, L.; Mu, H.; Ros, M.; Ding, D.; Pan, Z.; Li, H. Research and application of artificial intelligence techniques for wire arc additive manufacturing: A state-of-the-art review. Robot. Comput. Integr. Manuf. 2023, 82, 102525. [Google Scholar] [CrossRef]
- INCONEL Alloy 718. Technical Report, Special Metals, New York, USA. 2021. Available online: https://www.specialmetals.com/documents/technical-bulletins/inconel/inconel-alloy-718.pdf (accessed on 21 August 2023).
- INVAR 36. Technical Report, Salomon’s Metalen BV, Groningen, The Netherlands. 2020. Available online: https://salomons-metalen.nl/datasheets/Invar_36.pdf (accessed on 21 August 2023).
- INCONEL Alloy 625. Technical Report, Special Metals, New York, USA. 2021. Available online: https://www.specialmetals.com/documents/technical-bulletins/inconel/inconel-alloy-625.pdf (accessed on 21 August 2023).
- The Arc Welding Robot System TAWERS. Technical Report, Panasonic, Osaka, Japan. 2018. Available online: https://industrial.panasonic.com/content/data/WS/PDF/201801_TAWERS_E.pdf (accessed on 21 August 2023).
- Lin, Z.; Ya, W.; Subramanian, V.; Goulas, C.; di Castri, B.; Hermans, M.; Pathiraj, B. Deposition of Stellite 6 alloy on steel substrates using wire and arc additive manufacturing. Int. J. Adv. Manuf. Technol. 2020, 111, 411–426. [Google Scholar] [CrossRef]
- Bevans, B.; Ramalho, A.; Smoqi, Z.; Gaikwad, A.; Santos, T.G.; Rao, P.; Oliveira, J. Monitoring and flaw detection during wire-based directed energy deposition using in-situ acoustic sensing and wavelet graph signal analysis. Mater. Des. 2023, 225, 111480. [Google Scholar] [CrossRef]
- Ramalho, A.; Santos, T.G.; Bevans, B.; Smoqi, Z.; Rao, P.; Oliveira, J. Effect of contaminations on the acoustic emissions during wire and arc additive manufacturing of 316L Stainless Steel. Addit. Manuf. 2022, 51, 102585. [Google Scholar] [CrossRef]
- Hauser, T.; Reisch, R.T.; Kamps, T.; Kaplan, A.F.; Volpp, J. Acoustic emissions in directed energy deposition processes. Int. J. Adv. Manuf. Technol. 2022, 119, 3517–3532. [Google Scholar] [CrossRef]
- Sainburg, T.; Thielk, M.; Gentner, T.Q. Finding, visualizing, and quantifying latent structure across diverse animal vocal repertoires. PLoS Comput. Biol. 2020, 16, e1008228. [Google Scholar] [CrossRef] [PubMed]
- O’Shaughnessy, D. Speech Communication: Human and Machine; Addison-Wesley: Boston, MA, USA, 1987; p. 150. [Google Scholar]
- 2017 ASME Boiler & Pressure Vessel Code Section VIII Division; ASME: New York, NY, USA, 2017.
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Menze, B.H.; Kelm, B.M.; Masuch, R.; Himmelreich, U.; Bachert, P.; Petrich, W.; Hamprecht, F.A. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of Spectral Data. BMC Bioinform. 2009, 10, 213. [Google Scholar] [CrossRef] [PubMed]
- Grossi, E.; Buscema, M. Introduction to artificial neural networks. Eur. J. Gastroenterol. Hepatol. 2008, 19, 1046–1054. [Google Scholar] [CrossRef] [PubMed]
- Rithani, M.; Kumar, R.; Doss, S. A review on big data based on deep neural network approaches. Artif. Intell. Rev. 2023, 56, 14765–14801. [Google Scholar] [CrossRef]
- Buda, M.; Maki, A.; Mazurowski, M.A. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 2018, 106, 249–259. [Google Scholar] [CrossRef]
- Leevy, J.; Khoshgoftaar, T.; Bauder, R.; Seliya, N. A survey on addressing high-class imbalance in big data. J. Big Data 2018, 5. [Google Scholar] [CrossRef]
- Johnson, J.; Khoshgoftaar, T. Survey on deep learning with class imbalance. J. Big Data 2019, 6, 27. [Google Scholar] [CrossRef]
- Elmrabit, N.; Zhou, F.; Li, F.; Zhou, H. Evaluation of Machine Learning Algorithms for Anomaly Detection. In Proceedings of the 2020 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Dublin, Ireland, 15–19 June 2020; pp. 1–8. [Google Scholar] [CrossRef]
- Aminikhanghahi, S.; Cook, D.J. A survey of methods for time series Change point detection. Knowl. Inf. Syst. 2016, 51, 339–367. [Google Scholar] [CrossRef] [PubMed]
- Chicco, D.; Jurman, G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom. 2020, 21, 6. [Google Scholar] [CrossRef] [PubMed]
- Zoubir, A.; Iskander, D. Bootstrap Methods and Applications. Signal Process. Mag. IEEE 2007, 24, 10–19. [Google Scholar] [CrossRef]
- Nandeshwar, A.R. Models for Calculating Confidence Intervals for Neural Networks. Master’s Thesis, College of Engineering and Mineral Resources at West Virginia University, Morgantown, WV, USA, 2006. [Google Scholar]
- Lundberg, S.; Lee, S.I. A Unified Approach to Interpreting Model Predictions. arXiv 2017, arXiv:cs.AI/1705.07874. [Google Scholar]
- Fiocchi, J.; Casati, R.; Tuissi, A.; Biffi, C.A. Laser beam welding of cocufemnni high entropy alloy: Processing, microstructure, and mechanical properties. Adv. Eng. Mater. 2022, 24, 10. [Google Scholar] [CrossRef]
- Raza, S. Superalloys: An introduction with thermal analysis. J. Fundam. Appl. Sci. 2015, 7, 364. [Google Scholar] [CrossRef]
- Tinoco, J.; Fredriksson, H. Solidification of a modified Inconel 625 alloy under different cooling rates. High Temp. Mater. Process. 2004, 23, 13–24. [Google Scholar] [CrossRef]
- Obidigbo, C.N.; Gockel, J. A Numerical and Experimental Investigation of Steady-State and Transient Melt Pool Dimensions in Additive Manufacturing of Invar 36. Master’s Thesis, Wright State University, Dayton, OH, USA, 2017. Available online: https://corescholar.libraries.wright.edu/cgi/viewcontent.cgi?article=2962&context=etd_all (accessed on 21 August 2023).
- Artaza, T.; Bhujangrao, T.; Suárez, A.; Veiga, F.; Lamikiz, A. Influence of Heat Input on the Formation of Laves Phases and Hot Cracking in Plasma Arc Welding (PAW) Additive Manufacturing of Inconel 718. Metals 2020, 10, 771. [Google Scholar] [CrossRef]
- The formation and control of Laves phase in superalloy 718 welds. J. Mater. Sci. 1997, 32, 1977–1984. [CrossRef]
- Scipioni Bertoli, U.; Wolfer, A.J.; Matthews, M.J.; Delplanque, J.P.R.; Schoenung, J.M. On the limitations of Volumetric Energy Density as a design parameter for Selective Laser Melting. Mater. Des. 2017, 113, 331–340. [Google Scholar] [CrossRef]
- Li, Y.; Polden, J.; Pan, Z.; Cui, J.; Xia, C.; He, F.; Mu, H.; Li, H.; Wang, L. A defect detection system for wire arc additive manufacturing using incremental learning. J. Ind. Inf. Integr. 2022, 27, 100291. [Google Scholar] [CrossRef]
Element | Fe | Ni | Cr | Nb | Mo | Ti | Co | Mn | Si |
---|---|---|---|---|---|---|---|---|---|
Inconel 718 | 17 | 50–55 | 17–21 | 4.75–5.50 | 2.80–3.30 | 0.65–1.15 | ≤1 | ≤0.35 | ≤0.53 |
Inconel 625 | ≤5 | ≥58 | 20–23 | 3.15–4.15 | 8–10 | ≤0.4 | ≤1 | ≤0.5 | ≤0.5 |
Invar 36 | 63 | 36 | - | - | - | - | - | 0.35 | 0.20 |
Sl. No. | Test Type | Inconel 718 | Invar 36 | Inconel 625 |
---|---|---|---|---|
1 | Single Beads | 15 | 9 | 6 |
2 | Single Bead Walls | 0 | 136 | 0 |
3 | Block Walls/Pyramids | 166 | 0 | 16 |
Total | 181 | 145 | 22 |
Parameter | Symbol | Description |
---|---|---|
Voltage peak count variance | The variance of the number of peaks per voltage pulse | |
Voltage peak width variance | The variance of the voltage pulse widths | |
Current peak count variance | The variance of the number of peaks per current pulse | |
Current peak width variance | The variance of the current pulse widths | |
Audio kurtosis | Kurtosis of filtered audio signal | |
Audio spectral variance | Variance of 3072 Hz–8192 Hz frequency band of audio Mel spectrogram |
Hyperparameter | Value |
---|---|
Number of trees (n_estimators) | 1000 |
Maximum tree depth (max_depth) | 8 |
Criterion (criterion) | Entropy |
Number of features at node | 2 |
Hyperparameter | Value |
---|---|
Number of hidden layers | 4 |
Number of neurons per layer | 25 |
Activation function | ReLU (hidden layers), Sigmoid (output layer) |
Loss | Binary cross entropy |
Optimizer | Adam |
Optimizer learning rate | 0.0004 |
Number of epochs | 450 |
Material | Inconel 718 | Inconel 625 | Invar 36 |
---|---|---|---|
Clean | 30 | 22 | 121 |
Defective | 151 | 0 | 24 |
Imbalance Ratio | 5.033 | ∞ | 5.042 |
Evaluation Metric | Inconel 718 | Invar 36 |
---|---|---|
Accuracy | 0.911 | 0.611 |
Precision | 0.862 | 1.000 |
Recall | 1.000 | 0.125 |
False Positive Rate (FPR) | 0.200 | 0.000 |
F1 | 0.926 | 0.222 |
Matthew’s Correlation Coefficient (MCC) | 0.830 | 0.271 |
Evaluation Metric | Inconel 718 | Invar 36 |
---|---|---|
Mean Squared Error (MSE) | 0.086 (95% CI {0.084, 0.089}) | 0.358 (95% CI {0.355, 0.362}) |
Root Mean Squared Error (RMSE) | 0.286 (95% CI {0.282, 0.290}) | 0.597 (95% CI {0.595, 0.600}) |
Mean Absolute Error (MAE) | 0.092 (95% CI {0.089, 0.095}) | 0.368 (95% CI {0.365, 0.371}) |
Evaluation Metric | Inconel 718 | Invar 36 |
---|---|---|
Accuracy | 0.894 (95% CI {0.887, 0.901}) | 0.611 (95% CI {0.605, 0.617}) |
Precision | 0.844 (95% CI {0.835, 0.853}) | 0.846 (95% CI {0.831, 0.860}) |
Recall | 0.972 (95% CI {0.961, 0.982}) | 0.271 (95% CI {0.259, 0.282}) |
False Positive Rate (FPR) | 0.202 (95% CI {0.197, 0.208}) | 0.117 (95% CI {0.099, 0.135}) |
F1 | 0.903 (95% CI {0.893, 0.912}) | 0.354 (95% CI {0.346, 0.363}) |
Matthew’s Correlation Coefficient (MCC) | 0.796 (95% CI {0.781, 0.810}) | 0.245 (95% CI {0.230, 0.259}) |
Evaluation Metric | Score on Invar 36 | Score on Inconel 625 |
---|---|---|
Accuracy | 0.258 (95% CI {0.245, 0.272}) | 0.078 (95% CI {0.069, 0.087}) |
Precision | 0.181 (95% CI {0.178, 0.184}) | 0.000 (95% CI {0.000, 0.000}) |
Recall | 0.962 (95% CI {0.954, 0.969}) | N/A |
False Positive Rate (FPR) | 0.881 (95% CI {0.865, 0.898}) | 0.922 (95% CI {0.913, 0.931}) |
F1 | 0.303 (95% CI {0.299, 0.307}) | 0.000 (95% CI {0.000, 0.000}) |
Matthew’s Correlation Coefficient (MCC) | 0.086 (95% CI {0.076, 0.097}) | N/A |
Evaluation Metric | Score on Inconel 718 | Score on Inconel 625 |
---|---|---|
Accuracy | 0.271 (95% CI {0.260, 0.281}) | 0.681 (95% CI {0.643, 0.720}) |
Precision | 0.906 (95% CI {0.884, 0.928}) | 0.000 (95% CI {0.000, 0.000}) |
Recall | 0.144 (95% CI {0.131, 0.158}) | N/A |
False Positive Rate (FPR) | 0.093 (95% CI {0.071, 0.116}) | 0.319 (95% CI {0.280, 0.357}) |
F1 | 0.234 (95% CI {0.216, 0.252}) | 0.000 (95% CI {0.000, 0.000}) |
Matthew’s Correlation Coefficient (MCC) | 0.064 (95% CI {0.043, 0.084}) | N/A |
Evaluation Metric | Score on Invar 36 | Score on Inconel 625 |
---|---|---|
Accuracy | 0.172 | 0.000 |
Precision | 0.162 | 0.000 |
Recall | 0.958 | N/A |
False Positive Rate (FPR) | 0.983 | 1.000 |
F1 | 0.277 | 0.000 |
Matthew’s Correlation Coefficient (MCC) | -0.066 | N/A |
Evaluation Metric | Score on Inconel 718 | Score on Inconel 625 |
---|---|---|
Accuracy | 0.199 | 0.545 |
Precision | 0.636 | 0.000 |
Recall | 0.093 | N/A |
False Positive Rate (FPR) | 0.267 | 0.455 |
F1 | 0.162 | 0.000 |
Matthew’s Correlation Coefficient (MCC) | -0.198 | N/A |
Material | Volumetric Melting Energy (J/mm3) | Clean | Dirty | ||
---|---|---|---|---|---|
Power (W) | Arc Energy/Length (J/mm) | Power (W) | Arc Energy/Length (J/mm) | ||
Inconel 718 | 5.92 | 3201.88 | 291.08 | 2938.61 | 322.57 |
Inconel 625 | 6.86 | 3769.24 | 339.62 | - | - |
Invar 36 | 7.99 | 2216.95 | 308.84 | 2492.30 | 536.46 |
ML Model | Trained on Inconel 718 Tested on Invar 36 | Trained on Invar 36 Tested on Inconel 718 | ||||
---|---|---|---|---|---|---|
Precision | Recall | F1 | Precision | Recall | F1 | |
ANN | 0.181 | 0.962 | 0.303 | 0.906 | 0.144 | 0.234 |
RF | 0.162 | 0.958 | 0.277 | 0.636 | 0.093 | 0.267 |
ML Model | Trained on Inconel 718 | Trained on Invar 36 |
---|---|---|
ANN | 0.922 | 0.319 |
RF | 1.000 | 0.455 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Rajesh, A.; Ya, W.; Hermans, M. Anomaly Detection in WAAM Deposition of Nickel Alloys—Single-Material and Cross-Material Analysis. Metals 2023, 13, 1820. https://doi.org/10.3390/met13111820
Rajesh A, Ya W, Hermans M. Anomaly Detection in WAAM Deposition of Nickel Alloys—Single-Material and Cross-Material Analysis. Metals. 2023; 13(11):1820. https://doi.org/10.3390/met13111820
Chicago/Turabian StyleRajesh, Aditya, Wei Ya, and Marcel Hermans. 2023. "Anomaly Detection in WAAM Deposition of Nickel Alloys—Single-Material and Cross-Material Analysis" Metals 13, no. 11: 1820. https://doi.org/10.3390/met13111820
APA StyleRajesh, A., Ya, W., & Hermans, M. (2023). Anomaly Detection in WAAM Deposition of Nickel Alloys—Single-Material and Cross-Material Analysis. Metals, 13(11), 1820. https://doi.org/10.3390/met13111820