Review—Deep Learning Methods for Sensor Based Predictive Maintenance and Future Perspectives for Electrochemical Sensors

Namuduri, Srikanth; Narayanan, Barath Narayanan; Davuluru, Venkata Salini Priyamvada; Burton, L. K.; Bhansali, Shekhar

doi:10.1149/1945-7111/ab67a8

Cited by 118 publications

(59 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning has emerged as a potential data-processing approach to improve selectivity and to compensate for drift error. However, it requires a large amount of labeled data under different circumstances for accurate training of classifier models [59,66,121]. A large dataset (with hundreds/thousands of examples) of a sensor response to a particular analyte will probably result in high redundancies due to the co-existence of data points.…”

Section: Machine Learning-based Smart Gas Sensorsmentioning

confidence: 99%

Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review

Yaqoob

Younis

2021

Sensors

152

View full text Add to dashboard Cite

Nowadays, there is increasing interest in fast, accurate, and highly sensitive smart gas sensors with excellent selectivity boosted by the high demand for environmental safety and healthcare applications. Significant research has been conducted to develop sensors based on novel highly sensitive and selective materials. Computational and experimental studies have been explored in order to identify the key factors in providing the maximum active location for gas molecule adsorption including bandgap tuning through nanostructures, metal/metal oxide catalytic reactions, and nano junction formations. However, there are still great challenges, specifically in terms of selectivity, which raises the need for combining interdisciplinary fields to build smarter and high-performance gas/chemical sensing devices. This review discusses current major gas sensing performance-enhancing methods, their advantages, and limitations, especially in terms of selectivity and long-term stability. The discussion then establishes a case for the use of smart machine learning techniques, which offer effective data processing approaches, for the development of highly selective smart gas sensors. We highlight the effectiveness of static, dynamic, and frequency domain feature extraction techniques. Additionally, cross-validation methods are also covered; in particular, the manipulation of the k-fold cross-validation is discussed to accurately train a model according to the available datasets. We summarize different chemresistive and FET gas sensors and highlight their shortcomings, and then propose the potential of machine learning as a possible and feasible option. The review concludes that machine learning can be very promising in terms of building the future generation of smart, sensitive, and selective sensors.

show abstract

Section: Machine Learning-based Smart Gas Sensorsmentioning

confidence: 99%

Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review

Yaqoob

Younis

2021

Sensors

152

View full text Add to dashboard Cite

show abstract

“…The most successful family of unsupervised methods are those based on neural networks [27][28][29][30], whose detailed description is beyond the scope of this review. In the context of the proposed study, miniaturization of sensors and their management over a WSN can be effectively carried on and an optimal use of resources can be achieved through ML techniques.…”

Section: Machine Learningmentioning

confidence: 99%

Miniaturized Pervasive Sensors for Indoor Health Monitoring in Smart Cities

et al. 2021

View full text Add to dashboard Cite

Sensors and electronics technologies are pivotal in several fields of science and engineering, especially in automation, industry and environment monitoring. Over the years, there have been continuous changes and advancements in design and miniaturization of sensors with the growth of their application areas. Challenges have arisen in the deployment, fabrication and calibration of modern sensors. Therefore, although the usage of sensors has greatly helped improving the quality of life, especially through their employment in many IoT (Internet of Things) applications, some threats and safety issues still remain unaddressed. In this paper, a brief review focusing on pervasive sensors used for health and indoor environment monitoring is given. Examples of technology advancements in air, water and radioactivity are discussed. This bird’s eye view suggests that solid-state pervasive sensors have become essential parts of all emerging applications related to monitoring of health and safety. Miniaturization, in combination with gamification approaches and machine learning techniques for processing large amounts of captured data, can successfully address and solve many issues of massive deployment. The development paradigm of Smart Cities should include both indoor and outdoor scenarios.

show abstract

“…Zhu used RNN to analyze the components and structural change of soil [20]. In addition, defects in electrochemical sensors or polymer were diagnosed using machine learning models such as RNN, LSTM, and CNN [21,22]. Aside from that, RNN is applied to the prediction for temperature control of the variable frequency based oil cooler in the industrial process.…”

Section: Time-series Predictionmentioning

confidence: 99%

“…Quality prediction is carried out by collecting equipment data. In the previous study, sensor data is used to predict and maintain the quality of the process, and there are studies using deep learning and machine learning for sensor-based prediction [21,22]. For improving the quality prediction of small data, we apply SSL to labeling and RNN to generating predictive feature data.…”

Section: Differences From Previous Studiesmentioning

confidence: 99%

Quality Prediction and Yield Improvement in Process Manufacturing Based on Data Analytics

2020

View full text Add to dashboard Cite

Quality management is important for maximizing yield in continuous-flow manufacturing. However, it is more difficult to manage quality in continuous-flow manufacturing than in discrete manufacturing because partial defects can significantly affect the quality of an entire lot of final product. In this paper, a comprehensive framework that consists of three steps is proposed to predict defects and improve yield by using semi-supervised learning, time-series analysis, and classification model. In Step 1, semi-supervised learning using both labeled and unlabeled data is applied to generate quality values. In addition, feature values are predicted in time-series analysis in Step 2. Finally, in Step 3, we predict quality values based on the data obtained in Step 1 and Step 2 and calculate yield values with the use of the predicted value. Compared to a conventional production plan, the suggested plan increases yield by up to 8.7%. The production plan proposed in this study is expected to contribute to not only the continuous manufacturing process but the discrete manufacturing process. In addition, it can be used in early diagnosis of equipment failure.

show abstract

Review—Deep Learning Methods for Sensor Based Predictive Maintenance and Future Perspectives for Electrochemical Sensors

Cited by 118 publications

References 80 publications

Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review

Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review

Miniaturized Pervasive Sensors for Indoor Health Monitoring in Smart Cities

Quality Prediction and Yield Improvement in Process Manufacturing Based on Data Analytics

Contact Info

Product

Resources

About