Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Harichandran, Aparna; Raphael, Benny; Mukherjee, Abhijit

doi:10.1111/mice.12848

Cited by 11 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to these methods, hybrid studies have used unsupervised and supervised machine learning (HUS-ML) classification algorithms. From these studies, the authors achieved the highest accuracy of 98.46% and F1-score of 78.80% [54]. Our study, including both SML and DL classification algorithms alongside data preprocessing, provides a more comprehensive analysis of not only machine failure class but also all other fault types in the dataset.…”

Section: Discussionmentioning

confidence: 93%

An Efficient Approach for Automatic Fault Classification Based on Data Balance and One-Dimensional Deep Learning

Ileri,

Altun,

Narin

2024

Applied Sciences

View full text Add to dashboard Cite

Predictive maintenance (PdM) is implemented to efficiently manage maintenance schedules of machinery and equipment in manufacturing by predicting potential faults with advanced technologies such as sensors, data analysis, and machine learning algorithms. This paper introduces a study of different methodologies for automatically classifying the failures in PdM data. We first present the performance evaluation of fault classification performed by shallow machine learning (SML) methods such as Decision Trees, Support Vector Machines, k-Nearest Neighbors, and one-dimensional deep learning (DL) techniques like 1D-LeNet, 1D-AlexNet, and 1D-VGG16. Then, we apply normalization, which is a scaling technique in which features are shifted and rescaled in the dataset. We reapply classification algorithms to the normalized dataset and present the performance tables in comparison with the first results we obtained. Moreover, in contrast to existing studies in the literature, we generate balanced dataset groups by randomly selecting normal data and all faulty data for all fault types from the original dataset. The dataset groups are generated with 100 different repetitions, recording performance scores for each one and presenting the maximum scores. All methods utilized in the study are similarly employed on these groups. From these scores, the use of 1D-LeNet deep learning classifiers and feature normalization resulted in achieving the highest overall accuracy and F1-score performance of 98.50% and 98.32%, respectively. As a result, the goal of this study was to develop an efficient approach for automatic fault classification, leveraging data balance, and additionally, to provide an analysis of one-dimensional deep learning and shallow machine learning-based classification methods. In light of the experimentation and comparative analysis, this study successfully achieves its stated goal by demonstrating that one-dimensional deep learning and data balance collectively emerge as the optimal approach, offering good prediction accuracy.

show abstract

Section: Discussionmentioning

confidence: 93%

An Efficient Approach for Automatic Fault Classification Based on Data Balance and One-Dimensional Deep Learning

Ileri,

Altun,

Narin

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…2 . Its main drawback is the long-range dependence problem caused by gradient explosion and gradient disappearance 27 , 28 . Moreover, there will be a large amount of continuous data in the calculation process of backpropagation algorithm over time.…”

Section: Methodsmentioning

confidence: 99%

PM2.5 concentration prediction based on EEMD-ALSTM

Liu,

Ji,

Wang

2024

Sci Rep

View full text Add to dashboard Cite

The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly.

show abstract

“…This problem has become even more pronounced in recent years due to the growing size of construction projects, which renders manual site management and supervision infeasible and further necessitates the need for the development of accurate automated monitoring methods. Automated construction monitoring methods can generally be categorized into sensor‐based (C. Chen et al., 2022; Harichandran et al., 2023; Rafiei & Adeli, 2018) and vision‐based methods (C. Chen et al., 2021; Jung et al., 2023; Zifeng Wang et al., 2022). Considering that videos can provide comprehensive real‐time information about the visual characteristics of the construction site and the physical movements of construction entities, in the past decade, various vision‐based methods have been developed to provide automated activity recognition monitoring information (Ghelmani & Hammad, 2023b; Golparvar‐Fard et al., 2013; X. Luo et al., 2020).…”

Section: Introductionmentioning

confidence: 99%

Improving single‐stage activity recognition of excavators using knowledge distillation of temporal gradient data

Ghelmani,

Hammad

2024

Computer aided Civil Eng

View full text Add to dashboard Cite

Single‐stage activity recognition methods have been gaining popularity within the construction domain. However, their low per‐frame accuracy necessitates additional post‐processing to link the per‐frame detections. Therefore, limiting their real‐time monitoring capabilities is an indispensable component of the emerging construction of digital twins. This study proposes knowledge DIstillation of temporal Gradient data for construction Entity activity Recognition (DIGER), built upon the you only watch once (YOWO) method and improving its activity recognition and localization performance. Activity recognition is improved by designing an auxiliary backbone to exploit the complementary information in the temporal gradient data (transferred into YOWO using knowledge distillation), while localization is improved primarily through integration of complete intersection over union loss. DIGER achieved a per‐frame activity recognition accuracy of 93.6% and localization mean average precision at 50% of 79.8% on a large custom dataset, outperforming state‐of‐the‐art methods without requiring additional computation during inference, making it highly effective for real‐time monitoring of construction site activities.

show abstract

Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework

Cited by 11 publications

References 49 publications

An Efficient Approach for Automatic Fault Classification Based on Data Balance and One-Dimensional Deep Learning

An Efficient Approach for Automatic Fault Classification Based on Data Balance and One-Dimensional Deep Learning

PM2.5 concentration prediction based on EEMD-ALSTM

Improving single‐stage activity recognition of excavators using knowledge distillation of temporal gradient data

Contact Info

Product

Resources

About