A Study on Gradient Boosting Algorithms for Development of AI Monitoring and Prediction Systems

Data-driven predictive maintenance for the prediction of machine failure has been widely studied and performed to test machine failures. Predictive maintenance refers to the machine learning method, which utilizes data for identification of potential system malfunction and provides an alert when a system assessed to be prone to breakdown. The proposed work reveals a novel framework called Artificial Intelligence Monitoring 4.0 (AIM 4.0), which is capable of determining the current condition of equipment and provide a predicted mean time before failure occurs. AIM 4.0 utilizes three different ensemble machine learning methods, including Gradient Boost Machine (GBM), Light GBM, and XGBoost for prediction of machine failures. The machine learning methods stated are implemented to produce acceptable accuracy for the monitoring task as well as producing a prediction with a high confidence level.

[1]  Basilio Sierra,et al.  Predictive Maintenance on the Machining Process and Machine Tool , 2019 .

[2]  Xiaoyu Yang,et al.  A novel diagnostic and prognostic framework for incipient fault detection and remaining service life prediction with application to industrial rotating machines , 2019, Appl. Soft Comput..

[3]  Essam Al Daoud,et al.  Comparison between XGBoost, LightGBM and CatBoost Using a Home Credit Dataset , 2019 .

[4]  Zhigang Tian,et al.  A review on pipeline integrity management utilizing in-line inspection data , 2018, Engineering Failure Analysis.

[5]  Biliang Zhong,et al.  Product marketing prediction based on XGboost and LightGBM algorithm , 2019, AIPR '19.

[6]  Svante Gunnarsson,et al.  Failure detection in robotic arms using statistical modeling, machine learning and hybrid gradient boosting , 2019, Measurement.

[7]  P. E. Komers,et al.  Statistical analysis of environmental consequences of hazardous liquid pipeline accidents , 2018, Heliyon.

[8]  Fabio Babiloni,et al.  A LightGBM-Based EEG Analysis Method for Driver Mental States Classification , 2019, Comput. Intell. Neurosci..

[9]  Izzatdin Abdul Aziz,et al.  Parameter Calculation in Time Analysis for the Approach of Filtering to Select IMFs of EMD in AE Sensors for Leakage Signature , 2019, CSOC.

[10]  Pawel Góra,et al.  Investigating performance of neural networks and gradient boosting models approximating microscopic traffic simulations in traffic optimization tasks , 2018, ArXiv.

[11]  Osmar R. Zaïane,et al.  Detecting the Onset of Machine Failure Using Anomaly Detection Methods , 2019, DaWaK.

[12]  Seong-Hoon Hwang,et al.  Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls , 2020 .

[13]  Saifur Rahman,et al.  Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living , 2020, International journal of environmental research and public health.

[14]  Didrik Nielsen,et al.  Tree Boosting With XGBoost - Why Does XGBoost Win "Every" Machine Learning Competition? , 2016 .

[15]  Mir Jafar Sadegh Safari,et al.  Pipe failure rate prediction in water distribution networks using multivariate adaptive regression splines and random forest techniques , 2019, Urban Water Journal.

[16]  Clay C. Pendarvis.  Pipeline and Hazardous Materials Safety Administration , 2009 .

[17]  José-Raúl Ruiz-Sarmiento,et al.  A predictive model for the maintenance of industrial machinery in the context of industry 4.0 , 2020, Eng. Appl. Artif. Intell..

[18]  B. Dindoruk,et al.  A comparative analysis of bubble point pressure prediction using advanced machine learning algorithms and classical correlations , 2020 .

[19]  Steven X. Ding,et al.  An Improved LightGBM Algorithm for Online Fault Detection of Wind Turbine Gearboxes , 2020, Energies.

[20]  Mario R. Eden,et al.  Formation lithology classification using scalable gradient boosted decision trees , 2019, Comput. Chem. Eng..

[21]  Peng Xu,et al.  Predicting pipeline leakage in petrochemical system through GAN and LSTM , 2019, Knowl. Based Syst..

[22]  Pritika Bahad,et al.  Study of AdaBoost and Gradient Boosting Algorithms for Predictive Analytics , 2019 .

[23]  Abdulhamit Subasi,et al.  Comparison of Bagging and Boosting Ensemble Machine Learning Methods for Automated EMG Signal Classification , 2019, BioMed research international.

[24]  Yufei Xia,et al.  A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring , 2017, Expert Syst. Appl..

[25]  Izzatdin Abdul Aziz,et al.  Machine Failure Prediction Technique Using Recurrent Neural Network Long Short-Term Memory-Particle Swarm Optimization Algorithm , 2019, CSOC.

[26]  Xinrui Liu,et al.  Prediction of Double-High Biochemical Indicators Based on LightGBM and XGBoost , 2019, Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science.

[27]  F. Nasiri,et al.  A Review of Failure Prediction Models for Oil and Gas Pipelines , 2020 .

[28]  Said Nawar,et al.  Comparison between Random Forests, Artificial Neural Networks and Gradient Boosted Machines Methods of On-Line Vis-NIR Spectroscopy Measurements of Soil Total Nitrogen and Total Carbon , 2017, Sensors.

[29]  Kheng Cher Yeo,et al.  Critical review of machine learning approaches to apply big data analytics in DDoS forensics , 2018, 2018 International Conference on Computer Communication and Informatics (ICCCI).

[30]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[31]  Haruna Chiroma,et al.  Machine learning for email spam filtering: review, approaches and open research problems , 2019, Heliyon.

[32]  Duc-Kien Thai,et al.  Gradient tree boosting machine learning on predicting the failure modes of the RC panels under impact loads , 2019, Engineering with Computers.

[33]  Nabil Zemiti,et al.  Optimal Feature Selection for EMG-Based Finger Force Estimation Using LightGBM Model , 2019, 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).

[34]  Xinhan Tong,et al.  Breast Cancer Prediction from Genome Segments with Machine Learning , 2018 .