Machine learning algorithms for the prediction of the strength of steel rods: an example of data-driven manufacturing in steelmaking

Implementation of machine learning to increase productivity in the manufacturing industry: a literature review.

“…Penerapan machine learning dalam industri, terutama industri manufaktur banyak diterapkan guna meningkatkan produktivitas dalam proses bisnisnya (Brito et al, 2020) (Ruiz et al, 2020). Datadata yang selama ini diolah secara manual akan di gantikan dengan algoritma dalam machine learning, sehingga di harapkan suatu keputusan penting dapat dilakukan secara cepat dan akurat (Ağbulut et al, 2020).…”

“…SVM = Support Vector Machine; LR = Linear Regression; NB = Naïve Bayes; RF = Random Forest; k-NN = k-Nearest Neighbour; ANN = Artificial Neural Network; GB = Gradient Boosting; BR = Bayesian Ridge; KR = Kernel Ridge; CART = Classification And Regression Trees; RVFL = Random Vector Functional Link; DT = Decision Trees; MP = Multilayer Perception; NN = Neural Network; DBSCAN = Densitybased Spatial Clustering of Applications with Noise; PR = Polynomial Regression; XGB = XG Boost; AB = Ada Boost; ARIMA = Autoregressice model Moving Average; MAL = Mean Absolute Lateness; RMSL = Root Mean Squared Lateness, FR = Fill Rate; FNN = Feed Forward Neural Network; DRBM = Deep Restricted Boltzmann Machine; SAN = Stack Autoencoder Network Berdasarkan beberapa artikel yang berhasil dikumpulkan dapat dilihat pada Tabel 2, bahwa machine learning sangat bermanfaat dalam beberapa aspek peningkatan produktivitas melalui diagnosis dan prediksi dalam membantu pengambilan suatu keputusan secara akurat, diantaranya yakni prediksi untuk meningkatkan akurasi inspeksi terhadap kualitas dengan mendeteksi suatu mesin atau produk dengan probabilitas tinggi menggunakan algoritma neural network (Brito et al, 2020) (Ko et al, 2017) (Park et al, 2016) (Carvajal Soto et al, 2019) (Diren et al, 2019) (Peres et al, 2019) (Escobar & Morales-Menendez, 2018), meningkatkan pengembangan produk untuk dapat mengendalikan variasi terhadap produk dengan menggunakan algoritma DBSCAN(Filz et al, 2020) (Ruiz et al, 2020) (Li, Zhang, et al, 2019), meningkatkan efisiensi dalam proses produksi seperti kontrol stok untuk mengevaluasi persediaan yang diharapkan sehingga menghemat biaya pemeliharaan dengan menggunakan algoritma autoregressive integrated moving average(Kim et al, 2019) (Murphy et al, 2019) (Syafrudin et al, 2018) (Bergmann et al, 2017) (J. H Han & Chi, 2016),. memaksimalkan dalam melaksanakan kegiatan perawatan preventif dan analisa kondisi mesin seperti dengan menggabungkan beberapa algoritma seperti CART, RF, K-NN dan SVM sehingga dapat mengklasifikasikan kondisi keausan alat dengan akurasi tinggi (Li, Liu, et al, 2019) (Paolanti et al, 2018) (Susto et al, 2015).…”

Prediction on the Distributions of the Strength and Toughness of Thick Steel Plates Based on Bayesian Neural Network

“…Predictions on physical properties of manufactures are important problems in various industry areas. For a steelmaking process, several attempts have been made to predict the physical properties using machine learning techniques [1][2][3] and neural networks. [4][5][6][7] Recently, due to a reduction of data collection costs and rapid advances in the artificial intelligence technology, the prediction ability of neural network model has become more accurate.…”

Machine learning based modelling and optimization in hard turning of AISI D6 steel with newly developed AlTiSiN coated carbide tool

“…From the outcomes it was found that the proposed algorithm was very effective regarding diversity and optimization ability. Ruiz et al (2020) predicted the tensile strength of the steel rods by machine learning algorithms those are manufactured in an electric arc furnace. Various ML algorithms are proposed like multiple linear regression, K-Nearest Neighbors, Classification and Regression Tree, Random forest, Adaboost gradient boost algorithms and ANN.…”