Mas Irfan P. Hidayat

Neural networks with NARX structure for material lifetime assessment application

In the present paper, neural networks (NN) with non-linear auto-regressive exogenous inputs (NARX) structure is developed and further applied for material lifetime assessment application. Rational of the use of the NARX structure in the application was emphasized and linked to the concept of constant life diagram (CLD), the well known concept in fatigue of material analysis and design. Fatigue life assessment was then performed and realized as one-step ahead prediction with respect to each stress level corresponding to stress ratio values arranged in such a way that transition took place from a fatigue region to another one in the CLD. As a result, material lifetime assessment can be fashioned for a wide spectrum of loading in an efficient manner. The simulation results for different materials and loading situations are presented and discussed.

A new meshless local B-spline basis functions-FD method for two-dimensional heat conduction problems

Purpose – The purpose of this paper is to present a new approach of meshless local B-spline based finite difference (FD) method for solving two dimensional transient heat conduction problems. Design/methodology/approach – In the present method, any governing equations are discretized by B-spline approximation which is implemented in the spirit of FD technique using a local B-spline collocation scheme. The key aspect of the method is that any derivative is stated as neighbouring nodal values based on B-spline interpolants. The set of neighbouring nodes are allowed to be randomly distributed thus enhanced flexibility in the numerical simulation can be obtained. The method requires no mesh connectivity at all for either field variable approximation or integration. Time integration is performed by using the Crank-Nicolson implicit time stepping technique. Findings – Several heat conduction problems in complex domains which represent for extended surfaces in industrial applications are examined to demonstrate ...

Internal geometry effect of structured PLA materials manufactured by dropplet-based 3D printer on its mechanical properties

Rapid Prototyping (RP) technologies, the manufacturing technology with less time consuming including high precission and complicated structure of products, are now become high demanding technologies. Those technologies can be base on top-down or bottom-up approaches. One of the bottom-up approach of RP technology is 3D printing machine. In this research, we have succeed to apply the droplet-based 3D printer to make the structured PLA (Polylactic Acid) materials with different internal geometry structures. The internal geometry used are triangle and honeycomb structure with different size of each symmetry axis of 4.5 mm and 9 mm and the thickness varied of 1 mm and 2 mm as well. The mechanical properties of those structures including tensile and bending stregth are evaluated by using tensile and flexural test respectively. Test results show that the best performance obtained by measuring its tensile and flexural strength is the sampel with triangle geometry of 9 mm geometrical size and 2 mm of thickness. T...

Prediction of composite fatigue life under variable amplitude loading using artificial neural network trained by genetic algorithm

Neural networks (NN) have been widely used in application of fatigue life prediction. In the use of fatigue life prediction for polymeric-base composite, development of NN model is necessary with respect to the limited fatigue data and applicable to be used to predict the fatigue life under varying stress amplitudes in the different stress ratios. In the present paper, Multilayer-Perceptrons (MLP) model of neural network is developed, and Genetic Algorithm was employed to optimize the respective weights of NN for prediction of polymeric-base composite materials under variable amplitude loading. From the simulation result obtained with two different composite systems, named E-glass fabrics/epoxy (layups [(±45)/(0)2]S), and E-glass/polyester (layups [90/0/±45/0]S), NN model were trained with fatigue data from two different stress ratios, which represent limited fatigue data, can be used to predict another four and seven stress ratios respectively, with high accuracy of fatigue life prediction. The accuracy of NN prediction were quantified with the small value of mean square error (MSE). When using 33% from the total fatigue data for training, the NN model able to produce high accuracy for all stress ratios. When using less fatigue data during training (22% from the total fatigue data), the NN model still able to produce high coefficient of determination between the prediction result compared with obtained by experiment.Neural networks (NN) have been widely used in application of fatigue life prediction. In the use of fatigue life prediction for polymeric-base composite, development of NN model is necessary with respect to the limited fatigue data and applicable to be used to predict the fatigue life under varying stress amplitudes in the different stress ratios. In the present paper, Multilayer-Perceptrons (MLP) model of neural network is developed, and Genetic Algorithm was employed to optimize the respective weights of NN for prediction of polymeric-base composite materials under variable amplitude loading. From the simulation result obtained with two different composite systems, named E-glass fabrics/epoxy (layups [(±45)/(0)2]S), and E-glass/polyester (layups [90/0/±45/0]S), NN model were trained with fatigue data from two different stress ratios, which represent limited fatigue data, can be used to predict another four and seven stress ratios respectively, with high accuracy of fatigue life prediction. The accuracy ...

Studi Pengaruh Tubing pada Performa In-Situ Well Repair Menggunakan Material Polyacrylamide dengan Coupled CFD-FEM

Tubing N80 sering digunakan sebagai production tubing, namun sering dilaporkan sering mengalami kebocoran akibat kontak langsung dengan fluida. Beberapa faktor penyebab kebocoran tubing ini yaitu perbedaan temperatur dan tekanan yang berlebih. Terdapat teknologi terbaru yaitu metode patch repair dengan menggunakan material non-logam, polimer superabsorbent. Polimer yang digunakan adalah Polyacrylamide, yang memiliki sifat unik dalam menyerap dan memelihara aliran fluida bertekanan. Akibat keterbatasan informasi tentang teknologi ini, maka mulai dikembangkan simulasi patch terhadap kebocoran tubing. Dalam penelitian ini akan menganalisis distribusi thermal dan deformasi pada tubing beserta patchnya, dengan temperatur operasi yang berbeda. Pembuatan geometri dan simulasi dilakukan dengan menggunakan software ANSYS Mechanical APDL Release 18.0 berdasarkan metode elemen hingga. Penelitian ini diharapkan dapat membantu industri minyak dan gas mensimulasikan kinerja patch terhadap kebocoran tubing, sebelum dilakukan secara praktik.

Simulasi Proses Pemotongan Bubut Baja Karbon Rendah Aisi 1018 dengan Mesin Bubut Menggunakan Metode Elemen Hingga

Tegangan dan gaya pada permukaan material dan perkakas potong dihasilkan oleh sudut dan kedalaman potong yang berbeda. Secara khusus dua analisis berbeda dilakukan untuk membandingkan pengukuran gaya potong dan tegangan geser yaitu dengan kedalaman, sudut potong, dan tipe pemotongan tertentu. Proses simulasi permesinan dilakukan dengan menggunakan alat potong single point High Speed Steel (HSS). Selama proses machining deformasi sangat terkonsentrasi di zona yang sangat kecil dan tegangan yang dihasilkan di zona deformasi mempengaruhi benda kerja dan alat. Telah cukup banyak penelitian yang ditujukan untuk mengembangkan model analitis dan model numerik untuk mensimulasikan proses pemotongan logam untuk memprediksi efek dari variabel machining seperti kecepatan, feed, kedalaman pemotongan dan juga geometri alat dalam deformasi. Analisa dilakukan pada material benda kerja AISI 1018 mild steel dengan menggunakan perkakas potong AISI T15 High Speed Steel. Variabel yang digunakan pada penelitian ini antara lain adalah sudut serpih (rake angle) -15o, 0o, dan 15o, kemudian kedalaman potong yaitu 1 mm dan 1.5 mm, dan yang terakhir adalah membandingkan dua tipe pemotongan yaitu orthogonal (tegak lurus) dan oblique (miring). Pada penelitian ini telah diteliti bagaimana gaya potong dan tegangan geser pada perkakas potong dan material uji pada saat proses pemotongan dan menggunakan metode smooth particle hydrodinamics. Dari hasil simulasi menunjukkan penurunan gaya potong terjadi ketika sudut serpih perkakas mengalami penurunan dari 15o ke -15o, Nilai tegangan maksimum diamati memiliki nilai tertinggi pada sudut 15o dengan kedalaman potong 1.5 mm. Proses simulasi juga telah dilakukan untuk mengamati pengaruh dari kedalaman potong dan tipe pemotongan.

Analisis Pengaruh Flow Rate dan Pressure pada In Situ Well Repair Menggunakan Material Polyacrylamide dengan CFD-FEM Coupling Method

Kebocoran pipa produksi (production tubing) dalam kegiatan eksplorasi minyak bumi dan gas alam dapat mengganggu proses produksi. Untuk itu, diperlukan metode yang tepat untuk memperbaiki kebocoran tubing tanpa menghentikan proses (shutdown). Salah satu metode perbaikan yang dapat digunakan adalah in situ well repair. In situ well repair dilakukan dengan penambalan (patching) menggunakan polimer superabsorbent jenis polyacrylamide pada flow rate dan tekanan tertentu. Pada penelitian ini dilakukan simulasi dengan CFD dan FEM untuk menganalisis pengaruh tekanan dan flow rate yang menghasilkan kemampuan in situ well repair paling optimum untuk mengatasi kebocoran tubing dengan menggunakan software ANSYS. Hasil yang diperoleh yaitu semakin besar flow rate dan tekanan, maka akan semakin besar pula kemungkinan terjadinya deformasi patch pada lokasi in situ well repair. Flow rate yang menghasilkan kemampuan in situ well repair paling optimum adalah 1000 bpd dengan nilai tekanan sebesar 36,82 Pa pada lokasi patch dengan jarak 180 inch dari dasar tubing.

Analisa Pengaruh Desain Gritcone terhadap Pola Patahan Gritcone pada Vertical Roller Mill dengan simulasi Explicit Dynamic (LS-DYNA)

Polysius Vertical Roller Mill adalah coal mill yang digunakan PT Holcim Indonesia untuk menggiling batubara bituminous untuk bahan bakar rotary kiln. Dalam pengoperasiannya, salah satu komponen dari Vertical Roller Mill mengalami kegagalan aus yaitu gritcone. Penelitian ini dilakukan untuk menganalisa perseberan ketebalan dari komponen gritcone dengan disimulasikan secara dinamis eksplisit dan berdasarkan kondisi operasional. Ketebalan dinding dipetakan karena permukaan yang terkena abrasi terdapat patahan mikro di permukaannya. Penelitian dilakukan dengan variasi ketebalan 0.01 m, dan 0.02 m serta variasi desain gritcone dengan radius bawah sebesar 0.165 m, 0.215 m, 0.265 m, 0.315 m, dan 0.365 m. Hasil penelitian menunjukkan pengurangan ketebalan paling besar terjadi pada desain gritcone dengan radius 0.165 m dengan ketebalan 0.01 m dan 0.02 m, dengan pengurangan sebesar 1.423x10-5 m dan 2.45x10-5 m.

System Identification Technique and Neural Networks for Material Lifetime Assessment Application

Modeling of a material lifetime to assess the material useful lifetime during its service in design has been always challenging task. In the present study, a framework of system identification technique based upon nonlinear autoregressive exogenous inputs (NARX) was introduced and presented for material lifetime assessment using neural networks (NN). Using the framework, the task of material lifetime assessment was accomplished in a fashion of one-step ahead prediction with respect to stress level. In addition, by sliding over one-step to one-step of the stress level, the task of prediction dynamically covered all loading spectrum. As a result, material lifetime assessment can be fashioned for a wide spectrum of loading in an efficient manner based upon limited material lifetime data as the basis of the NARX regressor. The multilayer perceptron (MLP)-NARX and radial basis functions NN (RBFNN)-NARX models were developed to predict fatigue lives of composite materials under multiaxial and multivariable loadings. Several multidirectional laminates of polymeric based composites were examined in this study.