An Explainable DL-Based Condition Monitoring Framework for Water-Emulsified Diesel CR Systems

Despite global patronage, diesel engines still contribute significantly to urban air pollution, and with the ongoing campaign for green automobiles, there is an increasing demand for controlling/monitoring the pollution severity of diesel engines especially in heavy-duty industries. Emulsified diesel fuels provide a readily available solution to engine pollution; however, the inherent reduction in engine power, component corrosion, and/or damage poses a major concern for global adoption. Notwithstanding, on-going investigations suggest the need for reliable condition monitoring frameworks to accurately monitor/control the water-diesel emulsion compositions for inevitable cases. This study proposes the use of common rail (CR) pressure differentials and a deep one-dimensional convolutional neural network (1D-CNN) with the local interpretable model-agnostic explanations (LIME) for empirical diagnostic evaluations (and validations) using a KIA Sorento 2004 four-cylinder line engine as a case study. CR pressure signals were digitally extracted at various water-in-diesel emulsion compositions at various engine RPMs, pre-processed, and used for necessary transient and spectral analysis, and empirical validations. Results reveal high model trustworthiness with an average validation accuracy of 95.9%.

Download Full-text

Condition Monitoring with Prediction Based on Oil Engines of Urban Buses – A Case Study

10.20944/preprints201811.0167.v1 ◽

2018 ◽

Cited By ~ 1

Author(s):

Hugo Raposo ◽

José Torres Farinha ◽

Inácio Fonseca ◽

Luis Ferreira

Keyword(s):

Condition Monitoring ◽

Diesel Engines ◽

Predictive Maintenance ◽

Maintenance Policy ◽

Normal Functioning ◽

The Real ◽

Maintenance Policies

The paper presents a case study and a model for condition monitoring of Diesel engines’ oil of urban buses, through the accompaniment of the evolution of its degradation, with the objective to implement a predictive maintenance policy. Along time, because the usage, there is some decay in the lubricant properties. However, in normal functioning conditions, the lubricants properties, at the time the manufacturers recommend its changing, regardless of they are within the safety limits. Then, based on the accompaniment of the lubricants’ oil condition, the intervals of oil replacement can be enlarged what implies the availability increasing and the corresponding production increasing of the equipment. The model presented in this paper shows its potential to be spread to other types of equipment and organisations that want can implement similar maintenance policies, to achieve the best availability based on the real equipment health conditioning conditions

Download Full-text

Stamping Monitoring by Using an Adaptive 1D Convolutional Neural Network

Sensors ◽

10.3390/s21010262 ◽

2021 ◽

Vol 21 (1) ◽

pp. 262

Author(s):

Chih-Yung Huang ◽

Zaky Dzulfikri

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Template Matching ◽

Health Condition ◽

Vibration Measurement ◽

One Dimensional ◽

Stamping Process ◽

Metalworking Industry ◽

Increasing Demand ◽

Wear Condition

Stamping is one of the most widely used processes in the sheet metalworking industry. Because of the increasing demand for a faster process, ensuring that the stamping process is conducted without compromising quality is crucial. The tool used in the stamping process is crucial to the efficiency of the process; therefore, effective monitoring of the tool health condition is essential for detecting stamping defects. In this study, vibration measurement was used to monitor the stamping process and tool health. A system was developed for capturing signals in the stamping process, and each stamping cycle was selected through template matching. A one-dimensional (1D) convolutional neural network (CNN) was developed to classify the tool wear condition. The results revealed that the 1D CNN architecture a yielded a high accuracy (>99%) and fast adaptability among different models.

Download Full-text

On the Application of the Lu-Gre Model to Simulate Joint Friction in Multi-Body Systems

Volume 4: 8th International Conference on Multibody Systems, Nonlinear Dynamics, and Control, Parts A and B ◽

10.1115/detc2011-47360 ◽

2011 ◽

Author(s):

Kedar Gajanan Kale ◽

Rajiv Rampalli

Keyword(s):

Friction Model ◽

Lugre Model ◽

Friction Forces ◽

Joint Friction ◽

Modeling Techniques ◽

Static Regime ◽

Increasing Demand ◽

Automotive Suspension ◽

Multi Body

Advances in the application of multi-body simulation technology to real world problems have led to an ever increasing demand for higher fidelity modeling techniques. Of these, accurate modeling of friction is of strategic interest in applications such as control system design, automotive suspension analysis, robotics etc. Joints (sometimes referred to as constraints) play an important role in defining the dynamics of a multi-body system. Hence, it is imperative to accurately account for friction forces arising at these joints due to the underlying interface dynamics. In this paper, we discuss the application of LuGre, a dynamic friction model to simulate joint friction. We choose the LuGre model due to its ability to capture important effects such as the Stribeck effect and the Dahl effect. The native 1-d LuGre model is extended to formulate friction computations for non-trivial joint geometries and dynamics in 2 and 3 dimensions. It is also extended to work in the quasi-static regime. Specific applications to revolute, cylindrical and spherical joints in multi-body systems are discussed. Finally, an engineering case study on the effects of joint friction in automotive suspension analysis is presented.

Download Full-text

THE CHANCES FOR REDUCTION OF VIBRATIONS IN MECHANICAL SYSTEM WITH LOW-EMISSION SHIPS COMBUSTION ENGINES

The International Journal of Maritime Engineering ◽

10.5750/ijme.v157ia4.964 ◽

2021 ◽

Vol 157 (A4) ◽

Author(s):

R Grega ◽

J Homišin ◽

M Puškár ◽

J Kul’ka ◽

J Petróci ◽

...

Keyword(s):

Mechanical System ◽

Diesel Engines ◽

Fuel Mixture ◽

Adverse Impact ◽

Exhaust Gas ◽

Combustion Engines ◽

Low Emission ◽

Power Outputs ◽

Exhaust Gas Emissions ◽

Engine Power

Development of diesel engines is focused on reduction of exhaust gas emissions, increase of efficiency of the fuel mixture combustion and decrease of fuel consumption. Such engines are referred to as low-emission engines. Low- engines trends bring higher engine power outputs, torques and also increase of vibrations and noisiness level. In order to reduce these vibrations of diesel engines, it is necessary to apply different dynamical elements, which are able to increase an adverse impact of exciting amplitudes. One of the results is application of a pneumatic dual-mass flywheel. The pneumatic dual-mass flywheel is a dynamical element that consists of two masses (the primary and the secondary mass), which are jointed together by means of a flexible interconnection. This kind of the flywheel solution enables to change resonance areas of the mechanical system which consequently leads to reduction of vibrations.

Download Full-text

The SMART SRP Well – Application of Edge Analytics for Automated Well Performance Control and Condition Monitoring in a Mature Brownfield Environment – A Case Study from Austria

10.2118/208521-ms ◽

2021 ◽

Author(s):

Christian Windisch

Keyword(s):

Condition Monitoring ◽

Data Communication ◽

Holistic Approach ◽

Well Performance ◽

Measuring Device ◽

Technology Transfers ◽

Failure Conditions ◽

Diverse Data ◽

Bottomhole Pressure

Abstract This paper presents a holistic approach to modern oilfield and well surveillance through the inclusion of state-of-the-art edge computing applications in combination with a novel type of data transmission technology and algorithms developed in-house for automatic condition monitoring of SRP systems. The objective is to enable the responsible specialist staff to focus on the most important decisions regarding oilfield management, rather than wasting time with data collection and preparation. An own operated data communication system, based on LPWAN-technology transfers the dyno-cards, generated by an electric load cell, into the in-house developed production assistance software platform. Suitable programmed AI-algorithms enable automatic condition detection of the incoming dyno cards, including conversion and analysis of the corresponding subsurface dynamograms. A smart alarming system informs about occurring failure conditions and specifies whether an incident of rod rupture, pump-off condition, gas lock or paraffin precipitation occurred in the well. A surface mounted measuring device delivers liquid level and bottomhole pressure information automatically into the software. Based on these diverse data, the operations team plans the subsequent activities. The holistic application approach is illustrated using the case study of an SPR-operated well in an Austrian brownfield.

Download Full-text

ANALISIS JENIS LAYANAN PENDIDIKAN DAN NON PENDIDIKAN YANG PENTING BAGI PENINGKATAN KEPUASAN MAHASISWA (STUDI KASUS: FAKULTAS TEKNIK UNIVERSITAS DIPONEGORO)

J TI UNDIP JURNAL TEKNIK INDUSTRI ◽

10.14710/jati.13.1.7-16 ◽

2018 ◽

Vol 13 (1) ◽

pp. 7

Author(s):

Aries Susanty ◽

Haryo Santoso ◽

Pramudiastuti Nursyachbani

Keyword(s):

Taguchi Method ◽

Student Satisfaction ◽

Educational Services ◽

Optimal Result ◽

One Dimensional ◽

The Right ◽

Right Order ◽

Item Item

AbstrakPenelitian ini memiliki dua tujuan. Pertama, penelitian ini bertujuan untuk mengindentifikasi item layanan pendidikan dan non pendidikan yang dianggap penting untuk peningkatan kepuasan mahasiswa Fakultas Teknik Univesitas Diponegoro (UNDIP). Kedua, penelitian ini bertujuan untuk menyusun sejumlah rekomendasi untuk perbaikan atas item layanan pendidikan dan non pendidikan yang dianggap penting tersebut. Terdapat 7 dimensi dan 28 item layanan yang digunakan untuk mengindentifikasi jenis layanan pendidikan dan non Pendidikan yang diterima oleh mahasiswa Fakultas Teknik UNDIP. Penelitian ini menggunakan Metode Kano dan Taguchi untuk mengindentifikasi item layanan pendidikan dan non pendidikan yang dianggap paling penting. Dalam hal ini, Metode Kano digunakan untuk memilih sejumlah item layanan pendidikan dan non pendidikan yang termasuk dalam kelompok attractive dan one-dimentional. Adapun Metode Taguchi digunakan untuk dua hal, yang pertama yaitu memverifikasi hasil pengelompokan dari Metode Kano sehingga diperoleh hasil yang lebih optimal dan mengurutkan prioritas perbaikan dari item-item layanan yang termasuk dalam kelompok attractive dan one-dimentional. Data untuk penelitian ini diperoleh dari hasil pengisian kuesioner oleh 120 responden untuk kuesioner Kano dan 60 responden untuk kuesioner Taguchi. Hasil pengolahan data dengan menggunakan Metode Kano menunjukkan bahwa terdapat 6 item layanan yang termasuk dalam kategori one-dimensional dan terdapat 2 item layanan .yang termasuk dalam kategori attractive. Selanjutnya, pengolahan data dengan menggunakan Metode Taguchi diperoleh bahwa terdapat 2 item layanan yang perpindah dari one-dimensional ke attractive dan 1 item layanan yangberpindah dari attractive ke one-dimensional. AbstractAnalysis of the type of educational and non-educational services that are important for the enhancement of student satisfaction (case study Faculty of Engineering, Diponegoro University)] This research has two objective. First this study aims to identify the type of educational and non-educational services that are important for the satisfaction’s enhancement of the student of Faculty Engineering, Diponegoro University. Second, this study aims to formulate some recommendation for improving the type of educational and non-educational services that are important for the satisfaction’s enhancement of the student of Faculty Engineering. There are 7 dimensions and 28 indicators used to identify the type of educational and non-educational received by the student. This research uses the Kano and Taguchi method to identify the type of educational and non-educational services that are important for student. In this case, the Kano method is used to identify educational and non-educational services that are include attractive and one-dimensional categories. Whereas the Taguchi method is used to verify Kano’s categorize result for getting more optimal result than Kano method and to put priorities in the right order of those services that are include attractive and one-dimensional categories. Data for this research is got from questionnaires that were distributed to 120 respondents for Kano method and 60 respondents for Taguchi method. Kano method’s result showed that there are 6 type of services that are include in one-dimensional category and 2 type of services that are include in attractive category. However, based on validation result that is using Taguchi method showed that there are 5 type of services that are include in one-dimensional category and 3 type of services that are include in attractive category.Keywords: Educational and Non-educational Services; Satisfaction’s Enhancement of Student; Faculty of Engineering Diponegoro Univesity; Kano Method; Taguchi Method.

Download Full-text