The International fright due to the occurrence of COVID has created an emergency act in the field of healthcare, bio medical and drug discovery process. However, finding the feasible solution to introduce a drug is a time-consuming process due to pre-clinical and post-clinical testing process. Prediction and estimation of COVID-19 can help the medical practitioners and government authorities to take preventable measure against the outcomes of COVID-19.From December 2019 to April 2020, 2844712 cases of COVID-19 have been informed, which includes 201315 deaths according to European Centre for Disease Prevention and Control. This drastic condition should be treated not only physicians and other health care providers. There are two types of time series forecasting techniques. The first technique time-domain approach models the forthcoming values as a function of previous and current values. The groundwork of this approach is the time series regression of current values of a time series on its own past values. The assessments of the model are applied for forecasting process. The second technique known as Frequency domain models are based on the interpretations of time using sines and cosines functions. These interpretations are known as Fourier representations. Overall, the technique utilizes regressions on sines and cosines function, to model the behavior of the data. The proposed work used Facebook Prophet model for Time Series Analysis to forecast the trend for the year 2021. The models will act as an inference tool to take decisions during pandemic conditions. © 2021 Karadeniz Technical University. All rights reserved.
Rolling element bearings are regarded as one of the critical components in industrial applications. In order to avoid the malfunctions and awful failures of the machinery, fault diagnosis plays a major role. Also, to increase the efficiency of monitoring systems, conventional diagnostic techniques have been replaced by Artificial Intelligence (AI) based methods. Deep learning (DL) as an advancement in AI, is found to be useful compared to the shallow structured Artificial Neural Networks (ANNs), in addition to the elimination of the need for diagnostic expertise. This paper presents a new 1-Dimensional Deep Convolutional Neural Network (1-D DCNN) based intelligent fault diagnosis method for rolling element bearings. The model is trained and tested using Case Western Reserve University (CWRU) dataset and is designed to classify ten fault classes using the acquired vibration signals. Unlike conventional DCNN architectures, the model does not use Fully connected (FC) layer. Thus, considerable decrease in the number of parameters is achieved and also leads to an increase in classification accuracy and decrease in computation time. This indeed reduces the computation power required and thus eliminates the need for using Graphical Processing Units (GPUs) for training deep learning neural networks, which is a significant contribution of this work.
As an important component in mechanical equipment, the health status analysis and fault identification of bearing have signification meaning for the operation and maintenance of equipment. Since the speed conditions have a serious influence on the periodic characteristic and statistical feature distribution of vibration signal, The conventional fault diagnosis methods and fault identification theories based on vibration signal have high misjudgement performance for rolling bearing fault classification once the speed information was uncertain. In this manner, based on architecture artificial neural network theory, this paper constructed a new weighted neural network architecture consisted of several different units and proposed a multiple-weight fusion identification method for bearing under uncertain speed conditions. Compared with the traditional networks, a speed-insensitive fault identification model is built by fusing different units to extract and integrating different information of the input samples, and hence the fault recognition accuracy of bearing faults under uncertain speed condition is greatly improved. The feasibility and effectiveness of the proposed method are further validated by experimental data analysis.
Digital asset management, as part of a larger organisational data strategy, is arguably a firm’s most valuable asset. Proprietary data encompass theanalytical actualities of the day-to-day, and illuminate the value-add assets driving business strategy. It is difficult to replicate; it can be a powerful device. The New Zealand microcosm can spark innovative and integrated insights into digitally enabled asset management initiatives. For big data that is raw, structured, unstructured or high-dimensional, nascent technologies are creating entirely new frontiers that organisations may ignore at their peril. By viewing a small, tech-savvy ecosystem within a culture that values sustainability, environmental regeneration and stewardship, paradigms that lead to novel or agile innovations arise. This research indicates new trends in high-dimensional digital asset management that can be leveraged intrapreneurially to develop world-class opportunities of global consequence. Asset reallocation considerations are indicated, while issues and challenges are explored. In particular, emerging high dimensional research advances are highlighted with an evolutionary focus. Applications for these data are discussed as a preface for shedding light on fields that are opening in more entrepreneurial settings, because of the digital ecosystem that is developing. The summary groups applications most likely to return transformational outcomes when targeted digital asset strategies underpin organisational operations, albeit with supportive management.
In this paper, the contingency is ranked for the system under a single transmission line outage condition. The ranking is carried with the static model of Quadrature Booster (QB) in the system. QB is incorporated by modifying the Jacobian matrix of the Newton-Raphson load flow technique. Thecontingencies are ranked based on the Condition Number of the Jacobian. The ranking is also carried for the enhanced system loading condition. IEEE-30 bus system is used for the proposed methodology and MATLAB environment is considered for the simulation purpose.
In this paper a new heuristic approach, Fractional Order Fuzzy Logic Controller (FOFLC) is used for Maximum power Point Tracking (MPPT) of PVsystem. It provides a comparison between Fuzzy Logic Controller (FLC) and FOFLC to track photo-voltaic system MPP and it also shows the maintenance of constant voltage by using charge controller. MATLAB/SIMULINK are used to study the FLC and FOFLC. Analysis is considered at two different conditions (i) constant temperature and varying irradiance (ii) constant irradiance and varying temperature. Simulation results reveal the effectiveness of FOFLC compared with FLC.
Modeling of AMT gearshift and clutch controls has attracted considerable attention in the past decade for optimizing the algorithms and simulation of control strategy and shift calibration, for reducing development time and costs involved in physical validation. Modeling of AMT system for simulation of gearbox and clutch performance is done using MATLAB/Simulink software. Time to market and investment for development can be greatly reduced through the use of a simulation-based design. A complete vehicle system simulation can allow multiple iterations without need for physical validation of the design concepts, prior to manufacturing test samples. This simulation methodology enables optimisation of interface components and sub-systems. Furthermore, design concepts can be tested using software model without the need of prototype parts, test vehicle, test track and test rig or test track.
The efficient project management of information systems (IS) and information technology (IT) projects is a crucial factor since, in many cases, they fail to meet the expected demands and requirements of the different stakeholders’. It is well known that poor project management, like inadequate risk management and insufficient project planning, is one of the main reasons for ICT project failure. An understanding of the digitalisation and the ICTs digital capabilities, i.e. adoption of disruptive technologies are crucial as well for its successful implementation. Thus, with the emergence of the new ICTs such as the Internet of Things, cloud computing, and big data, the digitalisation of the maintenance domain has become even more complicated. It is, therefore, essential to revisit standard processes when carrying out software development projects for the area of interest. A broad selection of software development methodologies exists today. However, these are general-purpose development approaches, and it is, therefore, crucial to have an understanding of the best options and best practices of the existent methodologies for context-specific development projects. Thus, the authors present a literature review of ICT project methodologies and later discuss these findings taking into consideration the characteristics of the domain of interest. Based on this, an ICT project management methodology suitable for the Industrial maintenance domain is suggested.
The paper describes how the use of MIMOSA open source data model supports the development of a low-cost monitoring system that is capable to carry out automatic diagnosis and prognosis. MIMOSA follows the ISO 13374 definitions (condition monitoring) and links well with the ISO 17359 (diagnosis) and ISO 13381 (prognosis). The MIMOSA data model defines all the necessary ontology for the automatic monitoring system. As a use case the paper describes the installation of the MIMOSA data model in a Raspberry where MariaDB is used as the database engine. A low-cost MEMS accelerometer has been installed to a Raspberry thus enabling the collection of vibration data from rolling element bearings of a conveyor. The goal is to compare the results of low cost devices to a more expensive data acquisition system. The necessary signal analysis functions are programmed with VTT O&M Analytics, which provides the ability to conveniently perform signal analysis, offering a comprehensive set of algorithms that can detect a bearing failure and calculate the Remaining Useful Life (RUL). The amplitudes of the bearing fault frequencies can be reliably seen using envelope analysis, and the magnitude of the amplitudes can be used to determine whether the bearing is defective. In addition, the article discusses the system architecture, which enables data transfer from cloud to cloud conveniently and reliably, regardless of the number or location of the clouds. In conclusion, the paper summarises the key role of MIMOSA in building and using this kind of automatic monitoring systems.
Maintenance plays a significant role in asset management of power organisations. Utilisation of right maintenance strategies contributes to high availability and reliability of power plants. This paper is a part of a research project to study the barriers that could affect total productive maintenance (TPM) implementation within the power industry context. The aim is to investigate the integration of artificial intelligence (AI) applications and TPM programmes within the power industry environment. The main objectives of this work are to appraise the impact of effective prognostic techniques and examine the role of reliability centred maintenance (RCM) on successful participation of autonomous maintenance in power plants using maintenance optimisation models. This work presents a novel methodology including modelling and simulation to support participation of operators in maintenance activities based on their capability, skills and technical knowledge. There has been almost no research applied in this area within power plants. This research study emphasises issues related to maintenance practice operations, suggesting optimal maintenance strategies with lowest maintenance costs that predict potential failure time of critical power plants. It integrates methods and principles of RCM and TPM and utilises diverse tools based on maintenance optimisation models to support operators in decision making through identifying new policies for machine maintenance or assessment and enhancement of existing maintenance plans. The proposed maintenance optimisation models performed good simulation results, and the latter show that the proposed models are really a new contribution in the area of TPM implementation in the power industry. Simulation results are presented to verify the analytical approach and validate proposed operational procedures. The analysis is based on degradation analysis, and failure mode effective and criticality analysis (FMECA). Based on the analysis, remaining useful life (RUL) of critical power assets (transformer paper insulation) was determined and maintenance costs of transformer tap changers are optimised. With respect to the simulation results of power transformers, the findings can contribute towards improved equipment operations and successful implementation of TPM in power organisations.
With modern health monitoring systems on-board, helicopters are still experiencing undetected faults in super critical mechanical components. Over the last decade, two fatal crashes of the Airbus Super Puma helicopter were caused by faults in a planetary gear-bearing component in the main transmission gearbox. The accident investigations showed that the bore/rim crack initiated from fatigue spalls on the planet bearing outer raceway that is integral with the bore of the planet gear. A recent study proposed a method based on planet-gear synchronous signal averaging to detect a planet gear bore crack. Applying deep neural networks to gear fault diagnosis has been gaining momentum in machine health monitoring, with the majority of studies focused on fault classification problems. In this paper, we employ a deep machine learning method, the long short-term memory (LSTM) based recurrent neural network, as a signalprocessing tool to analyse vibration data generated in gear rig tests with faulty gears for gear fault diagnostics. We focus on detecting anomalies or changes induced by the gear faults in the LSTM prediction error signal. We compare the fault detectability using this LSTM-anomaly method with that of other commonly used residual signal methods in gear fault diagnostics. We also provide a detailed study on how to apply the LSTM network to monitoring gear tooth crack growth at various stages of the fault development and to detecting planet gear bore cracks. Additionally, we discuss the potential pitfalls in applying the LSTM network to gear diagnostics – especially the problem of false detection.
Reliability Centered Maintenance (RCM) has been one of the most recent and successful methodologies in maintenance around the world. With an end goal to accomplish aggregate life cycle management, it is robustly preferred to understand the systematic planning method of maintenance tasks. It is such a systematic approach for the selection of relevant and suitable maintenance strategies. One of the important factors for the implementation of RCM in an organization is the adoption of a suitable framework that provides the required flow of various elements for structured implementation process. In this paper, ten most significant elements are identified from the various elements of existing RCM frameworks based on Strength, Weakness, Opportunity and threats (SWOT) analysis to help with design of a framework for the implementation of RCM. An attempt has been made to design a framework in two phases i.e. (i) Establishing the contextual interrelationship between the identified RCM elements using ISM approach, (ii) Designing a framework for the implementation of RCM. The objective of this research is the design of roadmap for the implementation of RCM in an organization. The significance of the proposed framework for RCM implementation is that it will help the maintenance managers, engineers, practitioners, and consultants to implement RCM successfully in an organization. Also, it presents the sequential and decision-making approach for systematic implementation of RCM in an organization in a phase-wise manner.
The digital signal processing has application in the field of computing block functions. The arithmetic logic unit is a digital electronic circuit, which is used to perform the operation of the arithmetic and logical functions on FIR filter. An arithmetic logic unit is the main block of computing circuits, which includes Central Processing Unit, and Graphical Processing Unit. In VLSI Design, the major parameters are the logic delay, chip area, and power consumption. This is reduced by using adders and multipliers functional block in ALU based FIR filter. The conventional method uses a divider algorithm with shifters since takes the number of looping unit and it assigns only the real numbers on IIR filter, therefore it does not give the bestoutputs. The proposed method comprises the design of Arithmetic Logical Unit based FIR filter by using the Enhanced Gate level design circuitry with Modified Carry look ahead and enhanced binary multiplier with subtractor and shifter blocks. Here the Adder, Multiplier, Subtractor, and shifter blocks are design with Gate level circuit model and it reduces the power consumption by adding clock-gating technique in the logic circuits of ALU based FIR filter. By using this proposed algorithms gives the better results for VLSI parameters and it increases the speed, which is applicable for biomedical image processing techniques. When compared to the conventional method, the proposed method gives the best result by the way of Area, Delay, and Power Consumption on VLSI design; the MSE and PSNR on medical image processing. The software MATLAB 2018a is used on the image processing, which adopts retinal image. The Xilinx ISE 14.5 is used for synthesizing the logic unit and Modelsim is used for simulating the results. This proposed algorithm achieves the better result than most recent related surveys.
This paper provides an intelligent plant condition monitoring system using Convolutional Neural Network (CNN) integrated into a decision-making process. CNN unsupervised model can identify faults in complex engineering system, recognize and classify the pattern of failure in an intelligent way that enable plant crew to make quick response for planning maintenance strategy. CNN have been applied to detect machine anomalies in plant and found to be efficient method for fast data processing, identification and classification of normal and abnormal condition of plant rotary components and have shown tremendous results for handling and classification of different faults from massive amount of plant machinery data intrinsic structures irrespective of distortion invariance and scale. CNN overcome dreads using Artificial Intelligence that provides a quick real time condition monitoring and fault detection ability and robustness in decision making with high diagnostic accuracy.
Sustainable decisions can be thwarted by a plethora of conflicting influences and information, yet the need to prioritise sustainability in management has never been greater. In an era of high- and ultra-high dimensional data, deep learning models offer the scalability required to extract good representations of significant features from raw data. With automatic learning at several levels of abstraction, deep learning can support sustainable asset management by learning complex functions mapping of systems. By processing data directly from input to output, clear and concise information can support visionary asset management whilst exposing hidden insights, detecting anomalies or predicting future states. This research will look at the necessity of applying deep learning in sustainable asset management and reveal some of the challenges that exist.
Friction as a global natural phenomenon of energy transformation and dissipation is strictly subject to the energy balance equation. A structural-energy analysis of evolution for friction contact is proposed. As the result of most full evolution of contact the unique nanostructure (subtribosystems) is formed and the basis of which is one mechanical (nano) quantum. Mechanical quantum represents the least structural form of solid material body in conditions of plastic deformation. Mechanical quantum is dynamic oscillator of dissipative friction structure. The nano-quantum model of the surfaces damping is proposed. Heavy loaded tribosystem (Hertzian friction contact) has the ideal damping properties – «wearlessness». In these terms only one mechanicalquantums is the lost – tribological structure standard and thus standard of wear.
During operation, it was observed that a specific mechanical system experienced undesirable vibration and it became necessary to understand and mitigate this phenomenon. This document investigates the tools, methodology, and results of the dynamic characterization of the system. The characterization makes use of the experimental modal analysis (EMA) methods of single input multiple output (SIMO) and single input single output (SISO). The validity of the theory of reciprocity is confirmed to minimize measurement error, cost, and time of repeat testing. Finite element analysis (FEA) is used in choosing transducer and modal impact locations to adequately characterize the system. Single degree of freedom (SDOF) and multiple degree of freedom (MDOF) curve fitting is used to fully characterize the system’s mode shapes and natural frequencies. The EMA characterization results are used to modify and validate the FEA model so that FEA can be used to model potential structural modifications to the system to mitigate the undesirable vibration. Structural modifications are chosen, implemented, and their effectiveness is quantified using EMA. A qualitative evaluation of the methodology of FEA validation by EMA and tuning of the model to match the experimental results is discussed.
Condition based maintenance has been coming to the fore especially in recent decades and it is at the expense of conventional maintenance strategies. Wear particle tribology-based predictive maintenance is based on continuous monitoring, evaluating its condition and uses knowledge of technical diagnostics and prognostics. The use of sliding wear particle mass distribution as a means for distinguishing different modes of wear and determining its transitory behavior is evaluated in terms of the quantitative analysis of the multi-filtergram slides produced from a series of wear tests from a multiple point contact sliding wear tester. In this particular research, a four ball machine was used throughout. At the end of each test the wear debris generated was collected and then separated using a multi- filtergram maker which resulted in the wear debris being extracted due to their specific size ranges. Each filtergram patch of each specific size range was subsequently weighed to obtain “wear particle mass distribution” which in turn can be used to produce a histogram plot of the particle mass distribution. Various distribution functions have been fitted with the data. The results obtained from different sliding wear modes are presented; they confirm that changes in the mean and the variance of the selected statistical distributions provide clear indications of the type and extent of the sliding wear as it progresses.
Amount of electrical power, generated depending upon the load demand has to be transported effectively to ultimate consumers. Distribution of electrical power to ultimate consumers safely and securely is an important task. Ultimate consumers are mostly residential, commercial and industrial. System supplying power to these forms a typical complex network and designing such a system involves many safety and reliability constraints. Improper supply system design may lead to many hazards and hence, multidimensional care has to be taken at the designing stage of power infrastructure elements to ensure safety of the system and personnel. In this paper, methodologies for testing various power infrastructure elements for their load withstanding capability are proposed. A typical residential complex building proposed to be constructed in real time, is considered and its complete power infrastructure is designed and diagnosed based on the proposed methodologies and validated using relevant NBC-2005, NEMA, NFPA and IS standards. Remedial solutions are proposed to ensure the reliability of the concern system and safety of the personnel. Also investigated for the possibility of reduction in energy consumption and found that by retrofitting the lighting system, annual energy savings about 6632.707 MCal is arrived which accounts in the reduction of about 7.095 tons of CO2 emissions per annum paving a path towards green electricity.
High quality information is essential for the efficient decision making. Road condition is, together with traffic frequency, commonly used as input forclassifying road status. Road condition is also a major input for the maintenance executor (vehicle operator) when deciding on maintenance actions, such as amount of gravel to replenish. With better condition related information, the maintenance execution as well as maintenance planning could be greatly improved. The current deficiencies in gravel road condition monitoring methods and technologies are described in this paper, and an approach for objective measurement of gravel road condition is proposed, including new measurement techniques and systems as well as information processing for decision making. This is realized by utilizing research findings from the area of signal processing, maintenance engineering, and information systems engineering in the specific context of gravel road monitoring, thus utilizing available technologies and methods as well as physics.
