Futuristic Trends in Intelligent Manufacturing

Smart manufacturing is utmost need of industries to secure high productivity and profit. Industry 4.0 encompasses digital transformation of manufacturing industries and service industries. Smart manufacturing can be adopted by not only the large-scale manufacturers, but also small manufacturing enterprises (SME). The implementation of digital system onto each entity or stack holder of the enterprise will help the organization to avoid wastages. This article highlights the issue of wastes in manufacturing, importance of smart machining and proposes a technical approach to reduce such wastages, clearing the way to achieve sustainable manufacturing.

Titanium alloys are substantially used in the aerospace industry due to their high strength to weight ratio. During turning of titanium alloys, obtaining smooth surface with dimensional accuracy is a requirement in machining of parts. The quality of machining is a function of machining parameters used in turning. Twenty-seven experiments were conducted with different combination of cutting speed(Vc), Feed rate (f) and Depth of cut (ap) and the corresponding surface roughness (Ra) was measured. Response surface methodology (RSM) was firstly developed with the experimental data and Genetic algorithm(GA) was then applied to minimize the surface roughness. Validation experiments showed that the error rate was 4.27%. In order to minimize the error rate, a systematic approach was implemented to develop optimal Artificial neural network (ANN) model with the contemplation of effect of ANN architecture and activation functions on the prediction. The predicted ANN data were further used to develop revised RSM model. The later prediction model and the respective optimization resulted the best cutting parameters for achieving the minimum Ra. The predicted surface roughness from GA is \( R_{a} = 1.42 \mu {\text{m}} \) for the optimum turning condition of \( V_{c} = 148\,{\text{m/minute}},\, f = 0.1\,{\text{mm/rev}}, ap = 0.5 \,{\text{mm}} \). The error rate between the predicted results and the validation results is only 2.27%. The proposed model can be used practically in the turning of titanium alloys.

Plastics parts are mostly produced through injection molding or compression molding. But they may not meet the precise dimensions or tolerances during molding process. Moreover, obtaining smooth surface is also a challenge to the company. The human based selection of process parameters may be inaccurate and conservative, leading to a loss of quality and productivity. This research attempts to utilize artificial intelligence (AI) technique to predict the optimal control parameters for drilling a polyoxymethylene (POM) polymer material. Sugeno fuzzy inference system was used to model the drilling process parameters. Three inputs and 26 output functions were used to fit the experimental data. It is observed that the developed FIS has mean error of 7.59% with the correlation coefficient of 0.98.

Electrochemical Micromachining (EMM) is a non-conventional technique that has the potential to provide excellent accuracy due to its ionic dissolution nature. The technique is evolving rapidly with continuous research works and emerging as a frontline technology in the micro-fabrication domain. The dominant input factors of electrochemical machining (ECM) process become very sensitive at micro-domain and parametric optimization is inevitable for enhanced performance. New researches are required to enhance every aspect of the processing system that includes electric power, electrolyte, feed mechanism, gap control etc. The aim of the current work is to produce micro-holes on SS-304 sheet using tungsten tool and citric acid electrolyte through EMM process. An EMM device fabricated for experimentation purpose with pulse generator was utilized in this research. The operating factors preferred for study are voltage, current, pulse-on-time & electrolyte concentration. Taguchi’s L9 design for trials and Grey Relational Analysis (GRA) for multi response optimization were employed. The optimum set of parameters obtained through GRA included 12 V,1.2 A, 15 ms of pulse-on-time period and 20 g/l of solution concentration. The most influential factor observed was pulse-on-time. Though machining was slow with citric acid as electrolyte, holes produced were of good accuracy.

The spikes formation is one of the major drawbacks of the Electrochemical Machining (ECM) process. The generation of spikes directly affects its performance objectives namely Material Removal Rate (MRR) and average surface roughness (Ra). It is mainly formed due to the formation of a passive layer at the Inter Electrode Gap (IEG) which affects the uniformity of current density at the machining zone. Hence, the rationale of this research is to examine the impact of Copper metal Nano-particles suspended aqua Sodium Nitrate electrolyte on electrochemically machined High Carbon High Chromium (HCHcr) die tool steel. The selected primary machining factors namely flow-rate of electrolytes, voltage applied, and feed-rate of tool. The results of Fifty-four experiments were discussed and the process parameters were optimized by employing the Artificial Fish Swarm (AFS) algorithm. This work has concretely proven that the Copper metal Nano-particles has shown significant improvements in obtaining better MRR and Ra concurrently. The maximum MRR of 347.876 mm³/min was achieved using Copper metal Nano-particles suspended Sodium Nitrate aqua electrolyte at 0.54 mm/min, 18 V, and 12 lpm and the corresponding Ra is 1.6 micron which is 12% higher in MRR and 50% lower in Ra than that of plain electrolyte. The result of the confirmatory experiment revealed that the deviation of the result from the AFSA value was found to be 2.5%, hence the adopted strategy is so significant and consistent.

Predictive maintenance is considered cost-efficient and acts as an enabler for businesses to be more competitive. Maintenance of pipelines can be complex and costly especially when it is located underground or subsea. Based on the literature review done for this comparative analysis, there has been rapid development to come up with pipeline condition prediction methods. The first part of the paper reviews several common methods of pipeline prediction including the comparison between conventional and machine learning methods by taking into account the capability, accuracy, complexity, and effectiveness of the methods considered in this review. Based on the comparison, pipeline prediction using machine learning methods is seen to have advantages over the conventional approach and hence, many studies have shifted towards the use of machine learning for pipeline prediction. Most of the research work on this subject is focusing on determining or improving the accuracy of the prediction for selected methods only. Hence, the second part of this paper provides an overview of the accuracy of Machine Learning methods used in various applications based on the literature review while trying to relate specifically to how it can improve the performance of pipeline prediction. The methods that have proven good prediction accuracy and have been used in pipeline prediction were compared against each other in a matrix format. Based on the outcome, the Machine Learning methods that are widely used in the field of pipeline predictive maintenance with good prediction accuracy are Support Vector Machine (SVM) and Artificial Neural Network (ANN). However, Fuzzy methods and Regression analysis methods have shown a lot of potential in this field due to their promising performance.

Modern engineering applications require the amalgamation of unlike materials for achieving specific thermal, electrical, and physical properties. Aluminium alloys are quite often employ fusion or solid-state processes to join with copper. However, fusion welding of dissimilar materials results in defects such as porosity and the formation of brittle particles. Friction Stir Welding (FSW) is energy efficient, environment friendly process used for joining dissimilar metals. Hence, an attempt is made to join aluminium alloy (AA6061-T6) and pure copper. In this article, the effect of tool pin offset, eccentric weave tool path, and the addition of graphene nano-platelets was studied and compared with the conventional FSW. The effect of pin offset compared to the conventional pin position helped in obtaining a good weld strength due to the large volume of material transportation of base materials and better stirring effect. The novel eccentric weave motion of the tool was useful for obtaining enhanced joint property due to higher holding time, adequate heat input, and uniform mixing during the joining process. A back propagation network (BPN) was utilized in arriving at the optimal process parameters.

Particleboard is normally used for attractive interior designs. Machining reduces its surface characteristics. Hence the evaluation of favorable machining conditions is desired in improving the quality. In the present investigation, drilling has been performed using HSS drills based on Taguchi’s L27 orthogonal array with three parameters and three levels to analyze the surface roughness. Two modelling approaches have been used to develop mathematical models for comparing their effectiveness.

Smart manufacturing is the integration of information technology infrastructure and intelligent computational algorithms in manufacturing process. Smart manufacturing provides intelligent and interoperable environments, effectively targeting the mass production requirements and quality. In this work, the interdependence between the current smart manufacturing industry and healthcare applications are presented. Importance of product tracking of state of art healthcare equipment using cloud-based environments and improved manufacturing processes using machine learning algorithms leverages further innovations in healthcare applications including drug discovery, early diagnosis of diseases, rehabilitation and pandemic modelling.

Sales forecasting is a trending area of research in diary production as it helps the industry project the future demand, revenue generation and profit expectation of the industry. Several research methods have been employed in sales forecasting while the Artificial Intelligence (AI) methods offer more plausible and accurate prediction as compared to traditional statistical methods. A new soft computing method, established on the fundamentals of Gene Expression Programming (GEP) is presented in this work to forecast sales in a real-case dairy production company. The study employed back propagation neural network (BNN) which is useful in artificial neural network (ANN) methods. The study also conducted results validation for results’ accuracy, dependability and reliability as well as compared ANN results of prediction against GEP results using R-square and mean square error (MSE). The associated results showed that both AI techniques are robust in sales forecasting. However, the accuracy of GEP was observed to be more promising in comparison to the ANN.

Digitization is the backbone and major cause in the era of Industry 4.0. Manufacturing industries are in the midst of a transformation regarding the method of manufacturing processing and delivering of goods to customers. Until now the production of various goods done by the manufacturing industries uses the traditional method of old machines and human labor but looking into the plan of industry 4.0 it gives tremendous outcomes in terms of economical aspect as well as safety-wise in the long run.. In the first revolution, the manufacturing sector was mainly based on using mechanical human-operated machines which needed a lot of labors to complete the work, Second revolution is the use of mass production and assembly lines with the help of electricity. The third revolution was mainly based on advancements made in machines by introducing computers and reducing the burden on human shoulders. But now the beginning of industry 4.0 has started and many manufacturing sectors are getting benefited from this. Industry 4.0 is the automation simulation smart system based environment where Augmented reality(AR) and Virtual reality(VR) comes into play. Industry 4.0 has started to change the complete industrial experience and with the introduction of AR and VR in manufacturing sectors the profit-economy growth graph is starting to rise hence establishing a strong foundation and helping to deliver good sufficient advanced products that customer desires with the help of purely Automation and Artificial intelligence. Industry 4.0 is based on data the way it can be gathered, analyzed and deployed in the manufacturing sector with help of Augmented and Virtual reality.

Intelligent manufacturing is the new, emerging trend in Industry4.0, reflecting the impact of cutting edge technologies like Internet of Things, Big-data, Artificial intelligence(AI), Cloud Networking. In order to increase productivity and to explore new ways to modernise the manufacturing technologies and supply chain logistics, the digital transformation of Industries is the need of the hour. More innovative and competitive applications are in practice to meet the customer expectations and to reduce the complexity in the global supply chain. Industrial Internet of Things (IIoT) is a way of digital transformation in manufacturing. The ‘Industrial Internet of Things’ is the new paradigm, which is the application of Internet of Things (IoT) in Industries especially in manufacturing, using sensor data from machine-to machine (M2M) communication with the help of automation technologies. This chapter addresses the various methodologies of IIoT, in industrial sector with proper use cases. The latest application of this IIoT is Digital Twin, which is very useful in simulation of the machines, has been clearly dealt in this chapter.

The promise of the Fourth Industrial Revolution (IR4), coupled with the agility demanded by the COVID-19 pandemic has driven large scale adoption of IR4 technologies. However studies show that only 30% of all digital transformation projects succeed, making it a risky proposition, especially for Small Medium Enterprises (SMEs). Successful prototype implementations are needed for SMEs to believe in the power of IR4 initiatives and to motivate them to invest time and effort. In this paper, we showcase such a prototype implementation by first providing an overview of the cyber-physical system architectural framework in the manufacturing context. Next, we showcase a real-life, low-cost, reliable pilot that will boost IR4.0 technology adoption for SMEs in a timely manner without large investments or disruption to existing operations. The presented case study shows an example of a pilot project that demonstrated early success, with well-established needs and measured signposts to harness the benefits of IR4.

Abrasive machining is a recent technology, which is eminently suitable for making micro holes in brittle and composite materials used in many industrial components. Polymeric composite materials find extensive use in aircraft, automobile industries, and household applications due to their lightweight, excellent strength, corrosion resistance, and attractive fracture toughness. These composites, when machined, suffer heavy delamination when a conventional machining process like drilling is used. The machining time and surface roughness using the conventional nozzle in the machining of the above composites is also found to be high. Hence, the existing design of the conventional nozzle was modified and used in the setup. Two different polymeric composites, namely, Carbon Fibre Reinforced Polymer (CFRP) and Glass Fiber Reinforced Polymer (GFRP) have been used to understanding the machining characteristics.

The unique advantage of Fused Deposition Modelling (FDM) technology over other Additive Manufacturing (AM) technology is its viability to optimize the infill of the part through various densities and structures. The current study aims at investigating the infill density and structure with its strength to weight ratio. The material Nylon-6 were chosen for the investigation. The property such as Tensile, Compression and Flexural strength were analysed to understand the implications. It was found that the Tensile and compression results best fitted with 2nd degree polynomial and flexural results were in agreement to the linear curve fit. The Honeycomb and Diamond infill structures were analysed for the study. The results revealed the rectilinear structure has better strength to weight ratio and it is also by far more preferable in terms of economical perspective.