How-to articleMethodology & analyticsEngineering & technology

Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation

Engineering doctorates that combine machine learning, sensors and industrial automation need a methodology that connects the physical system, the data it produces and the claims a model can support. This guide reviews what Indian studies of Industry 4.0 have done and sets out a design that will stand up to examination.

What you will learn

  • Frame an engineering research gap in terms of a physical system, a measurable outcome and a decision
  • Describe how Indian Industry 4.0 studies have collected and analysed their data, and their limits
  • Choose between experimental, simulation, field and survey designs, or combine them deliberately
  • Split data so that model performance reflects new machines, sites or time periods rather than leakage
  • Plan sensitivity analysis and uncertainty quantification for models and digital twins
  • Place the work within Indian doctoral, funding and data protection requirements

What you will unlearn

  • Applying AI to an industrial data set is a methodology.A methodology states the system, the question, the data-generating process and the validation that would show the model works on new cases.
  • A random train-test split gives an honest accuracy estimate.When records from the same machine or time window fall in both sets, the split leaks information and inflates accuracy.
  • A digital twin validates itself because it mirrors the plant.A twin is a model; it has to be calibrated and validated against held-out measurements, with its uncertainty stated.
  • Expert surveys establish which technologies improve performance.Surveys and structural modelling capture expert judgement about barriers and priorities, not measured technical effects.

Skills you will practise

  • Problem framing for CPS
  • Experimental and simulation design
  • Leakage-free validation
  • Sensitivity analysis
  • Survey and expert-judgement methods
  • Reproducible engineering software

Frame the gap around a system and a decision

Engineering doctorates in artificial intelligence, cyber-physical systems (CPS) and automation often begin with a technology rather than a problem: "apply deep learning to predictive maintenance" or "build a digital twin of a production line". A defensible methodology starts instead from a physical system, a quantity that matters about it, and a decision that a better estimate of that quantity would improve. For example: which pump bearings in a given plant will fail within the next maintenance interval, and how much unplanned downtime would a condition-based schedule avoid?

Reference architectures help you locate the contribution. Lee et al. (2015) proposed a five-level CPS architecture for manufacturing, running from smart connection and data-to-information conversion through a cyber level to cognition and configuration. Monostori et al. (2016) reviewed CPS in manufacturing more broadly, and Tao et al. (2018) set out a framework in which a digital twin links physical and virtual product models across design, manufacturing and service. Use such frameworks to say which level or link your thesis improves, not as evidence that a technology works.

What Indian Industry 4.0 studies have done

The verified Indian studies reviewed here are mostly studies of adoption: what stops firms from using Industry 4.0 technologies and what they need first. They are useful for framing the industrial context of a thesis, and they show a characteristic methodological pattern, but they are not evidence about how well particular AI or CPS techniques perform. Technical method guidance in this article therefore draws on international literature.

At NIT Rourkela, Jena and Patel (2022) used a questionnaire survey of Indian industry to identify industrial system requirements and barriers to Industry 4.0 implementation, then ranked both with fuzzy multi-criteria decision-making and examined the relationships between them. At Poornima University and Banasthali Vidyapith in Rajasthan, Rawat et al. (2024) studied barriers in Indian small and medium enterprises using interpretive structural modelling (ISM) and MICMAC analysis within the technology-organisation-environment framework. They identified a lack of government regulations and a lack of awareness of the benefits of digital infrastructure as root barriers, and found that concern about the future workforce had high dependence but low driving power, contrary to earlier studies. Kamble et al. (2018) similarly analysed the driving and dependence power of barriers to Industry 4.0 adoption in Indian manufacturing.

Three methodological lessons follow. First, these designs rest on expert judgement, so the selection, number and independence of experts determine how far the results generalise, and the published abstracts do not always report them. Second, ISM and fuzzy rankings are sensitive to how pairwise judgements are aggregated, so a thesis using them should test whether the structure changes under reasonable alternatives. Third, adoption studies are best combined with technical work: a barrier analysis can justify why a low-cost, explainable monitoring system matters for Indian SMEs, and the technical chapters can then test such a system.

Indian Industry 4.0 studies reviewed in this guide (from published abstracts and bibliographic records)
Study (institution)Data and methodsMain contributionMethodological caution
Jena & Patel, 2022 (NIT Rourkela)Questionnaire survey; fuzzy multi-criteria decision-makingRanked system requirements and barriers and related themSample and sectors to be reported; sensitivity of fuzzy weights
Rawat et al., 2024 (Poornima University; Banasthali Vidyapith)ISM and MICMAC within the TOE frameworkRoot barriers for Indian SMEs; workforce concern as dependentExpert panel composition; aggregation of judgements
Kamble et al., 2018Driving and dependence power analysis of barriersBarrier structure in Indian manufacturingExpert judgement, not measured performance

Choosing and combining designs

Most AI and CPS theses combine several of the designs below. State which one answers each research question, and why.

Common designs in AI, CPS and automation doctorates
DesignTypical dataWhat it can showMain threat
Laboratory experiment (test rig)Sensor signals under controlled faults or loadsWhether a method detects known conditionsRig conditions may not resemble the field
Simulation or digital twinModel outputs under designed scenariosBehaviour across conditions too costly to test physicallyModel error and unvalidated assumptions
Field study in a plantHistorian, PLC and maintenance recordsPerformance on real machines and decisionsMissing labels, drift, confounding by operations
Survey or expert methodQuestionnaires, pairwise expert judgementsPriorities, barriers and requirementsPanel selection and aggregation

Whatever the design, describe the measurement chain before the model. For sensor data, state the sensor type and mounting, sampling rate, filtering, synchronisation between channels and how faulty or missing readings were detected. For labels taken from maintenance logs, state who recorded them, how failure dates were assigned and how uncertain they are, since a model cannot be more accurate than the labels it learns from. For survey and expert methods, state how respondents were selected, their roles and experience, the response rate and how disagreements between experts were aggregated. These details are often missing from published work, and supplying them is an easy way to make a thesis stronger than the papers it cites.

Field data from Indian plants are often the most valuable and the hardest to obtain. Agree access, data ownership, confidentiality and publication rights in writing with the industrial partner before data collection, and record them in the methodology chapter.

A walkthrough: designing a leakage-free evaluation

The following project is illustrative. A candidate wants to predict bearing faults in centrifugal pumps using vibration data from twelve pumps at one plant over eighteen months, with maintenance records as labels.

  1. Define the prediction task precisely. For example, whether a pump will need a bearing replacement within 30 days, predicted from the preceding 7 days of vibration features.
  2. Define the unit of independence. Windows from the same pump are strongly correlated, so the pump, not the window, is the unit to hold out.
  3. Split by pump and by time. Train on some pumps and earlier months; test on held-out pumps and later months. A random split of windows would put near-identical data in both sets.
  4. Fit preprocessing inside the training data. Scaling, feature selection and threshold tuning are learned on the training folds only (Varma & Simon, 2006).
  5. Compare with simple baselines. A threshold on overall vibration level or a fixed replacement interval shows whether the model adds value.
  6. Report decision metrics. Precision and recall at the operating threshold, false alarms per month and the lead time gained, not only accuracy.
Evaluation splits for an illustrative predictive maintenance study
Split strategyQuestion it answersRisk
Random split of windowsCan the model interpolate within machines it has seen?Severe leakage; optimistic results
Hold out whole pumpsWill it work on new machines of the same type?Few pumps means wide uncertainty
Hold out later monthsWill it work in the future at this plant?Drift and changed operating regimes
Hold out another plantWill it transfer to a new site?Hardest to obtain; most convincing

Kapoor and Narayanan (2023) documented data leakage as a widespread cause of irreproducible results in machine-learning-based science and proposed model info sheets that require authors to justify the separation between training and test data. Writing such a justification into your methodology chapter is one of the most effective ways to pre-empt an examiner's questions.

Sensitivity, uncertainty and explanation

Simulation models and digital twins need two kinds of checking. Validation compares model outputs with held-out measurements. Sensitivity analysis asks which uncertain inputs drive the outputs. Global methods, which vary all inputs together across their plausible ranges, are preferable to changing one factor at a time, and Monte Carlo sampling is the usual way of propagating input uncertainty to the outputs (Saltelli et al., 2008). State the input ranges and distributions and report outputs with intervals.

Explainability methods such as Shapley-value attributions show which features drove a prediction. They help engineers check that a model relies on physically plausible signals, but they explain the model, not the machine, and they do not replace validation on unseen equipment.

Computational comparisons should also control implementation. When you compare your algorithm with published ones, run all of them in the same environment and at a similar level of optimisation, and report the hardware and software versions (Kriegel et al., 2017).

Working within Indian requirements

The UGC 2022 doctoral regulations set coursework of at least 12 credits, including research methodology and research and publication ethics, semester reviews before a Research Advisory Committee and an open pre-submission presentation (University Grants Commission, 2022). Use the advisory committee reviews to fix your evaluation design early, since changing the split strategy after results are known undermines the analysis.

Funding for engineering research now flows in part through the Anusandhan National Research Foundation, set up under the ANRF Act, 2023 (Anusandhan National Research Foundation, n.d.). If your data include information about identifiable people, such as operators, drivers or building occupants, check your institution's guidance under India's Digital Personal Data Protection Act, 2023, and seek ethics review where people are involved. Industrial data that are commercially sensitive need a written agreement on what can be published or shared.

What to report and common mistakes

Minimum reporting set for an AI, CPS or automation methodology
ReportWhy it matters
The physical system, operating conditions and decision supportedDefines where results apply
Data sources, sampling rates, labelling and missing dataLets readers judge data quality
Unit of independence and split strategyShows the evaluation is free of leakage
Baselines and decision-relevant metricsShows whether the method adds practical value
Simulation or twin validation, sensitivity and uncertaintyShows how far model outputs can be trusted
Expert panel selection and aggregation, for survey methodsDetermines generalisability
Hardware, software versions, code and data availabilityAllows reproduction
  • Describing tools and buzzwords instead of the system, question and evaluation.
  • Randomly splitting correlated sensor windows into training and test sets.
  • Tuning thresholds or selecting features on the test data.
  • Reporting accuracy on heavily imbalanced fault data without precision, recall or false-alarm rates.
  • Presenting a digital twin without validation against held-out measurements.
  • Citing a framework paper as evidence that a technology improves performance.

Key takeaways

Your next step

Want to apply this to your own study?

  1. 1Tell us your topic, data and deadline
  2. 2A subject mentor reviews your work with you
  3. 3You get a plan and a quote
Research design support

References

  1. Anusandhan National Research Foundation. (n.d.). About ANRF. Retrieved October 4, 2026. https://anrfonline.in/ANRF/aboutANRF
  2. Jena, A., & Patel, S. K. (2022). Analysis and evaluation of Indian industrial system requirements and barriers affect during implementation of Industry 4.0 technologies. The International Journal of Advanced Manufacturing Technology, 120(3), 2109–2133. https://doi.org/10.1007/s00170-022-08821-0
  3. Kamble, S. S., Gunasekaran, A., & Sharma, R. (2018). Analysis of the driving and dependence power of barriers to adopt industry 4.0 in Indian manufacturing industry. Computers in Industry, 101, 107–119. https://doi.org/10.1016/j.compind.2018.06.004
  4. Kapoor, S., & Narayanan, A. (2023). Leakage and the reproducibility crisis in machine-learning-based science. Patterns, 4(9), 100804. https://doi.org/10.1016/j.patter.2023.100804
  5. Kriegel, H.-P., Schubert, E., & Zimek, A. (2017). The (black) art of runtime evaluation: Are we comparing algorithms or implementations? Knowledge and Information Systems, 52(2), 341–378. https://doi.org/10.1007/s10115-016-1004-2
  6. Lee, J., Bagheri, B., & Kao, H.-A. (2015). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23. https://doi.org/10.1016/j.mfglet.2014.12.001
  7. Monostori, L., Kádár, B., Bauernhansl, T., Kondoh, S., Kumara, S., Reinhart, G., Sauer, O., Schuh, G., Sihn, W., & Ueda, K. (2016). Cyber-physical systems in manufacturing. CIRP Annals, 65(2), 621–641. https://doi.org/10.1016/j.cirp.2016.06.005
  8. Rawat, P., Yashpal, & Purohit, J. K. (2024). Evaluating and prioritizing the barriers of Industry 4.0 implementation in Indian SMEs: An ISM approach. Journal of The Institution of Engineers (India): Series C, 105(3), 543–560. https://doi.org/10.1007/s40032-024-01042-2
  9. Saltelli, A., Ratto, M., Andres, T., Campolongo, F., Cariboni, J., Gatelli, D., Saisana, M., & Tarantola, S. (2008). Global sensitivity analysis: The primer. Wiley. https://doi.org/10.1002/9780470725184
  10. Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H., & Sui, F. (2018). Digital twin-driven product design, manufacturing and service with big data. The International Journal of Advanced Manufacturing Technology, 94(9–12), 3563–3576. https://doi.org/10.1007/s00170-017-0233-1
  11. University Grants Commission. (2022). UGC (Minimum standards and procedures for award of Ph.D. degree) regulations, 2022. Gazette of India, 7 November 2022. https://www.ugc.gov.in/pdfnews/0909572_Minimum-Standards-and-Procedure-for-Award-of-PhD-Degree.pdf
  12. Varma, S., & Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics, 7, 91. https://doi.org/10.1186/1471-2105-7-91

How to cite this article

Choose your referencing style, then copy. Check your university's or journal's guide for local variations.

PhD Research Lab Academy. (2026, May 14). Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation. PhD Research Lab. https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india/

PhD Research Lab Academy. “Designing an Engineering PhD Methodology in India: AI, Cyber-physical Systems and Automation.” PhD Research Lab, 14 May 2026, www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india. Accessed [access date].

PhD Research Lab Academy (2026) Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation. PhD Research Lab. Available at: https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india/ (Accessed: [access date]).

PhD Research Lab Academy. “Designing an Engineering PhD Methodology in India: AI, Cyber-physical Systems and Automation.” PhD Research Lab. May 14, 2026. https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india.

PhD Research Lab Academy, ‘Designing an Engineering PhD Methodology in India: AI, Cyber-physical Systems and Automation’ (PhD Research Lab, 14 May 2026) <https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india> accessed [access date].

PhD Research Lab Academy. Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation [Internet]. PhD Research Lab; 2026 May 14 [cited [access date]]. Available from: https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india/

PhD Research Lab Academy, “Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation,” PhD Research Lab, May 14, 2026. [Online]. Available: https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india. [Accessed: [access date]].

@online{phd_dissertation_methodology_writing_services_in_india_2026,
  author = {{PhD Research Lab Academy}},
  title = {{Designing an engineering PhD methodology in India: AI, cyber-physical systems and automation}},
  organization = {PhD Research Lab},
  date = {2026-05-14},
  url = {https://www.phdassistance.com/academy/how-to-article/phd-dissertation-methodology-writing-services-in-india},
  urldate = {[access date]}
}

This article is for learning. Use it to understand the method and cite the original sources above in your own work; do not copy or submit it as your own.

Designing an engineering PhD methodology in IndiaNeed help applying it to your study?
Research design support