Experimental validation of the numerical results

The gap

Evidence profile

Sourced from the inline gaps and future-work section and stated research gap of the source papers, classified as general, spanning 4 journals.

Supporting evidence — 4 representative gaps

• ANN-driven analysis of Cattaneo–Christov heat transfer and entropy generation in Maxwell hybrid nanofluid flow over a vertical cone (2026) · Frontiers in Artificial Intelligence · doi

  Future research may consider physics-informed neural networks, larger parametric datasets, and unsteady, three-dimensional, and temperature-dependent models to extend the applicability of the predictive framework to more complex thermal systems. 2 Prospects for the future and extensions of research accurate predictions, Although the ANN provides its performance is limited by the numerical dataset used for training.

  generalinline gaps
  Keywords: future consider physics informed neural networks larger parametric datasets unsteady three dimensional temperature dependent models
• CFD simulation for thermal performance analysis of twisted oval double-pipe heat exchangers with ANN prediction (2026) · Journal of Mechanical Science and Technology · doi

  Future studies can focus on experimental validation of the numerical results. Future studies can investigate the thermal-hydraulic performance of other types of heat exchangers. Future studies can develop more advanced artificial neural network models that can predict the performance of heat exchangers under various operating conditions.

  generalfuture-work sectionevidence 5/5
  Keywords: future studies focus experimental validation numerical results investigate
• Variational Physics-Informed Neural Network for 3D Transient Melt Pool Thermal Modeling (2026) · Applied Sciences · doi

  Conventional finite element methods impose prohibitive computational costs for parametric process exploration. The need for a more efficient and accurate method for predicting transient melt pool thermal fields in LPBF. The limitation of conventional physics-informed neural networks in handling complex thermophysical properties and phase change phenomena.

  generalstated research gapevidence 5/5
  Keywords: conventional finite element methods impose prohibitive computational costs
• Overview on Predictive Maintenance Techniques for Turbomachinery (2026) · Machines · doi

  The paper identifies the gap in the current technological landscape, including the lack of advanced digital architectures for predictive maintenance. It highlights the challenges posed by high-dimensional multivariate time series and labeled data scarcity. The paper also identifies the need for hybrid physics-informed models that can effectively integrate physical laws with neural networks.

  generalstated research gapevidence 5/5
  Keywords: paper identifies gap current technological landscape including lack

Questions about this gap