Explore artificial intelligence in measurement systems through a published research reference related to Artificial Intelligence & Machine Learning. This B.Tech resource summarizes the available source and suggests questions to validate before choosing an implementation.
Artificial intelligence in measurement systems: source and project details
| Research overview |
This resource gives guidance on how to apply and evaluate artificialβintelligence methods for industrial measurement systems. Industrial transmitters that measure temperature, pressure, or flow often drift because of environmental conditions, wear, and electromagnetic interference. The paper surveyed softβcomputing techniquesβespecially artificial neural networks (ANN) and deep learningβto improve transmitter performance in terms of linearity, accuracy, and repeatability. Key results include:
- A hardwareβplusβsoftβcomputing solution cut the nonβlinearity error of thermocouple linearization by **84.63 %**.
- A hybrid optimizer that mixes a Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) with a BackβPropagation Neural Network (BPNN) lowered the mean absolute percentage error for industrial weir measurements to **1.2 %**, though it required more computing power.
The accompanying project material shows students how to simulate calibration and estimation algorithms such as **LevenbergβMarquardt**, **Scaled Conjugate Gradient**, and **Bayesian Regularization** to build sensorβcompensation models. Note: This review is based on the indexed metadata and abstract; the fullβtext implementation details have not been fully examined.
|
| Reference Paper |
Investigation on the Role of Artificial Intelligence in Measurement System |
| Publication year (source record) |
2025 |
| Source document classification |
Research reference (type not independently verified) |
| Discovered via |
DOAJ metadata |
| Authors (source metadata) |
P. A. Rezvy, Venkata Lakshmi Narayana Komanapalli |
| Publication type (source metadata) |
journal-article |
| Journal / conference (source metadata) |
IEEE Access |
| Publisher (source metadata) |
Institute of Electrical and Electronics Engineers (IEEE) |
| DOI (from source metadata) |
10.1109/access.2025.3575164 |
| Metadata consistency check |
DOI registration metadata compared with indexed record; original PDF text not independently verified. |
| Evidence reviewed by generator |
Indexed abstract/description only; original full text, author names in PDF and methods require editorial verification. |
| Domain |
Computer Science & Engineering |
| Sub-Domain |
Artificial Intelligence & Machine Learning |
| Research source |
View research source |
| Get Help |
Get Help on WhatsApp
Message: Hi FE, I need help with “Investigation on the Role of Artificial Intelligence in Measurement System” in “Computer Science & Engineering”
|
Project or research direction
This is a source-backed research starting point, not a tested, ready-made student project. Any implementation requires independent feasibility, safety and results verification.
Possible tools or components to evaluate
MATLAB / Simulink, Python (TensorFlow/Keras, Scikit-learn), LabVIEW, Neural Network Toolbox
Methods or operating principles to examine
Modeling of sensor non-linearity and environmental drift; Implementation of Levenberg-Marquardt, Scaled Conjugate Gradient, and Bayesian Regularization training algorithms; Simulation of hybrid GA-PSO-BPNN optimization for industrial weir calibration; Comparative analysis of hardware-based vs. soft-computing-based error reduction.
Outputs to plan and verify
A simulated calibration model demonstrating up to 84.63% reduction in thermocouple non-linearity error; Comparative performance plots of different training algorithms; Evaluation of mean absolute percentage error (MAPE) for hybrid GA-PSO-BPNN models.
Further study ideas to evaluate
Integration of the trained ML models with virtual PLC/DCS communication protocols (like Modbus TCP or OPC UA); Real-time hardware-in-the-loop (HIL) testing using microcontrollers (e.g., ESP32 or Arduino) for edge-based sensor linearization.
Check the complete source before describing any of these as new or absent from the original work.
Suggested verification steps
- Read the cited paper and check which methods, parameters and results it actually reports.
- Define a measurable project objective and list equipment or software you can access.
- Validate the proposed approach independently before claiming results, working code or experimental success.
Implementation ideas above are planning suggestions, not claims that the cited researchers built or tested those exact extensions.
Explore related B.Tech project topics or browse the engineering resource library for different methods and reference papers.