Skip to content

Stopping Corrosion Before It Starts: Real-Time Multisensor AI Forecasting for Hydroprocessing Units

Sep 2026 · GOTECH · 0 citations · 3 references

Abstract

Reactor-effluent piping in hydroprocessing units represents one of the most integrity-critical environments in modern refining. In Diesel Hydrotreating Units (DHTs), stabilized austenitic stainless steel SS321 is exposed to high-temperature hydrogen, steep thermal gradients, rapid depressurization, and mixed-phase flow transitions immediately downstream of the reactor. These coupled conditions promote hydrogen-assisted degradation and episodic thinning that evolve dynamically and often escape detection between periodic inspections. This paper presents a refinery-validated, multisensor artificial intelligence (AI) framework that forecasts metal-loss excursions 45–60 days in advance in the hot high-pressure loop of a 1.2 MMTPA DHT. High-frequency process data are fused with process-intelligence diagnostics and historical Ultrasonic Thickness (UT) measurements to generate forward-looking integrity predictions. Long Short-Term Memory (LSTM) neural networks are employed to capture temporal degradation behaviour, while XGBoost models quantify nonlinear interactions and rank process drivers. A novel Integrity Forecasting Index (IFI) is introduced to translate AI outputs into actionable integrity risk aligned with refinery Risk-Based Inspection (RBI) workflows. Forward validation against UT measurements from a future inspection cycle demonstrates strong agreement between predicted and measured thinning, achieving 93% predictive accuracy with a Mean Absolute Percentage Error (MAPE) of 6.8% and a 35% reduction in Root Mean Square Error (RMSE) relative to conventional rate-based methods. The framework identified multiple short-duration thinning accelerations that were not apparent from inspection intervals alone, enabling proactive mitigation and measurable operational benefit. The study demonstrates a practical pathway for transitioning refinery integrity management from retrospective inspection to predictive foresight using existing plant data infrastructure, aligning directly with digital transformation and sustainability objectives.

View source

Similar papers

#artificial intelligence Preprint Jul 2024

The Llama 3 Herd of Models

It is found that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks, and performs competitively with the state-of-the-art on image, video, and speech recognition tasks.

Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri et al. · 21,082 citations · ⚡3,832
#artificial intelligence Conference Open access Jun 2018

Gibson Env: Real-World Perception for Embodied Agents

This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.

F. Xia, Amir Zamir, Zhi-Yang He et al. · 1,069 citations · ⚡112
#artificial intelligence Open access May 2023

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...

Xiaotian Zhang, Chun-yan Li, Yi Zong et al. · 216 citations · ⚡17

KTO: Model Alignment as Prospect Theoretic Optimization

This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.

Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff et al. · 195 citations · ⚡28
#artificial intelligence Open access Jul 2024

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.

Kyra Wilson, Aylin Caliskan · 131 citations · ⚡8

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.