arXiv subjects

Muhammad Anwar

Publications and source records attributed to Muhammad Anwar.

10 recordsLinked to original sources

arXiv2026

AI-Assisted Knowledge Access for Legacy Enterprise Asset Management in Energy Operations: A Practical Retrieval System

Energy utilities still run engineering work management, engineering procurement, and inventory processes on long-lived enterprise asset management platforms. Replacing these platforms is often cost prohibitive and operationally disruptive, so practical improvement layers are required. This paper presents a retrieval assistant that improves day-to-day knowledge access across three operational modes: vendor documentation question answering, operational data store (ODS) schema question answering, and user interface usage and how-to question answering. The runtime method combines intent understanding, query rewriting, hybrid semantic and vector retrieval, context engineering under token limits, grounded answer generation, and deterministic hyperlink conversion for panel identifiers and cited documentation. The data preparation pipeline emphasizes semantic enrichment as the primary quality lever by adding table and field descriptions, normalizing acronyms across sources, and indexing representative row-level context when useful. A measured pilot shows consistent gains in retrieval quality and user outcomes. Precision at five improved from 0.56 to 0.72, mean reciprocal rank from 0.43 to 0.58, and normalized discounted cumulative gain (nDCG) at five from 0.51 to 0.66. Median task completion time dropped from 14.2 to 8.3 minutes, while usefulness and confidence both increased to 4.0 on a five-point scale. Results are based on a small sample and are reported as pilot findings, but they indicate that intent understanding and semantic enrichment can deliver meaningful operational value in legacy environments while also establishing reusable foundations for future analytics and automation tools.

cs.IR↗

arXiv2025

Towards Secure and Private Language Models for Nuclear Power Plants

This paper introduces a domain-specific Large Language Model for nuclear applications, built from the publicly accessible Essential CANDU textbook. Drawing on a compact Transformer-based architecture, the model is trained on a single GPU to protect the sensitive data inherent in nuclear operations. Despite relying on a relatively small dataset, it shows encouraging signs of capturing specialized nuclear vocabulary, though the generated text sometimes lacks syntactic coherence. By focusing exclusively on nuclear content, this approach demonstrates the feasibility of in-house LLM solutions that align with rigorous cybersecurity and data confidentiality standards. Early successes in text generation underscore the model's utility for specialized tasks, while also revealing the need for richer corpora, more sophisticated preprocessing, and instruction fine-tuning to enhance domain accuracy. Future directions include extending the dataset to cover diverse nuclear subtopics, refining tokenization to reduce noise, and systematically evaluating the model's readiness for real-world applications in nuclear domain.

cs.CL↗

arXiv2025

Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data

The nuclear industry possesses a wealth of valuable information locked away in unstructured text data. This data, however, is not readily usable for advanced Large Language Model (LLM) applications that require clean, structured question-answer pairs for tasks like model training, fine-tuning, and evaluation. This paper explores how synthetic data generation can bridge this gap, enabling the development of robust LLMs for the nuclear domain. We discuss the challenges of data scarcity and privacy concerns inherent in the nuclear industry and how synthetic data provides a solution by transforming existing text data into usable Q&A pairs. This approach leverages LLMs to analyze text, extract key information, generate relevant questions, and evaluate the quality of the resulting synthetic dataset. By unlocking the potential of LLMs in the nuclear industry, synthetic data can pave the way for improved information retrieval, enhanced knowledge sharing, and more informed decision-making in this critical sector.

cs.CL↗

arXiv2025

Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL

Retrieving operational data from nuclear power plants requires exceptional accuracy and transparency due to the criticality of the decisions it supports. Traditionally, natural language to SQL (NL-to-SQL) approaches have been explored for querying such data. While NL-to-SQL promises ease of use, it poses significant risks: end-users cannot easily validate generated SQL queries, and legacy nuclear plant databases -- often complex and poorly structured -- complicate query generation due to decades of incremental modifications. These challenges increase the likelihood of inaccuracies and reduce trust in the approach. In this work, we propose an alternative paradigm: leveraging function-calling large language models (LLMs) to address these challenges. Instead of directly generating SQL queries, we define a set of pre-approved, purpose-specific functions representing common use cases. Queries are processed by invoking these functions, which encapsulate validated SQL logic. This hybrid approach mitigates the risks associated with direct NL-to-SQL translations by ensuring that SQL queries are reviewed and optimized by experts before deployment. While this strategy introduces the upfront cost of developing and maintaining the function library, we demonstrate how NL-to-SQL tools can assist in the initial generation of function code, allowing experts to focus on validation rather than creation. Our study includes a performance comparison between direct NL-to-SQL generation and the proposed function-based approach, highlighting improvements in accuracy and maintainability. This work underscores the importance of balancing user accessibility with operational safety and provides a novel, actionable framework for robust data retrieval in critical systems.

cs.CL↗

arXiv2024

Evaluating ChatGPT on Nuclear Domain-Specific Data

This paper examines the application of ChatGPT, a large language model (LLM), for question-and-answer (Q&A) tasks in the highly specialized field of nuclear data. The primary focus is on evaluating ChatGPT's performance on a curated test dataset, comparing the outcomes of a standalone LLM with those generated through a Retrieval Augmented Generation (RAG) approach. LLMs, despite their recent advancements, are prone to generating incorrect or 'hallucinated' information, which is a significant limitation in applications requiring high accuracy and reliability. This study explores the potential of utilizing RAG in LLMs, a method that integrates external knowledge bases and sophisticated retrieval techniques to enhance the accuracy and relevance of generated outputs. In this context, the paper evaluates ChatGPT's ability to answer domain-specific questions, employing two methodologies: A) direct response from the LLM, and B) response from the LLM within a RAG framework. The effectiveness of these methods is assessed through a dual mechanism of human and LLM evaluation, scoring the responses for correctness and other metrics. The findings underscore the improvement in performance when incorporating a RAG pipeline in an LLM, particularly in generating more accurate and contextually appropriate responses for nuclear domain-specific queries. Additionally, the paper highlights alternative approaches to further refine and improve the quality of answers in such specialized domains.

cs.CL↗

arXiv2024

Classification of Safety Events at Nuclear Sites using Large Language Models

This paper proposes the development of a Large Language Model (LLM) based machine learning classifier designed to categorize Station Condition Records (SCRs) at nuclear power stations into safety-related and non-safety-related categories. The primary objective is to augment the existing manual review process by enhancing the efficiency and accuracy of the safety classification process at nuclear stations. The paper discusses experiments performed to classify a labeled SCR dataset and evaluates the performance of the classifier. It explores the construction of several prompt variations and their observed effects on the LLM's decision-making process. Additionally, it introduces a numerical scoring mechanism that could offer a more nuanced and flexible approach to SCR safety classification. This method represents an innovative step in nuclear safety management, providing a scalable tool for the identification of safety events.

cs.CL↗

arXiv2022

Proximal Policy Optimization Based Reinforcement Learning for Joint Bidding in Energy and Frequency Regulation Markets

Driven by the global decarbonization effort, the rapid integration of renewable energy into the conventional electricity grid presents new challenges and opportunities for the battery energy storage system (BESS) participating in the energy market. Energy arbitrage can be a significant source of revenue for the BESS due to the increasing price volatility in the spot market caused by the mismatch between renewable generation and electricity demand. In addition, the Frequency Control Ancillary Services (FCAS) markets established to stabilize the grid can offer higher returns for the BESS due to their capability to respond within milliseconds. Therefore, it is crucial for the BESS to carefully decide how much capacity to assign to each market to maximize the total profit under uncertain market conditions. This paper formulates the bidding problem of the BESS as a Markov Decision Process, which enables the BESS to participate in both the spot market and the FCAS market to maximize profit. Then, Proximal Policy Optimization, a model-free deep reinforcement learning algorithm, is employed to learn the optimal bidding strategy from the dynamic environment of the energy market under a continuous bidding scale. The proposed model is trained and validated using real-world historical data of the Australian National Electricity Market. The results demonstrate that our developed joint bidding strategy in both markets is significantly profitable compared to individual markets.

eess.SY↗

arXiv2015

The Early Crystal Nucleation Process in Hard Spheres shows Synchronised Ordering and Densification

We investigate the early part of the crystal nucleation process in the hard sphere fluid using data produced by computer simulation. We find that hexagonal order manifests continuously in the overcompressed liquid, beginning approximately one diffusion time before the appearance of the first `solid-like' particle of the nucleating cluster, and that a collective influx of particles towards the nucleation site occurs simultaneously to the ordering process: the density increases leading to nucleation are generated by the same individual particle displacements as the increases in order. We rule out the presence of qualitative differences in the early nucleation process between medium and low overcompressions, and also provide evidence against any separation of translational and orientational order on the relevant lengthscales.

cond-mat.soft↗

arXiv2014

Crystal nucleation mechanism in melts of short polymer chains under quiescent conditions and under shear flow

We present a molecular dynamics simulation study of crystal nucleation from undercooled melts of n-alkanes, and we identify the molecular mechanism of homogeneous crystal nucleation under quiescent conditions and under shear flow. We compare results for n-eicosane(C20) and n-pentacontahectane(C150), i.e. one system below the entanglement length and one above. Under quiescent conditions, we observe that entanglement does not have an effect on the nucleation mechanism. For both chain lengths, the chains first align and then straighten locally. Then the local density increases and finally positional ordering sets in. At low shear rates the nucleation mechanism is the same as under quiescent conditions, while at high shear rates the chains align and straighten at the same time. We report on the effects of shear rate and temperature on the nucleation rates and estimate the critical shear rates, beyond which the nucleation rates increase with the shear rate. We show that the viscosity of the system is not affected by the crystalline nuclei.

cond-mat.soft↗

arXiv2013

Crystallization mechanism in melts of short n-alkane chains

We study crystallization in a model system for eicosane (C20) by means of molecular dynamics simulation and we identify the microscopic mechanisms of homogeneous crystal nucleation and growth. For the nucleation process, we observe that chains first align and then straighten. Then the local density increases and finally the monomer units become ordered positionally. The subsequent crystal growth process is characterized by a sliding-in motion of the chains. Chains preferably attach to the crystalline cluster with one end and then move along the stems of already crystallized chains towards their final position. This process is cooperative, i.e. neighboring chains tend to get attached in clusters rather than independently

cond-mat.soft↗