FacProcessTwin: An LLM-Based System for Process Twin Development

Process twins provide real-time representations of entire production processes. By capturing how process steps interact, rather than monitoring a single machine in isolation as an asset-based digital twin does, they have the potential to drive efficiency gains across the whole process. However, developing a process twin is costly. It requires accurately modelling the entire production process: its process steps, the equipment and product-specific settings each step uses, and its process variations. The resulting model must then be bound to live operational data. We present FacProcessTwin, a system that leverages a large language model (LLM) to reduce this development time, building a process twin from a plant's process documentation and natural-language input from an operator. FacProcessTwin generates this complete process model and then automatically binds its process steps to live operational data. The generated model and its data bindings are rendered as an interactive process diagram through which manufacturing personnel can monitor and correct the system's autonomous decisions, such as resolving uncertainty at safety-critical binding steps. We evaluate FacProcessTwin through a real-world case study of an Australian food manufacturer, covering 16 production process flows that span chilled, frozen, and aseptic shelf-stable product categories and include process variations within the same product. The results show that FacProcessTwin generates these process models accurately (a mean F1 of 95.2% against ground truth) and builds each twin in roughly a sixth of the manual time. Its human-in-the-loop governance then keeps the safety-critical bindings correct: at ambiguous tags where a single-pass baseline silently mis-binds 75.0% of the time, FacProcessTwin defers to the operator and mis-binds none.

FactoryLLM: A Safe and Open-Source AI Playground for Evaluating LLMs in Smart Factories

Fault diagnostics and recovery in smart factories is challenging because critical information is dispersed across manuals of multiple machines which are interconnected through the manufacturing process. Large Language Models (LLMs) can provide a promising approach. In this paper, we propose FactoryLLM, a safe and open-source AI playground designed for evaluating different LLM-based retrieval-augmented generation (RAG) models by analysing documents from multiple machines across the manufacturing process. FactoryLLM enables the user to configure the LLM, and assess performance when reasoning over multiple documents, through a dual evaluation setup using both RAGAS and NVIDIA's LLM-as-a-Judge metrics. FactoryLLM is safe because it allows users to run local or open-source LLMs without sharing sensitive industrial data, providing a controlled environment for experimentation. We demonstrate the efficacy of FactoryLLM through a case study which involves an Autonomous Intelligent Vehicle and its Mobile Planner software, evaluating three LLMs across 30 maintenance queries derived from approximately 600 pages of cross-machine documentation. The results suggest that FactoryLLM is effective in cross-machine document reasoning: every model achieved a groundedness score above 0.88. The full code and documentation for community to test FactoryLLM with their manufacturing specific scenarios are publicly available.

An IIoT machine model for achieving consistency in product quality in manufacturing plants

Consistency in product quality is of critical importance in manufacturing. However, achieving a target product quality typically involves balancing a large number of manufacturing attributes. Existing manufacturing practices for dealing with such complexity are driven largely based on human knowledge and experience. The prevalence of manual intervention makes it difficult to perfect manufacturing practices, underscoring the need for a data-driven solution. In this paper, we present an Industrial Internet of Things (IIoT) machine model which enables effective monitoring and control of plant machinery so as to achieve consistency in product quality. We present algorithms that can provide product quality prediction during production, and provide recommendations for machine control. Subsequently, we perform an experimental evaluation of the proposed solution using real data captured from a food processing plant. We show that the proposed algorithms can be used to predict product quality with a high degree of accuracy, thereby enabling effective production monitoring and control.

Evaluating Sensor Data Quality in Internet ofThings Smart Agriculture Applications

The unprecedented growth of Internet of Things (IoT) and its applications in areas such as Smart Agriculture compels the need to devise newer ways for evaluating the quality of such applications. While existing models for application quality focus on the quality experienced by the end-user (captured using likert scale), IoT applications have minimal human involvement and rely on machine to machine communication and analytics to drive decision via actuations. In this paper, we first present a conceptual framework for the evaluation of IoT application quality. Subsequently, we propose, develop and validate via empirical evaluations a novel model for evaluating sensor data quality that is a key component in assessing IoT application quality. We present an implementation of the sensor data quality model and demonstrate how the IoT sensor data quality can be integrated with a Smart Agriculture application. Results of experimental evaluations conducted using data from a real-world testbed concludes the paper.