The transition towards Industry 4.0 has led to a significant increase in the adoption of smart manufacturing, where advanced technologies, such as Artificial Intelligence and Machine Learning, are used to optimize production processes. Quality control in manufacturing presents significant challenges, particularly in detecting non-visible defects. This paper proposes a novel approach to improve quality assurance in die-casting machines for car engine block production through thermographic image analysis. Specifically, we verify whether thermal patterns in the mold, captured immediately after the part is extracted, can serve as an indicator of internal defects in manufactured components, thereby avoiding the need for expensive and time-consuming leak tests. Our approach employs a stacking ensemble as its core. The ensemble integrates Convolutional Neural Networks and Vision Transformers, leveraging their complementary strengths for defect detection. An ensemble and threshold selection process is then carried out to identify optimal classifiers for defective and non-defective parts. Experimental results based on thermographic images from a mold used in the manufacture of 4-cylinder engine blocks demonstrate that the proposed framework can ensure the internal quality of up to 63.3% of components with high confidence. This result enables a significant reduction in reliance on leak tests, illustrating the viability of a real-time, cost-effective decision-making process that reduces bottlenecks and enhances overall manufacturing efficiency.

Abstract Predictability is key for efficient and safe air traffic management. In particular, accurately estimating time of arrival for current passenger flights may help terminal controllers to plan ahead and optimize airport operations in terms of safety and resource allocation. While traditional physics-based simulations are still widely used, they are complex to model and often fail to include many factors affecting the progress of a flight. In this paper, we propose a deep learning approach based on LSTM that leverages the 4D trajectory of the flight and weather data at the destination airport, to accurately predict estimated time of arrival. We evaluate our model on flights arriving at Adolfo Suárez-Madrid Barajas airport (Spain), in the first three quarters of 2022, achieving a mean absolute error of 2.65 min over the entire flight and reporting competitive short- and long-term predictions at different spatial and temporal horizons.

Fast and efficient fault monitoring and diagnostics methods are essential for fault diagnosis and prognosis tasks in Health Monitoring Systems. These tasks are even more complicated when facing dynamic systems with multiple operation points. This article introduces a symbiotic solution for fault detection and isolation, based on the integration of two complementary techniques: Possible Conflicts (PCs), a model-based diagnosis technique from the Artificial Intelligence (AI) community, and Principal Component Analysis (PCA), a Multivariate Statistical Process Control (MSPC) technique. Our proposal improves the PCA-based fault detection in systems with multiple operation points and transient states and provides a straightforward fault isolation stage for PCA. At the same time, the proposal increases the robustness for fault detection using PCs through the application of PCA to the residual signals. PCA has the ability to filter out residual deviations caused by model uncertainties that can lead to a high number of false positives. The proposed method has been successfully tested in a real-world plant with accurate fault detection results. The plant has noisy sensors and a system model without the same accuracy at each operation point and transient states.

Reliable and timely fault detection and isolation are necessary tasks to guarantee continuous performance in complex industrial systems, avoiding failure propagation in the system and helping to minimize downtime. Model-based diagnosis fulfils those requirements, and has the additional advantage of using reusable models. However, reusing existing complex non-linear models for diagnosis in large industrial systems is not straightforward. Most of the times, the models have been created for other purposes different from diagnosis, and many times the required analytical redundancy is small. The approach proposed in this work combines techniques from two different research communities within Artificial Intelligence: Model-based Reasoning and Neural Networks. In particular, in this work we propose to use Possible Conflicts, which is a model decomposition technique from the Artificial Intelligence community to provide the structure (equations, inputs, outputs, and state variables) of minimal models able to perform fault detection and isolation. Such structural information is then used to design a grey box model by means of state space neural networks. In this work we prove that the structure of the Minimal Evaluable Model for a Possible Conflict can be used in real-world industrial systems to guide the design of the state space model of the neural network, reducing its complexity and avoiding the process of multiple unknown parameter estimation in the first principles models. We demonstrate the feasibility of the approach in an evaporator for a beet sugar factory using real data.

Fault diagnosis is an essential part in the Health Management of autonomous vehicles. Within these vehicles the traction subsystem is a critical component, especially in those exploring planetary surfaces. Recent advances in brushless DC motors has raised the interest in new models and control configurations to integrate them in those vehicles due to their low energy consumption high torque/- mass ratio and low maintenance requirements. In this work we develop a full Bond Graph model of this subsystem, including the brushless motor and the control blocks needed for proper and efficient operation. These models will allow us to perform fault diagnosis with Bond Graph Possible Conflicts as the unifying formalism. We derive the Bond Graph-Possible Conflicts of the system, discussing the viability of the proposal.

Within systems health management, prognostics focuses on predicting the remaining useful life of a system. In the model-based prognostics paradigm, physics-based models are constructed that describe the operation of a system, and how it fails. Such approaches consist of an estimation phase, in which the health state of the system is first identified, and a prediction phase, in which the health state is projected forward in time to determine the end of life. Centralized solutions to these problems are often computationally expensive, do not scale well as the size of the system grows, and introduce a single point of failure. In this paper, we propose a novel distributed model-based prognostics scheme that formally describes how to decompose both the estimation and prediction problems into computationally-independent local subproblems whose solutions may be easily composed into a global solution. The decomposition of the prognostics problem is achieved through structural decomposition of the underlying models. The decomposition algorithm creates from the global system model a set of local submodels suitable for prognostics. Computationally independent local estimation and prediction problems are formed based on these local submodels, resulting in a scalable distributed prognostics approach that allows the local subproblems to be solved in parallel, thus offering increases in computational efficiency. Using a centrifugal pump as a case study, we perform a number of simulation-based experiments to demonstrate the distributed approach, compare the performance with a centralized approach, and establish its scalability.

The development of efficient and reliable fault detection approaches is necessary to improve performance, safety, and reliability in engineering systems. Moreover, these approaches have to be simple enough to provide quick diagnosis results and to reduce development and maintenance costs. Consistency-based diagnosis using possible conflicts (PCs) relies upon the simulation of numerical models to provide a simple and efficient fault diagnosis approach. However, simulation approaches need to know the initial state, and this assumption is not easily fulfilled in real systems, even in the presence of measurements related to state variables due to noise and parameter uncertainties. In this paper, we develop an approach where PCs are used to automatically compute structural models which can be implemented as simulation and state observer models. Using these models, we propose a framework which integrates those state observers to estimate the initial states for simulation within the consistency-based diagnosis framework. Then, both the simulation models and the state observers are used to provide quick detection decisions without increasing the complexity of the diagnoser. Our integration proposal is open to different kinds of state observers, except for the structural model, and different fault detection configurations. The proposal has been tested on a thermohydraulic reconfigurable laboratory plant using real data with satisfactory results.

The systems dynamics and control engineering (FDI) and the artificial intelligence diagnosis (DX) communities have developed complementary approaches that exploit structural relations in the system model to find efficient solutions for the residual generation and residual evaluation steps in fault detection and isolation in dynamic systems. This paper compares three different structural fault diagnosis techniques, two from the DX community and one from the FDI community. To simplify our comparison, we start with bond graphs as the common system modeling language and develop a graph-based framework using temporal causal graphs as the basis for analyzing the three fault isolation approaches. This framework allows for systematic comparison of the diagnosability properties of the three algorithms. The three-tank system is used as a running example to illustrate our concepts and algorithms.

Fault isolation and identification are necessary components for system reconfiguration and fault adaptive control in complex systems. However, accurate and timely on-line fault identification in nonlinear systems can be difficult and computationally expensive. In this paper, we improve the quantitative fault identification scheme in the TRANSCEND diagnosis approach. First, we propose to use possible conflicts (PCs) to find the set of minimally redundant subsystems that can be used for parameter estimation. Second, we introduce new algorithms for computing PCs from the temporal causal graph model used in TRANSCEND. Third, we use the minimal estimators to decompose the system model into smaller, independent subsystems for the parameter estimation task. We demonstrate the feasibility of this method by running experiments on a simulated model of the reverse osmosis subsystem of the advanced water recovery system developed at the NASA Johnson Space Center. Our results show a considerable reduction in parameter estimation time without loss of accuracy and robustness in the estimation.

This paper is focused on structural approaches to study diagnosability properties given a system model taking into account, both simultaneously or separately, integral and differential causal interpretations for differential constraints. We develop a model characterization and corresponding algorithms, for studying system diagnosability using a structural decomposition that avoids generating the full set of system analytical redundancy relations. Simultaneous application of integral and differential causal interpretations for differential constraints results in a mixed causality interpretation for the system. The added power of mixed causality is demonstrated using a Reverse Osmosis Subsystem from the Advanced Water Recovery System developed at the NASA Johnson Space Center. Finally, we summarize our work and provide a discussion of the advantages of mixed causality over just derivative or just integral causality.

Behaviour simulation in Consistency-based Diagnosis requires knowing the initial value. This assumption is not easily fulfilled in real systems, even in the presence of measurements related to state variables due to noise and parameter uncertainties.