XMDCA-TL: An Explainable Multi-Domain Channel Attention Transfer Learning Framework for Fault Diagnosis in Industrial Gas Turbines

In this study, a multi-task, interpretable transfer learning framework, XMDCA-TL, is proposed for fault diagnosis in industrial gas turbines. In the proposed method, the vibration time waveform is first converted into a multi-domain RGB representation comprising time, frequency, and time-frequency domains. A ConvNeXtV2-based encoder then processes these images, and the Multi-Domain Channel Attention (MDCA) mechanism is applied to its deep layers to model interactions among different domains and complementary dependencies in the signals. To improve the quality of the learned representations and enhance the model's robustness to noise, a self-supervised strategy based on hybrid masking, along with a UNet-based decoder to reconstruct the masked regions, has been designed. To overcome the limitation of labeled data in industrial environments, transfer learning was employed to transfer knowledge from laboratory data to real-world data from a 42.2 MW MGT-40 gas turbine at the Zahedan power plant. Additionally, a comprehensive Explainable Artificial Intelligence (XAI) framework was developed to analyze decision-making regions, evaluate domain importance, examine the flow of attention between domains, and assess reconstruction uncertainty. The results showed that XMDCA-TL, while achieving satisfactory fault diagnosis performance, possesses domain adaptability and robustness to noise and provides a physical interpretation of the model's decision-making process.

Predictive Modeling of Rat Brain Local Field Potentials using Single-Variable and Multivariable Approaches

Accurate prediction of neural dynamics in the brain's reward circuitry is crucial for elucidating how natural and pharmacological rewards influence neural activity and connectivity. Traditional linear models, such as autoregressive (AR) and vector autoregressive (VAR), often inadequately capture the inherent nonlinear interactions in neural data. This study develops and benchmarks both linear and advanced deep learning models for predicting local field potentials (LFPs) in the rat hippocampus (HIP) and nucleus accumbens (NAc) across morphine, food, and saline conditions. We compared AR, VAR, long short-term memory (LSTM), and wavelet-based deep learning model (WCLSA). Additionally, a novel wavelet coherence-enhanced model (WCOH CLSA) was introduced to capture cross-region connectivity. Results indicate that WCLSA achieves superior predictive accuracy (up to 0.97 for HIP in food, 0.96 for NAc in morphine), while VAR performs competitively in the food group due to significant HIP-NAc correlation. Wavelet coherence analysis reveals robust connectivity in natural reward contexts and disrupted or nonlinear relationships under pharmacological influence. These findings highlight the differential engagement of HIP and NAc in reward processing and underscore the importance of advanced nonlinear models for capturing complex neural dynamics. The study provides a robust framework for predictive neuroscience and elucidates functional interactions within the reward circuitry.

Applications of wavelet transform in classification of local field potential recorded from the rat brain in conditioned place preference paradigm

This study investigates the multi-label classification of Local Field Potential (LFP) data from the hippocampus (HIP) and nucleus accumbens (NAc) in the rat brain, focusing on reward responses using the Conditioned Place Preference (CPP) paradigm. Rats were conditioned with saline, morphine, and food rewards, and LFP recordings were conducted from both HIP and NAc during pre- and post-tests. The LFP data were classified into four categories: treatment types, test phases, recording channels, and chamber positions within the CPP setup. Features were extracted using Continuous Wavelet Transform (CWT), Wavelet Coherence, and Wavelet Scattering. Classification was performed via Decision Trees, Multilayer Perceptrons, and Support Vector Machines. Notably, in the Food group, HIP and combined HIP-NAc features yielded the highest classification accuracy for CPP chambers, whereas NAc features excelled in the Morphine group. Employing wavelet scattering, an 80% classification accuracy was achieved across treatment groups, test phases, and channels. Exceptionally high classification accuracies were observed for Food-post-test-HIP (99.75%) and Morphine-post-test-NAc (99.58%). The study reveals that NAc activity is pivotal for morphine-induced CPP, whereas HIP and HIP-NAc connectivity are crucial for food-induced CPP. The proposed methodology provides a novel avenue for precisely classifying LFP data, shedding light on neural circuit activities underlying behavioral responses.

Learning a Factorized Orthogonal Latent Space using Encoder-only Architecture for Fault Detection; An Alarm management perspective

False and nuisance alarms in industrial fault detection systems are often triggered by uncertainty, causing normal process variable fluctuations to be erroneously identified as faults. This paper introduces a novel encoder-based residual design that effectively decouples the stochastic and deterministic components of process variables without imposing detection delay. The proposed model employs two distinct encoders to factorize the latent space into two orthogonal spaces: one for the deterministic part and the other for the stochastic part. To ensure the identifiability of the desired spaces, constraints are applied during training. The deterministic space is constrained to be smooth to guarantee determinism, while the stochastic space is required to resemble standard Gaussian noise. Additionally, a decorrelation term enforces the independence of the learned representations. The efficacy of this approach is demonstrated through numerical examples and its application to the Tennessee Eastman process, highlighting its potential for robust fault detection. By focusing decision logic solely on deterministic factors, the proposed model significantly enhances prediction quality while achieving nearly zero false alarms and missed detections, paving the way for improved operational safety and integrity in industrial environments.

Dynamic importance learning using fisher information gain for nonlinear system identification

The Fisher Information Matrix (FIM) provides a way for quantifying the information content of an observable random variable concerning unknown parameters within a model that characterizes the variable. When parameters in a model are directly linked to individual features, the diagonal elements of the FIM can signify the relative importance of each feature. However, in scenarios where feature interactions may exist, a comprehensive exploration of the full FIM is necessary rather than focusing solely on its diagonal elements. This paper presents an end-to-end black box system identification approach that integrates the FIM into the training process to gain insights into dynamic importance and overall model structure. A decision module is added to the first layer of the network to determine the relevance scores using the entire FIM as input. The forward propagation is then performed on element-wise multiplication of inputs and relevance scores. Simulation results demonstrate that the proposed methodology effectively captures various types of interactions between dynamics, outperforming existing methods limited to polynomial interactions. Moreover, the effectiveness of this novel approach is confirmed through its application in identifying a real-world industrial system, specifically the PH neutralization process.

A Global Data-Driven Model for The Hippocampus and Nucleus Accumbens of Rat From The Local Field Potential Recordings

In brain neural networks, Local Field Potential (LFP) signals represent the dynamic flow of information. Analyzing LFP clinical data plays a critical role in improving our understanding of brain mechanisms. One way to enhance our understanding of these mechanisms is to identify a global model to predict brain signals in different situations. This paper identifies a global data-driven based on LFP recordings of the Nucleus Accumbens and Hippocampus regions in freely moving rats. The LFP is recorded from each rat in two different situations: before and after the process of getting a reward which can be either a drug (Morphine) or natural food (like popcorn or biscuit). A comparison of five machine learning methods including Long Short Term Memory (LSTM), Echo State Network (ESN), Deep Echo State Network (DeepESN), Radial Basis Function (RBF), and Local Linear Model Tree (LLM) is conducted to develop this model. LoLiMoT was chosen with the best performance among all methods. This model can predict the future states of these regions with one pre-trained model. Identifying this model showed that Morphine and natural rewards do not change the dynamic features of neurons in these regions.

Contrastive Multi-Modal Representation Learning for Spark Plug Fault Diagnosis

Due to the incapability of one sensory measurement to provide enough information for condition monitoring of some complex engineered industrial mechanisms and also for overcoming the misleading noise of a single sensor, multiple sensors are installed to improve the condition monitoring of some industrial equipment. Therefore, an efficient data fusion strategy is demanded. In this research, we presented a Denoising Multi-Modal Autoencoder with a unique training strategy based on contrastive learning paradigm, both being utilized for the first time in the machine health monitoring realm. The presented approach, which leverages the merits of both supervised and unsupervised learning, not only achieves excellent performance in fusing multiple modalities (or views) of data into an enriched common representation but also takes data fusion to the next level wherein one of the views can be omitted during inference time with very slight performance reduction, or even without any reduction at all. The presented methodology enables multi-modal fault diagnosis systems to perform more robustly in case of sensor failure occurrence, and one can also intentionally omit one of the sensors (the more expensive one) in order to build a more cost-effective condition monitoring system without sacrificing performance for practical purposes. The effectiveness of the presented methodology is examined on a real-world private multi-modal dataset gathered under non-laboratory conditions from a complex engineered mechanism, an inline four-stroke spark-ignition engine, aiming for spark plug fault diagnosis. This dataset, which contains the accelerometer and acoustic signals as two modalities, has a very slight amount of fault, and achieving good performance on such a dataset promises that the presented method can perform well on other equipment as well.

Imbalanced Classification In Faulty Turbine Data: New Proximal Policy Optimization

There is growing importance to detecting faults and implementing the best methods in industrial and real-world systems. We are searching for the most trustworthy and practical data-based fault detection methods proposed by artificial intelligence applications. In this paper, we propose a framework for fault detection based on reinforcement learning and a policy known as proximal policy optimization. As a result of the lack of fault data, one of the significant problems with the traditional policy is its weakness in detecting fault classes, which was addressed by changing the cost function. Using modified Proximal Policy Optimization, we can increase performance, overcome data imbalance, and better predict future faults. When our modified policy is implemented, all evaluation metrics will increase by $3\%$ to $4\%$ as compared to the traditional policy in the first benchmark, between $20\%$ and $55\%$ in the second benchmark, and between $6\%$ and $14\%$ in the third benchmark, as well as an improvement in performance and prediction speed compared to previous methods.

Time-domain Classification of the Brain Reward System: Analysis of Natural- and Drug-Reward Driven Local Field Potential Signals in Hippocampus and Nucleus Accumbens

Addiction is a major public health concern characterized by compulsive reward-seeking behavior. The excitatory glutamatergic signals from the hippocampus (HIP) to the Nucleus accumbens (NAc) mediate learned behavior in addiction. Limited comparative studies have investigated the neural pathways activated by natural and unnatural reward sources. This study has evaluated neural activities in HIP and NAc associated with food (natural) and morphine (drug) reward sources using local field potential (LFP). We developed novel approaches to classify LFP signals into the source of reward and recorded regions by considering the time-domain feature of these signals. Proposed methods included a validation step of the LFP signals using autocorrelation, Lyapunov exponent and Hurst exponent to assess the meaningful stability of these signals (lack of chaos). By utilizing the probability density function (PDF) of LFP signals and applying Kullback-Leibler divergence (KLD), data were classified to the source of the reward. Also, HIP and NAc regions were visually separated and classified using the symmetrized dot pattern technique, which can be applied in real-time to ensure the deep brain region of interest is being targeted accurately during LFP recording. We believe our method provides a computationally light and fast, real-time signal analysis approach with real-world implementation.

Adaptive Model Learning of Neural Networks with UUB Stability for Robot Dynamic Estimation

Since batch algorithms suffer from lack of proficiency in confronting model mismatches and disturbances, this contribution proposes an adaptive scheme based on continuous Lyapunov function for online robot dynamic identification. This paper suggests stable updating rules to drive neural networks inspiring from model reference adaptive paradigm. Network structure consists of three parallel self-driving neural networks which aim to estimate robot dynamic terms individually. Lyapunov candidate is selected to construct energy surface for a convex optimization framework. Learning rules are driven directly from Lyapunov functions to make the derivative negative. Finally, experimental results on 3-DOF Phantom Omni Haptic device demonstrate efficiency of the proposed method.