Coverage-enhanced fault diagnosis for Deep Learning programs: A learning-based approach with hybrid metrics

The problem of the wind turbine gearbox fault diagnosis was investigated by employing the support vector machine (SVM), which is optimized by the improved fruit fly intelligent algorithm with decreasing steps. First of all, the fault characteristic value extracted by Hilbert transform envelope is presented. Secondly, the general SVM solution to the wind turbine gearbox fault diagnosis problem is presented, where the improved fruit fly intelligent algorithm is adopted to optimize the performance of the model of the fault detection and diagnosis. Thirdly, the effectiveness of three fault diagnosis models are compared, including the fault detection and diagnosis model by the traditional SVM, its improved model optimized by the partical swarm optimization algorithm, and improved model by the SVM optimized by the proposed approach. By using the proposed optimization algorithm, the accuracy of gearbox fault diagnosis is much better than other two models, which are validated by the extensive simulation results based on practical historical operation data.

Many assessment and detection methods are used to diagnose faults in machines. High accuracy in fault detection and diagnosis can be achieved by using numerical methods with noise-resistant properties. However, to some extent, noise always exists in measured data on real machines, which affects the identification results, especially in the diagnosis of early- stage faults. In view of this situation, a damage assessment method based on blind source separation and dynamic fuzzy neural network (DFNN) is presented to diagnose the early-stage machinery faults in this paper. In the processing of measurement signals, blind source separation is adopted to reduce noise. Then sensitive features of these faults are obtained by extracting low dimensional manifold characteristics from the signals. The model for fault diagnosis is established based on DFNN. Furthermore, on-line computation is accelerated by means of compressed sensing. Numerical vibration signals of ball screw fault modes are processed on the model for mechanical fault diagnosis and the results are in good agreement with the actual condition even at the early stage of fault development. This detection method is very useful in practice and feasible for early-stage fault diagnosis.

Training deep neural networks can generate non-descriptive error messages or produce unusual output without any explicit errors at all. While experts rely on tacit knowledge to apply debugging strategies, non-experts lack the experience required to interpret model output and correct Deep Learning (DL) programs. In this work, we identify DL debugging heuristics and strategies used by experts, andIn this work, we categorize the types of errors novices run into when writing ML code, and map them onto opportunities where tools could help. We use them to guide the design of Umlaut. Umlaut checks DL program structure and model behavior against these heuristics; provides human-readable error messages to users; and annotates erroneous model output to facilitate error correction. Umlaut links code, model output, and tutorial-driven error messages in a single interface. We evaluated Umlaut in a study with 15 participants to determine its effectiveness in helping developers find and fix errors in their DL programs. Participants using Umlaut found and fixed significantly more bugs and were able to implement fixes for more bugs compared to a baseline condition.

Diagnosing faults in electric vehicles (EVs) is a great challenge. The purpose of this paper is to demonstrate the detection of faults in an electromechanical conversion chain for conventional or autonomous EVs. The information and data coming from different sensors make it possible for EVs to recover a series of information including currents, voltages, speeds, and so on. This information is processed to detect any faults in the electromechanical conversion chain. The novelty of this study is to develop an architecture for a fault diagnosis model by means of the feature extraction technique. In this regard, the long short-term memory (LSTM) approach for the fault diagnosis is proposed. This approach has been tested for an EV prototype in practice, is superior in accuracy over other fault diagnosis techniques, and is based on machine learning. An EV in an urban context is modeled, and then the fault diagnosis approach is applied based on deep learning architectures. The EV and the fault diagnosis model is simulated in Matlab software. It is also revealed how deep learning contributes to the fault diagnosis of EVs. The simulation and practical results confirm that higher accuracy in the fault diagnosis is obtained by applying the LSTM.

Nowadays, we are witnessing an increasing adoption of Deep Learning (DL) based software systems in many industries. Designing a DL program requires constructing a deep neural network (DNN) and then training it on a dataset. This process requires that developers make multiple architectural (e.g., type, size, number, and order of layers) and configuration (e.g., optimizer, regularization methods, and activation functions) choices that affect the quality of the DL models, and consequently software quality. An under-specified or poorly-designed DL model may train successfully but is likely to perform poorly when deployed in production. Design smells in DL programs are poor design and-or configuration decisions taken during the development of DL components, that are likely to have a negative impact on the performance (i.e., prediction accuracy) and then quality of DL based software systems. In this paper, we present a catalogue of 8 design smells for a popular DL architecture, namely deep Feedforward Neural Networks which is widely employed in industrial applications. The design smells were identified through a review of the existing literature on DL design and a manual inspection of 659 DL programs with performance issues and design inefficiencies. The smells are specified by describing their context, consequences, and recommended refactorings. To provide empirical evidence on the relevance and perceived impact of the proposed design smells, we conducted a survey with 81 DL developers. In general, the developers perceived the proposed design smells as reflective of design or implementation problems, with agreement levels varying between 47% and 68%.

Comparative study on deep transfer learning strategies for cross-system and cross-operation-condition building energy systems fault diagnosis

In order to meet the requirements of multi-parameter and real-time fault diagnosis of China VI vehicle emission standards diesel engine air system, this paper focuses on the research of the diesel engine air system fault detection and diagnosis method based on deep learning to improve the operational safety and fault diagnosis efficiency. In this paper, the air system fault detection and diagnosis are completed based on the AE model and the CNN model, combined with the actual operation of the diesel engine. Among them, the AE model successfully detected all real-time operation faults, and the false detection rate on the health data was 0.1162%; the CNN model obtained a 90.77% fault diagnosis accuracy rate on the test set of the real-time operation data set. The results show that the model has high accuracy in the diagnosis of diesel engine faults, which is of great significance to the application of deep learning based on big data processing.

A novel deep metric learning model for imbalanced fault diagnosis and toward open-set classification

Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions

Fault diagnosis keeps an essential tool to ensure the safety and reliability of a motor system. Based on deep learning, fault diagnosis models constructed by mining historical fault data of equipment have received extensive attention. However, the high computational cost constrains the application of deep learning models for fault diagnosis, especially when coping with multisource data. Inspired by the model reduction and neural network structure automatic search method, this article proposed a light weight multisensory fusion model for induction motor data fusion and diagnosis. Inverted residual block and network architecture search technology are introduced to accelerate the training speed and prediction speed of the diagnostic model, so that the diagnostic accuracy is maintained at an acceptable level. The effectiveness of the proposed model is demonstrated through motor fault diagnosis experiments. Compared with other popular neural networks, the proposed method is capable of judging fault patterns accurately with shorter prediction time.

Implementation of automation routines leveraging deep learning (DL) methods has been a growing topic of interest. The focus of this work is on the Gamma Knife (GK) workflow, specifically the approximation of dose distributions from GK plan parameters and the prediction of dose distributions using DL. These works contribute towards the larger goal of treatment plan prediction and are seen as intermediate steps towards that end. The approximation of dose distributions was motivated by the closed nature of the GK system, which causes complications with the evaluation of the predictions made by the DL models. The approximation utilizes a superposition method, accumulating dose from a basis set of dose distributions which correspond to specific sector activations of the GK system. The approximation method was compared to the original dose distributions calculated by the GK treatment planning system (TPS), Leksell GammaPlan, for 30 patients using the similarity metrics of Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) as well as the plan quality metrics of coverage, selectivity, and gradient index. In the range of clinical planning significance, the metrics reported strong agreement to the original calculation (DSC > 0.85, HD < 2.5mm, coverage difference = 0.014 ± 0.035, selectivity difference = 0.008 ± 0.037, and gradient index difference = 0.118 ± 0.192). The second focus of this work was to improve the performance of DL models used to predict dose distributions from target contour information. This was accomplished by applying transforms to the binary target contour volumes, resulting in alternate model input channels that encode the distance of each voxel to the boundary of the nearest contour, both within and outside of the contours. Training and evaluation were performed with a standard UNet and HD-UNet architecture for large and small targets separately. DSC and Predictions resulting from these encodings resulted in significantly better predictions (p < 0.05) than their binary target counterparts at all (excluding 90% isodose for the HD-Unet) threshold levels for small targets. The large target trainings were significantly (p < 0.05) improved in the mid-to-high dose ranges.

Turbocharged diesel engines are widely used for the propulsion and as the generators for powering auxiliary systems in marine applications. Many works were published on the development of diagnosis tools for the engines using data from simulation models or from experiments on a sophisticated engine test bench. However, the simulation data varies a lot with actual operational data, and the available sensor data on the actual vessel is much less compared to the data from test benches. Therefore, it is necessary to develop anomaly prediction and fault diagnosis models from limited data available from the engines. In this paper, an artificial intelligence (AI)-based anomaly detection model and machine learning (ML)-based fault diagnosis model were developed using the actual data acquired from a diesel engine of a cargo vessel. Unlike the previous works, the study uses operational, thermodynamic, and vibration data for the anomaly detection and fault diagnosis. The paper provides the overall architecture of the proposed predictive maintenance system including details on the sensorization of assets, data acquisition, edge computation, and AI model for anomaly prediction and ML algorithm for fault diagnosis. Faults with varying severity levels were induced in the subcomponents of the engine to validate the accuracy of the anomaly detection and fault diagnosis models. The unsupervised stacked autoencoder AI model predicts the engine anomalies with 87.6% accuracy. The balanced accuracy of supervised fault diagnosis model using Support Vector Machine algorithm is 99.7%. The proposed models are vital in marching towards sustainable shipping and have potential to deploy across various applications.

Background Until now, no method is available for automatic extraction of indicators of image quality and view standardization from echocardiographic recordings. Thus, description of data quality has been indirect, often by description of operators experience and the methodology used. Peak systolic global longitudinal strain (GLS) is a sensitive measure of left ventricular (LV) function, still hampered by random variability due to suboptimal standardization of recordings and variability in data processing by the operators. Data on how acquisitions and data processing influence GLS and its variability are scarce. Objectives Aim was to study the importance of image acquisition and data processing by experienced operators for GLS in a large healthy population by automatically extracting quality indicators using novel deep learning based image analysis software and vendor specific metadata. Secondly, we aimed to study how these characteristics influenced the reference ranges and GLS variability. Methods Participants from a large echocardiographic study were included. Echocardiography was performed according to current recommendations. Two experienced operators and two expert cardiologists read and re-read all GLS recordings (1,412 paired analyses). Acquisition- and data processing characteristics were extracted using deep learning and GLS software metadata providing specific data on position of landmarks in the view, as well as rotation and tilt of the cut-plane according to the best possible standard. From these measurements several quality indicators were provided (Table 1). Results Mean age for the 1,412 participants was 58±12 years and 56% were women. Averaged apical LV foreshortening in the recordings was ≤2 mm and the view specific recordings were well standardized, with high alignment with the preferred cut-plane for tilt and rotation across the three apical views (Figure 1). Most quality indicators influenced GLS and absolute GLS was lower with longer LVs (-0.2% per 1 cm, p=0.003) and longer distance from the transducer to the LV apex (-0.3% per 1 cm, p=0.02) in the recordings, and also for wider regions of interest during data processing (-0.7% per 1 mm, p &amp;lt;0.001). Absolute GLS was 0.7% higher per mm systolic foreshortening of the apical region of interest, and when more knots were placed under initialization of the ROI (0.1% per knot, p=0.004). In test-retest analyses, the results for agreement between operators followed the above presented data. Conclusions Novel quality indicators were successfully extracted using novel DL software and strain specific metadata. Even though acquisitions and data processing were well standardized, several quality indicators from both steps influenced GLS. Deep learning software and data processing metadata may provide quality indicators of the echocardiographic databases of importance to interpret the study outcomes and motivate researchers to optimize echocardiographic acquisitions and analyses.

This paper deals with information model for power grid fault diagnosis based on Common Information Model (CIM). Fault diagnosis gains information from topology information and device parameters of primary system grid based on IEC61970 standard and device information of secondary system grid based on IEC 61850. Device information contains information of protection movement wave record and protection configuration. However, the existent CIM can't fully represent power system fault diagnosis information. Thus, it is need to extend CIM. All kinds of information are based on different model, which causes different information standard. In this paper a preliminary study on CIM extensions which is based on power system fault diagnosis, has been proposed to perfect fault information model. On the basis of different standard model, this paper has discussed the theory of coordinating IEC 61850 and IEC61970 standard, and proposed using Web Ontology Language (OWL) based on Extensible Mark-up Language (XML) to the solution of this problem. A fault Information Model is then provided to the fault diagnosis system according to Component Interface Specification (CIS) in IEC61970. After receiving fault information, the fault diagnosis system starts for real-time, on-line fault diagnosis. Fault information model has solved the problem of the deficiency and non-standard of fault diagnosis information, attaining fault diagnosis information integrity and standardization, and making the fault diagnosis result fast and accurate.

Fault diagnosis of power distribution networks is a significant task for power system operation and maintenance, which can support rapid and accurate identification, localisation and repair of various faults that may occur in power distribution networks. To improve the accuracy and efficiency of fault diagnosis, this paper proposes a deep adaptive learning model for dealing with the data-driven identification problems in power systems. In the deep adaptive learning model, an adaptive shortcut learning scheme is designed to adaptively adjust the aggregation between the convolutional layers and the attention modules. In this manner, the hidden features can be effectively captured by adaptive learning with the proposed scheme. Therefore, the proposed model can effectively make online decisions on the fault types in high-voltage AC and DC test transmission. The experimental case study and comparison study in this paper demonstrate the reliable performance of the proposed model for online fault diagnosis of power distribution networks, which also show its capability and feasibility for online implementation.