Classification of spot-welded joint strength using ultrasonic signal time-frequency features and PSO-SVM method

Inspection of Spot Welded Joints with the Use of the Ultrasonic Surface Wave

Spot welded joints play a crucial role in the construction of modern automobiles, serving as a vital method for enhancing the structural integrity, strength, and durability of the vehicle body. Taking into account spot welding process in automotive bodies, numerous defects can arise, such as insufficient weld nugget diameter. It may have evident influence on vehicle operation or even contribute to accidents on the road. Hence, there is a need for non-invasive methods that allow to assess the quality of the spot welds without compromising their structural integrity and characteristics. Thus, this study describes a novel method for assessing spot welded joints using ultrasound technology. The usage of ultrasonic surface waves is the main component of the proposed advancement. The study employed ultrasonic transducers operating at a frequency of 10 MHz and a specially designed setup for testing various spot welded samples. The parameters of the spot welding procedure and the size of the weld nugget caused differences in the ultrasonic surface waveforms that were recorded during experiments. One of the indicators of weld quality was the amplitude of the ultrasonic pulse. For low quality spot welds, the amplitude amounted to around 25% of the maximum value when using single-sided transducers. Conversely, for high-quality welds an amplitude of 90% was achieved. Depending on the size of the weld nugget, a larger or smaller amount of wave energy is transferred, which results in a smaller or larger amplitude of the ultrasonic pulse. Comparable results were obtained when employing transducers on both sides of the tested joint, as an amplitude ranging from 13% for inferior welds to 97% for superior ones was observed. This research confirmed the feasibility of employing surface waves to assess the diameter of the weld nugget accurately.

Machine learning for ultrasonic nondestructive examination of welding defects: A systematic review

Recent years have seen a substantial increase in the application of machine learning (ML) for automated analysis of nondestructive examination (NDE) data. One of the applications of interest is the use of ML for the analysis of data from in-service inspection of welds in nuclear power and other industries. These types of inspections are performed in accordance with criteria described in the ASME Boiler and Pressure Vessel Code and require the use of reliable NDE techniques. The rapid growth in ML methods and the diversity of possible approaches indicate a need to assess the current capabilities of ML and automated data analysis for NDE and identify any gaps or shortcomings in current ML technologies as applied to the automated analysis of NDE data. In particular, there is a need to determine the impact of ML on the NDE reliability. This paper discusses the findings from a literature survey on the current state of ML for the automated analysis of data from ultrasonic NDE of weld flaws. It discusses an overview of ultrasonic NDE as used for weld inspections in nuclear power and other industries. Data sets and ML models used in the literature are summarized, along with a generally applicable workflow for ML. Findings on the capabilities, limitations and potential gaps in feature selection, data selection, and ML model optimization are discussed. The paper identified several needs for quantifying and validating the performance of ML methods for ultrasonic NDE, including the need for common data sets.

A New Approach to Optimize SVM for Insulator State Identification Based on Improved PSO Algorithm

The failure of insulators may seriously threaten the safe operation of the power system, where the state detection of high-voltage insulators is a must for the normal and safe operation of the power system. Based on the data of insulators in aerial images, this work explored an enhanced particle swarm algorithm to optimize the parameters of the support vector machine. A support vector machine model was therefore established for the identification of the normal and defective states of the insulators. This methodology works with the structure minimization principle of SVM and the characteristics of particle swarm fast optimization. First, the aerial insulator image was segmented as a target by way of the seed region growth based on double-layer cascade morphological improvements, and then, HOG features plus GLCM features were extracted as sample data. Finally, an ameliorated PSO-SVM classifier was designed to realize insulator state identification. Comparisons were made between PSO-SVM and conventional machine learning algorithms, SVM and Random Forest, and an optimization algorithm, Gray Wolf Optimization Support Vector Machine (GWO-SVM), and advanced neural network CNN. The experimental results showed that the performance of the algorithm proposed in this paper touched the top level, where the recognition accuracy rate was 92.11%, the precision rate 90%, the recall rate 94.74%, and the F1-score 92.31%.

A review of ultrasonic sensing and machine learning methods to monitor industrial processes

Supervised machine learning techniques are increasingly being combined with ultrasonic sensor measurements owing to their strong performance. These techniques also offer advantages over calibration procedures of more complex fitting, improved generalisation, reduced development time, ability for continuous retraining, and the correlation of sensor data to important process information. However, their implementation requires expertise to extract and select appropriate features from the sensor measurements as model inputs, select the type of machine learning algorithm to use, and find a suitable set of model hyperparameters. The aim of this article is to facilitate implementation of machine learning techniques in combination with ultrasonic measurements for in-line and on-line monitoring of industrial processes and other similar applications. The article first reviews the use of ultrasonic sensors for monitoring processes, before reviewing the combination of ultrasonic measurements and machine learning. We include literature from other sectors such as structural health monitoring. This review covers feature extraction, feature selection, algorithm choice, hyperparameter selection, data augmentation, domain adaptation, semi-supervised learning and machine learning interpretability. Finally, recommendations for applying machine learning to the reviewed processes are made.

Novel Leakage Detection Method by Improved Adaptive Filtering and Pattern Recognition based on Acoustic Waves

Pipeline leakages have plagued pipeline transportation for long time. Therefore, accurately extracting the features of leak signal in the presence of noise, and prompt identification of leak states and leak sizes is essential when leakage occurs. A novel leakage detection method based on the improved adaptive filter, whose parameters were optimized by the particle swarm optimization (PSO), was formulated and applied. The PSO-adaptive filter proved to be an effective signal processing method in contrast with variational mode decomposition (VMD). Its efficiency stems from the fact that the adaptive filter employs the noise collected from the detection environment. Therefore, the filter can adjust its parameters according to the changing situation. What is more, the application of PSO is conducive to automatically set suitable parameters for adaptive filter. After signal denoising, principal component analysis (PCA) was used for feature dimension reduction and selecting optimal features. The features after PCA proved to be more helpful in pattern recognition than the features without PCA. Furthermore, the relationship between the recognition results of leakage sizes and the measurement distance of the sensor was studied. Experimental results show that the method used in this paper can identify the leakage states with the accuracy of 100%. The identification result of leakage size reaches an accuracy of 86.75% under the influence of the measurement distance.

Ultrasonic based concrete defects identification via wavelet packet transform and GA-BP neural network

Concrete is the main material in building. Since its poor structural integrity may cause accidents, it is significant to detect defects in concrete. However, it is a challenging topic as the unevenness of concrete would lead to the complex dynamics with uncertainties in the ultrasonic diagnosis of defects. Note that the detection results mainly depend on the direct parameters, e.g., the time of travel through the concrete. The current diagnosis accuracy and intelligence level are difficult to meet the design requirement for automatic and increasingly high-performance demands. To solve the mentioned problems, our contribution of this paper can be summarized as establishing a diagnosis model based on the GA-BPNN method and ultrasonic information extracted that helps engineers identify concrete defects. Potentially, the application of this model helps to improve the working efficiency, diagnostic accuracy and automation level of ultrasonic testing instruments. In particular, we propose a simple and effective signal recognition method for small-size concrete hole defects. This method can be divided into two parts: (1) signal effective information extraction based on wavelet packet transform (WPT), where mean value, standard deviation, kurtosis coefficient, skewness coefficient and energy ratio are utilized as features to characterize the detection signals based on the analysis of the main frequency node of the signals, and (2) defect signal recognition based on GA optimized back propagation neural network (GA-BPNN), where the cross-validation method has been used for the stochastic division of the signal dataset and it leads to the BPNN recognition model with small bias. Finally, we implement this method on 150 detection signal data which are obtained by the ultrasonic testing system with 50 kHz working frequency. The experimental test block is a C30 class concrete block with 5, 7, and 9 mm penetrating holes. The information of the experimental environment, algorithmic parameters setting and signal processing procedure are described in detail. The average recognition accuracy is 91.33% for the identification of small size concrete defects according to experimental results, which verifies the feasibility and efficiency.

An improved QPSO-SVM-based approach for predicting the milling force for white marble in robot stone machining

Milling force prediction is one of the most important ways to improve the quality of products and stability in robot stone machining. In this paper, support vector machines (SVMs) are introduced to model the milling force of white marble, and the model parameters in the SVMs are optimized by the improved quantum-behaved particle swarm optimization (IQPSO) algorithm. A set of online inspection data from stone-machining robotic manipulators is adopted to train and test the model. The overall performance of the model is evaluated based on the decision coefficient (R2), mean absolute percentage error (MAPE) and root mean square error (RMSE), and the results obtained by IQPSO-SVM are superior to those of the PSO-SVM model. On this basis, the relationship between the milling force of white marble and various machining parameters is explored to obtain optimal machining parameters. The proposed model provides a tool for the adjustment of machining parameters to ensure stable machining quality. This approach is a new method and concept for milling force control and optimization research in the robotic stone milling process.

Identification of Rice Varieties and Transgenic Characteristics Based on Near-Infrared Diffuse Reflectance Spectroscopy and Chemometrics

Background: In recent years, genetically modified technology has developed rapidly, and the potential impact of genetically modified foods on human health and the ecological environment has received increasing attention. The currently used methods for testing genetically modified foods are cumbersome, time-consuming, and expensive. This paper proposed a more efficient and convenient detection method. Methods: Near-infrared diffuse reflectance spectroscopy (NIRDRS) combined with multivariate calibration methods, including principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), were used for identification of different rice varieties and transgenic (Bt63)/non-transgenic rice. Spectral pretreatment methods, including Norris–Williams smooth (NWS), standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky–Golay 1st derivative (SG 1st-Der), were used for spectral noise reduction and effective information enhancement. Accuracy was used to evaluate the qualitative discriminant models. Results: The results showed that the SG 1st-Der pretreatment method, combined with the SVM, provided the optimal model to distinguish different rice varieties. The accuracy of the optimal model was 98.33%. For the discrimination model of transgenic/non-transgenic rice, the SNV-SVM model, MSC-SVM model, and SG 1st-Der-PLS-DA model all achieved good analysis results with the accuracy of 100%. Conclusion: The results showed that portable NIR spectroscopy combined with chemometrics methods could be used to identify rice varieties and transgenic characteristics (Bt63) due to its fast, non-destructive, and accurate advantages.

Grouting Quality Evaluation in Post-Tensioning Tendon Ducts Using Wavelet Packet Transform and Bayes Classifier

The grouting quality of tendon ducts is very important for post-tensioning technology in order to protect the prestressing reinforcement from environmental corrosion and to make a smooth stress distribution. Unfortunately, various grouting defects occur in practice, and there is no efficient method to evaluate grouting compactness yet. In this study, a method based on wavelet packet transform (WPT) and Bayes classifier was proposed to evaluate grouting conditions using stress waves generated and received by piezoelectric transducers. Six typical grouting conditions with both partial grouting and cavity defects of different dimensions were experimentally investigated. The WPT was applied to explore the energy of received stress waves at multi-scales. After that, the Bayes classifier was employed to identify the grouting conditions, by taking the traditionally used total energy and the proposed energy vector of WPT components as input, respectively. The experimental results demonstrated that the Bayes classifier input with the energy vector could identify different grouting conditions more accurately. The proposed method has the potential to be applied at key spots of post-tensioning tendon ducts in practice.

Methane Detection Based on Improved Chicken Algorithm Optimization Support Vector Machine

Methane, known as a flammable and explosion hazard gas, is the main component of marsh gas, firedamp, and rock gas. Therefore, it is important to be able to detect methane concentration safely and effectively. At present, many models have been proposed to enhance the performance of methane predictions. However, the traditional models displayed inevitable shortcomings in parameter optimization in our experiment, which resulted in their having poor prediction performance. Accordingly, the improved chicken swarm algorithm optimized support vector machine (ICSO-SVM) was proposed to predict the concentration of methane precisely. The traditional chicken swarm optimization algorithm (CSO) easily falls into a local optimum due to its characteristics, so the ICSO algorithm was developed. The formula for position updating of the chicks of the ICSO is not only about the rooster of the same subgroup, but also about the roosters of other subgroups. Therefore, the ICSO algorithm more easily avoids falling into the local extremum. In this paper, the following work has been done. The sample data were obtained by using the methane detection system designed by us; In order to verify the validity of the ICSO algorithm, the ICSO, CSO, genetic algorithm (GA), and particle swarm optimization algorithm (PSO) algorithms were tested, and the four models were applied for methane concentration prediction. The results showed that he ICSO algorithm had the best convergence effect, relative error percentage, and average mean squared error, when the four models were applied to predict methane concentration. The results showed that the average mean squared error values of ICSO-SVM model were smaller than other three models, and that the ICSO-SVM model has better stability, and the average recovery rate of the ICSO-SVM is much closer to 100%. Therefore, the ICSO-SVM model can efficiently predict methane concentration.

Short-Term Wind Power Prediction Based on Improved Chicken Algorithm Optimization Support Vector Machine

Renewable energy technologies are essential contributors to sustainable energy including renewable energy sources. Wind energy is one of the important renewable energy resources. Therefore, efficient and consistent utilization of wind energy has been an important issue. The wind speed has the characteristics of intermittence and instability. If the wind power is directly connected to the grid, it will impact the voltage and frequency of the power system. Short-term wind power prediction can reduce the impact of wind power on the power grid and the stability of power system operation is guaranteed. In this study, the improved chicken swarm algorithm optimization support vector machine (ICSO-SVM) model is proposed to predict the wind power. The traditional chicken swarm optimization algorithm (CSO) easily falls into a local optimum when solving high-dimensional problems due to its own characteristics. So the CSO algorithm is improved and the ICSO algorithm is developed. In order to verify the validity of the ICSO-SVM model, the following work has been done. (1) The particle swarm optimization (PSO), ICSO, CSO and differential evolution algorithm (DE) are tested respectively by four standard testing functions, and the results are compared. (2) The ICSO-SVM and CSO-SVM models are tested respectively by two sets of wind power data. This study draws the following conclusions: (1) the PSO, CSO, DE and ICSO algorithms are tested by the four standard test functions and the test data are analyzed. By comparing it with the other three optimization algorithms, the ICSO algorithm has the best convergence effect. (2) The number of training samples has an obvious impact on the prediction results. The average relative error percentage and root mean square error (RMSE) values of the ICSO model are smaller than those of CSO-SVM model. Therefore, the ICSO-SVM model can efficiently provide credible short-term predictions for wind power forecasting.