TYRE DYNAMICS MODELLING OF VEHICLE BASED ON SUPPORT VECTOR MACHINES

Various methods of tyre modelling are implemented from pure theoretical to empirical or semi-empirical models based on experimental results. A new way of representing tyre data obtained from measurements is presented via support vector machines （SVMs）. The feasibility of applying SVMs to steady-state tyre modelling is investigated by comparison with three-layer backpropagation （BP） neural network at pure slip and combined slip. The results indicate SVMs outperform the BP neural network in modelling the tyre characteristics with better generalization performance. The SVMsqyre is implemented in 8-DOF vehicle model for vehicle dynamics simulation by means of the PAC 2002 Magic Formula as reference. The SVMs-tyre can be a competitive and accurate method to model a tyre for vehicle dynamics simuLation.

Small-time scale network traffic prediction based on a local support vector machine regression model

In this paper we apply the nonlinear time series analysis method to small-time scale traffic measurement data. The prediction-based method is used to determine the embedding dimension of the traffic data. Based on the reconstructed phase space, the local support vector machine prediction method is used to predict the traffic measurement data, and the BIC-based neighbouring point selection method is used to choose the number of the nearest neighbouring points for the local support vector machine regression model. The experimental results show that the local support vector machine prediction method whose neighbouring points are optimized can effectively predict the small-time scale traffic measurement data and can reproduce the statistical features of real traffic measurements.

Nonlinear model predictive control based on support vector machine and genetic algorithm

This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.

FAULT DIAGNOSIS APPROACH BASED ON HIDDEN MARKOV MODEL AND SUPPORT VECTOR MACHINE

Aiming at solving the problems of machine-learning in fault diagnosis, a diagnosis approach is proposed based on hidden Markov model （HMM） and support vector machine （SVM）. HMM usually describes intra-class measure well and is good at dealing with continuous dynamic signals. SVM expresses inter-class difference effectively and has perfect classify ability. This approach is built on the merit of HMM and SVM. Then, the experiment is made in the transmission system of a helicopter. With the features extracted from vibration signals in gearbox, this HMM-SVM based diagnostic approach is trained and used to monitor and diagnose the gearbox＇s faults. The result shows that this method is better than HMM-based and SVM-based diagnosing methods in higher diagnostic accuracy with small training samples.

Clinical Analysis of Primary Tracheobronchial Tumors in Children and Evaluation of the Predicting Models for Mucoepidermoid Carcinoma

Objective:To determine the clinical characteristics and prognosis of primary tracheobronchial tumors(PTTs)in children,and to explore the most common tumor identification methods.Methods:The medical records of children with PTTs who were hospitalized at the Children's Hospital of Chongqing Medical University from January 1995 to January 2020 were reviewed retrospectively.The clinical features,imaging,treatments,and outcomes of these patients were statistically analyzed.Machine learning techniques such as Gaussian na?ve Bayes,support vector machine(SVM)and decision tree models were used to identify mucoepidermoid carcinoma(ME).Results:A total of 16 children were hospitalized with PTTs during the study period.This included 5(31.3%)children with ME,3(18.8%)children with inflammatory myofibroblastic tumors(IMT),2 children(12.5%)with sarcomas,2(12.5%)children with papillomatosis and 1 child(6.3%)each with carcinoid carcinoma,adenoid cystic carcinoma(ACC),hemangioma,and schwannoma,respectively.ME was the most common tumor type and amongst the 3 ME recognition methods,the SVM model showed the best performance.The main clinical symptoms of PPTs were cough(81.3%),breathlessness(50%),wheezing(43.8%),progressive dyspnea(37.5%),hemoptysis(37.5%),and fever(25%).Of the 16 patients,7 were treated with surgery,8 underwent bronchoscopic tumor resection,and 1 child died.Of the 11 other children,3 experienced recurrence,and the last 8 remained disease-free.No deaths were observed during the follow-up period.Conclusion:PTT are very rare in children and the highest percentage of cases is due to ME.The SVM model was highly accurate in identifying ME.Chest CT and bronchoscopy can effectively diagnose PTTs.Surgery and bronchoscopic intervention can both achieve good clinical results and the prognosis of the 11 children that were followed up was good.

Selective ensemble modeling based on nonlinear frequency spectral feature extraction for predicting load parameter in ball mills

Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.

Construction of precise support vector machine based models for predicting promoter strength

Background： The prediction of the prokaryotic promoter strength based on its sequence is of great importance not only in the fundamental research of life sciences but also in the appfied aspect of synthetic biology. Much advance has been made to build quantitative models for strength prediction, especially the introduction of machine learning methods such as artificial neural network （ANN） has significantly improve the prediction accuracy. As one of the most important machine learning methods, support vector machine （SVM） is more powerful to learn knowledge from small sample dataset and thus supposed to work in this problem. Methods： To confirm this, we constructed SVM based models to quantitatively predict the promoter strength. A library of 100 promoter sequences and strength values was randomly divided into two datasets, including a training set （≥10 sequences） for model training and a test set （≥ 10 sequences） for model test. Results： The results indicate that the prediction performance increases with an increase of the size of training set, and the best performance was achieved at the size of 90 sequences. After optimization of the model parameters, a high-performance model was finally trained, with a high squared correlation coefficient for fitting the training set （R^2〉 0.99） and the test set （R^2〉 0.98）, both of which are better than that of ANN obtained by our previous work. Conclusions： Our results demonstrate the SVM-based models can be employed for the quantitative prediction of promoter strength.

Combined forecast method of HMM and LS-SVM about electronic equipment state based on MAGA

For the deficiency that the traditional single forecast methods could not forecast electronic equipment states, a combined forecast method based on the hidden Markov model（HMM） and least square support vector machine（LS-SVM） is presented. The multi-agent genetic algorithm（MAGA） is used to estimate parameters of HMM to overcome the problem that the Baum-Welch algorithm is easy to fall into local optimal solution. The state condition probability is introduced into the HMM modeling process to reduce the effect of uncertain factors. MAGA is used to estimate parameters of LS-SVM. Moreover, pruning algorithms are used to estimate parameters to get the sparse approximation of LS-SVM so as to increase the ranging performance. On the basis of these, the combined forecast model of electronic equipment states is established. The example results show the superiority of the combined forecast model in terms of forecast precision,calculation speed and stability.

Non-Destructive Crack Detection of Preserved Eggs Using a Machine Vision and Multivariate Analysis

Pidan or century egg, also known as preserved egg, is one of the most traditional and popular egg products in China. The crack detection of preserved eggshell is very important to guarantee its quality. In this study, we develop an image algorithm for preserved eggshell＇s crack detection by using natural light and polarized image. Four features including crack length, crack state coefficient, maximum projection and angular point are extracted from the natural light image by morphology calculus algorithms. The support vector machines（SVM） model with radial basis kernel function is established using the four features with an accuracy of about 92%. The detection accuracy is improved to 94% by using a new characteristic parameter of crack length on polarization image. The Multi-information fusion analysis indicates the potential for cracks detection by a real-time synthesis imaging system.

Anomaly detection of hot components in gas turbine based on frequent pattern extraction

Hot components operate in a high-temperature and high-pressure environment. The occurrence of a fault in hot components leads to high economic losses. In general, exhaust gas temperature(EGT) is used to monitor the performance of hot components.However, during the early stages of a failure, the fault information is weak, and is simultaneously affected by various types of interference, such as the complex working conditions, ambient conditions, gradual performance degradation of the compressors and turbines, and noise. Additionally, inadequate effective information of the gas turbine also restricts the establishment of the detection model. To solve the above problems, this paper proposes an anomaly detection method based on frequent pattern extraction. A frequent pattern model(FPM) is applied to indicate the inherent regularity of change in EGT occurring from different types of interference. In this study, based on a genetic algorithm and support vector machine regression, the relationship model between the EGT and interference was tentatively built. The modeling accuracy was then further improved through the selection of the kernel function and training data. Experiments indicate that the optimal kernel function is linear and that the optimal training data should be balanced in addition to covering the appropriate range of operating conditions and ambient temperature. Furthermore, the thresholds based on the Pauta criterion that is automatically obtained during the modeling process, are used to determine whether hot components are operating abnormally. Moreover, the FPM is compared with the similarity theory, which demonstrates that the FPM can better suppress the effect of the component performance degradation and fuel heat value fluctuation. Finally, the effectiveness of the proposed method is validated on seven months of actual data obtained from a Titan130 gas turbine on an offshore oil platform. The results indicate that the proposed method can sensitively detect malfunctions in hot components during the early stages of a fault, and is robust to various types of interference.