Improving Ultrasonic Testing by Using Machine Learning Framework Based on Model Interpretation Strategy

Ultrasonic testing(UT)is increasingly combined with machine learning(ML)techniques for intelligently identifying damage.Extracting signifcant features from UT data is essential for efcient defect characterization.Moreover,the hidden physics behind ML is unexplained,reducing the generalization capability and versatility of ML methods in UT.In this paper,a generally applicable ML framework based on the model interpretation strategy is proposed to improve the detection accuracy and computational efciency of UT.Firstly,multi-domain features are extracted from the UT signals with signal processing techniques to construct an initial feature space.Subsequently,a feature selection method based on model interpretable strategy(FS-MIS)is innovatively developed by integrating Shapley additive explanation(SHAP),flter method,embedded method and wrapper method.The most efective ML model and the optimal feature subset with better correlation to the target defects are determined self-adaptively.The proposed framework is validated by identifying and locating side-drilled holes(SDHs)with 0.5λcentral distance and different depths.An ultrasonic array probe is adopted to acquire FMC datasets from several aluminum alloy specimens containing two SDHs by experiments.The optimal feature subset selected by FS-MIS is set as the input of the chosen ML model to train and predict the times of arrival(ToAs)of the scattered waves emitted by adjacent SDHs.The experimental results demonstrate that the relative errors of the predicted ToAs are all below 3.67%with an average error of 0.25%,signifcantly improving the time resolution of UT signals.On this basis,the predicted ToAs are assigned to the corresponding original signals for decoupling overlapped pulse-echoes and reconstructing high-resolution FMC datasets.The imaging resolution is enhanced to 0.5λby implementing the total focusing method(TFM).The relative errors of hole depths and central distance are no more than 0.51%and 3.57%,respectively.Finally,the superior performance of the proposed FS-MIS is validated by comparing it with initial feature space and conventional dimensionality reduction techniques.

Predicting major adverse cardiovascular events after orthotopic liver transplantation using a supervised machine learning model:A cohort study

BACKGROUND Liver transplant(LT)patients have become older and sicker.The rate of post-LT major adverse cardiovascular events(MACE)has increased,and this in turn raises 30-d post-LT mortality.Noninvasive cardiac stress testing loses accuracy when applied to pre-LT cirrhotic patients.AIM To assess the feasibility and accuracy of a machine learning model used to predict post-LT MACE in a regional cohort.METHODS This retrospective cohort study involved 575 LT patients from a Southern Brazilian academic center.We developed a predictive model for post-LT MACE(defined as a composite outcome of stroke,new-onset heart failure,severe arrhythmia,and myocardial infarction)using the extreme gradient boosting(XGBoost)machine learning model.We addressed missing data(below 20%)for relevant variables using the k-nearest neighbor imputation method,calculating the mean from the ten nearest neighbors for each case.The modeling dataset included 83 features,encompassing patient and laboratory data,cirrhosis complications,and pre-LT cardiac assessments.Model performance was assessed using the area under the receiver operating characteristic curve(AUROC).We also employed Shapley additive explanations(SHAP)to interpret feature impacts.The dataset was split into training(75%)and testing(25%)sets.Calibration was evaluated using the Brier score.We followed Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for reporting.Scikit-learn and SHAP in Python 3 were used for all analyses.The supplementary material includes code for model development and a user-friendly online MACE prediction calculator.RESULTS Of the 537 included patients,23(4.46%)developed in-hospital MACE,with a mean age at transplantation of 52.9 years.The majority,66.1%,were male.The XGBoost model achieved an impressive AUROC of 0.89 during the training stage.This model exhibited accuracy,precision,recall,and F1-score values of 0.84,0.85,0.80,and 0.79,respectively.Calibration,as assessed by the Brier score,indicated excellent model calibration with a score of 0.07.Furthermore,SHAP values highlighted the significance of certain variables in predicting postoperative MACE,with negative noninvasive cardiac stress testing,use of nonselective beta-blockers,direct bilirubin levels,blood type O,and dynamic alterations on myocardial perfusion scintigraphy being the most influential factors at the cohort-wide level.These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE,making it a valuable tool for clinical practice.CONCLUSION Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE,using both cardiovascular and hepatic variables.The model demonstrated impressive performance,aligning with literature findings,and exhibited excellent calibration.Notably,our cautious approach to prevent overfitting and data leakage suggests the stability of results when applied to prospective data,reinforcing the model’s value as a reliable tool for predicting post-LT MACE in clinical practice.

Improving Prediction Efficiency of Machine Learning Models for Cardiovascular Disease in IoST-Based Systems through Hyperparameter Optimization

This study explores the impact of hyperparameter optimization on machine learning models for predicting cardiovascular disease using data from an IoST(Internet of Sensing Things)device.Ten distinct machine learning approaches were implemented and systematically evaluated before and after hyperparameter tuning.Significant improvements were observed across various models,with SVM and Neural Networks consistently showing enhanced performance metrics such as F1-Score,recall,and precision.The study underscores the critical role of tailored hyperparameter tuning in optimizing these models,revealing diverse outcomes among algorithms.Decision Trees and Random Forests exhibited stable performance throughout the evaluation.While enhancing accuracy,hyperparameter optimization also led to increased execution time.Visual representations and comprehensive results support the findings,confirming the hypothesis that optimizing parameters can effectively enhance predictive capabilities in cardiovascular disease.This research contributes to advancing the understanding and application of machine learning in healthcare,particularly in improving predictive accuracy for cardiovascular disease management and intervention strategies.

Real-time embedded software testing method based on extended finite state machine

The reliability of real-time embedded software directly determines the reliability of the whole real-time embedded sys- tem, and the effective software testing is an important way to ensure software quality and reliability. Based on the analysis of the characteristics of real-time embedded software, the formal method is introduced into the real-time embedded software testing field and the real-time extended finite state machine （RT-EFSM） model is studied firstly. Then, the time zone division method of real-time embedded system is presented and the definition and description methods of time-constrained transition equivalence class （timeCTEC） are presented. Furthermore, the approaches of the testing sequence and test case generation are put forward. Finally, the proposed method is applied to a typical avionics real- time embedded software testing practice and the examples of the timeCTEC, testing sequences and test cases are given. With the analysis of the testing result, the application verification shows that the proposed method can effectively describe the real-time embedded software state transition characteristics and real-time requirements and play the advantages of the formal methods in accuracy, effectiveness and the automation supporting. Combined with the testing platform, the real-time, closed loop and automated simulation testing for real-time embedded software can be realized effectively.

Software Development for Digital Control of WDW Series Testing Machine and Measurement of K_(IC)

Software has been developed for digital control of WDW series testing machine and the measurement of fracture toughness by modularized design. Development of the software makes use of multi-thread and serial communication techniques, which can accurately control the testing machine and measure the fracture toughness in real-time. Three-point bending specimens were used in the measurement. The software operates stably and reliably, expanding the function of WDW series testing machine.

Experimental Study on Thermal Stress of Concrete with Different Expansive Minerals Using a Temperature Stress Testing Machine

In order to compare the compensation effect of expansive materials with different mineral sources on the temperature stress of concrete,we investigated the temperature stress of concrete when adding calcium sulfoaluminate type expansive materials(CSA)or CaO and calcium sulfoaluminate mixed type expansive materials(HCSA)at different temperatures by temperature-stress testing machine(TSTM)considering the influence of temperature history on the expansion.The experimental results show that the expansion characteristics of the two kinds of expansive materials with different mineral sources significantly vary.When adding expansive materials,the growth rate of compressive stress during the heating stage increases obviously,the maximum compressive stress is higher,while the decline rate of tensile stress in the late cooling stage becomes slow,and finally cracking temperature decreases.It is proved that concrete with HCSA has lower cracking temperatures and better temperature shrinkage compensation effect.Therefore,it is rational to choose HCSA when preparing concrete with high expansion energy to reduce thermal cracking.

Machines and Testing Equipment

National Quality Supervision ＆ Inspection Center for Refractories Business scope： Selective examination for national quality supervision; Identification of production license; Arbitration inspection and technical achievements evaluation; Commodities inspection and otherquality inspections .

Estimation of Fatigue Strength of Reinforced Complete Upper Denture Using a Newly Designed Testing Machine: A Laboratory Research Project

In the present study, an aero pneumatic fatigue testing machine for complete dentures was designed, fabricated, and tested for the evaluation of the fatigue life of reinforced complete upper denture (CUD). On completion and testing, it was observed that the machine has the potential of generating reliable number of cyclic data. The machine’s performance was evaluated using test specimens of identical CUDs that were machined in conformity with standard procedures. The fatigue machine compressed the lower dental arch over the upper denture-specimen in centric occlusion, in the same way that the two masticatory muscles pull the lower jaw over the upper jaw during chewing. The incorporation of glass fibres into the CUD using a sandwich technique quadruples the lifespan of the denture (P = 0.004). The low standard deviation, along with the low coefficient of variation (CV) of the group of unreinforced dentures shows the repeatability of the results and the reliability of the machine. The high standard deviation and coefficient of variation of reinforced dentures was expected, since a high variation of results is usually recorded in fibre reinforcement cases. This research confirmed the view that the crack during denture fracture initiates in the anterior palatal area and propagates to the posterior.

Web Testing Generation: A Stream <i>X-Machine</i>Based Approach

To ensure the quality of Web applications, Web testing is one of the effective methods. The testing is a process of revealing errors that is used to give confidence that the implementation of a Web application meets its original specification. This work proposes a Web testing framework based on Stream X-Machines (SXMs), which provides a way to derive test cases for a Web application. It starts from constructing the SXM model, from which a test translator is employed to extract the test paths and then translates them into an XML-style test specification, which is the input of test engine. The test engine generates test cases and then executes them, and finally produces test report. This testing method is a significant contribution to informed research.

ANALYSIS AND SIMULATION ON THE MECHANISM OF A NOVEL DUAL-WAVE SHOCK TEST MACHINE

For qualifying the anti-shock performance of shipboard equipments and simulating actual underwater explosion environments, a novel dual-wave shock test machine is proposed to increase testing capability of shock test machines as well as to meet certain shock testing specification. The machine can generate a double-pulse acceleration shock for test articles according to specification defined in BV043/85. On the basis of the impact theory, a nonlinear dynamic model of the hydraulically-actuated test machine is established with thorough analysis on its mechanism which involves conversion of gas potential energy and dissipation of kinetic energy. Simulation results have demonstrated that the machine can produce a double-pulse acceleration shock in the time domain or a desired shock response spectrum in the frequency domain, which sets a theoretical base for the construction of the proposed machine.

Identification of Kinematic Errors of Five-axis Machine Tool Trunnion Axis from Finished Test Piece

Compared with the traditional non-cutting measurement,machining tests can more accurately reflect the kinematic errors of five-axis machine tools in the actual machining process for the users.However,measurement and calculation of the machining tests in the literature are quite difficult and time-consuming.A new method of the machining tests for the trunnion axis of five-axis machine tool is proposed.Firstly,a simple mathematical model of the cradle-type five-axis machine tool was established by optimizing the coordinate system settings based on robot kinematics.Then,the machining tests based on error-sensitive directions were proposed to identify the kinematic errors of the trunnion axis of cradle-type five-axis machine tool.By adopting the error-sensitive vectors in the matrix calculation,the functional relationship equations between the machining errors of the test piece in the error-sensitive directions and the kinematic errors of C-axis and A-axis of five-axis machine tool rotary table was established based on the model of the kinematic errors.According to our previous work,the kinematic errors of C-axis can be treated as the known quantities,and the kinematic errors of A-axis can be obtained from the equations.This method was tested in Mikron UCP600 vertical machining center.The machining errors in the error-sensitive directions can be obtained by CMM inspection from the finished test piece to identify the kinematic errors of five-axis machine tool trunnion axis.Experimental results demonstrated that the proposed method can reduce the complexity,cost,and the time consumed substantially,and has a wider applicability.This paper proposes a new method of the machining tests for the trunnion axis of five-axis machine tool.

Vibration test of micro machined gyroscope based on high speed photography and SURF

Based on three kinds of dynamic test of MEMS, a dynamic system for the vibration test of micro machined gyroscope based on high speed photography is introduced. Firstly, the architecture of the system hardware is introduced. Secondly, the image tracking performance is compared by the test using the template matching algorithm, the mean shift algorithm and the SURF algorithm. The vibration curve shows that high speed photograph combined with SURF algorithm is faster, more ac- curate, and more suitable for the vibration test of micro machined gyroscope. After the frequency a- nalysis and related interpolation, more characteristics of micro gyroscope can be obtained.

结合GUM和MCM的R-Test在机标定不确定度评定方法

R-Test因其高精度、操作便捷等的优点而被广泛应用于五轴数控机床转动轴误差测量,但其测量精度受其标定不确定度的影响。针对原有通用的评定方法不能对接触式R-Test标定不确定度进行准确评定,基于接触式R-Test标定原理,提出一种结合GUM和MCM的在机标定不确定度评定方法,首先分析了不确定度的影响因素并采用变参数方法确定了其灵敏度系数,然后根据测量不确定度导则(GUM)计算传感器位置的标准不确定度分量,最后采用蒙特卡洛方法(MCM)实现对标定方法最终的不确定度评定。通过具体的评定实例,与独立使用GUM的评定结果进行对比,验证了该方法具有更高的评定精度。

使用Xcelium Machine Learning技术加速验证覆盖率收敛

随着设计越来越复杂,受约束的随机化验证方法已成为验证的主流方法。一般地,验证激励做到不违反spec描述条件下尽量随机,这样验证能跑到的空间才更充分。但是,这给功能覆盖率收敛带来极大挑战,为解决这一难题,Cadence率先推出了仿真器的机器学习功能——Xcelium Machine Learning,采用机器学习技术让功能覆盖率快速收敛,大大提高验证仿真效率。介绍了Xcelium Machine Learning的使用流程,并给出在相同模拟(simulation)验证环境下应用Machine Learning前后情况对比。最后Machine Learning在模拟(simulation)验证中的应用前景进行了展望。

Test Selection on Extended Finite State Machines with Provable Guarantees

Building high confidence regression test suites to validate new system versions is a challenging problem. A modelbased approach to build a regression test suite from a given test suite is described. The generated test suite includes every test that will traverse a change performed to produce the new version, and consists of only such tests to reduce the testing costs. Finite state machines extended with typed variables (EFSMs) are used to model systems and system changes are mapped to EFSM transition changes adding/deleting/replacing EFSM transitions and states. Tests are a sequence of input and expected output messages with concrete parameter values over the supported data types. An invariant is formulated to characterize tests whose runtime behavior can be accurately predicted by analyzing their descriptions along with the model. Incremental procedures to efficiently evaluate the invariant and to select tests for regression are developed. Overlaps among the test descriptions are exploited to extend the approach to simultaneously select multiple tests to reduce the test selection costs. Effectiveness of the approach is demonstrated by applying it to several protocols, Web services, and model programs extracted from a popular testing benchmark. Our experimental results show that the proposed approach is economical for regression test selection in all these examples. For all these examples, the proposed approach is able to identify all tests exercising changes more efficiently than brute-force symbolic evaluation.

NUMERICAL MODELING OF MULTI-CYLINDER ELECTRO-HYDRAULIC SYSTEM AND CONTROLLER DESIGN FOR SHOCK TEST MACHINE

A high fidelity dynamic model of a high-energy hydraulically-actuated shock test machine for heavy weight devices is presented to satisfy the newly-built shock resistance standard and simulate the actual underwater explosion environments in laboratory as well as increase the testing capability of shock test machine. In order to produce the required negative shock pulse in the given time duration, four hydraulic actuators are utilized. The model is then used to formulate an advanced feedforward controller for the system to produce the required negative waveform and to address the motion synchronization of the four cylinders. The model provides a safe and easily controllable way to perform a ＂virtual testing＂ before starting potentially destructive tests on specimen and to predict performance of the system. Simulation results have demonstrated the effectiveness of the controller.

Development of a Test Machine for IVECO Drive Axle

To improve the automation level of the vehicle drive axle test and better simulate a vehicle＇s actual operation, an advanced test machine has been developed. The load system of the machine consists of hand brakes and electric cylinders. It is simple-structured and low-cost. The major motor of the machine is controlled by a transducer and its speed can be adjusted easily. In addition, the programmed machine can automatically test such parameters as the grinding condition, the differential speed, the noise level, etc. It can also adjust the test procedures according to different requirements. Detailed discussion of the structure and mechanism of the test machine is given in this paper.

Support-Vector-Machine-Based False Alarm Filter of Mechatronic Built-in Test

Diagnosing intermittent fault is an important approach to reduce built-in test（BIT） false alarms. Aiming at solving the shortcoming of the present diagnostic method of intermittent fault, and according to the merit of support vector machines （ SVM） which can be trained with a small-sample, an SVM-based diagnostic model of 3 states that include OK state, intermittent state and faulty state is presented. With the features based on the reflection coefficients of an alarm rate （ AR ） model extracted from small vibration samples, these models are trained to diagnose intermittent faults. The experimental results show that this method can diagnose multiple intermittent faults accurately with small training samples and BIT false alarms are reduced.

Machine Learning Approach to Enhance the Performance of MNP?Labeled Lateral Flow Immunoassay

The use of magnetic nanoparticle(MNP)-labeled immunochromatography test strips(ICTSs) is very important for point-ofcare testing(POCT). However, common diagnostic methods cannot accurately analyze the weak magnetic signal from ICTSs, limiting the applications of POCT. In this study, an ultrasensitive multiplex biosensor was designed to overcome the limitations of capturing and normalization of the weak magnetic signal from MNPs on ICTSs. A machine learning model for sandwich assays was constructed and used to classify weakly positive and negative samples, which significantly enhanced the specificity and sensitivity. The potential clinical application was evaluated by detecting 50 human chorionic gonadotropin(HCG) samples and 59 myocardial infarction serum samples. The quantitative range for HCG was 1–1000 mIU mL^(-1) and the ideal detection limit was 0.014 mIU mL^(-1), which was well below the clinical threshold. Quantitative detection results of multiplex cardiac markers showed good linear correlations with standard values. The proposed multiplex assay can be readily adapted for identifying other biomolecules and also be used in other applications such as environmental monitoring, food analysis, and national security.

Seismic liquefaction potential assessment by using relevance vector machine

Determining the liquefaction potential of soil is important in earthquake engineering. This study proposes the use of the Relevance Vector Machine （RVM） to determine the liquefaction potential of soil by using actual cone penetration test （CPT） data. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. The results are compared with a widely used artificial neural network （ANN） model. Overall, the RVM shows good performance and is proven to be more accurate than the ANN model. It also provides probabilistic output. The model provides a viable tool for earthquake engineers to assess seismic conditions for sites that are susceptible to liquefaction.