Target Machine Research Articles

Digital dynamic modeling and topology optimized design of shell face mills

This paper presents digital modeling of shell face mills in milling cylinder heads. The cutter's structural dynamics and its mode shapes are predicted using a Finite Element system. The geometries of the cutter body and inserts are imported from their Computer Aided Design (CAD) models. The insert edge is discretized into small segments to model its varying normal rake and inclination angles, which affect the cutting mechanics. The cutter is dynamically assembled with the target machine tool spindle using the receptance coupling method. A general dynamic cutting force model, which considers the varying edge geometry and inserts’ run-outs, is developed and used to predict cutting forces and chatter stability diagrams. The proposed model is experimentally verified to demonstrate the feasibility of the systematic application of physics-based digital design and analysis of tools for the mass machining of specific parts. The cutter body shape is optimized to increase the stiffness of the bending mode shape that caused chatter via topology optimization, which led to five-fold increase in the absolute stable depth of cut.

Modeling and performance analysis of an electric two-wheeler on various driving cycles and validation using a performance real-time target machine

Compared with conventional two-wheelers, electric two-wheelers are gaining popularity owing to their potential to reduce emissions, their dependency on fossil fuels, and their enhanced economic benefits. However, the electric two-wheelers face key challenges such as inconsistent performance and driving range due to varying driving conditions. This study overcomes this challenge by developing a comprehensive system to investigate and predict the behavior of electric two-wheelers under various vehicle and battery parameters, driving conditions, and ambient conditions. The developed system, implemented in MATLAB Simulink, includes five subsections (the driving cycle, motor controller unit, electric motor, battery pack, and vehicle model) and evaluates the state of health, cell temperature, energy consumption, driving range, and state of charge. To validate the model, a simulation was conducted using a Speedgoat performance real-time target machine. An extensive evaluation is executed to validate the accuracy of the developed system against the real-time performance of an electric two-wheeler. For both simulated and standard driving cycles, the model offers an error of less than 1 %. The results of the analysis show that maintaining a mean speed between 18 km/h and 35 km/h results in the least energy consumption, a higher driving range, and a lower cell temperature. In addition, the research results show that driving aggressively consumes more energy. The results of this research indicate an innovative contribution toward the recognition and selection of appropriate electric two-wheelers.

Robust knowledge transfer for bearing diagnosis in neural network models using multilayer maximum mean discrepancy loss function

Abstract This paper introduces a robust transfer learning method to enhance bearing diagnosis, particularly in cross-machine scenarios. The method trains a shallow neural network using labeled data from a different machine and unlabeled data from the target monitoring machine. To facilitate effective knowledge transfer, a multilayer maximum mean discrepancy loss function is employed, enabling the model to adapt learned features from the source machine to the target machine’s unlabeled data. This approach addresses the challenges of low accuracy and robustness often seen in transfer learning, especially when dealing with different machines. Experiments conducted on the Hanoi University of Science and Technology bearing dataset validate the effectiveness of the proposed method. The results show significant improvements in prediction accuracy and robustness, making this method superior to existing transfer learning models for cross-machine bearing diagnosis.

A Novel Estimating Algorithm of Critical Driving Parameters for Dual-Motor Electric Drive Tracked Vehicles Based on a Nonlinear Observer and an Adaptive Kalman Filter

High-speed dual-motor electric drive tracked vehicles (DDTVs) have emerged as a research hotspot in the field of tracked vehicles in recent years due to their advantages in fuel economy and the scalability of electrical equipment. The emergency braking of a DDTV at high speed can lead to slipping or even yawing (which is caused by a large deviation of forces at each track directly), posing significant challenges to the vehicle’s stability and safety. Therefore, the accurate real-time acquisition of critical driving parameters, such as the longitudinal force and vehicle speed, is crucial for the stability control of a DDTV. This paper developed a novel estimating algorithm of critical driving parameters for DDTVs equipped with conventional sensors such as rotary transformers at PMSMs and onboard accelerometers on the basis of their dynamics models. The algorithm includes a sensor signal preprocessing module, a longitudinal force estimation method based on a nonlinear observer, and a speed estimation method based on an adaptive Kalman filter. Through hardware-in-loop experiments based on a Speedgoat real-time target machine, the proposed algorithm is proven to estimate the longitudinal force of the track and vehicle speed accurately, whether the vehicle has stability control functions or not, providing a foundation for the further development of vehicle stability control algorithms.

Simplified Finite Control Set Model Predictive Control for single-phase grid-tied inverters with twisted parameters

Large computational burden, time delay, and the necessity for precise modeling accuracy are the three main challenges for Finite Control Set-Model Predictive Control (FCS-MPC) in single-phase grid-tied inverters. To solve these issues, a twisted parameter scheme is proposed for the single-phase inverter in this article. Firstly, the law regarding the influence of the model parameter on the current total harmonic distortion (THD) is outlined, emphasizing that a decrease in the inductance parameter leads to a corresponding reduction in current THD. Second, a linear observer is constructed to identify the actual value of inductance and resistance, and an RBF-GA (Radial Basis Function neural network-Genetic Algorithm) scheme is used to obtain the optimal twisted parameter. Subsequently, the efficacy of the proposed methods was verified utilizing MATLAB/Simulink simulations, with further validation conducted through hardware-in-the-loop (HIL) experiments performed on Speedgoat performance real-time target machines. Simulation and experimental results demonstrate that within a specific range, decreasing the inductance parameter can significantly improve the quality of the current. Furthermore, the proposed method outperforms the traditional delay compensation method by reducing computational complexity, minimizing prediction error, and decreasing the number of switching transitions.

Design of adaptive barrier function-based backstepping finite time guidance control for interceptor-target systems

This study introduces an optimal finite-time backstepping sliding mode guidance law, leveraging an adaptive continuous barrier function to examine the interceptor-target system’s motion in cylindrical coordinates. The integration of sliding mode and backstepping controllers enhances the robustness and performance of the proposed guidance method amidst external disturbances and model uncertainties. This combination also improves transient response, reduces chattering, and lowers control efforts. The adaptive continuous barrier function employed in this method eliminates the need for prior knowledge of the upper bounds of uncertainties and disturbances. Additionally, it ensures that adaptation gains are not overestimated, leading to more accurate performance and complete elimination of chattering. The Lyapunov stability theory is used to prove the finite-time convergence of the state trajectories of the interceptor-target system to a predefined neighborhood around the origin, despite external disturbances and uncertainties. A genetic optimization algorithm is utilized to optimally select the parameters of the guidance method. The efficacy of the proposed technique is validated through simulation results and real-time experiments on the Baseline Speedgoat Real-Time Target Machine platform. The method’s effectiveness and performance are further demonstrated through analysis and simulation in the MATLAB/Simulink environment.

Targeting Machine Learning and Artificial Intelligence Algorithms in Health Care to Reduce Bias and Improve Population Health.

Policy Points Artificial intelligence (AI) is disruptively innovating health care and surpassing our ability to define its boundaries and roles in health care and regulate its application in legal and ethical ways. Significant progress has been made in governance in the United States and the European Union. It is incumbent on developers, end users, the public, providers, health care systems, and policymakers to collaboratively ensure that we adopt a national AI health strategy that realizes the Quintuple Aim; minimizes race-based medicine; prioritizes transparency, equity, and algorithmic vigilance; and integrates the patient and community voices throughout all aspects of AI development and deployment.

Robot material processing and hardware-in-the-loop-based real-time simulations

Abstract This paper presents a cyber-physical production system that consists of a simulation, an industrial robot cell, and sensors. The industrial robot hardware, used for welding and additive manufacturing applications, is connected or “in-the-loop” with a real-time target machine on which simulations are running. These simulations are updated in real-time by the data provided by process sensors. Particular focus is given to wire-arc additive manufacturing (WAAM). Still, the cyber-physical system allows use in other robot-based material processes, such as sheet forming, (dis)assembly and material handling applications. It is also argued that the proposed cyber-physical system can be used so that it competes against the concept of using machine learning to optimize manufacturing processes. The proposed cyber-physical system enables the transition from traditional robot automation to autonomous robot systems.

Research on an Active Adjustment Mechanism Based on Non-Singular Terminal Sliding Mode and Finite-Time Disturbance Observer

With the continuous development of synchrotron radiation light sources, higher requirements have been put forward for the stability of double-crystal monochromators in synchrotron radiation facilities. This paper designs an active adjustment mechanism for a double-crystal monochromator to improve its stability. Firstly, three spatial degrees of freedom are designed based on the active adjustment mechanism of flexible leaf spring parallel coupling, and the prototype of the mechanism is fabricated. Secondly, system identification experiments are carried out and the system transfer function curve is fitted by the nonlinear least squares method. Thirdly, the controller based on non-singular terminal sliding modes and a finite-time disturbance observer was designed for stability control and disturbance compensation. Finally, the effectiveness of the controller is verified by a model-in-the-loop approach based on the performance of the real-time target machine. The results show that the non-singular terminal sliding mode + finite-time disturbance observer control strategy can reduce the RMS value of the vibration displacement of Axis-1/Axis-2/Axis-3 by 81.25%, 78.53%, and 71.82%.

Kernel rootkit prevention model using multiclass

Malicious individuals can access a computer network or application thanks to a series of programmes known as rootkit malware. These kernel rootkits use covert methods to conceal the kernel components, various control frameworks, and system activities, making identifying or prohibiting their presence in the target machine challenging. The bulk of rootkit detection and prevention techniques used today are particular to a system and dependent on recognized sources, making them ineffective for growing, evolving, concealed, or unnamed rootkits. This study proposes using the kernel rootkit prevention model using multiclass (KRPMM) system to identify hash values and detect/prevent such rootkits. The file downloaded by the client, who is availing of the service, is not permitted into the node used by the client in the cloud. But, it is redirected to the node wherein the file that has been downloaded and has entered the node anew is examined by a program which is specially coded to test the presence of rootkit in the file by some mechanisms and then comes to a conclusion of either the file being malicious or the file being clean and is free of rootkits. KRPMM tested only 64 rootkits.

The effect of Inc parameter on VMAT radiotherapy plans quality for rectal cancer using Monaco TPS.

To investigate the effect of the Increment of gantry angle (Inc) parameter setting of the Monaco Treatment planning system (Monaco TPS) on the dosimetry and quality parameters of the volumetric modulated arc therapy (VMAT) program for rectal cancer. A retrospective analysis was conducted on 50 patients with rectal cancer who underwent intensity modulated radiation therapy using the Monaco TPS system from 2020 to 2021. Under the same optimization function configuration and other parameter settings, the Inc parameters in the VMAT radiotherapy plan were set to 10°, 20°, 30°, and 40°. The dose-volume histogram (DVH) was used to evaluate the dose distribution of the target area and the radiation dose of the organs at risk (OAR). The differences in the dosimetry of the planning target volume (PTV) and OAR, as well as the gamma pass rate (GPR) were compared. In terms of target dose, D98, Dmin, HI, and conformity index (CI) of Inc10 group was significantly lower than those of Inc20, 30, and 40 groups (P<0.05), and D2 of Inc10 group was significantly higher than that of Inc20 group (P=0.009). We also found CI of Inc20 and 30 were significantly better than that of Inc40 (both P<0.05). In terms of OAR dose, the study found that the Dmean, Dmin, V50%, V45%, and V40% for the bladder of the Inc10 group were lower than those of the other groups (all P<0.05), the Dmean for femoral head of the Inc20 group was lower than that of the Inc30 group (P<0.05), and Inc20 showed a better protective effect on the femoral head. The MUs tend to decrease as the Inc parameter setting is increased. The monitor unit (MU) in Inc10 group were significantly higher than those in Inc20, Inc30, and Inc40 groups, and the MU of Inc20 group was significantly higher than that of Inc40 group (both P<0.05). We found that for the 3%/3mm and 2%/2mm standards, the GPRs of each plan were>90%, which met clinical requirements. Different settings of Inc parameters have varying degrees of impact on target dose, OAR dose, and machine MU. It is important for doctors to choose different Inc parameters according to different clinical needs.

SpChar: Characterizing the sparse puzzle via decision trees

Sparse matrix computation is crucial in various modern applications, including large-scale graph analytics, deep learning, and recommender systems. The performance of sparse kernels varies greatly depending on the structure of the input matrix, making it difficult to gain a comprehensive understanding of sparse computation and its relationship to inputs, algorithms, and target machine architecture. Despite extensive research on certain sparse kernels, such as Sparse Matrix-Vector Multiplication (SpMV), the overall family of sparse algorithms has yet to be investigated as a whole. This paper introduces SpChar, a workload characterization methodology for general sparse computation. SpChar employs tree-based models to identify the most relevant hardware and input characteristics, starting from hardware and input-related metrics gathered from Performance Monitoring Counters (PMCs) and matrices. Our analysis enables the creation of a characterization loop that facilitates the optimization of sparse computation by mapping the impact of architectural features to inputs and algorithmic choices. We apply SpChar to more than 600 matrices from the SuiteSparse Matrix collection and three state-of-the-art Arm Central Processing Units (CPUs) to determine the critical hardware and software characteristics that affect sparse computation. In our analysis, we determine that the biggest limiting factors for high-performance sparse computation are (1) the latency of the memory system, (2) the pipeline flush overhead resulting from branch misprediction, and (3) the poor reuse of cached elements. Additionally, we propose software and hardware optimizations that designers can implement to create a platform suitable for sparse computation. We then investigate these optimizations using the gem5 simulator to achieve a significant speedup of up to 2.63× compared to a CPU where the optimizations are not applied.

Analysis of neural network detectors for network attacks

While network attacks play a critical role in many advanced persistent threat (APT) campaigns, an arms race exists between the network defenders and the adversary: to make APT campaigns stealthy, the adversary is strongly motivated to evade the detection system. However, new studies have shown that neural network is likely a game-changer in the arms race: neural network could be applied to achieve accurate, signature-free, and low-false-alarm-rate detection. In this work, we investigate whether the adversary could fight back during the next phase of the arms race. In particular, noticing that none of the existing adversarial example generation methods could generate malicious packets (and sessions) that can simultaneously compromise the target machine and evade the neural network detection model, we propose a novel attack method to achieve this goal. We have designed and implemented the new attack. We have also used Address Resolution Protocol (ARP) Poisoning and Domain Name System (DNS) Cache Poisoning as the case study to demonstrate the effectiveness of the proposed attack.

Localization of Coordinated Cyber-Physical Attacks in Power Grids Using Moving Target Defense and Machine Learning

Coordinated cyber-physical attacks (CCPAs) are dangerously stealthy and have considerable destructive effects against power grids. The problem of stealthy CCPA (SCCPA) localization, specifically identifying disconnected lines in attack, is a nonlinear multi-classification problem. To the best of our knowledge, only one paper has studied the problem; nevertheless, the total number of classifications is not appropriate. In the paper, we propose several methods to solve the problem of SCCPA localization. Firstly, considering the practical constraints and abiding by one of our previous studies, we elaborately determine the total number of classifications and design an approach for generating training and testing datasets. Secondly, we develop two algorithms to solve multiple classifications via the support vector machine (SVM) and random forest (RF), respectively. Similarly, we also present a one-dimensional convolutional neural network (1D-CNN) architecture. Finally, extensive simulations are carried out for IEEE 14-bus, 30-bus, and 118-bus power system, respectively, and we verify the effectiveness of our approaches in solving the problem of SCCPA localization.

Kernel rootkit detection multi class on deep learning techniques

The harmful code application known as a rootkit is designed to be loaded and run directly from the operating system's (OSs') Kernel. Rootkits deployed in the Kernel, called Kernel-mode rootkits, can alter the OS. The intention behind these Kernel changes is to conceal the hack. Detecting a Kernel rootkit in a target machine is found to be quite challenging. Numerous techniques can be employed to modify the Kernel of a system. Kernel rootkits also create hidden access for attacks, enabling unauthorized entry to be gained by attackers on the machine. The ultimate consequence is that essential computer data can be modified, personal information can be gathered, and hackers can observe behavior. Synthetic neural networks support artificial intelligence, a branch of deep learning that models the human brain and operates on large datasets. This study proposed the Kernel rootkit detection multi-class deep learning techniques (KRDMCDLT). Deep learning algorithms are utilized to recognize the Kernel rootkit from a batch of data by selecting essential properties for learning tracking models. Thus, by identifying the OS malware, trojan assaults can be stopped before they can access infected data. This Kernel rootkit detection was tested in a Google Cloud Platform (GCP) computing system.

An Efficient Model to Detect and Prevent SQL Injection Attack

SQL injection attack (SQLIA) is considered one of most threats used to attack web applications. Therefore, attackers used SQL injection vulnerability to gain ultimate access to databases that belong to applications and expose their sensitive information. Thus, attackers use SQL injections vulnerability to manipulate data also it could be used to take full control of the target machine. Accordingly, several methods were proposed in the literature to address this vulnerability widely because of its importance and high impact on the security of web applications.Thus, we propose a model to detect and prevent SQL injection attack, which uses runtime validation to detect the occurrence of such attacks, our proposed model is adaptable to any existing system, with no need to modify the client or server and either no need to know web application source code. Furthermore, the modification independence is done by adding additional middleware between client and server. Thus, any check process is done on this middleware, and it is represented as a proxy that can do sanitize the inputs for detecting and preventing SQLIA.Furthermore, our proposed model accuracy reaches 86.6% for detecting and preventing SQLIA.

Adaptive prescribed performance based on recursive nonsingular terminal sliding mode control for quad-rotor systems under uncertainty and disturbance: Real-time validation

In this paper, at the aim of the fast trajectory-following control of the Unmanned Aerial Vehicle (UAV) systems subject to uncertainty and disturbance, the adaptive prescribed performance control based recursive nonsingular terminal sliding mode control is suggested. Afterward, for the fast trajectory-following control of the uncertain and perturbed quad-rotor system, a recursive nonsingular terminal sliding mode strategy is recommended. Since the better transient and steady-state response of the sliding mode surface is of the utmost importance in the design of the controller, the prescribed performance control scheme is proposed in which the transformed prescribed form of the previously proposed recursive nonsingular terminal sliding surface is obtained to prove that the recursive nonsingular terminal sliding surface can converge to a preset region. Whereas unknown bounded uncertainty and disturbance always exist in the UAV system's dynamical model which decreases its performance and efficiency, the adaptive mechanism is applied to approximate uncertain bounds of uncertainty and disturbance to advance the implementation of the UAV system. Later, quick reachability of the prescribed form switching surface is demonstrated using Lyapunov concept. Ultimately, simulation results using MATLAB/Simulink over a quad-rotor system and real-time simulation using the Speedgoat Real-Time Target Machine platform are conducted to validate the feasibility and performance of the proposed method.

A Rapid Control Prototyping and Hardware-in-the Loop Approach for Upper Limb Robotic Exoskeletons Control

In the last decade, robotic-mediated rehabilitation has emerged as a potential solution to improve repetitive task training. Each device in this field has a unique development history shaped by engineers’ expertise in specific programming languages or platforms. In this work we adopt an approach that tries to abstract from the final implementation with the aim to make control logic more shareable and understandable. The authors will present the outcomes of the application of a Rapid Control Prototyping strategy to an upper-limb robotic exoskeleton. A model-based design approach implemented on a real-time target machine is presented. This modern design approach was explored with several control strategies and was used to test the exoskeleton’s performances. The proposed method highlights how it is possible to develop the entire control architecture in a single programming environment.

Predictive Path-Tracking Control of an Autonomous Electric Vehicle with Various Multi-Actuation Topologies.

This paper presents the development of path-tracking control strategies for an over-actuated autonomous electric vehicle. The vehicle platform is equipped with four-wheel steering (4WS) as well as torque vectoring (TV) capabilities, which enable the control of vehicle dynamics to be enhanced. A nonlinear model predictive controller is proposed taking into account the nonlinearities in vehicle dynamics at the limits of handling as well as the crucial actuator constraints. Controllers with different actuation formulations are presented and compared to study the path-tracking performance of the vehicle with different levels of actuation. The controllers are implemented in a high-fidelity simulation environment considering scenarios of vehicle handling limits. According to the simulation results, the vehicle achieves the best overall path-tracking performance with combined 4WS and TV, which illustrates that the over-actuation topology can enhance the path-tracking performance during conditions under the limits of handling. In addition, the performance of the over-actuation controller is further assessed with different sampling times as well as prediction horizons in order to investigate the effect of such parameters on the control performance, and its capability for real-time execution. In the end, the over-actuation control strategy is implemented on a target machine for real-time validation. The control formulation proposed in this paper is proven to be compatible with different levels of actuation, and it is also demonstrated in this work that it is possible to include the particular over-actuation formulation and specific nonlinear vehicle dynamics in real-time operation, with the sampling time and prediction time providing a compromise between path-tracking performance and computational time.

On sampling determinantal and Pfaffian point processes on a quantum computer

DPPs were introduced by Macchi as a model in quantum optics the 1970s. Since then, they have been widely used as models and subsampling tools in statistics and computer science. Most applications require sampling from a DPP, and given their quantum origin, it is natural to wonder whether sampling a DPP on a quantum computer is easier than on a classical one. We focus here on DPPs over a finite state space, which are distributions over the subsets of {1,…,N} parametrized by an N × N Hermitian kernel matrix. Vanilla sampling consists in two steps, of respective costs O(N3) and O(Nr2) operations on a classical computer, where r is the rank of the kernel matrix. A large first part of the current paper consists in explaining why the state-of-the-art in quantum simulation of fermionic systems already yields quantum DPP sampling algorithms. We then modify existing quantum circuits, and discuss their insertion in a full DPP sampling pipeline that starts from practical kernel specifications. The bottom line is that, with P (classical) parallel processors, we can divide the preprocessing cost by P and build a quantum circuit with O(Nr) gates that sample a given DPP, with depth varying from O(N) to O(rlogN) depending on qubit-communication constraints on the target machine. We also connect existing work on the simulation of superconductors to Pfaffian point processes (PfPP), which generalize DPPs and would be a natural addition to the machine learner’s toolbox. In particular, we describe ‘projective’ PfPPs, the cardinality of which has constant parity, almost surely. Finally, the circuits are empirically validated on a classical simulator and on 5-qubit IBM machines.