Complex Engineering Systems

This paper presents a framework for generating high-definition (HD) map, and then achieves accurate and robust localization by virtue of the map. An iterative approximation based method is developed to generate a HD map in Lanelet2 format. A feature association method based on structural consistency and feature similarity is proposed to match the elements of the HD map and the actual detected elements. The feature association results from the HD map are used to correct lateral drift in the light detection and ranging odometry. Finally, some experimental results are presented to verify the reliability and accuracy of autonomous driving localization.

Electro-hydraulic power steering (EHPS) systems are widely used in commercial vehicles due to their adjustable power assist and energy-saving advantages. In this paper, a dynamic model of the EHPS system is developed, and quantitative expressions for three evaluation indexes, steering road feel, steering sensibility and steering energy loss, are derived for the first time. A multi-objective collaborative optimization model of the EHPS system is then established, which consists of one total system and three parallel subsystems, based on collaborative optimization theory. Considering the coupled variables of each subsystem, the total system is optimized by a multi-objective algorithm, while the subsystems are optimized by a single-objective algorithm. The optimization results demonstrate that the average frequency domain energy of the steering road feel is increased by 69.1%, the average frequency domain energy of steering sensitivity is reduced by 19.2%, and steering energy consumption is reduced by 10.8% compared to the initial value. The non-dominated sorting genetic algorithm-II (NSGA-II) shows superior comprehensive performance compared to the other two multi-objective algorithms, and the optimization performance can be further improved by setting appropriate algorithm parameters.

This paper presents the use of two popular explainability tools called Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) to explain the predictions made by a trained deep neural network. The deep neural network used in this work is trained on the UCI Breast Cancer Wisconsin dataset. The neural network is used to classify the masses found in patients as benign or malignant based on 30 features that describe the mass. LIME and SHAP are then used to explain the individual predictions made by the trained neural network model. The explanations provide further insights into the relationship between the input features and the predictions. SHAP methodology additionally provides a more holistic view of the effect of the inputs on the output predictions. The results also present the commonalities between the insights gained using LIME and SHAP. Although this paper focuses on the use of deep neural networks trained on UCI Breast Cancer Wisconsin dataset, the methodology can be applied to other neural networks and architectures trained on other applications. The deep neural network trained in this work provides a high level of accuracy. Analyzing the model using LIME and SHAP adds the much desired benefit of providing explanations for the recommendations made by the trained model.

In this paper, we examine the stability of highly nonlinear switched stochastic systems (SSSs) with time-varying delays, where the switching time instants are deterministic rather than stochastic. Herein, the boundedness of the global solution is first proven for highly nonlinear SSSs via the average dwell time (ADT) method and multiple Lyapunov function (MLF) approach. Then, the stability criteria for qth moment exponential stability and almost surely exponential stability are presented. The main difficulty lies in the presence of switching and time-varying delay terms, which prevents the validation of existing methods. New inequality techniques have been developed to counteract the effects of switching signals and time-varying delays. Finally, an example is provided to verify the effectiveness of the results.

The search for pulsars is an important area of study in modern astronomy. The amount of collected pulsar data is increasing exponentially as the performance of modern radio telescopes improves, necessitating the improvement of the original pulsar search methods. Artificial intelligence techniques are currently being used in pulsar candidate identification tasks. However, improving the accuracy of pulsar candidate identification using artificial intelligence techniques remains a challenge. Because the amount of collected data is so large, the number of real pulsar samples is very limited, which leads to a serious sample imbalance problem. Many existing methods ignore this issue, making it difficult for the model to reach the optimal solution. A framework combining generative adversarial networks and residual networks is proposed to greatly alleviate the problem of sample inequality. The framework first generates stable pulsar images using generative adversarial networks and then designs a deep neural network model based on residual networks to identify pulsar candidates using intra-block and inter-block residual connectivity. The ResNet approach has a better ability to fit the data than the CNN approach and can achieve the extraction of features with more classification ability with a smaller dataset. Meanwhile, the data expanded by the high-quality simulated samples generated by the generative adversarial network can provide richer identification features and improve the identification accuracy for pulsar candidates.

This paper presents a power dispatch strategy combining the main grid and distributed generators based on aggregative game theory and the Cournot price mechanism. Such a dispatch strategy aims to increase the electricity under the power shortage situation. Under the proposed strategy, this paper designs a discrete-time algorithm fusing the estimation technique and the Digging method to solve the power shortage problem in a distributed way. The distributed algorithm can provide privacy protection and information safety and improve the power grid's extendibility. Moreover, the simulation results show that the proposed algorithm has favorable performance and effectiveness in the numerical example.

Hybrid impedance/admittance control aims to provide an adaptive behavior to the manipulator in order to interact with the surrounding environment. In fact, impedance control is suitable for stiff environments, while admittance control is suitable for soft environments/free motion. Hybrid impedance/admittance control, indeed, allows modulating the control actions to exploit the combination of such behaviors. While some work has addressed the proposed topic, there are still some open issues to be solved. In particular, the proposed contribution aims: (i) to satisfy the continuity of the interaction force in the switching from impedance to admittance control when a feedforward velocity term is present; and (ii) to adapt the switching parameters to improve the performance of the hybrid control framework to better exploit the properties of both impedance and admittance controllers. The proposed approach was compared in simulation with the standard hybrid impedance/admittance control in order to show the improved performance. A Franka EMIKA panda robot was used as a reference robotic platform to provide a realistic simulation.

Wheeled robots enjoy popularity in extensive areas such as food delivery and room disinfection. They can lower labor costs, protect human health from infection, and so on. Given the need to avoid obstacles, the path planning of robots is an elementary module. The A* algorithm has been widely used thus far, but it suffers much memory overhead and provides a suboptimal path. Therefore, we propose an improved A* algorithm with the jump point search method and pruning idea. Specifically, the jump point search method reduces the occupancy rate of the open list. The shorter length of the path can be achieved by pruning. Simulation experiments proved that the improvement was effective and practical.

The estimation of the parameters of a system by a set membership approach consists in characterizing the set of parameters completely compatible with all the measurements made on the system, the model of this system and the characteristics of the errors and uncertainties that affect the measurements and the system. In this context, it is assumed that the error affecting the measurements is bounded and belongs to a set that is realizable a priori. The estimation problem to be solved then consists in finding the set of admissible values of the model parameters in adequacy with the measurements, the errors and the uncertainties. These uncertainties are handled by an approach that takes into account the unknowns that are the structural error of the model and the values of these parameters. From a practical point of view, the result obtained is a domain of parameters varying in time, domain which is characterized by its bounds. The volume of this domain is minimized, the proposed model explaining the measurements made at each time by optimizing a criterion of precision of the volume in consideration.

The increase of train speed leads to a violent vibration of the pantograph and overhead system. To evaluate the interaction performance of the pantograph and overhead system, a whole railway dynamics model including the track, vehicle, pantograph, and overhead system is established. The overhead system is represented by the finite element approach using the analytical formulas of nonlinear cable and truss elements. The vehicle is modeled by a multi-rigid-body system with a pantograph installed on its roof. A beam element with elastic foundations is used to model the track, which possesses harmonic and random irregularities. An iterative algorithm is implemented to solve the nonlinear behavior of the coupling model. The nonlinearities in the deformation of overhead system, the contact of the pantograph and contact line, and the contact of the vehicle-track are properly considered. Several numerical simulations are implemented to systematically investigate the influence of the vehicle-track vibration on the dynamic behavior of pantograph and overhead system. The results indicate that the vehicle-track vibration induced by the rail irregularities with large amplitude or certain wavelength can significantly aggravate the interaction performance of pantograph and overhead system.

We propose an algorithm for n-dimensional regression problems with continuous variables. Its main property is explainability, which we identify as the ability to understand the algorithm’s decisions from a human perspective. This has been achieved thanks to the simplicity of the architecture, the lack of hidden layers (as opposed to deep neural networks used for this same task) and the linguistic nature of its fuzzy inference system. First, the algorithm divides the joint input-output space into clusters that are subsequently approximated using linear functions. Then, we fit a Cauchy membership function to each cluster, therefore identifying them as fuzzy sets. The prediction of each linear regression is merged using a Takagi-Sugeno-Kang approach to generate the prediction of the model. Finally, the parameters of the algorithm (those from the linear functions and Cauchy membership functions) are fine-tuned using Gradient Descent optimization. In order to validate this algorithm, we considered three different scenarios: The first two are simple one-input and two-input problems with artificial data, which allow visual inspection of the results. In the third scenario we use real data for the prediction of the power generated by a Combined Cycle Power Plant. The results obtained in this last problem (3.513 RMSE and 2.649 MAE) outperform the state of the art (3.787 RMSE and 2.818 MAE).

In this work, we propose connected energy management systems for a cooperative hybrid electric vehicle (HEV) platoon. To this end, cooperative driving scenarios are established under different car-following behavior models using connected and automated vehicles technology, leading to a cooperative cruise control system (CACC) that explores the energy-saving potentials of HEVs. As a real-time energy management control, an equivalent consumption minimization strategy (ECMS) is utilized, wherein global energy-saving is achieved to promote environment-friendly mobility. The HEVs cooperatively communicate and exchange state information and control decisions with each other by sixth-generation vehicle-to-everything (6G-V2X) communications. In this study, three different car-following behavior models are used: intelligent driver model (IDM), Gazis–Herman–Rothery (GHR) model, and optimal velocity model (OVM). Adopting cooperative driving of six Toyota Prius HEV platoon scenarios, simulations under New European Driving Cycle (NEDC), Worldwide Harmonized Light Vehicle Test Procedure (WLTP), and Highway Fuel Economy Test (HWFET), as well as human-in-the-loop (HIL) experiments, are carried out via MATLAB/Simulink/dSPACE for cooperative HEV platooning control via different car-following-linked-vehicle scenarios. The CACC-ECMS scheme is assessed for HEV energy management via 6G-V2X broadcasting, and it is found that the proposed strategy exhibits improvements in vehicular driving performance. The IDM-based CACC-ECMS is an energy-efficient strategy for the platoon that saves: (i) 8.29% fuel compared to the GHR-based CACC-ECMS and 10.47% fuel compared to the OVM-based CACC-ECMS under NEDC; (ii) 7.47% fuel compared to the GHR-based CACC-ECMS and 11% fuel compared to the OVM-based CACC-ECMS under WLTP; (iii) 3.62% fuel compared to the GHR-based CACC-ECMS and 4.22% fuel compared to the OVM-based CACC-ECMS under HWFET; and (iv) 11.05% fuel compared to the GHR-based CACC-ECMS and 18.26% fuel compared to the OVM-based CACC-ECMS under HIL.

This paper is concerned with the sampled-data bipartite tracking consensus problem for a class of nonlinear multiagent systems (MASs) with input saturation. Both competitive and cooperative interactions coexist among agents in the concerned network. By resorting to Lyapunov stable theory and linear matrix inequality (LMI) technique, several criteria are obtained to ensure that the considered MASs can achieve the bipartite tracking consensus. Besides, with the help of the decoupled method, the dimensions of LMIs are reduced for mitigation of the computation complexity so that the obtained results can be applied to large-scaled MASs. Furthermore, the controller gain matrix is explicitly expressed in terms of solutions to a set of LMIs. We also provide with an estimate of elliptical attraction domain of bipartite tracking consensus. Finally, numerical simulation is exploited to support our theoretical analysis.

In this paper, the nonlinear model of polymer exchange membrane (PEM) fuel cell system is first extracted and then tested and evaluated for various temperatures and pressures. With the severe nonlinear characteristics of the PEM fuel cell system, using the proportional-integral-derivative (PID) controller for the linear model of the PEM fuel cell system could not guarantee robust control under parametric uncertainty and severe load fluctuations. The use of a linear model-based controller increases the pressure in both the anode and cathode areas, which in turn induces a high pressure difference across the polymer membrane, thus reducing the lifespan of the fuel cell. The proposed method uses the particle swarm optimization (PSO) algorithm, taking into account practical parameters, to design a PID controller for a nonlinear model of the fuel cell. Comparison of the results obtained from the conventional PID controller and the proposed PID-PSO structure shows that PID-PSO can desirably guarantee the specifications of overshoot, transient time, and settling time for a defined pressure difference across the anode and cathode plates.

Proportional-Integral-Derivative (PID) control has been the dominant control strategy in the process industry due to its simplicity in design and effectiveness in controlling a wide range of processes. However, most traditional PID tuning methods rely on trial and error for complex processes where insights about the system are limited and may not yield the optimal PID parameters. To address the issue, this work proposes an automatic PID tuning framework based on reinforcement learning (RL), particularly the deterministic policy gradient (DPG) method. Different from existing studies on using RL for PID tuning, in this work, we explicitly consider the closed-loop stability throughout the RL-based tuning process. In particular, we propose a novel episodic tuning framework that allows for an episodic closed-loop operation under selected PID parameters where the actor and critic networks are updated once at the end of each episode. To ensure the closed-loop stability during the tuning, we initialize the training with a conservative but stable baseline PID controller and the resultant reward is used as a benchmark score. A supervisor mechanism is used to monitor the running reward (e.g., tracking error) at each step in the episode. As soon as the running reward exceeds the benchmark score, the underlying controller is replaced by the baseline controller as an early correction to prevent instability. Moreover, we use layer normalization to standardize the input to each layer in actor and critic networks to overcome the issue of policy saturation at action bounds, to ensure the convergence to the optimum. The developed methods are validated through setpoint tracking experiments on a second-order plus dead-time system. Simulation results show that with our scheme, the closed-loop stability can be maintained throughout RL explorations and the explored PID parameters by the RL agent converge quickly to the optimum. Moreover, through simulation verification, the developed RL-based PID tuning method can adapt the PID parameters to changes in the process model automatically without requiring any knowledge about the underlying operating condition, in contrast to other adaptive methods such as the gain scheduling control.

This paper presents the development and testing of a remotely operated vehicle (ROV). The outstanding ability of this ROV lies in its underwater hovering positioning control. At the same time, it is equipped with a seven-function underwater electric operation manipulator and the master-slave control mode is adopted. These are obvious advantages over other medium-sized ROVs. The control hardware architecture and control software architecture of this ROV are also provided. Finally, the test results of the depth trajectory tracking control, heading trajectory tracking control and hover control in the lake environment are presented and analyzed.

The state estimation problem is investigated for a class of continuous-time stochastic nonlinear systems, where a novel filter design method is proposed based on backstepping design and stochastic differential equation. In particular, the structure of the filter is developed following the nonlinear system model, and then the estimation error dynamics can be described by a stochastic differential equation. Motivated by backstepping procedure, the nonlinear dynamics can be converted to an Ornstein–Uhlenbeck process via the control loop design. Thus, the estimation can be achieved once the estimation error is bounded and the variance of the error can be optimized. Since the ideal estimation error is a Brownian motion, the filter parameters can be selected following the Lyapunov stability theory and variance assignment method. Following the same framework, the multivariate stochastic systems can be handled with the block backstepping design. To validate the presented design approach, a numerical example is given as the simulation results to demonstrate the state estimation performance.

Offshore crane operations are frequently carried out under adverse weather conditions. While offshore cranes attempt to finish the load-landing or lifting operation, the impact between the loads and the vessels is critical, as it can cause serious injuries and extensive damage. Multiple offshore crane operations, including load-landing operations, have used reinforcement learning (RL) to control their activities. In this paper, the Q-learning algorithm is used to develop optimal control sequences for the offshore crane’s actuators to minimize the impact velocity between the crane’s load and the moving vessel. To expand the RL environment, a mathematical model is constructed for the dynamical analysis utilizing the Denavit–Hartenberg (DH) technique and the Lagrange approach. The Double Q-learning algorithm is used to locate the bias that is common in Q-learning algorithms. The average return feature is studied to assess the performance of the Q-learning algorithm. Furthermore, the trained control sequence was tested on a separate sample of episodes, and the hypothesis that, unlike supervised learning, reinforcement learning cannot have a global optimal control sequence but only a local one, was confirmed in this application domain.

In this paper, we propose a feedforward air conditioning temperature control method for high-speed railway locomotives with sleeper compartments to improve energy efficiency. First, we construct the geometric model of two typical types of compartments and three types of passengers. Then, based on the analysis of possible passenger layout patterns in each compartment, we utilize computational fluid dynamics simulations to calculate the optimal air volume for each pattern. The optimal air volume is calculated to guarantee the passenger comfort level and reduce the energy cost. In addition, we adopt an image recognition method to detect the number and types of passengers in each compartment. Passenger layout patterns serve as independent variables to determine the corresponding optimal air volume. Finally, numerical simulations were conducted to verify the effectiveness of the proposed method.

This paper investigates a fuzzy reduced-order filter design for a class of nonlinear partial differential equation (PDE) systems. First, a Takagi-Sugeno (T-S) fuzzy model is considered to reconstruct the nonlinear PDE system. Then, the employment of an event-triggered mechanism (ETM) can effectively avoid signal redundancy and improve network resource utilization. Furthermore, based on the advantages of the fuzzy model and ETM, several Lyapunov functions are designed and the proposed filter parameters are obtained by adopting linear matrix inequality methods to satisfy the asymptotic stability condition with H∞ performance. Finally, a simulation example is presented to demonstrate the practicality and effectiveness of the proposed filter design method.

This paper proposes the topics of sliding mode control for nonlinear Takagi-Sugeno systems based on a state observer with application to single-link flexible joint robotic. Firstly, a state observer relying on estimated premise variables is constructed, based on which we define an integral-type switching surface function on the estimation space. Secondly, by the equivalent control method, a sliding mode dynamics with an error system is obtained. Then, an adaptive variable structure controller is constructed to make sure that the predefined switching surface will be arrived in finite-time. Furthermore, stability analysis with an H∞ performance is analyzed for the whole closed-loop system by linear matrix inequality condition. Finally, simulation study based on the robotics is conducted to confirm the validity of the proposed observer-based fuzzy controller.

As one of the critical components of rotating machinery, fault diagnosis of rolling bearings has great significance. Although deep learning is useful in diagnosing rolling bearing faults, it is difficult to diagnose the faults of bearings under multiple operating conditions. To overcome the above-mentioned problem, this paper designs a modular federated learning network for fault diagnosis in multiple working conditions by using dynamic routing technology as the federation strategy for federated learning of the multiple modular neural network. First, according to different working conditions, the collected multi-working condition data are divided into different groups for feeding of modular network to extract the local features under different working conditions. Then, an additional deep neural network is constructed to extract the feature involved in data without working condition division. Finally, the global adaptive feature extraction of each working condition can be obtained by designing a federated strategy based on dynamic routing technology to achieve the weights allocation scheme of the modular neural network. The bearing dataset of Case Western Reserve University is taken as a benchmark dataset to verify the effectiveness of the proposed method.

The ocean is a complex system. Ocean temperature is an important physical property of seawater, so studying its variation is of great significance. Two kinds of network structures for predicting thermocline time series data are proposed in this paper. One is the LSTM-GRU hybrid neural network model, and the other is the temporal convolutional network (TCN) model. The two networks have obvious advantages over other models in accuracy, stability, and adaptability. Compared with the traditional auto-regressive integrate moving average model, the proposed method considers the influence of temperature history, salinity, depth, and other information. The experimental results show that TCN performs better in prediction accuracy, while LSTM-GRU can better predict abnormal data and has higher robustness.

This paper presents a Model Predictive Control (MPC) algorithm for Nonlinear systems represented through quasi-Linear Parameter Varying (qLPV) embeddings. Input-to-state stability is ensured through parameter-dependent terminal ingredients, computed offline via Linear Matrix Inequalities. The online operation comprises three consecutive Quadratic Programs (QPs) and, thus, is computationally efficient and able to run in real-time for a variety of applications. These QPs stand for the control optimization (MPC) and a Moving-Horizon Estimation (MHE) scheme that predicts the behaviour of the scheduling parameters along the future horizon. The method is practical and simple to implement. Its effectiveness is assessed through a benchmark example (a CSTR system).

The correlation relations of batch process variables are quite complex. For local abnormalities, there is a problem that the variant features are overwhelmed. In addition, batch process variables have obvious non-Gaussian distributions. In response to the above two problems, a new multiple subspace monitoring method called principal component analysis - multiple subspace support vector data description (PCA-MSSVDD) is proposed, which combines the subspace design of latent variables with the SVDD modeling method. Firstly, PCA is introduced to obtain latent variables for removing redundant information. Secondly, the subspace design result is obtained through K-means clustering. Finally, SVDD is introduced to build the monitoring model. Numerical simulation and penicillin fermentation process prove that the proposed PCA-MSSVDD method has better monitoring performance than traditional methods.

Digitization and digitalization have already changed our world significantly. Further disruptions are imminent with the ongoing digital transformation, a major component of which is digital twins. As the big data techniques, Internet of Things, cloud computing, and artificial intelligence algorithms advance, the digital twin technology has entered a phase of rapid development. It has been stated to be one of the top ten most promising technologies. Although it is still in its early stages, digital twins are already being widely used in a variety of fields, especially in industry, smart cities, and smart health, which are points that attract most researchers to study. In the literature, there can be seen numerous articles and reviews on digital twins, published every year in these three fields. It is therefore timely, even necessary, to provide an analysis of the published work. This is the motivation behind this article, the focus of which is the major research and application areas of digital twins. The survey first analyzes the recent developments of digital twins, then summarizes the theoretical underpinnings of the technology, and finally concludes with specific developments in various application areas of digital twins. It also discusses the challenges that may be encountered in the future.

This paper presents a model predictive control (MPC) method for single-phase three-level grid-connected F-type inverters. The main control objective in grid-connected inverters is to regulate the grid current with low total harmonic distortion. Since the F-type inverter has emerged recently, there is no specific control method developed for this inverter topology in the literature yet. In this paper, the mathematical model of the F-type inverter and the design of model predictive control is presented. Since the dc capacitor voltage balancing is essential for F-type inverters, both current control and dc capacitor voltage controllers are combined in a multi-objective cost function. Thus, the control of the dc and ac sides of the F-type inverter is achieved successfully. The theoretical considerations were verified through simulation studies. The effectiveness of the proposed MPC method was investigated in the steady state as well as dynamic transients under variations in grid current, input dc voltage, and grid voltage. The simulation results show that the grid current and dc capacitor voltages are successfully controlled in all operating conditions.