ISA transactions最新文献

{"title":"Robust contrastive learning based on evidential uncertainty for open-set semi-supervised industrial fault diagnosis","authors":"Shuaijie Chen,&nbsp;Chuang Peng,&nbsp;Lei Chen,&nbsp;Kuangrong Hao","doi":"10.1016/j.isatra.2025.01.041","DOIUrl":"10.1016/j.isatra.2025.01.041","url":null,"abstract":"<div><div>Semi-supervised learning is increasingly applied in industrial fault diagnosis, presuming that the label spaces of labeled samples and unlabeled samples are identical. However, unknown faults in real-world scenarios present a challenge for traditional closed-set approaches. To this end, we propose a novel framework for open-set semi-supervised industrial fault diagnosis, named Evidential Robust Contrastive Learning (ERCL). The theory of evidence is introduced to explicitly assess sample uncertainty, guiding the evidential robust contrastive representation module to implement instance-level training strategies for each unlabeled sample. Additionally, an adaptive out-of-distribution detection module is developed to detect unknown faults by evaluating the difference in mutual information distributions between in-distribution (ID) and out-of-distribution (OOD) samples, thereby avoiding over-reliance on prior knowledge. The proposed framework is validated with the Tennessee Eastman process and polyester esterification process. As proved in the experiments, ERCL exhibits superior diagnosis accuracy in open scenarios with limited labeled data.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"159 ","pages":"Pages 32-43"},"PeriodicalIF":6.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143367081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel nonlinear model predictive control approach to minimize losses in open-channel irrigation systems","authors":"Gregory Conde ,&nbsp;Carlos Ocampo-Martinez ,&nbsp;Nicanor Quijano","doi":"10.1016/j.isatra.2025.02.003","DOIUrl":"10.1016/j.isatra.2025.02.003","url":null,"abstract":"<div><div>Open-channel irrigation systems (OCIS) are widely recognized as the simplest, most widely adopted, and economically advantageous method of water transportation in agriculture. However, these systems often experience substantial water losses due to seepage and leaks, which are closely correlated with the channel levels. The control mechanisms commonly discussed for OCIS primarily emphasize preserving constant channel levels, leading to constant losses. In order to overcome this limitation, the present study offers a paradigm change in control objectives, thereby facilitating the management of channel levels and flow variability. The new objectives seek to address user water demands, mitigate channel water levels, prevent overflow instances, and limit ecological and infrastructural impacts. A request-based operational approach is utilized in implementing a nonlinear model predictive control (NMPC) technique. The NMPC employs a simple modeling framework that can effectively describe the behavior of OCIS in various operational settings. It also integrates a receding-horizon cost function to optimize water allocation and minimize water levels. The provided design of the control strategy includes a set of feasible conditions that ensure the operability and stability of the controlled system. The efficacy of the proposed control technique has been verified by experimentation on a well-established testbed documented in previous academic papers. This validation process has demonstrated a notable 50% decrease in water waste while simultaneously ensuring sufficient water supply to users.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"159 ","pages":"Pages 278-292"},"PeriodicalIF":6.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143477026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trajectory tracking control for ships with fixed-time prescribed performance considering input saturation and dead zone","authors":"Yunsong Lei ,&nbsp;Xianku Zhang ,&nbsp;Shihang Gao ,&nbsp;Qiang Guo","doi":"10.1016/j.isatra.2025.03.014","DOIUrl":"10.1016/j.isatra.2025.03.014","url":null,"abstract":"<div><div>To enable underactuated ships to achieve trajectory tracking under unknown external disturbances, model uncertainties, and actuator saturation and dead zone, a fixed-time prescribed performance trajectory tracking control method is designed. Firstly, the position tracking errors are constrained by designing the barrier Lyapunov function, and the prescribed performance function is set as the constraint boundary to address the issue of fixed constraint boundaries in traditional methods. Secondly, RBF neural networks are employed to estimate the model uncertainties, and adaptive laws are used to estimate the upper bound of the composite disturbances. Finally, the controller is designed by incorporating fixed-time convergence theory and further using fixed-time sliding mode surface in order to overcome the shortcomings of traditional control algorithms in terms of slow response and the use of finite-time convergence with respect to the initial state. Through Lyapunov stability analysis, it is proven that all signals in the closed-loop system are bounded, and the velocity tracking errors can achieve global fixed-time convergence. Simulation results demonstrate that the proposed control scheme enables underactuated ship to achieve trajectory tracking even in the presence of input saturation and dead zone. Statistical results show that the performance indicators of the proposed controller are significantly smaller than those of the first group in the comparative experiments, with a shorter settling time. Moreover, compared to traditional saturation handling methods, the input curves of the proposed controller are smoother and more aligned with practical engineering requirements.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 155-165"},"PeriodicalIF":6.3,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143782366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The suspension load deviation control method for high-power locomotives via Harris Hawk optimization","authors":"Yuqi Xiao ,&nbsp;Yongjun Wu","doi":"10.1016/j.isatra.2025.03.023","DOIUrl":"10.1016/j.isatra.2025.03.023","url":null,"abstract":"<div><div>In this study, the theoretical model for the static secondary spring load adjustment of six-axle railway vehicles is established, which can be applicable to any six-axle railway vehicle, including locomotives, subways, passenger trains and freight trains. Meanwhile, the simplified model of the supporting structure is proposed, which reduces the calculation process greatly by simplifying the 12-points supporting structure of a six-axle railway vehicle into a 4-points supporting structure. Moreover, we present the Harris hawk optimization method in the field of suspension load control of railway vehicles. The load control experiments of a six-axle railway vehicle prove that the performance of this method is significantly improved compared with the classical method in terms of maximum force difference, root mean square error and calculation efficiency. The proposed method reduces the position and amount of padding, further reducing the padding workload and improves the efficiency of the static secondary spring load deviation control.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 289-301"},"PeriodicalIF":6.3,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maximum sensitivity constrained region based tuning of active disturbance rejection control for industrial applications in presence of time-varying disturbances","authors":"Faraz Haider,&nbsp;Ahmad Ali","doi":"10.1016/j.isatra.2025.03.011","DOIUrl":"10.1016/j.isatra.2025.03.011","url":null,"abstract":"<div><div>Linear active disturbance rejection control (ADRC) uses conventional Luenberger type linear extended state observer (LESO) and a simple proportional derivative (PD) controller for anti-disturbance applications. Limitation of the linear ADRC lies in its inability to adequately reject time-varying disturbances. Modified ADRC strategies discussed in this manuscript, including LESO-based proportional integral derivative-ADRC (LESO-PID-ADRC) and proportional resonant-ADRC (LESO-PR-ADRC), exhibit the capability to proficiently track ramp and sinusoidal references while effectively suppressing similar disturbances. Additionally, a quasi-generalized integrator-extended state observer based PID-ADRC (QGI-PID-ADRC) is proposed which is capable of tracking both step and ramp references while simultaneously rejecting ramp and sinusoidal disturbances. Furthermore, maximum sensitivity constrained region (MSCR) based graphical tuning approach is presented for the PID and PR controllers. Frequency domain analysis is conducted to illustrate reference tracking and disturbance rejection capability of the designed controllers. Moreover, stability of the closed loop system is illustrated using Nyquist plots. Simulation study is conducted in MATLAB for two complex systems (ship motion model and pressurized water reactor (PWR)) which have associated nonlinearities, time-varying system parameters and modeling uncertainties. The research demonstrates that LESO-PID-ADRC, QGI-PID-ADRC and LESO-PR-ADRC, when tuned using the proposed graphical approach, outperform recently introduced control strategies, excelling in both reference tracking and disturbance rejection.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 122-135"},"PeriodicalIF":6.3,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143789461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive event-triggered control for uncertain nonlinear systems with multiple intermittent actuator faults of uncertain directions","authors":"Xinpeng Fang ,&nbsp;Huijin Fan ,&nbsp;Lei Liu ,&nbsp;Wei Wang ,&nbsp;Bo Wang","doi":"10.1016/j.isatra.2025.03.013","DOIUrl":"10.1016/j.isatra.2025.03.013","url":null,"abstract":"<div><div>Reverse actuator faults may occur intermittently in practical systems due to reversed magnetic field polarity, aeroelasticity, radiation, software errors, wrong wiring, etc., which cause the actuators to perform the opposite control actions from the desired, and thus the directions of the faults are not only unknown but also uncertain. In practice, the faults with reverse mode may force the system to be unstable and reduce its safety and lifespan. Therefore, tolerating intermittent faults of uncertain directions can significantly contribute to the safety enhancement and lifespan extension of the system. This paper investigates the adaptive event-triggered fault-tolerant control issue for uncertain nonlinear systems in the presence of multiple intermittent actuator faults of uncertain directions. Unlike the existing results, the faults with reverse mode are considered in this study while their total number could be infinite. Therefore, the possibly infinite number of jumps of the reverse faults makes the existing fault-tolerant control approaches no longer applicable. To solve this problem, a series of novel Nussbaum functions with well-defined sign properties in certain intervals is first proposed. Then, a piecewise integration-based contradiction argument is devised in a well-constructed fault-related time sequence, which shows the boundedness of the designed Nussbaum functions even if the reverse actuator faults are multiple and intermittent. Furthermore, considering the frequent changes of the control signals caused by intermittent actuator faults, a novel event-triggering mechanism is proposed, which is related not only to the magnitude but also to the rate of change of the transmitted signals. Besides showing the global uniform boundedness of all the closed-loop signals, it is also established that the system output tracks the given reference trajectory asymptotically. Finally, simulation and comparison results illustrate the effectiveness and advantages of the proposed fault-tolerant control scheme.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 14-23"},"PeriodicalIF":6.3,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Event-triggered output feedback tracking against random deception attacks for nonlinear systems","authors":"Zebin Wu ,&nbsp;Yanjun Shen","doi":"10.1016/j.isatra.2025.03.009","DOIUrl":"10.1016/j.isatra.2025.03.009","url":null,"abstract":"<div><div>In this paper, the scheme of event-triggered output feedback tracking control is investigated for nonlinear systems with input/output filters when there exist random deception attacks. The success rate of the random deception attacks is represented by a Bernoulli process, and the successful attack is to inject false data into the output or input signals. To address this issue, event-triggered mechanisms are adopted in the sensor-to-controller (SC) and controller-to-actuator (CA) channels to reduce the utilization of network resources and the frequency of effective attacks. Moreover, two filters (the input and output filters) are designed to mitigate the impact of the random attacks and enable the backstepping method applicable by rendering discontinuous triggering signals differentiable. Sufficient conditions for tracking effectiveness are provided by using the Lyapunov stability theory. Finally, a simulation example verifies the validity and practicality of the proposed methods.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 1-13"},"PeriodicalIF":6.3,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143744616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finite-time stability and stabilization for highly nonlinear stochastic Markov jump systems","authors":"Shiyu Zhong ,&nbsp;Weihai Zhang","doi":"10.1016/j.isatra.2025.03.006","DOIUrl":"10.1016/j.isatra.2025.03.006","url":null,"abstract":"<div><div>The research on finite-time stability (FTS) mainly focuses on linear and nonlinear systems, however, there are few studies on such problems for highly nonlinear systems. At present, most studies on FTS use the Lyapunov function method, and most of the results not only require the Lyapunov function in different modes to have the same feature, but also require the diffusion operators in different modes to be constrained by the same type of functions. This is somewhat restrictive to the selection of the Lyapunov function. Based on this, this paper concerns with FTS and asynchronous control of highly nonlinear stochastic Markov jump systems (HNSMJSs). Firstly, the criteria of <span><math><mi>m</mi></math></span>th moment finite-time stability (<span><math><mi>m</mi></math></span>-MFTS) for HNSMJSs in Lyapunov function form and parameter form are given and the asynchronous controller is provided to guarantee the <span><math><mi>m</mi></math></span>th moment finite-time stabilization (<span><math><mi>m</mi></math></span>-MFT stabilization). Moreover, HNSMJSs with deterministic time delay are extended to that with time-varying delay, and a more general result is given. Finally, three examples are provided to clarify the effectiveness of the proposed work.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"160 ","pages":"Pages 131-138"},"PeriodicalIF":6.3,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive super-twisting nonsingular fast terminal sliding mode fault tolerant control of a 2-DOF helicopter with input quantization","authors":"Hui Bi ,&nbsp;Tao Zou ,&nbsp;Jincai Zhu ,&nbsp;JiaKun Liu","doi":"10.1016/j.isatra.2025.03.003","DOIUrl":"10.1016/j.isatra.2025.03.003","url":null,"abstract":"<div><div>To address system uncertainties and external disturbances in a 2-DOF helicopter system, this paper proposes a novel adaptive super-twisting non-singular fast terminal sliding mode (NFTSM) fault-tolerant control (FTC) strategy. First, a hysteresis quantizer is utilized to mitigate chattering during the signal quantization process, and reduce energy loss. Second, a novel finite-time convergent NFTSM manifold is proposed, enabling the tracking trajectories to quickly reach the sliding mode surface, thereby endowing the controller with strong robustness. Additionally, neural networks (NNs) are employed to approximate the system’s nonlinear uncertainty functions. Furthermore, to overcome the dependency of the super-twisting algorithm on boundary information regarding disturbances during the design process, an adaptive super-twisting algorithm is introduced to compensate for the effects of quantization errors and external disturbances, ensuring FTC performance. Finally, simulation and experiment results effectively validate the superiority of the proposed control strategy.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"160 ","pages":"Pages 175-185"},"PeriodicalIF":6.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143744615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoupling compensation accuracy from sensor misalignment: A generalized black-box model for gravity gradiometers","authors":"Mingbiao Yu ,&nbsp;Yu Liang ,&nbsp;Xiaobing Yu ,&nbsp;Chenyuan Hu ,&nbsp;Zhenlong Hou ,&nbsp;Li Yu ,&nbsp;Wei Zhao ,&nbsp;Huafeng Liu ,&nbsp;Liang Zhang ,&nbsp;Ji Fan ,&nbsp;Yuanhang Sun ,&nbsp;Congmei Jiang ,&nbsp;Liangcheng Tu ,&nbsp;Zebing Zhou","doi":"10.1016/j.isatra.2025.03.010","DOIUrl":"10.1016/j.isatra.2025.03.010","url":null,"abstract":"<div><div>Moving-base gravity gradiometers are widely used in applications such as mineral exploration and passive navigation; however, their high sensitivity to platform motion presents significant challenges in compensating for motion-induced errors. Existing methods rely on precise alignment between motion sensors and the gradiometer’s coordinate system, making compensation accuracy heavily dependent on sensor installation precision. To address this issue, we propose a novel generalized black-box modeling method for motion error compensation in gravity gradiometers. By incorporating sensor misalignment directly into the model, our approach effectively decouples compensation accuracy from installation precision. Constructed based on the gradiometer’s dynamic characteristics and the excitation and input–output behavior of its sensitive components, the black-box model inherently avoids redundant operational terms, reduces multicollinearity, and lowers computational resource requirements. Validation through numerical simulations in a dynamic 0.1<!--> <!-->g environment demonstrates that the output consistency between the black-box and analytical models reaches 10⁻¹⁰, achieving an compensation accuracy of 0.1<!--> <!-->E. Furthermore, experimental results using a gravity gradiometer prototype confirm the model’s effectiveness in real-world conditions. The proposed method significantly reduces motion errors induced by 1<!--> <!-->mg linear motion and 0.001<!--> <!-->rad/s angular motion, lowering the noise level to 4<!--> <!-->ng/<span><math><msqrt><mrow><mi>H</mi><mi>z</mi></mrow></msqrt></math></span>, approaching the static inherent noise level of 1<!--> <!-->ng/<span><math><msqrt><mrow><mi>H</mi><mi>z</mi></mrow></msqrt></math></span>. These results verify the black-box model’s effectiveness and robustness in dynamic environments, highlighting its potential to enhance the practical performance of gravity gradiometers by mitigating motion-induced errors without stringent requirements on sensor installation precision.</div></div>","PeriodicalId":14660,"journal":{"name":"ISA transactions","volume":"161 ","pages":"Pages 228-242"},"PeriodicalIF":6.3,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143694800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}