Self-adaptive Control Research Articles

Autonomous intelligent additive manufacturing of continuous fiber-reinforced composites: data-enhanced knowledgebase and multi-sensor fusion

ABSTRACT Additive manufacturing (AM) are an emerging technique to generate complex structures of composite. However, the instability of the AM process leads to adverse manufacturing effects, including dimensional inaccuracies and poor mechanical performance in CFRP composites. Online monitoring and adaptive control based on autonomous cognition are suggested to ensure the accuracy of as-fabricated parts and enhance their quality upon manufacturing. In this study, a method of online monitoring and self-adaptive control based on multi-sensor fusion is proposed to predict and adjust the process parameters during AM of CFRP. The force sensor, visual camera, and thermal camera are employed to obtain the multiple signals upon manufacturing and then realize the autonomous perception, cognition, and decision features. Herein, the quantitative correlations between local defects and multi-sensing features are established to guide the decision-making of closed-loop adjustment. Besides, an empirical surrogate model between the misalignment of fiber bundles and input parameters is built to predict the proper parameters. Moreover, the temperature difference and contact force are selected as the controlled features, which are acquired using a thermal camera and a force sensor. The proposed system offers a novel framework for bolstering both the stability of the AM process and the quality of fabricated components.

A self-adaptive fractional-order PID controller for the particle velocity regulation in a pneumatic conveying system

This paper presents the methodical development of a state-error-driven self-adaptive fractional-order proportional–integral–derivative (AFOPID) control algorithm to efficiently regulate the velocity of pneumatically conveyed particles at the desired set point and to prevent the blockage of particles in a pipe due to an imbalanced combination of their velocity and corresponding mass flow rate. The proposed fractional control law is constituted by adaptively modulating fractional orders of the integral and differential operators in the control based on the state-error variations in the velocity of solid particles. The particle’s velocity is measured and updated via electrostatic sensors in conjunction with cross-correlation signal processing algorithms. All the other fixed hyper-parameters associated with the proportional–integral–derivative (PID) control scheme are meta-heuristically optimized by using a genetic algorithm. The proposed AFOPID is benchmarked against conventional integer-order PID and the fractional-order proportional–integral–derivative (FOPID) controllers. Experiments are performed on a laboratory-scale test rig to comparatively analyze the aforesaid control schemes, where each controller is examined for three velocity set points and three disturbance levels. The experimental results validate the superior time optimality and robustness of the proposed AFOPID controller against bounded disturbances and abrupt velocity set-point variations by manifesting relatively faster settling time, low overshoots (and undershoots), and smaller steady-state fluctuations.

An artificial intelligence based self-adaptive dynamic process control system for enhancing in-situ bioremediation of benzene-contaminated groundwater – Part I methods

This study develops a new AI-based self-adaptive dynamic process control (SADPC) system based on stepwise inference combined with genetic algorithm optimization technologies, including a filtered-clustering inference prediction model (FCI simulator), a stepwise inference controller (SI emulator), a model predictive control controller, and two optimizers. This system effectively reflects the dynamics and complexity of the bioremediation process and controls the remediation system based on the feedback information. To achieve this goal, a statistical model for simulating the enhanced bioremediation process through the FCI simulator is proposed, which can predict the resulting contamination situation based on the previous contamination situation and pumping/injecting flow rate. Then a bridge is established through the SI emulator, which can generate a control action based on a given contamination situation. This suggested decision makers that guidelines and policies on remediation-oriented SADPC systems could be tentatively investigated, developed, and applied in the future effort.

An artificial intelligence-assisted digital microfluidic system for multistate droplet control

Digital microfluidics (DMF) is a versatile technique for parallel and field-programmable control of individual droplets. Given the high level of variability in droplet manipulation, it is essential to establish self-adaptive and intelligent control methods for DMF systems that are informed by the transient state of droplets and their interactions. However, most related studies focus on droplet localization and shape recognition. In this study, we develop the AI-assisted DMF framework μDropAI for multistate droplet control on the basis of droplet morphology. The semantic segmentation model is integrated into our custom-designed DMF system to recognize the droplet states and their interactions for feedback control with a state machine. The proposed model has strong flexibility and can recognize droplets of different colors and shapes with an error rate of less than 0.63%; it enables control of droplets without user intervention. The coefficient of variation (CV) of the volumes of split droplets can be limited to 2.74%, which is lower than the CV of traditional dispensed droplets, contributing to an improvement in the precision of volume control for droplet splitting. The proposed system inspires the development of semantic-driven DMF systems that can interface with multimodal large language models (MLLMs) for fully automatic control.

Robust Adaptive Fuzzy Control for Second-Order Euler-Lagrange Systems With Uncertainties and Disturbances via Nonlinear Negative-Imaginary Systems Theory.

Ensuring robust and precise tracking control in the presence of uncertain multi-input-multi-output (MIMO) system dynamics and environmental variations is a significant challenge in the field of robust and adaptive control theory. While fuzzy control strategies have demonstrated good tracking performance in normal conditions, designing and tuning fuzzy controllers can be a challenging task in highly uncertain environments. In this study, we investigate a novel approach that combines robust nonlinear negative-imaginary (NI) systems theory with a self-adaptive fuzzy control scheme and the Lyapunov synthesis to develop a robust adaptive negative-imaginary-fuzzy (RANIF) control scheme. We optimize the critical parameters of the proposed fuzzy system using a self-tuning technique with a proportional-derivative sliding manifold. Furthermore, unlike the existing adaptive fuzzy control methods, we propose a small number of membership functions and systematically derive the fuzzy rules by employing Lyapunov, nonlinear NI, and dissipativity theories, which simplify the tuning process, work out the matter of "explosion of complexity," and reduce computational complexity. We demonstrate the global stability of the closed-loop system using nonlinear NI theory. To evaluate the effectiveness of our proposed approach, we present simulation results for two examples involving uncertain MIMO second-order Euler-Lagrange systems. These systems, known for their capacity to represent a diverse range of practical physical systems, serve as suitable testbeds for our methodology. Our results show that RANIF outperforms other control methods, such as nonlinear strictly NI-Fuzzy, fuzzy-logic control, model predictive control, and conventional PID control, in terms of robustness to disturbances and inestimable faults, trajectory tracking performance, and computational complexity.

Underwater manipulator arm control based on Harris Hawk algorithm optimized RBF neural network

This article addresses the control issues of underwater manipulator arms in complex marine environments, proposing a composite control strategy based on the Harris Hawk Optimization (HHO) algorithm and Radial Basis Function (RBF) neural network. Combining the global search capability of the HHO algorithm with the fast approximation characteristics of RBF neural networks, a self-adaptive control method for underwater manipulator arms is designed. By automatically optimizing the parameters of the neural network, the performance and robustness of the control system are enhanced. Through simulation experiments, the effectiveness of the proposed control algorithm is verified. The results show that compared with the traditional RBF neural network control and fuzzy sliding mode control, the optimized control algorithm proposed in this paper has significant improvement compared with both of them, demonstrates good control effect and high practical value, and provides an effective solution for the precise control of the underwater manipulator arm.

Application of Adaptive Fuzzy Algorithm in Single-Chip Microcomputer Control System

Objective: In practical application, an SCM control system needs to respond to user instructions quickly and accurately, and at the same time needs to have robustness and adaptability to adapt to complex and changeable environments and working states. Therefore, how to improve the control accuracy and stability of SCM control systems, and how to adapt to the change of different working environments and working states, has become one of the important issues in the design and research of SCM control systems. Methods: Adaptive fuzzy algorithm, as a new control algorithm, has the advantages of simple structure, easy implementation and high precision, and has been widely used in many fields. On the basis of three kinds of fuzzy logic system framework, this paper analyzes the self-adaptive fuzzy algorithm single-chip microcomputer control system and carries on the corresponding performance test of the system by constructing an intelligent car. The testability test of single-chip microcomputer detection, hardware detection, algorithm recognition rate and system control rate is tested, respectively, to ensure the normal operation of the system. Conclusion: The microcontroller control system of fuzzy algorithm system is compared with that of traditional algorithm system in many aspects. The average error rate of the traditional algorithm system is 2%, while the average error rate of the fuzzy algorithm system is 0.8%. In other aspects, the fuzzy algorithm system is superior to the traditional system. For example, the fuzzy algorithm system has a 100% instruction recognition rate and a data processing speed of up to 1 second. According to the characteristics and requirements of the single-chip microcomputer control system, applying the adaptive fuzzy algorithm to the design of a single-chip microcomputer control system can effectively improve the control precision and stability of thesystem.

A Digital Twin-Based Adaptive Height Control for a Shearer

The shearer is an important component of the smart mining workface, and its effective control is a key aspect that guarantees safe and high-efficient production in coal mines. To address the issue of autonomous height adjustment during the shearer’s cutting process, a self-adaptive speed control method driven by digital twin technology is proposed. A digital twin-based control architecture for the shearer is first established, which consists of physical and the corresponding virtual entities, as well as reality–virtual interaction between them. Based on the mathematic model formulated for height adjustment system of the shearer, an adaptive fuzzy sliding mode controller (AFSMC) with the displacement estimation is designed for the virtual entity, with the purpose of guiding the operation of the corresponding physical entity. Simulation experiments on MATLAB compares the control performance among the proposed method and four comparative ones, including PID controller, integral sliding mode controller (ISMC), feedback linearization controller (FLC), and fuzzy sliding mode controller (FSMC). The experimental results confirm the effectiveness of the proposed AFSMC. More specifically, its steady-state error is 0.024, the maximum absolute control input is 8.43, and the settling time is 1.74 s. This also proves that the digital twin-based control method enables the precise adaptive height adjustment of the shearer, providing potential reference for the intelligent development of a smart mining workface.

Frequency stability of new energy power systems based on VSG adaptive energy storage coordinated control strategy

A self-adaptive energy storage coordination control strategy based on virtual synchronous machine technology was studied and designed to address the oscillation problem caused by new energy units. By simulating the characteristics of synchronous generators, the inertia level of the new energy power system was enhanced, and frequency stability optimization was achieved. This strategy is integrated with the frequency response model of the new energy power system to improve the system's frequency regulation capability and achieve more stable and efficient operation. From the results, the damping of the system increased, the oscillation frequency decreased after a duration of about 15 s, and the system stability improved by 76.09%. The proposed strategy based on virtual synchronous generator adaptive energy storage coordination control strategy was improved by 83.25%. In addition, the proposed strategy has improved stability indicators and system completion efficiency by 40.57% and 22.21% respectively, both of which are better than the comparative strategies. As a result, this strategy significantly enhances the frequency regulation capability of the system, which has a positive effect on achieving efficient operation of the new energy power system and maintaining the stability of the power system.

Research on the Smart Broad Bean Harvesting System and the Self-Adaptive Control Method Based on CPS Technologies

With the rapid development of new-generation cyber–physical system (CPS) technologies, the smart operation and management of the broad bean harvesting system are enabled. This paper proposed a smart broad bean harvesting system (SBHS) and a self-adaptive control method based on CPS technologies. Firstly, the overall architecture of the SBHS is designed, which consists of four main components, namely optimal intelligent perception environment configuration, digital twin model construction, virtual simulation and real-time optimization, self-adaptive adjustment and control. Then, three key enabling technologies are discussed in detail, namely, intelligent perception environment configuration for the SBHS, digital twin model construction for the SBHS, colored Petri net (CPN)-based self-adaptive analysis and control of the harvesting system. Lastly, a proof-of-concept experiment based on a cooperative company is presented to illustrate the main work logic and advantage of the proposed SBHS. After the edge–cloud cooperative intelligent harvesting environment is configured, the CPN model for the workflow of the SBHS is created to analyze and optimize the harvesting processes. In addition, a management and control platform are developed to further illustrate the implementation of the proposed SBHS and the self-adaptive control method.

Solar-heat pump combined drying with phase change heat storage: Multi-energy self-adaptive control

Due to the various uncertainties in multi-energy drying systems, traditional condition control struggles with the rational matching of multiple heat sources and precise temperature regulation. In order to automatically switch energy utilization modes based on current parameters to reduce energy consumption, this paper developed a fuzzy control system for a kelp multi-energy drying device. An automatic switching strategy between different operating modes and the action processes of various actuators were established for matching multiple energy sources. The system hardware and software were designed and installed, including a remote monitoring devices and human-machine interface. Drying experiments of kelp were conducted in solar, solar-heat pump, heat pump and Heat storage-heat pump mode using both the fuzzy control system and the original. The fuzzy control system showed a temperature overshoot of 2.57 %–3.95 %, temperature deviation within ±1.5 °C, which were superior to the original control system. The energy consumption in solar-heat pump mode was 0.398 kW h/kg, only 43 % of the original control system. BP neural networks prediction model of kelp moisture content under different drying modes was established to prevent over-drying. The model can accurately describe the pattern of moisture content variation with RMSE of 2.36–4.27.

Analysis of mixing enhancement ability of bypass dual throat nozzle with single/multi-tabs

Bypass dual throat nozzle (BDTN) represents an innovative fluidic thrust vectoring nozzle capable of adjusting thrust vectoring angles through self-adaptive flow control. This study explores the BDTN-single/multi-tabs configurations, ensuring that the nozzle’s outlet projected area remains constant while introducing one or more pairs of tabs coplanar with the convergent section of the cavity. This design accounts for aerodynamic performance, thrust vectoring capabilities, and mixing abilities of the BDTN. Through theoretical analysis, design implementation, numerical simulations, and wind tunnel experiments, findings reveal that, in the case of BDTN-single-tab configuration, an increase in tab angle (α) leads to heightened streamwise vortex intensity at the nozzle outlet, reduced high-temperature core area, and enhanced jet centerline velocity and temperature attenuation rate. BDTN-single-tab achieves up to a 90% reduction in centerline-temperature/velocity decay rate, implying stronger mixing enhancement with higher tab angles. Compared to α = 10° BDTN-single-tab, the area of the high-temperature core area decays by 75%. For the BDTN-multi-tab configuration, an increase in the number of tabs results in increased thrust coefficient and vectoring angle, alongside diminished streamwise vortex strength at the nozzle outlet, and a more complex streamwise vortex structure. However, the jet’s centerline velocity and temperature decay rate decreased as a consequence.

Development and verification of shield thrust vector self-adaptive control technology in soft soil strata

To solve the difficulty in automatically obtaining an effective total thrust vector relative to the shield posture adjustment requirements during self-driving in soft soil strata, a shield thrust vector self-adaptive control technology for shield machines was proposed. Subsequently, a large-scale model platform was established to simulate the straight-line advancement of the testing shield machine under dynamic loads, and the feasibility of steady shield driving was verified. The test results showed that: the actual total thrust force exhibited the same variation characteristics according to load force, while a relatively fixed difference of 1000 kN between the two caused by the system friction was observed. A quick recovery after an abrupt jump of the shield speed was discovered once there was a sudden, significant change in the load. The actual resultant moment of total thrust force effectively responded to the load force, and the shield postures were maintained well. Further, the driving speed and the horizontal stroke difference were controlled in the ranges of ±3 mm/min and ±5 mm of each set values, respectively. Subsequently, this technology was applied to the Wusongkou Yangtze River Tunnel project in Shanghai, and the on-site test results verified its feasibility in actual soft soil strata. The shield speed remained stable as the actual thrust forces shared the same changing low of the target values, and a fixed difference between the two was maintained to ensure the movement of the shield machine. The variation curves of the actual steering angles in both the horizontal and vertical directions coincided with those of the target steering angles because the resultant horizontal and vertical moments of the thrust force effectively responded to each steering requirement, which was executed with high quality.

Simulating the Effects of Global Warming on the Agricultural Yields in a Reel Greenhouse Controlled Via a New Self-Adaptive Fuzzy Controller

Simulating the Effects of Global Warming on the Agricultural Yields in a Reel Greenhouse Controlled Via a New Self-Adaptive Fuzzy Controller

Modulation of an Si-O-Si structure in uniformly photochromic microcapsules for solar heat and daylight management

Photochromic microcapsules adjust to sunlight adaptively and using them to fill windows is an attractive option for constructing smart windows that can manage solar heat and daylight. However, fabricating high-durability polymer-composite photochromic microcapsules for use in outdoor glass windows remains challenging, requiring high contrast ratio, high transparency, and low haze. Herein, we synthesized a novel poly(urea-siloxane) shell monomer containing Si-O-Si bonds and successfully prepared a photochromic microcapsule by modulating the mass ratios of shell monomers and emulsifiers. The photochromic poly(urea-siloxane)-based microcapsule-coated glass (PCPUS MCG) showed high luminance transmittance (83.66 %) and low haze (20.31 %). The as-prepared PCPUS MCG exhibited self-adaptive sunlight control without additional energy input, with strong solar modulation ability (Δτsol of 38.30 %). Furthermore, the response indoor air temperature was reduced by approximately 3.7 °C in a field test using a model house equipped with PCPUS MCG windows, showing promising energy-saving potential compared with conventional windows. Therefore, uniform photochromic-microcapsule modification using Si-O-Si bonds warrants attention in future energy-saving window designs.

Dynamics in a light-sensitive neuron with two capacitive variables

Involvement of two capacitive variables into neuron models provides better description of the cell membrane property and then the diversity effect of electromagnetic field inner and outer of the cell membrane can be estimated in clear way. Specific electric components can be combined to build equivalent neural circuits for reproducing similar neural activities under some self-adaptive control schemes. A phototube converts external light into electric stimuli and the injected energy is encoded to excite the cell membranes for presenting suitable firing patterns. Two capacitors are connected via a linear resistor for mimicking the energy exchange and changes of membrane potentials. Combination of memristor into an additive branch circuit of the neural circuit can estimate the effect of electromagnetic induction and energy absorption. The energy function H for this light-sensitive and memristive neuron is calculated in theoretical way, and the average energy function 〈H〉 can predict the occurrence of stochastic resonance, which can be confirmed by estimating the distribution of signal to noise ratios. The firing mode is relative to the energy value of the neuron, and a control law is suggested to control the mode transition in neural activities in an adaptive way.

Deep reinforcement learning for adaptive flexible job shop scheduling: coping with variability and uncertainty

ABSTRACT The frequently evolving manufacturing system necessitates real-time large-scale data analytics, surpassing the capabilities of classical systems or human skills, necessitating knowledge development and self-adaptive control. Unpredictable real-time events in smart factories cause changes in the effectiveness of planned schedules or tasks; even slight interruptions can accumulate to make the preplanned schedule unoptimized, if not impossible. To meet the required production efficiency, typical dynamic scenarios on the shop floor, such as failures, random job arrivals, and machine setup, must be addressed quickly. Hence, this study proposes a novel Triple Deep Q Network (TDQN) approach for learning high-quality dispatching rules for addressing the Flexible Job Shop Scheduling Problem (FJSSP) in uncertainty. For the dispatching rule-based FJSSP, the Markov Decision Process (MDP) to choose a suitable operation-machine (O-M) pair is formulated to allow operation selection and resource assignment resolutions to be made simultaneously. The performance of the TDQN method is investigated against the Double Deep Q Network (DDQN) and Deep Q Network (DQN) approach and found to be more stable. Moreover, among the 29 different shopfloor configuration settings, TDQN performed better in 62.07% of the overall instances, while DDQN and DQN performed better in only 31.03% and 6.9% of instances, respectively.

A Self-Adaptive Inertia Hybrid Control of a Fully Constrained Cable-Driven Parallel Robot

A Cable-Driven Parallel Robot (CDPR) is a special type of parallel robot actuated by elastic cables instead of rigid links, which brings uncertainties of model nonlinearities and structural friction depending on the payload variation. A precise motion with minimum control effort against an unknown payload has been a challenging task. To conquer it, we propose an adaptive hybrid control approach for the fully-constrained CDPR with an unknown payload in this paper. A Cartesian space position control and a joint space cable force control are designed through inertia estimation to encounter the effect of the uncertain payload. And then, an artificial neural network (ANN) is employed to estimate the end-effector force in Cartesian space for precise force control and consecutive uncertainties compensation. The stability of the proposed controller is proven based on the Lyapunov method and the efficacy is verified by the experiments. As for feasibility results, the proposed adaptive hybrid control-based cable force estimation was evaluated on the Mini CDPR. Compared to the traditional control scheme, the tracking error was decreased approximately 56% and the utilized tension was significantly reduced for the given trajectory tracking test. Furthermore, the investigation of free movements of the helix trajectory and pick-and-place tasks showed that the proposed hybrid adaptive control can control the position and cable force altogether while being able to estimate the inertia of the end-effector. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The study was motivated by the control problem of adjusting cable tensions of a cable-driven parallel robot (CDPR) against varying payloads at the end-effector. Several advanced control approaches were proposed for but limited to CDPR model parameter estimation and did not consider varying payload. This paper suggests a practical methodology capable of both self-adaptation to unknown payload inertia and consequently improving tracking control performance for a CDPR. In this paper, we derived an adaptive control model and proved stability to ensure safety. In order to encounter unmodeled uncertainties such as pulley friction and cable characteristics, we utilized an artificial neural network (ANN) trained by experiments. The experimental results could confirm that the proposed scheme can estimate the payload inertia and generate minimized cable tension while maintaining good trajectory tracking performance. In future research, we will show more practical validation for a scale-up CDPR with heavy objects toward logistics or pick-and-place application in practice.

High-precision and wide-range temperature measurement and control system of satellite-borne calibration blackbody

The accurate measurement and control of blackbody temperature can play an important role in radiometric calibration. A novel circuit suitable for the aerospace environment is designed to measure and control the temperature of the blackbody. A coarse-fine measurement method considering the wire resistance and self-heating effect of the platinum resistance is presented to calculate the resistance values of the platinum resistors. The precision of temperature measurement is improved using a line fitting algorithm with error calibration and temperature drift error compensation. A fuzzy self-adaptive PID controller is designed to improve the temperature control effect. The performances of the developed system are implemented on an FPGA/A3PE3000-FG484I controller board. The test results show that the device temperature measurement precision can reach ±0.03K for the entire temperature range 238 K to 367 K, the temperature stability is better than 0.02 K/20 s, and the temperature uniformity is better than 0.1 K.

A model-based approach for self-adaptive security in CPS: Application to smart grids

Security risk assessment is an important challenge in the design of Cyber Physical Systems (CPS). Even more importantly, the intrinsically dynamical nature of these systems, due to changes in their environment, as well as evolutions in their infrastructures, makes them self-adaptive systems, where security aspects have to be considered in terms of management of detections and reactions for self-protection. In this work, we propose an approach to autonomously mitigate the threats in each reconfiguration at application or infrastructure levels of CPS. We propose and implement a framework for self-adaptive security: software architecture, design method, and integration with model-based decision. We use Attack-Defense Trees for modeling threats, and our approach involves security risk assessment, taking into account its balancing and coordination with quality-of-service aspects. We formulate and formalize the on-line decision problem to be solved at each cycle of the self-adaptation control loop in terms of Constraint Programming (CP) modeling and resolution. The CP model implements a set of constraints that allow to specify secure configurations, evaluated regarding their impact on system performance to pinpoint the most relevant one portraying a good balance between the security and quality of service. We perform validation of our approach with its application to Smart Grids, more particularly to an industrial case study from RTE (the French Energy Transmission company).