Velocity signal is difficult to obtain in practical electro-hydraulic servomechanisms. Even though it can be approximately derived via numerical differentiation on position measurement, the strong noise effect will greatly deteriorate the achievable control performance. Hence, how to design a high performance tracking controller without velocity measurement is of practical significance. In this paper, a practical adaptive tracking controller without velocity measurement is proposed for electro-hydraulic servomechanisms. To estimate the unmeasurable velocity signal, an extended state observer (ESO) which also provides an estimate of the mismatched disturbance is constructed. The ESO uses the unknown parameter estimates updated by a novel adaptive law which only depends on the actual position and desired trajectory. Moreover, the matched parametric uncertainty is also handled by on-line parameter adaptation and the matched disturbance is suppressed via a robust control law. The proposed ESO-based adaptive controller theoretically achieves an excellent asymptotic tracking performance when existing time-invariant modeling uncertainties. In the presence of time-variant modeling uncertainties, guaranteed transient performance and prescribed final tracking accuracy can also be achieved. The proposed control strategy bridges the gap between adaptive control and disturbance observer based control without using velocity signal and preserves the performance results of both control methods while overcoming their practical performance limitations. Comparative experiments are performed on an actual servovalve controlled double-rod hydraulic actuator to verify the superiority of the proposed control strategy.

This paper focuses on developing an advanced nonlinear controller for hydraulic system to achieve asymptotic tracking with various disturbances. To accomplish this study, a multilayer neural-networks (NNs) estimator is first developed to improve the compensation accuracy of model-based feed-forward control terms, which can greatly reduce the uncompensated disturbance, then a continuous robust integral of the sign of the error (RISE) control approach is effectively integrated with the multilayer neural-networks (NNs) estimator to deal with the residual mismatched disturbance, in which the RISE feedback gain is adapted online to further decrease the high-gain feedback. At last, by considering the inwardness of matched disturbance in hydraulic systems, it is estimated by another multilayer NNs fully with the residual functional reconstruction inaccuracies handled by a novel adaptive term. As a result, theoretical analysis reveals that the proposed controller guarantees a semi-global asymptotic stability. Extensively comparative experimental results verify the priority of the proposed control strategy, and a 0.2% dynamic tracking accuracy is achieved.

The industrial gearboxes usually work in harsh and variable conditions, which results in partial failure of gears or bearings. Accordingly, the continuous irregular fluctuations of gearbox under variable conditions maybe increase the intraclass difference and reduce the interclass difference for the monitored samples. To this end, a new intelligent fault diagnosis method of gearbox based on adaptive intraclass and interclass convolutional neural network (AIICNN) under variable working conditions is proposed. The core of the proposed algorithm is to apply the designed intraclass and interclass constraints to improve the distribution differences of samples. Meanwhile, the adaptive activation function is added into the 1-D convolutional neural network (1dCNN) to enlarge the heterogeneous distance and narrow the homogeneous distance of samples. Specifically, the training sample subset with intraclass and interclass spacing fluctuations under variable conditions is first converted into frequency domain through the fast Fourier transform (FFT), and the designed AIICNN algorithm is employed for model training. Afterward, the testing subset is provided to the trained AIICNN algorithm for fault diagnosis. The experimental data of the planetary gearbox test rig verify the feasibility of the proposed diagnosis method and algorithm. Compared with other methods, this method can eliminate the difference of sample distribution under variable conditions and improve its diagnostic generalization.

Hydraulic manipulators are extremely complicated systems due to the highly nonlinear characteristics, strong coupling among multiple joints, and heavy modeling uncertainties, which greatly complicate the high-performance tracking controller development compared with conventional manipulators driven by electrical motors. To overcome the above obstacles, this article proposes a novel radial basis function neural network (RBFNN)-based adaptive asymptotic prescribed performance controller for $n$ -degrees of freedom (DOF) hydraulic manipulators. First, the entire manipulator system model containing actuator dynamics is derived. Then, the adaptive asymptotic prescribed performance controller is synthesized based on the backstepping framework, in which the RBFNN is employed to estimate the unknown joint coupling dynamics, while the RBFNN reconstruction error and uncertainties of the actuator dynamics are handled by the robust integral of the sign of the error (RISE) feedbacks. Meanwhile, a prescribed performance function (PPF), which characterizes both the certain transient and steady-state performance, is innovatively incorporated into the control design to restrict the joint tracking errors. The theoretical analysis proves that the proposed control strategy can achieve a prescribed tracking performance and the asymptotic stability of the whole closed-loop system can also be ensured. Finally, comparative simulations are conducted to verify the validity of the proposed controller.

In this article, an innovative backstepping controller for hydraulic systems is proposed to handle system uncertainties and accomplish specified performance tracking without violating the full-state constraints. To deal with uncertainties, extended state observers ESOs and an adaptive law are integrated. ESOs are structured to estimate disturbances, whereas adaptive law is applied to approximate unknown parameters. The estimated uncertainties are then incorporated into a constrained controller, ensuring that both the prescribed transient tracking performance and the nonviolation of full-state constraints can be guaranteed. A prescribed performance function (PPF) and the barrier Lyapunov function (BLF) are synthesized to guarantee the transient behavior of the tracking error and all state errors within desirable boundaries. Then, an adaptive prescribed performance controller with uncertainty compensation is constructed by merging the BLF and PPF through back-stepping design to stabilize the closed-loop system. Finally, abundant comparative experimental results validate the proposed controller's tracking performance.