Compensation Network Research Articles

An airborne gravity gradient compensation method based on residual backpropagation

Abstract Airborne gravity gradient dynamic measurement error compensation is a crucial aspect of data processing in gravity gradient dynamic measurements. This study introduces a deep learning approach based on a residual backpropagation (Res-BP) neural network for post-error compensation in airborne gravity gradient dynamic measurement. The network employs residual connections to facilitate identity mapping, thereby enabling gradient propagation across layers. This strategy preserves the original information while acquiring additional information through nonlinear operations, effectively mitigating the gradient vanishing issue and enhancing the neural network's fitting capability. The method proposed in this paper is applied to both simulation data from a gravity gradiometer and high-altitude dynamic measured data of an airborne gravity gradient. Compared to traditional neural network multilayer perceptron (MLP), the Res-BP method significantly improves compensation accuracy through its application in high flight experiment of the southern section of
Zhangguangcai Ridge on the western side of Mudanjiang City, Heilongjiang Province.

Physics-driven untrained neural network for vortex beam compensation in adaptive optics aided underwater wireless optical communications

Orbital angular momentum (OAM) multiplexing is emerging as a critical technique for achieving high data capacity in underwater wireless optical communications (UWOC). Nonetheless, wavefront distortions induced by underwater turbulence compromise the orthogonality of OAM modes. In this paper, we introduce a physics-driven untrained learning approach for adaptive optics that operates independently of extensive amplitude datasets. Without iterative processing and pre-trained datasets, the underwater turbulence characteristics can be retrieved accurately by only relying on a one-shot distorted probe beam and a priori known amplitude of the probe beam. By leveraging a single distorted diffraction pattern and a priori known amplitude of the probe beam, the characteristics of underwater turbulence can be accurately retrieved without iterative processing or pre-trained datasets. Furthermore, by implementing a hybrid input/output alternating projection algorithm with a square constraint area, the retrieved underwater turbulence phase screen beyond the [0, 2π] range aligns with the target pattern. This consistency indicates that the proposed wavefront recovery technology is validated across a broad range of turbulence strengths. As a demonstration of feasibility, numerical simulations, and optical experiments were conducted to validate the compensation of OAM beams. Furthermore, the theoretical bit error rate (BER) and channel capacity were inferred based on the purity of OAM modes and the level of crosstalk.

Single Miller Compensation Based Four Stage CMOS Amplifier

Like reversed nested Miller compensation, four nested Miller loops are exploited as a compensation network for a four-stage amplifier. However, isolating the feed-forward path via two differential stages allows the use of a single Miller compensation capacitor while the output node remains intact regarding capacitive loading from compensation. The exploited configuration for the compensation network provides the capability of reducing the number and size of needed capacitors due to positioning at the outputs of differential stages. This scenario is linearly modeled by a transfer function, then a circuit realization is suggested and simulated using 0.18 µm CMOS technology. According to the simulation results, the proposed amplifier can obtain 158 dB DC gain, 11.2 MHz GBW, and 84° PM while consuming 298 µW. Ample sensitivity analysis verifies the robustness of the proposed amplifier against probable mismatches and errors.

Online-Trained Radial Basis Function Neural Network Compensator for Current Harmonics Suppression of Electric Drives

Online-Trained Radial Basis Function Neural Network Compensator for Current Harmonics Suppression of Electric Drives

Model Reference Control for Reducing Pilot-Induced Oscillation Tendencies

Lags between pilot inputs and aircraft responses may lead to a pilot–vehicle system entering into a pilot-induced oscillation. A model reference control element can compensate for these lags, avoiding pilot-induced oscillations and improving tracking performance. Neural network compensation drives the combined controller–plant system to exhibit a closed-loop response similar to that of an idealized system, immune to the factors that trigger pilot-induced oscillations. Actuator rate limiting has been a historically ubiquitous cause of pilot-induced oscillations; meanwhile, aeroelastic effects pose a threat to future lightweight, flexible aircraft designs. Model reference control can reduce pilot-induced oscillation tendencies caused by either of these factors. This paper presents the methods used to train the model reference controller, including conditions for system stability under model reference control. It then showcases results from a pair of simulation experiments applying the control design to compensate for rate limiting and aeroelasticity, respectively. Results demonstrate that the model reference control scheme reduces pilot-induced oscillation tendencies and improves closed-loop tracking performance.

Modeling, Simulation, and Control of a Rotary Inverted Pendulum: A Reinforcement Learning-Based Control Approach

In this paper, we address the modeling, simulation, and control of a rotary inverted pendulum (RIP). The RIP model assembled via the MATLAB (Matlab 2021a)®/Simulink (Simulink 10.3) Simscape (Simscape 7.3)™ environment demonstrates a high degree of fidelity in its capacity to capture the dynamic characteristics of an actual system, including nonlinear friction. The mathematical model of the RIP is obtained via the Euler–Lagrange approach, and a parameter identification procedure is carried out over the Simscape model for the purpose of validating the mathematical model. The usefulness of the proposed Simscape model is demonstrated by the implementation of a variety of control strategies, including linear controllers as the linear quadratic regulator (LQR), proportional–integral–derivative (PID) and model predictive control (MPC), nonlinear controllers such as feedback linearization (FL) and sliding mode control (SMC), and artificial intelligence (AI)-based controllers such as FL with adaptive neural network compensation (FL-ANC) and reinforcement learning (RL). A design methodology that integrates RL with other control techniques is proposed. Following the proposed methodology, a FL-RL and a proportional–derivative control with RL (PD-RL) are implemented as strategies to achieve stabilization of the RIP. The swing-up control is incorporated into all controllers. The visual environment provided by Simscape facilitates a better comprehension and understanding of the RIP behavior. A comprehensive analysis of the performance of each control strategy is conducted, revealing that AI-based controllers demonstrate superior performance compared to linear and nonlinear controllers. In addition, the FL-RL and PD-RL controllers exhibit improved performance with respect to the FL-ANC and RL controllers when subjected to external disturbance.

The deep convolution network in immersive design of digital media art in smart city

The goal of the paper is to examine how convolutional neural network (CNN) is used in the immersive world of digital media art. In order to do this, this paper first explains digital media art in the context of smart cities and the use of immersive scenarios. Next, a brief analysis of the Unet network model and deep aggregation structure is provided. Then, a projector, camera, and computer-based immersive projector-camera display system is constructed. Based on the mathematical reflection model of the system, this paper discusses the method of using CNN to solve the photometric compensation of the projection picture. Meanwhile, a Projection Compensation Network (PCN) is designed, and a multi-scale perceptual loss is added to this compensation network, and the content information of the compensated image is improved by calculating the loss of feature maps of different scales. The final network is named Perceptual Loss-Projection Compensation Network (PL-PCN). Experiments are used to confirm the PL-PCN model’s efficacy. The outcomes demonstrate that the SSIM and PSNR of the projected picture compensated by PL-PCN are boosted by 35.8% and 31.6%, respectively. While the RMSE is reduced by 40.9%, demonstrating an improvement in the compensated image’s quality. Additionally, utilizing a CNN makes it possible to do cross-reflection compensation. Additionally, compared to the network without deep polymerization, the PL-PCN with deep polymerization structure boosts the projected image’s SSIM and PSNR by 6% and 7.57%, respectively, and lowers the RMSE by 13.3% This demonstrates that the addition of deep polymerization structure can have a stronger compensatory effect. This paper can offer a theoretical framework for improving the immersive scene quality of digital media art.

A Single-Input Multi-Output Inverter with Voltage Boosting for Multi-Load Wireless Power Transfer Systems

Multi-load wireless power transfer systems generally require the configuration of multiple transmitting coils. Using traditional single-output inverters will increase the number of inverters, leading to increased system costs and complex structures. Therefore, this paper proposes a single-input multi-output inverter that can drive multiple transmitting coils simultaneously. Compared with traditional single-output inverters and existing multi-output inverters, the proposed inverter utilizes a topology improvement design and an efficient expansion method. By adding only one inductor, one capacitor, and a small number of power switches, it can generate multiple controllable and stable outputs while ensuring output gain, which is expected to simplify the system structure and improve system performance. This paper first introduces the topology evolution process and operating principle of the proposed inverter. Secondly, a mathematical model is established to analyze its operating characteristics, and its parameter design is carried out. Meanwhile, a comparison with existing multi-output inverters is conducted. Then, the resonant compensation networks are analyzed and selected to match the requirements of different loads. Finally, a simulation model of the proposed inverter is constructed, and an experimental setup is set up. The feasibility and superiority of the proposed inverter are verified through simulation and experiments.

Offset Compensation Network: Improving the Control of Battery Energy Storage Systems

Offset Compensation Network: Improving the Control of Battery Energy Storage Systems

PCNet: a human pose compensation network based on incremental learning for sports actions estimation

Human pose estimation has a wide range of applications. Existing methods perform well in conventional domains, but there are certain defects when they are applied to sports activities. The first is lack of estimation of the extremity posture, making it impossible to comprehensively evaluate the movement posture; the second is insufficient occlusion handling. Therefore, we propose a human pose compensation network based on incremental learning, which obtains shared weights to extract detailed features under the premise of limited extremity training data. We propose a higher-order feature compensator (HOF-compensator) to embed the attributes of the extremity into the torso and limbs topology structure, building a complete higher-order feature. In addition, to improve the occlusion handling performance, we propose an occlusion feature enhancement attention mechanism (OFE-attention) that can identify occluded keypoints and enhance attention to occlusion areas. We design comparative experiments on three public datasets and a self-built sports dataset, achieving the highest mean accuracy among all comparative methods. In addition, we design a series of ablation analysis and visualization displays to verify that our method performs best in sports pose estimation.

Machine remaining useful life prediction method based on global-local attention compensation network

Machine remaining useful life prediction method based on global-local attention compensation network

Enhanced predictive PDF control of stochastic distribution systems with neural network compensation and its application

Compared to the conventional control algorithms that use mean and variance as indicators, predictive probability density function (PDF) control can effectively handle the output PDF control problem of non-Gaussian stochastic distribution systems. However, the existing predictive PDF control method does not consider the construction error between output PDF and weight, thus the control performance is still unsatisfactory. Therefore, this paper proposes a new Enhanced Predictive PDF control method (En-PDF) to improve the output PDF control performance of stochastic distribution systems. The proposed method mainly consists of two parts: the predictive PDF control part and the neural network compensation control part aiming to reduce the bias of output PDF. First, the Radical Basis Functions (RBFs) are used to approximate the PDF of the stochastic systems output, and then a prediction model representing the relationship between input and weight is established using the subspace identification algorithm to design the predictive PDF control for the stochastic systems. Next, the Kullback-Leibler (KL) divergence is used to measure the similarity between the output PDF and the set PDF, combined with the weight error and compensation to design a new performance index. Based on this, the parameters of the neural network are adjusted using the gradient descent algorithm to obtain the optimal compensation, and the stability and tracking performance of the proposed algorithm are analyzed using inductive reasoning method. Finally, the predictive PDF control input with the compensation work together on the controlled plant to achieve high-performance control of the output PDF of non-Gaussian stochastic distribution systems. Both simulation experiments and physical control experiments validate the effectiveness and superiority of the proposed method.

A Power Boosting Method for Wireless Power Transfer Systems Based on a Multilevel Inverter and Dual-Resonant Network

With the deepening of research on wireless power transfer (WPT) technology, there is an urgent need to improve the output power of WPT systems. Therefore, this paper proposes a power boosting method based on a multilevel inverter and dual-resonant network. The system adopts a five-level inverter whose output voltage contains rich fundamental and harmonic components. The transmitting side adopts a dual-resonant compensation network, and, through its parameter configuration, the system can be in a resonant state at both the fundamental and third harmonic frequencies. The receiving side adopts two receiving channels which can simultaneously receive power at both frequencies, thus boosting the output power. Firstly, the overall structure and operating principle of the system are introduced. Then, the relationship between the system output power and efficiency with the inverter modulation parameters is obtained and the strategy for selecting the optimal operating points of the inverter is designed by comprehensively considering the THD of the inverter output voltage and the efficiency of the system. Furthermore, the proposed system is simulated in a Matlab/Simulink platform. Finally, an experimental setup is created to verify the proposed method. The results show that, compared with the single-channel WPT system, the proposed method can enhance the output power from 160 W to 310 W with a boosting coefficient of nearly double and with the highest efficiency exceeding 92%.

A Decoupled Modulation Strategy for Constant Voltage/Current Wireless Charging System Under High Coils Misalignment

ABSTRACTOutput fluctuation and lower transmission efficiency under load and mutual inductance variation are hot concerned in the wireless charging system for power batteries. In this paper, a decoupled tracking strategy is proposed to realize constant voltage (CV) or current (CC) output and high transmission efficiency. The circuit model of series–series compensation network is built, and corresponding transmission characteristics can be derived. First, the load and mutual inductance value can be estimated by measuring the primary electrical information, including the inverter output voltage, current, and the phase error between them. Then load‐independent voltage or current output characteristics under coils misalignment can be maintained by tracking the optimal switching frequency of inverter part. In addition, the value of output voltage or current can be adjusted flexibly for different operation occasions by the employment of pulse‐width modulation. As a result, the load‐independent output characteristics realization and output adjustment can be decoupled. Based on only the primary measuring information, the CV/CC output can be maintained via the proposed hybrid control strategy when the coils misalignment and load variation happen, increasing the robustness of whole wireless power transfer (WPT) system. Furthermore, the soft switching of all power switches in the inverter part can be realized to reduce the switching loss. Compared with previous research, the proposed wireless charging system has a higher power density and a simplified control strategy. Finally, an experimental platform with 60‐V charging voltage and 3.6‐A charging current is built to verify the feasibility of the proposed sys‐tem and control method.

Analysis and control design for input‐series output‐parallel multi‐channel inductive power transfer system

AbstractTo realize high‐power inductive power transfer (IPT) for fast charging of electric vehicles (EVs), an input‐series output‐parallel (ISOP) multi‐channel IPT system is analysed in this paper, and an output control strategy based on single neuron controller is proposed to improve the stability of the system. Firstly, the steady‐state operating conditions of ISOP‐IPT system is analysed based on different compensation networks which shows that the constant‐voltage‐output compensation networks are more suitable for the proposed circuit structure. Then, to improve the voltage equalization between channels, an open‐loop control method combining parameter design and phase‐shift control is proposed against different coil misalignments. At the same time, based on the single neuron controller, the system output closed‐loop control is realized without the need of accurate system modelling. Finally, a three‐channel ISOP‐IPT experimental system was constructed, which operated stably at 2.9 kW with a power efficiency of 93.38%. The system closed‐loop control with control time of 22 ms is realized. The voltage equalization control offset is less than 1%.

Dual-path Imbalanced Feature Compensation Network for Visible-Infrared Person Re-identification

Dual-path Imbalanced Feature Compensation Network for Visible-Infrared Person Re-identification

Research on parameter deviation modelling of dual LCC wireless power transfer system

Abstract In this paper, parameter deviation modelling analysis is performed based on the dual LCC compensation network of wireless power transfer (WPT) system. Firstly, the mutual inductive coupling model of the dual LCC compensation circuit is derived based on the fundamental wave analysis method; secondly, the parameter deviation is introduced into the circuit model for the errors existing in the inductive and capacitive components of the compensation network circuit of the actual wireless charging system, and the relation between the deviation and the amplitude of the branch currents, the phase angle and the output characteristics of system are obtained through the establishment of derivation model and the resistive deviation correction term is introduced; finally, the parameter deviation is verified through the simulation. The establishment of parameter deviation model increases the accuracy of the whole circuit model and provides the theoretical basis to reduce the negative influence of parameter deviation on transmission characteristics. The value of parameter deviation can be inverted through the phase angle, thus providing a basis for adjusting the resonant state of the compensation circuit.

Neural networks for ID gap orbit distortion compensation in PETRA III

Undulators are used in storage rings to produce extremely brilliant synchrotron radiation. In the ideal case, a perfectly tuned undulator always has a first and second field integrals equal to zero. But, in practice, field integral changes during gap movements can never be avoided for real-life devices. As they significantly impact the circulating electron beam, there is the need to routinely compensate such effects. Deep Neural Networks can be used to predict the distortion in the closed orbit induced by the undulator gap variations on the circulating electron beam. In this contribution several state-of-the-art deep learning algorithms were trained on measurements from PETRA III. The different architecture performances are then compared to identify the best model for the gap-induced distortion compensation. It is found that realistic data, with several gaps moving simultaneously to arbitrary gaps must be used to train the neural networks. The deep feed-forward neural network was found to be more effective than the recurrent and convolutional neural networks.

Multilayer neuroadaptive constraint-handling control architecture for a family of nonlinear systems with uncertainty compensation

In practical applications, there are some requirements for time-varying constraints on full system states. Currently, Barrier Lyapunov Function is a popular tool for constraint control. However, how to handle various uncertainties while satisfying constraint requirements is worth further research. Accordingly, a high-performance multilayer neuroadaptive constraint-handling controller for a class of nonlinear systems with uncertainty compensation will be developed. Significantly, asymmetric time-varying constraints for full system states can be implemented. Furthermore, a set of novel multilayer neuroadaptive disturbance observers will be proposed to address modeling uncertainties. Moreover, by introducing a set of nonlinear command filters, the intelligent control algorithm will be designed via the command filtered backstepping method. The stability of the whole closed-loop system is strictly proved. Additionally, the proposed algorithm is applied to different nonlinear systems including a hydraulic robotic manipulator system to verify its feasibility.

Consistency Prototype Module and Motion Compensation for few-shot action recognition (CLIP-CPM[formula omitted]C)

Recently, few-shot action recognition has progressed significantly, as it has learned the feature discriminability and designed suitable comparison methods. Still, there are the following restrictions. (a) Previous works are mainly based on visual mono-modal. Although some multi-modal works use labels as supplementary to construct prototypes of support videos, they cannot use this information for query videos. The labels are not used efficiently. (b) Most of the works ignore the motion feature of video, although the motion features are essential for distinguishing. We proposed a Consistency Prototype and Motion Compensation Network(CLIP-CPM2C) based on CLIP to address these issues. Firstly, in order to make the amount of information between the prototype and the query more similar, we propose a novel method to compensate for the text(prompt) information of query videos when text(prompt) does not exist, which depends on a Consistency Loss. Secondly, we use the differential features of the adjacent frames in two directions as the motion features, which explicitly embeds the network with motion dynamics, and then apply the Consistency Loss to the motion features. Extensive experiments on standard benchmark datasets demonstrate that the proposed method can compete with state-of-the-art results. Our code is available at the URL: https://github.com/cofly2014/CPM-MC.git.