Data-driven Compensation Research Articles

Flood Mapping Through Satellite Images Using Deep Learning

Flooding is a pervasive natural disaster that significantly impacts agriculture, infrastructure, and communities, particularly in rural and agricultural regions. Traditional methods of flood assessment and compensation are often manual, time-intensive, and prone to inaccuracies, resulting in delayed aid and inequitable resource distribution. With advancements in technology, satellite imagery and artificial intelligence (AI) provide new opportunities for real-time flood mapping and automated disaster response. This project proposes a Real-Time Flood Mapping and Compensation System using the Attention U-Net deep learning model. Satellite imagery is analysed to detect and segment flood-affected regions with high precision. The Attention U-Net architecture enhances segmentation accuracy by focusing on the most relevant regions in the images while ignoring irrelevant or noisy areas, such as clouds or non-flooded landscapes. The system integrates geospatial data on land boundaries to assess flood severity for individual properties, enabling fair and data-driven compensation for affected landowners. This project holds significant potential for transforming flood disaster management by reducing response times, fostering transparency, and empowering affected communities to recover more effectively. The integration of advanced AI and geospatial technologies marks a critical step toward mitigating the impacts of natural disasters in a rapidly changing climate

Robust Data-Driven Compensation Iterative Learning Consensus Tracking Control for MIMO Multiagent Systems With Random Packet Dropouts

Robust Data-Driven Compensation Iterative Learning Consensus Tracking Control for MIMO Multiagent Systems With Random Packet Dropouts

Data-Driven Compensation Algorithm for Optimizing Power Quality in Interleaved Boost PFC

Data-Driven Compensation Algorithm for Optimizing Power Quality in Interleaved Boost PFC

Continuous action iterated dilemma with data-driven compensation network and limited learning ability

This paper proposes a continuous action iterated dilemma (CAID) in evolutionary game theory with a data-driven compensation network and limited learning ability that considers both players' differences and unknown environment effects. In the traditional dynamic model of CAID, players have identical learning abilities and ignore the influence caused by the environment, which is inconsistent with real society. Therefore, we study the limited learning ability of CAID and the unknown learning mechanism caused by the environment to overcome these problems. Firstly, we propose the dynamic model of limited learning ability for CAID to reveal the law of cooperative evolution in the case when the learning abilities of players are varied. Considering the unknown learning mechanism of players, we adopt the data-driven compensation network to confront the effects of unknown dynamics caused by the environment. In addition, based on the limited learning ability and data-driven compensation network of players, the Lyapunov function is designed to prove the convergence of the CAID, avoiding the high computational complexity caused by the eigenvalues of the Jacobin matrix. In this case, simulations based on two classical dynamic model of evolutionary game theory are carried out to show the effectiveness of our proposed method.

A data-driven compensation scheme for last-mile delivery with crowdsourcing

A recent relevant innovation in last-mile delivery is to consider the possibility of goods being delivered by couriers appointed through crowdsourcing. In this paper we focus on the setting of in-store customers delivering goods, ordered by online customers, on their way home. We assume that not all the proposed delivery tasks will necessarily be accepted, and use logistic regression to model the crowd agents’ willingness to undertake a delivery. This model is then used to build a novel compensation scheme that determines reward values, based on the current plan for the professional fleet’s routes and on the couriers’ probabilities of acceptance, by employing a direct search algorithm that seeks to minimise the expected cost.

Time Delay of Wide Area Damping Control in Urban Power Grid: Model-Based Analysis and Data-Driven Compensation

Due to the rapid development of economies, large urban cities consume an increasing amount of energy and have a higher requirement for power quality. Voltage source converter based high voltage direct current (VSC-HVDC) is a promising device to transmit clean power from remote regions to urban power systems, while also providing wide area damping control (WADC) for frequency stabilization. However, the time-delay naturally existing in the VSC-HVDC system may degrade the performance of WADC and even result in instability. To address this issue, this paper develops a time-delay correction control strategy for VSC-HVDC damping control in urban power grids. First, a small signal model of WADC is built to analyze the negative impacts of time delay. Then, a data-driven approach is proposed to compensate for the inherent time delay in VSC-HVDC damping control. The extensive training data will be generated under various disturbances. After offline training, the long short-term memory network (LSTM) can be implemented online to predict the actual frequency deviation based on real-time measurements. Finally, the proposed method is validated through MATLAB-Simulink in a two-area four-machine system. The results indicate that the data-driven compensation has a strong generalization ability for random delay time constants and can improve the performance of WADC significantly.

A Signal Compensation-Based Robust Swing-Up and Balance Control Method for the Pendubot

This article proposes a novel robust swing-up and balance control method using data-driven compensation signals for the Pendubot system, which is underactuated and subject to dynamic friction, backlash, and modeling uncertainty. The method involves three major developments. First, the uncertainty of the system is described by a previous sampled unknown nonlinear term and its changing rate. Compensation signals are then designed to eliminate the influence of the previous sampled unknown nonlinear term and its changing rate on the outputs of the controlled plant. Second, based on the Lyapunov stability theory, a robust swing-up control method is proposed. Third, in order to eliminate the limit cycle phenomenon caused by the uncertainty near the unstable equilibrium point, a proportional-derivative balance controller based on compensation signals is proposed. The stability and tracking error analysis show that the compensation signals can effectively eliminate the influence of dynamic friction, backlash, and modeling uncertainty on the system. Experimental results verify the effectiveness of the proposed method by showing significant improvements in production rate, accuracy, and cost.

Development of a Real-Time, Mobile Nitrate Monitoring Station for High-Frequency Data Collection

A mobile monitoring station was developed to measure nitrate and physicochemical water quality parameters remotely, in real-time, and at very high frequencies (thirty minutes). Several calibration experiments were performed to validate the outputs of a real-time nutrient sensor, which can be affected by optical interferences such as turbidity, pH, temperature and salinity. Whilst most of these proved to play a minor role, a data-driven compensation model was developed to account for turbidity interferences. The reliability of real-time optical sensors has been questioned previously; however, this study has shown that following compensation, the readings can be more accurate than traditional laboratory-based equipment. In addition, significant benefits are offered by monitoring waterways at high frequencies, due to rapid changes in analyte concentrations over short time periods. This, combined with the versatility of the mobile station, provides opportunities for several beneficial monitoring applications, such as of fertiliser runoff in agricultural areas in rural regions, aquaculture runoff, and waterways in environmentally sensitive areas such as the Great Barrier Reef.

Data-Driven Compensation for Bulk Formed Parts Based on Material Point Tracking

Currently, common inefficient trial-and-error procedures are used in designing bulk forming dies. Numerous iterations, consisting of numerical simulations and subsequent real tests, are needed to achieve accurate parts. During the compensation cycles, manual redesign in CAD environments is necessary to transform discrete data into parametric descriptions causing approximation errors. Automation of these surface reconstruction processes is barely possible. To address these issues, different data-driven numerical strategies have been deduced based on either displacement or force. In this work, a material point tracking method in forming simulation between die and part geometry is presented. Based on this, enhanced displacement-based and stress-based methods for compensation of bulk forming parts are compared. The convergence behavior of both methods is analyzed with respect to the compensation factor. Finally, the material point tracking approach is validated and verified by compensating a two-dimensional bulk-formed component.

Hybrid modeling scheme for PM concentration prediction of electrostatic precipitators

A hybrid modeling scheme for electrostatic precipitators (ESPs) integrating particulate matter (PM) removal mechanism and the data-driven compensation method is presented in this article. The structure of the training and coupling method for the mechanism model, which considers electrodynamics, including corona discharging, particle charging, and removal, and the data-driven method that was trained based on operation data to compensate for the distortion and flaw of the mechanism model was constructed. Design parameters and operation data of an ESP in a coal-fired power plant were collected for model training, and prediction performances were compared. Different combinations of correction factors, including exponential, proportional, and bias, were studied. The form with the highest prediction R2 of 0.889 on the training set and 0.867 on the validation set was chosen as the mechanism part of the model. Deep neural networks with the highest R2 of 0.885 on the training set and 0.857 on the validation set were also trained as a comparison group. The performance of the hybrid model achieved a R2 of 0.933 on the training set and 0.887 on the validation set and outperformed the mechanism and data-driven models, thereby indicating that the hybrid modeling method could enhance prediction performance while maintaining the generalization capability of the PM removal mechanism in ESP.

Data-Driven PID Controller and Its Application to Pulp Neutralization Process

The pulp neutralization process is a complex industrial process with strong nonlinearity and time-varying dynamics. In general, this kind of process is hardly controlled by using traditional control techniques such as the proportional-integral-derivative (PID) controller. To resolve this problem, a novel PID control scheme is proposed by integrating a data-driven compensation of unmodeled dynamics and a multistep ahead of optimal control strategy. Essential difference from the classical PID controller lies in the use of unmodeled dynamics, the measured data from the pulp neutralization process is used directly for building the nonlinear PID controller, which plays an important role in control system design. Based on multistep ahead prediction optimal control theory, the controller parameters can be obtained through optimizing a cost function. Some theoretical results on the stability and convergence of the closed-loop system are established. To demonstrate the effectiveness of the proposed control techniques, a simulation model and a cobalt nickel hydroxide pulp neutralization process are employed. Simulations were carried out using data extracted from an actual pulp neutralization process, followed by some industrial experiments. Results from both simulations and experiments indicate that our proposed controller can effectively control the pH value of the pulp neutralization process with promising control performance.

Data-driven compensation method for sensor drift faults in digital PID systems with unknown dynamics

This paper investigates the problem of compensating for the slow-changing sensor drift failures occurring in digital PID systems with unknown dynamics. It is extremely difficult to ensure the tracking performance of the faulty systems, due to the system models unavailable, the measurements corrupted by the faults, and the impact of the sensor failures propagated under feedback control. Therefore, the existing data-driven fault-tolerant control (FTC) methods are not capable of dealing with the above problem. Contrary to the current state-of-the-art, a novel residual generator structure is devised. Furthermore, its data-driven realization is accomplished, along with the convergence analysis of the proposed closed-loop recursive identification algorithm. On this basis, such failures can be estimated continuously from the residual signals, using an iterative estimation procedure, the convergence of whose mean-square estimation error is theoretically proven. As a result, the effect of the aforementioned failures on the tracking properties is eliminated with the aid of a fault detection mechanism and based on the tracking error signal corrected with the estimated faults. Finally, the effectiveness and merits of the resultant data-driven FTC algorithm are validated by the continuous stirred tank heater benchmark process.

Nonparametric statistical learning control of robot manipulators for trajectory or contour tracking

This paper presents a method of precision tracking control for industrial robot manipulators. For robotic laser and plasma cutting tasks, the required tracking performance is much more demanding than that for material handling, spot welding, and machine tending tasks. Challenges in control come from the nonlinear coupled multi-body dynamics of robot manipulators, as well as the transmission error in the geared joints. The proposed method features data-driven iterative compensation of torque and motor reference. Motor side tracking and transmission error are handled by separate learning modules in a two-part compensation structure. Depending on the specific setup of end-effector sensing, the method can utilize either timed trajectory measurement or untimed two-dimensional contour inspection. Nonparametric statistical learning is used for the compensation. Considerations on incorporating analytical models and selecting data subsets for more efficient learning are discussed. The method is validated using a six-axis industrial robot. HighlightsA control method of robot manipulators for precision trajectory or contour tracking is presented.Nonparametric statistical learning is used for data-driven compensation of both torque and motor reference.A two-part compensation structure is adopted to handle motor side tracking and transmission error.The compensation can be done using either timed trajectory measurement or untimed contour inspection.

An integrated prediction model of cobalt ion concentration based on oxidation–reduction potential

Cobalt removal is an important step in zinc hydrometallurgy, in which by adding zinc dust and catalyzer, cobalt ion is gradually removed. Reasonable operation of cobalt removal process requires online detection of cobalt ion concentration, which indicates the current state of cobalt removal. The aim of this paper is to build a model capable of predicting cobalt ion concentration online. A kinetic model was built based on a mechanism study. ORP (oxidation–reduction potential), which can be detected online, was introduced into the kinetic model by applying the kinetics of electrode reaction. The kinetic model shows satisfying tracking ability but limited accuracy. To overcome the limitation in accuracy, a data-driven compensation method was proposed and integrated with the kinetic model. Test results show that the proposed integrated model can provide an accurate prediction of outlet cobalt ion concentration in time.

Data-Driven Compensation for Flow Cytometry of Solid Tissues

Propidium Iodide is a fluorochrome that is used to measure the DNA content of individual cells, taken from solid tissues, with a flow cytometer. Compensation for spectral cross-over of this fluorochrome still leads to compensation results that are depending on operator experience. We present a data-driven compensation (DDC) algorithm that is designed to automatically compensate combined DNA phenotype flow cytometry acquisitions. The generated compensation values of the DDC algorithm are validated by comparison with manually determined compensation values. The results show that (1) compensation of two-color flow cytometry leads to comparable results using either manual compensation or the DDC method; (2) DDC can calculate sample-specific compensation trace lines; (3) the effects of two different approaches to calculate compensation values can be visualized within one sample. We conclude that the DDC algorithm contributes to the standardization of compensation for spectral cross-over in flow cytometry of solid tissues.