External Error Research Articles

Quantitative simulation and validation of energy carbon emission efficiency changes in Chinese urban agglomerations

In the context of the global energy dilemma, enhancing energy efficiency has inevitably become a pivotal strategy for mitigating energy waste and promoting sustainable development. Urban agglomerations, as growth poles leading high-quality regional economic development, play a significant role in this process. Within these urban agglomerations, the aggregation of various factors and the substitution of energy resources substantially influence the energy carbon emission efficiency (ECEE) of surrounding cities during their development and maturation phases. This study initially employs a three-stage Data Envelopment Analysis (DEA) to quantitatively analyze the ECEE values of 19 urban agglomerations from 2006 to 2020. It then establishes a methodology for calculating the joint intensity (JI) and joint threshold (JT) of ECEE within these urban agglomerations. Finally, a validation process is executed using MATLAB simulation and verification methodology to fit and authenticate the evolutionary patterns of ECEE in Chinese urban agglomerations. The primary objective of this research is to model the evolution of ECEE, thereby exploring the sustainable development pathways for urban agglomerations in China. The research findings indicate that: (1) The results from the three-stage DEA demonstrate that, after removing the influences of external environmental factors and random errors, the comprehensive technical efficiency (TE) of energy carbon emissions for the 19 urban agglomerations in China experienced a wave-like increase, rising from 0.410 to 0.506 between 2006 and 2020. (2) The calculation results of the constructed JI model indicate that the JT values of ECEE for national-level, regional-level, and local-level urban agglomerations are 1006.92, 226.60, and 160.14, respectively. The national-level urban agglomerations have significantly higher JT values and JI than the other two levels of urban agglomerations. (3) The results of the Matlab simulation verification show that 16 urban agglomerations fit well with the wave-like ascending evolutionary pattern. However, four urban agglomerations exhibit an opposite fitting effect due to the influence of their pillar industries or the small number of cities within these accumulations, making them unrepresentative. Consequently, the evolutionary curve of ECEE in Chinese urban agglomerations generally exhibits a wave-like upward trend over time.

Development of a model of the process of development of manufacturing defects in automation means

In automated process control systems, automation equipment (sensors, converters, amplifiers, etc.) with technical defects arising during their manufacture, which are one of the main causes of failures, is widely used. The paper establishes the possibility of using the laws of nonequilibrium thermodynamics as the basis for determining the relationship between the controlled parameters of automation equipment and the parameters of the displayed medium, which made it possible to build a deterministic model of the development of production defects and, ultimately, determine the directions for changing and adjusting the technological processes of production of automation equipment. A method has been developed for implementing a guaranteed forecast of changes in the parameters of automation equipment based on solving the evolution equation using optimal filtering algorithms, which is the subject of research. The purpose of the work is to improve the quality and reliability of automation equipment by improving the monitoring of defects arising in the production of instruments, functional units and sensors of automation equipment. The article solves the following problems: analysis of existing approaches to the problem of manufacturing defects and methods for their detection and setting a research task; modeling of the process of development of production defects causing changes in the technical condition of automation equipment; development of a decision-making method based on guaranteed prediction of the technical state of automation equipment. The methodology of work is based on the methods of thermodynamic description of the kinetics of processes (when developing a model of the process of development of production defects that cause a change in technical condition) and methods of assessment and forecasting based on optimal filtering algorithms (when developing a decision-making method based on guaranteed foresight of technical condition). The results of the work include a model of the process of development of manufacturing defects that cause a change in the technical condition of automation equipment, and a decision-making method based on a guaranteed forecast of the technical condition of automation equipment. Conclusions. The paper establishes the possibility of using the laws of nonequilibrium thermodynamics to determine the relationship between the controlled parameters of automation equipment and the displayed medium, and to build a deterministic thermodynamic model of the development of production defects. Disclosed is an equation of evolution of technical state of automation equipment based on a deterministic kinetic model of processes occurring in a multicomponent medium, and an observation model which takes into account errors caused by instability of external effects and measurement errors. Disclosed is a method of implementing a guaranteed forecast of change in parameters of automation equipment based on solving the evolution equation using optimal filtering algorithms, which are used to solve estimation and prediction problems.

A seafarers’ cognitive error mining model based on IDA and TRACEr and mitigation measures for ship collision accidents

Human factor is the main cause of maritime accidents. However, the in-depth study on the mechanism of cognitive errors in seafarers’ human error needs to be supplemented. This study empirically analyzes 116 collision cargo ships along the Yangtze River trunk line. To explore the relationship between seafarers’ task errors and the cognitive process of accidents, a seafarers’ cognitive error mining model is proposed, which integrates the Information, Decision, and Action (IDA) cognitive model into the Technique for the Retrospective and Predictive Analysis of Cognitive Errors (TRACEr). According to the approach of mining from the outside to the inside, firstly, the error mode in the cognitive stage of seafarer tasks are identified. Then the fine-grained main manifestation of the task errors is mined by K-means, and Apriori algorithm is employed to mine the hidden features between the external and internal error modes. The results show that there are four main problems of Yangtze River ship accidents, and seafarers have four to seven corresponding causal chains from psychological error mechanism to performance shaping factors for each major issue in the cognitive stage. On the basis of the results, this study summarizes the guiding principles of accident prevention and seafarer management measures to provide decision support for water traffic safety.

Adaptive Nonsingular Fast Terminal Sliding Mode Control for Shape Memory Alloy Actuated System

Due to its high power-to-weight ratio, low weight, and silent operation, shape memory alloy (SMA) is widely used as a muscle-like soft actuator in intelligent bionic robot systems. However, hysteresis nonlinearity and multi-valued mapping behavior can severely impact trajectory tracking accuracy. This paper proposes an adaptive nonsingular fast terminal sliding mode control (ANFTSMC) scheme aimed at enhancing position tracking performance in SMA-actuated systems by addressing hysteresis nonlinearity, uncertain dynamics, and external disturbances. Firstly, a simplified third-order actuator model is developed and a variable gain extended state observer (VGESO) is employed to estimate unmodeled dynamics and external disturbances within finite time. Secondly, a novel nonsingular fast terminal sliding mode control (NFTSMC) law is designed to overcome singularity issues, reduce chattering, and guarantee finite-time convergence of the system states. Finally, the ANFTSMC scheme, integrating NFTSMC with VGESO, is proposed to achieve precise position tracking for the prosthetic hand. The convergence of the closed-loop control system is validated using Lyapunov’s stability theory. Experimental results demonstrate that the external pulse disturbance error of ANFTSMC is 8.19°, compared to 19.21° for the comparative method. Furthermore, the maximum absolute error for ANFTSMC is 0.63°, whereas the comparative method shows a maximum absolute error of 1.03°. These results underscore the superior performance of the proposed ANFTSMC algorithm.

Fuzzy PI vibration suppression control strategy for space double flexible telescopic manipulator with fractional disturbance observer

The space double flexible telescopic manipulator (SDFTM) with time-varying length, is called the space flexible manipulator and can carry out reciprocating linear telescopic motion along its axis. It possesses characteristics such as lightweight flexibility, small space occupation, large turning radius, and a wide working range. These features can assist astronauts in performing complex tasks in dangerous outer space environments and offer broad application prospects. However, due to the highly nonlinear and time-varying length characteristics of the space flexible manipulator, its dynamic modeling becomes more complex and challenging. Moreover, during the rotation of the space flexible manipulator, its inherent flexible behavior can trigger vibration phenomena, significantly impacting the execution accuracy of on-orbit tasks. Therefore, proposing control methods to address vibration issues is an effective approach. Thus, achieving stable and precise operation of the space flexible manipulator necessitates the precise establishment of its dynamic model and the development of high-precision control algorithms, which have become key research directions. Firstly, a time-varying dynamic modeling method of the space manipulator is proposed by combining the Lagrange principle and flexible beam vibration theory. Unlike the traditional method, which only considers the limit length of the space manipulator under static conditions, the dynamic process of the space manipulator presented during actual operation is fully considered, which greatly improves the modeling accuracy. Then, a time-varying model based on the fuzzy PI real-time control strategy (FD-FZPI) with fractional order disturbance observer (FO-DOB) is proposed. Based on the robust stability principle, a more accurate FO-DOB is proposed based on integer order DOB, coupled with a fuzzy PI controller to compensate for the external disturbance and modeling error of the space manipulator. Finally, numerical simulation analysis is carried out, and the results show that the average parameter difference between the time-varying dynamic model and the static dynamic model can reach about 5.2 %, which indicates the accuracy of the proposed dynamic modeling method. At the same time, the proposed FD-FZPI control strategy achieves about 14.6 % performance improvement over the traditional DOB-PI control method, indicating that the proposed control strategy can effectively suppress the flutter fluctuation of the space manipulator and achieve accurate and stable dynamic tracking.

Pilot protection based on the similarity of the traveling waves between the quadratic fitting curve and the calculated curve for the All-DC wind power transmission system

The All-DC wind power generation system can effectively solve the harmonic resonance problem caused by large-scale wind power AC collection and transmission, gradually becoming a hot topic in future research. However, there are few studies on the relay protection of the All-DC wind power transmission systems. In the All-DC wind power systems, there are differences in topology, control strategies, fault characteristics, boundary characteristics, etc. At the same time, existing pilot protection has problems such as strict information synchronization requirements and selection of setting values through simulation. Therefore, the proposed pilot protection based on the similarity of the traveling wave between the quadratic fitting curve and the calculated curve for the All-DC wind power system transmission lines. Firstly, the difference of the 1-mode initial current waveform characteristics is analyzed in the time domain at both ends. Then, the least squares method is introduced to fit the differential curves of the current forward and backward traveling waves at two terminals. The differential characteristics of the differences between the fitted curve, the calculated curve, and the measured curve under the influence of internal and external errors are analyzed. Finally, the calculated value of traveling wave current during external metallicity fault is used as the standard. By comparing the fitting curve of current traveling waves and the difference in the calculation curve to distinguish internal faults from external faults. The simulation results show that the proposed protection principle can fault resistance of 2200 Ω and noise interference of 20 dB. In addition, the proposed method does not require strict data synchronization, higher sampling frequency, and setting value through simulation.

Robust Fixed-Time Adaptive Fault-Tolerant Control for Dynamic Positioning of Ships with Thruster Faults

The ship dynamic positioning system has long been a subject of great interest due to the intricate and unpredictable nature of the maritime environment, which affects its dependability and timeliness. This study focuses on the issue of developing a robust, efficient, and adaptable fault-tolerant control system for ship dynamic positioning systems that experience thruster malfunctions. Firstly, we build the motion model of the ship’s dynamic positioning system with three degrees of freedom, as well as the model for faults in the thruster. A second-order fast fixed-time nonsingular sliding mode surface is formulated, and a robust adaptive control technique is introduced to counteract external environmental disturbances and model errors. The objective is to ensure rapid convergence of the system within a predetermined time frame. Simultaneously, combined with the fault-tolerant control technique, it is ensured that the dynamic positioning ship can still achieve system stability when thruster faults occur. In addition, the analysis of the Lyapunov stability criterion proves that the proposed fixed-time adaptive fault-tolerant control scheme can make the system tracking error converge within a fixed time. Finally, the effectiveness of the proposed control scheme is verified by numerical simulation results.

Deep reinforcement learning attitude control of stabilized platform for rotary steerable system based on extended state observer

A Deep Deterministic Policy Gradient with Extended State Observer (DDPG_ESO) method is proposed to address control accuracy and robustness issues in the attitude control of stabilized platforms for rotary steerable systems. A nonlinear extended state observer is developed to estimate the total system disturbance, which is then integrated into a deep reinforcement learning framework to enhance the controller’s adaptive capabilities. The controller is trained using variable amplitude and frequency external disturbances to improve its ability to suppress these disturbances. The superiority of the DDPG_ESO controller is validated through simulation experiments, demonstrating rapid tracking of toolface angles, reduced overshoot, and maintained steady-state errors. Compared to Proportional Integral Derivative (PID), Active Disturbance Rejection Control (ADRC), and Deep Deterministic Policy Gradient (DDPG) controllers, the DDPG_ESO algorithm exhibits higher robustness and adaptability under varying operational conditions, effectively mitigating the impact of external disturbances and modeling errors. The results indicate potential for practical application in the drilling industry

What explains the operational efficiency of listed commercial banks in China? Evidence from a three-stage DEA-tobit modeling analysis

Based on the actual situation of listed commercial banks in China, this study utilizes a three-stage DEA model to eliminate external macro-environmental factors and random error factors. As a result, the study objectively measures the true efficiency values of 42 listed commercial banks in China from 2015 to 2021. On this basis, a Tobit model is constructed to analyze the micro-level factors influencing the operational efficiency of listed commercial banks in China.Empirical research shows that the operational efficiency values in the first stage are significantly lower than those in the third stage. Analyzing the proportion of banks with an efficiency value of 1, it is found that state-owned banks and joint-stock banks account for a large proportion. The proportion of city commercial banks decreases significantly, while agricultural banks and commercial banks have the lowest proportion. In addition, the Tobit regression results show that bank size, innovation level, profitability, and development capacity have a significant positive impact on the operational efficiency of listed commercial banks in China at the current stage. Based on the above empirical results and analysis, specific measures are proposed to improve the operational efficiency of listed commercial banks in China.Based on the above empirical results and analysis, the study finally suggests the following specific measures to enhance the operational efficiency of listed commercial banks in China: 1. Strengthening technological investment to achieve diversified operations and cultivate new niche markets; 2. Emphasizing intermediate business income to enhance market competitiveness; 3. Undertaking digital transformation and upgrading to improve sustainable profitability.

A High-Gain Observer Approach to Robust Trajectory Estimation and Tracking for a Multi-Rotor Uav

Abstract Using the context of trajectory estimation and tracking for multi-rotor UAVs, we explore the challenges in applying high-gain observers to highly dynamic systems. The multi- rotor will operate in the presence of external disturbances and modeling errors. At the same time, the reference trajectory is unknown and generated from a reference system with unknown or partially known dynamics. We assume the only measurements that are available are the position and orientation of the multi-rotor and the position of the reference sys- tem. We adopt an extended high-gain observer (EHGO) estimation framework to estimate the unmeasured multi-rotor states, modeling errors, external disturbances, and the reference trajectory. We design a robust output feedback con- troller for trajectory tracking that comprises a feedback linearizing controller and the EHGO. The proposed control method is rigorously analyzed to establish its stability properties. Finally, we illustrate our theoretical results through numerical simulation and experimental validation in which a multi-rotor tracks a moving ground vehicle with an unknown trajectory and dynamics and successfully lands on the vehicle while in motion.

Differential privacy for diffusion LMS algorithm over a distributed network

This article presents a way to improve the Diffusion LMS algorithm in practical scenarios while maintaining data privacy. It focuses on reducing external errors and ensuring accurate estimation of the parameter vector through distributed and adaptive privacy protection. By combining these improvements, the overall performance of the algorithm can be significantly enhanced without compromising Mean Square Deviation (MSD). One important aspect is tuning the privacy noise power based on data sensitivity. This work provides a novel solution for improving the performance and privacy of the Diffusion LMS algorithm with implications for future research. The mean square error and evolution behavior of the algorithms are also analyzed, showing their effectiveness and robustness in preserving privacy and MSD over the network.

Active suspension hierarchical control with parameter uncertainty and external disturbance of electro-hydraulic actuators

In order to improve the ride comfort and handling stability of the electro-hydraulic active suspension system, a hierarchical control strategy is proposed. For the active suspension system with body mass uncertainty and safety constraints, an enhanced constraint adaptive backstepping controller is designed to generate the target force of body vertical motion. When dealing with constraints, nonlinear filters are introduced, backstepping technology and quadratic Lyapunov function are used to combine the control target and domain constraints, and the vertical displacement of the body and the suspension deflection control index are synthesized into a single controlled variable, so that the control variable converging to zero meets the suspension dynamic displacement limit. The ride comfort and safety of the active suspension system are improved. Secondly, stability analysis is conducted on the zero dynamic error system to ensure that all safety performance indicators are bounded. The effects of external disturbances, parameter uncertainties and modelling errors on the force tracking accuracy of asymmetric cylinder electrohydraulic systems are addressed. A backstepping dynamic surface control method based on a nonlinear perturbation observer is proposed, which estimates the composite perturbation terms such as modelling error and external perturbation, and uses the estimated value of the nonlinear observer to design a feedforward compensating control term to offset the effect of the composite perturbation on the system performance. In addition, the dynamic surface control method is used to calculate the derivative of the target force input, which avoids the derivative explosion phenomenon and reduces the computational complexity of the system. Simulation test results show that this method reduces the computational complexity of the system and improves the control performance. And under random and bumpy road conditions, the root-mean-square value of sprung mass acceleration performance index is reduced by 48.354 % and 72.677 % compared with passive suspension, which improves the ride comfort of the vehicle.

Trajectory tracking control of the pushing ore truck manipulator based on adaptive sliding mode control with interference observer

An improved sliding mode controller was designed to solve the problem of low tracking accuracy caused by various disturbances and errors existing in the hydraulic-driven manipulator for pushing ore truck. The state space equation of the hydraulic system of the pushing ore truck manipulator was modeled and derived, and a sliding mode function was designed. For interference signals, use interference observers for observation. For the unobserved parts, adaptive laws are used for compensation to reduce system chattering, and system’s stability is verified using Lyapunov functions. The simulation results show that, compared with the traditional Sliding mode control and adaptive sliding mode control, the adaptive sliding mode control strategy based on interference observer proposed in this paper can effectively weaken the system chattering, reduce the uncertainty caused by external interference and modeling error, and improve the trajectory tracking accuracy of the pushing ore truck manipulator.

Trajectory tracking of binocular vision system for picking robot based on fast non-singular terminal sliding mode control

This paper proposes a non-singular fast terminal sliding mode control method for a binocular active vision platform of a picking robot with unknown dynamics. The method uses radial basis function (RBF) neural networks to achieve trajectory tracking accuracy and enhance robustness against external interference. A non-singular fast terminal sliding mode controller is designed for the system’s convergence within a limited time. An adaptive neural network approximates the unknown nonlinear function of the dynamic model. Stability and finite-time convergence of the closed-loop system are established using Lyapunov theory. Experimental verification on the binocular vision platform demonstrates position and speed errors converging to the desired trajectory within 2 and 1 second, respectively. Moreover, when subjected to external interference, the position and velocity errors converge within 0.1 seconds. Simulation experiments confirm the method’s effectiveness in improving convergence speed, trajectory tracking accuracy, and robustness against external interference, while reducing system chattering.

Multiple‐missile fixed‐time integrated guidance and control design with multi‐stage interconnected observers under impact angle and input saturation constraints

AbstractIn this paper, a novel three‐dimensional fixed‐time integrated guidance and control (IGC) scheme with multi‐stage interconnected observers is proposed for cooperative attacks using multiple missiles against a maneuvering target under impact angle and input saturation constraints. External disturbances, modeling errors, and aerodynamic parameter variations are considered as system uncertainties and a three‐channel fully coupled IGC model for multiple missiles is established. The IGC system is designed optimally based on fixed‐time stability theory, sliding mode control, and the backstepping technique. Three inter‐cascaded fixed‐time disturbance observers based on an improved super‐twisting algorithm are designed to estimate and compensate for system uncertainties. Second‐order command filters are used to constrain virtual control signals, and additional filtering error subsystems are introduced to compensate for the tracking errors of filters. System stability and uniformly ultimately fixed‐time boundedness of all states are proven using the Lyapunov stability theory. Finally, the limits of the acceleration components of the maneuvering target perpendicular to the line of sight direction are derived. The effectiveness of the designed IGC scheme and the ability of multi‐stage interconnected observers to sense disturbances with each other are verified through simulations.

Evaluation of High-Frequency Measurement Errors from Turned Surface Topography Data Using Machine Learning Methods.

Manufacturing processes in industry applications are often controlled by the evaluation of surface topography. Topography, in its overall performance, includes form, waviness, and roughness. Methods of measurement of surface roughness can be roughly divided into tactile and contactless techniques. The latter ones are much faster but sensitive to external disturbances from the environment. One type of external source error, while the measurement of surface topography occurs, is a high-frequency noise. This noise originates from the vibration of the measuring system. In this study, the methods for reducing high-frequency errors from the results of contactless roughness measurements of turned surfaces were supported by machine learning methods. This research delves into optimizing filtration methods for surface topography measurements through the application of machine learning models, focusing on enhancing the accuracy of surface roughness assessments. By examining turned surfaces under specific machining conditions and employing a variety of digital filters, the study identifies the Gaussian regression filter and spline filter as the most effective methods at a 22.5 µm cut-off. Utilizing neural networks, support vector machines, and decision trees, the research demonstrates the superior performance of SVMs, achieving remarkable accuracy and sensitivity in predicting optimal filtration methods.

The Texas Creek landslide, southwestern British Columbia: new ages and implications for the culture history and geomorphology of the mid-Fraser River region

The Texas Creek rock avalanche is a prehistoric deposit in the Fraser River Canyon, 17 km south of Lillooet, southwestern British Columbia, Canada. Original mapping suggested that the debris consisted of two landslides: a 45 Mm3 event deposited after the Mazama tephra but before about 2 ka ago, and a 7.2 Mm3 event about 1.1 ka ago. The proposed timing of the younger landslide was correlated with a decline in the First Nations population and was proposed as an agent of cultural collapse driven by its impact on salmon returns vital to the population's sustenance. We provide six surface exposure ages using 10Be from boulder tops, with three samples from each surface that were originally posited to be older and younger debris. The six samples yielded similar ages suggesting the landslide deposit represents a single event with an average age of 2.28 ± 0.19 (2σ external error) ka before 1950 AD. Evidently, the landslide played no role in the cultural collapse. Fraser River Holocene incision rates, estimated pre- and post-landslide are between 13 and 24 mm/yr, consistent with previous estimates for the mid-Fraser River region. Landslide timing is coincident with the explosive eruption of Mount Meager, 120 km to the northwest, and with a possible landslide at Mystery Creek 85 km to the west and 65 km south of Mount Meager. The landslide may have been seismically triggered, but attribution is speculative.

Maintenance and control of coating baths: Rapid and simultaneous hypophosphite and phosphite determination in a Ni[sbnd]P deposition bath

In this work, a method based on UV–VIS spectrophotometry using the molybdenum blue reaction is described to monitor hypophosphite and phosphite levels in nickel electroless baths. Nickel is one of the most employed metals in the electroless coating industry and during the deposition process the metal is reduced from Ni (II) to Ni (0). Hypophosphite is a widely employed reducing agent, which is oxidized to phosphite. Therefore, the hypophosphite concentration should be monitored in order to replenish the bath while it is being consumed maintaining an optimum concentration in order to guarantee the desired coating. Phosphite, which could interfere with the coating process, must be monitored to ensure it does not exceed a certain concentration after which the bath stops working. Although iodometric titrations are the most commonly used methods to control hypophosphite and phosphite concentrations, these are time- and reagent-consuming. Thus, with the aim of developing a more appropriate methodology a colorimetric determination was carried out in this work. In certain conditions, the hypophosphite reacts with molybdenum, giving rise to a blue compound that can be measured between 390 and 1100 nm. The phosphite presence modifies the obtained spectra and that effect allows individual Partial Least Square (PLS) models to be built for each analyte. In this study, the calibration, cross-validation and external prediction relative error were always lower than 8 %, and the relative standard deviation lower than 12 %. The models were applied to real samples from two different nickel electroless baths, and the results were compared and validated using ion chromatography (IC). No significant differences were observed between the proposed and the reference methods for either of the two analytes. Therefore, the colorimetric method could be an improvement over the methods currently used for the control of the two anions in coating baths in term of saving time, money and reagents, making the coating process more efficient.

Unified Shape and External Load State Estimation for Continuum Robots.

Continuum robots navigate narrow, winding passageways while safely and compliantly interacting with their environments. Sensing the robot's shape under these conditions is often done indirectly, using a few coarsely distributed (e.g. strain or position) sensors combined with the robot's mechanics-based model. More recently, given high-fidelity shape data, external interaction loads along the robot have been estimated by solving an inverse problem on the mechanics model of the robot. In this paper, we argue that since shape and force are fundamentally coupled, they should be estimated simultaneously in a statistically principled approach. We accomplish this by applying continuous-time batch estimation directly to the arclength domain. A general continuum robot model serves as a statistical prior which is fused with discrete, noisy measurements taken along the robot's backbone. The result is a continuous posterior containing both shape and load functions of arclength, as well as their uncertainties. We first test the approach with a Cosserat rod, i.e. the underlying modeling framework that is the basis for a variety of continuum robots. We verify our approach numerically using distributed loads with various sensor combinations. Next, we experimentally validate shape and external load errors for highly concentrated force distributions (point loads). Finally, we apply the approach to a tendon-actuated continuum robot demonstrating applicability to more complex actuated robots.

Predictor-Based Neural Attitude Control of A Quadrotor With Disturbances

An attitude control issue is concerned for a quadrotor with external disturbances in this paper. For unknown system dynamics, predictor-based neural networks (NNs) are introduced, where prediction errors, angular velocities, are constructed, instead of tracking errors, for updating NNs' weights. This replacement reduces the occurrence of high-frequency oscillations in NNs' approximation. With this improved NNs, a predictorbased NN disturbance observer is then developed for compensation for external disturbances and NNs' approximation errors, and a normalization learning technique is employed for reduction of the number of learning parameters. A predictor-based neural attitude control strategy is proposed for a quadrotor with external disturbances. Furthermore, measurement noise are taken into account in our predictor-based neural attitude control strategy. The Lyapunov-based stability analysis shows that all closed-loop signals in the designed attitude system are semiglobally bounded. A numerical simulation and a hardware-in-loop experiment as well as outdoor flight verify the effectiveness of the proposed anti-disturbance attitude control strategy.