Load Identification Research Articles

Application of Machine Learning Algorithms in Real-Time Monitoring of Conveyor Belt Damage

This paper is devoted to the real-time monitoring of close transportation devices, namely, belt conveyors. It presents a novel measurement system based on the linear strain gauges placed on the tail pulley surface. These gauges enable the monitoring and continuous collection and processing of data related to the process. An initial assessment of the machine learning application to the load identification was made. Among the tested algorithms that utilized machine learning, some exhibited a classification accuracy as high as 100% when identifying the load placed on the moving belt. Similarly, identification of the preset damage was possible using machine learning algorithms, demonstrating the feasibility of the system for fault diagnosis and predictive maintenance.

Low-resource dynamic loading identification of nonlinear system using pretraining

To address the challenge of load identification in nonlinear systems, an audio neural network-based method called WaveNet is proposed that leverages its capability to capture long-term dependencies in mechanical systems, enabling accurate load identification. Unlike traditional dynamic load identification methods that often encounter difficulties with matrix solutions, this approach takes advantage of WaveNet’s capabilities, enhancing both accuracy and efficiency. We integrate pre-training and transfer learning techniques to address the data scarcity challenges often encountered in real-world engineering applications. By transferring features across distributed datasets, this method reduces the dependency on single-task data, thereby improving model robustness. The performance of the WaveNet method is rigorously evaluated against traditional benchmarks such as Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) benchmarks under random load conditions applied to a complex structural framework. The proposed method achieves a root mean squared error (RMSE) of 1.521 and a determination coefficient (R²) of 0.996 in the random load case, demonstrating superior accuracy compared to other approaches. Moreover, its applicability is verified through simulations of both impact load and harmonic load scenarios, showcasing the effectiveness of transfer learning in overcoming domain discrepancies. Finally, the method is tested in random experiments to validate its engineering applicability. The results highlight the significant accuracy improvement in low-resource tasks achieved through pre-training, showcasing the potential and value of the proposed method.

Research on improved dynamic load identification method based on Kalman filter under noise interference

As a mathematical approach for solving inverse problems, the dynamic load identification method is particularly useful when directly measuring the load acting on a structure is challenging. The Kalman filter (KF) algorithm is commonly employed for dynamic load identification. However, in practice, measurement noise can significantly affect the accuracy of the KF algorithm's results. In this study, we investigate the impact of response noise on the accuracy of load identification results using the KF algorithm. To eliminate the influence of measurement noise on identification accuracy, we propose an improved dynamic load identification method. This method incorporates adaptive techniques to assess varying levels of response noise and improve the load identification accuracy. Notably, this method is applicable in both physical and modal domains. We conduct numerical simulations using a 5-DOF system under different noise conditions. Compared to traditional dynamic load identification method based on KF algorithm, the improved method consistently achieves superior accuracy in load identification across various noise levels. Moreover, an experiment is conducted to further validate the feasibility of the proposed method. The results showed that the proposed method is effective and can achieve high-precision identification of unknown loads.

Accurate identification of moving vehicle loads on beam-like bridge structures integrating novel PCA-based dictionary with grouping and weighting strategy

Most moving load identification (MLI) methods incorporate the dictionary theory as a regularization technique to address the ill-posedness of the problem. However, the selection of atoms in the dictionary often inadequately represents the actual vehicle loads in existing methods, and the prior information from these atoms is disregarded in the subsequent MLI computations. Therefore, a novel MLI framework is proposed for beam-like bridge structures based on a novel dictionary derived from principal component analysis (PCA) and newly grouping and weighting strategy in this study. At first, a vehicle-bridge coupling system (VBCS) is established to obtain the interaction forces between the moving vehicles and bridge deck. The system matrices between the interaction forces and structural responses are derived in the time domain. The PCA technique is then employed to extract information from these interaction forces and to subsequently construct a PCA-based dictionary. Based on the eigenvalues of each principal component in the dictionary, a weighted group sparse model, incorporating the newly grouping and weighting strategy, is defined to obtain the coefficients of each atom. The solution to this model is obtained using the alternating direction method (ADM). Finally, the proposed method is validated in numerical simulations comparing with some existing methods. The effects of noise levels, road surface roughness, number of training data, response combinations and the tolerances in ADM were also studied. Similarity law for the VBCS is conducted in experimental verifications to construct the PCA-based dictionary, allowing for a reasonable identification of gross vehicle weights. The results indicate that the MLI accuracy has been enhanced by the proposed method, and the similarity law employed in experiments is reasonable. Settingthe tolerance in ADM as ε = 1 × 10−5 can lead to a higher accuracy and reduce the computation cost in both numerical simulations and experimental verifications.

Typical Scenario Load Identification Based on Feature Fusion and Transfer Learning

Background: The electricity demand is continuously increasing. However, various institutions, enterprises, and individuals exhibit many irregularities in their electricity usage, leading to significant wastage of electricity. To achieve effective energy management, researchers are attempting to analyze and regulate users' electricity demands by monitoring their load usage through Non- Intrusive Load Monitoring (NILM) technology. The accuracy of load identification in this technology will greatly impact the results of load monitoring. Although there are currently many articles and patents related to NILM, they utilize a large amount of computational resources and require high sampling rates from devices, yet the results are still unsatisfactory. Therefore, it is necessary to improve the accuracy of load identification in data with relatively low sampling frequencies. Objective: To improve the accuracy of load identification with low sampling frequency data, this paper proposes a typical scenario load identification method based on feature fusion and transfer learning. Methods: This method adopts the fusion of current and power factor angles to provide abundant identification information for NILM, effectively reducing the situation of single-feature overlap of different loads. By inputting the fused feature data into GoogLeNet and utilizing transfer learning for training, not only is the accuracy improved, but also the training time and the requirement for the sampling rate of training data are greatly reduced. In addition, selecting typical scenario loads can monitor loads in a targeted manner, reduce the waste of computing resources caused by irrelevant loads, and more effectively guide electricity usage strategies. Results: The proposed load identification method was tested on the low sampling frequency dataset used in this paper. It achieved an overall load identification accuracy of 94.61% across three scenarios, improving accuracy by 3% to 7% compared to other models. Conclusion: The simulation results indicate that this method achieves high load identification accuracy at low sampling frequencies. It also exhibits good generalization ability. This method not only reduces the performance requirements for monitoring equipment but also enhances monitoring efficiency.

Non-intrusive identification of building loads using EDCA-ShuffleNetV2 with fused feature visualization

Abstract Non-intrusive load monitoring (NILM) enables monitoring of appliance operation status and energy consumption without additional meters, providing innovative data support for energy management. However, current NILM systems still face challenges such as insufficient load feature information and low load identification accuracy. To utilize the load feature information and improve the accuracy of load identification more effectively, this paper first selects loads with high energy consumption and high usage frequency as the research object, makes full use of the load feature information through feature fusion, and converts the fused typical load data into an image through the Gramian summation angular field, and further carries out the identification of loads that still have similarity after feature fusion. Secondly, this paper improves the ShuffleNetV2 model structure by embedding an efficient dual-channel attention (EDCA) module in the basic feature extraction module of ShuffleNetV2 to enhance it to extract adequate load feature information. A residual structure is also introduced to mitigate the information loss and gradient disappearance issues of the model. Finally, the superiority and effectiveness of the fused load features and the proposed model in load identification and typical scenario applications are validated using the iAWE and AMPDS datasets.

Ride comfort assessment of road vehicles on a long-span truss girder suspension bridge under crosswinds

The precise identification of the aerodynamic loads on vehicles is a fundamental concern in assessing the ride comfort of vehicles crossing long-span bridges in the presence of strong crosswinds. However, the consideration of aerodynamic interference between vehicles and truss girder bridges is limited in existing studies. Furthermore, in practical engineering, wind barriers are commonly installed to enhance the ride comfort of vehicles crossing long-span bridges, but previous studies have primarily focused on the impact of wind barriers on the aerodynamic coefficients and dynamic responses of vehicles. This paper focuses on the aerodynamic interaction between trucks and truss girder bridges, through wind tunnel testing. The aerodynamic coefficients of the vehicle with three different ventilation ratios and four different heights of wind barriers were obtained. The dynamic response of road vehicles on a truss girder suspension bridge with a main span of 965 m was numerically calculated using the coupled analysis of wind-vehicle-bridge system and measured aerodynamic coefficients considering aerodynamic interference. On this basis, the comfort of road vehicles was investigated with different section types of the girder and different wind barrier parameters, and it was evaluated accordance with the overall vibration total value (OVTV) recommended in the ISO 2631–1. It is found that the aerodynamic coefficients of road vehicles are sensitive to the type of wind barrier. Wind barriers can reduce the road vehicle’s aerodynamic loads at high wind yaw angles. Wind barriers can also improve the ride comfort of road vehicles on the long-span truss girder suspension bridge.

Intelligent aerodynamic identification method based on wavelet transform and deep learning

Abstract Wind tunnel force testing is particularly crucial for the aerodynamic characteristics of hypersonic vehicles, and the intelligent and high-precision aerodynamic identification technology serves as the key supporting technology. Due to the short effective test time of the pulse combustion wind tunnel, the inertial force vibration generated by the force measurement system is difficult to be attenuated completely at the start of the wind tunnel. At the same time, there are many interference signals in the output signal during the test, which makes it difficult to achieve high-precision aerodynamic load identification. Therefore, in order to eliminate the influence of interference signals on aerodynamic identification accuracy and obtain accurate aerodynamic loads, this paper introduces an intelligent aerodynamic identification method based on wavelet transform and deep learning. Firstly, meyer wavelet is selected as the wavelet basis, and signal processing is performed on the output signal through wavelet transform to eliminate interference signals and improve signal quality. Then, through RNN-GRU network model to identify the load. The reliability of the method is verified by the rod balance test platform. The results show that the method can effectively reduce the influence of interference signal, and the relative error between the identified load and the real load is about 2%. At the same time, the identification results of the method are compared with those of the mean value method, which further verifies the accuracy of the proposed method.

A distributed dynamic load identification approach for thin plates based on inverse Finite Element Method and radial basis function fitting via strain response

Dynamic load identification is crucial for structural design and health monitoring. Traditional methods for distributed dynamic loads (DDLs) typically involve establishing a transfer matrix, which often leads to ill-posed problems. In this paper, a novel method based on the inverse Finite Element Method (iFEM) and radial basis function (RBF) fitting was proposed to identify DDLs from measured strain responses. The method begins with the reconstruction of the displacement field from discrete strain data using iFEM, followed by applying RBF fitting to obtain a continuous displacement field. To enhance the performance of the RBF fitting, a constrained matrix for force boundary conditions is introduced, along with a selection rule for the RBF shape parameter. The identified loads are subsequently determined by incorporating the well-fitted RBFs into the motion equations of thin plates. This approach eliminates the need for a transfer matrix, thereby avoiding ill-posedness, and enables the simultaneous identification of the spatial distribution and time history of the loads. Three numerical examples for the identification of concentrated loads, uniformly distributed loads, and globally distributed loads demonstrate the method's effectiveness, accuracy, and noise resistance, with additional validation provided through a comparison with the classic time-domain method.

Identification of equivalent wind and wave loads for monopile-supported offshore wind turbines in operating condition

Wind and wave loads are critical to monopile-supported offshore wind turbines (OWTs) in determining whether OWTs are in safe conditions to generate electricity. However, these random and complex loads vary with time and location, and are difficult to measure directly. Theoretically, the loads can be identified based on structural responses. Nevertheless, it is challenging due to the complexity of external loads and the existence of harmonic loads generated by rotor rotation. This study proposes a new load identification framework using a limited amount of monitoring data to estimate the equivalent wind and wave loads of OWTs simultaneously. Both loads are modeled as Gaussian processes with exponential covariance function and incorporated into the augmented state-space model. Kalman filter is employed to identify the equivalent loads. The effectiveness and accuracy of the proposed method were validated based on a numerical OWT model and a scaled OWT test model. The results demonstrate that the framework can successfully identify equivalent wind and wave loads of OWTs in both parked and operating conditions. The probability distribution of identified load data is consistent with actual load data, with an error of less than 9.1 %. The proposed framework can find vast applications in operational management for OWTs.

An Interval Neural Network Method for Identifying Static Concentrated Loads in a Population of Structures

During the design and validation of structural engineering, the focus is on a population of similar structures, not just one. These structures face uncertainties from external environments and internal configurations, causing variability in responses under the same load. Identifying the real load from these dispersed responses is a significant challenge. This paper proposes an interval neural network (INN) method for identifying static concentrated loads, where the network parameters are internalized to create a new INN architecture. Additionally, the paper introduces an improved interval prediction quality loss function indicator named coverage and mean square criterion (CMSC), which balances the interval coverage rate and interval width of the identified load, ensuring that the median of the recognition interval is closer to the real load. The efficiency of the proposed method is assessed through three examples and validated through comparative research against other loss functions. Our research findings indicate that this approach enhances the interval accuracy, robustness, and generalization of load identification. This improvement is evident even when faced with challenges such as limited training data and significant noise interference.

IDENTIFICATION OF AN ARBITRARY MOVING AXISYMMETRIC LOAD ACTING ON A CYLINDRICAL SHELL

Various types of external non-stationary loads can act on various structural elements and cylindrical shells of finite length in particular distributed and concentrated, stationary and moving load. When using various external load identification methods, the type of external load is usually known. In prac- tice this is not always the case. The purpose of the study is to develop a method for identifying an arbitrary axisymmetric load acting on an elastic cy- lindrical shell of finite length, which can be used to identify a moving load. To model the non-stationary load of a cylindrical shell, a system of differ- ential equations of the refined Timoshenko theory for medium thickness shells was used. The solution to this system of differential equations is ob- tained by expanding the unknown functions into Fourier series and applying the integral Laplace transform. The solution of the inverse problem was obtained using the theory of integral equations and the Tikhonov regularization method. As a result of the study, a solution of the inverse problem of solid mechanics to identify an arbitrary axisymmetric non-stationary load was obtained. A numerical experiment was carried out to use the developed method to identify a moving non-stationary load acting on a simply supported cylindrical shell of medium thickness. The simulation results indicate a fairly accurate identification of both the change in time and the distribution along the shell of a non-stationary axisymmetric moving load. A method has been developed for identifying an external non-stationary load randomly distributed along a cylindrical shell, which makes it possible to identify a moving load without preliminary information about the type of this load. The developed method allows us to reproduce moving non-stationary loads, which are often encountered in practice, and expand it to other types of structural elements.

Innovative load identification with Res-UNet: Integrating phase space reconstruction and physics-informed deep learning

This study developed a specialized load identification model for a specific ocean platform that integrates advanced deep learning techniques with the unique physical characteristics of marine engineering. Key achievements include high-dimensional mapping of data features using phase space reconstruction (PSR) techniques to enhance the predictive capacity of the model through chaos system theory; optimization of ResNet and UNet deep learning networks with attention mechanisms to boost performance; calculation of stiffness, mass, and damping matrices using finite element software; establishment of corresponding state-space equations; and integration of structural dynamics equations with the deep learning network loss function to significantly improve load identification accuracy. In addition, proprietary structural equations for ocean platform structures were developed, underscoring the uniqueness and applicability of the algorithm. The proposed physics-informed Res-UNet model exhibited excellent performance in identifying both periodic and random loads. These improvements were validated through training with finite element simulated data and subsequent experimental applications, demonstrating the effectiveness of the proposed innovative methods.

A physical‒data-driven combined strategy for load identification of tire type rail transit vehicle

Tire load is one of the basic input parameters required for vehicle design and safety evaluation. Identifying the tire load with high accuracy is of great significance. However, the direct measurement of tire load is often high-cost and complex. Meanwhile, load identification solely based on physical measurement or data has great limitations of low accuracy and low robustness. This paper proposes a physical‒data-driven combined load identification strategy that includes an extended Kalman filter (EKF) and a data-driven correction model. These two models are configured in series. Derived from a physical state-space model of the vehicle dynamics, the EKF is used for the preliminary identification of the load. The data-driven model extracts the spatial and temporal characteristics of signals through the convolutional neural network and bidirectional gated recurrent unit, and then predicts the errors of the extended Kalman filter and corrects the identified results. The presented strategy is applied to an APM300 rubber wheel vehicle for load identification. The results have shown that the physical‒data-driven combined strategy can reduce the influence of parameter perturbation and improve the identification accuracy (6.4%). Thanks to organically combining the physical- and data-driven methods and integrating the rules and experience of the entire system, the strategy has strong generalization performance. Compared with traditional algorithms, the presented strategy could effectively reduce the error of load identification, improve adaptability under different operating conditions, and handle the measurement error of different noise levels, which are of practical application value in the engineering field.

An online reconstruction method of dynamic loading based on adaptive tracking dual nested Kalman filter

Accurately reconstructing the unknown dynamic loading is crucial for controlling the vibration of mechanical systems. Many methods have been proposed for load identification of time-invariant systems, but in some mechanical systems, their structural parameters exhibit time-varying dynamic characteristics during their operation. Therefore, tracking the time-varying structural parameters to update the transfer function is necessary, which is the most important prerequisite for load reconstruction. However, some existing methods are unstable because of the nonlinear conditions. To overcome this issue, an improved dual-nested Kalman filter framework has been proposed. This method allocates unknown variables to two Kalman filters, allowing them to iterate and loop with each other. As a result, it achieves linear reconstruction of the dynamic loading for a time-varying system. The proposed method has been validated in two numerical examples: one is a spring-mass system with abruptly changing mass parameters, and the other is a milling system with slowly changing mass parameters. The results show that the proposed method can reconstruct loading stably and is not susceptible to noise interference.

Study on instrumental coupler for heavy haul train

As a crucial load-bearing component, coupler’s safety is pivotal for sustainable railway industry development and is extensively scrutinized due to its complex loading environment. However, current research predominantly concentrates on the longitudinal dynamic behavior of couplers, neglecting factors such as nodding and shaking during traversals along curves and ramps. This study proposes an innovative method aimed at identifying multiple loads on couplers, which includes longitudinal tension and compression, lateral shaking, and vertical nodding forces. A theoretical load identification method based on strain sum and difference on coupler shank faces under various loading scenarios is established by finite element analysis. To facilitate accurate measurement, Wheatstone bridges are employed for three-dimensional force measurement, facilitating strain calculation and temperature compensation. The validity of the proposed approach is confirmed through comprehensive validation, encompassing finite element simulation, laboratory experimentation, and vehicle tests. Results demonstrate the robustness of the method, with maximum load deviations of 2.32% longitudinally, 22.52% horizontally, and 19.86% vertically observed during laboratory tests. Results indicate the proposed method’s accuracy and efficiency in heavy haul train coupler load assessment.

Non-Intrusive Load Monitoring Based on Dimensionality Reduction and Adapted Spatial Clustering

Non-invasive load monitoring (NILM) deduces changes in energy consumption patterns and operational statuses of electrical equipment from power signals in the feed line. With the emergence of fine-grained power load distribution, the importance of utilizing this technology for implementing demand-side energy management in smart grid development has become increasingly prominent. To address the issue of low load identification accuracy stemming from complex and diverse load types, this paper introduces a NILM method based on uniform manifold approximation and projection (UMAP) reduction and enhanced density-based spatial clustering of applications with noise (DBSCAN). Firstly, this paper combines the characteristics of user load under transient and steady-state conditions and selects data with significant differences to construct a load-characteristic database. Additionally, UMAP is employed to reduce the dimensionality of high-dimensional load features and rebuild a load feature database. Subsequently, DBSCAN is utilized to categorize typical user loads, followed by a correlation analysis with the load-characteristic database to determine the types or classes of loads that involve switching actions. Finally, this paper simulates and analyzes the proposed method using the electricity consumption data of industrial users from the CER–Electricity–Data dataset. It identifies the electricity load data commonly utilized by users in a specific area of Zhejiang Province in China. The experimental results indicate that the accuracy of the proposed non-invasive load identification method reaches 95%. Compared to the wavelet transform, decision tree, and backpropagation network methods, the improvement is approximately 5%.

Non-intrusive residential load identification based on load feature matrix and CBAM-BiLSTM algorithm

Non-intrusive residential load identification based on load feature matrix and CBAM-BiLSTM algorithm

Application of Artificial Neural Networks to a Model of a Helicopter Rotor Blade for Damage Identification in Realistic Load Conditions.

Monitoring the integrity of aeronautical structures is fundamental for safety. Structural Health Monitoring Systems (SHMSs) perform real-time monitoring functions, but their performance must be carefully assessed. This is typically done by introducing artificial damages to the components; however, such a procedure requires the production and testing of a large number of structural elements. In this work, the damage detection performance of a strain-based SHMS was evaluated on a composite helicopter rotor blade root, exploiting a Finite Element (FE) model of the component. The SHMS monitored the bonding between the central core and the surrounding antitorsional layer. A damage detection algorithm was trained through FE analyses. The effects of the load's variability and of the damage were decoupled by including a load recognition step in the algorithm, which was accomplished either with an Artificial Neural Network (ANN) or a calibration matrix. Anomaly detection, damage assessment, and localization were performed by using an ANN. The results showed a higher load identification and anomaly detection accuracy using an ANN for the load recognition, and the load set was recognized with a satisfactory accuracy, even in damaged blades. This case study was focused on a real-world subcomponent with complex geometrical features and realistic load conditions, which was not investigated in the literature and provided a promising approach to estimate the performance of a strain-based SHMS.

A bridge dynamic response analysis and load recognition method using traffic imaging

As the primary variable load of bridges, vehicle load is an important parameter for bridge health monitoring. However, traditional Weigh-in-Motion (WIM) systems and the commonly used method of placing sensors on the bridge are challenging to apply in load monitoring for many small and medium-sized bridges. Therefore, this paper proposes a bridge vehicle load identification method based on traffic surveillance video data. Leveraging the surveillance video data on the bridge, without introducing additional hardware devices, the displacement of target points is detected through sub-pixel level image detection algorithms, enabling non-contact measurement of bridge structural response through imaging. A spatiotemporal relationship model of structural displacement, vehicle load, and load distribution is established to solve for vehicle load. Finally, model bridge tests under various loading conditions and engineering practice experiments are conducted to validate the feasibility of the method. The results of the model bridge tests show that the structural displacement measured using traffic video measurement has a deviation of less than 10% compared to the measurements obtained using contact displacement sensors (LVDT), and it can accurately reflect the displacement characteristics of the structure. The results of the field tests demonstrate that the average estimation deviation for heavy vehicle loads ranging from 12 to 18 tons is approximately 18%, meeting the engineering requirements. The proposed method can provide load statistical information for the extensive health monitoring of small and medium-sized bridges and offer a new technical pathway for obtaining bridge load information.