Load Identification Research Articles

A Non-Intrusive Load Identification Method Based on Novel Data Acquisition Terminals and Model Fusion

A Non-Intrusive Load Identification Method Based on Novel Data Acquisition Terminals and Model Fusion

Power supply reliability evaluation of distribution network based on non-intrusive low-voltage power load identification and time series algorithm

Power supply reliability evaluation of distribution network based on non-intrusive low-voltage power load identification and time series algorithm

A Nonintrusive Load Identification Method Based on Dual-Branch Attention GRU Fusion Network

A Nonintrusive Load Identification Method Based on Dual-Branch Attention GRU Fusion Network

Improving multi-state appliance classification by SE-DenseNet based on color encoding in non-intrusive load monitoring

Non-intrusive load monitoring (NILM) is a technique that efficiently monitors appliances' operational status and energy consumption by utilizing voltage and current data, without intrusive measurements. In NILM, designing efficient classification models and building distinctive load features are crucial. However, due to its continuously variable load characteristics, multi-state load identification remains the most challenging problem in NILM. In this paper, we improve the encoding of the color V–I trajectory by incorporating instantaneous power, thereby enhancing the uniqueness of V–I trajectory features. Furthermore, we investigate a NILM method based on deep learning methods and propose a densely connected convolutional network with squeeze-and-excitation network (SE-DenseNet) architecture to solve the multi-state load identification problem. Initially, the architecture leverages DenseNet's dense connectivity property to generate a multitude of feature maps from the V–I trajectory. Then, SENet's channel attention mechanism is employed to enhance the utilization of effective features, which is more effective for multi-state load identification. Experimental results on the NILM public datasets PLAID and WHITED show that the recognition accuracy of the proposed method reaches 98.60% and 98.88%, respectively, which outperforms most existing methods.

Power supply reliability evaluation of distribution network based on non-intrusive low-voltage power load identification and time series algorithm

Power supply reliability evaluation of distribution network based on non-intrusive low-voltage power load identification and time series algorithm

Non-Intrusive Load Identification of Residential Appliances Using Improved Dictionary Learning Technique

With the advent of time, the demand for power in the residential sector is increasing. Along with supply-side management, the demand side is also used to balance electricity and supply demand. To apply different demand-side management techniques, the energy disaggregation on metered data is used to retrieve information related to available demand. Non-intrusive load monitoring is a technique that separates the total power consumption into appliance loads with minimum invasion of privacy. Non-intrusive load monitoring covers the methods of Stochastic finite state machines, Neural Networks and Sparse Coding. Developing an efficient algorithm for NILM is a key challenge in maximizing energy conservation. Recently, a new deep learning technique called dictionary learning has been developed for energy disaggregation. Smart meters provide the whole house data, and the Dictionary technique is trained to predict an appliance's power or ON/OFF based on its power consumption. This research proposes the event-based dictionary learning technique, which can disaggregate multiple appliances through orthogonal matching pursuit (OMP) and kernel-singular value decomposition (K-SVD). The sparse matrix is predicted through OMP, and K-SVD predicts the dictionary matrix. The training, testing and validation are done on the ECO dataset. The results of this research are noticeable and show the validity of the proposed methodology for energy disaggregation.

Non-intrusive load identification method based on GAF and RAN networks

Non-intrusive load identification can improve the interaction efficiency between the power supply side and the user side of the grid. Applying this technology can alleviate the problem of energy shortage and is a key technique for achieving efficient management on the user side. In response to the cumbersome process of manually selecting load features and the low accuracy of identification in traditional machine learning algorithms for non-intrusive load identification, this paper proposes a method that transforms the one-dimensional reactive electric signal of the load into a two-dimensional image using Gram coding and utilizes the Residual Attention Network (RAN) for load classification and recognition. By transforming the one-dimensional electrical signal into a two-dimensional image as the input to the RAN network, this approach retains the original load information while providing richer information for the RAN network to extract load features. Furthermore, the RAN network effectively addresses the poor performance and gradient vanishing issues of deep learning networks through bottleneck residual blocks. Finally, experiments were conducted on a public dataset to verify the effectiveness of the proposed method.

Research on a Non-Intrusive Load Recognition Algorithm Based on High-Frequency Signal Decomposition with Improved VI Trajectory and Background Color Coding

Against the backdrop of the current Chinese national carbon peak and carbon neutrality policies, higher requirements have been put forward for the construction and upgrading of smart grids. Non-intrusive Load Monitoring (NILM) technology is a key technology for advanced measurement systems at the end of the power grid. This technology obtains detailed power information about the load without the need for traditional hardware deployment. The key step to solve this problem is load decomposition and identification. This study first utilized the Long Short-Term Memory Denoising Autoencoder (LSTM-DAE) to decompose the mixed current signal of a household busbar and obtain the current signals of the multiple independent loads that constituted the mixed current. Then, the obtained independent current signals were combined with the voltage signals to generate multicycle colored Voltage–Current (VI) trajectories, which were color-coded according to the background. These color-coded VI trajectories formed a feature library. When the Convolutional Neural Network (CNN) was used for load recognition, in light of the influence of the hyperparameters on the recognition results, the Bayesian Optimization Algorithm (BOA) was used for optimization, and the optimized CNN network was employed for VI trajectory recognition. Finally, the proposed method was validated using the PLAID dataset. The experimental results show that the proposed method exhibited better performance in load decomposition and identification than current methods.

A novel dynamic load identification method based on improved basis functions and implicit Newmark-[formula omitted] for continuous system with unknown initial conditions

For structural design and optimization, precise knowledge of dynamic load on structures is essential. However, load identification can be sensitive to the initial conditions, and even small variations can lead to inaccurate results. The existing load identification methods always assume that the structure’s initial condition is zero, which is not the case in real engineering problems where structures are already in a state of vibration before load identification implementation. In this work, we propose a novel dynamic load identification method that takes into account unknown initial conditions of structures which is based on the improved basis functions and implicit Newmark-β method. The real vibration response is decomposed into forced vibration caused by dynamic load and free vibration caused by initial condition, which are characterized by the coefficients of undetermined orthogonal polynomials. Moreover, to overcome the ill-posedness problem arising from factors such as response noise and model error, we introduce the L1 regularization method. To validate the performance of the proposed method, numerical simulations and tests of load identification are conducted on simply supported beam. The effects of noise and model error on the load identification results are analyzed. Finally, we discuss the impact of modal truncation order and the effect of measurement points on load identification.

A NILM load identification method based on structured V-I mapping

With the increasing number and types of global power loads and the development and popularization of smart grid technology, a large number of researches on load-level non-intrusive load monitoring technology have emerged. However, the unique power characteristics of the load make NILM face the difficult problem of low robustness of feature extraction and low accuracy of classification and identification in the recognition stage. This paper proposes a structured V-I mapping method to address the inherent limitations of traditional V-I trajectory mapping methods from a new perspective. In addition, for the verification of the V-I trajectory mapping method proposed in this paper, the complexity of load characteristics is comprehensively considered, and a lightweight convolutional neural network is designed based on AlexNet. The experimental results on the NILM dataset show that the proposed method significantly improves recognition accuracy compared to existing VI trajectory mapping methods.

Strain/displacement field reconstruction and load identification of bracket arm structure of high-speed maglev train based on superposition conversion algorithm

The bracket arm structure, subjected to long-term vertical levitation and transversal guidance forces, is a key load-bearing component of high-speed maglev trains. It is crucial to monitor strain, displacement, and load in real time to evaluate structural health. However, it is almost impossible to measure directly at the service site of trains due to the intricacy of the bracket arm structure and the constrained installation area. Hence, it is an effective and feasible approach to reconstruct the strain/displacement field using a limited amount of strain information from FBG sensors. In order to reconstruct the strain/displacement field and identify the load on complicated structures, a load–strain/displacement superposition conversion algorithm is proposed in this paper. The modal coordinate and the mode-shape matrix are swapped out for the load weight and the load–strain/displacement matrix, respectively. Thus, it gets around the difficulty of choosing the mode order in traditional modal theory. In addition, the algorithm can achieve full-field reconstruction of both strain and displacement by measuring only part of the nodal strain response, reducing the redundancy of the traditional algorithm. Finally, numerical simulations and experimental tests were carried out to verify the feasibility of the proposed method for field reconstruction and load identification.

Definition of parameters of loading modes of the test bench for tractor cabin’s vibration isolators

BACKGROUND: During the operation, tractor cabin’s vibration isolators are under the simultaneous load vertical, longitudinal- and lateral-angular vibrations of the cabin. These vibrations have different amplitudes, frequencies and time-domain behavior. It is possible to simulate comprehensive operational loads on vibration isolators only with bench testing. AIMS: Within this study, the trial to define parameters of loading modes for bench testing of tractor cabin’s vibrational isolators and to define corresponding parameters of drives of the bench loading devices was made. METHODS: This paper presents explanation and the results of calculation of loading modes parameters for testing of tractor cabin’s vibration isolator at the bench capable of producing loads from vertical, longitudinal- and lateral-angular vibrations of a tractor cabin simultaneously, as well as the results of calculation of corresponding parameters of drives of this bench. The procedure of preparation for testing was developed. This procedure includes estimation of values of operational loads amplitudes and frequencies, the range of change of necessary velocities and torques of electric drives of the bench loading devices and identification of adequate drives with required properties, determination of behavior of force and kinematic excitation reproduced by the test bench. Exemplary calculation of parameters of vertical loading at the considered bench was performed for the AKSS-400M rubber-metal vibration isolator used in cabin suspension of the K-708.4 wheeled tractor. A number of assumptions were made in the calculation. Nominal values of velocity and torque of the electric motor drive of the vertical loading device of the bench were obtained as the results. Thus, the electric motor with the reduction gear made by TRANSTECNO was selected. Characteristics of force and kinematic excitations reproduced by the bench using electric motor frequency control were built. RESULTS: Analysis of graphs helped to define acceptable range of frequencies reproduced by the bench for operational loads in vertical direction limited by abilities of the selected electric drive. CONCLUSIONS: The results of calculation of electric drive parameters can be used in design of the considered bench for testing of tractor cabin’s vibration isolators, particularly in the development of loading devices (cam eccentrics, pushers, return springs).

Research on new energy grid-connected load monitoring method based on the network analysis method

Abstract The steady-state characteristic parameters of the loads are used to identify new energy grid-connected loads using an event-based network analysis method in this paper. The analysis of interdependence among elements is done by studying the element layer and special structure of the network analysis method. Using the principle of limit relative ranking vector calculation, the supermatrix and weighting matrix of the ANP element layer are constructed, and the basic steps of ANP model weights are determined. The ANP-based load monitoring algorithm is evaluated by combining the load identification accuracy with the F-value. The results show that event detection algorithms are generally more than 70% accurate. 17 out of 18 times of identifying load events of computers can be correctly identified with an accuracy rate of 89.37%, 9 out of 10 times of identifying fluorescent lamps with an accuracy rate of 89.98%, and 14 out of 15 times of identifying microwave ovens with an accuracy rate of 92.75%. The new energy grid-connected load can also be detected by combining the harmonic content rate. The harmonic content rates when the desktop computer was turned on were 93.04%, 86.67%, 60.16%, 61.76%, and 23.46%, respectively. This study helps to improve the accuracy of new energy grid-connected load monitoring.

Research on the Prediction of Tire Radial Load Based on 1D CNN and BiGRU

As an important indicator of vehicle systems, tire load is a key factor in the structural design and safety assessment of vehicles. Direct measurement methods for tire loads are expensive and complicated, while conventional load identification methods are limited by low accuracy and poor robustness. This study aimed to propose a radial load identification method for rubber-tired vehicles based on a one-dimensional convolutional neural network (1D CNN) and bidirectional gated recurrent unit (BiGRU). Considering a priori information of the radial load data of tires and based on the observability of the vehicle vibration system, the proposed method selected feature sets and then retained the effective feature subsets through feature selection to construct samples with multiple time steps as input and with a single time step as output for network training. In doing so, the load prediction results were obtained, and the theoretical model was modified by integrating prediction accuracy, generalization performance, and robustness. Compared with traditional algorithms, the proposed method 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.

Train Load Identification of the Medium-Small Railway Bridge using Virtual Axle Theory and Bayesian Inference

Accurately identifying the axle loads of the moving train on the railway bridge can provide reliable information for assessing the safety of the train–bridge system. Bridge weigh-in-motion, namely, BWIM, is an effective approach for identifying the positions and weights of the train axles based on the monitored bridge responses. Existing BWIM methods generally focus on identifying the probable value of the axle weights instead of quantifying the identification uncertainty. To address this issue, a novel two-stage train load identification framework for the medium-small railway bridge is developed by combining the virtual axle theory and Bayesian inference. In the first stage, the axle configuration including the axle number, axle spacing and axle weight of the moving train, are estimated according to the modified virtual axle theory in which a clustering algorithm is embedded to automatically determine the axle number. In the second stage, the most probable value (MPV) and the uncertainty of the train axle weight are accurately identified using the Bayesian inference method which takes five types of error patterns into consideration. Finally, the proposed framework is verified using the data from numerical simulations and an in-situ railway bridge. Results show that the proposed framework can improve the accuracy of train load identification after quantifying the uncertainty of estimated axle weights and can confirm the confidence interval of the individual axle weight and gross train weight.

Exploring the impact of body mass change on fatigue and activity of the muscular system during daily routine.

Correct body weight is one of the factors that allows you to maintain a properly functioning body. Abnormal body weight can cause muscle tissue remodelling, affecting activity and muscle fatigue. Changes in the muscular system can cause occurrence of functional limitations. To determine the effect of weight change on fatigue and activity of the muscular system during daily activities. The evaluation of musculoskeletal functioning was based on the results of computer simulations conducted in the AnyBody Modeling System. The following activities were analysed: standing, sitting down and getting up from a chair, holding and lifting an object, and walking. The simulations of the activities were carried out using averaged kinematic data, and by changing body mass in the range of 50 kg to 100 kg by increments of 2 kg, to map different nutritional status from excessive thinness to extreme obesity. Identification of loads in the musculoskeletal system was based on solving an inverse dynamics problem and then the estimation of muscle force values using static optimization. The simulation results allowed to determine the value of muscle fatigue and the level of muscle activity. For activities (i.e., standing, walking, sitting down and getting up from a chair) it was observed that the value of muscle fatigue increases with increasing body mass. However, for activities that cause more load on the musculoskeletal system, i.e. lifting and holding an object, the highest value of muscle fatigue was observed in underweight individuals. The change in body weight alters the functioning of the muscular system and thus the ability to perform activities. It was shown that in case of underweight, overweight or obese people, abnormal body weight can be the reason for occurrence of difficulties in performing the activities of lifting and holding a 20 kg object, as well as walking.

Spectral modelling approach for crowd-rhythmic activities performed on steel-concrete composite floors

During the last decades, building floors have become sensitive to vibrations caused by human activities, especially when a group of individuals perform rhythmic activities in a coordinated manner. Resulting effects on floor occupants can range from a mere perception, can pass through discomfort and can even go so far to cause panic. The present paper proposes a spectral modelling approach for crowd-rhythmic activities applied on floor structures. The proposed model comprises a frequency domain model for a single person, combined with coordination factors to account for the lack of synchronization between individuals. The identification of this model was based on vibration experiments carried out on a floor specimen specifically designed for that purpose. Two particular types of rhythmic activity were investigated: jumping and skipping, and performed by up to 16 individuals, where realistic coordination stimulus was adopted. Using least-squares identification procedures, the single person load parameters were determined and predicted load models are in good agreement with their measured counterparts. Resulting parameters are dependent on the motion style of each investigated activity. Coordination factors are also derived from crowd forces and present a hyperbolic decrease by crowd size for jumping activities against an exponential decrease for skipping activities. Based on a closed-form expression using the established crowd model, a design-oriented method is proposed for a simplified evaluation of floor response due to crowd-rhythmic activities and verified against floor response measurements. Slight differences were found between measured and numerical responses due to the variabilities either encountered during experiments or resulting from the load identification process.

Non-Intrusive Load Monitoring Method for Multi-Energy Coupling Appliances Considering Spatio-Temporal Coupling

The multi-energy coupling (MEC) appliances couple electricity, gas, heat, and cold, of which the gas, heat, and cold have long transient processes. However, these transient features have never been considered in past non-intrusive load monitoring (NILM) methods. This paper proposes a novel NILM method for MEC appliances considering spatio-temporal coupling, which combines semi-supervised learning and weakly supervised learning. Firstly, the unlabeled historical events are labeled by graph-based semi-supervised learning (GBSSL) and distinguished into three categories, i.e., reliable, uncertain, and unreliable samples. Then, to fully use of spatio-temporal coupling information, the unreliable samples are discarded and the feature vectors of other samples are expanded into spatio-temporal coupling feature vectors. To improve the accuracy of load identification, this paper proposes a two-stage deep learning framework “Teaching and Mutual Learning" (TML). In the teaching stage, two convolutional neural networks (CNN) are pre-trained with reliable samples. In the mutual learning stage, the noise samples are filtered by using the different learning abilities of the two networks. The effectiveness and superiority of the proposed method are verified on five types of MEC appliances in a park IES.

Minimum variance unbiased Bayesian smoothing for input and state estimation of systems without direct Feedthrough: Mitigating Ill-Posedness of online load identification

In this paper, the problem of moving load identification using pure displacement measurements is addressed. It is known that when no assumptions are made on the statistics of the unknown loads and a minimum variance unbiased (MVU) estimation approach is adopted, the existing methods in the literature suffer from a very elevated load estimation uncertainty. This elevated uncertainty is due to ill-posedness of the problem. In this paper a new method is proposed that addresses this issue via an MVU smoothing approach. To alleviate this problem, a MVU smoothing algorithm is proposed in this study, via modification of a MVU smoothing Bayesian estimator proposed by some of the co-authors of this paper hence referred to as MSBE, which leads to substantial decrease in the moving load estimation uncertainties using pure displacement measurements. The efficacy of the MSBE is studied through a simulated experiment corresponding to a numerical model of an operating steel railway bridge with riveted connections and a multi-axle load. The selection of the hyperparameters of the smoothing and filtering techniques are discussed, and the optimal values are presented. The parametric studies show that the proposed method can yield highly accurate results, and substantially outperforms a celebrated MVU filter proposed by Gillijns and De Moor.

An improved non-intrusive load identification using sample shifting and fuzzy rule-based technique

In this paper, a method to analyse load features utilising sample shifting technique (SST) for non-intrusive load identification (NILI) is presented and discussed. Fuzzy rules are used as the foundation for the identification logic. Voltage and current signals for electrical home appliances are acquired in order to develop their respective features. Two features like reactive power and total harmonic distortion for current (THDI), are created with the necessary computations of the samples using SST. A method based on fuzzy rules is created in order to identify different electrical equipment both for their individual as well as simultaneous running. Again, the performance of the proposed system is tested under the noisy environment while the accuracy of the system is found satisfactory. By utilising SST, the burden of computation is reduced in comparison to the other methods which are justified with the experimental results.