Search

In strong wind area, wind vibration on key railway catenary components may lead to safety hidden danger like fatigue failures. In this work, a load identification approach was proposed by decoupling the wind-induced suspension attitude to acquire the hard-to-get environmental wind load and evaluate the catenary fatigue damage on railway catenary. In theoretical modeling, mechanical relation between wind load and registration displacement is formulated in pure lateral and vertical loading by finite element analysis. Wind load is identified via suspension attitude decoupling into displacement under individual load. Nodal forces, as the external load acting on catenary connections between supporting beams, are further correlated with the identified wind load to calculate the structural stress of catenary components. In experiment, visual detection is used to measure the wind-induced attitude of catenary suspension in wind area, where maximum wind speed climbs up to 41 m/s. Experimental results are transferred into wind loads and nodal forces using the proposed model. Stress spectra and fatigue damage evaluation of connection components are carried out adopting the rain-flow counting method and damage accumulation rule. Research outcome certifies that the proposed methodology provides an effective means to evaluate the fatigue behavior of railway catenary in wind area.

Smart power consumption is an important part of ubiquitous power Internet of things. Load identification, as an important part of smart power consumption, is of great significance to users and power grid. Aiming at the problems of long training time and low recognition accuracy in existing algorithms, this paper proposes a non-invasive load identification algorithm based on LSTM-BP. Firstly, the data is normalized, and then the dimension of high-dimensional data is reduced by PCA. Then, LSTM-BP neural network is built for load identification. Finally, Redd data set is used to test and analyze the algorithm. Compared with the existing load identification algorithm based on event detection, this method has higher stability and accuracy.

Electrical load planning and demand response programs are often based on the analysis of individual load-level measurements obtained from houses or buildings. The identification of individual appliances’ power consumption is essential, since it allows improvements, which can reduce the appliances’ power consumption. In this article, the problem of identifying the electrical loads connected to a house, starting from the total electric current measurement, is investigated. The proposed system is capable of extracting the energy demand of each individual device using a nonintrusive load monitoring (NILM) technique. An NILM algorithm based on a convolutional neural network is proposed. The proposed algorithm allows simultaneous detection and classification of events without having to perform double processing. As a result, the calculation times can be reduced. Another important advantage is that only the acquisition of current is required. The proposed measurement system is also described in this article. Measurements are conducted using a test system, which is capable of generating the electrical loads found on a typical house. The most important experimental results are also included and discussed in the article.

The output power of a wireless power transfer (WPT) system depends highly on the load and the coupling conditions, which are variable in practical applications generally. In order to attain stable output power with high transfer efficiency under various coupling condition and load, this paper proposes a series-series compensated WPT system based on parity-time ( PT ) symmetry with front-end DC-DC converter and a novel primary-side-only control strategy. The strategy comprises the negative resistance control of PT -symmetric circuit, the online load identification approach by PT -symmetry, and the power closed-loop control method. The advantages are that the mutual inductance information is not needed, and dual-side wireless communication as well as the secondary-side control circuit is avoided, which compresses the volume of the secondary side, simplifies the control algorithm, and improves the robustness of the system. With the proposed primary-side-only control strategy, the output power is coupling-independent and can automatically stabilize at specified values over reasonable variations both in coupling coefficient and load. The experimental results obtained from a prototype are included. They confirm the proposed control strategy and indicate that system can stably output 200 W and 400 W with the maximum error 4.10% and 3.40% respectively when the coupling coefficient and loads vary, and achieves high overall efficiency at 91.9%.

Population growth and new consumer needs, among other factors, have lead to growing energy demand, without a concomitant increase in energy generation. This way, reduction and rationalization of energy consumption, especially by residential users, have become a global concern generating a need for developing techniques for efficient management and distribution of the available energy. Non-Intrusive Load Monitoring (NILM) techniques have provided valuable information about energy consumption for power generation companies as well as consumers. Such information is important for making decisions related to sustainable use of energy resources. This study proposes an automated system based on Artificial Neural Network for performing some of the NILM tasks. A stacked neural network was developed to extract features of power signals of appliances to identify those in operation during a given period. This information is then used to disaggregate individual appliance loads through the total aggregate signal, and consumption is calculated through numerical integration. The system was tested using real data from two databases about appliances with On/Off, multi-level, and variable consumption patterns collected in low frequency. The performance metrics, resulting from identification and disaggregation tasks, demonstrate the efficiency of the proposed system.

In railway freight transport of over-size cargos, elastic deflection of overloaded structures is the main cause of train-line collision in running. Deflection monitoring remains a challenge for the non-uniform and opening beam on well-hole freight cars. This work presented a new approach by strain perception and Finite Element Analysis (FEA). In theoretical modeling, support locations and the geometry symmetry were taken into account, to identify the support loads with bottom strains in single loading. Deflection calculation was developed by mathematically correlating bottom deflections with support loads, and further extended to the concerning region of the non-uniform and opening beam. Validation underwent in loading simulation and tests. The identified deflection deviates from the read and measured within 5.98%. In application, in-transit monitoring reveals that the most unfavorable vertical cargo movement, which is calculated with the identified support deflections and the measured suspension displacement, climbs up to 231.6 mm in synthetic evaluation, when the train runs on a 400-m radius line curve at the speed of 19.6 km/h. The detecting maximum is within but very close to the limit dimension between cargo bottom and rail top, 250 mm. Hence, it is recommended to measure the limit after the transformer is loaded. Research outcome indicates that the proposed approach enables the real-time deflection monitoring and safety evaluation in railway freight transport, which offers scientific evidence for its operation maintenance and structural optimization.

Non-Intrusive Load Monitoring (NILM) makes it possible for users and energy providers to track the fine-grained energy consumption information of residential and commercial buildings. The load identification methods in NILM usually require labeling many samples for training and evaluation, which is always expensive and time-consuming. In order to reduce the labeling cost, this paper proposed a load identification method based on Active Deep Learning (ADL). In this method, Discrete Wavelet Transform (DWT) was applied to extract high-dimensional appliance features from original current signals. Then a pool-based or stream-based active deep learning model was built to learn the features and select high-value samples that worthy of labeling. A mixed dataset based on three public datasets was formed to evaluate the proposed method and three sampling approaches of active learning. The results showed that the proposed method could significantly reduce labeling cost on large datasets, and the number of samples required is 33% lower than the state-of-the-art method when the F1 score is equal. Compared with pool-based sampling approaches, the stream-based approach's benefits are that the classifier improved and the query frequency decreased with continuous input of samples.

Flexible corrugated skins are ideal structures for morphing wings, and the associated load measurements are of great significance in structural health monitoring. This paper proposes a novel load-identification method for flexible corrugated skins based on improved Fisher discrimination dictionary learning (FDDL). Several fiber Bragg grating sensors are pasted on the skin to monitor the load on multiple corrugated crests. The loads on different crests cause nonuniform strain fields, and these discriminative spectra are recorded and used as training data. The proposed method involves load-positioning and load-size identification. In the load-size-identification stage, a classifier is trained for every corrugated crest. An interleaved block grouping of samples is introduced to enhance the discrimination of dictionaries, and a two-resolution load-size classifier is introduced to improve the performance and resolution of the grouping labels. An adjustable weight is introduced to the FDDL classification scheme to optimize the contribution from different sensors for different load-size classifiers. With the proposed method, the individual loads on eight crests can be identified by two fiber Bragg grating sensors. The positioning accuracy is 100%, and the mean error of the load-size identification is 0.2106 N, which is sufficiently precise for structural health monitoring.

Non-Intrusive Load Monitoring (NILM) allows load identification of appliances through a single sensor. By using NILM, users can monitor their electricity consumption, which is beneficial for energy efficiency or energy saving. In advance NILM systems, identification of appliances on/off events should be processed instantly. Thus, it is necessary to use an extremely short period signal of appliances to shorten the time delay for users to acquire event information. However, acquiring event information from a short period signal raises another problem. The problem is target load feature to be easily mixed with background load. The more complex the background load has, the noisier the target load occurs. This issue certainly reduces the appliance identification performance. Therefore, we provide a novel methodology that leverages Generative Adversarial Network (GAN) to generate noise distribution of background load then use it to generate a clear target load. We also built a Convolutional Neural Network (CNN) model to identify load based on single load data. Then we use that CNN model to evaluate the target load generated by GAN. The result shows that GAN is powerful to denoise background load across the complex load. It yields a high accuracy of load identification which could reach 92.04%.

To achieve load disaggregation in non-intrusive load monitoring (NILM) system, a load event matching method based on graph theory is proposed, which is built on the improved Kuhn-Munkras algorithm. In this method, firstly, an adaptive fitting method using time window is applied to detect the load whether it is switched on and/or off. Particularly, to avoid the fluctuation of load signatures, the kernel density estimation is then built by a number of the independent features of the load switching on, including the active and reactive power signatures. The distribution of load signatures is thereby obtained, allowing the load event to be classified by its features. The load matching, which is based on the improved KM algorithm, is then utilized to resolve the matrix formed by the matching probability of the load event. Similarly, load identification can also be realized by matching the features of events with the signatures in the database. Finally, the experimental results using datasets of our lab and REDD demonstrate that the proposed method can obtain the desirable result for load event matching, and promote the performance in load identification.

More and more researches have been carried out recently on Weigh-In-Motion (WIM) technology for solving the traffic safety problems caused by overload. In this article, we aim to study the measurement accuracy of the WIM system. Based on the electromechanical theory and elastic half-space method, we establish a theoretical model of multi-layer structure to investigate the correlation between the output voltage of the piezoelectric sensor and the applied force. In addition, we performed cyclic and moving load experiments to verify the accuracy of the analytical calculations. The load magnitude identified by this theoretical model matched the experiments very well, which shows that this model is effective for the WIM system. In addition, we proved that the load frequency is an important factor affecting the measurement accuracy of the sensor, which further enables us to design more suitable sensors for certain use scenarios.

Non-intrusive load identification is important to load monitoring and smart power utilization. In order to effectively identify load status and obtain detailed power data, this paper explained a load identification algorithm based on load decomposition and frequency domain filtering. It realized load decomposition through solving an underdetermined problem of a single current signal under non-intrusive collection mode and then further achieved load identification. The underdetermined problem was optimized into a 1-D underdetermined problem. The solving model was constructed as separating the collecting current into two channels. According to the sparseness of the current frequency domain signal, the optimal solution was obtained by a two-step iterative shrinkage threshold algorithm. Therefore, each operation load can be decomposed independently. The frequency-domain filter group was conducted to filter the decomposition current, and load identification was realized based on the decision of the frequency component after filtering. The algorithm simplified the identification complexity, with a fast convergence rate and high identification accuracy. The performance was validated by the actually measured data. The load decomposition and identification was effective, which could accurately determine the load status, and obtain the current waveform of the independent load.

Plate-like structures in real mechanical system is always simplified and modeled as an elastically restrained thin plate loaded with stiffness or mass. The dynamic model of the plate distinguished with previous classic model is complex vibrational characteristics and merely proposed by numerical method. Accordingly, identification of harmonic load acting on this plate becomes difficult for hardly obtaining inverse equations or matrix from its response functions directly. To solve this problem, dynamic model of the plate is established by numeric method and combined with particle swarm optimization (PSO) method to reconstruct harmonic load by minimizing total error between vibration responses in identification and test. Then, it is used to deal with acceleration responses tested in an elastically supported plate derived by a harmonic load. Parameters of the harmonic load are identified and found to agree with those of real source by their comparison. Thus, it is concluded that harmonic load driving on the plate linked with elastic boundary and attachment can be identified accurately by proposed numeric model of this paper. Furthermore, acceleration distribution of the plate at modal frequencies and responses at different test point, which are acquired from identification and test, are demonstrated and discussed. It is revealed that the numeric model proposed in this paper identifies parameters of harmonic load mainly through tendency of vibration distribution on the plate, and the accuracies of its reconstruction results at some locations are limited.

In this paper we mainly focus on monitoring the energy consumption of individual electrical appliances connected to a home. The adopted system measures the total electric current and extracts the absorption of each individual device, using a NILM algorithm (Non Intrusive Load Monitoring). The characteristics of a new NILM algorithm have been identified by comparing the different load disaggregation techniques. It was initially verified with aggregate data available online. Successively, measurements were performed using a suitable system that reproduces a typical domestic electrical wiring with connected household appliances was implemented. The paper describes the measurement system, including the NILM algorithm. Additionally, some performance evaluation results are also reported in the paper.

This paper develops an approach for household appliance identification and classification of household activities of daily living (ADLs) using residential smart meter data. The process of household appliance identification, i.e., decomposing a mains electricity measurement into each of its constituent individual appliances, is a very challenging classification problem. Recent advances have made deep learning a dominant approach for classification in fields, such as image processing and speech recognition. This paper presents a deep learning approach based on multilayer, feedforward neural networks that can identify common household electrical appliances from a typical household smart meter measurement. The performance of this approach is tested and validated using publicly available smart meter data sets. The identified appliances are then mapped to household activities, or ADLs. The resulting ADL classifier can provide insights into the behavior of the household occupants, which has a number of applications in the energy domain and in other fields.

Aiming at the output control issues of a lithium ion battery wireless charging system, a primary side control method based on load characteristic identification is proposed. The primary side impedance is calculated by detecting the effective value of the primary side voltage and current, and the mapping relationship between the equivalent load and the primary side impedance is established based on the AC impedance model. Using this mapping relation, the output of the secondary side can be regulated indirectly by controlling the input voltage of the inverter. Compared with the traditional control methods, the proposed control method not only eliminates the communication requirement between the primary side and secondary side, but also simplifies the hardware circuit design, reduces the complexity of the control circuit and also reduces the volume and cost of the system. In the paper, the impedance characteristics of the lithium ion battery at constant current and constant voltage stage are analyzed. The principle of the primary side control method is expounded and the realization method is given. The feasibility of the proposed control method is verified by simulation and experiment.

Non-intrusive load monitoring (NILM) is an important research direction and development goal on the distribution side of smart grid, which can significantly improve the timeliness of demand side response and users’ awareness of load. Due to rapid development, deep learning becomes an effective way to optimize NILM. In this paper, we propose a novel load identification method based on long short term memory (LSTM) on deep learning. Sequence-to-point (seq2point) learning is introduced into LSTM. The innovative combination of the LSTM and the seq2point brings their respective advantages together, so that the proposed model can accurately identify the load in process of time series data. In this paper, we proved the feature of reducing identification error in the experimental data, from three datasets, UK-DALE dataset, REDD dataset, and REFIT dataset. In terms of mean absolute error (MAE), the three datasets have increased by 15%, 14%, and 18% respectively; in terms of normalized signal aggregate error (SAE), the three datasets have increased by 21%, 24%, and 30% respectively. Compared with the existing models, the proposed model has better accuracy and generalization in identifying three open source datasets.

Moving load is a fundamental loading pattern for many civil engineering structures and machines. This paper proposes and experimentally verifies an approach for indirect identification of 2D trajectories of moving loads. In line with the &ldquo, structure as a sensor&rdquo, paradigm, the identification is performed indirectly, based on the measured mechanical response of the structure. However, trivial solutions that directly fit the mechanical response tend to be erratic due to measurement and modeling errors. To achieve physically meaningful results, these solutions need to be numerically regularized with respect to expected geometric characteristics of trajectories. This paper proposes a respective multicriterial optimization framework based on two groups of criteria of a very different nature: mechanical (to fit the measured response of the structure) and geometric (to account for the geometric regularity of typical trajectories). The state-of-the-art multiobjective genetic algorithm NSGA-II is used to find the Pareto front. The proposed approach is verified experimentally using a lab setup consisting of a plate instrumented with strain gauges and a line-follower robot. Three trajectories are tested, and in each case the determined Pareto front is found to properly balance between the mechanical response fit and the geometric regularity of the trajectory.

Non-intrusive load monitoring is a vital part of an overall load management scheme. One major disadvantage of existing non-intrusive load monitoring methods is the difficulty to accurately identify loads with similar electrical characteristics. To overcome the various switching probability of loads with similar characteristics in a specific time period, a new non-intrusive load monitoring method is proposed in this paper which will modify monitoring results based on load switching probability distribution curve. Firstly, according to the addition theorem of load working currents, the complex current is decomposed into the independently working current of each load. Secondly, based on the load working current, the initial identification of load is achieved with current frequency domain components, and then the load switching times in each hour is counted due to the initial identified results. Thirdly, a back propagation (BP) neural network is trained by the counted results, the switching probability distribution curve of an identified load is fitted with the BP neural network. Finally, the load operation pattern is profiled according to the switching probability distribution curve, the load operation pattern is used to modify identification result. The effectiveness of the method is verified by the measured data. This approach combines the operation pattern of load to modify the identification results, which improves the ability to identify loads with similar electrical characteristics.

Non-intrusive load monitoring (NILM) is an effective way to achieve demand-side measurement and energy efficiency optimization. This paper studies a method of non-intrusive on-line load monitoring under a high-frequency mode of electric data acquisition, which enables the NILM to be automated and in real-time, including the short-term construction of a dynamic signature library and continuous on-line load identification. Firstly, in the short initial operation phase, load separation and category determination are carried out to construct the load waveform library of the monitoring user. Then, the continuous load monitoring phase begins. Based on the data of each user&rsquo, s signature library, the decomposition waveforms are classified by convolutional neural network models that are constructed to be suitable for each signature library in order to realize load identification. The real-time power consumption status of the load can be obtained continuously. In this paper, the electricity data of actual users are collected and used to perform the experiments, which show that the proposed method can construct the load signature library adaptively for different users. Meanwhile, the classification of the convolutional neural network model based on a library constructed in actual operation ensures the real-time and accuracy of load monitoring.

Load power sensitivity to voltage changes continuously in the distribution grid due to the increased variability of the load demand (e.g., electric vehicles charging) and generation production (e.g., photovoltaic). Classical sensitivity identification methods do not respect the fast dynamics of such changes: they require long data history and/or high computational power to update the load sensitivity. The proposed online load sensitivity identification (OLLI) approach is able to identify the load sensitivity in real time (e.g., every minute). This paper demonstrates that the OLLI can be achieved not only with the advanced smart transformer metering system but also with commercial industrial metering products. It is shown that OLLI is able to identify correctly the load sensitivity also in the presence of noise or fast stochastic variation of power consumption. The industrial metering-based OLLI application has been proven by means of a power-hardware-in-loop evaluation applied on an experimental microgrid.

This paper presents a comparison of two static nondestructive methods used to assess compressive loads in columns of steel space frames. The first method requires knowledge of the flexural rigidity of the column under investigation, whereas the second method requires knowledge of the column’s buckling load. In each method, short-term displacements are measured at given cross-sections along the member under examination, which is subjected to an additional transverse load. The two methods were verified in this study through experimental and numerical tests on a column of a small-scale space frame prototype with generic connections and end conditions. Estimations of compressive forces were generally reliable when second-order effects were accurately considered. In conclusion, the two methods can be successfully used to test steel space frames in a laboratory or under real conditions.

Load identification plays an important role in structural health monitoring, which aims at preventing structural failures. In order to identify load for linear systems and nonlinear systems, this paper presents methods to identify load for a cantilever beam based on dynamic strain measurement by Fiber Bragg Grating (FBG) sensors. For linear systems, the proposed inverse method consists of Kalman filter with no load terms and a linear estimator. For nonlinear systems, the proposed inverse method consists of cubature Kalman filter (CKF) with no load terms and a nonlinear estimator. In the process of load identification, the state equations of the beam structures are constructed by using the finite element method (FEM). Kalman filter or CKF is used to suppress noise. The residual innovation sequences, gain matrix, and innovation covariance generated by Kalman filter or CKF are used to identify a load. To prove the effectiveness of the proposed method, numerical simulations and experiments of the beam structures are employed and the results show that the method has an excellent performance.

In this paper we present a new methodology for the formulation of efficient load signatures towards the implementation of a near-real time Non-Intrusive Load Monitoring (NILM) approach. The purpose of this work relies on defining representative current values regarding the 1st, 3rd and 5th harmonic orders to be utilized in the load signatures formulation. A measurement setup has been developed and steady-state measurements have been performed in a Low Voltage residence. A data processing methodology is proposed aiming to depict representative current values for each harmonic order in order to keep the load signature short and simple. In addition, a simple disaggregation scheme is proposed under linear equations for the disaggregation mode in order to examine the near-real time application of the methodology. The analysis indicates that the developed load signatures could be efficient for a per second application rate of the NILM algorithm. The results show that the higher harmonic currents facilitate the identification performance. Finally, the analysis concludes that for combinations that include appliances with intense harmonic content, the phase angle of the higher for harmonic currents should also be considered to the load signatures formulation.

To overcome the difficulty of accurately determining the load state of a wet ball mill during the grinding process, a method of mill load identification based on improved empirical wavelet transform (EWT), multiscale fuzzy entropy (MFE), and adaptive evolution particle swarm optimization probabilistic neural network (AEPSO_PNN) classification is proposed. First, the concept of a sliding frequency window is introduced based on EWT, and the adaptive frequency window EWT algorithm, which is used to decompose the vibration signals recorded under different load states to obtain the intrinsic mode components, is proposed. Second, a correlation coefficient threshold is used to select the sensitive mode components that characterize the state of the original signal for signal reconstruction. Finally, the MFE of the reconstructed signal is used as the characteristic vector to characterize the load state of the mill, and the partial mean value of MFE is calculated. The results show that the mean value of MFE under different load states varies. To further identify the load state, a characteristic mill load vector is constructed from the MFE values of the reconstructed signal under different load conditions and is used as the input of the AEPSO_PNN model, which then outputs the predicted ball mill load state. Thus, a load state identification model is established. The feasibility of the method is verified based on grinding experiments. The results show that the overall recognition rate of the proposed method is as high as 97.3%. Compared with the back propagation (BP) neural network, Bayes discriminant method, and PNN classification, AEPSO_PNN classification increases the overall recognition rate by 8%, 5.3%, and 3.3%, respectively, which indicates that this method can be used to accurately identify the different load states of a ball mill.

The load and angle of attack (AoA) for wing structures are critical parameters to be monitored for efficient operation of an aircraft. This study presents wing load and AoA identification techniques by integrating an optical fiber sensing technique and a neural network approach. We developed a 3.6-m semi-spanned wing model with eight flaps and bonded two optical fibers with 30 fiber Bragg gratings (FBGs) each along the main and aft spars. Using this model in a wind tunnel test, we demonstrate load and AoA identification through a neural network approach. We input the FBG data and the eight flap angles to a neural network and output estimated load distributions on the eight wing segments. Thereafter, we identify the AoA by using the estimated load distributions and the flap angles through another neural network. This multi-neural-network process requires only the FBG and flap angle data to be measured. We successfully identified the load distributions with an error range of &minus, 1.5&ndash, 1.4 N and a standard deviation of 0.57 N. The AoA was also successfully identified with error ranges of &minus, 1.03&ndash, 0.46&deg, and a standard deviation of 0.38&deg

The manufacturing and the preliminary numerical and experimental testing results of a fiber optic based sensor, able to recognize different load paths, are herein presented. This device is conceived to identify load directions by strain detection along a circumferential geometry. A demonstrator is realized by manufacturing a circular shaped, flexible glass/epoxy laminate hosting the sensible elements. Three loops of optical fiber, laying at different quotes along its thickness, are there integrated. The sensor system is supposed to be bonded on the structural element and then able to follow its deformations under load. The working principle is based on the comparison of the strain paths detected at each fiber optic loop at homologous positions. Rayleigh backscattering optical technology is implemented to measure high spatial resolution strains. A finite element model is used to simulate the sensor behavior and assess its optimal configuration. A preliminary experimental campaign and a numerical correlation are performed to evaluate sensor performance considering in-plane and bending loads.

In this paper, a load identification approach for dynamic wireless power transfer for electric vehicles is introduced. In the proposed method, determination of the load parameters and position are achieved without requiring any communication link between the transmitter and receiver or using any extra coil. The load detection procedure is achievable using two modes: the energy injection mode and the free resonant mode. The operating principles and theoretical analysis of this method are presented in this paper, together with experimental results.