Novel Fractal-Based Features for Low-Power Appliances in Non-Intrusive Load Monitoring

Non-intrusive load monitoring is a method that disaggregates the overall energy consumption of a building to estimate the electric power usage and operating status of each appliance individually.Prior studies have mostly concentrated on the identification of high-power appliances like HVAC systems while overlooking the existence of low-power appliances.Low-power consumer appliances have comparable power consumption patterns,which can complicate the detection task and can be mistaken as noise.This research tackles the problem of classification of low-power appliances and uses turn-on current transients to extract novel features and develop unique appliance signatures.A hybrid feature extraction method based on mono-fractal and multi-fractal analysis is proposed for identifying low-power appliances.Fractal dimension,Hurst exponent,multifractal spectrum and the Hölder exponents of switching current transient signals are extracted to develop various‘turn-on’appliance signatures for classification.Four classifiers,i.e.,deep neural network,support vector machine,decision trees,and K-nearest neighbours have been optimized using Bayesian optimization and trained using the extracted features.The simulated results showed that the proposed method consistently outperforms state-of-the-art feature extraction methods across all optimized classifiers,achieving an accuracy of up to 96%in classifying low-power appliances.

Online Fault Monitoring of On-Load Tap-Changer Based on Voiceprint Detection

The continuous operation of On-Load Tap-Changers (OLTC) is essential for maintaining stable voltage levels in power transmission and distribution systems. Timely fault detection in OLTC is essential for preventing major failures and ensuring the reliability of the electrical grid. This research paper proposes an innovative approach that combines voiceprint detection using MATLAB analysis for online fault monitoring of OLTC. By leveraging advanced signal processing techniques and machine learning algorithms in MATLAB, the proposed method accurately detects faults in OLTC, providing real-time monitoring and proactive maintenance strategies.

基于N-LMS算法的电流互感器异常数据智能监测方法

为了提高电流互感器异常数据智能监测的准确性,应对多工况的监测需求,设计一个基于N-LMS算法的电流互感器异常数据智能监测方法。设定电网参考电压信号的采样参数,采用随机抽样方法获取数据特征维度取值,采用等宽法处理电压数值,获得每组数据之间的关系。为了避免电压波形畸变对检测结果的影响,采用自适应滤波方法检测谐波电流,使反馈误差接近于0。提取电流互感器粗集规则,制定决策表,结合决策表判定故障发生的区段,实现基于N-LMS算法的电流互感器异常数据智能监测方法设计。实验结果表明,所设计方法在泄漏电流、电容量情况与谐波电流波形的监测上,在电流互感器A相升压过程介损监测与电流互感器A相降压过程介损监测上,都具有较高的准确度,能满足设计需求。

Event-Driven Non-Intrusive Load Monitoring Algorithm Based on Targeted Mining Multidimensional Load Characteristics

Nowadays,the advancement of nonintrusive load monitoring(NILM)has been hastened by the ever-increasing requirements for the reasonable use of electricity by users and demand side management.Although existing researches have tried their best to extract a wide variety of load features based on transient or steady state of electrical appliances,it is still very difficult for their algorithm to model the load decomposition problem of different electrical appliance types in a targeted manner to jointly mine their proposed features.This paper presents a very effective event-driven NILM solution,which aims to separately model different appliance types to mine the unique characteristics of appliances from multi-dimensional features,so that all electrical appliances can achieve the best classification performance.First,we convert the multi-classification problem into a serial multiple binary classification problem through a pre-sort model to simplify the original problem.Then,ConTrastive Loss K-Nearest Neighbour(CTLKNN)model with trainable weights is proposed to targeted mine appliance load characteristics.The simulation results show the effectiveness and stability of the proposed algorithm.Compared with existing algorithms,the proposed algorithm has improved the identification performance of all electrical appliance types.

Exploring CNN Model with Inrush Current Pattern for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring(NILM)has gradually become a research focus in recent years to measure the power consumption in households for energy conservation.Most of the existing algorithms on NILM models independently measure when the total current load of appliances occurs,and NILM usually undergoes the problem of signatures of the appliance.This paper presents a distingue NILM design to measure and classify the appliances by investigating the inrush current pattern when the alliances begin.The proposed method is implemented while the five appliances operate simultaneously.The high sampling rate of field-programmable gate array(FPGA)is used to sample the inrush current,and then the current is converted to be image patterns using the kurtogram technique.These images are arranged to be four groups of data set depending on the number of appliances operating simultaneously.Furthermore,the five proposed modifications convolutional neural networks(CNN),which is based on very deep convolutional networks(VGGNet),are designed by adjusting the size to decrease the training time and increase faster operation.The proposed CNNs are then implement as a classification model to compare with the previous models.The F1 score and Recall are used to measure the accuracy classification.The results showed that the proposed system could be achieved at 99.06 accuracy classification.

Solid Model Bridge Static Damage Monitoring Based on GBSAR

Bridge deformation monitoring usually adopts contact sensors,and the implementation process is often limited by the environment and observation conditions,resulting in unsatisfactory monitoring accuracy and effect.Ground-Based Synthetic Aperture Radar(GBSAR)combined with corner reflectors was used to perform static load-loaded deformation destruction experiments on solid model bridges in a non-contact manner.The semi parametric spline filtering and its optimization method were used to obtain the monitoring results of the GBSAR radar’s line of sight deformation,and the relative position of the corner reflector and the millimeter level deformation signals under different loading conditions were successfully extracted.The deformation transformation model from the radar line of sight direction to the vertical vibration direction was deduced.The transformation results of deformation monitoring and the measurement data such as the dial indicator were compared and analyzed.The occurrence and development process of bridge deformation and failure were successfully monitored,and the deformation characteristics of the bridge from continuous loading to eccentric loading until bridge failure were obtained.The experimental results show that GBSAR combined with corner reflector can be used for deformation feature acquisition,damage identification and health monitoring of bridges and other structures,and can provide a useful reference for design,construction and safety evaluation.

基于LMS Virtual Lab对多孔同心式液压脉动衰减器的优化研究

多孔同心式液压脉动衰减器采用穿孔管作为压力脉动的衰减部件,通过改变穿孔管的阻抗特性,避开系统的流固耦合谐振点。传统的衰减器在低频段衰减效果良好,但在中频和高频效果欠佳。通过改变穿孔管内部穿孔段的孔径、管壁厚度、穿孔率来优化衰减器在中频和高频段的衰减效果。在LMS Virtual.Lab Acoustics的管道声学有限元模块中应用了传递导纳函数,通过常温下衰减器的传递损失计算,得到衰减器在中频和高频段良好的衰减性能,并通过两负载法进行实验论证。

基于SMI-LMS的自适应旁瓣干扰抑制算法研究

提出基于SMI-LMS的自适应旁瓣干扰抑制算法,即利用采样矩阵求逆(SMI)算法计算初始权值,并以此作为LMS算法的初值。通过比较分析LS-LMS和SMI-LMS的方向图增益和运算量,并运用对角加载技术对SMI-LMS算法作出改进,验证了SMI-LMS算法的优势。仿真实验表明,SMI-LMS算法具有快的收敛速度和低的算法复杂度,在低快拍下有着好的性能。

Process Monitoring and Terminal Verification of Cable-Stayed Bridges with Corrugated Steel Webs under Contruction

In this paper,the construction process of a cable-stayed bridge with corrugated steel webs was monitored.Moreover,the end performance of the bridge was verified by load test.Owing to the consideration of the bridge structure safety,it is necessary to monitor the main girder deflection,stress,construction error and safety state during construction.Furthermore,to verify whether the bridge can meet the design requirements,the static and dynamic load tests are carried out after the completion of the bridge.The results of construction monitoring show that the stress state of the structure during construction is basically consistent with the theoretical calculation and design requirements,and both meet the design and specification requirements.The final measured stress state of the structure is within the allowable range of the cable-stayed bridge,and the stress state of the structure is normal and meets the specification requirements.The results of load tests show that the measured deflection values of the mid-span section of the main girder are less than the theoretical calculation values.The maximum deflection of the girder is−20.90 mm,which is less than−22.00 mm of the theoretical value,indicating that the girder has sufficient structural stiffness.The maximum impact coefficient under dynamic load test is 1.08,which is greater than 1.05 of theoretical value,indicating that the impact effect of heavy-duty truck on this type of bridge is larger.This study can provide important reference value for construction and maintenance of similar corrugated steel web cable-stayed bridges.

Health Monitoring-Based Assessment of Reinforcement with Prestressed Steel Strand for Cable-Stayed Bridge

This paper presents the method of reinforcing main girder of reinforced concrete cable-stayed bridge with prestressed steel strands.To verify the effectiveness of external prestressed strand reinforcement method.Static load tests and health monitoring-based assessment were carried out before and after reinforcement.Field load test shows that the deflection and stress values of the main girder are reduced by 10%~20%after reinforcement,and the flexural strength and stiffness of the strengthened beam are improved.The deflection and strain data of health monitoring of the specified section are collected.The deflection of the second span is 4 mm~10 mm,the strain range of the upper edge of the second span is-10με~-40με,and the strain range of the lower edge is 30με~75με.These values show the deflection and strain values fluctuate within a prescribed range,verifying the safety of the bridge.The reinforcement method of prestressed steel strand is feasible and effective.It can provide reference basis for the application of external prestressed strand reinforcement technology in similar projects.

A coal rib monitoring study in a room-and-pillar retreat mine

The National Institute for Occupational Safety and Health(NIOSH)conducted a comprehensive monitoring program in a room-and-pillar mine located in Southern Virginia.The deformation and the stress change in an instrumented pillar were monitored during the progress of pillar retreat mining at two sites of different geological conditions and depths of cover.The main objectives of the monitoring program were to better understand the stress transfer and load shedding on coal pillars and to quantify the rib deformation due to pillar retreat mining;and to examine the effect of rib geology and overburden depth on coal rib performance.The instrumentation at both sites included pull-out tests to measure the anchorage capacity of rib bolts,load cells mounted on rib bolts to monitor the induced loads in the bolts,borehole pressure cells(BPCs)installed at various depths in the study pillar to measure the change in vertical pressure within the pillar,and roof and rib extensometers installed to quantify the vertical displacement of the roof and the horizontal displacement of the rib that would occur during the retreat mining process.The outcome from the monitoring program provides insight into coal pillar rib support optimization at various depths and geological conditions.Also,this study contributes to the NIOSH rib support database in U.S coal mines and provides essential data for rib support design.

Development of All-Weather and Real-Time Bottom-Mounted Monitor of Bed Load Quantity

Quantity of bed load is an important physical parameter in sediment transport research. Aiming at the difficulties in the bed load measurement, this paper develops a bottom-mounted monitor to measure the bed load transport rate by adopting the sedimentation pit method and resolving such key problems as weighing and desilting, which can achieve long-time, all-weather and real-time telemeasurement of the bed load transport rate of plain rivers, estuaries and coasts. Both laboratory and field tests show that this monitor is reasonable in design, stable in properties and convenient in measurement, and it can be used to monitor the bed load transport rate in practical projects.

基于UMAP流形特征提取和KELM的非侵入式负荷监测方法研究

非侵入式负荷监测是“坚强智能电网”用户侧智能数据挖掘的关键技术。针对现有辨识算法对叠加态负荷辨识准确率低的问题,提出了一种基于均匀流形逼近与投影(UMAP)和KELM结合的非侵入式负荷辨识模型。首先利用UMAP对原始负荷特征作嵌入,提取负荷的类内流形结构,并结合随机梯度下降法优化负荷的全局结构,在保留负荷原始相邻位置信息的前提下有效增大负荷特征的区分度;然后,采用径向基函数搭建核映射网络,利用ACO算法对映射网络的径向范围和模型的惩罚系数寻优,建立最优辨识模型。与多种基于机器学习的辨识方法相比,所提模型对叠加态负荷的辨识准确率提升显著,在TIPDM和BLUED数据集上的辨识准确率分别达到了98.48%和99.44%。

A Review of NILM Applications with Machine Learning Approaches

In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power grid.Furthermore, by integrating Machine Learning (ML), NILM can efficiently use electrical energy and offer less ofa burden for the energy monitoring process. However, conducted research works have limitations for real-timeimplementation due to the practical issues. This paper aims to identify the contribution of ML approaches todeveloping a reliable Energy Management (EM) solution with NILM. Firstly, phases of the NILM are discussed,along with the research works that have been conducted in the domain. Secondly, the contribution of machinelearning approaches in three aspects is discussed: Supervised learning, unsupervised learning, and hybridmodeling.It highlights the limitations in the applicability of ML approaches in the field. Then, the challenges in the realtimeimplementation are concerned with six use cases: Difficulty in recognizing multiple loads at a given time,cost of running the NILM system, lack of universal framework for appliance detection, anomaly detection andnew appliance identification, and complexity of the electricity loads and real-time demand side management.Furthermore, options for selecting an approach for an efficientNILMframework are suggested. Finally, suggestionsare provided for future research directions.

IoT Based Nurse Activities Monitoring and Controlling System

IoT technology has emerged as a valuable tool in modern healthcare, providing real-time monitoring of patients, effective management of healthcare, and proper administration of patient information. The proposed system aims to develop a system that can prevent backward blood flow from stopping saline fluid, as well as monitor the temperature, heart rate, and oxygen level of patients by using multiple sensors like weight, temperature and heart rate, etc. Additionally, the proposed system can monitor the room temperature and humidity for contributing to the patient’s overall comfort. In emergency situations, it includes an emergency push button for quick alert medical staff and initiates timely interventions. It is designed to support nurses and doctors in monitoring patients and providing timely interventions to prevent complications.

Field Load Test Based SHM System Safety Standard Determination for Rigid Frame Bridge

The deteriorated continuous rigid frame bridge is strengthened by external prestressing. Static loading tests wereconducted before and after the bridge rehabilitation to verify the effectiveness of the rehabilitation process. Thestiffness of the repaired bridge is improved, and the maximum deflection of the load test is reduced from 37.9 to27.6 mm. A bridge health monitoring system is installed after the bridge is reinforced. To achieve an easy assessmentof the bridge’s safety status by directly using transferred data, a real-time safety warning system is createdbased on a five-level safety standard. The threshold for each safety level will be determined by theoretical calculationsand the outcomes of static loading tests. The highest risk threshold will be set at the ultimate limit statevalue. The remaining levels, namely middle risk, low risk, and very low risk, will be determined usingreduction coefficients of 0.95, 0.9, and 0.8, respectively.

基于遗传LM算法的分布式电网异常负荷自动识别方法

传统分布式电网异常负荷自动识别方法直接对电网负荷数据实施分类,未进行预处理,识别错误率较高。提出基于遗传LM算法的分布式电网异常负荷自动识别方法。首先,预处理采集到的分布式电网异常负荷数据;其次,通过遗传算法生成初始种群,其中,每个个体对应一个电网负载数据、异常负荷特征的参数组合;然后,利用LM算法的局部优化特性对电网数据参数组合进行局部优化,对遗传算法进行改进,计算其适应度,得到准确的电网负荷数据异常分类结果;最后,进行电力负荷异常值的识别。结果表明,该研究方法识别错误率更低,具有实用性。

基于NILM的电子仪器监管系统设计

阐述为解决电子仪器管理中的用电侧监测缺失以及开放性不足问题,设计基于NILM的电子仪器监测系统,其中,监测节点用于负荷数据的采集与预处理,服务器负责数据统计与负荷辨识,用户端则实现用户预约和信息查询等功能。

基于NILM技术的家庭用户精确负荷建模方法

结合非侵入负荷监测NILM系统的负荷辨识流程,本文提出了一种基于NILM技术的家庭用户精确负荷建模方法。该方法应用NILM技术提取家庭主要设备负荷特性。然后通过模糊C聚类法实现家庭负荷模型归类,获得设备针对不同电价的转移灵敏度和自灵敏度用电特性,并在此基础上形成家庭负荷特性。通过电网公司分时电价环境下实测的家庭典型用电负荷数据验证可知,空调、洗衣机、热水器、电动汽车具有较大的弹性,其中洗衣机的自弹性和交叉弹性最大,在高电价时段可削减100%。该方法所获得的家庭负荷辨识的结果,可支持居民电价/激励等需求侧管理政策的制定,也可支持用户家庭用电设备状态监测服务等。

嵌入式NILM电力负荷识别及特征库构建系统设计

针对非侵入式电力负荷识别系统负荷特征库构建困难,算法复杂,硬件成本高的问题,构建了基于STM32嵌入式处理的电力负荷采集识别系统。介绍了系统硬件结构。分析了基于嵌入式处理器的电力数据通信方式。设计了低复杂度的快速滤波算法和基于最小二乘的负荷状态监测、识别算法。基于本系统,对常见家用电力负荷实际工作状态进行了实测。测试数据分析表明本系统的综合识别率符合要求,且算法更加适用于嵌入式硬件结构。系统硬件成本低,有利于推广应用。