A Fuzzy Regression Method for Long-Term and Medium-Term Load Forecasting

In view of the observation data fuzziness and load pattern fuzziness,a new fuzzy regression prediction method was presented for long-term and medium-term load forecasting. With the established fuzzy regression model, the future load value can be forecasted based on the fuzzy historical observation data. The validity of the proposed method was verified with the numerical example of a practical system.     

The Application of Fuzzy Theory to Power Load Forecasting

A new method was presented for power load forecasting.Based on the fuzzyclustering technique,the historical samples of power load and its relative environmental factors wereclassified into several typical categories,the fuzzy numbers and sets were then used to describe thepatterns of load variation and the features of the environmental factors for every class. Finally,byunderstanding the state of future environmental factors, the future power load can be predictedthrough determining the category of load variation pottern. The validity of the proposed method wasverified with a practical medium-term load forecasting.     

Real time monitoring for multivariate statistical process with on line multiscale filtering

By analyzing shortages of current MSPCA model, an on line multi variable statistical process monitoring method is proposed, which uses some concepts from online multi scale filtering and can be applied to sensor fault diagnosis. In the method, wavelet decomposition is employed to the signals using edge correction filter in a fixed length data window, and then wavelet denoising is conducted with wavelet threshold filtering. Next, an on line multi scale model is constructed for data combining wavelet transformation and adaptive PCA in the previous data window. This model avoids time waste in direct signal denoising and reduces time cost in multi scale data with conventional PCA, which eventually increases accuracy in fault diagnosis. Experiments on eight vibration signals of 6135D diesel engine under severe leak condition prove the practicability and feasibility of the proposed method.     

Intelligent Extracting Method for Feature Mode of Electric Days Load

Generally there have a number of bad data in the electric load data and it affects the precision of load forecasting,so it is necessary for extracting the feature mode of days load data,then cleaning the load data before it is used to forecasting electric load or performing power system analysis.Inspired by soft clustering thought,a intelligent feature mode of days load data extracting method is proposed based on the mutual offset of fuzzy c-means clustering arithmetic and Kohonen self organization feature map neural network.With the merits of not only high extracting precision and convergent speed but also dynamic calculation capability,the method proposed can supply load forecasting or system analysis procedure with due data.Test results using actual data of Chengqu power supply bureau in Chongqing demonstrate the effectivity and feasibility of the method.     

Parameter optimized Morlet wavelet de noising method based on cross validation method

A new de noising method based on parameter optimized Morlet wavelet is put forward. The Morlet wavelet is chosen as the mother wavelet because its shape is similar to the mechanical shock signals. The mother Morlet wavelet is improved by adding two parameters which decide the shape of the mother wavelet in time domain. The added parameters and the appropriate scale parameter for the wavelet transformation are designed by the cross validation method. Finally, the useful components of the signal can be obtained by the improved Morlet wavelet de noising method. The gear fault diagnosis experimental result shows that the proposed method has a good de nosing performance and it is effective in fault feature extraction.     

Cellular automata spatial temporal data model and forecasting approach

The standard cellular automata(CA) model is expanded to meet requests of space time dynamic simulation and forecast under the platform of geographic information system(GIS). Taking power load forecasting of the electric power industry as the specific application, the relations between dynamic model of the land use and power load space are established. The data and attribute data interactive discrete in spatial temporal data management have been solved. The CA theory is practically used to simulate the process of urban land use dynamic development, to forecast future land use types of each small area, to establish spatial load forecasting model. It breaks through the localization of all kinds of forecasting methods of traditional space time separation power prediction. The effectiveness of the prediction method is verified by example.     

Application of Combination Grey Model in Power Load Forecasting

Based on the gray forecast theory, this paper studies the principle and deficiency in power load forecasting by the basic grey model and other improved models, and introduces a new method -the combination grey model to forecast the long-medium power load. Based on an example, the basic grey model, other improved models and combination grey model are used to forecast power load and results of all models are analyzed and compared. The calculation results show that forecasting power load by grey theory is credible and simple. For this type of complex problems such as forecasting the long-medium power load, the combination grey model is specially useful because of it's high precision and facility. The method can be used as one of the tools of forecasting the long-medium power load.     

Detecting a fault line under a single phase to ground of distribution network based on analysis of multi frequency bands

Addressing the problem of choosing a fault line under single phase to ground of distribution network, we presented a new criterion based on analysis of the development of fault line selection and a method using wavelet packets. The feature frequency band, or the combined feature frequency bands of each line, in which the transient capacity current was concentrated was chosen for maximum energy. Based on the principle that the transient capacity current's energy of the fault line was larger than the that of normal lines, fault line selection can be carried out adaptively by contrasting the energy of the transient capacity currents of all lines in each chosen frequency band. The simulation results and spot testing data shows the proposed method can detect the fault line in distribution networks precisely and reliably.     

A New Method of Diesel Engine Fuel System Fault Diagnosis

A method of diesel engine fuel system fault diagnosis based on wavelet transform and fuzzy C-means clustering is presented. Five characteristic parameters of reflecting fault state are distilled with wavelet transform of pressure wave of high-pressure oil pipe of diesel. The theory and generic approach of fuzzy C-means clustering algorithm (FCM) is given, and the validity of evaluating fuzzy clustering making use of partition coefficient, partition entropy and parting coefficient is pointed out. Identification of fault mode can be completed utilizing standard fault character modes established by FCM algorithm, and calculating and comparing the similarity degree between this standard mode and sample. The arithmetic is applied to all kinds of typical faults diagnose in the diesel engine fuel system. Measuring results indicate that the precision of fault diagnosis is increased with the analysis of wavelet and FCM.     

Application of higher density wavelet transform to composite fault diagnosis of rolling bearing

Aiming at the difficulties in accurate reorganization of several weak faults currently, a composite fault diagnosis method based on higher density discrete wavelet transform and envelope spectrum is proposed. Firstly, the higher density discrete wavelet transform is used to decompose acquired vibration signals of rolling bearings. Then, the single-subband reconstruction is performed on the wavelet coefficients and scaling coefficients at each scale in order to solve frequency aliasing. Finally, the envelope spectra of all subband signals are calculated, and all faults can be recognized according to the characteristic frequencies of the typical faults. The proposed method is applied to the diagnosis of the rolling bearings with composite faults, and is compared with other common fault diagnosis method. The results show that the proposed method can be effectively used for the early composite fault diagnosis of rolling bearings.     

Application of data mining method in power load bad data intelligent identification and correction

There is a number of bad data in the load database produced, thus the data must be cleaned before it is used to forecasting electric load or performing power system analysis. The WKFCM measures distance by kernel functions instead of the complicated Euclidean distance and this kernel based distance is used as dissimilarity function of target clustering formula which can reduce the calculation complexity. After the clustering, a super circle covering neural network based identification model for load data is proposed, and the bad data is modified. It is proved that the proposed data processing model has good effect.     

Application of Attribute Reduct Method in Spatial Load Forecasting

Spatial load forecasting is a process distributing the total forecasted load to all partitioned area, and involving more spatial information and more factor influencing application of the future small area, which need a great deal of memory space and longer operation time. Rough set is new method of data analysis. It need not be provided with any advanced information except data set. But attribute reduct is its main algorithms. Division matrix approach on rough set used to reduce the attribute related to land - use decision in order to remove redundancy attribute and then the rules of small area land - use decision is distilled. The method obtained better effect and enhanced the total load forecasting efficiency.     

THE NEW PHASE SELECTION SCHEMES ON USE OE FAULT COMPONENT

In accordance with the characteristic of digital relay and fault locatoin four methods of phase selection on fault component are presented in this paper.These methods are simple in principle, reliable in action, and immune from load flow,system oscillation.Hardly affected by fault location, source impedance and fault resistance, they can select fault phase reliably for any power system and fault type.As phase selection schemes, they can be used for perfect digital relay.     

analysis and application of demand forecasting model with multi element variable parameters

A forecasting model for logistics demand was presented to overcome the limitations of single goal forecasts of logistics demand and forecast data complexity. Based on the forecasting evaluation index and pretreatment of rough set theory, a multi input and multi output wavelet network (MMWNN) model for forecasting multi element regional logistics demand was studied. The network configuration was confirmed using the stepwise checkout and iterative gradient descent methods. After rough set reduction, the evaluation index was used to forecast the multi element regional logistics demand. The results of the numerical example indicate the feasibility and effectiveness of the model.     

Short-Term Electric Load Forecasting Based Trends Combination Model

In short term load forecasting based on ANN,weather is one of the important factors which impacts on load greatly. In order to capture the effect of weather on load, this paper presents a novel thought based on ANN and trends combination short term load forecasting. Decompose the underlying relationships between load and weather variables into three main trends of weekly, daily and hourly. Three separated ANNs capture each trend. Another ANN to arrive at the final forecast combines the forecasts yielded by individual ANNs. The performances of the proposed model and the traditional model are compared on the basis of one week ahead hourly forecasts. Results indicate that the proposed ANN based model can achieve greater forecasting accuracy than the traditional ANN based model.     

Simulation and Protective Algorithm of Power Transformers Considering Hysteresis Effect

Based on the study on the properties of Magnetic Inrush Current and Fault Current of power transformers, Saber is applied to realize the simulation of such conditions as no-load closing and all the fault conditions including turn-to-turn fault and turn-to-earth fault. Grounded on the wavelet analysis theory, a new method is proposed which can differentiate effectively the internal and external faults and detect the turn-to-turn fault. The simulation result shows its effectiveness.     

Time-frequency Characteristic of Wavelet Base and Its Application Transient Signal Detection

The application of wavelet analysis in fault diagnosis is growing rapidly.There are many different wavelet base to use but no accepted procedure for choosing among them, the analysis results by using them have great difference. This paper describes the significant properties of wavelet base, and analysis behavior of transient signal in wavelet transform, result on some methods for how to choose wavelet base in analysis transient signal.     

Local Nonlinear Forecasting of Short-term Power Load Forecasting

The nearest points in phase space are determined by Euclid distance in chaotic local prediction. The prediction accuracy depends on quality of the nearest points. But the shortest distance does not imply better forecasting effect. While false nearest neighboring point or high embedding dimensions appear evolvement track of some nearest neighboring point should be apart from prediction point. Because it is difficult for Euclid distance to reflect the correlation degree between the nearest points and prediction point. So the idea of combining Euclid distance with correlation degree is put forward. The method is applied to short-term electrical load forecasting. The result of load series forecasting by the presented method is more effective to improve prediction accuracy.     

新疆石河子冻土特征及冻土融化期地温、冻土深度预报研究

为了确保春季播种安全,有必要开展播种期地温的监测和冻土融化深度预报业务。利用新疆农八师冻土气象观测资料,运用相关系数和线性回归方法,分析冻土特征及融化过程中地温变化、深度变化规律,建立春季冻土融化预报模型。结果表明,新疆农八师垦区稳定冻土期在11月中旬至翌年3月下旬,冻土最大深度呈逐年变浅趋势,倾向率为-5.4 cm/10 a;冻土结冻日期推后,倾向率为2.0 d/10 a;冻土化通日期提前,倾向率为-1.5 d/10 a。冻土融化期在3月中旬至4月上旬,冻土融化速率在3.1~4.0 cm/d之间。春季地温与平均气温、冻土融化深度与正积温具有显著的正相关,以此建立了相应的预报模型。10 cm地温预报模型历史回代准确率在96%以上,冻土融化深度预报模型历史回代准确率在94%以上。通过模型可以开展春季地温和土壤融化预报业务。     

The Signals Analysis System Based on Fast Wavelet Transform

The fast wavelet transform (FWT) algorithm in wavelet analysis was introduced in the paper. With quadrature mirror filters (QMF) associated with popular wavelet bases, the fast wavelet decomposition and reconstruction for signals were implemented. Combined with virtual instrument technique, the FWT analysis system for signals was successfully developed. The system can break up signal not only into approximations, which are the high-scale and low-frequency components of the signal, but also into details which are the low-scale and high-frequency components. Especially it can identify singularity signal, which contain some important message of equipment condition and fault, and refine signal from noisy signal, which is corrupted by noise.