WO2020114449A1 - 风电场机组运行状态的动态评估方法、装置及电子设备 - Google Patents

风电场机组运行状态的动态评估方法、装置及电子设备 Download PDF

Info

Publication number
WO2020114449A1
WO2020114449A1 PCT/CN2019/123254 CN2019123254W WO2020114449A1 WO 2020114449 A1 WO2020114449 A1 WO 2020114449A1 CN 2019123254 W CN2019123254 W CN 2019123254W WO 2020114449 A1 WO2020114449 A1 WO 2020114449A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
principal component
matrix
wind farm
dynamic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/123254
Other languages
English (en)
French (fr)
Inventor
郭媛君
杨之乐
于建强
朱俊丞
王颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Publication of WO2020114449A1 publication Critical patent/WO2020114449A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Definitions

  • the invention belongs to the technical field of state assessment of wind farm units, and particularly relates to a dynamic assessment method, device and electronic equipment of the operation state of wind farm units.
  • Wind energy is safe, clean, abundant and stable.
  • the use of wind energy will effectively alleviate the contradiction between supply and demand of resources and the degree of environmental pollution.
  • my country's research and investment in wind power has entered a new stage of development.
  • the damage and damage accidents of wind farm units have increased year by year.
  • Wind farm units are generally located in remote and harsh areas, and it is difficult to perform maintenance work on the units in time, which increases the capital and labor costs of wind farm unit operation and maintenance. Therefore, how to quickly detect potential faults in real time in the operation state of wind farm units and optimize the operation plan is currently the key research direction of wind farm units.
  • the principal component analysis method is a multivariate statistical analysis method, using the idea of dimensionality reduction to convert multiple indicators into several comprehensive indicators.
  • the principal component analysis method is to project the high-dimensional information into the low-dimensional subspace and retain the original information of the data to the greatest extent.
  • the basic idea is to find a new set of low-dimensional variables to replace the high-dimensional original variables, and the new variables are the original variables. Linear combination.
  • the low-dimensional new variable data more intensively reflects the change information contained in the original variable data.
  • the primary and secondary status of the direction of change is determined according to the variance of the data change, and the primary component is obtained in the order of primary and secondary, which is called the first principal component , The second principal component, etc. These principal components are independent of each other.
  • Dynamic principal component analysis is a new multivariate statistical modeling method that combines the construction of dynamic sequence data and principal component analysis. This method uses dynamic time series to expand the static data of the original variables into dynamic time data. Through the analysis of the dynamic time data, the complexity of the original data analysis can be simplified, and the dynamic relationship between the system variables can be effectively extracted to ensure the prediction accuracy. Improve the efficiency of assessment under the circumstances.
  • the so-called power curve of wind turbine generally refers to the relationship curve of the output power of wind turbine with the change of wind speed.
  • the actual efficiency of the wind turbine is mainly reflected by the actual power curve of the wind turbine.
  • the actual power curve reflects the economic efficiency of the wind turbine.
  • a single performance curve can only reflect whether the operation of the wind farm or a single unit is good and whether the economy meets the standard. There are still many deficiencies in discovering potential hazards and finding the source of the fault. If all operating data are plotted, and comparative observations will be made one by one, although the overall operating status can be grasped, the workload is heavy and time-consuming, and it is not an efficient evaluation method.
  • the purpose of the present invention is to provide a method, device and electronic device for dynamically evaluating the operating state of a wind farm unit, aiming to solve the problem that the prior art cannot accurately and efficiently perform real-time dynamic evaluation of the operating state of a wind farm unit.
  • the present invention provides a method for dynamically evaluating the operating status of wind farm units, the method including the following steps:
  • the running state of the wind farm unit is judged by the principal component.
  • the steps of preprocessing the operation data of the wind farm unit to obtain a data matrix include:
  • the operation data modified by the erroneous data is constructed as a data matrix.
  • the step of constructing the operation data modified by the error data into a data matrix includes:
  • the step of constructing the dynamic augmentation matrix of the data matrix according to the time lag length includes:
  • the time-lag augmentation matrix is standardized to obtain a dynamic augmentation matrix.
  • the step of calculating the time lag length of the operation data includes:
  • the target time lag length is determined according to the static relationship number and the dynamic relationship number.
  • the principal component contribution rate is calculated according to the eigenvalues and eigenvectors of the covariance matrix, and the steps of selecting the principal components include:
  • the principal component contribution rate is calculated by the principal component score and the corresponding principal component coefficient, and the principal component is selected.
  • the step of determining the operating state of the wind farm unit by the principal component includes:
  • the running state of the wind farm unit is judged by comparison of the complained data graphics.
  • a dynamic assessment device for the operating status of wind farm units including:
  • Pre-processing module used to pre-process the operation data of wind farm units to obtain a data matrix
  • a dynamic augmentation matrix calculation module used to construct the dynamic augmentation matrix of the data matrix according to the target delay time
  • a covariance matrix calculation module used to calculate the covariance matrix of the dynamic augmentation matrix by a principal component analysis method
  • the principal component contribution rate calculation module is used to calculate the principal component contribution rate according to the eigenvalues and eigenvectors of the covariance matrix, and select the principal component;
  • the operation state judgment module is used to judge the operation state of the wind farm unit through the main component.
  • an electronic device including:
  • a memory communicatively connected to the processor; wherein,
  • the memory stores readable instructions, which when executed by the processor implement the method of the first aspect.
  • a computer-readable storage medium on which a computer program is stored, and when executed, the computer program implements the method as in the first aspect.
  • the principal component analysis method is applied to the dynamic process, and the dynamic relationship between the variables in the operation data of the wind farm unit is analyzed according to the target time lag length, so as to be more accurate and Efficiently evaluate the operation status of wind farm units in real time.
  • FIG. 1 is an implementation flowchart of a dynamic assessment method for the operating state of a wind farm unit provided in Embodiment 1 of the present invention
  • FIG. 2 is a flowchart of a method for calculating a time lag length according to Embodiment 1;
  • FIG. 3 shows a block diagram of a dynamic evaluation device for the operating state of a wind farm unit provided in Embodiment 2 of the present invention
  • FIG. 4 is a schematic diagram of the principal component contribution rate when dynamically evaluating the operation state of a wind farm unit provided by Embodiment 3 of the present invention.
  • FIG. 5 is a schematic diagram of the principal component scores of different operating conditions when dynamically evaluating the operating state of the wind farm unit provided by Embodiment 3 of the present invention.
  • FIG. 6 is a schematic drawing of the characteristic values of the covariance matrix under three operating conditions when dynamically evaluating the operating state of the wind farm unit provided by Embodiment 3 of the present invention
  • FIG. 7 is a structural block diagram of an electronic device 100 according to Embodiment 4 of the present invention.
  • FIG. 1 shows an implementation process of the dynamic evaluation method of the operating state of the wind farm unit provided by Embodiment 1 of the present invention.
  • the dynamic evaluation method of the operating state of the wind farm unit provided by Embodiment 1 can be operated with various electronic devices such as computers, servers, etc.
  • electronic devices such as computers, servers, etc.
  • Step S110 Pre-process the operation data of the wind farm unit to obtain a data matrix.
  • the embodiments of the present invention are applicable to electronic devices such as computers and servers. Processors are provided in these electronic devices to dynamically evaluate the operating status of wind farm units.
  • Operating data is various data generated during the operation of wind farm units, such as temperature, power, pressure and other data.
  • the operation data of wind farm units changes with time and is itself stray. Therefore, by preprocessing the operation data, the stray operation data is converted into a data matrix, and then the data matrix Processing can facilitate data modeling and analysis, and effectively improve the efficiency of data processing.
  • Data preprocessing refers to processing the operating data, retaining the most important data information, and constructing a data matrix.
  • data preprocessing may include data cleaning and data standardization:
  • the original operation data of the wind farm unit needs to be checked for data consistency. According to the reasonable value range and mutual relationship of each data, check whether the data meets the requirements. If you find data that is beyond the normal range, logically unreasonable, or contradictory, you need to modify or delete the data, and use the sample mean and median of a certain data to estimate the data, instead of missing data. For example, for invalid data obtained partly due to the short stoppage of the detection equipment or the transient interruption of the wind turbine, the data needs to be deleted to maintain the continuity of the data.
  • the dimensions of various data indicators are different, and the dispersion of data values is relatively large.
  • the overall variance will be controlled by a data with a large variance. Therefore, in order to further improve the accuracy of data processing and try to avoid errors, standardize the data to eliminate the effect of dimensionality, and then build a data matrix in the standardization process.
  • the Z-score standardization method is based on the data mean and standard deviation to standardize the data.
  • Step S120 construct a dynamic augmentation matrix of the data matrix according to the target time lag length.
  • the target time lag length is the time range related to the actual running data in time series.
  • the target time lag length may be preset or calculated based on specific operating data.
  • the adaptive time lag length L can be calculated to find the most relevant time series range, so as to extract the disturbance factors of the process to the greatest extent, and to predict the location of the upcoming fault to the greatest extent.
  • the length of time lag is gradually increased, according to the recursive formula Calculate the new dynamic relationship number, when r new (l) ⁇ 0, that is, there is no new static and dynamic relationship, then L is the target delay time.
  • FIG. 2 is a flowchart of a method for calculating a lag length according to the first embodiment.
  • step S130 the covariance matrix of the dynamic augmentation matrix is calculated by the principal component analysis method.
  • PCA Principal Components Analysis
  • PCA is a technique for simplifying data sets. It is a linear transformation. This transformation transforms the data into a new coordinate system so that the first large variance of any data projection is at the first coordinate (called the first principal component), and the second largest variance is at the second coordinate (the second principal Ingredients), and so on.
  • Principal component analysis methods are often used to reduce the dimensionality of the data set, while maintaining the features of the data set that contribute the most to the variance. This is done by preserving low-order principal components and ignoring high-order principal components. Such low-order components can often retain the most important aspects of the data.
  • the data matrix is expanded according to the calculated delay length, and the delay augmentation matrix with L delay lengths can be expressed as:
  • the dynamic data matrix X(l) is standardized by the Z-score standardization method to obtain the dynamic augmented matrix.
  • Step S140 Calculate the principal component contribution rate according to the eigenvalues and eigenvectors of the covariance matrix, and select the principal component.
  • the data analysis stage is based on the principal component analysis method. During the evaluation and analysis of the operating state, the principal component is extracted according to the contribution rate of the principal component, and the principal component is analyzed to determine the operation state of the wind farm.
  • Each working condition analysis method is similar.
  • the following uses a working condition as an example to illustrate the analysis process of this embodiment.
  • the covariance matrix of the dynamically augmented data matrix is obtained by the PCA method, and the relationship between the dimensions and the dimensions is measured, so that the matrix eigenvalues are easy to find:
  • the principal component analysis can decompose the dynamic augmentation matrix into the sum of the product of the load vector p i and the score vector t i plus the residual error E:
  • K in the formula represents the number of selected principal elements, which is used to represent the principal element space with the largest variance in the data. Normally, the number of principal elements selected for k can contain 95% of the total variance of the data.
  • the top k components with a cumulative contribution rate greater than 95% can be used as the main components.
  • step S150 the running state of the wind farm unit is determined by the main component.
  • the running state of the wind farm unit can be judged by calculating the principal component score.
  • the wind farm unit can be more accurately and efficiently evaluated in real time Running status.
  • FIG. 3 shows a block diagram of a dynamic evaluation device for the operating state of a wind farm unit provided in Embodiment 2 of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown, including:
  • the preprocessing module 110 is used to preprocess the operation data of the wind farm unit to obtain a data matrix
  • the dynamic augmentation matrix calculation module 120 is configured to construct the dynamic augmentation matrix of the data matrix according to the target time lag length;
  • the covariance matrix calculation module 130 is used to calculate the covariance matrix of the dynamic augmentation matrix by the principal component analysis method
  • the principal component contribution rate calculation module 140 is used to calculate the principal component contribution rate according to the eigenvalues and feature vectors of the covariance matrix, and select the principal component;
  • the operation state judgment module 150 is used to judge the operation state of the wind farm unit through the principal component.
  • each module of the dynamic evaluation device of the operation status of the wind farm unit may be implemented by a corresponding hardware or software unit, and each module may be an independent software or hardware module, or may be integrated into one software or hardware unit. It is not used here to limit the invention.
  • each module reference may be made to the description of Embodiment 1, and details are not described herein again.
  • Embodiment 3 is an embodiment of the result of the principal component analysis of the dynamic evaluation method of the operating state of the wind farm unit provided by the present invention.
  • the data working conditions are divided, and the working conditions are divided into three types.
  • the scores of the first and third principal components of the three working conditions are plotted, as shown in Figures 5(a) and 5(b). And 5(c). It can be clearly seen from the figure that the shape of the principal component scores of the first and the third working conditions are similar, and the value range of the principal component scores is also roughly the same, while the principal component scores of the second working conditions are obviously different. Dispersed and discontinuous, so preliminary judgments were made that abnormal conditions occurred during unit operation in the second operating condition.
  • Figures 6(a), 6(b), and 6(c) are bar graphs drawn according to the eigenvalues of the covariance matrix under three operating conditions. From this figure, it can be seen that the first principal under the second operating condition The characteristic value of the component is obviously higher than the characteristic value under the first and third working conditions, thus further confirming that the operation of the wind farm unit has failed under the second working condition.
  • FIG. 7 shows a structural block diagram of an electronic device 100 provided by Embodiment 4 of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown.
  • the electronic device 100 may include one or more of the following components: a processing component 101, a memory 102, a power supply component 103, a multimedia component 104, an audio component 105, a sensor component 107 and a communication component 108. Among them, the above components are not all necessary.
  • the electronic device 100 may add other components or reduce some components according to its own functional requirements, which is not limited in this embodiment.
  • the processing component 101 generally controls the overall operations of the electronic device 100, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 101 may include one or more processors 109 to execute instructions to complete all or part of the steps of the above operations.
  • the processing component 101 may include one or more modules to facilitate interaction between the processing component 101 and other components.
  • the processing component 101 may include a multimedia module to facilitate interaction between the multimedia component 104 and the processing component 101.
  • the memory 102 is configured to store various types of data to support operation at the electronic device 100. Examples of these data include instructions for any application or method operating on the electronic device 100.
  • the memory 102 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as SRAM (Static Random Access Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory, electrically Erasable Programmable Read Only Memory), EPROM (Erasable Programmable Read Only Memory), PROM (Programmable Read-Only Memory, Programmable Read Only Memory), ROM (Read-Only Memory, only Read memory), magnetic memory, flash memory, magnetic disk or optical disk.
  • One or more modules are also stored in the memory 102, and the one or more modules are configured to be executed by the one or more processors 109 to complete all or part of the steps in any of the methods shown below.
  • the power supply component 103 provides power to various components of the electronic device 100.
  • the power supply component 103 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 100.
  • the multimedia component 104 includes a screen that provides an output interface between the electronic device 100 and the user.
  • the screen may include an LCD (Liquid Crystal Display) and a TP (Touch Panel) touch panel. If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding action, but also detect the duration and pressure related to the touch or sliding operation.
  • the audio component 105 is configured to output and/or input audio signals.
  • the audio component 105 includes a microphone, and when the electronic device 100 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal.
  • the received audio signal may be further stored in the memory 102 or transmitted via the communication component 108.
  • the audio component 105 further includes a speaker for outputting audio signals.
  • the sensor assembly 107 includes one or more sensors for providing the electronic device 100 with various aspects of status assessment.
  • the sensor assembly 107 can detect the on/off state of the electronic device 100, the relative positioning of the components, and the sensor assembly 107 can also detect the coordinate change of the electronic device 100 or one component of the electronic device 100 and the temperature change of the electronic device 100.
  • the sensor assembly 107 may also include a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 108 is configured to facilitate wired or wireless communication between the electronic device 100 and other devices.
  • the electronic device 100 can access a wireless network based on a communication standard, such as WiFi (Wireless-Fidelity, wireless network), 2G or 3G, or a combination thereof.
  • the communication component 108 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 108 further includes an NFC (Near Field Communication) module to facilitate short-range communication.
  • NFC Near Field Communication
  • the NFC module can be based on RFID (Radio Frequency Identification) technology, IrDA (Infrared Data Association) technology, UWB (Ultra-Wideband, ultra-wideband) technology, BT (Bluetooth, Bluetooth) technology and others Technology to achieve.
  • RFID Radio Frequency Identification
  • IrDA Infrared Data Association
  • UWB Ultra-Wideband, ultra-wideband
  • BT Bluetooth, Bluetooth
  • the electronic device 100 may be implemented by one or more ASIC (Application Specific Integrated Circuit), DSP (Digital Signal Processing), PLD (Programmable Logic Device), programmable logic Device), FPGA (Field-Programmable Gate Array, field programmable gate array), controller, microcontroller, microprocessor or other electronic components to implement the above method.
  • ASIC Application Specific Integrated Circuit
  • DSP Digital Signal Processing
  • PLD Programmable Logic Device
  • programmable logic Device programmable logic Device
  • FPGA Field-Programmable Gate Array, field programmable gate array
  • controller microcontroller, microprocessor or other electronic components to implement the above method.
  • the present invention also provides a device that executes all or part of the steps of the intelligent identification method for the switch state of the packaging box shown in any one of the above.
  • the equipment includes:
  • At least one processor At least one processor
  • a memory communicatively connected to the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute as described in any of the above exemplary embodiments method.
  • a storage medium is also provided.
  • the storage medium is a computer-readable storage medium, for example, it may be a temporary and non-transitory computer-readable storage medium including instructions.
  • the storage medium includes, for example, a memory 102 of instructions that can be executed by the processor 109 of the device 100 to complete the intelligent identification method of the opening and closing state of the packaging box.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种风电场机组运行状态的动态评估方法、装置及电子设备，适用风电场机组状态评估技术领域，该方法包括：对风电场机组的运行数据进行预处理得到数据矩阵（S110）；根据目标时滞长度构建所述数据矩阵的动态增广矩阵（S120）；通过主成分分析方法计算所述动态增广矩阵的协方差矩阵（S130）；根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分（S140）；通过所述主成分判断所述风电场机组的运行状态（S150）。从而通过将主成分分析法应用到动态过程中，并根据目标时滞长度分析风电场机组的运行数据中变量间的动态关系，更准确、高效地实时评估风电场机组的运行状态。

Description

风电场机组运行状态的动态评估方法、装置及电子设备 技术领域
本发明属于风电场机组状态评估技术领域，尤其涉及风电场机组运行状态的动态评估方法、装置及电子设备。
背景技术
随着经济社会的发展，世界各国的能源矛盾日益突出。风能具有安全、清洁、充裕，稳定等特点，风能的利用将有效地缓解资源供需矛盾、减缓环境污染的程度。近年来，我国在风电上的研究与投入进入了一个新的发展阶段。但在风电技术迅猛发展的同时，风电场机组的故障损坏事故也逐年增加。风电场机组一般位于偏远及环境恶劣的地区，机组修护工作难以及时进行，增加了风电场机组运行维护的资金和人力成本。因此，如何在风电场机组的运行状态中实时快速检测出潜在故障并优化运行方案是目前风电场机组重点研究的方向。
主成分分析法是一种多元统计分析方法，利用降维的思想，将多个指标转化为若干综合指标。主成分分析方法是将高维信息投影到低维子空间，最大程度保留数据的原始信息，其基本思想是：寻找一组低维的新变量代替高维的原变量，且新变量是原变量的线性组合。低维的新变量数据更集中的反应了原变量数据所包含的变化信息，根据数据变化的方差大小来确定变化方向的主次地位，按主次顺序得到主成分，依次称为第一主成分、第二主成分等，这些主成分之间是相互独立的。动态主成分分析法是将动态序列数据的构造和主成分分析法相结合的一种新型多元统计学建模方法。此方法利用动态时间序列将原变量的静态数据，扩展成动态时间数据，通过对动态时间数据的分析，可以简化 原始数据分析的复杂程度，有效地提取系统变量间的动态关系，在保证预测精度的情况下提高评估效率。
现有的风电场机组运行状态的评估方法大多是采用曲线图绘制的方法，例如通过绘制功率曲线、部件温度曲线、压力曲线等来对风电机组进行评估。所谓风电机组的功率曲线，一般是指风电机组输出功率随风速变化的关系曲线。风电机组的实际效率主要通过风电机组实际运行的功率曲线得到反映，实际功率曲线的好坏综合反映了风电机组的经济性。然而通过单一的性能曲线仅能反映出风电场或单个机组的运行是否良好、经济性是否达标，对于发现潜在隐患、找到故障源头等方面还有许多不足。若把所有运行数据都绘制曲线图，来一一进行对比观察，虽然可以掌握整体运行状态，但工作量大、耗时费力，并不是一种高效的评估方法。
发明内容
本发明的目的在于提供风电场机组运行状态的动态评估方法、装置及电子设备，旨在解决由于现有技术无法准确、高效地对风电场机组的运行状态进行实时动态评估的问题。
第一方面，本发明提供了一种风电场机组运行状态的动态评估方法，所述方法包括下述步骤：
对风电场机组的运行数据进行预处理得到数据矩阵；
根据目标时滞长度构建所述数据矩阵的动态增广矩阵；
通过主成分分析方法计算所述动态增广矩阵的协方差矩阵；
根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分；
通过所述主成分判断所述风电场机组的运行状态。
可选的，对风电场机组的运行数据进行预处理得到数据矩阵的步骤包括：
对所述风电场机组的运行数据进行数据清洗，修改所述运行数据中的错误数据。
将经过错误数据修改的所述运行数据构建为数据矩阵。
可选的，将经过错误数据修改的所述运行数据构建为数据矩阵的步骤包括：
对经过错误数据修改的所述运行数据进行标准化处理后构建数据矩阵；
可选的，根据时滞长度构建所述数据矩阵的动态增广矩阵的步骤包括：
计算所述运行数据的时滞长度；
根据所述时滞长度构建时滞增广矩阵；
对所述时滞增广矩阵进行标准化得到动态增广矩阵。
可选的，计算所述运行数据的时滞长度的步骤包括：
计算无时滞长度的静态关系数，以及时滞长度不断增加时不同时滞长度的动态关系数；
根据所述静态关系数及所述动态关系数确定目标时滞长度。
可选的，根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分的步骤包括：
计算所述协方差矩阵的特征值及特征向量；
通过所述特征值及特征向量计算主成分得分及相应的主成分系数；
通过所述主成分得分及相应的主成分系数计算主成分贡献率，并选取主成分。
可选的，通过所述主成分判断所述风电场机组的运行状态的步骤包括：
根据各主成分的主成分贡献率绘制数据图形；
通过所诉数据图形的对比判断所述风电场机组的运行状态。
第二方面，提供了一种风电场机组运行状态的动态评估装置，包括：
预处理模块，用于对风电场机组的运行数据进行预处理得到数据矩阵；
动态增广矩阵计算模块，用于根据目标时滞长度构建所述数据矩阵的动态增广矩阵；
协方差矩阵计算模块，用于通过主成分分析方法计算所述动态增广矩阵的协方差矩阵；
主成分贡献率计算模块，用于根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分；
运行状态判断模块，用于通过所述主成分判断所述风电场机组的运行状态。
第三方面，提供了一种电子设备，包括：
处理器；以及
与所述处理器通信连接的存储器；其中，
所述存储器存储有可读性指令，所述可读性指令被所述处理器执行时实现如第一方面所述的方法。
第四方面，提供了一种计算机可读性存储介质，其上存储有计算机程序，所述计算机程序在被执行时实现如第一方面的方法。
本发明在对风电场机组的运行状态进行评估时，通过将主成分分析法应用到动态过程中，并根据目标时滞长度分析风电场机组的运行数据中变量间的动态关系，从而更准确、高效地实时评估风电场机组的运行状态。
附图说明
图1是本发明实施例一提供的风电场机组运行状态的动态评估方法的实现流程图；
图2是根据实施例一示出的一种计算时滞长度的方法流程图；
图3示出了本发明实施例二提供的风电场机组运行状态的动态评估装置的框图；
图4是本发明实施例三提供的对风电场机组运行状态进行动态评估时的主成分贡献率示意图；
图5是本发明实施例三提供的对风电场机组运行状态进行动态评估时各不同工况的主成分得分示意图；
图6是本发明实施例三提供的对风电场机组运行状态进行动态评估时三种工况下协方差矩阵特征值的绘制示意图；
图7是本发明实施例四提供的电子设备100的结构框图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
以下结合具体实施例对本发明的具体实现进行详细描述：
实施例一：
图1示出了本发明实施例一提供的风电场机组运行状态的动态评估方法的实现流程，实施例一提供的风电场机组运行状态的动态评估方法可运行与电脑、服务器等各种电子设备中，为了便于说明，仅示出了与本发明实施例相关 的部分，详述如下：
步骤S110，对风电场机组的运行数据进行预处理得到数据矩阵。
本发明实施例适用于电脑、服务器等电子设备，这些电子设备中设置处理器，以对风电场机组的运行状态进行动态评估。
运行数据是风电场机组运行过程中所产生的各种数据，例如温度、功率、压力等数据。
可以理解的是，风电场机组的运行数据是随着时间变化的，其本身是杂散的，因此，通过对运行数据进行预处理，将杂散的运行数据转化为数据矩阵，进而对数据矩阵进行处理，能够更加方便进行数据建模分析，有效提高的数据处理的效率。
数据预处理是指把运行数据进行处理，保留最重要的数据信息，并构建数据矩阵。例如，数据预处理可包括数据清洗和数据标准化：
(1)数据清洗
由于数据采集过程中不可避免地产生误差，因此，对于风电场机组的原始运行数据，需要进行数据一致性检查。根据每个数据的合理取值范围和相互关系，检查数据是否合乎要求。若发现超出正常范围、逻辑上不合理或者相互矛盾的数据，需要进行数据修改或删除，并利用某项数据的样本均值、中位数来对数据进行估算，代替缺失数据。例如，对于部分由于检测设备短暂的停歇或风电机组瞬时性的间断所得出的无效数据，需要将数据删除，以保持数据的连续性。
(2)数据标准化
对于风电场运行数据，各项数据指标量纲不同，数据取值的分散程度较大，在计算协方差矩阵时，总体方差会受某个方差较大的数据所控制。因此，为进 一步提高数据处理的准确性，尽量避免出现误差，通过对数据进行标准化处理来消除量纲影响，进而在标准化处理构建数据矩阵。例如，Z-score标准化法是基于数据的均值和标准差来进行数据的标准化。
步骤S120，根据目标时滞长度构建数据矩阵的动态增广矩阵。
在实际工况中，由于受到不可避免的扰动因素的影响，系统运行状态常常会发生偏离，而偏离的幅度一般较小，仍保持在正常工况范围之内。因此，通过运用动态主元分析，获取现实工况中偏离幅度的特性，即实际运行数据在时间序列上的相关性，找出最相关的时间序列的范围，从而最大程度上提取过程的扰动因素。
目标时滞长度是实际运行数据在时间序列上相关的时间范围。目标时滞长度可以是预先设置的，也可以是根据具体的运行数据而计算出来的。
根据具体的运行数据计算适应性的时间滞后长度L，可以找出最相关的时间序列的范围，从而最大程度上提取过程的扰动因素，最大程度地预估即将出现故障的位置。
计算目标时滞长度时，首先考虑时滞长度为零的静态情况，求出静态关系数，静态关系数等于变量数与主成分个数之差；
然后令时滞长度为1，计算动态关系数，动态关系数等于变量减去主成分个数和(1)中的静态关系数；
再令时滞长度逐渐增加，根据递推公式
Figure PCTCN2019123254-appb-000001
计算新的动态关系数，当r new(l)≤0，即没有新的静态和动态关系，此时L即为目标时滞长度。
具体的，图2是根据实施例一示出的一种计算时滞长度的方法流程图。
步骤S130，通过主成分分析方法计算动态增广矩阵的协方差矩阵。
PCA(Principal Components Analysis)即主成分分析方法，旨在利用降维的思想，把多指标转化为少数几个综合指标。
在统计学中，主成分分析方法PCA是一种简化数据集的技术。它是一个线性变换。这个变换把数据变换到一个新的坐标系统中，使得任何数据投影的第一大方差在第一个坐标(称为第一主成分)上，第二大方差在第二个坐标(第二主成分)上，依次类推。主成分分析方法经常用减少数据集的维数，同时保持数据集的对方差贡献最大的特征。这是通过保留低阶主成分，忽略高阶主成分做到的。这样低阶成分往往能够保留住数据的最重要方面。
根据计算得到的时滞长度对数据矩阵进行扩展，具有L个时滞长度的时滞增广矩阵可表示为：
Figure PCTCN2019123254-appb-000002
其中X∈R n+m，X T t指在t时刻m维的观测量。
时滞增广矩阵构造完成后，利用Z-score标准化法对动态数据阵X(l)进行标准化处理得到动态增广矩阵。
步骤S140，根据协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分。
数据的分析阶段是基于主成分分析法来展开的，在运行状态的评估分析过程中，根据主成分贡献率来提取主成分，并对主成分进行分析判断风电场机组的运行状态。
可选的，在得到动态增广矩阵之后，可对进行简单的分段处理。通过观察重点数据变化，或者绘制参数曲线，来判断各项数据是否有明显的波动，如果数据在某一范围内发生了较大波动，不同于之前的变化趋势，此范围数据就要 作为特殊工况进行单独分析，以提高数据处理的针对性，避免其他工况对特殊工况的分析造成影响，从而进一步提高动态评估的准确性。
每种工况分析方法类似，下面以一种工况为例，来说明本实施例的分析过程。
(1)求出动态增广数据矩阵的协方差矩阵。通过PCA方法求出动态增广矩阵的协方差矩阵，度量维度与维度之间的关系，便于求取矩阵特征值：
Figure PCTCN2019123254-appb-000003
(2)求取协方差矩阵的特征值及对应的单位特征向量。将协方差矩阵特征值分解得到特征值对角矩阵，进一步得到特征向量矩阵并将其正交化。样本的协方差矩阵的特征向量能够反映出样本分布变换最剧烈的方向，特征值的大小代表了正交基对线性空间的影响权重，通过协方差矩阵的特征值和特征向量可以看出数据的变化趋势和方向：
X＝UΛ 0V T
其中∧∈R N×N是对角矩阵，包含了协方差矩阵的特征值Λ＝[λ 1,λ 2,…λ N]；协方差矩阵可以进行如下分解：
Figure PCTCN2019123254-appb-000004
(3)计算主成分得分、主成分系数等相关系数。通过主元分析可以将动态增广矩阵分解为载荷向量p i和得分向量t i的乘积之和再加上残余误差E：
Figure PCTCN2019123254-appb-000005
式中的k表示选取的主元个数，用来代表数据中方差最大的主元空间。通常情况下，选取k各主元个数能够包含数据总方差的95％。
(4)求出主成分贡献率，根据主成分贡献率挑选出主成分。如果所选取的主成分个数太少，会丢失数据信息，误差较大；当所选取的主成分过多时， 会包含过多的无用信息，增加分析与诊断的复杂性。主成分贡献率越接近为1，则说明选取的主成分包含的原始信息越多。累计贡献率根据如下公式求得：
Figure PCTCN2019123254-appb-000006
可选的，可将累计贡献率大于95％的前k个成分即可作为主成分。
步骤S150，通过主成分判断风电场机组的运行状态。
在选取主成分后，可通过计算主成分得分判断风电场机组的运行状态。
例如，通过以下公式计算主成分得分T＝XP，再将主成分得分以散点图显示，将协方差矩阵特征值向量绘制成柏拉图。通过输出的检测图形与正常工况检测图的比较，可以判断风电机组的运行工况发生故障。
利用如上所述的方法，通过将主成分分析法应用到动态过程中，并根据目标时滞长度分析风电场机组的运行数据中变量间的动态关系，从而更准确、高效地实时评估风电场机组的运行状态。
实施例二：
图3示出了本发明实施例二提供的风电场机组运行状态的动态评估装置的框图，为了便于说明，仅示出了与本发明实施例相关的部分，其中包括：
预处理模块110，用于对风电场机组的运行数据进行预处理得到数据矩阵；
动态增广矩阵计算模块120，用于根据目标时滞长度构建所述数据矩阵的动态增广矩阵；
协方差矩阵计算模块130，用于通过主成分分析方法计算所述动态增广矩阵的协方差矩阵；
主成分贡献率计算模块140，用于根据所述协方差矩阵的特征值及特征向 量计算主成分贡献率，并选取主成分；
运行状态判断模块150，用于通过所述主成分判断所述风电场机组的运行状态。
在本发明实施例中，该风电场机组运行状态的动态评估装置的各模块可由相应的硬件或软件单元实现，各模块可以为独立的软、硬件模块，也可以集成为一个软、硬件单元，在此不用以限制本发明。各模块的具体实施方式可参考实施例一的描述，在此不再赘述。
实施例三：
实施例三为对本发明提供的风电场机组运行状态的动态评估方法的主成分分析结果实施例。
(1)主成分的选取
计算出主成分贡献率，如图4所示，前五个主成分的累计贡献率达到了85％左右，包含了足够的信息，所以选取主成分数为五个。
(2)主成分得分散点图与协方差矩阵特征值条形图的分析
在分析阶段完成对数据的工况划分，将工况分为三种，分别对三种工况的第一主成分、第三主成分得分进行绘图，如图5(a)、5(b)、5(c)所示。从图中可以明显看出，第一种工况和第三种工况的主成分得分图形形状相似，主成分得分取值范围也大致相同，而第二种工况主成分得分图形明显不同，分散且不连续所以初步判断，在第二种工况机组运行出现了异常情况。
图6(a)、6(b)、6(c)是根据三种工况下协方差矩阵特征值绘制的条形图，从该图可以看出，第二种工况下的第一主成分特征值明显高于第一和第三种工况下的特征值，从而进一步确认了第二种工况下，风电场机组运行出 现了故障。
实施例四：
图7示出了本发明实施例四提供的电子设备100的结构框图，为了便于说明，仅示出了与本发明实施例相关的部分。
参考图7，电子设备100可以包括以下一个或者多个组件：处理组件101，存储器102，电源组件103，多媒体组件104，音频组件105，传感器组件107以及通信组件108。其中，上述组件并不全是必须的，电子设备100可以根据自身功能需求增加其他组件或减少某些组件，本实施例不作限定。
处理组件101通常控制电子设备100的整体操作，诸如与显示、电话呼叫、数据通信、相机操作以及记录操作相关联的操作等。处理组件101可以包括一个或多个处理器109来执行指令，以完成上述操作的全部或部分步骤。此外，处理组件101可以包括一个或多个模块，便于处理组件101和其他组件之间的交互。例如，处理组件101可以包括多媒体模块，以方便多媒体组件104和处理组件101之间的交互。
存储器102被配置为存储各种类型的数据以支持在电子设备100的操作。这些数据的示例包括用于在电子设备100上操作的任何应用程序或方法的指令。存储器102可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如SRAM(Static Random Access Memory，静态随机存取存储器)，EEPROM(Electrically Erasable Programmable Read-Only Memory，电可擦除可编程只读存储器)，EPROM(Erasable Programmable Read Only Memory，可擦除可编程只读存储器)，PROM(Programmable Read-Only Memory，可编程只读存储器)，ROM(Read-Only Memory，只读存储器)，磁存储器，快闪 存储器，磁盘或光盘。存储器102中还存储有一个或多个模块，该一个或多个模块被配置成由该一个或多个处理器109执行，以完成以下任一所示方法中的全部或者部分步骤。
电源组件103为电子设备100的各种组件提供电力。电源组件103可以包括电源管理系统，一个或多个电源，及其他与为电子设备100生成、管理和分配电力相关联的组件。
多媒体组件104包括在电子设备100和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括LCD(Liquid Crystal Display，液晶显示器)和TP(Touch Panel，触摸面板)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。
音频组件105被配置为输出和/或输入音频信号。例如，音频组件105包括一个麦克风，当电子设备100处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器102或经由通信组件108发送。在一些实施例中，音频组件105还包括一个扬声器，用于输出音频信号。
传感器组件107包括一个或多个传感器，用于为电子设备100提供各个方面的状态评估。例如，传感器组件107可以检测到电子设备100的打开/关闭状态，组件的相对定位，传感器组件107还可以检测电子设备100或电子设备100一个组件的坐标改变以及电子设备100的温度变化。在一些实施例中，该传感器组件107还可以包括磁传感器，压力传感器或温度传感器。
通信组件108被配置为便于电子设备100和其他设备之间有线或无线方式的通信。电子设备100可以接入基于通信标准的无线网络，如WiFi(Wireless-Fidelity，无线网络)，2G或3G，或它们的组合。在一个示例性实施例中，通信组件108经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件108还包括NFC(Near Field Communication，近场通信)模块，以促进短程通信。例如，在NFC模块可基于RFID(Radio Frequency Identification，射频识别)技术，IrDA(Infrared Data Association，红外数据协会)技术，UWB(Ultra-Wideband，超宽带)技术，BT(Bluetooth，蓝牙)技术和其他技术来实现。
在示例性实施例中，电子设备100可以被一个或多个ASIC(Application Specific Integrated Circuit，应用专用集成电路)、DSP(Digital Signal Processing，数字信号处理器)、PLD(Programmable Logic Device，可编程逻辑器件)、FPGA(Field－Programmable Gate Array，现场可编程门阵列)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
该实施例中的电子设备中处理器执行操作的具体方式已在有关该风电场机组运行状态的动态评估方法的实施例中进行详细描述，此处将不再做详细阐述说明。以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。
可选的，本发明还提供一种设备，执行上述任一所示的包装箱开关状态的智能识别方法的全部或者部分步骤。该设备包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上述任一示例性实施例所述的方法。
该实施例中的设备中处理器执行操作的具体方式已经在有关该包装箱开关状态的智能识别方法的实施例中执行了详细描述，此处将不做详细阐述说明。
在示例性实施例中，还提供了一种存储介质，该存储介质为计算机可读存储介质，例如可以为包括指令的临时性和非临时性计算机可读存储介质。该存储介质例如包括指令的存储器102，上述指令可由设备100的处理器109执行以完成上述包装箱开关状态的智能识别方法。
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种风电场机组运行状态的动态评估方法，其特征在于，所述方法包括下述步骤：
    对风电场机组的运行数据进行预处理得到数据矩阵；
    根据目标时滞长度构建所述数据矩阵的动态增广矩阵；
    通过主成分分析方法计算所述动态增广矩阵的协方差矩阵；
    根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分；
    通过所述主成分判断所述风电场机组的运行状态。
  2. 如权利要求1所述的方法，其特征在于，对风电场机组的运行数据进行预处理得到数据矩阵的步骤包括：
    对所述风电场机组的运行数据进行数据清洗，修改所述运行数据中的错误数据；
    将经过错误数据修改的所述运行数据构建为数据矩阵。
  3. 如权利要求2所述的方法，其特征在于，将经过错误数据修改的所述运行数据构建为数据矩阵的步骤包括：
    对经过错误数据修改的所述运行数据进行标准化处理后构建数据矩阵。
  4. 如权利要求1所述的方法，其特征在于，根据时滞长度构建所述数据矩阵的动态增广矩阵的步骤包括：
    计算所述运行数据的时滞长度；
    根据所述时滞长度构建时滞增广矩阵；
    对所述时滞增广矩阵进行标准化得到动态增广矩阵。
  5. 如权利要求4所述的方法，其特征在于，计算所述运行数据的时滞长度的步骤包括：
    计算无时滞长度的静态关系数，以及时滞长度不断增加时不同时滞长度的动态关系数；
    根据所述静态关系数及所述动态关系数确定目标时滞长度。
  6. 如权利要求1所述的方法，其特征在于，根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分的步骤包括：
    计算所述协方差矩阵的特征值及特征向量；
    通过所述特征值及特征向量计算主成分得分及相应的主成分系数；
    通过所述主成分得分及相应的主成分系数计算主成分贡献率，并选取主成分。
  7. 如权利要求1所述的方法，其特征在于，通过所述主成分判断所述风电场机组的运行状态的步骤包括：
    根据各主成分的主成分贡献率绘制数据图形；
    通过所诉数据图形的对比判断所述风电场机组的运行状态。
  8. 一种风电场机组运行状态的动态评估装置，其特征在于，所述装置包括：
    预处理模块，用于对风电场机组的运行数据进行预处理得到数据矩阵；
    动态增广矩阵计算模块，用于根据目标时滞长度构建所述数据矩阵的动态增广矩阵；
    协方差矩阵计算模块，用于通过主成分分析方法计算所述动态增广矩阵的协方差矩阵；
    主成分贡献率计算模块，用于根据所述协方差矩阵的特征值及特征向量计算主成分贡献率，并选取主成分；
    运行状态判断模块，用于通过所述主成分判断所述风电场机组的运行状态。
  9. 一种电子设备，其特征在于，所述电子设备包括：
    处理器；以及
    与所述处理器通信连接的存储器；其中，
    所述存储器存储有可读性指令，所述可读性指令被所述处理器执行时实现如权利要求1-7任一项所述的方法。
  10. 一种计算机可读性存储介质，其上存储有计算机程序，其特征在于，所述计算机程序在被执行时实现如权利要求1-7任一项所述的方法。
PCT/CN2019/123254 2018-12-06 2019-12-05 风电场机组运行状态的动态评估方法、装置及电子设备 Ceased WO2020114449A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811483815.4 2018-12-06
CN201811483815.4A CN109657943A (zh) 2018-12-06 2018-12-06 风电场机组运行状态的动态评估方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2020114449A1 true WO2020114449A1 (zh) 2020-06-11

Family

ID=66112556

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/123254 Ceased WO2020114449A1 (zh) 2018-12-06 2019-12-05 风电场机组运行状态的动态评估方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN109657943A (zh)
WO (1) WO2020114449A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115271423A (zh) * 2022-07-25 2022-11-01 中国电建集团成都勘测设计研究院有限公司 基于混合相似度的风力发电机组运行状态评估方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109657943A (zh) * 2018-12-06 2019-04-19 中国科学院深圳先进技术研究院 风电场机组运行状态的动态评估方法、装置及电子设备
TWI706149B (zh) * 2019-12-04 2020-10-01 財團法人資訊工業策進會 產生一馬達診斷模型的裝置及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130073223A1 (en) * 2010-05-13 2013-03-21 University Of Cincinnati Turbine-To-Turbine Prognostics Technique For Wind Farms
CN105303468A (zh) * 2015-11-20 2016-02-03 国网天津市电力公司 一种基于主成分聚类分析的智能电网建设综合评价方法
CN105677791A (zh) * 2015-12-31 2016-06-15 新疆金风科技股份有限公司 用于分析风力发电机组的运行数据的方法和系统
CN108572639A (zh) * 2018-03-19 2018-09-25 宁波大学 一种基于主成分自相关性剔除的动态过程监测方法
CN109657943A (zh) * 2018-12-06 2019-04-19 中国科学院深圳先进技术研究院 风电场机组运行状态的动态评估方法、装置及电子设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106444666B (zh) * 2016-09-22 2018-11-20 宁波大学 基于加权型动态分布式pca模型的动态过程监测方法
CN108196165A (zh) * 2018-01-09 2018-06-22 贵州大学 基于样本协方差矩阵最大特征值的电网异常状态检测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130073223A1 (en) * 2010-05-13 2013-03-21 University Of Cincinnati Turbine-To-Turbine Prognostics Technique For Wind Farms
CN105303468A (zh) * 2015-11-20 2016-02-03 国网天津市电力公司 一种基于主成分聚类分析的智能电网建设综合评价方法
CN105677791A (zh) * 2015-12-31 2016-06-15 新疆金风科技股份有限公司 用于分析风力发电机组的运行数据的方法和系统
CN108572639A (zh) * 2018-03-19 2018-09-25 宁波大学 一种基于主成分自相关性剔除的动态过程监测方法
CN109657943A (zh) * 2018-12-06 2019-04-19 中国科学院深圳先进技术研究院 风电场机组运行状态的动态评估方法、装置及电子设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115271423A (zh) * 2022-07-25 2022-11-01 中国电建集团成都勘测设计研究院有限公司 基于混合相似度的风力发电机组运行状态评估方法

Also Published As

Publication number Publication date
CN109657943A (zh) 2019-04-19

Similar Documents

Publication Publication Date Title
CN108830745A (zh) 基于监控信息的电网连锁故障诊断、预警、评估系统
CN114155072B (zh) 基于大数据分析的财务预测模型构建方法及系统
WO2020114449A1 (zh) 风电场机组运行状态的动态评估方法、装置及电子设备
CN114997342B (zh) 一种scr故障诊断方法、装置、设备及存储介质
CN118350543A (zh) 一种基于能效标识数据库的工业产品碳足迹分析方法及系统
CN115204532A (zh) 基于多变量误差修正组合模型的油气产量预测方法及系统
CN106570567A (zh) 一种主网检修多约束多目标评估专家系统及优化方法
CN108241901A (zh) 一种基于预测数据的变压器预警评估方法及装置
CN119415365B (zh) 一种多设备能耗优化的智能化在线学习系统及方法
CN112434961B (zh) 一种铁钢界面铁水温降预测方法、装置和终端设备
CN120355224A (zh) 一种项目管理大数据动态优化方法
CN118551335A (zh) 一种配电网多能耦合云-边-端融合方法及系统
CN113269359A (zh) 用户财务状况预测方法、设备、介质及计算机程序产品
CN118551924A (zh) 一种环保智慧管控方法及系统
CN118674237A (zh) 机床报工方法、装置、设备及存储介质
CN115511186A (zh) 一种深度学习训练时长的预测管理方法、装置及设备
CN119231760A (zh) 一种电气配电柜及其控制方法
CN120763177A (zh) 一种企业项目数据库智能管理方法与系统
CN120408607A (zh) 网络安全合规风险评估方法、装置、设备和存储介质
US20250139464A1 (en) Method for predicting energy consumption and electronic device
CN118857374A (zh) 一种高铁雨棚结构监测预警方法和系统
CN118378952A (zh) 一种数字员工评价方法及装置
CN115774790A (zh) 一种基于能源大数据的企业画像确定方法及系统
CN120687915B (zh) 基于多模态数据动态门控的回转窑喷煤量预测方法、装置及其可读存储介质
CN119848421B (zh) 基于长时间序列注意力网络的污染治理设备状态预测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19892186

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19892186

Country of ref document: EP

Kind code of ref document: A1