CN108051035A - The pipe network model recognition methods of neural network model based on gating cycle unit - Google Patents

The pipe network model recognition methods of neural network model based on gating cycle unit Download PDF

Info

Publication number
CN108051035A
CN108051035A CN201710998436.8A CN201710998436A CN108051035A CN 108051035 A CN108051035 A CN 108051035A CN 201710998436 A CN201710998436 A CN 201710998436A CN 108051035 A CN108051035 A CN 108051035A
Authority
CN
China
Prior art keywords
historical
data
layer
network model
training
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.)
Granted
Application number
CN201710998436.8A
Other languages
Chinese (zh)
Other versions
CN108051035B (en
Inventor
刘书明
郭冠呈
吴雪
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.)
Tsinghua University
Original Assignee
Tsinghua University
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 Tsinghua University filed Critical Tsinghua University
Priority to CN201710998436.8A priority Critical patent/CN108051035B/en
Publication of CN108051035A publication Critical patent/CN108051035A/en
Application granted granted Critical
Publication of CN108051035B publication Critical patent/CN108051035B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01FMEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
    • G01F1/00Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Fluid Mechanics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明提供了一种基于门控循环单元的神经网络模型及其训练方法和应用。其中,基于门控循环单元的神经网络模型,包括:多个门控循环单元层,其被配置成接收供水管网在不同时间段的流量特征;第一全连接层,其与所述多个门控循环单元层并联构成输入层,所述第一全连接层被配置成接收供水管网的气象特征;与所述输入层以张量串联的模式连接的合并层;均与所述合并层以张量串联的模式连接的第二全连接层至第M全连接层,M为大于或等于2的整数;以及与所述第M全连接层以张量串联的模式连接的输出层,其被配置成输出供水管网在下一时刻的预测流量。

The invention provides a neural network model based on a gated cycle unit and its training method and application. Wherein, the neural network model based on the gated recurrent unit includes: multiple gated recurrent unit layers, which are configured to receive the flow characteristics of the water supply network in different time periods; the first fully connected layer, which is connected with the multiple The gated recurrent unit layer is connected in parallel to form an input layer, and the first fully connected layer is configured to receive the meteorological characteristics of the water supply pipe network; a merge layer connected with the input layer in a tensor series mode; both connected with the merge layer The second fully connected layer to the Mth fully connected layer connected in tensor series mode, M is an integer greater than or equal to 2; and the output layer connected with the Mth fully connected layer in tensor series mode, which Configured to output the predicted flow of the water supply network at the next moment.

Description

基于门控循环单元的神经网络模型的管网漏损识别方法Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model

技术领域technical field

本发明涉及神经网络领域,具体涉及一种基于门控循环单元的神经网络模型及其训练方法和应用。The invention relates to the field of neural networks, in particular to a neural network model based on a gated recurrent unit and its training method and application.

背景技术Background technique

在管道老化、技术投入有限、监管体制落后等因素的影响下,我国城市供水管网漏损现象较为普遍。供水管网漏损不仅给自来水公司带来了巨大的经济损失,也造成了能源和资源的浪费。我国大部分自来水公司对于供水管网缺乏科学有效的管理办法,管网的基础数据也不完善,这些问题一直制约着自来水公司的管理效率和服务水平。因此,对待测管网进行漏损识别,辅助管理者的科学决策,及时发现和维护管网漏损区域,具有重要的经济意义和现实意义。Under the influence of factors such as aging pipelines, limited technical investment, and backward regulatory systems, the leakage of urban water supply networks in my country is relatively common. Leakage of water supply pipe network not only brings huge economic losses to water supply companies, but also causes waste of energy and resources. Most of the water supply companies in my country lack scientific and effective management methods for the water supply pipe network, and the basic data of the pipe network are not perfect. These problems have always restricted the management efficiency and service level of the water supply company. Therefore, it is of great economic and practical significance to identify the leakage of the pipeline network to be tested, assist the manager to make scientific decisions, and discover and maintain the leakage area of the pipeline network in time.

常见的用于识别管网漏损的模型主要分为两大类:一类是基于实验室试验的物理机理研究模型;一类是基于计算机模拟的数据挖掘模型,包括统计模型、概率模型、机器学习模型等,通常需要大量的历史数据。随着云时代的来临,大数据吸引了越来越多的关注,已经在诸多领域取得了不错的成绩,因此第二类模型也成为目前的研究热点,尤其是机器学习模型。The common models used to identify pipeline network leakage are mainly divided into two categories: one is the physical mechanism research model based on laboratory experiments; the other is the data mining model based on computer simulation, including statistical models, probability models, and machine models. Learning models, etc., usually requires a large amount of historical data. With the advent of the cloud era, big data has attracted more and more attention, and has achieved good results in many fields. Therefore, the second type of model has become a current research hotspot, especially the machine learning model.

我国城市供水管网数据量大,基础数据质量不高,导致管网漏损的因素众多且关系复杂。现有的管网漏损识别模型,大多基于一些经典的传统算法对管网的正常流量或压力进行预测,例如多元线性回归、指数平滑法、反向传播(Back Propagation,简称BP)神经网络等,随后通过比较预测值和实际监测值识别漏损事故。这些传统的预测方法在处理大量复杂非线性数据方面的能力有限,不能较好的挖掘出抽象数据之间的隐含特征,存在预测精度不高的问题,这也使得漏损事故识别的准确性无从保障。my country's urban water supply network has a large amount of data, and the quality of the basic data is not high. There are many factors and complex relationships that lead to network leakage. Most of the existing pipeline network leakage identification models are based on some classic traditional algorithms to predict the normal flow or pressure of the pipeline network, such as multiple linear regression, exponential smoothing method, back propagation (Back Propagation, BP) neural network, etc. , and then identify leakage accidents by comparing predicted values with actual monitored values. These traditional forecasting methods have limited ability to deal with a large amount of complex nonlinear data, and cannot well dig out the hidden features between abstract data, and there is a problem of low prediction accuracy, which also makes the accuracy of leakage accident identification There is no guarantee.

发明内容Contents of the invention

为了节约水资源,降低供水管网的漏损率,减少经济损失,符合可持续发展的理念,我们需要利用现有技术深入挖掘出供水管网数据的隐含特征,建立精度高、稳定性好的模型来识别管网漏损区域。针对现有技术的不足,本发明旨在提供一种新的基于门控循环单元的神经网络模型及其训练方法和应用,通过构建区别于传统的神经网络模型的新型神经网络,可处理大量数据、挖掘非线性关系、并综合评估模型效果,将其应用于供水管网的漏损事故识别,能够提高漏损识别的准确率,以便日常管理者能够及时发现管网漏损区域,减少经济损失,节约水资源,辅助自来水公司做出科学合理的决策。In order to save water resources, reduce the leakage rate of the water supply network, reduce economic losses, and conform to the concept of sustainable development, we need to use existing technologies to dig out the hidden characteristics of the water supply network data, and establish high precision and good stability. model to identify leakage areas in the pipeline network. Aiming at the deficiencies of the prior art, the present invention aims to provide a new neural network model based on gated recurrent units and its training method and application. By constructing a new neural network different from the traditional neural network model, a large amount of data can be processed , excavate the nonlinear relationship, and comprehensively evaluate the model effect, and apply it to the leakage accident identification of the water supply network, which can improve the accuracy of leakage identification, so that daily managers can find the leakage area of the pipeline network in time and reduce economic losses , save water resources, and assist water companies to make scientific and reasonable decisions.

本发明一方面提供一种基于门控循环单元的神经网络模型,用于识别供水管网的漏损事故,包括:One aspect of the present invention provides a neural network model based on gated cyclic units for identifying leakage accidents in water supply pipe networks, including:

多个门控循环单元(Gated Recurrent Unit,简称GRU)层,其被配置成接收供水管网在不同时间段的流量特征;A plurality of gated recurrent unit (Gated Recurrent Unit, GRU for short) layers, which are configured to receive flow characteristics of the water supply network in different time periods;

第一全连接层,其与所述多个门控循环单元层并联构成输入层,所述第一全连接层被配置成接收供水管网的气象特征;A first fully connected layer, which is connected in parallel with the multiple gated recurrent unit layers to form an input layer, and the first fully connected layer is configured to receive meteorological features of the water supply network;

与所述输入层以张量串联的模式连接的合并层;a pooling layer connected in tensor concatenation with said input layer;

均与所述合并层以张量串联的模式连接的第二全连接层至第M全连接层,M为大于或等于2的整数;以及The second fully-connected layer to the Mth fully-connected layer, all of which are connected to the merging layer in tensor series, where M is an integer greater than or equal to 2; and

与所述第M全连接层以张量串联的模式连接的输出层,其被配置成输出供水管网在下一时刻的预测流量。An output layer connected to the Mth fully connected layer in tensor series, configured to output the predicted flow rate of the water supply network at the next moment.

本发明所提供的门控循环神经网络(Gated Recurrent Unit Network,简称GRUN)是对现有循环神经网络的改进。这种网络的特点在于利用记忆模块代替普通的隐含节点,确保梯度在传递跨越很多时间步骤之后不会消失或爆炸,从而克服传统循环神经网络训练中遇到的困难,本发明采用的记忆模块是门控循环单元(GRU)。图1显示了本发明的一个实施方式中的基于门控循环单元的神经网络模型的拓扑结构图。The Gated Recurrent Unit Network (GRUN for short) provided by the present invention is an improvement to the existing recurrent neural network. The characteristic of this kind of network is to use the memory module to replace the ordinary hidden nodes, to ensure that the gradient will not disappear or explode after passing through many time steps, so as to overcome the difficulties encountered in the traditional cycle neural network training. The memory module used in the present invention is a gated recurrent unit (GRU). FIG. 1 shows a topology diagram of a neural network model based on gated recurrent units in an embodiment of the present invention.

本发明另一方面提供一种上述神经网络模型的训练方法,包括,Another aspect of the present invention provides a training method for the aforementioned neural network model, including:

构建所述神经网络模型;Construct the neural network model;

将不同时间段的历史流量特征和历史气象特征按比例随机分为训练集和验证集;Randomly divide the historical flow characteristics and historical meteorological characteristics of different time periods into a training set and a verification set;

将所述训练集中不同时间段的历史流量特征输入到所述多个门控循环单元层中,并将所述训练集中的历史气象特征输入到所述第一全连接层中,获取所述神经网络模型输出的训练流量;Input the historical traffic characteristics of different time periods in the training set into the multiple gated recurrent unit layers, and input the historical meteorological characteristics in the training set into the first fully connected layer, and obtain the neural The training traffic output by the network model;

将所述验证集中不同时间段的历史流量特征输入到所述多个门控循环单元层中,并将所述验证集中的历史气象特征输入到所述第一全连接层中,获取所述神经网络模型输出的验证流量;Input the historical traffic characteristics of different time periods in the verification set into the multiple gated recurrent unit layers, and input the historical meteorological characteristics in the verification set into the first fully connected layer to obtain the neural Verification traffic output by the network model;

基于所述训练集和训练流量生成训练曲线,并基于所述验证集和验证流量生成验证曲线,当所述训练曲线和验证曲线的均方误差值稳定在恒定值时,完成所述神经网络模型的训练。Generate a training curve based on the training set and training traffic, and generate a verification curve based on the verification set and verification traffic, when the mean square error value of the training curve and verification curve is stable at a constant value, complete the neural network model training.

该训练方法充分考虑了在训练过程中梯度下降方向的随机性和模型的泛化能力,提高了模型的收敛速度和训练效率,充分挖掘数据之间的有效信息。This training method fully considers the randomness of the gradient descent direction and the generalization ability of the model during the training process, improves the convergence speed and training efficiency of the model, and fully mines the effective information between the data.

在本发明的一个优选的实施方式中,上述训练方法还包括获取所述不同时间段的历史流量特征,包括:In a preferred embodiment of the present invention, the above-mentioned training method also includes acquiring the historical flow characteristics of the different time periods, including:

获取待测供水管网的历史流量数据;以及Obtain historical flow data of the water supply network to be tested; and

对所述历史流量数据进行提取处理和归一化处理得到所述历史流量特征。Extraction processing and normalization processing are performed on the historical traffic data to obtain the historical traffic features.

根据本发明,所述历史流量数据可获取自自来水公司的独立计量区域(districtmetered areas,简称为DMA)供水管网的历史流量数据。According to the present invention, the historical flow data may be obtained from historical flow data of independent metered areas (districtmetered areas, DMA for short) water supply pipe network of the water company.

在本发明的一个更优选的实施方式中,对所述历史流量数据进行提取处理包括,在供水管网的历史流量数据中,分别从所述第一时间段、第二时间段、第三时间段中以等间隔提取指定个数的流量数据,其中,In a more preferred embodiment of the present invention, extracting the historical flow data includes, in the historical flow data of the water supply pipeline network, respectively starting from the first time period, the second time period, and the third time period Extract the specified number of traffic data at equal intervals in the segment, where,

在临近待预测时刻t之前选取第一时间段,Select the first time period before the time t to be predicted,

在所述第一时间段的起始时刻之前选取第二时间段,selecting a second time period before the starting moment of the first time period,

在所述第二时间段的起始时刻之前选取第三时间段。A third time period is selected before the starting moment of the second time period.

根据本发明,考虑流量时间序列的趋势性,提取临近待预测时刻t时刻的流量数据,即第一时间段的流量数据。考虑流量时间序列的周期性,提取与待预测时刻t相隔一段时间的流量数据,可考虑按天划分为两个时间段,即第二时间段和第三时间段的流量数据。According to the present invention, considering the trend of the flow time series, the flow data near the time t to be predicted is extracted, that is, the flow data in the first time period. Considering the periodicity of the flow time series, extracting the flow data separated by a period of time from the time t to be predicted can be divided into two time periods by day, namely the flow data of the second time period and the third time period.

在本发明的一个具体的实施方式中,在包括第一时间段、第二时间段和第三时间段的整个时间段内,以采样频率k次/h进行平均采样,则整个时间段内包括的流量数据包括t-24k·d、t-24k·d+1……t-2、t-1时刻的流量数据,其中d表示天数,从中获取t-m至t-1时刻的流量数据,其中m的取值范围为2-24的整数,优选为5,作为第一时间段的流量数据;获取t-h1至t-h2时刻的流量数据,其中h1和h2的取值范围为24k-2至24k+20的整数,优选地,h1为24k+2,h2为24k-2;获取t-h3至t-h4时刻的流量数据,其中h3和h4的取值范围为48k-2至48k+20的整数,优选地,h3为48k+2,h4为48k-2。In a specific embodiment of the present invention, during the entire time period including the first time period, the second time period and the third time period, average sampling is performed at a sampling frequency of k times/h, then the whole time period includes The flow data of t-24k·d, t-24k·d+1...t-2, t-1 time flow data, where d represents the number of days, from which to obtain the flow data from tm to t-1 time, where m The value range is an integer of 2-24, preferably 5, as the flow data of the first time period; obtain the flow data of th 1 to th 2 moments, wherein the value range of h 1 and h 2 is 24k-2 to An integer of 24k+20, preferably, h 1 is 24k+2, h 2 is 24k-2; obtain the flow data from th 3 to th 4 , where the values of h 3 and h 4 range from 48k-2 to 48k An integer of +20, preferably, h 3 is 48k+2, and h 4 is 48k-2.

优选地,k为1-12的整数,优选为3-5。Preferably, k is an integer of 1-12, preferably 3-5.

在本发明的另一个优选的实施方式中,上述训练方法还包括获取所述历史气象特征,包括:In another preferred embodiment of the present invention, the above-mentioned training method also includes obtaining the historical meteorological features, including:

获取待测供水管网的历史气象数据;以及Obtain historical weather data of the water supply network to be tested; and

对所述历史气象数据进行提取处理和归一化处理得到所述历史气象特征。Extraction processing and normalization processing are performed on the historical meteorological data to obtain the historical meteorological features.

根据本发明,所述历史气象数据可获取自中国气象数据网的历史气象数据,包括最高温度、最低温度、相对湿度、降水量等。According to the present invention, the historical meteorological data can be obtained from the historical meteorological data of China Meteorological Data Network, including maximum temperature, minimum temperature, relative humidity, precipitation and the like.

在本发明的一个更优选的实施方式中,对所述历史气象数据进行提取处理包括对所述历史气象数据和所述历史流量数据进行Pearson相关性分析,选取相关系数大于或等于规定值V的历史气象数据,得到提取处理后的历史气象数据。In a more preferred embodiment of the present invention, extracting the historical meteorological data includes performing Pearson correlation analysis on the historical meteorological data and the historical flow data, and selecting the correlation coefficient greater than or equal to the specified value V The historical meteorological data is obtained by extracting and processing the historical meteorological data.

在本发明的一个更优选的实施方式中,所述规定值V为0.80-0.99。In a more preferred embodiment of the present invention, the specified value V is 0.80-0.99.

根据本发明,所述归一化处理包括,将原始数据的数值转化到[0,1]范围内,归一化处理的公式如式(1)所示,According to the present invention, the normalization process includes converting the numerical value of the original data into the range of [0,1], and the formula of the normalization process is as shown in formula (1),

式(1)中,y代表归一化处理后的数据,x代表输入的原始数据,xmax和xmin分别代表输入数据的最大值和最小值。In formula (1), y represents the normalized data, x represents the input original data, x max and x min represent the maximum value and minimum value of the input data respectively.

根据本发明,各网络层的激活函数选择tanh、ReLU或者Linear。According to the present invention, the activation function of each network layer is selected from tanh, ReLU or Linear.

本发明再一方面提供一种供水管网的漏损事故的识别方法,包括,Another aspect of the present invention provides a method for identifying leakage accidents of a water supply pipe network, including:

特征获取步骤,在未发生漏损事故的规定时间T内,获取待测供水管网的不同时间段的参考流量特征和参考气象特征;The feature acquisition step is to acquire the reference flow characteristics and reference meteorological characteristics in different time periods of the water supply network to be tested within the specified time T when no leakage accident occurs;

预测流量获取步骤,将所述不同时间段的参考流量特征输入到所述神经网络模型的多个门控循环单元层中,并将所述参考气象特征输入到所述神经网络模型的第一全连接层中,获取所述神经网络模型输出的预测流量;The forecast flow acquisition step is to input the reference flow characteristics of the different time periods into the multiple gated recurrent unit layers of the neural network model, and input the reference meteorological characteristics into the first full network of the neural network model In the connection layer, the predicted traffic output by the neural network model is obtained;

参考数据集确定步骤,获取在所述规定时间T内的实测流量,每组处于相同时刻的预测流量与实测流量构成一个时间序列向量,将所述规定时间T内的所有时间序列向量构成的矩阵作为参考数据集;Refer to the step of determining the data set to obtain the measured flow within the specified time T, each group of predicted flow and measured flow at the same time constitutes a time series vector, and a matrix composed of all time series vectors within the specified time T as a reference dataset;

事故识别步骤,计算新增的时间序列向量相对于所述参考数据集中的每个时间序列向量的余弦距离,统计余弦距离小于距离阈值D的时间序列向量的个数n,当n小于或等于数量阈值N时,确定发生了所述漏损事故。Accident identification step, calculating the cosine distance of the newly added time series vector relative to each time series vector in the reference data set, counting the number n of time series vectors whose cosine distance is less than the distance threshold D, when n is less than or equal to the number When the threshold N is reached, it is determined that the leakage accident has occurred.

根据本发明,所述新增时间序列向量为,在所述规定时间T以外的时间段依照所述特征获取步骤、预测流量获取步骤、参考数据值确定步骤获得的时间序列向量。According to the present invention, the newly added time series vector is a time series vector obtained according to the feature acquisition step, forecast flow acquisition step, and reference data value determination step during a time period other than the specified time T.

根据本发明,通过式(2)来计算新增时间序列向量相对于所述参考数据集中的每个时间序列向量的余弦距离。According to the present invention, formula (2) is used to calculate the cosine distance of the newly added time series vector relative to each time series vector in the reference data set.

式(2)中,i为新增时间序列向量,j为参考数据集中的时间序列向量,‖i‖和‖j‖为向量的模。In formula (2), i is the new time series vector, j is the time series vector in the reference data set, and ‖i‖ and ‖j‖ are the modulus of the vector.

根据本发明,待测供水管网的不同时间段的参考流量特征和参考气象特征的获取方式与上文的训练方法中,历史流量特征和历史气象特征的获取方式一致。According to the present invention, the acquisition method of the reference flow characteristics and the reference meteorological characteristics in different time periods of the water supply network to be tested is consistent with the acquisition method of the historical flow characteristics and historical meteorological characteristics in the above training method.

根据本发明,在上述识别方法中,设定所述时间T为2天,即48小时,设定数据的采集频率为k次/h(即一个小时内获得k个时间序列向量),则参考数据集中所包含的时间序列向量的个数为48k个。According to the present invention, in the above identification method, the time T is set to be 2 days, i.e. 48 hours, and the data collection frequency is set to be k times/h (that is, k time series vectors are obtained within one hour), then refer to The number of time series vectors contained in the data set is 48k.

在本发明的另一个优选的实施方式中,所述距离阈值D为为针对所述参考数据集中所有时间序列向量计算的所有余弦距离的中位数的0.1-0.5倍,优选为0.4-0.5倍。In another preferred embodiment of the present invention, the distance threshold D is 0.1-0.5 times the median of all cosine distances calculated for all time series vectors in the reference data set, preferably 0.4-0.5 times .

与现有城市供水管网漏损识别方法相比,本发明的识别方法的优势在于:Compared with the existing urban water supply network leakage identification method, the identification method of the present invention has the advantages of:

第一,区别于传统的神经网络模型,本发明把多个GRU层和全连接层通过并联或者串联的方式连接,形成一个复杂的深度神经网络。GRUN具有较强的处理非线性数据的能力,尤其是对于序列数据的处理能力较强,能够产生对过去数据的记忆状态,并建立不同时段数据之间的依赖关系。其次,GRUN的拟合能力较强,在学习过程中更容易收敛,不易陷入局部极小状态。所以采用GRUN能够更加精确的预测管网流量,从而对管网漏损进行识别,提高了管网漏损识别的准确率。First, different from the traditional neural network model, the present invention connects multiple GRU layers and fully connected layers in parallel or in series to form a complex deep neural network. GRUN has a strong ability to deal with nonlinear data, especially for sequence data. It can generate a memory state for past data and establish dependencies between data in different periods. Secondly, GRUN has a strong fitting ability, it is easier to converge during the learning process, and it is not easy to fall into a local minimum state. Therefore, the use of GRUN can predict the flow of the pipeline network more accurately, thereby identifying the leakage of the pipeline network, and improving the accuracy of the identification of the leakage of the pipeline network.

第二,本发明在使用GRUN精确预测流量后,使用基于余弦距离的异常值检测方法识别漏损事故,通过分析比较时间序列向量(由预测值和实测值构成)间的余弦距离判定是否发生漏损事故。一方面,余弦距离的使用消除了管网监测数据波动范围大对异常值检测造成的影响;另一方面,相较于分析预测值与实测值间的绝对差值,多个时间序列向量间余弦距离的比较避免了判定漏损事故时的主观性,准确度更高。Second, after using GRUN to accurately predict the flow rate, the present invention uses an outlier detection method based on cosine distance to identify leakage accidents, and determines whether leakage occurs by analyzing and comparing the cosine distance between time series vectors (consisting of predicted values and measured values). damage accident. On the one hand, the use of cosine distance eliminates the impact of the large fluctuation range of pipe network monitoring data on outlier detection; on the other hand, compared with the absolute difference between the analysis predicted value and the measured value, the cosine The comparison of the distance avoids the subjectivity when judging the leakage accident, and the accuracy is higher.

附图说明Description of drawings

图1为本发明的一个实施方式中的基于门控循环单元的神经网络模型的拓扑结构图。FIG. 1 is a topological structure diagram of a neural network model based on a gated recurrent unit in an embodiment of the present invention.

图2为本发明的一个实施方式中训练基于门控循环单元的神经网络模型的流程图。FIG. 2 is a flow chart of training a neural network model based on gated recurrent units in an embodiment of the present invention.

图3为表示本发明的实施例1中训练曲线和验证曲线的均方误差的图。FIG. 3 is a graph showing mean square errors of training curves and verification curves in Example 1 of the present invention.

图4为利用本发明的一个实施方式中的神经网络模型进行供水管网的漏损事故识别的流程图。Fig. 4 is a flow chart of using the neural network model in an embodiment of the present invention to recognize leakage accidents of the water supply pipe network.

具体实施方式Detailed ways

为更好的理解和实施本发明,下面将结合附图和具体实施例对本发明进行详细阐述。应当理解的是,虽然对本发明的实施方式进行了说明,但是显然,本发明不限定于上述实施方式,可以在不脱离其主旨的范围内进行各种变形。In order to better understand and implement the present invention, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that although the embodiments of the present invention have been described, it is obvious that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the gist thereof.

在以下实施方式中,利用Python 2.7软件作为模型的开发平台,并采用Numpy和Pandas库来读取、存储、分析数据,采用Matplotlib库来做数据的可视化,采用Keras库来搭建神经网络模型,大大提高了开发效率。In the following embodiments, Python 2.7 software is used as the model development platform, Numpy and Pandas libraries are used to read, store, and analyze data, Matplotlib library is used to visualize data, and Keras library is used to build neural network models. Improve development efficiency.

实施例1训练神经网络模型Embodiment 1 training neural network model

1)按照图1构建神经网络模型1) Construct the neural network model according to Figure 1

由3个GRU层和第一全连接层并联构成输入层(设定3个GRU层和第一全连接层的节点数分别为48,32,32,8,GRU层的激活函数为tanh和ReLU,第一全连接层的激活函数为ReLU);The input layer is composed of 3 GRU layers and the first fully connected layer in parallel (set the number of nodes of the 3 GRU layers and the first fully connected layer to be 48, 32, 32, 8 respectively, and the activation functions of the GRU layer are tanh and ReLU , the activation function of the first fully connected layer is ReLU);

以张量串联的模式使3个GRU层和第一全连接层分别与合并(Merge)层连接;Connect the 3 GRU layers and the first fully connected layer to the Merge layer in a tensor series mode;

以张量串联的模式使合并层与第二全连接层、第三全连接层、第四全连接层、第五全连接层、第六全连接层、第七全连接层连接(设定第二全连接层至第七全连接层的节点数为64,32,16,8,4,2,激活函数为ReLU);Connect the merged layer with the second fully connected layer, the third fully connected layer, the fourth fully connected layer, the fifth fully connected layer, the sixth fully connected layer, and the seventh fully connected layer in the tensor series mode (set the first The number of nodes from the second fully connected layer to the seventh fully connected layer is 64, 32, 16, 8, 4, 2, and the activation function is ReLU);

以张量串联的模式使第七全连接层与输出层连接(输出层的激活函数为Linear,学习率为0.02,batch_size为60)。The seventh fully connected layer is connected to the output layer in the tensor series mode (the activation function of the output layer is Linear, the learning rate is 0.02, and the batch_size is 60).

2)生成训练集和验证集2) Generate training set and validation set

2-1)对自来水公司的CZ市某DMA供水管网从2016年2月1日到2017年1月31日间的流量数据以采集频率为4次/h进行平均采样,即获取每隔15min的流量数据,对获取的数据进行预处理:包括清洗非自然因素(第三方、人为)导致事故的流量数据;修正录入错误,清洗明显异常数据等。然后,从中提取第一时间段、第二时间段、第三时间段的历史流量数据,并根据式(1)进行归一化处理,获取不同时间段的历史流量特征,其中,2-1) The flow data of a DMA water supply network in CZ City of the water company from February 1, 2016 to January 31, 2017 was averagely sampled at a collection frequency of 4 times/h, that is, every 15 minutes Preprocessing of the acquired data: including cleaning the traffic data caused by unnatural factors (third party, man-made) accidents; correcting input errors, cleaning obviously abnormal data, etc. Then, extract the historical flow data of the first time period, the second time period, and the third time period, and perform normalization processing according to the formula (1) to obtain the historical flow characteristics of different time periods, where,

第一时间段的流量数据包括t-75min、t-60min、t-45min、t-30min、t-15min时刻的流量数据;The flow data in the first time period include flow data at t-75min, t-60min, t-45min, t-30min, and t-15min;

第二时间段的流量数据包括t-24.5h、t-24.25h、t-24h、t-23.75h至t-23.5h时刻的流量数据;The flow data in the second time period includes the flow data from t-24.5h, t-24.25h, t-24h, t-23.75h to t-23.5h;

第三时间段的流量数据包括t-48.5h、t-48.25h、t-48h、t-47.75h至t-47.5h时刻的流量数据。The flow data in the third time period includes the flow data at time t-48.5h, t-48.25h, t-48h, t-47.75h to t-47.5h.

2-2)从中国气象数据网获取历史气象数据,包括最高温度、最低温度、相对湿度和降水量,对获取的数据进行预处理:包括清洗非自然因素(第三方、人为)导致事故的流量数据;修正录入错误,清洗明显异常数据等。将其与步骤2-1)中的历史流量数据进行Pearson相关性分析,发现最高温度、最低温度与流量的相关性显著,相关系数大于0.8,因此将最高温度、最低温度的归一化处理结果,作为历史气象特征。2-2) Obtain historical meteorological data from the China Meteorological Data Network, including maximum temperature, minimum temperature, relative humidity and precipitation, and preprocess the obtained data: including cleaning the flow of accidents caused by unnatural factors (third parties, man-made) data; correct input errors, clean obviously abnormal data, etc. Perform Pearson correlation analysis with the historical flow data in step 2-1), and find that the correlation between the highest temperature and the lowest temperature and the flow rate is significant, and the correlation coefficient is greater than 0.8, so the normalized processing results of the highest temperature and the lowest temperature , as a historical meteorological feature.

2-3)将不同时间段的历史流量特征和历史气象特征组成建模所需样本,先把样本随机打乱,然后把样本分为10份,随机抽取1份作为验证集,其余9份作为训练集,训练集22500个样本,验证集2500个样本。2-3) The historical flow characteristics and historical meteorological characteristics of different time periods are used to form the samples required for modeling. First, the samples are randomly disrupted, and then the samples are divided into 10 parts. One part is randomly selected as the verification set, and the remaining 9 parts are used as the verification set. The training set has 22500 samples in the training set and 2500 samples in the verification set.

3)训练模型3) Training model

按照图2的流程图进行神经网络模型的训练,具体地,将训练集和验证集的历史流量特征和历史气象特征分别输入神经网络模型的输入层中,获取输出的训练流量和验证流量。每完成一轮训练,训练集中的样本都会被随机打乱一次。The training of the neural network model is carried out according to the flow chart in Figure 2. Specifically, the historical flow characteristics and historical meteorological characteristics of the training set and the verification set are respectively input into the input layer of the neural network model, and the output training flow and verification flow are obtained. Every time a round of training is completed, the samples in the training set will be randomly shuffled once.

表1Table 1

4)验证模型4) Verify the model

基于所述训练集和训练流量生成训练曲线,并基于所述验证集和验证流量生成验证曲线。如图3所示,横坐标表示训练的轮数,每一轮训练迭代了375次;纵坐标表示训练集和验证集的均方误差。可以看出,当训练曲线和验证曲线的均方误差稳定在恒定值时,说明模型稳定,拟合较好,适于作为识别的神经网络模型。A training curve is generated based on the training set and training traffic, and a verification curve is generated based on the verification set and verification traffic. As shown in Figure 3, the abscissa indicates the number of rounds of training, and each round of training iterates 375 times; the ordinate indicates the mean square error of the training set and the verification set. It can be seen that when the mean square error of the training curve and the verification curve is stable at a constant value, it indicates that the model is stable and fits well, and is suitable as a neural network model for recognition.

另一方面,若两条曲线的均方误差没有稳定在恒定值,则说明模型不稳定,拟合较差,训练数据太少或者模型参数还需要优化。On the other hand, if the mean square error of the two curves is not stable at a constant value, it means that the model is unstable, the fitting is poor, there are too few training data or the model parameters need to be optimized.

在本例中,经训练得到的神经网络模型可示例性的表示为:In this example, the trained neural network model can be exemplarily expressed as:

Qt=Qt-i×W+bQ t =Q ti ×W+b

上式中,Qt为待预测时刻t的需水量;In the above formula, Qt is the water demand at the time t to be predicted;

Qt-i为t-i时刻的历史需水量,i=1,2,3…;Q ti is the historical water demand at time ti, i=1, 2, 3...;

W为权值矩阵;W is the weight matrix;

b为偏置项。b is a bias term.

实施例2漏损事故识别Embodiment 2 Leakage Accident Identification

已知,2017年2月1日至2月10日未发生任何漏损事故,以2017年2月1日-2月2日的流量数据构建参考数据集,并用于识别2017年2月3日到2月10日的漏损事故。It is known that no leakage accidents occurred from February 1, 2017 to February 10, 2017. The reference data set was constructed with the flow data from February 1 to February 2, 2017, and used to identify February 3, 2017 Leakage accident until February 10.

为了验证识别效果,人为的给2017年2月4日、5日和6日的流量数据分别增加该DMA日均流量(79m3/h)的5%、10%和15%。In order to verify the identification effect, the flow data on February 4, 5 and 6, 2017 were artificially increased by 5%, 10% and 15% of the DMA daily average flow (79m 3 /h) respectively.

按照图4所示的流程图进行漏损事故的识别,具体地,Carry out leakage accident identification according to the flow chart shown in Figure 4, specifically,

步骤一,按照实施例1中步骤2)的方式获得在未发生漏损事故的2017年2月1日-2017年2月2日的48h内的参考流量特征和参考气象特征。Step 1: Obtain the reference flow characteristics and reference meteorological characteristics within 48 hours from February 1, 2017 to February 2, 2017, according to the method of step 2) in Example 1.

步骤二,将步骤一获得的不同时间段的参考流量特征输入到实施例1训练完成的神经网络模型的多个门控循环单元层中,并将步骤一获得的参考气象特征输入到所述第一全连接层中,获取输出的预测流量。Step 2, input the reference flow characteristics obtained in step 1 in different time periods into the multiple gated recurrent unit layers of the neural network model trained in embodiment 1, and input the reference meteorological characteristics obtained in step 1 into the first In a fully connected layer, the output prediction flow is obtained.

步骤三,获取2017年2月1日-2017年2月2日的48h内的实测流量数据,将每一实测流量与处于相同时刻的步骤二获得的预测流量构成一个时间序列向量。那么,在这两天时间内,共构成192个时间序列向量(48h,采集频率为4次/h),将这192个时间序列向量构成的矩阵作为参考数据集,表2为参考数据集的一部分的示例。Step 3: Acquire the measured flow data within 48 hours from February 1, 2017 to February 2, 2017, and form a time series vector with each measured flow and the predicted flow obtained in step 2 at the same time. Then, in these two days, a total of 192 time series vectors (48h, the acquisition frequency is 4 times/h) are formed, and the matrix formed by these 192 time series vectors is used as a reference data set. Table 2 shows the reference data set Part of the example.

表2Table 2

步骤四,按照上述步骤一至步骤三的方式,将2017年2月3日到2月10日的流量数据处理为768个新增时间序列向量(192h,采集频率为4次/h)。Step 4: Process the flow data from February 3rd to February 10th, 2017 into 768 new time series vectors (192h, the collection frequency is 4 times/h) according to the above steps 1 to 3.

基于式(2),计算每个新增时间序列向量相对于步骤三获得的参考数据集中的每个时间序列向量的余弦距离,在每个新增时间序列向量所计算出的192个余弦距离中,统计余弦距离小于距离阈值D的时间序列向量的个数n。在本例中,距离阈值D为192个余弦距离中位数的0.45倍,即0.00133,数量阈值N为42。Based on formula (2), calculate the cosine distance of each new time series vector relative to each time series vector in the reference data set obtained in step 3, among the 192 cosine distances calculated by each new time series vector , the number n of time series vectors whose cosine distance is less than the distance threshold D is counted. In this example, the distance threshold D is 0.45 times the median of 192 cosine distances, that is, 0.00133, and the number threshold N is 42.

当n大于数量阈值N时,认定该新增时间序列向量为正常向量,代表该时间识别到没有漏损事故发生;当n在数量阈值N以下时,认定该新增时间序列向量为异常向量,代表该时间识别到有漏损事故发生。When n is greater than the number threshold N, the newly added time series vector is determined to be a normal vector, which means that no leakage accidents have been identified at this time; when n is below the number threshold N, the newly added time series vector is determined to be an abnormal vector, Indicates the time at which a leakage accident was identified.

表3识别结果Table 3 Recognition results

理论上来说,在2017年2月3日到2月10日共计8天的768个新增时间序列中,应有480个正常向量和288个异常向量。根据表3的识别结果可知,实施例1的神经网络模型可以识别出流量较小的漏损(+5%的DMA日均流量),但不敏感;而对于流量较大的漏损(+10%、+15%的DMA日均流量)可以实现准确识别,准确率在85%以上。Theoretically, there should be 480 normal vectors and 288 abnormal vectors among the 768 new time series for 8 days from February 3 to February 10, 2017. According to the identification result of table 3, it can be known that the neural network model of embodiment 1 can identify the leakage (+5% DMA daily average flow) of the flow, but it is not sensitive; %, +15% DMA daily average traffic) can realize accurate identification, and the accuracy rate is above 85%.

以上结果说明,基于门控循环单元的神经网络模型,能够较为准确的识别出供水管网的漏损事故,并且该方法的实用性较强。本发明扩展了现有的管网漏损识别模型的研究内容,为自来水公司做出科学合理的决策提供了一种新的思路。The above results show that the neural network model based on the gated cyclic unit can more accurately identify the leakage accidents of the water supply network, and the method is more practical. The invention expands the research content of the existing pipeline network leakage identification model, and provides a new idea for water companies to make scientific and reasonable decisions.

虽然本发明已作了详细描述,但对本领域技术人员来说,在本发明精神和范围内的修改将是显而易见的。此外,应当理解的是,本发明记载的各方面、不同具体实施方式的各部分、和列举的各种特征可被组合或全部或部分互换。在上述的各个具体实施方式中,那些参考另一个具体实施方式的实施方式可适当地与其它实施方式组合,这是将由本领域技术人员所能理解的。此外,本领域技术人员将会理解,前面的描述仅是示例的方式,并不旨在限制本发明。While the invention has been described in detail, modifications within the spirit and scope of the invention will be readily apparent to those skilled in the art. In addition, it should be understood that various aspects described in the present invention, various parts of different specific embodiments, and various listed features may be combined or interchanged in whole or in part. In each of the specific embodiments described above, those embodiments that refer to another specific embodiment may be appropriately combined with other embodiments, as will be understood by those skilled in the art. Furthermore, those skilled in the art will appreciate that the foregoing description is by way of example only, and is not intended to limit the invention.

Claims (9)

1.一种基于门控循环单元的神经网络模型,用于识别供水管网的漏损事故,包括:1. A neural network model based on gated recurrent units for identifying leakage accidents in water supply networks, including: 多个门控循环单元层,其被配置成接收供水管网在不同时间段的流量特征;a plurality of layers of gated recirculation units configured to receive flow characteristics of the water distribution network at different time periods; 第一全连接层,其与所述多个门控循环单元层并联构成输入层,所述第一全连接层被配置成接收供水管网的气象特征;A first fully connected layer, which is connected in parallel with the multiple gated recurrent unit layers to form an input layer, and the first fully connected layer is configured to receive meteorological features of the water supply network; 与所述输入层以张量串联的模式连接的合并层;a pooling layer connected in tensor concatenation with said input layer; 均与所述合并层以张量串联的模式连接的第二全连接层至第M全连接层,M为大于或等于2的整数;以及The second fully-connected layer to the Mth fully-connected layer, all of which are connected to the merging layer in tensor series, where M is an integer greater than or equal to 2; and 与所述第M全连接层以张量串联的模式连接的输出层,其被配置成输出供水管网在下一时刻的预测流量。An output layer connected to the Mth fully connected layer in tensor series, configured to output the predicted flow rate of the water supply network at the next moment. 2.一种权利要求1所述的神经网络模型的训练方法,包括:2. a training method of the neural network model claimed in claim 1, comprising: 构建所述神经网络模型;Construct the neural network model; 将不同时间段的历史流量特征和历史气象特征按比例随机分为训练集和验证集;Randomly divide the historical flow characteristics and historical meteorological characteristics of different time periods into a training set and a verification set; 将所述训练集中不同时间段的历史流量特征输入到所述多个门控循环单元层中,并将所述训练集中的历史气象特征输入到所述第一全连接层中,获取所述神经网络模型输出的训练流量;Input the historical traffic characteristics of different time periods in the training set into the multiple gated recurrent unit layers, and input the historical meteorological characteristics in the training set into the first fully connected layer, and obtain the neural The training traffic output by the network model; 将所述验证集中不同时间段的历史流量特征输入到所述多个门控循环单元层中,并将所述验证集中的历史气象特征输入到所述第一全连接层中,获取所述神经网络模型输出的验证流量;Input the historical traffic characteristics of different time periods in the verification set into the multiple gated recurrent unit layers, and input the historical meteorological characteristics in the verification set into the first fully connected layer to obtain the neural Verification traffic output by the network model; 基于所述训练集和训练流量生成训练曲线,并基于所述验证集和验证流量生成验证曲线,当所述训练曲线和验证曲线的均方误差值稳定在恒定值时,完成所述神经网络模型的训练。Generate a training curve based on the training set and training traffic, and generate a verification curve based on the verification set and verification traffic, when the mean square error value of the training curve and verification curve is stable at a constant value, complete the neural network model training. 3.根据权利要求2所述的训练方法,其特征在于,还包括获取所述不同时间段的历史流量特征,包括:3. The training method according to claim 2, further comprising obtaining historical traffic characteristics of the different time periods, including: 获取待测供水管网的历史流量数据;以及Obtain historical flow data of the water supply network to be tested; and 对所述历史流量数据进行提取处理和归一化处理得到所述历史流量特征。Extraction processing and normalization processing are performed on the historical traffic data to obtain the historical traffic features. 4.根据权利要求3所述的训练方法,其特征在于,对所述历史流量数据进行提取处理包括,在供水管网的历史流量数据中,分别从所述第一时间段、第二时间段、第三时间段中以等间隔提取指定个数的流量数据,其中,4. The training method according to claim 3, wherein extracting the historical flow data comprises, in the historical flow data of the water supply pipe network, respectively starting from the first time period and the second time period , Extract the specified number of traffic data at equal intervals in the third time period, where, 在临近待预测时刻t之前选取第一时间段,Select the first time period before the time t to be predicted, 在所述第一时间段的起始时刻之前选取第二时间段,selecting a second time period before the starting moment of the first time period, 在所述第二时间段的起始时刻之前选取第三时间段。A third time period is selected before the starting moment of the second time period. 5.根据权利要求3或4所述的训练方法,其特征在于,还包括获取所述历史气象特征,包括:5. according to the described training method of claim 3 or 4, it is characterized in that, also comprise obtaining described historical meteorological characteristic, comprise: 获取待测供水管网的历史气象数据;以及Obtain historical weather data of the water supply network to be tested; and 对所述历史气象数据进行提取处理和归一化处理得到所述历史气象特征。Extraction processing and normalization processing are performed on the historical meteorological data to obtain the historical meteorological features. 6.根据权利要求5所述的训练方法,其特征在于,对所述历史气象数据进行提取处理包括:对所述历史气象数据和所述历史流量数据进行Pearson相关性分析,选取相关系数大于或等于规定值的历史气象数据,得到提取处理后的历史气象数据。6. training method according to claim 5, it is characterized in that, extracting described historical meteorological data comprises: carrying out Pearson correlation analysis to described historical meteorological data and described historical flow data, select correlation coefficient greater than or The historical meteorological data equal to the specified value is obtained to obtain the extracted and processed historical meteorological data. 7.根据权利要求6所述的训练方法,其特征在于,所述规定值为0.80-0.99。7. The training method according to claim 6, characterized in that, the prescribed value is 0.80-0.99. 8.一种供水管网的漏损事故的识别方法,包括,8. A method for identifying leakage accidents of a water supply pipe network, comprising: 特征获取步骤,在未发生漏损事故的规定时间内,获取待测供水管网的不同时间段的参考流量特征和参考气象特征;The feature acquisition step is to acquire the reference flow characteristics and reference meteorological characteristics of the water supply network to be tested in different time periods within the specified time period when no leakage accident occurs; 预测流量获取步骤,将所述不同时间段的参考流量特征输入到权利要求1所述的神经网络模型的多个门控循环单元层中,并将所述参考气象特征输入到所述神经网络模型的第一全连接层中,获取所述神经网络模型输出的预测流量;Forecast flow acquisition step, input the reference flow characteristics of the different time periods into the multiple gated recurrent unit layers of the neural network model according to claim 1, and input the reference meteorological characteristics into the neural network model In the first fully connected layer, obtain the predicted traffic output by the neural network model; 参考数据集确定步骤,获取在所述规定时间内的实测流量,每组处于相同时刻的预测流量与实测流量构成一个时间序列向量,将所述规定时间内的所有时间序列向量构成的矩阵作为参考数据集;Refer to the step of determining the data set to obtain the measured flow within the specified time, each group of predicted flow and measured flow at the same time constitutes a time series vector, and use the matrix formed by all time series vectors within the specified time as a reference data set; 事故识别步骤,计算新增的时间序列向量相对于所述参考数据集中的每个时间序列向量的余弦距离,统计余弦距离小于距离阈值的时间序列向量的个数,当统计的个数小于或等于数量阈值时,确定发生了所述漏损事故;The accident identification step is to calculate the cosine distance of the newly added time series vector relative to each time series vector in the reference data set, and count the number of time series vectors whose cosine distance is less than the distance threshold, when the number of statistics is less than or equal to When the quantity threshold value is reached, it is determined that the leakage accident has occurred; 其中,所述新增的时间序列向量为,在所述规定时间以外的时间段依照所述特征获取步骤、预测流量获取步骤、参考数据值确定步骤获得的时间序列向量。Wherein, the newly added time-series vector is a time-series vector obtained according to the feature acquisition step, forecast traffic acquisition step, and reference data value determination step in a time period other than the specified time. 9.根据权利要求8所述的识别方法,其特征在于,所述距离阈值为针对所述参考数据集中所有时间序列向量计算的所有余弦距离的中位数的0.1-0.5倍。9. The identification method according to claim 8, wherein the distance threshold is 0.1-0.5 times the median of all cosine distances calculated for all time series vectors in the reference data set.
CN201710998436.8A 2017-10-24 2017-10-24 Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model Active CN108051035B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710998436.8A CN108051035B (en) 2017-10-24 2017-10-24 Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710998436.8A CN108051035B (en) 2017-10-24 2017-10-24 Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model

Publications (2)

Publication Number Publication Date
CN108051035A true CN108051035A (en) 2018-05-18
CN108051035B CN108051035B (en) 2019-08-09

Family

ID=62119600

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710998436.8A Active CN108051035B (en) 2017-10-24 2017-10-24 Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model

Country Status (1)

Country Link
CN (1) CN108051035B (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108900446A (en) * 2018-05-28 2018-11-27 南京信息工程大学 Coordinate transform norm blind balance method based on gating cycle unit neural network
CN109359698A (en) * 2018-10-30 2019-02-19 清华大学 A leak identification method based on long short-term memory neural network model
CN109522716A (en) * 2018-11-15 2019-03-26 中国人民解放军战略支援部队信息工程大学 A kind of network inbreak detection method and device based on timing neural network
CN110070175A (en) * 2019-04-12 2019-07-30 北京市商汤科技开发有限公司 Image processing method, model training method and device, electronic equipment
CN110599468A (en) * 2019-08-30 2019-12-20 中国信息通信研究院 No-reference video quality evaluation method and device
CN110837933A (en) * 2019-11-11 2020-02-25 重庆远通电子技术开发有限公司 Leakage identification method, device, equipment and storage medium based on neural network
CN111062476A (en) * 2019-12-06 2020-04-24 重庆大学 Water quality prediction method based on gated circulation unit network integration
CN112101400A (en) * 2019-12-19 2020-12-18 国网江西省电力有限公司电力科学研究院 Industrial control system abnormality detection method, equipment and server, storage medium
CN112118143A (en) * 2020-11-18 2020-12-22 迈普通信技术股份有限公司 Traffic prediction model, training method, prediction method, device, apparatus, and medium
CN113280265A (en) * 2020-02-20 2021-08-20 中国石油天然气股份有限公司 Working condition identification method and device, computer equipment and storage medium
CN113944888A (en) * 2021-11-03 2022-01-18 北京软通智慧科技有限公司 Gas pipeline leakage detection method, device, equipment and storage medium
CN115031776A (en) * 2022-05-12 2022-09-09 浙江中控信息产业股份有限公司 Method for monitoring and analyzing siltation of drainage pipe network
CN115654381A (en) * 2022-10-24 2023-01-31 电子科技大学 Water supply pipeline leakage detection method based on graph neural network
CN117490002A (en) * 2023-12-28 2024-02-02 成都同飞科技有限责任公司 Water supply network flow prediction method and system based on flow monitoring data

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130066568A1 (en) * 2010-04-15 2013-03-14 Julio Roberto Alonso Integrated system with acoustic technology, mass imbalance and neural network for detecting, locating and quantifying leaks in ducts
CN103530818A (en) * 2013-10-12 2014-01-22 杭州电子科技大学 Water supply pipe network modeling method based on BRB (belief-rule-base) system
CN104061445A (en) * 2014-07-09 2014-09-24 中国石油大学(华东) Pipeline leakage detection method based on neural network
CN105221933A (en) * 2015-08-24 2016-01-06 哈尔滨工业大学 A kind of pipeline network leak detecting method in conjunction with resistance identification
CN106022518A (en) * 2016-05-17 2016-10-12 清华大学 Pipe damage probability prediction method based on BP neural network
CN106287239A (en) * 2016-08-16 2017-01-04 浙江大学 Ball device and method is detected in the intelligence pipe of public supply mains leakage location
CN106352244A (en) * 2016-08-31 2017-01-25 中国石油化工股份有限公司 Pipeline leakage detection method based on hierarchical neural network
CN206130547U (en) * 2016-07-07 2017-04-26 北京信息科技大学 Gas transmission pipeline leak testing system under multiplex condition
CN107013812A (en) * 2017-05-05 2017-08-04 西安科技大学 A kind of THM coupling line leakage method
CN107239859A (en) * 2017-06-05 2017-10-10 国网山东省电力公司电力科学研究院 The heating load forecasting method of Recognition with Recurrent Neural Network is remembered based on series connection shot and long term

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130066568A1 (en) * 2010-04-15 2013-03-14 Julio Roberto Alonso Integrated system with acoustic technology, mass imbalance and neural network for detecting, locating and quantifying leaks in ducts
CN103530818A (en) * 2013-10-12 2014-01-22 杭州电子科技大学 Water supply pipe network modeling method based on BRB (belief-rule-base) system
CN104061445A (en) * 2014-07-09 2014-09-24 中国石油大学(华东) Pipeline leakage detection method based on neural network
CN105221933A (en) * 2015-08-24 2016-01-06 哈尔滨工业大学 A kind of pipeline network leak detecting method in conjunction with resistance identification
CN106022518A (en) * 2016-05-17 2016-10-12 清华大学 Pipe damage probability prediction method based on BP neural network
CN206130547U (en) * 2016-07-07 2017-04-26 北京信息科技大学 Gas transmission pipeline leak testing system under multiplex condition
CN106287239A (en) * 2016-08-16 2017-01-04 浙江大学 Ball device and method is detected in the intelligence pipe of public supply mains leakage location
CN106352244A (en) * 2016-08-31 2017-01-25 中国石油化工股份有限公司 Pipeline leakage detection method based on hierarchical neural network
CN107013812A (en) * 2017-05-05 2017-08-04 西安科技大学 A kind of THM coupling line leakage method
CN107239859A (en) * 2017-06-05 2017-10-10 国网山东省电力公司电力科学研究院 The heating load forecasting method of Recognition with Recurrent Neural Network is remembered based on series connection shot and long term

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108900446A (en) * 2018-05-28 2018-11-27 南京信息工程大学 Coordinate transform norm blind balance method based on gating cycle unit neural network
CN109359698A (en) * 2018-10-30 2019-02-19 清华大学 A leak identification method based on long short-term memory neural network model
CN109522716A (en) * 2018-11-15 2019-03-26 中国人民解放军战略支援部队信息工程大学 A kind of network inbreak detection method and device based on timing neural network
CN110070175A (en) * 2019-04-12 2019-07-30 北京市商汤科技开发有限公司 Image processing method, model training method and device, electronic equipment
CN110070175B (en) * 2019-04-12 2021-07-02 北京市商汤科技开发有限公司 Image processing method, model training method and device and electronic equipment
CN110599468A (en) * 2019-08-30 2019-12-20 中国信息通信研究院 No-reference video quality evaluation method and device
CN110837933A (en) * 2019-11-11 2020-02-25 重庆远通电子技术开发有限公司 Leakage identification method, device, equipment and storage medium based on neural network
CN111062476A (en) * 2019-12-06 2020-04-24 重庆大学 Water quality prediction method based on gated circulation unit network integration
CN112101400A (en) * 2019-12-19 2020-12-18 国网江西省电力有限公司电力科学研究院 Industrial control system abnormality detection method, equipment and server, storage medium
CN113280265A (en) * 2020-02-20 2021-08-20 中国石油天然气股份有限公司 Working condition identification method and device, computer equipment and storage medium
CN113280265B (en) * 2020-02-20 2022-08-05 中国石油天然气股份有限公司 Working condition identification method and device, computer equipment and storage medium
CN112118143A (en) * 2020-11-18 2020-12-22 迈普通信技术股份有限公司 Traffic prediction model, training method, prediction method, device, apparatus, and medium
CN112118143B (en) * 2020-11-18 2021-02-19 迈普通信技术股份有限公司 Traffic prediction model training method, traffic prediction method, device, equipment and medium
CN113944888A (en) * 2021-11-03 2022-01-18 北京软通智慧科技有限公司 Gas pipeline leakage detection method, device, equipment and storage medium
CN113944888B (en) * 2021-11-03 2023-12-08 北京软通智慧科技有限公司 Gas pipeline leakage detection method, device, equipment and storage medium
CN115031776A (en) * 2022-05-12 2022-09-09 浙江中控信息产业股份有限公司 Method for monitoring and analyzing siltation of drainage pipe network
CN115654381A (en) * 2022-10-24 2023-01-31 电子科技大学 Water supply pipeline leakage detection method based on graph neural network
CN117490002A (en) * 2023-12-28 2024-02-02 成都同飞科技有限责任公司 Water supply network flow prediction method and system based on flow monitoring data
CN117490002B (en) * 2023-12-28 2024-03-08 成都同飞科技有限责任公司 Water supply network flow prediction method and system based on flow monitoring data

Also Published As

Publication number Publication date
CN108051035B (en) 2019-08-09

Similar Documents

Publication Publication Date Title
CN108051035B (en) Pipe Network Leakage Identification Method Based on Gated Recurrent Unit Neural Network Model
CN104199832B (en) Banking network based on comentropy transaction community discovery method extremely
CN112686464A (en) Short-term wind power prediction method and device
WO2016101628A1 (en) Data processing method and device in data modeling
CN104090974B (en) The Application of Data Mining of the follow-up water of extension reservoir and system
CN110910004A (en) A method and system for extracting reservoir scheduling rules with multiple uncertainties
CN107886160B (en) BP neural network interval water demand prediction method
CN105574642A (en) Smart grid big data-based electricity price execution checking method
CN105844294A (en) Electricity usage behavior analysis method based on FCM cluster algorithm
CN113408808B (en) Training method, data generation device, electronic equipment and storage medium
CN113256326A (en) Method for realizing prediction of commodity extra-large screen point position pedestrian volume based on deep learning
CN108154311A (en) Top-tier customer recognition methods and device based on random forest and decision tree
CN114169645A (en) A short-term load forecasting method for smart grid
CN115329930A (en) Flood process probability forecasting method based on mixed deep learning model
CN113449257A (en) Power distribution network line loss prediction method, control device, and storage medium
CN113361776A (en) Power load probability prediction method based on user power consumption behavior clustering
CN113962425A (en) Heating data generation method, apparatus, device and computer storage medium
CN108197795A (en) The account recognition methods of malice group, device, terminal and storage medium
CN118035760A (en) Canal filling water flow determining, model constructing and standard flow information extracting method
CN105488598A (en) Medium-and-long time electric power load prediction method based on fuzzy clustering
CN116595371A (en) Topic heat prediction model training method, topic heat prediction method and topic heat prediction device
CN111047079B (en) Wind power plant wind speed time series prediction method and system
CN106816871B (en) State similarity analysis method for power system
CN104915430A (en) Method for obtaining constraint relation rough set rules based on MapReduce
CN108491958A (en) Short-time bus passenger flow chord invariant prediction method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant