CN116739176A - Tunnel mechanized construction risk prediction method based on deep belief network - Google Patents

Tunnel mechanized construction risk prediction method based on deep belief network Download PDF

Info

Publication number
CN116739176A
CN116739176A CN202310743584.0A CN202310743584A CN116739176A CN 116739176 A CN116739176 A CN 116739176A CN 202310743584 A CN202310743584 A CN 202310743584A CN 116739176 A CN116739176 A CN 116739176A
Authority
CN
China
Prior art keywords
tunnel
risk prediction
mechanized construction
model
construction risk
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.)
Pending
Application number
CN202310743584.0A
Other languages
Chinese (zh)
Inventor
胡洋
宋战平
谢江胜
孙引浩
高永吉
赵亮
田小旭
张玉伟
刘乃飞
郑方
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.)
Xian University of Architecture and Technology
China Railway 20th Bureau Group Corp
Original Assignee
Xian University of Architecture and Technology
China Railway 20th Bureau Group Corp
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 Xian University of Architecture and Technology, China Railway 20th Bureau Group Corp filed Critical Xian University of Architecture and Technology
Priority to CN202310743584.0A priority Critical patent/CN116739176A/en
Publication of CN116739176A publication Critical patent/CN116739176A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/047Probabilistic or stochastic networks
    • 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
    • G06N3/0475Generative networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/088Non-supervised learning, e.g. competitive learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08Construction

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a tunnel mechanized construction risk prediction method based on a deep confidence network, which comprises the steps of establishing a tunnel mechanized construction risk evaluation system, establishing a tunnel mechanized construction risk prediction database, dividing a training set and a testing set, then carrying out learning training and verification on the training set, testing the performance of a tunnel mechanized construction risk prediction model by the testing set, and simultaneously adjusting the super parameters of a DBN model by using an improved particle swarm optimization algorithm, so that model training is accelerated and accuracy is improved. The method integrates data collection, data preprocessing, model building and risk prediction, can predict the tunnel mechanized construction risk according to the survey condition before construction, and can reduce the risk by adopting related measures by a designer.

Description

一种基于深度置信网络的隧道机械化施工风险预测方法A risk prediction method for tunnel mechanized construction based on deep belief network

技术领域Technical field

本申请涉及一种基于深度置信网络的隧道机械化施工风险预测方法,属于隧道机械化施工技术领域。This application relates to a tunnel mechanized construction risk prediction method based on a deep belief network, which belongs to the technical field of tunnel mechanized construction.

背景技术Background technique

随着隧道建设的快速发展,隧道掘进机因其具有掘进速度快、施工安全可靠、高校环保和降低工人劳动强度等特点,被广泛地应用到交通、水利等领域的隧道及地下工程施工中。在隧道机械化施工过程中如果出现突发的意外情况,将会对施工人员和设备造成难以承受的巨大损失。所以在施工前,通过对现场风险源进行分析,进而对隧道机械化施工风险进行预测是很有必要的。在施工前,通过对隧道机械化施工风险进行预测得到发生风险的可能值。当风险过大时,设计人员可以通过采取相关措施来降低风险,从而采取使施工风险达到最小的施工方案,有利于保障施工人员的生命安全和降低财产损失。With the rapid development of tunnel construction, tunnel boring machines are widely used in tunnel and underground engineering construction in transportation, water conservancy and other fields due to their characteristics of fast excavation speed, safe and reliable construction, environmental protection and reduced labor intensity for workers. If an unexpected situation occurs during the mechanized construction of tunnels, it will cause unbearable huge losses to construction personnel and equipment. Therefore, before construction, it is necessary to analyze the on-site risk sources and then predict the risks of tunnel mechanized construction. Before construction, the possible value of the risk can be obtained by predicting the risks of mechanized tunnel construction. When the risk is too great, designers can take relevant measures to reduce the risk and adopt a construction plan that minimizes construction risks, which is beneficial to protecting the lives of construction workers and reducing property losses.

目前,更多的传统方法是靠专家经验主观评判施工风险,仅靠专家经验进行风险识别很可能会导致风险遗漏和识别不全面的情况。而且隧道机械化施工具有复杂性、动态性和非线性的特点,仅使用专家评价法并不能解决隧道机械化施工风险评价的模糊性、随机性问题,表现为预测结果准确度较低,无法达到施工参考的要求。At present, more traditional methods rely on expert experience to subjectively judge construction risks. Relying solely on expert experience for risk identification is likely to lead to missed risks and incomplete identification. Moreover, mechanized tunnel construction has the characteristics of complexity, dynamics and nonlinearity. Only using expert evaluation methods cannot solve the problems of ambiguity and randomness in risk assessment of tunnel mechanized construction. The prediction results are less accurate and cannot reach the construction reference. requirements.

发明内容Contents of the invention

根据本申请的一个方面,提供了一种基于深度置信网络的隧道机械化施工风险预测方法,该预测方法集数据收集、数据预处理、模型建立、风险预测于一体,能够根据施工前的勘测情况,对隧道机械化施工风险进行预测,设计人员可以通过采取相关措施来降低风险。According to one aspect of this application, a risk prediction method for tunnel mechanized construction based on a deep belief network is provided. The prediction method integrates data collection, data preprocessing, model establishment, and risk prediction, and can be based on pre-construction survey conditions. By predicting the risks of mechanized tunnel construction, designers can reduce risks by taking relevant measures.

一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述施工风险预测方法包括以下步骤:A tunnel mechanized construction risk prediction method based on deep belief network, characterized in that the construction risk prediction method includes the following steps:

S1建立隧道机械化施工风险因素评价标准;S1 establishes risk factor evaluation standards for tunnel mechanized construction;

S2通过风险因素评价标准建立隧道机械化施工风险指标体系;S2 establishes a tunnel mechanized construction risk index system through risk factor evaluation standards;

S3收集专家们根据风险因素评价标准建立风险因素评价向量和风险预测结果,其中,每一组风险因素评价向量对应一组风险预测结果;S3 collects experts to establish risk factor evaluation vectors and risk prediction results based on risk factor evaluation standards. Each set of risk factor evaluation vectors corresponds to a set of risk prediction results;

S4对S3收集到的数据进行预处理,包括通过对数据集中的缺失值和异常值进行处理,避免异常数据对模型训练造成错误的影响;S4 preprocesses the data collected by S3, including processing missing values and outliers in the data set to avoid the erroneous impact of abnormal data on model training;

S5根据预处理后的数据构建隧道机械化施工风险预测数据库;S5 builds a tunnel mechanized construction risk prediction database based on the preprocessed data;

S6将S5中预测数据库中的数据划分为训练集和测试集,其中,训练集数据用来训练模型和验证模型的性能,测试集用来测试最优隧道机械化施工风险预测模型的预测准确性;S6 divides the data in the prediction database in S5 into a training set and a test set. The training set data is used to train the model and verify the performance of the model, and the test set is used to test the prediction accuracy of the optimal tunnel mechanized construction risk prediction model;

S7初始化隧道机械化施工风险预测模型的超参数;S7 initializes the hyperparameters of the tunnel mechanized construction risk prediction model;

S8使用K折交叉验证的方法,将训练集重新划分为新的训练集和验证集,随机初始化模型参数,使用新的训练集数据来训练模型,使用验证集中的数据测试模型的性能;S8 uses the K-fold cross-validation method to re-divide the training set into a new training set and a validation set, randomly initialize the model parameters, use the new training set data to train the model, and use the data in the validation set to test the performance of the model;

S9使用受限波尔兹曼机RBM无监督正向学习,将所述隧道机械化施工风险因素特征量输入,逐层训练,使浅层原始特征获得高层次表达;S9 uses restricted Boltzmann machine RBM unsupervised forward learning to input the feature quantities of the tunnel mechanized construction risk factors and train them layer by layer, so that the shallow original features can obtain high-level expression;

S10使用误差反向传播算法对隧道机械化施工风险预测模型的超参数进行反向微调,使其收敛至全局最优点,优化模型对风险因素的辨识能力;S10 uses the error back propagation algorithm to reversely fine-tune the hyperparameters of the tunnel mechanized construction risk prediction model so that it converges to the global optimal point and optimizes the model's ability to identify risk factors;

S11使用改进的粒子群寻优算法调整隧道机械化施工风险预测模型的超参数;S11 uses an improved particle swarm optimization algorithm to adjust the hyperparameters of the tunnel mechanized construction risk prediction model;

S12判断隧道机械化施工风险预测模型是否满足粒子群优化算法寻优条件,如果满足条件,得到性能最优的隧道机械化施工风险预测模型,如果没有满足条件,则使用S11中确定的超参数构建新的隧道机械化施工风险预测模型,重复步骤S8-S11;S12 determines whether the tunnel mechanized construction risk prediction model meets the particle swarm optimization algorithm optimization conditions. If the conditions are met, the tunnel mechanized construction risk prediction model with the best performance is obtained. If the conditions are not met, a new model is constructed using the hyperparameters determined in S11. Tunnel mechanized construction risk prediction model, repeat steps S8-S11;

S13使用S12中得到的隧道机械化施工风险预测模型,输入测试集数据对隧道机械化施工风险进行预测,测试隧道机械化施工风险预测模型的预测性能;S13 uses the tunnel mechanized construction risk prediction model obtained in S12, inputs the test set data to predict the tunnel mechanized construction risks, and tests the prediction performance of the tunnel mechanized construction risk prediction model;

S14现场人员根据现场施工情况,按照风险因素评价标准,将风险因素隶属度向量输入到隧道机械化施工风险预测模型中,得到隧道机械化施工风险概率。S14 On-site personnel input the risk factor membership vector into the tunnel mechanized construction risk prediction model based on the on-site construction conditions and risk factor evaluation standards to obtain the tunnel mechanized construction risk probability.

进一步的,所述超参数包括输入节点数、输出节点数、隐藏层层数、隐藏层节点数、训练迭代次数、批量大小、学习率和动量;Further, the hyperparameters include the number of input nodes, the number of output nodes, the number of hidden layer layers, the number of hidden layer nodes, the number of training iterations, batch size, learning rate and momentum;

需要初始化的超参数包括输入节点数、输出节点数、隐藏层层数、隐藏层节点数、训练迭代次数、批量大小、学习率和动量。Hyperparameters that need to be initialized include the number of input nodes, the number of output nodes, the number of hidden layer layers, the number of hidden layer nodes, the number of training iterations, batch size, learning rate, and momentum.

进一步的,所述初始化模型参数包括可见层单元i和隐藏层单元j的神经元连接权重wij、可见层单元神经元i的偏置ai和隐藏层单元j的偏置bjFurther, the initialized model parameters include the neuron connection weight w ij of the visible layer unit i and the hidden layer unit j, the bias a i of the visible layer unit neuron i and the bias b j of the hidden layer unit j;

其中,使用绝对平均误差MAE和相对平均误差MRE作为模型的性能评价指标,定义如下:Among them, the absolute average error MAE and the relative average error MRE are used as the performance evaluation indicators of the model, which are defined as follows:

其中:youtput,i和tfact,i分别表示第i个样本输入的预测值和真实值;Among them: y output,i and t fact,i respectively represent the predicted value and true value of the i-th sample input;

MRE与MAE的值越小,表示隧道机械化施工风险预测模型预测效果越准确。The smaller the values of MRE and MAE, the more accurate the prediction effect of the tunnel mechanized construction risk prediction model.

进一步的,在所述可见层单元所在的可见层和所述隐藏层单元所在的隐藏层中加入高斯噪声。Further, Gaussian noise is added to the visible layer where the visible layer unit is located and the hidden layer where the hidden layer unit is located.

进一步的,S9中所述受限波尔兹曼机RBM无监督的正向学习过程包括以下步骤:Further, the unsupervised forward learning process of the restricted Boltzmann machine RBM described in S9 includes the following steps:

参数初始化:初始化RBM模型参数,即层间的连接权值和各层的偏置,从[-1,1]中的均匀分布中随机抽取样本作为RBM模型的参数;Parameter initialization: Initialize the RBM model parameters, that is, the connection weights between layers and the bias of each layer, and randomly select samples from the uniform distribution in [-1,1] as parameters of the RBM model;

可见层和隐藏层间的联合能量函数为:The joint energy function between the visible layer and the hidden layer is:

其中,vi为可见层中第i个神经元状态;Among them, vi is the i-th neuron state in the visible layer;

hj为隐藏层中第j个神经元状态;h j is the j-th neuron state in the hidden layer;

ai和bj分别为可见层中第i个神经元和隐藏层中第j个神经元的偏置;a i and b j are the biases of the i-th neuron in the visible layer and the j-th neuron in the hidden layer respectively;

wij为可见层中第i个神经元和隐藏层中第j个神经元之间的权重;w ij is the weight between the i-th neuron in the visible layer and the j-th neuron in the hidden layer;

θ=[wij,ai,bj]表式需要通过训练求解的参数空间;θ=[w ij ,a i ,b j ] is a parameter space that needs to be solved through training;

c是高斯函数中的标准方差;c is the standard deviation in the Gaussian function;

计算隐藏层单元hj被激活概率:Calculate the activation probability of hidden layer unit h j :

其中:σ()表示使用Sigmoid函数作为激活函数;Among them: σ() means using the Sigmoid function as the activation function;

计算可见层单元vi被激活概率:Calculate the activation probability of visible layer unit v i :

使用CD-1算法,计算得到模型的权值和偏置:Using the CD-1 algorithm, calculate the weights and biases of the model:

其中,Δwij是权重的变化值;Among them, Δw ij is the change value of the weight;

Δai可见层中偏置向量的变化值;Δa iThe change value of the bias vector in the visible layer;

Δbj是隐藏层中偏置向量的变化值。Δb j is the change value of the bias vector in the hidden layer.

进一步的,所述使用误差反向传播算法进行反向微调过程包括以下步骤:Further, the reverse fine-tuning process using the error back propagation algorithm includes the following steps:

使用Adam算法设计梯度下降过程,经过偏置校正后,每一次迭代学习率都有个确定范围,加速隧道机械化施工风险预测模型的有监督学习;The Adam algorithm is used to design the gradient descent process. After bias correction, the learning rate of each iteration has a certain range, which accelerates the supervised learning of the tunnel mechanized construction risk prediction model;

更新规则如下:The update rules are as follows:

其中:mt和vt分别表示第t次迭代参数的一阶矩估计和二阶矩估计;Among them: m t and v t represent the first-order moment estimate and the second-order moment estimate of the t-th iteration parameter respectively;

ε是一个用于防止分母为0的极小常量;ε is a very small constant used to prevent the denominator from being 0;

α表示网络权重更新的步长因子。α represents the step size factor of network weight update.

进一步的,S11中所述使用粒子群寻优算法调整隧道机械化施工风险预测模型的超参数步骤如下:Further, the steps for using the particle swarm optimization algorithm to adjust the hyperparameters of the tunnel mechanized construction risk prediction model as described in S11 are as follows:

11-1初始化粒子群;11-1 Initialize particle swarm;

其中,初始化粒子的位置和速度/> Among them, initialize the position of the particle and speed/>

11-2计算适应度值;11-2 Calculate fitness value;

其中,计算每个粒子的适应度值,找到本轮粒子群最优的粒子的位置和搜索历史上的最优粒子的位置/> Among them, calculate the fitness value of each particle and find the optimal particle position of the particle swarm in this round. And search the optimal particle position in history/>

11-3更新粒子的速度和位置:11-3 Update the speed and position of particles:

式中,为粒子速度;/>为粒子位置;In the formula, is the particle speed;/> is the particle position;

ω表示惯性权重,取值介于[0,1],一般取ω=0.9;ω represents the inertia weight, the value is between [0,1], generally ω=0.9;

c1、c2为学习因子;c 1 and c 2 are learning factors;

r1、r2为在[0,1]之间的随机数;r 1 and r 2 are random numbers between [0,1];

是第i粒子的最优位置; is the optimal position of the i-th particle;

是全局最优粒子位置; is the global optimal particle position;

11-4如果训练样本的误分类率满足设定条件或者迭代次数达到预设值,则粒子群优化结束,否则跳转到11-2,k=k+1,重复执行11-3和11-4,直到满足判别条件;11-4 If the misclassification rate of the training sample meets the set conditions or the number of iterations reaches the preset value, the particle swarm optimization ends, otherwise jump to 11-2, k=k+1, and repeat 11-3 and 11- 4. Until the judgment conditions are met;

动态调整在迭代过程中的惯性权重ω:Dynamically adjust the inertia weight ω during the iteration process:

式中,k为迭代次数;In the formula, k is the number of iterations;

kmax为算法最大迭代次数;k max is the maximum number of iterations of the algorithm;

ωmax为惯性权重的最大值;ω max is the maximum value of inertia weight;

ωmin为惯性权重的最小值。ω min is the minimum value of inertia weight.

进一步的,所述预测方法还包括施工时的风险预测的输入因素做改动,对所述输入因素做出的改动步骤如下:Further, the prediction method also includes changing the input factors of risk prediction during construction. The steps for changing the input factors are as follows:

15.1将地下水情况、岩层特性、岩石特性、地应力影响、地下管线情况和与周围建筑物的距离这7个因素作为施工时的风险评价向量;15.1 Use seven factors, including groundwater conditions, rock layer properties, rock properties, ground stress effects, underground pipeline conditions and distance from surrounding buildings, as risk assessment vectors during construction;

15.2重复S1-S12,重新训练一个用于施工时的隧道机械化施工风险预测模型;15.2 Repeat S1-S12 to retrain a tunnel mechanized construction risk prediction model used during construction;

15.3将训练好的隧道机械化施工风险预测模型部署到隧道掘进机上,实现及时的隧道机械化施工风险预测。15.3 Deploy the trained tunnel mechanized construction risk prediction model to the tunnel boring machine to achieve timely tunnel mechanized construction risk prediction.

本申请能产生的有益效果包括:The beneficial effects this application can produce include:

1)本申请所提供的一种深度置信网络的隧道机械化施工风险预测方法,使用改进的粒子群寻优算法调整DBN模型的超参数,加快了模型训练并且提高了准确性;该方法集数据收集、数据预处理、模型建立、风险预测于一体,能够根据施工前的勘测情况,对隧道机械化施工风险进行预测;可以为现场工作人员提供施工参考,设计人员可以通过采取相关措施来降低风险,从而采取使施工风险达到最小的施工方案,有利于保障施工人员的生命安全和降低财产损失。1) The deep belief network tunnel mechanized construction risk prediction method provided by this application uses an improved particle swarm optimization algorithm to adjust the hyperparameters of the DBN model, speeding up model training and improving accuracy; this method sets data collection , data preprocessing, model establishment, and risk prediction, which can predict tunnel mechanized construction risks based on pre-construction surveys; it can provide construction references for on-site workers, and designers can reduce risks by taking relevant measures, thereby Adopting a construction plan that minimizes construction risks will help protect the lives of construction workers and reduce property losses.

附图说明Description of drawings

图1为本发明的流程示意图;Figure 1 is a schematic flow diagram of the present invention;

图2为本发明所包含的深度置信网络模型结构图;Figure 2 is a structural diagram of the deep belief network model included in the present invention;

图3为本发明所包含的RBM模型结构图。Figure 3 is a structural diagram of the RBM model included in the present invention.

具体实施方式Detailed ways

下面结合实施例详述本申请,但本申请并不局限于这些实施例。The present application will be described in detail below with reference to examples, but the present application is not limited to these examples.

参见图1-3,一种基于深度置信网络的隧道机械化施工风险预测,所述施工风险预测方法包括以下步骤:See Figure 1-3, a tunnel mechanized construction risk prediction based on a deep belief network. The construction risk prediction method includes the following steps:

S1建立隧道机械化施工风险因素评价标准;S1 establishes risk factor evaluation standards for tunnel mechanized construction;

具体地,可能会导致施工发生风险的因素包括:地下水情况、岩层特性、岩石特性、地应力影响、地下管线情况、与周围建筑物的距离、作业场地、施工操作不规范、施工技术不足和施工管理混乱;Specifically, factors that may cause construction risks include: groundwater conditions, rock formation characteristics, rock characteristics, ground stress effects, underground pipeline conditions, distance from surrounding buildings, working sites, non-standard construction operations, insufficient construction technology and construction management chaos;

其中,地下水情况:主要来自于隧道围岩中所含的地下水或部分地表水,在施工时以渗漏或涌出方式进入隧道内造成的危害。当空气中的水分含量过高时,会使施工机械设备锈蚀,严重的掌子面涌水甚至有一定几率会直接导致围岩崩塌,对隧道机械化施工造成威胁;Among them, the groundwater situation: mainly comes from the harm caused by groundwater or part of surface water contained in the surrounding rocks of the tunnel, which leaks or gushes into the tunnel during construction. When the moisture content in the air is too high, construction machinery and equipment will corrode, and severe water inflow from the tunnel face may even directly lead to the collapse of surrounding rocks, posing a threat to mechanized tunnel construction;

岩层特性:不同的岩层对隧道机械化施工造成的影响不同;Rock layer characteristics: Different rock layers have different effects on mechanized tunnel construction;

地应力影响:地应力是存在于地壳内部的应力。在隧道机械化施工过程中,会使围岩应力发生变化,也会引起构造应力,有发生岩爆的风险,对岩体的安全产生了巨大的影响;Influence of geostress: Geostress is the stress that exists inside the earth's crust. During the mechanized construction of the tunnel, the stress of the surrounding rock will change, and it will also cause tectonic stress, which will lead to the risk of rock burst and have a huge impact on the safety of the rock mass;

地下管线情况:当需要施工的地段存在地下管线时,如果因为操作失误而破坏了地下管线,将会对施工设备和周围居民的生活造成影响;Underground pipeline situation: When there are underground pipelines in the area to be constructed, if the underground pipelines are damaged due to operational errors, it will have an impact on the construction equipment and the lives of surrounding residents;

与周围建筑物的距离:当周围建筑物距离施工场地太近时,会对施工造成一定程度的影响;Distance from surrounding buildings: When surrounding buildings are too close to the construction site, it will affect the construction to a certain extent;

作业场地:作业场地是否有安全保障措施也很重要,当安全措施准备的很充分时,发生风险的概率就会比较低;Work site: It is also important whether there are safety measures at the work site. When safety measures are fully prepared, the probability of risks will be relatively low;

施工操作不规范、施工技术不足和施工管理混乱都会提高隧道机械化施工发生风险的可能性。Irregular construction operations, insufficient construction technology and chaotic construction management will increase the possibility of risks in mechanized tunnel construction.

考虑到有些风险因素过于抽象,很难直接用来训练神经网络模型,必须将以上风险因素数值化。将风险因素对施工的影响划为无影响、较小影响、中等影响、较大影响和严重影响这5个等级;相应的,将这五个等级分别用对应的数字1、2、3、4、5表示,当影响介于两个等级之间时,可以使用小数表示。Considering that some risk factors are too abstract and difficult to be directly used to train neural network models, the above risk factors must be digitized. The impact of risk factors on construction is divided into five levels: no impact, small impact, medium impact, large impact and severe impact; accordingly, these five levels are represented by the corresponding numbers 1, 2, 3, and 4 respectively. , 5 means that when the impact is between two levels, decimals can be used.

S2通过风险因素评价标准建立隧道机械化施工风险指标体系;S2 establishes a tunnel mechanized construction risk index system through risk factor evaluation standards;

具体地,考虑到S1中的风险因素,结合相关专家的经验,建立隧道机械化施工风险指标体系。Specifically, taking into account the risk factors in S1 and combining the experience of relevant experts, a tunnel mechanized construction risk index system was established.

其中一级风险有地质风险、周围环境风险、设备风险、隧道自身风险。Among them, the first-level risks include geological risks, surrounding environment risks, equipment risks, and tunnel own risks.

其中地质风险有掌子面坍塌、土体坍塌、土体渗漏和突水涌砂,周围环境风险有地层地面沉降、周围建筑变形和地下管线被破坏,设备风险有隧道掘进机卡机、隧道掘进机组装调试失败、托架变形失稳、通风集尘不畅和出渣不连续,隧道自身风险有掘进路线偏差、支护结构变形、衬砌渗漏和隧道积水,共计16个二级风险。Among them, geological risks include tunnel face collapse, soil collapse, soil leakage, and water and sand inrush. Surrounding environmental risks include ground subsidence, surrounding building deformation, and underground pipeline damage. Equipment risks include tunnel boring machine jamming, tunnel boring machine jamming, and underground pipeline damage. Tunnel boring machine assembly and debugging failure, bracket deformation and instability, poor ventilation and dust collection, and discontinuous slag discharge. The tunnel's own risks include excavation route deviation, support structure deformation, lining leakage, and tunnel water accumulation. A total of 16 secondary risks .

S3收集专家们根据风险因素评价标准所建立的风险因素评价向量和风险预测结果;S3 collects risk factor evaluation vectors and risk prediction results established by experts based on risk factor evaluation standards;

其中,风险因素评价向量如表1所示:Among them, the risk factor evaluation vector is shown in Table 1:

表1Table 1

向量格式如下:The vector format is as follows:

x=[x1,x2,…,x9,x10] xi∈R[1,5]x=[x 1 ,x 2 ,…,x 9 ,x 10 ] x i ∈R[1,5]

其中,风险预测结果向量如表2所示:Among them, the risk prediction result vector is shown in Table 2:

表2Table 2

向量格式如下:The vector format is as follows:

y=[y1,y2,y3,y4,y5],yi∈R[0,1]且 y=[y 1 , y 2 , y 3 , y 4 , y 5 ], y i ∈R[0,1] and

需要注意的是,每一组风险因素评价向量对应一组风险预测结果。It should be noted that each set of risk factor evaluation vectors corresponds to a set of risk prediction results.

S4对S3收集到的数据进行预处理;S4 preprocesses the data collected by S3;

其中,对收集到的数据划分之前需要对其进行预处理,所述数据预处理的方法为数据清理;Among them, the collected data needs to be preprocessed before being divided, and the data preprocessing method is data cleaning;

数据清理主要是通过对数据集中的缺失值和异常值进行处理,避免异常数据对模型训练造成错误的影响。Data cleaning mainly deals with missing values and outliers in the data set to avoid the erroneous impact of abnormal data on model training.

其中,缺失值在数据存储库中表示为Null,处理方法为丢弃,即直接删除带有缺失值的行记录;Among them, missing values are represented as Null in the data repository, and the processing method is discarding, that is, row records with missing values are directly deleted;

其中,风险因素评价向量中的值满足xi∈R[1,5],当xi不在此区间内时,则为异常值;Among them, the value in the risk factor evaluation vector satisfies x i ∈R[1,5]. When x i is not within this interval, it is an outlier;

风险预测结果向量中的值满足The values in the risk prediction result vector satisfy

yi∈R[0,1]且 y i ∈R[0,1] and

当yi不满足条件时,则为异常值。When yi does not meet the conditions, it is an outlier.

异常值的处理方法为丢弃,即直接删除含有异常值的行记录;The processing method for outliers is discarding, that is, directly deleting row records containing outliers;

S5根据预处理后的数据构建隧道机械化施工风险预测数据库;S5 builds a tunnel mechanized construction risk prediction database based on the preprocessed data;

其中,利用经过S4处理过后的数据,建立隧道机械化施工风险预测数据库。Among them, the data processed by S4 is used to establish a tunnel mechanized construction risk prediction database.

S6将S5中的数据划分为训练集和测试集,取原始数据集的80%作为训练集,取剩下的20%作为测试集;S6 divides the data in S5 into a training set and a test set, taking 80% of the original data set as the training set and the remaining 20% as the test set;

其中,训练集数据用来训练模型和验证模型的性能,以便从中选取预测效果最好的隧道机械化施工风险预测模型,测试集用来测试最优隧道机械化施工风险预测模型的预测准确性。Among them, the training set data is used to train the model and verify the performance of the model in order to select the tunnel mechanized construction risk prediction model with the best prediction effect, and the test set is used to test the prediction accuracy of the optimal tunnel mechanized construction risk prediction model.

步骤S7,随机初始化隧道机械化施工风险预测模型的超参数。Step S7: Randomly initialize the hyperparameters of the tunnel mechanized construction risk prediction model.

其中,需要初始化的超参数有输入节点数、输出节点数、隐藏层层数、隐藏层节点数、训练迭代次数、批量大小、学习率和动量;Among them, the hyperparameters that need to be initialized include the number of input nodes, the number of output nodes, the number of hidden layer layers, the number of hidden layer nodes, the number of training iterations, batch size, learning rate and momentum;

其中,输入节点数等于待处理数据中输入变量的数量。根据风险因素评价向量可知,应该分为10个节点,分别对应地下水情况、岩层特性、岩石特性、地应力影响、地下管线情况、与周围建筑物的距离、作业场地、施工操作不规范、施工技术不足和施工管理混乱;Among them, the number of input nodes is equal to the number of input variables in the data to be processed. According to the risk factor evaluation vector, it should be divided into 10 nodes, corresponding to groundwater conditions, rock formation characteristics, rock characteristics, ground stress effects, underground pipeline conditions, distance from surrounding buildings, working site, non-standard construction operations, and construction technology. inadequate and disorganized construction management;

需要指出的是,在输入节点的下一个隐藏层应该分为16个节点,分别对应掌子面坍塌、土体坍塌、土体渗漏、突水涌砂、地层地面沉降、周围建筑变形、地下管线被破坏、隧道掘进机卡机、隧道掘进机组装调试失败、托架变形失稳、通风集尘不畅、出渣不连续、掘进路线偏差、支护结构变形、衬砌渗漏和隧道积水。It should be pointed out that the next hidden layer under the input node should be divided into 16 nodes, corresponding to tunnel face collapse, soil collapse, soil leakage, water inrush and sand inrush, ground subsidence, surrounding building deformation, underground Damaged pipelines, stuck tunnel boring machines, failed assembly and debugging of tunnel boring machines, deformation and instability of brackets, poor ventilation and dust collection, discontinuous slag discharge, deviations in excavation routes, deformation of supporting structures, lining leakage and tunnel water accumulation .

输出节点数等于与每个输入关联的输出的数量,根据预测结果向量可知,应为1个节点,对应的是隧道机械化施工风险;The number of output nodes is equal to the number of outputs associated with each input. According to the prediction result vector, it should be 1 node, corresponding to the risk of tunnel mechanized construction;

需要指出的是,在输出节点的上一个隐藏层应该分为4个节点,分别对应地质风险、周围环境风险、设备风险和隧道自身风险;It should be pointed out that the previous hidden layer of the output node should be divided into 4 nodes, corresponding to geological risks, surrounding environment risks, equipment risks and tunnel own risks;

隐藏层数:隐藏层的意义就是把输入数据的特征,抽象到另一个维度空间,来展现其更抽象化的特征,这些特征能更好的进行线性划分。层数过小时,能够提取的特征有限,当问题过于复杂时,模型的准确率可能会达不到要求,导致欠拟合。层数越深,拟合函数的能力增强,但是可能会带来过拟合的问题,同时也会增加训练难度,使模型难以收敛;Number of hidden layers: The meaning of the hidden layer is to abstract the characteristics of the input data into another dimensional space to show its more abstract characteristics. These characteristics can be better linearly divided. If the number of layers is too small, the features that can be extracted are limited. When the problem is too complex, the accuracy of the model may not meet the requirements, leading to underfitting. The deeper the number of layers, the stronger the ability to fit the function, but it may cause over-fitting problems and increase the difficulty of training, making it difficult for the model to converge;

隐含节点数:在隐藏层中使用的神经元数。隐藏层中使用太少的神经元将导致欠拟合;当神经网络具有过多的节点时,训练集中包含的有限信息量不足以训练隐藏层中的所有神经元,就会导致过拟合;Number of hidden nodes: The number of neurons used in the hidden layer. Using too few neurons in the hidden layer will lead to underfitting; when the neural network has too many nodes, the limited amount of information contained in the training set is not enough to train all the neurons in the hidden layer, which will lead to overfitting;

批量大小:一次迭代使用的样本量。当批量过小时,训练数据就会非常难收敛;Batch size: The number of samples used in one iteration. When the batch size is too small, the training data will be very difficult to converge;

迭代次数:每当训练完一个批量的数据就是一个迭代次数。当迭代次数过大时,会导致过拟合;当迭代次数过小时,会导致欠拟合。Number of iterations: Each time a batch of data is trained, it is the number of iterations. When the number of iterations is too large, it will lead to overfitting; when the number of iterations is too small, it will lead to underfitting.

学习率:每次参数更新的幅度大小。当学习率过大时,会导致待优化的参数在最小值附近波动,不会收敛;当学习率过小时,会导致待优化的参数收敛缓慢;Learning rate: the magnitude of each parameter update. When the learning rate is too large, it will cause the parameters to be optimized to fluctuate near the minimum value and not converge; when the learning rate is too small, it will cause the parameters to be optimized to converge slowly;

动量:是依据物理学的势能与动能之间能量转换原理提出来的。当动量越大时,其转换为势能的能量也就越大,就越有可能摆脱局部凹域的束缚,进入全局凹域,进而获得全局最优解;动量主要用在权重更新的时候。Momentum: It is proposed based on the energy conversion principle between potential energy and kinetic energy in physics. When the momentum is greater, the energy converted into potential energy is greater, and the more likely it is to break away from the constraints of the local concave domain, enter the global concave domain, and obtain the global optimal solution; momentum is mainly used when updating weights.

S8使用K折交叉验证的方法,将训练集重新划分为新的训练集和验证集;随机初始化模型参数,使用新的训练集数据来训练模型,使用验证集中的数据测试模型的性能;S8 uses the K-fold cross-validation method to re-divide the training set into a new training set and a validation set; randomly initializes the model parameters, uses the new training set data to train the model, and uses the data in the validation set to test the performance of the model;

其中,随机初始化模型参数是从[-1,1]的均匀分布中随机抽取样本作为模型的参数;Among them, the randomly initialized model parameters are randomly selected samples from the uniform distribution of [-1,1] as the parameters of the model;

其中,模型的参数有可见层单元i与隐藏层单元j的神经元连接权重wij,可见层单元神经元i的偏置ai,隐藏层单元j的偏置bjAmong them, the parameters of the model include the neuron connection weight w ij of the visible layer unit i and the hidden layer unit j, the bias a i of the visible layer unit neuron i, and the bias b j of the hidden layer unit j;

其中,使用绝对平均误差MAE和相对平均误差MRE作为模型的性能评价指标,定义如下:Among them, the absolute average error MAE and the relative average error MRE are used as the performance evaluation indicators of the model, which are defined as follows:

其中:youtput,i和yfact,i分别表示第i个样本输入的预测值和真实值。MRE与MAE的值越小,表示隧道机械化施工风险预测模型预测效果越准确。Among them: y output,i and y fact,i respectively represent the predicted value and true value of the i-th sample input. The smaller the values of MRE and MAE, the more accurate the prediction effect of the tunnel mechanized construction risk prediction model.

S9使用受限波尔兹曼机RBM无监督正向学习,将风险因素特征量输入,逐层训练,使浅层原始特征获得高层次表达,为了增强模型的泛化能力,在可见层和隐藏层中加入高斯噪声;S9 uses restricted Boltzmann machine RBM unsupervised forward learning, inputs the risk factor feature quantities, and trains layer by layer, so that the shallow original features can obtain high-level expression. In order to enhance the generalization ability of the model, in the visible layer and hidden layer Add Gaussian noise to the layer;

所述RBM无监督的正向学习过程包括以下步骤:The RBM unsupervised forward learning process includes the following steps:

参数初始化:初始化RBM模型参数,即层间的连接权值和各层的偏置,一般从[-1,1]中的均匀分布中随机抽取样本作为模型的参数;Parameter initialization: Initialize the RBM model parameters, that is, the connection weights between layers and the biases of each layer. Generally, samples are randomly selected from the uniform distribution in [-1,1] as parameters of the model;

可见层和隐藏层间的联合能量函数为:The joint energy function between the visible layer and the hidden layer is:

其中vi为可见层中第i个神经元状态;hj为隐藏层中第j个神经元状态;ai和bj分别为可见层中第i个神经元和隐藏层中第j个神经元的偏置;wij为可见层中第i个神经元和隐藏层中第j个神经元之间的权重;θ=[wij,ai,bj]表式需要通过训练求解的参数空间;c是高斯函数中的标准方差;where v i is the state of the i-th neuron in the visible layer; h j is the state of the j-th neuron in the hidden layer; a i and b j are respectively the i-th neuron in the visible layer and the j-th neuron in the hidden layer The bias of the element; w ij is the weight between the i-th neuron in the visible layer and the j-th neuron in the hidden layer; θ = [w ij , a i , b j ] parameters that need to be solved through training space; c is the standard deviation in the Gaussian function;

计算隐藏层单元hj被激活概率:Calculate the activation probability of hidden layer unit h j :

其中:σ()表示使用Sigmoid函数作为激活函数;Among them: σ() means using the Sigmoid function as the activation function;

计算可见层单元vi被激活概率:Calculate the activation probability of visible layer unit v i :

使用CD-1算法(对比散度算法),计算得到模型的权值和偏置:Using the CD-1 algorithm (contrast divergence algorithm), calculate the weights and biases of the model:

其中,Δwij是权重的变化值;Among them, Δw ij is the change value of the weight;

Δai可见层中偏置向量的变化值;Δa iThe change value of the bias vector in the visible layer;

Δbj是隐藏层中偏置向量的变化值。Δb j is the change value of the bias vector in the hidden layer.

S10使用BP算法(误差反向传播算法)对隧道机械化施工风险预测模型的超参数进行反向微调,使其收敛至全局最优点,优化模型对风险因素的辨识能力,S10 uses the BP algorithm (error back propagation algorithm) to reversely fine-tune the hyperparameters of the tunnel mechanized construction risk prediction model so that it converges to the global optimal point and optimizes the model's ability to identify risk factors.

优选的,所述使用BP算法进行反向微调过程包括以下步骤:Preferably, the reverse fine-tuning process using the BP algorithm includes the following steps:

使用Adam算法设计梯度下降过程,其优势在于经过偏置校正后,每一次迭代学习率都有个确定范围,加速隧道机械化施工风险预测模型的有监督学习;更新规则如下:The advantage of using the Adam algorithm to design the gradient descent process is that after bias correction, the learning rate of each iteration has a certain range, which accelerates the supervised learning of the tunnel mechanized construction risk prediction model; the update rules are as follows:

其中:mt和vt分别表示第t次迭代参数的一阶矩估计和二阶矩估计;ε是一个用于防止分母为0的极小常量;α表示网络权重更新的步长因子;Among them: m t and v t represent the first-order moment estimate and the second-order moment estimate of the t-th iteration parameter respectively; ε is a minimal constant used to prevent the denominator from being 0; α represents the step factor for network weight update;

Adam算法是一种自适应动量的随机优化方法,为深度学习中的优化器算法。The Adam algorithm is an adaptive momentum stochastic optimization method and an optimizer algorithm in deep learning.

S11使用改进的粒子群寻优算法调整DBN模型的超参数;S11 uses an improved particle swarm optimization algorithm to adjust the hyperparameters of the DBN model;

其中,使用粒子群寻优算法调整DBN模型的超参数步骤如下:Among them, the steps to use the particle swarm optimization algorithm to adjust the hyperparameters of the DBN model are as follows:

11-1,初始化粒子群;11-1, initialize particle swarm;

其中,初始化粒子的位置和速度/> Among them, initialize the position of the particle and speed/>

11-2,计算适应度值;11-2, calculate the fitness value;

其中,计算每个粒子的适应度值,找到本轮粒子群最优的粒子的位置和搜索历史上的最优粒子的位置/> Among them, calculate the fitness value of each particle and find the optimal particle position of the particle swarm in this round. And search the optimal particle position in history/>

11-3,更新粒子的速度和位置;11-3, update the speed and position of particles;

其中,更新所有粒子的速度和位置:Among them, update the speed and position of all particles:

式中,为粒子速度;/>为粒子位置;ω表示惯性权重,取值介于[0,1],一般取ω=0.9;c1、c2为学习因子;r1、r2为在[0,1]之间的随机数;/>是第i粒子的最优位置;是全局最优粒子位置;In the formula, is the particle speed;/> is the particle position; ω represents the inertial weight, with a value between [0,1], generally ω=0.9; c 1 and c 2 are learning factors; r 1 and r 2 are random values between [0,1] Number;/> is the optimal position of the i-th particle; is the global optimal particle position;

11-4如果训练样本的误分类率满足设定条件或者迭代次数达到预设值,则粒子群PSO优化结束,否则跳转到11-2,k=k+1,重复执行11-3和11-4,直到满足判别条件。11-4 If the misclassification rate of the training sample meets the set conditions or the number of iterations reaches the preset value, the particle swarm PSO optimization ends, otherwise jump to 11-2, k=k+1, and repeat 11-3 and 11 -4 until the judgment conditions are met.

其中,在传统粒子群优化算法中,惯性权重ω在迭代过程中是定值,容易导致算法陷入局部最优。为避免迭代初期粒子陷入局部最优,可以在迭代过程中动态调整ω:Among them, in the traditional particle swarm optimization algorithm, the inertia weight ω is a fixed value during the iteration process, which can easily cause the algorithm to fall into a local optimum. In order to avoid particles falling into local optimum in the early iteration process, ω can be dynamically adjusted during the iteration process:

式中,k为迭代次数;kmax为算法最大迭代次数;ωmax为惯性权重的最大值;ωmin为惯性权重的最小值。In the formula, k is the number of iterations; k max is the maximum number of iterations of the algorithm; ω max is the maximum value of inertia weight; ω min is the minimum value of inertia weight.

S12判断隧道机械化施工风险预测模型是否满足粒子群优化算法寻优条件,如果满足条件,得到性能最优的隧道机械化施工风险预测模型,如果没有满足条件,则使用S11中确定的超参数构建新的隧道机械化施工风险预测模型,重复步骤S8-S11。S12 determines whether the tunnel mechanized construction risk prediction model meets the particle swarm optimization algorithm optimization conditions. If the conditions are met, the tunnel mechanized construction risk prediction model with the best performance is obtained. If the conditions are not met, a new model is constructed using the hyperparameters determined in S11. Tunnel mechanized construction risk prediction model, repeat steps S8-S11.

S13使用S12中得到的隧道机械化施工风险预测模型,输入测试集数据对隧道机械化施工风险进行预测,测试隧道机械化施工风险预测模型的预测性能。S13 uses the tunnel mechanized construction risk prediction model obtained in S12, inputs the test set data to predict the tunnel mechanized construction risks, and tests the prediction performance of the tunnel mechanized construction risk prediction model.

S14现场人员根据现场施工情况,按照风险因素评价标准,将风险因素隶属度向量输入到隧道机械化施工风险预测模型中,可以得到隧道机械化施工风险概率。S14 On-site personnel input the risk factor membership vector into the tunnel mechanized construction risk prediction model based on the on-site construction conditions and risk factor evaluation standards to obtain the tunnel mechanized construction risk probability.

其中,在实际使用中,所述风险因素评价向量为现场人员根据现场施工情况,按照风险因素评价标准得到的。Among them, in actual use, the risk factor evaluation vector is obtained by on-site personnel based on on-site construction conditions and in accordance with risk factor evaluation standards.

S15考虑到上述风险预测只能用于施工前的风险预测,需要对输入因素做一些改动,使其可以用于施工时的风险预测;S15 Considering that the above risk prediction can only be used for risk prediction before construction, some changes need to be made to the input factors so that it can be used for risk prediction during construction;

改动步骤如下:The modification steps are as follows:

15-1考虑到地下水情况、岩层特性、岩石特性、地应力影响、地下管线情况和与周围建筑物的距离这7个因素在施工时的重要性,应该将这7个因素作为施工时的风险评价向量;15-1 Taking into account the importance of groundwater conditions, rock layer characteristics, rock characteristics, ground stress effects, underground pipeline conditions and distance from surrounding buildings during construction, these seven factors should be regarded as risks during construction. evaluation vector;

15-2重复步骤S1-S12,重新训练一个用于施工时的隧道机械化施工风险预测模型;15-2 Repeat steps S1-S12 to retrain a mechanized tunnel construction risk prediction model for use during construction;

15-3,可以将训练好的隧道机械化施工风险预测模型部署到隧道掘进机上,实现及时的隧道机械化施工风险预测。15-3, the trained tunnel mechanized construction risk prediction model can be deployed on the tunnel boring machine to achieve timely tunnel mechanized construction risk prediction.

本发明提供了一种深度置信网络的隧道机械化施工风险预测方法,相较于传统的DBN,使用改进的粒子群寻优算法调整DBN模型的超参数,加快了模型训练并且提高了准确性;相较于传统的隧道机械化施工风险预测方法,该方法集数据收集、数据预处理、模型建立、风险预测于一体,能够根据施工前的勘测情况,对隧道机械化施工风险进行预测;为了提高其泛用性,对输入参数进行调整,使其可以部署到隧道掘进机上进行施工时的风险预测;该方法可以为现场工作人员提供施工参考,设计人员可以通过采取相关措施来降低风险,从而采取使施工风险达到最小的施工方案,有利于保障施工人员的生命安全和降低财产损失。The present invention provides a deep belief network tunnel mechanized construction risk prediction method. Compared with traditional DBN, an improved particle swarm optimization algorithm is used to adjust the hyperparameters of the DBN model, speeding up model training and improving accuracy; Compared with the traditional tunnel mechanized construction risk prediction method, this method integrates data collection, data preprocessing, model establishment, and risk prediction, and can predict tunnel mechanized construction risks based on pre-construction survey conditions; in order to improve its general application nature, the input parameters are adjusted so that they can be deployed on the tunnel boring machine for risk prediction during construction; this method can provide construction reference for on-site workers, and designers can reduce risks by taking relevant measures, thereby taking measures to minimize construction risks. Achieving the smallest construction plan will help protect the life safety of construction workers and reduce property losses.

以上所述,仅是本申请的几个实施例,并非对本申请做任何形式的限制,虽然本申请以较佳实施例揭示如上,然而并非用以限制本申请,任何熟悉本专业的技术人员,在不脱离本申请技术方案的范围内,利用上述揭示的技术内容做出些许的变动或修饰均等同于等效实施案例,均属于技术方案范围内。The above are only a few embodiments of the present application, and are not intended to limit the present application in any way. Although the present application is disclosed as above with preferred embodiments, they are not intended to limit the present application. Any skilled person familiar with this field, Without departing from the scope of the technical solution of this application, slight changes or modifications made using the technical content disclosed above are equivalent to equivalent implementation examples and fall within the scope of the technical solution.

Claims (8)

1.一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述施工风险预测方法包括以下步骤:1. A tunnel mechanized construction risk prediction method based on deep belief network, characterized in that the construction risk prediction method includes the following steps: S1建立隧道机械化施工风险因素评价标准;S1 establishes risk factor evaluation standards for tunnel mechanized construction; S2通过风险因素评价标准建立隧道机械化施工风险指标体系;S2 establishes a tunnel mechanized construction risk index system through risk factor evaluation standards; S3收集专家们根据风险因素评价标准建立风险因素评价向量和风险预测结果,其中,每一组风险因素评价向量对应一组风险预测结果;S3 collects experts to establish risk factor evaluation vectors and risk prediction results based on risk factor evaluation standards. Each set of risk factor evaluation vectors corresponds to a set of risk prediction results; S4对S3收集到的数据进行预处理,包括通过对数据集中的缺失值和异常值进行处理,避免异常数据对模型训练造成错误的影响;S4 preprocesses the data collected by S3, including processing missing values and outliers in the data set to avoid the erroneous impact of abnormal data on model training; S5根据预处理后的数据构建隧道机械化施工风险预测数据库;S5 builds a tunnel mechanized construction risk prediction database based on the preprocessed data; S6将S5中预测数据库中的数据划分为训练集和测试集,其中,训练集数据用来训练模型和验证模型的性能,测试集用来测试最优隧道机械化施工风险预测模型的预测准确性;S6 divides the data in the prediction database in S5 into a training set and a test set. The training set data is used to train the model and verify the performance of the model, and the test set is used to test the prediction accuracy of the optimal tunnel mechanized construction risk prediction model; S7初始化隧道机械化施工风险预测模型的超参数;S7 initializes the hyperparameters of the tunnel mechanized construction risk prediction model; S8使用K折交叉验证的方法,将训练集重新划分为新的训练集和验证集,随机初始化模型参数,使用新的训练集数据来训练模型,使用验证集中的数据测试模型的性能;S8 uses the K-fold cross-validation method to re-divide the training set into a new training set and a validation set, randomly initialize the model parameters, use the new training set data to train the model, and use the data in the validation set to test the performance of the model; S9使用受限波尔兹曼机RBM无监督正向学习,将所述隧道机械化施工风险因素特征量输入,逐层训练,使浅层原始特征获得高层次表达;S9 uses restricted Boltzmann machine RBM unsupervised forward learning to input the feature quantities of the tunnel mechanized construction risk factors and train them layer by layer, so that the shallow original features can obtain high-level expression; S10使用误差反向传播算法对隧道机械化施工风险预测模型的超参数进行反向微调,使其收敛至全局最优点,优化模型对风险因素的辨识能力;S10 uses the error back propagation algorithm to reversely fine-tune the hyperparameters of the tunnel mechanized construction risk prediction model so that it converges to the global optimal point and optimizes the model's ability to identify risk factors; S11使用改进的粒子群寻优算法调整隧道机械化施工风险预测模型的超参数;S11 uses an improved particle swarm optimization algorithm to adjust the hyperparameters of the tunnel mechanized construction risk prediction model; S12判断隧道机械化施工风险预测模型是否满足粒子群优化算法寻优条件,如果满足条件,得到性能最优的隧道机械化施工风险预测模型,如果没有满足条件,则使用S11中确定的超参数构建新的隧道机械化施工风险预测模型,重复步骤S8-S11;S12 determines whether the tunnel mechanized construction risk prediction model meets the particle swarm optimization algorithm optimization conditions. If the conditions are met, the tunnel mechanized construction risk prediction model with the best performance is obtained. If the conditions are not met, a new model is constructed using the hyperparameters determined in S11. Tunnel mechanized construction risk prediction model, repeat steps S8-S11; S13使用S12中得到的隧道机械化施工风险预测模型,输入测试集数据对隧道机械化施工风险进行预测,测试隧道机械化施工风险预测模型的预测性能;S13 uses the tunnel mechanized construction risk prediction model obtained in S12, inputs the test set data to predict the tunnel mechanized construction risks, and tests the prediction performance of the tunnel mechanized construction risk prediction model; S14现场人员根据现场施工情况,按照风险因素评价标准,将风险因素隶属度向量输入到隧道机械化施工风险预测模型中,得到隧道机械化施工风险概率。S14 On-site personnel input the risk factor membership vector into the tunnel mechanized construction risk prediction model based on the on-site construction conditions and risk factor evaluation standards to obtain the tunnel mechanized construction risk probability. 2.根据权利要求1所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述超参数包括输入节点数、输出节点数、隐藏层层数、隐藏层节点数、训练迭代次数、批量大小、学习率和动量;2. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 1, characterized in that the hyperparameters include the number of input nodes, the number of output nodes, the number of hidden layer layers, the number of hidden layer nodes, Number of training iterations, batch size, learning rate and momentum; 需要初始化的超参数包括输入节点数、输出节点数、隐藏层层数、隐藏层节点数、训练迭代次数、批量大小、学习率和动量。Hyperparameters that need to be initialized include the number of input nodes, the number of output nodes, the number of hidden layer layers, the number of hidden layer nodes, the number of training iterations, batch size, learning rate, and momentum. 3.根据权利要求1所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述初始化模型参数包括可见层单元i和隐藏层单元j的神经元连接权重wij、可见层单元神经元i的偏置ai和隐藏层单元j的偏置bj3. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 1, characterized in that the initialization model parameters include neuron connection weights w ij of visible layer unit i and hidden layer unit j, The bias a i of the visible layer unit neuron i and the bias b j of the hidden layer unit j; 其中,使用绝对平均误差MAE和相对平均误差MRE作为模型的性能评价指标,定义如下:Among them, the absolute average error MAE and the relative average error MRE are used as the performance evaluation indicators of the model, which are defined as follows: 其中:youtput,i和yfact,i分别表示第i个样本输入的预测值和真实值;Among them: y output,i and y fact,i respectively represent the predicted value and true value of the i-th sample input; MRE与MAE的值越小,表示隧道机械化施工风险预测模型预测效果越准确。The smaller the values of MRE and MAE, the more accurate the prediction effect of the tunnel mechanized construction risk prediction model. 4.根据权利要求3所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,在所述可见层单元所在的可见层和所述隐藏层单元所在的隐藏层中加入高斯噪声。4. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 3, characterized in that Gaussian is added to the visible layer where the visible layer unit is located and the hidden layer where the hidden layer unit is located. noise. 5.根据权利要求4所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,S9中所述受限波尔兹曼机RBM无监督的正向学习过程包括以下步骤:5. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 4, characterized in that the unsupervised forward learning process of the restricted Boltzmann machine RBM in S9 includes the following steps: 参数初始化:初始化RBM模型参数,即层间的连接权值和各层的偏置,从[-1,1]中的均匀分布中随机抽取样本作为RBM模型的参数;Parameter initialization: Initialize the RBM model parameters, that is, the connection weights between layers and the bias of each layer, and randomly select samples from the uniform distribution in [-1,1] as parameters of the RBM model; 可见层和隐藏层间的联合能量函数为:The joint energy function between the visible layer and the hidden layer is: 其中,vi为可见层中第i个神经元状态;Among them, vi is the i-th neuron state in the visible layer; hj为隐藏层中第j个神经元状态;h j is the j-th neuron state in the hidden layer; ai和bj分别为可见层中第i个神经元和隐藏层中第j个神经元的偏置;a i and b j are the biases of the i-th neuron in the visible layer and the j-th neuron in the hidden layer respectively; wij为可见层中第i个神经元和隐藏层中第j个神经元之间的权重;w ij is the weight between the i-th neuron in the visible layer and the j-th neuron in the hidden layer; θ=[wij,ai,bj]表式需要通过训练求解的参数空间;θ=[w ij ,a i ,b j ] is a parameter space that needs to be solved through training; c是高斯函数中的标准方差;c is the standard deviation in the Gaussian function; 计算隐藏层单元hj被激活概率:Calculate the activation probability of hidden layer unit h j : 其中:σ()表示使用Sigmoid函数作为激活函数;Among them: σ() means using the Sigmoid function as the activation function; 计算可见层单元vi被激活概率:Calculate the activation probability of visible layer unit v i : 使用CD-1算法,计算得到模型的权值和偏置:Using the CD-1 algorithm, calculate the weights and biases of the model: 其中,Δwij是权重的变化值;Among them, Δw ij is the change value of the weight; Δai可见层中偏置向量的变化值;Δa iThe change value of the bias vector in the visible layer; Δbj是隐藏层中偏置向量的变化值。Δb j is the change value of the bias vector in the hidden layer. 6.根据权利要求1所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述使用误差反向传播算法进行反向微调过程包括以下步骤:6. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 1, characterized in that the reverse fine-tuning process using an error back propagation algorithm includes the following steps: 使用Adam算法设计梯度下降过程,经过偏置校正后,每一次迭代学习率都有个确定范围,加速隧道机械化施工风险预测模型的有监督学习;The Adam algorithm is used to design the gradient descent process. After bias correction, the learning rate of each iteration has a certain range, which accelerates the supervised learning of the tunnel mechanized construction risk prediction model; 更新规则如下:The update rules are as follows: 其中:mt和vt分别表示第t次迭代参数的一阶矩估计和二阶矩估计;Among them: m t and v t represent the first-order moment estimate and the second-order moment estimate of the t-th iteration parameter respectively; ε是一个用于防止分母为0的极小常量;ε is a very small constant used to prevent the denominator from being 0; α表示网络权重更新的步长因子。α represents the step size factor of network weight update. 7.根据权利要求1所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,S11中所述使用粒子群寻优算法调整隧道机械化施工风险预测模型的超参数步骤如下:7. A tunnel mechanized construction risk prediction method based on deep belief network according to claim 1, characterized in that the steps of using the particle swarm optimization algorithm to adjust the hyperparameters of the tunnel mechanized construction risk prediction model described in S11 are as follows: 11-1初始化粒子群;11-1 Initialize the particle swarm; 其中,初始化粒子的位置和速度/> Among them, initialize the position of the particle and speed/> 11-2计算适应度值;11-2 Calculate fitness value; 其中,计算每个粒子的适应度值,找到本轮粒子群最优的粒子的位置和搜索历史上的最优粒子的位置/> Among them, calculate the fitness value of each particle and find the optimal particle position of the particle swarm in this round. And search the optimal particle position in history/> 11-3更新粒子的速度和位置:11-3 Update the speed and position of particles: 式中,为粒子速度;/>为粒子位置;In the formula, is the particle speed;/> is the particle position; ω表示惯性权重,取值介于[0,1],一般取ω=0.9;ω represents the inertia weight, the value is between [0,1], generally ω=0.9; c1、c2为学习因子;c 1 and c 2 are learning factors; r1、r2为在[0,1]之间的随机数;r 1 and r 2 are random numbers between [0,1]; 是第i粒子的最优位置; is the optimal position of the i-th particle; 是全局最优粒子位置; is the global optimal particle position; 11-4如果训练样本的误分类率满足设定条件或者迭代次数达到预设值,则粒子群优化结束,否则跳转到11-2,k=k+1,重复执行11-3和11-4,直到满足判别条件;11-4 If the misclassification rate of the training sample meets the set conditions or the number of iterations reaches the preset value, the particle swarm optimization ends, otherwise jump to 11-2, k=k+1, and repeat 11-3 and 11- 4. Until the judgment conditions are met; 动态调整在迭代过程中的惯性权重ω:Dynamically adjust the inertia weight ω during the iteration process: 式中,k为迭代次数;In the formula, k is the number of iterations; kmax为算法最大迭代次数;k max is the maximum number of iterations of the algorithm; ωmax为惯性权重的最大值;ω max is the maximum value of inertia weight; ωmin为惯性权重的最小值。ω min is the minimum value of inertia weight. 8.根据权利要求1所述的一种基于深度置信网络的隧道机械化施工风险预测方法,其特征在于,所述预测方法还包括施工时的风险预测的输入因素做改动,对所述输入因素做出的改动步骤如下:8. A risk prediction method for tunnel mechanization construction based on deep belief network according to claim 1, characterized in that the prediction method also includes changing the input factors of the risk prediction during construction, and modifying the input factors. The modification steps are as follows: 15.1将地下水情况、岩层特性、岩石特性、地应力影响、地下管线情况和与周围建筑物的距离这7个因素作为施工时的风险评价向量;15.1 Use seven factors, including groundwater conditions, rock layer characteristics, rock characteristics, ground stress effects, underground pipeline conditions and distance from surrounding buildings, as risk assessment vectors during construction; 15.2重复S1-S12,重新训练一个用于施工时的隧道机械化施工风险预测模型;15.2 Repeat S1-S12 to retrain a tunnel mechanized construction risk prediction model used during construction; 15.3将训练好的隧道机械化施工风险预测模型部署到隧道掘进机上,实现及时的隧道机械化施工风险预测。15.3 Deploy the trained tunnel mechanized construction risk prediction model to the tunnel boring machine to achieve timely tunnel mechanized construction risk prediction.
CN202310743584.0A 2023-06-21 2023-06-21 Tunnel mechanized construction risk prediction method based on deep belief network Pending CN116739176A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310743584.0A CN116739176A (en) 2023-06-21 2023-06-21 Tunnel mechanized construction risk prediction method based on deep belief network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310743584.0A CN116739176A (en) 2023-06-21 2023-06-21 Tunnel mechanized construction risk prediction method based on deep belief network

Publications (1)

Publication Number Publication Date
CN116739176A true CN116739176A (en) 2023-09-12

Family

ID=87918253

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310743584.0A Pending CN116739176A (en) 2023-06-21 2023-06-21 Tunnel mechanized construction risk prediction method based on deep belief network

Country Status (1)

Country Link
CN (1) CN116739176A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117236137A (en) * 2023-11-01 2023-12-15 龙建路桥股份有限公司 Winter continuous construction control system for deep tunnel in high and cold area
CN117252236A (en) * 2023-10-25 2023-12-19 中国路桥工程有限责任公司 Tunnel blasting vibration peak prediction method, system, equipment and medium based on DBN-LSTM-BWAA
CN118133635A (en) * 2024-05-07 2024-06-04 深地科学与工程云龙湖实验室 Tunnel contact channel deformation control method, system, equipment and storage medium
CN118332521A (en) * 2024-06-17 2024-07-12 山东建筑大学 A method for simulating crustal deformation time series based on random forest with particle swarm optimization
CN119337742A (en) * 2024-12-19 2025-01-21 石家庄铁道大学 Dynamic risk assessment method based on TBM operation parameters

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117252236A (en) * 2023-10-25 2023-12-19 中国路桥工程有限责任公司 Tunnel blasting vibration peak prediction method, system, equipment and medium based on DBN-LSTM-BWAA
CN117252236B (en) * 2023-10-25 2024-10-08 中国路桥工程有限责任公司 A tunnel blasting vibration peak prediction method, system, device and medium based on DBN-LSTM-BWOA
CN117236137A (en) * 2023-11-01 2023-12-15 龙建路桥股份有限公司 Winter continuous construction control system for deep tunnel in high and cold area
CN117236137B (en) * 2023-11-01 2024-02-02 龙建路桥股份有限公司 Winter continuous construction control system for deep tunnel in high and cold area
CN118133635A (en) * 2024-05-07 2024-06-04 深地科学与工程云龙湖实验室 Tunnel contact channel deformation control method, system, equipment and storage medium
CN118332521A (en) * 2024-06-17 2024-07-12 山东建筑大学 A method for simulating crustal deformation time series based on random forest with particle swarm optimization
CN119337742A (en) * 2024-12-19 2025-01-21 石家庄铁道大学 Dynamic risk assessment method based on TBM operation parameters

Similar Documents

Publication Publication Date Title
CN116739176A (en) Tunnel mechanized construction risk prediction method based on deep belief network
Zhou et al. Intelligent approach based on random forest for safety risk prediction of deep foundation pit in subway stations
Wang et al. Application of artificial neural network in tunnel engineering: a systematic review
Yang et al. Prediction of vibration velocity generated in mine blasting using support vector regression improved by optimization algorithms
Jahed Armaghani et al. A combination of the ICA-ANN model to predict air-overpressure resulting from blasting
Zhang et al. A novel model for risk assessment of adjacent buildings in tunneling environments
Li et al. Dynamic early warning of rockburst using microseismic multi-parameters based on Bayesian network
CN113408190B (en) Prediction method for surrounding rock deformation during highway tunnel construction based on Bayes-LSTM model
CN116992522A (en) Deep foundation pit support structure deformation prediction method, device, equipment and storage medium
Cheng et al. Groutability prediction of microfine cement based soil improvement using evolutionary LS-SVM inference model
Wu et al. A dynamic decision approach for risk analysis in complex projects
CN117252236A (en) Tunnel blasting vibration peak prediction method, system, equipment and medium based on DBN-LSTM-BWAA
CN108280289A (en) Bump danger classes prediction technique based on local weighted C4.5 algorithms
CN111950203A (en) Prediction method of blasting vibration velocity based on adaptive neuro-fuzzy inference system
Armaghani et al. Toward precise long-term rockburst forecasting: A fusion of SVM and cutting-edge meta-heuristic algorithms
Lv et al. A novel stacking-based ensemble learning model for drilling efficiency prediction in earth-rock excavation
CN115980826A (en) A Method for Predicting Rockburst Intensity Based on Weighted Metaheuristic Combination Model
Wang et al. Predicting Rock Burst in Underground Engineering Leveraging a Novel Metaheuristic-Based LightGBM Model.
Gong et al. Prediction and evaluation of coal mine coal bump based on improved deep neural network
CN118734724A (en) A method and system for intelligent prediction of blasting vibration PPV of jointed rock mass
Rusek et al. Bayesian networks and Support Vector Classifier in damage risk assessment of RC prefabricated building structures in mining areas
Feng et al. Bayesian-network-based predictions of water inrush incidents in soft rock tunnels
CN118229080A (en) Tunnel construction collapse risk assessment method, system, equipment and storage medium
CN117910336A (en) Prediction method and system for ground subsidence probability of shield construction in initial stage
CN111026790A (en) Structure safety assessment and forecasting method based on data mining

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