CN111582634A - Multi-factor safety grading method and system for underground large-space construction - Google Patents
Multi-factor safety grading method and system for underground large-space construction Download PDFInfo
- Publication number
- CN111582634A CN111582634A CN202010225494.9A CN202010225494A CN111582634A CN 111582634 A CN111582634 A CN 111582634A CN 202010225494 A CN202010225494 A CN 202010225494A CN 111582634 A CN111582634 A CN 111582634A
- Authority
- CN
- China
- Prior art keywords
- safety
- layer
- neural network
- construction
- grading
- 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
Links
- 238000010276 construction Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 21
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 7
- 230000007246 mechanism Effects 0.000 abstract description 6
- 239000002689 soil Substances 0.000 abstract description 4
- 239000011435 rock Substances 0.000 abstract description 3
- 239000011159 matrix material Substances 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 10
- 230000005284 excitation Effects 0.000 description 7
- 230000015572 biosynthetic process Effects 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 6
- 238000003786 synthesis reaction Methods 0.000 description 6
- 230000014509 gene expression Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000002364 input neuron Anatomy 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013530 stochastic neural network Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-factor safety grading method and a system for underground large-space construction, wherein the method comprises the following steps: establishing an underground large space construction multi-factor safety grading comparison table; collecting data samples associated with each security level according to the comparison table; constructing a safety grading BP neural network, training the safety grading BP neural network by using the data samples associated with each safety grade, and enabling the safety grading BP neural network to meet the following conditions: when the input layer has parameter input, the output layer automatically outputs the safety grade judgment result; and inputting data samples acquired in real time in construction into the safety grading BP neural network so as to predict the construction safety grade in real time. According to the invention, by establishing the corresponding safety grading comparison table and adopting the BP neural network to establish the construction safety grading model, the safety grading evaluation can be carried out on the underground large-space construction before the construction without depending on the internal working mechanism of a rock and soil system, so that the real-time prediction alarm is carried out in the construction process.
Description
Technical Field
The invention relates to the technical field of civil engineering construction, in particular to a multi-factor safety grading method and system for underground large-space construction.
Background
At present, existing monitoring systems for complex environments of urban underground large space construction are independent of each other, the monitoring data false alarm rate is high, an analysis method is single-index evaluation, consideration is not comprehensive, and a complete safety state grading early warning system cannot be formed, so that a standard for multi-index grading evaluation of urban underground large space construction safety states is urgently needed, and powerful guarantee is provided for construction safety of underground large spaces in China.
Furthermore, geotechnical engineering practice shows that in most cases, engineers can only measure and grasp the appearance of the rock, such as pressure of the bearing plate, ground subsidence, etc., and the working mechanism of the engineering engineers is not fully understood, although to some extent. Therefore, when describing these extrinsic objective expressions, the establishment of corresponding analytical expressions is inevitably difficult due to the unclear working mechanism of the geotechnical system. The expression of this phenomenon can be expressed by a "black box" system, and one knows only the input and output of the system, but not the internal working mechanism of the system, and the key of the problem is how to reproduce the macroscopic appearance of the system. In addition, because the relation between the input and the interference factors of the geotechnical engineering system to the output is quite complex, the output shows very complex high-order nonlinear characteristics, the nonlinear description is a problem which is not solved, and the difficulty of geotechnical working characteristic research can be seen. Due to the lack of cognition on the internal working mechanism of the rock-soil system, the manual safety assessment mainly adopted at present aiming at the safety state multi-index in the construction has great errors and contingency, and the problem of great potential safety hazard in the construction caused by manual false data reporting also exists.
The neural network is particularly suitable for processing various nonlinear problems due to the characteristics of adaptability, nonlinearity, strong fault tolerance and the like. It can extract the causal relationships implied in the samples through the learning of a large number of samples. Therefore, the neural network provides a research idea completely different from mathematical modeling for the field of underground engineering, avoids a complex constitutive model, and becomes an effective way for solving the problem of underground engineering.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a multi-factor safety grading method and system for underground large-space construction.
In order to achieve the above object, the present invention adopts the following aspects.
A multi-factor safety grading method for underground large space construction comprises the following steps:
step 101, determining a construction monitoring index and a threshold thereof according to an actual engineering situation; establishing an underground large space construction multi-factor safety grading comparison table according to the construction monitoring index and the threshold value thereof;
step 102, randomly generating data samples associated with each security level according to the underground large space construction multi-factor security grading comparison table;
103, constructing a safety hierarchical neural network, training the safety hierarchical neural network by using the data samples associated with each safety level to establish a nonlinear mapping relation from an input layer to an output layer of the safety hierarchical neural network, and enabling the safety hierarchical neural network to meet the following requirements: when the input layer has parameter input, the output layer automatically outputs the safety grade judgment result;
and 104, inputting data samples acquired in real time in construction into the safety grading neural network to predict the construction safety grade in real time.
Preferably, the determining the construction monitoring index and the threshold thereof according to the actual engineering situation includes: selecting an existing index, and performing proportional threshold reduction on the selected existing index.
Preferably, the underground large space construction multi-factor safety grading comparison table comprises the safety grade of a single monitoring index factor and the safety grade of a comprehensive multi-monitoring index factor.
Preferably, the input parameters of the input layer of the safety hierarchical neural network include: the method comprises the following steps of vertical displacement of a supporting pile or a supporting wall top, horizontal displacement of the supporting pile or the supporting wall body, vertical displacement of a stand column structure, surface settlement, stress of the supporting wall structure, stress of the stand column structure, supporting axial force and anchor rod tension.
Preferably, the total number of adjustable connection weights of the safety hierarchical neural network is 56.
Preferably, a Sigmoid function is used as an error function of the safety hierarchical neural network.
Preferably, the maximum iteration number of the safety hierarchical neural network is 5000, and the learning rate η is 0.5.
Preferably, when the error rate of the safety grading neural network is smaller than a preset value, the performance of the safety grading neural network is judged to tend to be stable, and the training is stopped.
In a further embodiment of the invention, a multi-factor safety prediction system for underground large space construction is also provided, which comprises at least one processor and a memory which is in communication connection with the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above described subterranean large space construction multifactor safety prediction method.
In summary, due to the adoption of the technical scheme, the invention at least has the following beneficial effects:
by researching multi-index grading evaluation of the construction safety state of the urban underground large space, establishing a corresponding safety grading comparison table, and establishing a construction safety grading model based on a neural network with self-adaptability, nonlinearity and strong fault tolerance, the safety grading evaluation can be performed on the underground large space construction in the construction process without depending on the internal working mechanism of a rock and soil system, so that real-time prediction and alarm are performed in the construction process. And through the automatic safety level identification of the neural network model, the construction safety prediction efficiency is improved, the manual intervention and the data false reporting are avoided, and the potential safety hazard of construction is greatly reduced.
Drawings
FIG. 1 is a multi-factor security level hierarchy model diagram in accordance with an exemplary embodiment of the present invention.
Fig. 2 is a network topology structure diagram of a neural network model according to an exemplary embodiment of the present invention.
Fig. 3 is a schematic structural view of a multi-factor safety prediction system for underground large space construction according to an exemplary embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and embodiments, so that the objects, technical solutions and advantages of the present invention will be more clearly understood. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
Fig. 1 shows an exemplary multi-factor safety grading method for underground large space construction, which includes:
step 1011, determining a construction monitoring index and a threshold thereof, comprising two parts:
firstly, selecting the existing indexes. The reasonable and available control indexes can be selected by combining national standards and local standards, and when the indexes are determined, all risk factors conforming to the engineering need to be provided according to the actual engineering general profile.
And secondly, reducing the existing indexes (aiming at special conditions such as large span and the like). And carrying out numerical experiments and model experiments, and determining the reduction coefficient through certain field experiments.
The specific monitoring index and the threshold value need to be comprehensively considered according to the actual engineering.
Step 1012, the security level determination method, which is divided into two steps to determine finally:
firstly, establishing single-factor safety grade division according to each monitoring index. The monitoring accumulated value and the change rate value are important indexes of the monitoring indexes for measuring the safety state of the foundation pit, and the accumulated alarm value and the change rate alarm value (the special conditions such as large span and the like need to be subjected to numerical experiments and model experiments and the reduction coefficient is determined through certain field experiments) specified by the standards are respectively used as the grading control standard of the safety state. The safety rating is classified into five levels according to the severity of the risk occurrence, as shown in table 1.
TABLE 1 grading Standard of Single-factor evaluation index of Foundation pit
And secondly, carrying out multi-factor safety grade division based on single-factor safety grade division. The multi-factor security level is determined by an analytic hierarchy process, which has the idea of decomposing a complex problem into various constituent elements and grouping the elements according to a dominating relationship, thereby forming an ordered hierarchical structure. And comparing every two elements of the hierarchy according to a certain rule at each level, writing the elements into a matrix form, calculating the weight of the elements of the hierarchy on the relative importance order of the criterion and the combined weight of the elements on the overall target by using a mathematical method, sequencing, and analyzing and deciding the problems by using the sequencing result. The division of the construction safety level of the multi-index underground engineering is described by taking the control values of foundation pit supporting structures and surrounding rock-soil mass monitoring projects of an open excavation method and a cover excavation method of urban rail transit engineering monitoring technical specifications as examples.
Firstly, a hierarchical structure is established, factors involved in the problem are classified, a hierarchical structure model with elements mutually connected is constructed, the uppermost hierarchy is generally a predetermined target of the problem, generally, only one element in the middle layer of the element is generally a criterion layer, and the bottommost layer of a sub-criterion layer is generally a decision scheme. On the basis of deep analysis specification, the factors and the mutual relations contained in the problem are analyzed, and the relevant factors are decomposed into a plurality of layers from top to bottom according to different attributes. The multi-factor security level hierarchy model is shown in fig. 1.
Secondly, a pairwise comparison judgment matrix is constructed (according to specific construction conditions, a fuzzy statistical method, an expert survey method, a distribution method, a binary comparison sorting method, experienced experts or engineering technicians are required to directly mark and the like for determination), and a corresponding judgment matrix form is established as shown in table 2 by taking the target layer A and the next layer n indexes B1, B2 and … … Bn related to the target layer A as examples.
TABLE 2 judgment matrix form
Wherein b isijDenotes for A, BiTo BjNumerical representation of relative importance. In general bij1, 2, …, 9 and their inverse can be taken as the scale [ i][ii]The meanings are shown in Table 3.
Thirdly, the hierarchical list is sorted according to the importance matrix, namely, the priority order of the indexes related to the hierarchical list for the index of the previous layer is sorted. The method can be summarized as the problem of calculating the characteristic root and the characteristic vector of a judgment matrix, and the judgment matrix is evaluation data for comparing the indexes related to the judgment matrix in the previous level pairwise. I.e. the decision matrix B, its maximum eigenvalue λ max and the corresponding eigenvector W are calculated such that BW ═ λ maxW. λ max and W are usually root-squares by approximate calculation.
TABLE 3 significance Scale
Then, the total hierarchical ranking utilizes the result of the single hierarchical ranking in the same hierarchy, and the importance weight of all the indexes in the hierarchy can be calculated for the previous hierarchy, which is the total hierarchical ranking. The total hierarchical ranking needs to be performed layer by layer from top to bottom, and for the second layer below the highest layer, the single hierarchical ranking is the total ranking. The total hierarchical ordering needs to be performed layer by layer from top to bottom. For the highest layer, its hierarchical single ordering is the hierarchical total ordering.
Finally, the consistency of the matrix is judged, in the practical problem, due to the complexity of the objects and the limitation of the judgment problem of people, when two matrixes are compared, the judgment matrix is difficult to have strict consistency, but rough consistency is required. Therefore, after calculating λ max, the consistency of the judgment matrix needs to be checked. Reference is made to the calculated consistency index c.i. formula (1) and the calculated mean random consistency index correction value r.i. determination method (table 4).
TABLE 4 mean random consistency index correction values
Through the calculation of the analytic hierarchy process, the sequence weight of each decision scheme relative to the total target can be finally obtained, and the decision is made according to the sequence weight.
Step 102, randomly generating data samples associated with each security level according to the underground large space construction multi-factor security grading comparison table; after the security level determination method is determined, n groups of data samples are randomly generated, that is, a multi-factor security grading comparison table for safe underground large space construction (specific grading samples are influenced by advance expert evaluation and are not shown in the table) can be established as shown in table 5, and the grade of the randomly generated data is determined by the grading method.
TABLE 5 safe underground large space construction multi-factor safety grading comparison table
103, constructing a safety hierarchical neural network, training the safety hierarchical neural network by using the data samples associated with each safety level to establish a nonlinear mapping relation from an input layer to an output layer of the safety hierarchical neural network, and enabling the safety hierarchical neural network to meet the following requirements: when the input layer has parameter input, the output layer automatically outputs the safety grade judgment result;
specifically, n level samples in table 5 are used as learning samples of the neural network, and a safety hierarchical neural network model is constructed and trained. The safety grading neural network model network identification model comprises a hidden layer, wherein the input layer, the hidden layer and the output layer are respectively composed of 9 input neurons, 4 hidden units and 5 output neurons. The model structure is shown in fig. 2. When the system performs safety grading network learning, relevant grading model data determined as learning samples in the database are automatically called.
The safety grading neural network determines grade according to randomly generated data through an analytic hierarchy process and then uses the grade as a sample, randomly generated data of a monitoring index is used as an input parameter, and corresponding data is output after network calculationAnd (4) grading. According to consideration, the input parameters of the safety grading network mainly comprise nine (the number of the input parameters can be corrected in the later stage), namely, the vertical displacement of the top of a supporting pile (wall), the horizontal displacement of the top of the supporting pile (wall), the horizontal displacement of a supporting pile (wall), the vertical displacement of an upright post structure, the ground surface settlement, the structural stress of the supporting wall, the structural stress of the upright post, the supporting axial force and the tension of an anchor rod. Accordingly, the output parameters of the safety hierarchical neural network are 5, namely the output levels. Therefore, in the embodiment, the number of the units of the actual input layer of the constructed safety hierarchical neural network is 9, and the number of the units of the actual output layer is 5. A three-layer neural network of a hidden layer is adopted between an input layer and an output layer, and the number of hidden layer units is as follows: n is1＝log29, taking n1＝4。
As shown in fig. 2, the security hierarchical neural network has a total of 3 layers: the input layer is layer 1, the hidden layer is layer 2, and the output layer is layer 3. The total number of connection weights w is 56, represented symbolically as (
The connection weight of the ith element of the (k-1) th layer to the jth element of the kth layer can be programmed by an array):
layers 1-2 (total 36 connection weights):
element 1:
element 2:
element 3:
element 4:
element 5:
element 6:
element 7:
element 8:
element 9:
represented by the array w1[9] [4 ]: dimension 1 is the number (9) of elements of the first layer (input layer), and each element has 3 connection weights with the elements (4) of the second layer; dimension 2 is the second layer element (4); the connection weights are 36 in total.
Layers 2-3 (total 20 connection weights):
element 1:
element 2:
element 3:
element 4:
represented by the array w2[4] [5 ]: dimension 1 is the number (4) of elements of the second layer, and each element has 5 connection weights with elements (5) of the third layer (output layer); dimension 2 is the third layer element (5); the connection weights are 20 in total. The total number of adjustable connection weights W of the neural network used in this example is 56. And setting a preset minimum error value, terminating training when the actual output error is smaller than the given error, and if the network model meets the requirement of the learning sample or does not meet the requirement of the learning sample but requires the network model to continue learning.
Specifically, the specific parameter setting of the safety hierarchical neural network in this example mainly includes: taking the total learning times of the network as the total number of samples, namely the total cycle times; setting the maximum iteration number of the network to be 5000; the weight values w1[ i ] in the network][j]，w2[i][j]Giving small non-zero random values [ -0.1,0.1 [)]The learning rate η is set to 0.5 (error can be set in the interface) where,
the connection weight value from the ith element of the kth-1 layer to the jth element of the kth layer is obtained;
the adjustment value of the connection weight from the ith element of the kth-1 layer to the jth element of the kth layer is obtained;
is the input sum of the ith element of the kth layer;
is the output of the ith element of the kth layer;
further, specifically setting 36 connection weights of layers 1-2 in the network:
element 1:
(w1[0][0]，w1[0][1]，w1[0][2],w1[0][3])；
element 2:
(w1[1][0]，w1[1][1]，w1[1][2]，w1[1][3])；
element 3:
(w1[2][0]，w1[2][1]，w1[2][2]，w1[2][3])；
element 4:
(w1[3][0]，w1[3][1]，w1[3][2]，w1[3][3])；
element 5:
(w1[4][0]，w1[4][1]，w1[4][2]，w1[4][3])；
element 6:
(w1[5][0]，w1[5][1]，w1[5][2]，w1[5][3])；
element 7:
(w1[6][0]，w1[6][1]，w1[6][2]，w1[6][3])；
element 8:
(w1[7][0]，w1[7][1]，w1[7][2]，w1[7][3])；
element 9:
(w1[8][0]，w1[8][1]，w1[8][2]，w1[8][3])。
represented by the array w1[9] [4] (see above): dimension 1 is the number (9) of elements of the first layer (input layer), and each element has 4 connection weights with the elements (4) of the second layer; dimension 2 is the second layer element (4); the connection weights are 36 in total.
Setting 20 connection weights of the 2 nd to 3 rd layers as follows:
element 1:
(w2[0][0]，w2[0][1]，w2[0][2]，w2[0][3]，w2[0][4])
element 2:
(w2[1][0]，w2[1][1]，w2[1][2]，w2[1][3]，w2[1][4])
element 3:
(w2[2][0]，w2[2][1]，w2[2][2]，w2[2][3]，w2[2][4])
element 4:
(w2[3][0]，w2[3][1]，w2[3][2]，w2[3][3]，w2[3][4])
represented by the array w2[3] [1 ]: dimension 1 is the number (4) of elements of the second layer, and each element has 5 connection weights with elements (5) of the third layer (output layer); dimension 2 is the third layer element (5); the connection weights are 20 in total. According to the input data of the input layer, the output of the 1 st layer (input layer) is calculated according to the excitation function, then the input and the output of each element of the 2 nd layer are calculated, and then the input and the output of each element of the 2 nd layer are calculated.
The error inverse propagation learning algorithm adopts a gradient descent method to calculate the minimum value of the error function in the weight vector space, and the weight combination of the minimized error function can be used as the solution of the learning problem. Since the gradient of the error function is calculated at each step in the learning iteration calculation, continuous differentiability of the error function must be ensured.
In the example, a Sigmoid function is adopted as a network excitation function; the Sigmoid function (or Sigmoid function) is the most commonly applied excitation function in the network, and the expression thereof is
In the formula, the constant c may be arbitrarily selected, and the reciprocal 1/c thereof is referred to as a temperature parameter in the stochastic neural network.
When c is 1, Sc(x) In a simple form, i.e.
The derivative is of the form:
when- ∞<x<Infinity, there is 0<Sc(x)<1. The derivative of this function can be expressed in itself, greatly reducing the computational effort in the iteration of the algorithm.
Specifically, layer 1 (input layer)
The input to this layer is the input parameters for each sample pair, so only the output of each element need be calculated.
Element 1:
wherein: f (x) -excitation function Sc(x)；
Element 2:
element 3:
element 4:
element 5:
element 6:
element 7:
element 8:
element 9:
represented by the array O1[9 ]: the output of the first layer of 9 elements is shown, the upper 9 outputs being the 9 elements of this array.
Specifically, layer 2 (hidden layer)
The input of each element of the layer is the sum of the product of the output of each element of the layer 1 and the transmitted weight, and the output of each element is obtained by calculation according to the excitation function and the input of each element.
Input of elements (4)
Element 1:
element 2:
element 3:
element 4:
represented by the array I2[4 ]: representing the input of the second level 4 elements, the upper 4 outputs being the 4 elements of this array.
Element 1:
I2[0]＝O1[0]w1[0][0]+O1[1]w1[1][0]+O1[2]w1[2][0]+O1[3]w1[3][0]+O1[4]w1[4][0]+O1[5]w1[5][0]+O1[6]w1[6][0]+O1[7]w1[7][0]+O1[8]w1[8][0]
element 2:
I2[1]＝O1[0]w1[0][1]+O1[1]w1[1][1]+O1[2]w1[2][1]+O1[3]w1[3][1]+O1[4]w1[4][1]+O1[5]w1[5][1]+O1[6]w1[6][1]+O1[7]w1[7][1]+O1[8]w1[8][1]
element 3:
I2[2]＝O1[0]w1[0][2]+O1[1]w1[1][2]+O1[2]w1[2][2]+O1[3]w1[3][2]+O1[4]w1[4][2]+O1[5]w1[5][2]+O1[6]w1[6][2]+O1[7]w1[7][2]+O1[8]w1[8][2]
element 4:
I2[3]＝O1[0]w1[0][3]+O1[1]w1[1][3]+O1[2]w1[2][3]+O1[3]w1[3][3]+O1[4]w1[4][4]+O1[5]w1[5][4]+O1[6]w1[6][4]+O1[7]w1[7][4]+O1[8]w1[8][4]
the synthesis is as follows: (i (0< ═ i <4) denotes the ith element of the 2 nd layer, and j (0< ═ j <9) denotes the jth element of the 1 st layer)
I2[i]＝O1[0]w1[0][i]+O1[1]w1[1][i]+O1[2]w1[2][i]+O1[3]w1[3][i]+O1[4]w1[4][i]+O1[5]w1[5][i]+O1[6]w1[6][i]+O1[7]w1[7][i]+O1[8]w1[8][i]
I2[0] ═ I2[1] ═ I2[2] ═ I2[3] ═ 0; (already having an initial value of 0)
for(i＝0；i<4；i++)
② output of each element (3)
Element 1:
wherein: f (x) -excitation function Sc(x)；
Element 2:
element 3:
the 4 thElements:
represented by the array O2[4 ]: representing the output of the second layer 4 elements.
The synthesis is as follows: i (0< ═ i <4) denotes the ith element of the 2 nd layer
O2[i]＝f(I2[i]) Wherein: f (x) -excitation function Sc(x)
Final layer 3 (output layer)
The input of each element of the layer is the sum of the product of the output of each element of the layer 2 and the transmitted weight, and the output of each element is obtained by calculation according to the excitation function and the input of each element.
Input of each element (5)
Element 1:
element 2:
element 3:
element 4:
element 5:
represented by the array I3[5 ]: representing the input of the third 5 elements and the upper 5 outputs being the 5 elements of this array.
Element 1: i3[0] ═ O2[0] w2[0] [0] + O2[1] w2[1] [0] + O2[2] w2[2] [0] + O2[3] w2[3] [0 ];
element 2: i3[0] ═ O2[0] w2[0] [1] + O2[1] w2[1] [1] + O2[2] w2[2] [1] + O2[3] w2[3] [1 ];
element 3: i3[0] ═ O2[0] w2[0] [2] + O2[1] w2[1] [2] + O2[2] w2[2] [2] + O2[3] w2[3] [2 ];
element 4: i3[0] ═ O2[0] w2[0] [3] + O2[1] w2[1] [3] + O2[2] w2[2] [3] + O2[3] w2[3] [3 ];
element 5: i3[0] ═ O2[0] w2[0] [4] + O2[1] w2[1] [4] + O2[2] w2[2] [4] + O2[3] w2[3] [4 ];
the synthesis is as follows: i3[0] ═ I3[1] ═ I3[2] ═ I3[3] ═ I3[4] ═ 0; (already having an initial value of 0)
② output of each element (1)
Element 1:
wherein: f (x) -excitation function Sc(x)
Element 2:
element 3:
element 4:
element 5:
represented by the array O3[5 ]: the output of the third 5 elements is shown, the upper 5 elements being the 5 elements of this array.
The synthesis is as follows: o3[ i ]]＝f(I3[i]) Wherein: f (x) -excitation function Sc(x)
Then calculating the error
After all outputs of the output layer 3 are calculated, the sum of squares r of errors of elements of the output layer can be calculated, and then the calculated error value is compared with the set error value. If r >, the error is too large and each connection weight value needs to be adjusted; otherwise, the error requirement is satisfied, each weight value is not needed to be adjusted, and each current connection weight value is reserved so as to carry out risk classification on the network determined by the weight values.
Error calculation formula:
if r >, then go to the next step to adjust each connection weight; if r <, then the reserved connection weight exits.
Finally, the back propagation is used to adjust the weight
If r > indicates a large difference between the actual output and the expected output (sample value), the connection weights must be adjusted. In the system, 15 weights from layer 2 to layer 3, and 36 weights from layer 1 to layer 2 are adjusted, corresponding to the connection weights.
1) Adjusting the weights of layer 2 to layer 3 (15 in total)
① calculation of output layer (layer 3)
Element 1:
wherein: f' (x) -derivative of the excitation function Sc(x)(1-Sc(x))
Element 2:
element 3:
element 4:
element 5:
represented by the array d3[5 ]: the d value of the 5 elements of the third layer is shown, and the upper 5 values are the 5 elements of the array.
Element 1: d3[0] - (O3[0] -class (1)) f' (I3[0])
Element 2: d3[1] - (O3[1] -class (2)) f' (I3[1])
Element 3: d3[2] - (O3[2] -class (3)) f' (I3[2])
Element 4: d3[3] - (O3[3] -class (4)) f' (I3[3])
Element 5: d3[4] - (O3[4] -class (5)) f' (I3[4])
Wherein: f' (x) -derivative of the excitation function Sc(x)(1-Sc(x))
② calculating and adjusting weight
According to the formula
The formula of the adjustment value of the weight from the layer 2 to the layer 3 can be calculated as follows:
second layer 1 element to third layer elements (5):
second layer 2 nd element to third layer respective elements (5):
second layer 3 rd element to third layer respective elements (5):
second layer 4 th element to third layer respective elements (5):
represented by the array dw2[5] [5 ]: the 1 st dimension is the number (4) of elements of the second layer, and each element has 1 connecting weight adjusting value connected with the elements (5) of the third layer (output layer); dimension 2 is the third layer element (5); the connection weight adjustment values are 20 in total.
Second layer 1 element to third layer elements (5):
dw2[0][0]＝-ηd3[0]O2[0]，dw2[0][1]＝-ηd3[1]O2[0]，dw2[0][2]＝-ηd3[2]O2[0]，dw2[0][3]＝-ηd3[3]O2[0]，dw2[0][4]＝-ηd3[4]O2[0]。
second layer 2 nd element to third layer respective elements (5):
dw2[1][0]＝-ηd3[0]O2[1]，dw2[1][1]＝-ηd3[1]O2[1]，dw2[1][2]＝-ηd3[2]O2[1]，dw2[1][3]＝-ηd3[3]O2[1]，dw2[1][4]＝-ηd3[4]O2[1]。
second layer 3 rd element to third layer respective elements (5):
dw2[2][0]＝-ηd3[0]O2[2]，dw2[2][1]＝-ηd3[1]O2[2]，dw2[2][2]＝-ηd3[2]O2[2]，dw2[2][3]＝-ηd3[3]O2[2]，dw2[2][4]＝-ηd3[4]O2[2]。
second layer 4 th element to third layer respective elements (5):
dw2[3][0]＝-ηd3[0]O2[3]，dw2[3][1]＝-ηd3[1]O2[3]，dw2[3][2]＝-ηd3[2]O2[3]，dw2[3][3]＝-ηd3[3]O2[3]，dw2[3][4]＝-ηd3[4]O2[3]。
the synthesis is as follows: (i (0< ═ i <4) denotes the ith element of the 2 nd layer, and j (0< ═ j <5) denotes the jth element of the 3 rd layer)
dw2[i][j]＝-η*d3[j]*O2[i]
for(i＝0；i<4；i++)
{
dw2[i][j]＝-η*d3[j]*O2[i]；
}
③ adjusting the weight
After the adjustment value of each connection weight is obtained through calculation, the adjustment value can be obtained according to a formula
Adjusting each connection weight, and modifying the formula into:
second layer 1 element to third layer elements (5):
second layer 2 nd element to third layer respective elements (5):
second layer 3 rd element to third layer respective elements (5):
second layer 4 th element to third layer respective elements (5):
2) adjusting the layer 1 to layer 2 weights (total 18)
① calculation of hidden layer (layer 2)
Element 1:
wherein: f (x) -excitation function Sc(x)
Element 2:
element 3:
element 4:
represented by the array d2[4 ]: the d value of the 4 elements of the second layer is shown, and the upper 4 values are 4 elements of the array.
Element 1:
d2[0]＝(d3[0]w2[0][0]+d3[1]w2[0][1]+d3[2]w2[0][2]+d3[3]w2[0][3]+d3[4]w2[0][4]+d3[5]w2[0][5]+d3[6]w2[0][6]+d3[7]w2[0][7]+d3[6]w2[0][8])f(I2[0])
wherein: f (x) -excitation functionNumber Sc(x)
Element 2:
d2[1]＝(d3[0]w2[1][0]+d3[1]w2[1][1]+d3[2]w2[1][2]+d3[3]w2[1][3]+d3[4]w2[1][4]+d3[5]w2[1][5]+d3[6]w2[1][6]+d3[7]w2[1][7]+d3[8]w2[1][8])f(I2[1])
element 3:
d2[2]＝(d3[0]w2[2][0]+d3[1]w2[2][1]+d3[2]w2[2][2]+d3[3]w2[2][3]+d3[4]w2[2][4]+d3[5]w2[2][5]+d3[6]w2[2][6]+d3[7]w2[2][7]+d3[8]w2[2][8])f(I2[2])
element 4:
d2[3]＝(d3[0]w2[3][0]+d3[1]w2[3][1]+d3[2]w2[3][2]+d3[3]w2[3][3]+d3[4]w2[3][4]+d3[5]w2[3][5]+d3[6]w2[3][6]+d3[7]w2[3][7]+d3[8]w2[3][8])f(I2[3])
② calculating and adjusting weight
According to the formula
The formula of the adjustment value of the weight from the layer 2 to the layer 3 can be calculated as follows:
first layer 1 element to second layer elements (4):
dw1[0][0]＝-ηd2[0]O1[0]，dw1[0][1]＝-ηd2[1]O1[0]，dw1[0][2]＝-ηd2[2]O1[0]，dw1[0][3]＝-ηd2[3]O1[0]。
first layer 2 nd element to second layer respective elements (4):
dw1[1][0]＝-ηd2[0]O1[1]，dw1[1][1]＝-ηd2[1]O1[1]，dw1[1][2]＝-ηd2[2]O1[1]，dw1[1][3]＝-ηd2[3]O1[1]。
first layer 3 rd element to second layer individual elements (4):
dw1[2][0]＝-ηd2[0]O1[2]，dw1[2][1]＝-ηd2[1]O1[2]，dw1[2][2]＝-ηd2[2]O1[2]，dw1[2][3]＝-ηd2[3]O1[2]。
first layer 4 th element to second layer respective elements (4):
dw1[3][0]＝-ηd2[0]O1[3]，dw1[3][1]＝-ηd2[1]O1[3]，dw1[3][2]＝-ηd2[2]O1[3]，dw1[3][3]＝-ηd2[3]O1[3]。
first layer 5 th element to second layer respective elements (4):
dw1[4][0]＝-ηd2[0]O1[4]，dw1[4][1]＝-ηd2[1]O1[4]，dw1[4][2]＝-ηd2[2]O1[4]，dw1[4][3]＝-ηd2[3]O1[4]。
first layer 6 th element to second layer respective elements (4):
dw1[5][0]＝-ηd2[0]O1[5]，dw1[5][1]＝-ηd2[1]O1[5]，dw1[5][2]＝-ηd2[2]O1[5]，dw1[5][3]＝-ηd2[3]O1[5]。
first layer 7 th element to second layer respective elements (4):
dw1[6][0]＝-ηd2[0]O1[6]，dw1[6][1]＝-ηd2[1]O1[6]，dw1[6][2]＝-ηd2[2]O1[6]，dw1[6][3]＝-ηd2[3]O1[6]。
first layer 8 th element to second layer individual elements (4):
dw1[7][0]＝-ηd2[0]O1[7]，dw1[7][1]＝-ηd2[1]O1[7]，dw1[7][2]＝-ηd2[2]O1[7]，dw1[7][3]＝-ηd2[3]O1[7]。
first layer 9 th element to second layer respective elements (4):
dw1[8][0]＝-ηd2[0]O1[8]，dw1[8][1]＝-ηd2[1]O1[8]，dw1[8][2]＝-ηd2[2]O1[8]，dw1[8][3]＝-ηd2[3]O1[8]。
represented by the array dw1[9] [4 ]: dimension 1 is the number of elements (9) in the first layer, each element has 4 connection weight adjustment values with elements (4) in the second layer (hidden layer); dimension 2 is the second layer element (4); the connection weight adjustment values are 36.
The synthesis is as follows: (i (0< ═ i <9) denotes the ith element of the 1 st layer, and j (0< ═ j <4) denotes the jth element of the 2 nd layer)
dw1[i][j]＝-η*d2[j]*O1[i]
for(i＝0；i<9；i++)
③ adjusting the weight
After the adjustment value of each connection weight is obtained through calculation, the adjustment value can be obtained according to a formula
Adjusting each connection weight, and modifying the formula into:
first layer 1 element to second layer elements (4):
first layer 2 nd element to second layer respective elements (4):
first layer 3 rd element to second layer individual elements (4):
first layer 4 th element to second layer respective elements (4):
first layer 5 th element to second layer respective elements (4):
first layer 6 th element to second layer respective elements (4):
first layer 7 th element to second layer respective elements (4):
first layer 8 th element to second layer individual elements (4):
first layer 9 th element to second layer respective elements (4):
and automatically adding 1 to the number of times to be recorded after adjustment to record the total number of times of adjustment, and stopping adjustment to avoid entering a dead cycle if the number of times of adjustment is greater than a specified maximum number (5000) and still does not meet the error requirement.
And after the adjustment of each connection weight value is finished, returning to the step 3, recalculating the input, output, error and the like of each element, and stopping the operation until the error is met or the adjustment is more than 5000 times as in the previous step.
The above steps are the processes of calculating and adjusting the connection weight value after inputting a sample pair, and then inputting the next sample pair to repeat the above steps until all samples are finished. After all sample pairs are input and adjusted, the network model learning is finished, and each connection weight value obtained after adjustment is stored for use in risk classification.
And 104, inputting data samples acquired in real time in construction into the safety grading neural network to predict the construction safety grade in real time.
After the system model is built, data samples in construction are collected in real time, and hierarchical prediction is carried out after relevant parameters of monitoring measurement are input.
Example 2
Fig. 3 illustrates a multi-factor safety prediction system for underground large space construction according to an exemplary embodiment of the present invention, namely, an electronic device 310 (e.g., a computer server with program execution function) including at least one processor 311, a power supply 314, and a memory 312 and an input/output interface 313 communicatively connected to the at least one processor 311; the memory 312 stores instructions executable by the at least one processor 311, the instructions being executable by the at least one processor 311 to enable the at least one processor 311 to perform a method disclosed in any one of the embodiments; the input/output interface 313 may include a display, a keyboard, a mouse, and a USB interface for inputting/outputting data; the power supply 314 is used to provide power to the electronic device 310.
Those skilled in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
When the integrated unit of the present invention is implemented in the form of a software functional unit and sold or used as a separate product, it may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The foregoing is merely a detailed description of specific embodiments of the invention and is not intended to limit the invention. Various alterations, modifications and improvements will occur to those skilled in the art without departing from the spirit and scope of the invention.
Claims (9)
1. A multi-factor safety grading method for underground large space construction is characterized by comprising the following steps:
step 101, determining a construction monitoring index and a threshold thereof according to an actual engineering situation; establishing an underground large space construction multi-factor safety grading comparison table according to the construction monitoring index and the threshold value thereof;
step 102, randomly generating data samples associated with each security level according to the underground large space construction multi-factor security grading comparison table;
103, constructing a safety hierarchical neural network, training the safety hierarchical neural network by using the data samples associated with each safety level to establish a nonlinear mapping relation from an input layer to an output layer of the safety hierarchical neural network, and enabling the safety hierarchical neural network to meet the following requirements: when the input layer has parameter input, the output layer automatically outputs the safety grade judgment result;
and 104, inputting data samples acquired in real time in construction into the safety grading neural network to predict the construction safety grade in real time.
2. The method of claim 1, wherein determining the construction monitoring indicator and its threshold value according to the actual conditions of the project comprises: selecting an existing index, and performing proportional threshold reduction on the selected existing index.
3. The method as claimed in claim 2, wherein the underground large space construction multi-factor safety grading comparison table comprises the safety level of a single monitoring index factor and the safety level of a comprehensive multi-monitoring index factor.
4. The method of claim 1, wherein the input parameters of the input layer of the security hierarchical neural network comprise: the method comprises the following steps of vertical displacement of a supporting pile or a supporting wall top, horizontal displacement of the supporting pile or the supporting wall body, vertical displacement of a stand column structure, surface settlement, stress of the supporting wall structure, stress of the stand column structure, supporting axial force and anchor rod tension.
5. The method of claim 1, wherein the security hierarchical neural network has a total number of tunable connection weights of 56.
6. The method according to any one of claims 1 to 5, wherein a Sigmoid function is used as an error function of the secure hierarchical neural network.
7. The method of any one of claims 1-5, wherein the safety-rated neural network has a maximum number of iterations of 5000 and a learning rate η of 0.5.
8. The method according to any one of claims 1 to 5, wherein when the error rate of the safety-graded neural network is less than a preset value, the performance of the safety-graded neural network is judged to be stable and the training is stopped.
9. The underground large space construction multi-factor safety prediction system is characterized by comprising at least one processor and a memory which is in communication connection with the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010225494.9A CN111582634B (en) | 2020-03-26 | 2020-03-26 | Multi-factor safety grading method and system for underground large-space construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010225494.9A CN111582634B (en) | 2020-03-26 | 2020-03-26 | Multi-factor safety grading method and system for underground large-space construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111582634A true CN111582634A (en) | 2020-08-25 |
| CN111582634B CN111582634B (en) | 2024-02-23 |
Family
ID=72111479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010225494.9A Active CN111582634B (en) | 2020-03-26 | 2020-03-26 | Multi-factor safety grading method and system for underground large-space construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582634B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113256261A (en) * | 2021-06-03 | 2021-08-13 | 北京汽车集团越野车有限公司 | Method and device for determining automobile modeling scheme and storage medium |
| CN114089055A (en) * | 2021-09-30 | 2022-02-25 | 安徽继远软件有限公司 | Method and system for monitoring safety state of power grid limited space operating personnel |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090265193A1 (en) * | 2008-04-17 | 2009-10-22 | Collins Dean | Methods and systems for automated property insurance inspection |
| CN102937784A (en) * | 2012-10-30 | 2013-02-20 | 中冶南方工程技术有限公司 | Artificial neural network based method for controlling online prediction of casting billet quality |
| CN104217122A (en) * | 2014-09-15 | 2014-12-17 | 北京市市政工程研究院 | Tunnel construction process safety evaluation method based on multi-element information early warning system |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
| CN106355540A (en) * | 2016-09-18 | 2017-01-25 | 三峡大学 | Small- and medium-sized reservoir dam safety evaluating method based on GRA-BP (grey relational analysis and back propagation) neural network |
| CN107782785A (en) * | 2017-09-08 | 2018-03-09 | 中冶建筑研究总院有限公司 | A kind of underground utilities security assessment method |
| CN108241964A (en) * | 2017-11-23 | 2018-07-03 | 贵州电网有限责任公司铜仁供电局 | Capital construction scene management and control mobile solution platform based on BP artificial nerve network model algorithms |
| CN109190872A (en) * | 2018-07-05 | 2019-01-11 | 珠海许继芝电网自动化有限公司 | A kind of power distribution network Supply Security integrated evaluating method |
-
2020
- 2020-03-26 CN CN202010225494.9A patent/CN111582634B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090265193A1 (en) * | 2008-04-17 | 2009-10-22 | Collins Dean | Methods and systems for automated property insurance inspection |
| CN102937784A (en) * | 2012-10-30 | 2013-02-20 | 中冶南方工程技术有限公司 | Artificial neural network based method for controlling online prediction of casting billet quality |
| CN104217122A (en) * | 2014-09-15 | 2014-12-17 | 北京市市政工程研究院 | Tunnel construction process safety evaluation method based on multi-element information early warning system |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
| CN106355540A (en) * | 2016-09-18 | 2017-01-25 | 三峡大学 | Small- and medium-sized reservoir dam safety evaluating method based on GRA-BP (grey relational analysis and back propagation) neural network |
| CN107782785A (en) * | 2017-09-08 | 2018-03-09 | 中冶建筑研究总院有限公司 | A kind of underground utilities security assessment method |
| CN108241964A (en) * | 2017-11-23 | 2018-07-03 | 贵州电网有限责任公司铜仁供电局 | Capital construction scene management and control mobile solution platform based on BP artificial nerve network model algorithms |
| CN109190872A (en) * | 2018-07-05 | 2019-01-11 | 珠海许继芝电网自动化有限公司 | A kind of power distribution network Supply Security integrated evaluating method |
Non-Patent Citations (4)
| Title |
|---|
| D.A.PATEL 等: ""Neural Network Model for the Prediction of Safe Work Behavior in Construction Projects"", 《JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT》, pages 1 - 11 * |
| 江新等: ""神经网络范式下硐室群施工安全风险预警研究"" * |
| 江新等: ""神经网络范式下硐室群施工安全风险预警研究"", 《中国安全科学学报》, 15 February 2018 (2018-02-15), pages 183 - 184 * |
| 江新等: ""神经网络范式下硐室群施工安全风险预警研究"", pages 183 - 184 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113256261A (en) * | 2021-06-03 | 2021-08-13 | 北京汽车集团越野车有限公司 | Method and device for determining automobile modeling scheme and storage medium |
| CN114089055A (en) * | 2021-09-30 | 2022-02-25 | 安徽继远软件有限公司 | Method and system for monitoring safety state of power grid limited space operating personnel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111582634B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kordnaeij et al. | Prediction of recompression index using GMDH-type neural network based on geotechnical soil properties | |
| Perera et al. | Static–dynamic multi-scale structural damage identification in a multi-objective framework | |
| CN105975735A (en) | Modeling method for assessing health state of power equipment | |
| CN115270635B (en) | Bayes-neural network high-rise building earthquake demand and vulnerability prediction method | |
| CN113971463A (en) | Heat supply pipeline risk distribution analysis method and routing inspection path planning system | |
| CN115659729B (en) | Dam safety monitoring analysis method and system based on structural simulation calculation | |
| Wang et al. | A Bayesian framework for estimating fragility curves based on seismic damage data and numerical simulations by adaptive neural networks | |
| CN111582634A (en) | Multi-factor safety grading method and system for underground large-space construction | |
| CN111914943B (en) | Information vector machine method and device for comprehensively judging stability of dumping type karst dangerous rock | |
| CN107295537A (en) | A kind of method and system for wireless sensor network reliability of testing and assessing | |
| CN109033509A (en) | A kind of Fusion Model construction method based on dam deformation analysis | |
| CN114792020B (en) | Quick evaluation method and system for building anti-seismic toughness based on machine learning | |
| CN115423167A (en) | Subway deep foundation pit construction safety early warning and decision-making assisting method and system | |
| CN111583067A (en) | Urban underground large space construction safety early warning and emergency decision-making method and system | |
| CN115456331B (en) | Application of multi-dimensional multi-measuring point model on-line monitoring algorithm to monitoring analysis system platform | |
| Chen et al. | Genetic programming for predicting aseismic abilities of school buildings | |
| CN116307352A (en) | Engineering quantity index estimation method and system based on machine learning | |
| CN110489844A (en) | One kind being suitable for the uneven large deformation grade prediction technique of soft rock tunnel | |
| Kao et al. | Aseismic ability estimation of school building using predictive data mining models | |
| Marasco et al. | A new evolutionary polynomial regression technique to assess the fundamental periods of irregular buildings | |
| CN111026790A (en) | Structure safety assessment and forecasting method based on data mining | |
| Inzunza-Aragón et al. | Use of artificial neural networks and response surface methodology for evaluating the reliability index of steel wind towers | |
| CN115906663A (en) | Building safety evaluation model establishing method, evaluation method, server and system | |
| CN114118688A (en) | Power grid engineering cost risk early warning method based on sequence relation analysis | |
| CN114169594A (en) | Gas concentration prediction method based on LSTM-LightGBM variable weight combined model |
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 |