CN116167147B - Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm - Google Patents
Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm Download PDFInfo
- Publication number
- CN116167147B CN116167147B CN202310453035.XA CN202310453035A CN116167147B CN 116167147 B CN116167147 B CN 116167147B CN 202310453035 A CN202310453035 A CN 202310453035A CN 116167147 B CN116167147 B CN 116167147B
- Authority
- CN
- China
- Prior art keywords
- peak
- coal rock
- energy
- coal
- rock
- 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.)
- Active
Links
- 239000011435 rock Substances 0.000 title claims abstract description 312
- 239000003245 coal Substances 0.000 title claims abstract description 281
- 238000011156 evaluation Methods 0.000 title claims abstract description 34
- 238000006243 chemical reaction Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 31
- 230000006835 compression Effects 0.000 claims abstract description 14
- 238000007906 compression Methods 0.000 claims abstract description 14
- 230000006378 damage Effects 0.000 claims description 94
- 238000000034 method Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 27
- 230000001066 destructive effect Effects 0.000 claims description 17
- 238000002372 labelling Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 206010035148 Plague Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012880 independent component analysis Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000007655 standard test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Structural Engineering (AREA)
- Civil Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Architecture (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The disclosure provides a coal rock impact tendency direct index evaluation method based on a multi-layer perceptron algorithm, which comprises the following steps: performing triaxial circulation loading and unloading treatment on initial coal rock to obtain a coal rock energy evolution data set, performing uniaxial compression treatment on the coal rock to be tested to obtain coal rock data to be tested, training an initial peak elastic energy determination model by adopting the coal rock energy evolution data set to obtain a target peak elastic energy determination model, training an initial peak post-failure strain energy determination model by adopting the coal rock energy evolution data set to obtain a target peak post-failure strain energy determination model, determining an effective elastic energy conversion index corresponding to the coal rock to be tested according to the target peak elastic energy determination model, the target peak post-failure strain energy determination model and the coal rock data to be tested, and determining an impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion index, thereby effectively improving the accuracy of the impact tendency evaluation result of the coal rock.
Description
Technical Field
The disclosure relates to the technical field of coal rock impact tendency evaluation and rock burst disaster prevention and control, in particular to a coal rock impact tendency direct index evaluation method based on a multi-layer perceptron algorithm.
Background
Rock burst is a coal-rock dynamic disaster which is common in coal mines, and is generally expressed as sudden and violent release of a large amount of elastic energy accumulated in a temporary rock mass, and a large amount of rock fragments are thrown into a mining space while the rock mass is destroyed, and along with explosion sound and shock waves, the rock fragments are thrown into the mining space. With the increase of mine exploitation depth, the coal mine production environment is more complex, the rock burst disaster threat is increasingly aggravated, and the rock burst disaster threat becomes a serious problem which plagues the safe and efficient production of the coal mine. Therefore, an efficient and accurate coal rock impact tendency evaluation method is urgently needed to be provided, and the method has important significance for underground rock burst disaster warning of the coal mine.
In the related art, the coal rock impact tendency evaluation index proposed based on the energy angle comprises an elastic energy index W ET Impact energy index K E Corrected impact energy index W CP ' impact energy velocity index W ST Effective elastic energy release rate index KET and residual elastic energy index C EF Peak strain energy storage index W ET P Etc. However, because of the heterogeneity of the coal-rock material, it is difficult to perform unloading tests at the peak point and at the post-peak softening stage, and therefore it is difficult to determine the relationship between the elastic energy at the peak of stress and the post-peak failure strain energy, thereby affecting the impact tendency evaluation effect of the coal rock.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
The embodiment of the disclosure provides a coal rock impact tendency direct index evaluation method based on a multi-layer perceptron algorithm, which comprises the following steps: performing triaxial circulation loading and unloading processing on initial coal rock to obtain initial coal rock data, performing uniaxial compression processing on the coal rock to be tested to obtain coal rock data to be tested, processing the initial coal rock data to obtain a coal rock energy evolution data set, training an initial peak elastic energy determining model by adopting the coal rock energy evolution data set to obtain a target peak elastic energy determining model, training an initial post-peak damage strain energy determining model by adopting the coal rock energy evolution data set to obtain a target post-peak damage strain energy determining model, wherein the initial peak elastic energy determining model and the initial post-peak damage strain energy determining model are both multi-layer perceptron models, determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target post-peak damage strain energy determining model and the coal rock data to be tested, and determining the impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion rate index.
The coal rock impact tendency direct index evaluation method based on the multi-layer perceptron algorithm has the following beneficial effects:
in the embodiment of the disclosure, firstly, triaxial cyclic loading and unloading processing is performed on initial coal and rock to be tested to obtain initial coal and rock data, uniaxial compression processing is performed on the coal and rock to be tested to obtain the coal and rock data to be tested, then the initial coal and rock data are processed to obtain a coal and rock energy evolution data set, an initial peak elastic energy determining model is trained by the coal and rock energy evolution data set to obtain a target peak elastic energy determining model, and an initial post-peak damage strain energy determining model is trained by the coal and rock energy evolution data set to obtain a target post-peak damage strain energy determining model, wherein the initial peak elastic energy determining model and the initial post-peak damage strain energy determining model are both multi-layer perceptron models, then an effective elastic energy conversion index corresponding to the coal and rock to be tested is determined according to the target post-peak damage strain energy determining model and the coal and rock to be tested, and an impact tendency evaluating result is determined according to the effective elastic energy conversion index, so that the accuracy of the impact tendency evaluating result of the coal and rock can be effectively improved.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a flow chart of a method for evaluating coal rock impact tendency direct index based on a multi-layer perceptron algorithm according to an embodiment of the present disclosure;
FIG. 2 is a schematic illustration of a triaxial cyclic loading and unloading stress-strain curve provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an axial stress-strain curve of a coal rock to be tested provided in an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a multi-layer perceptron model provided by an embodiment of the present disclosure;
fig. 5 is a schematic diagram of an axial stress-strain curve corresponding to a coal rock to be tested according to an embodiment of the disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
The following describes a coal rock impact tendency direct index evaluation method based on a multi-layer perceptron algorithm according to an embodiment of the present disclosure with reference to the accompanying drawings.
The embodiment of the disclosure is exemplified by the fact that the direct index evaluation method of the coal rock impact tendency based on the multi-layer perceptron algorithm is configured in a coal rock impact tendency detection device, and the coal rock impact tendency detection device can be applied to any electronic equipment so that the electronic equipment can execute the coal rock impact tendency detection function.
The electronic device may be a personal computer (Personal Computer, abbreviated as PC), a cloud device, a mobile device, etc., and the mobile device may be a hardware device with various operating systems, touch screens and/or display screens, such as a mobile phone, a tablet computer, a personal digital assistant, etc.
Fig. 1 is a flow chart of a method for evaluating coal rock impact tendency direct index based on a multi-layer perceptron algorithm according to an embodiment of the present disclosure.
As shown in fig. 1, the method for directly evaluating the coal rock impact tendency index based on the multi-layer perceptron algorithm can comprise the following steps:
and step 101, carrying out triaxial circulation loading and unloading treatment on the initial coal and rock so as to obtain initial coal and rock data.
The initial coal rock is a coal rock test piece which is obtained in advance before the coal rock impact tendency direct index evaluation method based on the multi-layer perceptron algorithm starts to be executed and is used for assisting in impact tendency detection of the coal rock to be tested, and the number of the initial coal rock can be multiple, so that the method is not limited.
Specifically, in practical application, the core collected on the engineering site can be processed into a standard cylindrical coal rock test piece with the size of 50 multiplied by 100mm according to the standard engineering rock standard test method (GB/T50266-2013).
In the embodiment of the disclosure, at least 500 target coal rock test pieces may be obtained through on-site experimental measurement and experimental data collection to be used as initial coal rocks, and triaxial cyclic loading and unloading treatment is performed on the initial coal rocks, (triaxial cyclic loading and unloading treatment refers to loading and unloading treatment performed no less than 9 times before a stress peak, loading and unloading treatment performed no less than 4 times in a post-peak softening stage, loading and unloading treatment performed no less than 6 times in a residual stage), so as to obtain triaxial cyclic loading and unloading stress-strain curves, see fig. 2, fig. 2 is a schematic diagram of the triaxial cyclic loading and unloading stress-strain curves provided by the embodiment of the disclosure, and input energy density, elastic energy density, dissipated energy density, axial stress, average stress, axial stress level, axial strain, hoop strain, axial strain level, axial stress density, axial strain limit data, axial strain level, axial strain limit data, and other data of the initial coal rocks under different surrounding pressure conditions are collected and measured and calculated according to the triaxial cyclic loading and unloading stress-strain curves.
And 102, carrying out uniaxial compression treatment on the coal rock to be tested to obtain the data of the coal rock to be tested.
The coal rock to be tested can be called as the coal rock to be tested, and the coal rock data obtained by performing uniaxial compression on the coal rock to be tested can be called as the coal rock data to be tested.
Optionally, in some embodiments, the uniaxial compression processing is performed on the coal rock to be tested to obtain the coal rock data to be tested, which may be that the uniaxial compression processing is performed on the coal rock to be tested to obtain an axial stress-strain curve, the first coal rock data to be tested at a peak point of the curve and the second coal rock data to be tested at a complete breaking point of the curve are determined according to the axial stress-strain curve, and then the first coal rock data to be tested and the second coal rock data to be tested are used together as the coal rock data to be tested.
That is, in the embodiment of the present disclosure, after performing triaxial cyclic loading and unloading processing on an initial coal rock to obtain initial coal rock data, uniaxial compression processing may be performed on the coal rock to be tested, referring to fig. 3, fig. 3 is a schematic diagram of an axial stress-strain curve of the coal rock to be tested, which is provided in the embodiment of the present disclosure, that is, the axial stress-strain curve of the coal rock to be tested may be obtained, then, the axial stress-strain curve may be combined, first coal rock data to be tested at a peak point of the curve and second coal rock data to be tested at a complete breaking point of the curve may be collected and measured, and then, the first coal rock data to be tested and the second coal rock data to be tested are used together as the coal rock data to be tested, where the coal rock data to be tested includes: the data of energy density, elastic energy density, dissipated energy density, axial stress, average stress, axial stress level, axial strain, hoop strain, axial strain level, time, etc. are input.
And 103, processing the initial coal and rock data to acquire a coal and rock energy evolution data set.
The embodiment of the disclosure performs triaxial circulation loading and unloading processing on initial coal and rock to obtain initial coal and rock data, and performs uniaxial compression processing on coal and rock to be tested to obtain coal and rock data to be tested, wherein the coal and rock data to be tested at least comprises: the axial stress-strain curve may be used to process initial coal and rock data to obtain a coal and rock energy evolution data set.
The coal rock energy evolution data set can be used for training an initial peak elastic energy determination model and an initial post-peak damage strain energy determination model, and the coal rock energy evolution data set can comprise a training set and a testing set which are respectively used for the initial peak elastic energy determination model, a model training process and a model testing process of the initial post-peak damage strain energy determination model.
In some embodiments, the initial coal-rock data is processed to obtain a coal-rock energy evolution data set, which may be a data feature extracted from a plurality of initial coal-rock data and used for training an initial peak elastic energy determination model and an initial post-peak damage strain energy determination model, and a set formed by the extracted data features is used as the coal-rock energy evolution data set.
Optionally, in some embodiments, processing the initial coal rock data to obtain a coal rock energy evolution dataset includes: extracting initial coal and rock data features from initial coal and rock data, performing feature expansion processing on the initial coal and rock data features to obtain coal and rock data features to be processed, and generating a coal and rock energy evolution data set according to the coal and rock data features to be processed, wherein each element set in the coal and rock energy evolution data set sequentially comprises: the method comprises the steps of inputting energy characteristics, elastic energy characteristics, dissipation energy characteristics, axial stress characteristics, confining pressure characteristics, average stress characteristics, axial stress level characteristics, axial strain characteristics and circumferential strain characteristics, and time characteristics, and performing characteristic expansion processing on initial coal and rock data characteristics, so that a coal and rock energy evolution data set can be generated according to the coal and rock data characteristics to be processed, which are obtained through the characteristic expansion processing, and the sample number and sample abundance of the coal and rock energy evolution data set can be effectively improved.
In the embodiment of the disclosure, a moving window is adopted to extract time sequence features (time dimension features) of initial coal and rock data, a least square method is adopted to extract related features (inter-variable correlation features) of the initial coal and rock data, an independent component analysis method is adopted to extract independent features (self-inherent attribute features irrelevant to other variables) of the initial coal and rock data, and the extracted time sequence features, related features and independent features of the initial coal and rock data are used as the initial coal and rock data features together.
In the embodiment of the disclosure, since unloading is difficult at the stress peak value and the post-peak softening stage, the initial coal-rock data features have serious feature data missing at the stress peak value and the post-peak softening stage, so that after the initial coal-rock data features are extracted from the initial coal-rock data, feature expansion processing can be performed on the initial coal-rock data features to obtain the coal-rock data features to be processed, namely the initial coal-rock data features
Performing linear mapping to obtain mapping matrix->
In the foregoing mapping process, the following conditions need to be satisfied: "can order the reconstruction error by calculating the local reconstruction weight matrix->
To a minimum value to minimize the error between the generated data and the original data, thereby completing the feature expansion process, error->
The determination mode of (2) is as follows:
wherein,,
reconstruction error, set->
Includes data points->
Is>
For initial coal rock data feature, < >>
As the characteristics of the coal and rock data to be processed,iandjand m is the number of initial coal rock data features for the matrix dimension.
The embodiment of the disclosure obtains a coal rock energy evolution data set, comprising: extracting initial coal and rock data features from the initial coal and rock data, and performing feature expansion processing on the initial coal and rock data features to obtain to-be-processed coal and rock data features, and then generating a coal and rock energy evolution data set according to the to-be-processed coal and rock data features.
Each element set in the coal rock energy evolution data set sequentially comprises: input energy density, elastic energy density, dissipated energy density, axial stress, confining pressure, average stress, axial stress level, axial strain, hoop strain, and time characteristics.
That is, in the embodiment of the present disclosure, the characteristics of the obtained coal rock data to be processed may be sorted, and a coal rock energy evolution data set may be constructed, where each element set in the coal rock energy evolution data set may be determined, and each element set sequentially includes the following 11 variables: the method sequentially comprises the following steps: input energy density, elastic energy density, dissipated energy density, axial stress, confining pressure, average stress, axial stress level, axial strain, hoop strain, and time characteristics. Each set of elements in the coal rock energy evolution data set is expressed as:
where x represents the standard energy evolution data,
respectively and sequentially represent: input energy density, elastic energy density, dissipated energy density, axial stress, confining pressure, average stress, axial stress level, axial strain, hoop strain, and time characteristics, if a variable of a certain data point is missing, then the blank is made.
In the embodiment of the disclosure, after each element set in the coal rock energy evolution data set is determined, m element sets may be sorted into a coal rock energy evolution data set, where the coal rock energy evolution data set is expressed as:
wherein,,
represents a coal rock energy evolution dataset, +.>
Representing the number of element sets.
And 104, training the initial peak elastic energy determination model by using the coal rock energy evolution data set to obtain a target peak elastic energy determination model, and training the initial post-peak damage strain energy determination model by using the coal rock energy evolution data set to obtain the target post-peak damage strain energy determination model.
After processing initial coal-rock data to obtain a coal-rock energy evolution data set, the embodiment of the disclosure may train the initial peak elastic energy determination model with the coal-rock energy evolution data set to obtain a target peak elastic energy determination model, and train the initial post-peak destructive strain energy determination model with the coal-rock energy evolution data set to obtain the target post-peak destructive strain energy determination model.
The initial peak elastic energy determining model is an untrained peak elastic energy determining model obtained in an initial stage of executing the coal rock impact tendency direct index evaluating method based on the multi-layer perceptron algorithm, the initial peak elastic energy determining model can be used for determining peak elastic energy values corresponding to the coal rock to be tested, and accordingly, the initial peak elastic energy determining model is an untrained post-peak damage strain energy model obtained in an initial stage of executing the coal rock impact tendency direct index evaluating method based on the multi-layer perceptron algorithm, and the initial post-peak damage strain energy model can be used for determining post-peak damage strain energy values corresponding to the coal rock to be tested without limitation.
In the embodiment of the disclosure, the initial peak elastic energy determination model and the initial post-peak damage strain energy determination model are both multi-layer perceptron models, the model structures of the initial peak elastic energy determination model and the initial post-peak damage strain energy determination model are shown in fig. 4, see fig. 4, fig. 4 is a schematic structural diagram of the multi-layer perceptron model provided by the embodiment of the disclosure, that is, a coal rock energy evolution data set can be trained by using a multi-layer perceptron algorithm, and a network structure of the multi-layer perceptron model is set, as shown in fig. 3. In the figure, the network structure is divided into an input layer, a hidden layer and an output layer. The input layer contains 11 neurons { y } 1 ，y 2 ，……y 11 Respectively 11 data in the coal rock energy evolution data set; the output layer contains 1 neuron, and the first hidden layer is sized to 11 neurons { b 1 ，b 2 ，……b 11 The remaining hidden layers are set to 2 layers of 15 neurons each. The connection relation between the input layer and the first hidden layer is set by adopting the Sigmoid activation function connection between the layers so as to make physical meaning clear and improve training efficiency. The energy characteristic unit is connected with the input energy density, the elastic energy density and the dissipation energy density and used for representing the relationship between the dissipation and conversion of the energy in the coal rock; the input energy unit is connected with the input energy density, the axial stress, the confining pressure and the average stress to reflect the factors influencing the change of the input energy density; the elastic energy unit is connected with the elastic energy density, the axial stress, the confining pressure and the average stress to reflect the influence of the elastic energyFactors of density variation; the dissipated energy unit is connected with the dissipated energy density, the axial stress level, the axial strain level and the time to reflect the factors influencing the change of the dissipated energy density; the stress characteristics are connected with axial stress, confining pressure and average stress to represent the stress state of the coal rock; the load characteristics are horizontally connected with axial stress, confining pressure, average stress and axial stress, and represent the load bearing state of the coal rock; the damage characteristic unit is connected with the axial stress level, the axial strain level and the time to represent the damage degree of the coal rock; the axial constitutive unit is connected with axial stress, axial strain and time to represent the stress-strain relation of the coal rock in the axial direction; the annular constitutive unit is connected with confining pressure, annular strain and time, represents the stress-strain relation of the coal rock in the annular direction, the strain characteristic is connected with axial strain, annular strain and axial strain level, represents the strain state of the coal rock, and the time characteristic unit is connected with axial stress, confining pressure and time, and represents the loading time and loading speed characteristic.
That is, in the embodiment of the disclosure, an untrained initial peak elastic energy determination model and an initial post-peak damage strain energy determination model may be obtained, and the initial peak elastic energy determination model and the initial post-peak damage strain energy determination model are trained by using a training set in the coal-rock energy evolution data set until the models converge, so as to obtain a target peak elastic energy determination model and a target post-peak damage strain energy determination model.
Optionally, in some embodiments, training the initial peak elastic energy determining model by using the coal rock energy evolution data set to obtain the target peak elastic energy determining model, that is, obtaining a marked peak elastic energy value corresponding to the coal rock energy evolution data set, inputting a plurality of elements in the coal rock energy evolution data set into corresponding input layers of the initial peak elastic energy determining model respectively, so as to obtain a predicted peak elastic energy value output by the initial peak elastic energy determining model, determining a first loss value between the marked peak elastic energy value and the predicted peak elastic energy value, and taking the peak elastic energy determining model obtained by training as the target peak elastic energy determining model when the first loss value is smaller than the first loss threshold, thereby accurately determining convergence time of the peak elastic energy determining model in combination with the first loss threshold, and effectively improving training effect of the peak elastic energy determining model.
The labeling peak elastic energy value may be a labeling result obtained in advance and used for training the initial peak elastic energy determination model.
And marking a loss value between the peak elastic energy value and the predicted peak elastic energy value, namely, a first loss value.
That is, in the embodiment of the present disclosure, elements in the coal-rock energy evolution data set may be respectively input into the corresponding input layers of the initial peak elastic energy determination model as shown in fig. 4, and the initial peak elastic energy determination model predicts the peak elastic energy value of the coal rock to be tested according to the coal-rock energy evolution data set, and outputs the corresponding predicted peak elastic energy value.
In the embodiment of the disclosure, after the marked peak elastic energy value corresponding to the coal rock energy evolution data set is obtained and the coal rock energy evolution data set is input into the initial peak elastic energy determination model to obtain the predicted peak elastic energy value output by the initial peak elastic energy determination model, a first loss value between the marked peak elastic energy value and the predicted peak elastic energy value can be determined, and the determination process of the first loss value can be expressed as:
wherein,,
for the first loss value, +.>
To mark peak elastic energy value +.>
To predict the peak elastic energy value, n is the number of predicted peak elastic energy values.
After determining the first loss value between the marked peak elastic energy value and the predicted peak elastic energy value, the embodiment of the disclosure may compare the first loss value with a predetermined loss threshold, determine that the model converges when the first loss value is smaller than the first loss threshold, and use the peak elastic energy determination model obtained by training as the target peak elastic energy determination model.
Optionally, in some embodiments, the training of the initial post-peak damage strain energy determining model by using the coal-rock energy evolution data set may be performed to obtain a target post-peak damage strain energy determining model, which may be obtained by obtaining a post-peak damage strain energy value corresponding to the coal-rock energy evolution data set, and inputting a plurality of elements in the coal-rock energy evolution data set into a corresponding input layer of the initial post-peak damage strain energy determining model, so as to obtain a predicted post-peak damage strain energy value output by the initial post-peak damage strain energy determining model, determining a second loss value between the post-peak damage strain energy value and the predicted post-peak damage strain energy value, and when the second loss value is smaller than the second loss threshold, using the post-peak damage strain energy determining model obtained by training as the target post-peak damage strain energy determining model, thereby, in combination with the first loss threshold, accurately determining a convergence time of the post-peak damage strain energy determining model, so as to effectively improve a training effect of the post-peak damage strain energy determining model.
The post-peak damage strain energy value may be a pre-obtained labeling result for training the initial post-peak damage strain energy determination model.
And marking a loss value between the post-peak damage strain energy value and the predicted post-peak damage strain energy value, namely a second loss value.
That is, in the embodiment of the disclosure, the coal-rock energy evolution data set may be debilitated in the corresponding input layer of the initial post-peak damage strain energy determination model of the above graph, the post-peak damage strain energy value of the coal-rock to be tested is predicted by the initial post-peak damage strain energy determination model according to the coal-rock energy evolution data set, and the corresponding predicted post-peak damage strain energy value is output.
In the embodiment of the disclosure, after the marked peak elastic energy value corresponding to the coal rock energy evolution data set is obtained and the coal rock energy evolution data set is input into the initial post-peak damage strain energy determination model to obtain the predicted post-peak damage strain energy value output by the initial post-peak damage strain energy determination model, a second loss value between the marked post-peak damage strain energy value and the predicted post-peak damage strain energy value can be determined, and the determination process of the second loss value can be expressed as:
wherein,,
for the second loss value, +.>
To mark the post-peak destructive strain energy value, +.>
To predict the post-peak strain energy value, n is the number of post-peak strain energy values predicted.
After determining the second loss value between the post-peak damage strain energy value and the predicted post-peak damage strain energy value, the embodiment of the disclosure may compare the second loss value with a predetermined second loss threshold, determine model convergence when the second loss value is smaller than the second loss threshold, and use the post-peak damage strain energy determination model obtained by training as the target post-peak damage strain energy determination model.
And 105, determining an effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy determination model, the target post-peak damage strain energy determination model and the coal rock data to be tested.
The effective elastic energy conversion index can be used for describing the relation between the elastic energy at the peak of stress and the damage strain energy after the peak, and the higher the effective elastic energy conversion index is, the higher the impact tendency of the coal rock to be tested is.
According to the embodiment of the disclosure, after the target peak elastic energy determination model is obtained, the target peak after-damage strain energy determination model can be used for determining an effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy determination model, the target peak after-damage strain energy determination model and the coal rock to be tested.
In some embodiments, according to the target peak elastic energy determination model, the target post-peak damage strain energy determination model and the axial stress-strain curve, the effective elastic energy conversion index corresponding to the coal and rock to be tested is determined, which may be that the data of the coal and rock to be tested are respectively input into the target peak elastic energy determination model and the target post-peak damage strain energy determination model, and the output results of the target peak elastic energy determination model and the target post-peak damage strain energy determination model are combined, so as to determine the effective elastic energy conversion index corresponding to the coal and rock to be tested.
And 106, determining an impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion rate index.
In some embodiments, the determining the impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion rate index may be that when the effective elastic energy conversion rate index is less than or equal to 0 is determined, the determining the impact tendency evaluation result of the coal rock to be tested is: the impact tendency is not generated, and when the effective elastic energy conversion rate index is larger than 0, the impact tendency evaluation result of the coal rock to be tested is determined as follows: there is a tendency to impact, and there is no limitation to this.
In the embodiment of the disclosure, triaxial cyclic loading and unloading processing is performed on initial coal and rock to obtain initial coal and rock data, uniaxial compression processing is performed on the coal and rock to be tested to obtain the coal and rock data to be tested, then the initial coal and rock data is processed to obtain a coal and rock energy evolution data set, an initial peak elastic energy determining model is trained by the coal and rock energy evolution data set to obtain a target peak elastic energy determining model, an initial post-peak damage strain energy determining model is trained by the coal and rock energy evolution data set to obtain a target post-peak damage strain energy determining model, wherein the initial peak elastic energy determining model and the initial post-peak damage strain energy determining model are both multi-layer perceptron models, then an effective elastic energy conversion index corresponding to the coal and rock to be tested is determined according to the target post-peak damage strain energy determining model and the coal and rock to be tested, and an impact tendency evaluation result is determined according to the effective elastic energy conversion index, so that the accuracy of the impact tendency evaluation result of the coal and rock can be effectively improved.
Fig. 5 is a flow chart of a method for evaluating coal rock impact tendency direct index based on a multi-layer perceptron algorithm according to another embodiment of the present disclosure.
As shown in fig. 5, the method for directly evaluating the coal rock impact tendency index based on the multi-layer perceptron algorithm can comprise the following steps:
and step 501, carrying out triaxial circulation loading and unloading treatment on the initial coal and rock so as to acquire initial coal and rock data.
The descriptions of steps 501 to 504 can be specifically referred to the above embodiments, and are not repeated here.
And 505, inputting the first coal rock data to be tested into the target peak elastic energy determination model to acquire a target peak elastic energy value output by the target peak elastic energy determination model.
In the embodiment of the disclosure, the uniaxial loading condition of the coal rock to be tested can be regarded as a special case of the triaxial loading condition of the initial coal rock. Thus, with the confining pressure set to 0, the target peak elastic energy determination model can be used to predict the target peak elastic energy value inside the coal rock to be tested under uniaxial loading conditions.
That is, in the embodiment of the present disclosure, the first coal rock data to be tested may be input into the target peak elastic energy determination model to obtain the target peak elastic energy value output by the target peak elastic energy determination model.
And step 506, inputting the second coal rock data to be tested into the target post-peak damage strain energy determination model to acquire a target post-peak damage strain energy value output by the target post-peak damage strain energy determination model.
In the embodiment of the disclosure, the uniaxial loading condition of the coal rock to be tested can be regarded as a special case of the triaxial loading condition of the initial coal rock. Therefore, the ambient pressure is set to 0, and the target post-peak destructive strain energy determination model can be used for predicting the target post-peak destructive strain energy value in the coal rock to be tested under the uniaxial loading condition.
That is, in the embodiment of the present disclosure, the input energy density, the axial strain level, and the time data of the curve full break point may be input into the target post-peak damage strain energy determination model to obtain the target post-peak damage strain energy value output by the target post-peak damage strain energy determination model.
And 507, determining an effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy value and the target post-peak damage strain energy value.
After the target peak elastic energy value and the target post-peak damage strain energy value are determined, the embodiment of the disclosure can determine the effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy value and the target post-peak damage strain energy value.
In some embodiments, determining the effective elastic energy conversion index corresponding to the coal and rock to be tested according to the target peak elastic energy value and the target post-peak destructive strain energy value may be to obtain in advance a reference peak elastic energy value and a reference post-peak destructive strain energy value corresponding to the reference effective elastic energy conversion index, and then determining the reference effective elastic energy conversion index corresponding to the target peak elastic energy value and the target post-peak destructive strain energy value, which are the same as the target peak elastic energy value and the target post-peak destructive strain energy value, as the effective elastic energy conversion index of the coal and rock to be tested after determining the target peak elastic energy value and the target post-peak destructive strain energy value.
Alternatively, in some embodiments, the determining the effective elastic energy conversion index corresponding to the coal rock to be tested according to the target peak elastic energy value and the target post-peak damage strain energy value may be obtaining a reference post-peak damage strain energy value of the coal rock to be tested, and determining the effective elastic energy conversion index corresponding to the coal rock to be tested according to the reference post-peak damage strain energy value, the target peak elastic energy value and the target post-peak damage strain energy value.
The post-reference peak strain energy value may be a post-spike strain energy value corresponding to the target post-peak strain energy value.
That is, in embodiments of the present disclosure, the reference post-peak strain-to-failure value may include a portion of the kinetic energy of the impact failure release of the coal rock, while the noted post-peak strain-to-failure value does not include a portion of the kinetic energy of the impact failure release of the coal rock.
That is, in the embodiment of the disclosure, the kinetic energy released by the impact damage of the coal and rock is determined according to the reference post-peak damage strain energy value and the target post-peak damage strain energy value, and the ratio between the kinetic energy released by the impact damage of the coal and rock and the target peak elastic energy value is determined as the effective elastic energy conversion index
The calculation formula of (2) is as follows:
wherein,,
for an effective elastic energy conversion index, +.>
For the target post-peak failure strain energy value, +.>
For the reference post-peak destructive strain energy value, +.>
Is the target peak elastic energy value.
And 507, determining an impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion rate index.
After determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested, the embodiment of the disclosure can determine the impact tendency grade of the coal rock to be tested according to the effective elastic energy conversion rate index, and the corresponding relationship between the impact tendency evaluation result and the effective elastic energy conversion rate index is shown in table 1:
TABLE 1
That is, in the embodiment of the present disclosure, when the effective elastic energy conversion rate index is less than 0, the impact tendency evaluation result of the coal rock to be tested is determined as follows: and when the effective elastic energy conversion rate index is more than or equal to 0 and less than 0.5, determining the impact tendency evaluation result of the coal rock to be tested as follows: weak impact tendency, when the effective elastic energy conversion rate index is more than or equal to 0.5, determining the impact tendency evaluation result of the coal rock to be tested as follows: strong impact tendency.
In the embodiment of the disclosure, triaxial cyclic loading and unloading processing is performed on initial coal and rock to obtain initial coal and rock data, uniaxial compression processing is performed on the coal and rock to be tested to obtain the coal and rock data to be tested, then the initial coal and rock data is processed to obtain a coal and rock energy evolution data set, then the initial peak elastic energy determination model is trained by the coal and rock energy evolution data set to obtain a target peak elastic energy determination model, the initial peak post-destruction strain energy determination model is trained by the coal and rock energy evolution data set to obtain a target peak post-destruction strain energy determination model, the first coal and rock data to be tested is input into the target peak elastic energy determination model to obtain a target peak elastic energy value output by the target peak elastic energy determination model, then the second coal and rock data to be tested is input into the target peak post-destruction strain energy determination model to obtain a target peak destruction strain energy value output by the target peak-destruction strain energy determination model, and then the effective energy conversion index corresponding to the coal to be tested is determined according to the target peak elastic energy value and the target peak post-destruction strain energy value, and the coal impact property conversion to be tested is evaluated. Compared with the existing evaluation method, the method directly calculates the effective elastic energy conversion rate index of the coal rock to be tested, belongs to the direct index evaluation method, and has the advantages of simple calculation process and high accuracy of impact tendency evaluation results.
Claims (5)
1. The method for directly evaluating the coal rock impact tendency index based on the multi-layer perceptron algorithm is characterized by comprising the following steps of:
carrying out triaxial circulation loading and unloading treatment on the initial coal rock to obtain initial coal rock data;
carrying out uniaxial compression treatment on the coal rock to be tested to obtain data of the coal rock to be tested;
processing the initial coal rock data to obtain a coal rock energy evolution data set;
training an initial peak elastic energy determination model by adopting the coal rock energy evolution data set to obtain a target peak elastic energy determination model, and training an initial post-peak destructive strain energy determination model by adopting the coal rock energy evolution data set to obtain a target post-peak destructive strain energy determination model, wherein the initial peak elastic energy determination model and the initial post-peak destructive strain energy determination model are both multi-layer perceptron models;
determining an effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy determination model, the target post-peak damage strain energy determination model and the coal rock to be tested;
determining an impact tendency evaluation result of the coal rock to be tested according to the effective elastic energy conversion rate index;
the determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy determining model, the target post-peak damage strain energy determining model and the coal rock to be tested data comprises the following steps:
inputting first coal rock data to be tested into the target peak elastic energy determining model to obtain a target peak elastic energy value output by the target peak elastic energy determining model;
inputting second coal rock data to be tested into the target post-peak damage strain energy determination model to obtain a target post-peak damage strain energy value output by the target post-peak damage strain energy determination model;
determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy value and the target post-peak damage strain energy value;
the determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested according to the target peak elastic energy value and the target post-peak damage strain energy value comprises the following steps:
obtaining a reference peak post-destructive strain energy value of the coal rock to be tested;
according to the reference peak post-failure strain energy value, the target peak elastic energy value and the target peak post-failure strain energy value, determining the effective elastic energy conversion rate index corresponding to the coal rock to be tested, wherein the determination formula of the effective elastic energy conversion rate index is as follows:
wherein,,
indicating the effective elastic energy conversion index, < >>
Representing the target post-peak destructive strain energy value, < >>
Representing the post-reference peak failure strain energy value, < >>
Representing the target peak elastic energy value;
if the effective elastic energy conversion rate index is smaller than 0, determining that the impact tendency evaluation result of the coal rock to be tested is as follows: no impact tendency;
if the effective elastic energy conversion rate index is more than or equal to 0 and less than 0.5, determining that the impact tendency evaluation result of the coal rock to be tested is as follows: weak impact tendency;
if the effective elastic energy conversion rate index is greater than or equal to 0.5, determining that the impact tendency evaluation result of the coal rock to be tested is as follows: strong impact tendency.
2. The method of claim 1, wherein processing the initial coal-rock data to obtain a coal-rock energy evolution dataset comprises:
extracting initial coal and rock data characteristics from the initial coal and rock data;
performing feature expansion processing on the initial coal rock data features to obtain coal rock data features to be processed;
generating a coal rock energy evolution data set according to the coal rock data characteristics to be processed; each element set in the coal rock energy evolution data set sequentially comprises: input energy density, elastic energy density, dissipated energy density, axial stress, confining pressure, average stress, axial stress level, axial strain, hoop strain, and time characteristics.
3. The method of claim 2, wherein training the initial peak elastic energy determination model with the coal rock energy evolution data set to obtain a target peak elastic energy determination model comprises:
acquiring a marked peak value elastic energy value corresponding to the coal rock energy evolution data set;
respectively inputting a plurality of elements in the coal rock energy evolution data set into corresponding input layers of the initial peak elastic energy determination model to obtain a predicted peak elastic energy value output by the initial peak elastic energy determination model;
determining a first loss value between the noted peak elastic energy value and the predicted peak elastic energy value;
and if the first loss value is smaller than a first loss threshold value, taking the peak elastic energy determination model obtained through training as the target peak elastic energy determination model.
4. The method of claim 2, wherein training the initial post-peak strain-to-failure energy determination model with the coal rock energy evolution data set to obtain a target post-peak strain-to-failure energy determination model comprises:
acquiring a post-peak damage strain energy value corresponding to the coal rock energy evolution data set, wherein the post-peak damage strain energy value is a pre-acquired labeling result for training an initial post-peak damage strain energy determination model;
respectively inputting a plurality of elements in the coal rock energy evolution data set into corresponding input layers of the initial post-peak damage strain energy determination model to obtain predicted post-peak damage strain energy values output by the initial post-peak damage strain energy determination model;
determining a second loss value between the post-noted peak strain energy value and the predicted post-peak strain energy value;
and if the second loss value is smaller than a second loss threshold value, taking the post-peak damage strain energy determination model obtained through training as the target post-peak damage strain energy determination model.
5. The method of claim 1, wherein the uniaxially compressing the coal rock to be tested to obtain the coal rock data to be tested comprises:
carrying out uniaxial compression treatment on the coal rock to be tested to obtain an axial stress-strain curve;
according to the axial stress-strain curve, determining first coal rock data to be tested corresponding to a curve peak point and second coal rock data to be tested corresponding to a curve complete breaking point;
and taking the first coal rock data to be tested and the second coal rock data to be tested together as the coal rock data to be tested.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310453035.XA CN116167147B (en) | 2023-04-25 | 2023-04-25 | Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310453035.XA CN116167147B (en) | 2023-04-25 | 2023-04-25 | Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116167147A CN116167147A (en) | 2023-05-26 |
| CN116167147B true CN116167147B (en) | 2023-07-07 |
Family
ID=86418616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310453035.XA Active CN116167147B (en) | 2023-04-25 | 2023-04-25 | Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167147B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11492891B1 (en) * | 2022-02-16 | 2022-11-08 | Liaoning University | Method and apparatus of controlling drilling for rock burst prevention in coal mine roadway |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107991195A (en) * | 2017-11-27 | 2018-05-04 | 中南大学 | A kind of method that elastic deformation energy at rock material peak load point is measured in three-point bending fracture experiment |
| CN107991185A (en) * | 2017-11-27 | 2018-05-04 | 中南大学 | A kind of Rock burst proneness Grade Judgment based on rock material peak value elastic energy index |
| CN109253928B (en) * | 2018-10-22 | 2021-05-28 | 山东科技大学 | Rock burst starting energy threshold determining method and rock burst predicting method |
| CN111859781A (en) * | 2020-06-16 | 2020-10-30 | 重庆大学 | Mining coal rock multi-field response rapid acquisition method |
| CN112304754B (en) * | 2020-10-11 | 2022-08-09 | 中国石油天然气股份有限公司大港油田分公司 | Shale brittleness logging evaluation method considering diagenesis and pressure change |
| CN115266348B (en) * | 2022-07-27 | 2024-04-26 | 中国科学院武汉岩土力学研究所 | Rock burst tendency grade judging method based on dynamic and static load superposition test |
| CN115372137A (en) * | 2022-08-17 | 2022-11-22 | 煤炭科学研究总院有限公司 | Coal rock impact tendency evaluation method based on energy dissipation and conversion mechanism |
| CN115468531A (en) * | 2022-08-26 | 2022-12-13 | 东南大学 | Surrounding rock burst tendency quantitative evaluation method considering excavation disturbance effect |
| CN115773937B (en) * | 2022-12-10 | 2023-08-08 | 北京科技大学 | Strain type rock burst tendency grade discrimination method |
-
2023
- 2023-04-25 CN CN202310453035.XA patent/CN116167147B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11492891B1 (en) * | 2022-02-16 | 2022-11-08 | Liaoning University | Method and apparatus of controlling drilling for rock burst prevention in coal mine roadway |
Non-Patent Citations (1)
| Title |
|---|
| 煤岩组合体峰后应力-应变关系模型及脆性特征;宋洪强;左建平;陈岩;黎立云;;采矿与安全工程学报(第05期);191-198 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116167147A (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Correlational fractal characterisation of stress and acoustic emission during coal and rock failure under multilevel dynamic loading | |
| Dong et al. | Prediction of rockburst classification using Random Forest | |
| CN103291364B (en) | Microseismic multidimensional information comprehensive time sequence early warning method for rock burst | |
| Tang et al. | Discontinuous deformation and displacement analysis: From continuous to discontinuous | |
| Li et al. | Acoustic emission and energy dissipation characteristics of gas-bearing coal samples under different cyclic loading paths | |
| Jiang et al. | Statistical characterization of the mechanical parameters of intact rock under triaxial compression: An experimental proof of the Jinping marble | |
| Chencho et al. | Development and application of random forest technique for element level structural damage quantification | |
| Beijing et al. | Crack detection and evolution law for rock mass under SHPB impact tests | |
| Tao et al. | Entropy method for structural health monitoring based on statistical cause and effect analysis of acoustic emission and vibration signals | |
| Ma et al. | Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel | |
| Zeng et al. | An innovative method for axial pressure evaluation in smart rubber bearing based on bidirectional long-short term memory neural network | |
| CN116167147B (en) | Coal rock impact tendency direct index evaluation method based on multi-layer perceptron algorithm | |
| Zhu | Review on structural health monitoring of offshore platform | |
| CN116822311B (en) | Method and system for predicting surrounding stress of explosion instant blast hole | |
| JP2019015572A (en) | Method for detecting strength index of earthquake motion having highly relevant to functional damage of equipment system | |
| Peng-hui et al. | Structural damage identification based on genetically trained ANNs in beams | |
| Saberi et al. | Damage detection of space structures using charged system search algorithm and residual force method | |
| Zhou et al. | A novel method to evaluate the effect of slope blasting under impact loading | |
| Ghadami et al. | A new adaptable multiple-crack detection algorithm in beam-like structures | |
| Mantey et al. | Fatigue damage development of grouted connection under varying cyclic loading | |
| Liu et al. | Support condition identification of wind turbines based on a statistical time-domain damping parameter | |
| Kang et al. | A support-vector-machine-based method for predicting large-deformation in rock mass | |
| Peixoto et al. | Prediction of rockburst based on an accident database | |
| Zhang et al. | Data-Driven Structural Health Monitoring: Leveraging Amplitude-Aware Permutation Entropy of Time Series Model Residuals for Nonlinear Damage Diagnosis | |
| Sun et al. | Classification of anchor bolts based on spectral kurtosis and K-means clustering algorithm |
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 |