CN112911532B - Foundation pit big data detection system - Google Patents
Foundation pit big data detection system Download PDFInfo
- Publication number
- CN112911532B CN112911532B CN202110040403.9A CN202110040403A CN112911532B CN 112911532 B CN112911532 B CN 112911532B CN 202110040403 A CN202110040403 A CN 202110040403A CN 112911532 B CN112911532 B CN 112911532B
- Authority
- CN
- China
- Prior art keywords
- foundation pit
- neural network
- network model
- settlement
- trapezoidal fuzzy
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D33/00—Testing foundations or foundation structures
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C19/00—Electric signal transmission systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
The invention discloses a foundation pit big data detection system, which consists of a foundation pit parameter acquisition platform and a foundation pit parameter big data processing subsystem, realizes foundation pit parameter detection and foundation pit safety prediction, and improves the safety and reliability management level of constructional engineering; the invention effectively solves the problem that the existing foundation pit has no influence on the safety of the foundation pit according to the nonlinearity and large lag of the change of the foundation pit parameters, the complicated change of the large parameters of the area of the foundation pit and the like, and the safety management of the foundation pit is greatly influenced by not predicting the parameters of the foundation pit and early warning the safety of the foundation pit.
Description
Technical Field
The invention relates to the technical field of foundation pit big data safety detection systems, in particular to a foundation pit big data detection system.
Background
With the rapid development of economy, high-rise buildings and large-scale buildings are more and more, the excavation depth and scale of the foundation pit of the buildings are larger and larger, the foundation pit develops towards a large depth and a large area, the surrounding environment is more complex, and the difficulty of excavation and supporting of the deep foundation pit is more and more increased. The foundation pit must be monitored to ensure the safety of the deep foundation pit excavation. The deep foundation pit engineering is a research subject with a long history of geotechnical engineering, is closely related to the development of civil engineering, is interdependent and is an important part belonging to a built engineering system. The reason why the two are closely related is that the development of civil engineering construction technology can promote and promote the development of deep foundation pit technology on the one hand, and the development of deep foundation pit engineering technology provides relevant foundation for civil engineering construction on the other hand. The deformation of the soil around the deep foundation pit is influenced by factors such as the soil quality of the soil layer of the foundation, the time required after the foundation pit is excavated, the area and soil quality of the foundation pit, and the form of the adjacent structure around the deep foundation pit. In the deep foundation pit engineering construction, deformation monitoring of the foundation pit is needed, horizontal displacement and settlement monitoring of some protection objects are needed, and along with rapid development of super high-rise buildings, people pay more and more attention to deformation monitoring of the foundation pit and popularization. The frequency of engineering accidents, such as foundation pit collapse, adjacent building cracking and even collapse, has increased over the last few years and has resulted in significant economic losses and loss of lives and personal injury. Such engineering accidents are caused by the fact that the foundation pit is physically deformed and even peripheral buildings or structures are settled in the excavation construction process of the foundation pit. Therefore, the deformation monitoring and predicting work for the foundation pit is very important. At present, in the domestic process of deep foundation pit engineering construction, the deformation monitoring of the foundation pit in the construction period is generally more important, and related foundation pit deformation monitoring technology is also widely applied. The foundation pit big data detection system has important significance in monitoring the safety of the foundation pit and improving the safety and reliability of construction engineering.
Disclosure of Invention
The invention provides a foundation pit big data detection system, which effectively solves the problem that the existing foundation pit has no influence on the safety of the foundation pit according to the nonlinearity and large lag of the change of the foundation pit parameters, the complicated change of the large parameters of the area of the foundation pit and the like, and the safety management of the foundation pit is greatly influenced by not predicting the foundation pit parameters and early warning the safety of the foundation pit.
The invention is realized by the following technical scheme:
a foundation pit big data detection system is composed of a foundation pit parameter acquisition platform and a foundation pit parameter big data processing subsystem, wherein the foundation pit parameter acquisition platform comprises a measurement node, a gateway node, a field monitoring end, a cloud platform and a mobile end App, and foundation pit parameter detection is realized; the foundation pit parameter big data processing subsystem comprises a plurality of parameter detection modules and a foundation pit safety classifier, so that the foundation pit safety is predicted, and the safety and reliability management level of the building engineering is improved.
The invention further adopts the technical improvement scheme that:
the foundation pit parameter acquisition platform comprises a plurality of detection nodes, gateway nodes, an on-site monitoring end, a cloud platform and a mobile end App of foundation pit parameters, and wireless communication between the detection nodes and the gateway nodes is realized by constructing a LoRa communication network between the detection nodes and the gateway nodes; the detection node sends the detected foundation pit parameters to an on-site monitoring end through an RS232 interface of the gateway node, and the on-site monitoring end manages the foundation pit parameters and classifies the foundation pit safety; the gateway node realizes bidirectional transmission of the foundation pit parameters between the NB-IoT module and the cloud platform and between the cloud platform and the mobile terminal App through the 5G network, and bidirectional transmission of the foundation pit parameters between the gateway node and the field monitoring terminal is realized through an RS232 interface.
The invention further adopts the technical improvement scheme that:
the foundation pit parameter big data processing subsystem comprises a plurality of parameter detection modules and a foundation pit safety classifier, the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number output by the parameter detection modules are respectively used as the input of 3 corresponding self-association neural network fusion models of the foundation pit safety classifier, and the trapezoidal fuzzy number output by the foundation pit safety classifier represents the foundation pit safety grade value.
The invention further adopts the technical improvement scheme that:
parameter detection module design
The parameter detection module consists of a displacement sensor, a settlement sensor, a tilt sensor, 3 beat Delay line TDL (tapped Delay line), 3 GM (1,1) gray prediction models, an Elman neural network model, a wavelet neural network model, an ANFIS neural network model, 3 integration loops, a dynamic recursive wavelet neural network model and 3 LSTM neural network models, 2 integration operators S are connected in series to form 1 integration loop respectively, and 2 integration operator connecting ends of each integration loop and the output of the integration loop are used as 2 corresponding inputs of the dynamic recursive wavelet neural network model respectively; the outputs of the displacement sensor, the settlement sensor and the tilt sensor are respectively used as the input of 3 corresponding beat delay lines TDL, the values of the displacement sensor, the settlement sensor and the tilt sensor which are output by 3 beat delay lines TDL in a period of time are respectively used as the input of 3 corresponding GM (1,1) gray prediction models, the outputs of 3 GM (1,1) gray prediction models are respectively used as the input of an Elman neural network model, a wavelet neural network model and an ANFIS neural network model, the outputs of the Elman neural network model, the wavelet neural network model and the ANFIS neural network model are respectively used as the input of 1 corresponding integral loop and the 1 corresponding input of a dynamic recursive wavelet neural network model, and the 3 trapezoidal fuzzy numbers output by the dynamic recursive wavelet neural network model respectively represent the dynamic trapezoidal fuzzy numbers of the values of a period of time displacement sensor, the settlement sensor and the tilt sensor, and the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the tilting trapezoidal fuzzy number output by the dynamic recursive wavelet neural network model are respectively used as the input of 3 corresponding LSTM neural network models, and the 3 LSTM neural network models are output as the predicted values of the displacement trapezoidal fuzzy numbers, the settlement trapezoidal fuzzy numbers and the tilting trapezoidal fuzzy numbers and the output of the parameter detection module.
The invention further adopts the technical improvement scheme that:
the foundation pit safety classifier consists of 3 self-associative neural network fusion models, 3 beat Delay lines TDL (tapped Delay line) and an ESN (electronic stability network) neural network classifier, foundation pit displacement, foundation pit settlement and trapezoidal fuzzy numbers of foundation pit inclining output by a plurality of parameter detection modules are respectively used as input of the 3 self-associative neural network fusion models corresponding to the foundation pit safety classifier and displacement trapezoidal fuzzy numbers output by the 3 self-associative neural network fusion models, the fusion values of the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number are respectively used as the input of 3 corresponding beat delay lines TDL, the fusion values of the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number output by the 3 beat delay lines TDL within a period of time are used as the input of an ESN (electronic stability network) classifier, and the trapezoidal fuzzy number output by the ESN classifier represents the safety grade value of the foundation pit; according to the engineering practice of foundation pit safety, the ESN neural network classifier divides the foundation pit safety into 5 different trapezoid fuzzy numbers which correspond to general safety, comparative safety, very safety, unsafe and very unsafe, a corresponding relation table of 5 trapezoid fuzzy numbers and 5 degree levels of the foundation pit safety is built, the similarity between the trapezoid fuzzy number output by the ESN neural network classifier and the 5 trapezoid numbers representing the 5 safety levels is calculated, and the foundation pit safety level corresponding to the trapezoid fuzzy number with the maximum similarity is determined as the foundation pit safety level.
Compared with the prior art, the invention has the following obvious advantages:
the difference between the dynamic recursive wavelet neural network model and the common static wavelet neural network model lies in that the dynamic recursive wavelet neural network model is provided with two associated layer nodes which play a role in storing the internal state of a network, and a self-feedback loop with fixed gain is added on the two associated layer nodes to enhance the memory performance of time sequence characteristic information, so that the tracking precision of the evolution track of trapezoidal fuzzy numbers of displacement, settlement and inclination of a foundation pit is enhanced to ensure better prediction precision; a group of connection weights are added between the first association layer node and the output layer node of the dynamic recursive wavelet neural network model to enhance the dynamic approximation capability of the dynamic recursive wavelet neural network model and improve the accuracy of trapezoidal fuzzy number prediction of foundation pit displacement, settlement and tilting.
The Elman neural network model is generally divided into 4 layers, namely an input layer, an intermediate layer (hidden layer), a carrying layer and an output layer, wherein the input layer, the hidden layer and the output layer are connected similarly to a feedforward network, a unit of the input layer only plays a role in signal transmission, and a unit of the output layer plays a role in linear weighting. The transfer function of the hidden layer unit can adopt a linear or nonlinear function, and the accepting layer is also called a context layer or a state layer, is used for memorizing the output values of foundation pit displacement, settlement and tilting at the previous moment of the hidden layer unit, and can be regarded as a primary delay operator. The Elman neural network model is characterized in that the output of the hidden layer is self-connected to the input of the hidden layer through the delay and storage of the bearing layer, the self-connection mode enables the output to have sensitivity to the historical state data of the displacement, the settlement and the tilting of the foundation pit, and the addition of the internal feedback network increases the capability of the network for processing dynamic information, so that the purpose of dynamic modeling of the trapezoidal fuzzy number of the displacement, the settlement and the tilting of the foundation pit is achieved. The Elman neural network model regression neural network is characterized in that the output of the hidden layer is self-connected to the input of the hidden layer through the delay and storage of the structural unit, the self-connection mode ensures that the hidden layer has sensitivity to the data of the historical states of displacement, settlement and tilting of the foundation pit, the addition of the internal feedback network increases the information processing capacity of the network for processing the displacement, settlement and tilting of the dynamic foundation pit, and the dynamic process modeling of the displacement, settlement and tilting of the foundation pit is facilitated; the Elman neural network prediction model fuses future prediction foundation pit displacement, settlement and tilting information and past prediction network information by utilizing feedback connection of dynamic neurons of an associated layer, so that the memory of the network to time series characteristic information is enhanced, and the accuracy and robustness of foundation pit displacement, settlement and tilting prediction are improved.
Thirdly, the ESN neural network classifier designs a network hidden layer into a sparse network consisting of a plurality of neurons, achieves the function of memorizing the displacement, the settlement and the inclination data of the foundation pit by adjusting the characteristics of the internal weight of the network, contains a large number of sparsely connected neurons in an internal dynamic reserve pool, contains the running state of the system, and has the functions of memorizing the displacement, the settlement and the inclination of the foundation pit in a short term, ensures the stability of the internal recursive network of the reserve pool by presetting the spectral radius of the internal connection weight matrix of the ESN neural network classifier, and improves the stability and the accuracy of the safety classification of the foundation pit.
And fourthly, the ESN neural network classifier inherits the state of the reserve pool at the current moment to the state at the previous moment, has a transient memory characteristic to the historical data of the trapezoidal fuzzy number of displacement, settlement and inclination of the foundation pit, and research results show that the ESN neural network with the historical memory has a good classification effect. The ESN neural network classifier has the characteristics of high precision, high accuracy, high timeliness and stability, and can be used as a means for rapidly and effectively classifying the safety of the foundation pit; as a novel dynamic recurrent neural network, the ESN neural network classifier adopts a linear regression method to establish a model, avoids the problems that the traditional neural network is low in convergence speed and easy to get into local minimum, simplifies the complexity of the training process, and achieves the purpose of efficient safe classification of the foundation pit.
The most representative low-dimensional subspace reflecting the system structure is extracted from the high-dimensional parameter space of the predicted value of the trapezoidal fuzzy number of the foundation pit displacement, the settlement and the inclination which is input by the associative neural network fusion model, meanwhile, noise and measurement errors in the input data of the trapezoidal fuzzy number of the foundation pit displacement, the settlement and the inclination are effectively filtered out, decompression of the data of the trapezoidal fuzzy number of the foundation pit displacement, the settlement and the inclination is realized through the bottleneck layer, the demapping layer and the output layer, and the front compressed information is restored to the parameter values of the trapezoidal fuzzy number of each foundation pit displacement, settlement and inclination, so that reconstruction of the input data of the trapezoidal fuzzy number of each foundation pit displacement, settlement and inclination is realized, and the accuracy and the stability of the trapezoidal fuzzy number of the foundation pit displacement, settlement and inclination are improved.
Sixthly, the scientificity and the reliability of the ESN neural network classifier of the invention, the ESN neural network classifier of the invention classifies the safety level of the trapezoidal fuzzy number of the displacement, the settlement and the inclination of the foundation pit, according to the engineering practical experience of the foundation pit displacement, settlement and roll safety control, the ESN neural network classifier quantifies the safety of influencing the foundation pit displacement, settlement and roll safety into safety levels, the foundation pit safety is divided into five grades of general safety, comparative safety, very safety, insecurity and very insecurity through the trapezoidal fuzzy number, 5 safety grades are respectively corresponding to 5 different trapezoidal fuzzy numbers, the similarity of the trapezoidal fuzzy number output by the ESN neural network classifier and the 5 trapezoidal fuzzy numbers representing the 5 safety grades is calculated, and determining the safety level corresponding to the trapezoidal fuzzy number with the maximum similarity as the safety level of the foundation pit, thereby realizing the dynamic performance and scientific classification of the safety level of the foundation pit.
And seventhly, because the primary and secondary variable quantities of the foundation pit parameter predicted value are introduced through the 3 integration loops, the dynamic recursive wavelet neural network model is applied to the time sequence prediction of the nonlinear parameters to convert the detected parameters into trapezoidal fuzzy numbers according to the predicted values of the detected parameters and the influence of the variable quantities, so that the prediction precision and the self-adaptive capacity are better, and the generalization capacity of the dynamic recursive wavelet neural network model is improved.
Drawings
FIG. 1 is a foundation pit parameter acquisition platform of the present invention;
FIG. 2 is a foundation pit security big data processing subsystem of the present invention;
FIG. 3 is a detection node according to the present invention;
FIG. 4 is a gateway node of the present invention;
fig. 5 shows the site monitoring software according to the present invention.
Detailed Description
The technical scheme of the invention is further described by combining the attached drawings 1-5:
design of overall system function
The invention realizes the detection of foundation pit parameters and the classification of foundation pit safety, and the system consists of a foundation pit parameter acquisition platform and a foundation pit parameter big data processing subsystem. The foundation pit parameter acquisition platform comprises a detection node, a gateway node, a field monitoring end, a cloud platform and a mobile end App of foundation pit parameters, and the detection node and the gateway node realize wireless communication between the detection node and the gateway node by constructing a LoRa communication network; the detection node sends the detected foundation pit parameters to the field monitoring terminal through an RS232 interface of the gateway node and sorts the data of the sensor and the safety of the foundation pit; the gateway node realizes bidirectional transmission of foundation pit parameter information between the NB-IoT and the cloud platform and between the cloud platform and the mobile terminal App through the 5G network, and bidirectional transmission of foundation pit information between the gateway node and the field monitoring terminal is realized through the RS232 interface. The structure of the foundation pit parameter acquisition platform is shown in figure 1.
Second, design of detection node
A large number of detection nodes 1 are used as foundation pit parameter sensing terminals, and information is bidirectionally transmitted between the detection nodes and the gateway node through an LoRa communication network. The detection node comprises sensors for collecting displacement, settlement, inclination and deflection of the foundation pit, corresponding signal conditioning circuits, an MSP430 microprocessor and an SX1278 radio frequency module; the software of the detection node mainly realizes the collection and pretreatment of communication and foundation pit parameters. The software is designed by adopting a C language program, so that the compatibility degree is high, the working efficiency of software design and development is greatly improved, and the reliability, readability and transportability of program codes are enhanced. The structure of the detection node is shown in fig. 3.
Third, gateway node design
The gateway node comprises an SX1278 radio frequency module, an NB-IoT module, an MSP430 single chip microcomputer and an RS232 interface, the SX1278 radio frequency module is used for realizing an LoRa communication network between the gateway node and the detection node, the NB-IoT is used for realizing data bidirectional interaction between the gateway and the cloud platform, and the RS232 interface is connected with the field monitoring terminal to realize information interaction between the gateway and the field monitoring terminal.
Site monitoring end software
The field monitoring end is an industrial control computer, mainly realizes the collection of foundation pit parameters and the safety classification of the foundation pit, realizes the information interaction with the gateway node, and mainly has the functions of communication parameter setting, data analysis and data management and a foundation pit parameter big data processing subsystem. The foundation pit parameter big data processing subsystem comprises a plurality of parameter detection modules and a foundation pit safety classifier. The structure of the big data processing subsystem of the foundation pit parameters is shown in figure 2. The management software selects Microsoft Visual + +6.0 as a development tool, calls an Mscomm communication control of a system to design a communication program, and the functions of the field monitoring end software are shown in figure 5.
The design of the big data processing subsystem of the foundation pit parameters is as follows:
1. parameter detection module design
The parameter detection module consists of a displacement sensor, a settlement sensor, a tilt sensor, 3 beat Delay line TDL (tapped Delay line), 3 GM (1,1) gray prediction models, an Elman neural network model, a wavelet neural network model, an ANFIS neural network model, 3 integration loops, a dynamic recursive wavelet neural network model and 3 LSTM neural network models, wherein each 2 integration operators S are connected in series to form 1 integration loop respectively, and 2 integration operator connecting ends of each integration loop and the output of the integration loop are used as 2 corresponding inputs of the dynamic recursive wavelet neural network model respectively; the outputs of the displacement sensor, the settlement sensor and the tilt sensor are respectively used as the inputs of 3 corresponding beat delay lines TDL, the displacement sensor value, the settlement sensor value and the tilt sensor value of a period of time output by 3 beat delay lines TDL are respectively used as the inputs of 3 corresponding GM (1,1) gray prediction models, the outputs of 3 GM (1,1) gray prediction models are respectively used as the inputs of an Elman neural network model, a wavelet neural network model and an ANFIS neural network model, the outputs of the Elman neural network model, the wavelet neural network model and the ANFIS neural network model are respectively used as the corresponding 1 integral loop input and 1 corresponding input of a dynamic recursive wavelet neural network model, and the 3 trapezoid fuzzy numbers output by the dynamic recursive wavelet neural network model respectively represent the dynamic trapezoid fuzzy numbers of the values of the displacement sensor, the settlement sensor and the tilt sensor of a period of time, wherein, 1 trapezoidal fuzzy number is [ a, b, c, d ], a, b, c and d respectively represent the minimum value, maximum value and maximum value of 1 kind of measuring sensor output in the displacement sensor, the settlement sensor and the tilting sensor, the dynamic trapezoidal fuzzy values of the displacement sensor, the settlement sensor and the tilting sensor output by the dynamic recursive wavelet neural network model are respectively used as the input of the corresponding 3 LSTM neural network models, and the 3 LSTM neural network models are output as the predicted values of the trapezoidal fuzzy numbers of displacement, settlement and tilting and the output of the parameter detection module. The design processes of the GM (1,1) gray prediction model, the Elman neural network model, the wavelet neural network model prediction model, the ANFIS neural network model and the dynamic recursive wavelet neural network model are as follows: the modeling process of the GM (1,1) gray prediction model is that original data of irregular displacement, settlement and heeling series of foundation pits are accumulated to obtain a generation sequence with stronger regularity, modeling is carried out, data obtained by the generation model is accumulated to obtain a predicted value of the original data, then prediction is carried out, and the assumption is that the original number of parameters to be predicted is as follows:
x(0)＝(x(0)(1),x(0)(2),…x(0)(n)) (1)
the new sequence generated after the first order accumulation is: x is the number of(1)＝(x(1)(1),x(1)(2),…x(1)(n)) (2)
Wherein:
then x(1)The sequence has an exponential growth law, i.e. satisfies the first order linear differential equation:
in the formula, a becomes the developing gray number which reflects x(1)And x(0)The development trend of (1); u is the endogenous control gray number, and reflects the change relationship among data. Solving the differential equation of the above formula yields x(1)The predicted value of (A) is:
obtaining an original sequence x by the accumulative reduction of the following formula(0)The grey prediction model of (a) is:
by constructing a gray prediction GM (1,1) model, the prediction of the displacement, the settlement and the inclination of the foundation pit can be realized, and the GM (1,1) gray prediction model for predicting the displacement, the settlement and the inclination series values of the foundation pit is constructed.
And 3 GM (1,1) grey prediction models for respectively predicting the displacement, the settlement and the inclination of the foundation pit are output as the input of the Elman neural network model, and the output of the Elman neural network model is output as the corresponding 1 integral loop input and 1 corresponding input of the dynamic recursive wavelet neural network model. The Elman neural network model can be regarded as a forward neural network with a local memory unit and a local feedback connection, and a special association layer is arranged besides a hidden layer; the association layer receives the feedback signal from the hidden layer, and each hidden layer node has a corresponding association layer node connection. The association layer takes the hidden layer state at the previous moment and the network input at the current moment as the input of the hidden layer, which is equivalent to state feedback. The transfer function of the hidden layer is generally a Sigmoid function, the output layer is a linear function, and the associated layer is also a linear function. In order to effectively solve the problem of approximation accuracy in foundation pit displacement, settlement and heeling prediction, the function of the associated layer is enhanced. Setting the number of an input layer, an output layer and a hidden layer of the Elman neural network model as m, n and r respectively; w1, w2，w3And w4Respectively representing the connection weight matrixes from the structural layer unit to the hidden layer, from the input layer to the hidden layer, from the hidden layer to the output layer and from the structural layer to the output layer, wherein the expressions of the hidden layer, the associated layer and the output layer of the Elman neural network model are respectively as follows:
cp(k)＝xp(k-1) (7)
and the output of the grey prediction model of 3 GM (1,1) for respectively predicting the displacement, the settlement and the inclination of the foundation pit is used as the input of the prediction model of the wavelet neural network model, and the output of the prediction model of the wavelet neural network model is used as the input of 1 corresponding integral loop and 1 corresponding input of the dynamic recursive wavelet neural network model. A wavelet Neural network model WNN (wavelet Neural networks) theoretical basis is a feedforward network which is provided by taking a wavelet function as an excitation function of a neuron and combining an artificial Neural network, wherein the expansion and contraction, the translation factor and the connection weight of wavelets in the wavelet Neural network model are adaptively adjusted in the optimization process of an error energy function. An input signal of the wavelet neural network model can be represented as an input one-dimensional vector xi(i ═ 1,2, …, n), the output signal is denoted yk(k ═ 1,2, …, m), and the calculation formula of the predicted value of the output layer of the wavelet neural network model prediction model is as follows:
in the formula omegaijInputting the connection weight between the i node of the layer and the j node of the hidden layer,
as wavelet basis functions, bjIs a shift factor of the wavelet basis function, ajScale factor, omega, of wavelet basis functionsjkAnd the connection weight between the j node of the hidden layer and the k node of the output layer is shown. The correction algorithm of the weight and the threshold of the wavelet neural network model prediction model in the patent adopts a gradient correction method to update the network weight and the wavelet basis function parameters, so that the output of the wavelet neural network model prediction model is continuously close to the expected output.
The output of the 3 GM (1,1) grey prediction models for respectively predicting the displacement, the subsidence and the heeling of the foundation pit is used as the input of the ANFIS neural network model, and the output of the ANFIS neural network model is used as the corresponding 1 integral loop input and the 1 corresponding input of the dynamic recursive wavelet neural network model. The ANFIS neural network model is an Adaptive Fuzzy Inference System ANFIS based on a neural network, also called an Adaptive neural-Fuzzy Inference System (Adaptive neural-Fuzzy Inference System), and organically combines the neural network and the Adaptive Fuzzy Inference System, thereby not only playing the advantages of the neural network and the Adaptive Fuzzy Inference System, but also making up the respective defects. The fuzzy membership function and the fuzzy rule in the ANFIS neural network model are obtained by learning known historical data of a large number of foundation pit displacements, subsidences and inclinations, and the ANFIS neural network model is mainly characterized by a data-based modeling method instead of being arbitrarily given based on experience or intuition. The ANFIS neural network model mainly comprises the following operation steps of a layer 1, fuzzifying numerical values output by an input 3 GM (1,1) gray prediction model for respectively predicting foundation pit displacement, settlement and inclination, wherein the corresponding output of each node can be represented as:
the formula n is the number of each input membership function, and the membership function adopts a Gaussian membership function.
And 2, realizing rule operation, outputting the applicability of the rule, and multiplying the rule operation of the ANFIS neural network model by adopting multiplication.
And 3, normalizing the applicability of each rule:
and 4, at the layer 4, the transfer function of each node is a linear function and represents a local linear model, and the output of each self-adaptive node i is as follows:
and 5, a single node of the layer is a fixed node, and the output of the ANFIS neural network model is calculated as follows:
the condition parameters determining the shape of the membership function and the conclusion parameters of the inference rule in the ANFIS neural network model can be trained through a learning process. The parameters are adjusted by an algorithm combining a linear least square estimation algorithm and gradient descent. In each iteration of the ANFIS neural network model, firstly, input signals are transmitted along the network in the forward direction until the layer 4, the conclusion parameters are adjusted by adopting a least square estimation algorithm, and the signals are continuously transmitted along the network in the forward direction until the output layer. The ANFIS neural network model reversely propagates the obtained error signals along the network, and the condition parameters are updated by a gradient method. By adjusting the given condition parameters in the ANFIS neural network model in this way, the global optimum point of the conclusion parameters can be obtained, so that the dimension of the search space in the gradient method can be reduced, and the convergence rate of the ANFIS neural network model parameters can be increased.
The difference between the dynamic recursive wavelet neural network model and the common static wavelet neural network model is that the dynamic recursive wavelet neural network model is provided with two associated layer nodes which play a role in storing the internal state of the network, and a self-feedback loop with fixed gain is added on the two associated layer nodes to enhance the memory performance of time sequence characteristic information, so that the tracking precision of the evolution track of the trapezoidal fuzzy number parameters of displacement, settlement and inclination of a foundation pit is enhanced to ensure better prediction precision; the first associated layer node is used for storing the state of the phase point of the hidden layer node at the previous moment and transmitting the state to the hidden layer node at the next moment; the second correlation layer node is used for storing the state of the phase point of the output layer node at the previous moment and transmitting the state to the hidden layer node at the next moment; feedback information of neurons of a hidden layer and an output layer can influence dynamic processing capacity of dynamic recursive wavelet neural network model prediction, and two associated layers belong to state feedback inside the dynamic recursive wavelet neural network model to form dynamic recursive wavelet neural network modelThe special dynamic memory performance of the recursion of the recursive wavelet neural network model improves the accuracy and the dynamic performance of the dynamic recursive wavelet neural network model; a group of connection weights are added between the first association layer node and the output layer node of the dynamic recursive wavelet neural network model to enhance the dynamic approximation capability of the dynamic recursive wavelet neural network model and improve the prediction precision of trapezoidal fuzzy numbers of foundation pit displacement, settlement and tilting. A wavelet Neural network model WNN (wavelet Neural networks) theoretical basis is a feedforward network which is provided by taking a wavelet function as an excitation function of a neuron and combining an artificial Neural network, wherein the expansion and contraction, the translation factor and the connection weight of wavelets in the wavelet Neural network model are adaptively adjusted in the optimization process of an error energy function. An input signal of the wavelet neural network model can be represented as an input one-dimensional vector xi(i ═ 1,2, …, n), the output signal is denoted yk(k ═ 1,2, …, m), and the calculation formula of the predicted value of the output layer of the wavelet neural network model prediction model is as follows:
in the formula omegaijInputting the connection weight between the i node of the layer and the j node of the hidden layer,
as wavelet basis functions, bjIs a shift factor of the wavelet basis function, ajScale factor, omega, of wavelet basis functionsjkThe connection weight between the node of the hidden layer j and the node of the output layer k. The weight and threshold correction algorithm of the dynamic recursive wavelet neural network model in the patent adopts a gradient correction method to update the network weight and the wavelet basis function parameters, so that the output of the dynamic recursive wavelet neural network model is continuously close to the expected output.
The 3 trapezoidal fuzzy numbers output by the dynamic recursive wavelet neural network model respectively represent dynamic trapezoidal fuzzy numbers of values of a displacement sensor, a settlement sensor and a roll sensor in a period of time, wherein 1 trapezoidal fuzzy number is [ a, b, c, d ]]And a, b, c and d respectively represent the minimum value, the maximum value and the maximum value of the output of 1 measuring sensor in the displacement sensor, the settlement sensor and the tilting sensor, the dynamic trapezoidal fuzzy values of the displacement sensor, the settlement sensor and the tilting sensor output by the dynamic recursive wavelet neural network model are respectively used as the input of the corresponding 3 LSTM neural network models, and the 3 LSTM neural network models are output as the predicted values of the trapezoidal fuzzy values of the displacement, the settlement and the tilting and the output of the parameter detection module. The temporal Recurrent Neural Network (RNN) model, which consists of Long Short Term Memory (LSTM) elements, is called the LSTM temporal recurrent neural network, also commonly referred to as the LSTM network. The LSTM neural network model introduces mechanisms of Memory cells (Memory cells) and hidden layer states (Cell states) to control the transfer of information between hidden layers. The memory unit of an LSTM neural network has 3 Gates (Gates) as Input Gate, forgetting Gate and Output Gate. The input door can control the addition or filtration of the fuzzy ladder-shaped number information of displacement, settlement and inclination of the foundation pit; the forgetting door can forget the information to be lost and retain the useful information of the fuzzy trapezoid number of the displacement, the settlement and the inclination of the foundation pit in the past; the output gate enables the memory unit to output only the information of the fuzzy ladder number of the displacement, the settlement and the inclination of the foundation pit related to the current time step. The 3 gate structures carry out operations such as matrix multiplication, nonlinear summation and the like in the memory unit, so that the memory still cannot be attenuated in continuous iteration. The long-short term memory unit (LSTM) structure unit is composed of a unit (Cell), an Input Gate (Input Gate), an Output Gate (Output Gate) and a forgetting Gate (Forget Gate). The unit is responsible for remembering values at arbitrary time intervals, and all three gates can be considered as conventional artificial neurons for computing a weighted sum of activation functions. The LSTM neural network model is a model capable of lasting long-term short-term memory and is suitable for work such as prediction of time sequences, the LSTM effectively prevents gradient disappearance during RNN training, and a long-term short-term memory (LSTM) network is a special RNN. The model can learn long-term information of fuzzy ladder numbers depending on foundation pit displacement, settlement and inclination, and simultaneously avoid the problem of gradient disappearance. Internal structure R of LSTM in neuronIn the neural node of the hidden layer of the NN, a structure called a Memory Cell (Memory Cell) is added for memorizing the information of the past fuzzy ladder number of the displacement, the subsidence and the inclination of the foundation pit, and three gate structures (Input, form and Output) are added for controlling the use of the historical information of the fuzzy ladder number of the displacement, the subsidence and the inclination of the foundation pit. The sequence of the fuzzy ladder-shaped numbers for inputting the displacement, the settlement and the inclination of the foundation pit is (x)1,x2,…,xT) The hidden layer state is (h)1,h2,…,hT) Then, time t has:
it＝sigmoid(Whiht-1+WxiXt) (16)
ft＝sigmoid(Whfht-1+WhfXt) (17)
ct＝ft⊙ct-1+it⊙tanh(Whcht-1+WxcXt) (18)
ot＝sigmoid(Whoht-1+WhxXt+Wcoct) (19)
ht＝ot⊙tanh(ct) (20)
wherein it、ft、otRepresenting input, forget and output doors, ctRepresenting cell units, Wh represents weight of recursive connections, Wx represents weight of input layer to hidden layer, and sigmoid and tanh are two activation functions. The method comprises the steps of firstly establishing an LSTM time recurrent neural network model, establishing a training set by utilizing preprocessed fuzzy trapezoidal number information data of foundation pit displacement, settlement and inclination, and training the model, wherein the LSTM neural network model considers the time sequence and nonlinearity of the fuzzy trapezoidal number information of foundation pit displacement, settlement and inclination and has higher prediction precision.
2. Design of foundation pit safety classifier
The foundation pit safety classifier consists of 3 self-associative neural network fusion models, 3 beat Delay lines TDL (tapped Delay line) and an ESN (electronic stability network) neural network classifier, wherein the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the tilting trapezoidal fuzzy number output by the parameter detection modules are respectively used as the input of the 3 corresponding self-associative neural network fusion models of the foundation pit safety classifier, and the displacement trapezoidal fuzzy numbers output by the 3 self-associative neural network fusion models, the fused values of the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number are respectively used as the input of 3 corresponding beat delay lines TDL, the fused values of the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number which are output by the 3 beat delay lines TDL within a period of time are used as the input of the ESN neural network classifier, and the trapezoidal fuzzy number output by the ESN neural network classifier represents the safety grade value of the foundation pit. The self-association neural network fusion model and the ESN neural network classifier are designed as follows: the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the tipping trapezoidal fuzzy number output by the multiple parameter detection modules are respectively used as the input of 3 corresponding self-association neural network fusion models of the foundation pit safety classifier, and the fusion values of the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the tipping trapezoidal fuzzy number output by the 3 self-association neural network fusion models are respectively used as the input of 3 corresponding beat delay lines TDL; an Auto-associative neural network fusion model (AANN), which is a feedforward neural network with a special structure, includes an input layer, a number of hidden layers and an output layer. The method comprises the steps of firstly compressing the input data information of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination through an input layer, a mapping layer and a bottleneck layer, extracting the most representative low-dimensional subspace reflecting the system structure from the high-dimensional parameter space of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination input by an associative neural network fusion model, effectively filtering out noise and measurement errors in the input data of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination, decompressing the data of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination through the bottleneck layer, the demapping layer and the output layer, and restoring the compressed information to the parameter values of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination, so that reconstruction of the input data of the trapezoidal fuzzy number of foundation pit displacement, settlement and inclination is realized. In order to achieve the purpose of information compression of trapezoidal fuzzy numbers of displacement, settlement and tilting of a foundation pit, the number of nodes of a bottleneck layer of a self-association neural network fusion model is obviously smaller than that of input layers, and in order to prevent simple single mapping between the input layers and the output layers, except that linear functions are adopted as excitation functions of the output layers, nonlinear excitation functions are adopted in other layers. In essence, the first layer of the hidden layer of the self-associative neural network fusion model is called as a mapping layer, and the node transfer function of the mapping layer can be an S-shaped function or other similar nonlinear functions; the second layer of the hidden layer is called a bottleneck layer, the dimension of the bottleneck layer is the minimum in the self-association neural network fusion model, the transfer function of the bottleneck layer can be linear or nonlinear, the bottleneck layer avoids the mapping relation that the one-to-one output and input are equal, the self-association neural network fusion model encodes and compresses the trapezoidal fuzzy number signals of foundation pit displacement, settlement and inclination to obtain a relevant model of input foundation pit displacement, settlement and inclination trapezoidal fuzzy number, and the relevant model is decoded and decompressed after the bottleneck layer to generate an estimated value of the predicted value input signal of the trapezoidal fuzzy number of the foundation pit displacement, settlement and inclination; the third layer or the last layer of the hidden layer is called a demapping layer, the node transfer function of the demapping layer is a generally nonlinear S-shaped function, and the self-associative neural network is trained by an error back propagation algorithm.
And 3, the fused values of the trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclination trapezoidal fuzzy number which are output by the time delay line TDL are used as the input of the ESN neural network classifier, and the trapezoidal fuzzy number output by the ESN neural network classifier represents the safety grade value of the foundation pit. An ESN (Echo state network) is a novel dynamic neural network, has all the advantages of the dynamic neural network, and can better adapt to nonlinear system identification compared with a common dynamic neural network because the Echo state network introduces a reserve pool concept. The reserve pool is a randomly connected reserve pool which is formed by converting a part connected among traditional dynamic neural networks, and the whole learning process is a process of learning how to connect the reserve pool. The "pool" is actually a randomly generated large-scale recursive structure in which the interconnection of neurons is sparse, usually denoted SD as the percentage of interconnected neurons in the total number of neurons N. The state equation of the ESN neural network classifier is as follows:
wherein W is the state variable of the neural network, WinInput variables of the ESN neural network classifier; wbackConnecting a weight matrix for an output state variable of the ESN neural network classifier; x (n) represents the internal state of the ESN neural network classifier; woutA connection weight matrix among a core reserve pool of the ESN neural network classifier, the input of the neural network and the output of the neural network;
is the output deviation of the ESN neural network classifier or can represent noise; f ═ f [ f1,f2,…,fn]N activation functions for neurons within the "pool of stores"; f. ofiIs a hyperbolic tangent function; f. ofoutIs the epsilon output functions of the ESN neural network classifier. The trapezoid fuzzy number output by the ESN neural network classifier represents a safety grade value of the foundation pit; according to the engineering practice of foundation pit safety, the ESN neural network classifier divides the foundation pit safety into 5 different trapezoid fuzzy numbers which correspond to general safety, comparative safety, very safety, insecurity and very insecurity, calculates the similarity between the trapezoid fuzzy number output by the ESN neural network classifier and the 5 trapezoid numbers representing 5 safety levels, wherein the foundation pit safety level corresponding to the trapezoid fuzzy number with the maximum similarity is determined as the foundation pit safety level. And (3) constructing a corresponding relation table of 5 trapezoidal fuzzy numbers and 5 degree grades of foundation pit safety, wherein the corresponding relation between the foundation pit safety grade and the trapezoidal fuzzy numbers is shown in a table 1.
TABLE 1 Foundation pit safety grade and trapezoidal fuzzy number corresponding relation table
| Serial number | Level of security | Fuzzy number of |
| 1 | General safety | (0.0，0.05，0.15，0.3) |
| 2 | Is relatively safe | (0.1，0.15，0.3,0.4) |
| 3 | Is very safe | (0.3，0.35，0.45，0.7) |
| 4 | Is not safe | (0.6，0.75，0.8,0.9) |
| 5 | Is very unsafe | (0.8，0.85,0.9,1.0) |
Design example of foundation pit parameter acquisition platform
According to the actual condition of the foundation pit parameter acquisition platform, the system is provided with a plane layout installation diagram of a detection node, a gateway node and a field monitoring end of the foundation pit parameter acquisition platform, wherein sensors of the detection node are arranged in all directions of the foundation pit in a balanced manner according to the detection requirement, and the foundation pit parameters are acquired through the system.
The technical means disclosed in the invention scheme are not limited to the technical means disclosed in the above embodiments, but also include the technical scheme formed by any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and such improvements and modifications are also considered to be within the scope of the present invention.
Claims (1)
1. The utility model provides a foundation ditch big data detecting system which characterized in that: the detection system comprises a foundation pit parameter acquisition platform and a foundation pit parameter big data processing subsystem, and realizes foundation pit parameter detection and foundation pit safety prediction;
the foundation pit parameter big data processing subsystem comprises a parameter detection module and a foundation pit safety classifier, wherein a displacement trapezoidal fuzzy number, a settlement trapezoidal fuzzy number and a tilting trapezoidal fuzzy number output by the parameter detection module are respectively used as the input of a corresponding self-association neural network fusion model of the foundation pit safety classifier, and the trapezoidal fuzzy number output by the foundation pit safety classifier represents a foundation pit safety grade value;
the parameter detection module comprises a displacement sensor, a settlement sensor, a tilt sensor, a Time Delay Line (TDL), a gray prediction model (GM (1, 1)), an Elman neural network model, a wavelet neural network model, an ANFIS neural network model, an integration loop, a dynamic recursive wavelet neural network model and an LSTM neural network model, 2 integration operators S are connected in series to respectively form 1 integration loop, and 2 integration operator connecting ends of each integration loop and the output of the integration loop are respectively used as the corresponding input of the dynamic recursive wavelet neural network model; the outputs of the displacement sensor, the settlement sensor and the tilt sensor are respectively used as the input of a corresponding beat delay line TDL, the displacement sensor value, the settlement sensor value and the tilt sensor value which are output by the beat delay line TDL for a period of time are respectively used as the input of a corresponding GM (1,1) gray prediction model, the outputs of the GM (1,1) gray prediction model are respectively used as the inputs of an Elman neural network model, a wavelet neural network model and an ANFIS neural network model, the outputs of the Elman neural network model, the wavelet neural network model and the ANFIS neural network model are respectively used as the corresponding 1 integral loop input and the corresponding 1 input of a dynamic recursive wavelet neural network model, and the trapezoidal fuzzy numbers output by the dynamic recursive wavelet neural network model respectively represent the dynamic trapezoidal fuzzy numbers of the values of the displacement sensor, the settlement sensor and the tilt sensor for a period of time, the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the tilting trapezoidal fuzzy number output by the dynamic recursive wavelet neural network model are respectively used as the input of the corresponding LSTM neural network model, and the output of the LSTM neural network model is used as the predicted values of the displacement trapezoidal fuzzy numbers, the settlement trapezoidal fuzzy numbers and the tilting trapezoidal fuzzy numbers and the output of the parameter detection module;
the foundation pit safety classifier comprises an auto-associative neural network fusion model, a beat delay line TDL and an ESN neural network classifier, foundation pit displacement, foundation pit settlement and foundation pit inclining trapezoidal fuzzy numbers output by a plurality of parameter detection modules are respectively used as the input of the corresponding auto-associative neural network fusion model of the foundation pit safety classifier, the fusion values of the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclining trapezoidal fuzzy number output by the auto-associative neural network fusion model are respectively used as the input of the corresponding beat delay line TDL, the fusion value of the displacement trapezoidal fuzzy number, the settlement trapezoidal fuzzy number and the inclining trapezoidal fuzzy number output by the beat delay line TDL for a period of time is used as the input of the ESN neural network classifier, and the trapezoidal fuzzy number output by the ESN neural network classifier represents a foundation pit safety grade value;
the ESN neural network classifier divides the foundation pit safety into 5 different trapezoid fuzzy numbers which are generally safe, relatively safe, very safe, unsafe and very unsafe and correspond to different degrees, a corresponding relation table of the 5 trapezoid fuzzy numbers and 5 degree levels of the foundation pit safety is constructed, the similarity between the trapezoid fuzzy number output by the ESN neural network classifier and the 5 trapezoid numbers representing the 5 safety levels is calculated, wherein the foundation pit safety level corresponding to the trapezoid fuzzy number with the maximum similarity is determined as the foundation pit safety level;
the foundation pit parameter acquisition platform comprises a plurality of detection nodes, gateway nodes, an on-site monitoring end, a cloud platform and a mobile end App of foundation pit parameters, and wireless communication between the detection nodes and the gateway nodes is realized by constructing a LoRa communication network between the detection nodes and the gateway nodes; the detection node sends the detected foundation pit parameters to an on-site monitoring end through a communication interface of the gateway node, and the on-site monitoring end manages the foundation pit parameters and classifies the foundation pit safety; the gateway node realizes bidirectional transmission of the foundation pit parameters between the communication module and the cloud platform and between the cloud platform and the mobile terminal App through the wireless network, and the gateway node realizes bidirectional transmission of the foundation pit parameters between the gateway node and the field monitoring terminal through the communication interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040403.9A CN112911532B (en) | 2021-01-13 | 2021-01-13 | Foundation pit big data detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040403.9A CN112911532B (en) | 2021-01-13 | 2021-01-13 | Foundation pit big data detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112911532A CN112911532A (en) | 2021-06-04 |
| CN112911532B true CN112911532B (en) | 2022-06-14 |
Family
ID=76112662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110040403.9A Active CN112911532B (en) | 2021-01-13 | 2021-01-13 | Foundation pit big data detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112911532B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407545A (en) * | 2016-09-12 | 2017-02-15 | 辽宁工程技术大学 | Soft soil foundation ditch safety evaluation method based on fuzzy comprehensive judgment method |
| CN108830012A (en) * | 2018-06-29 | 2018-11-16 | 上海勘察设计研究院(集团)有限公司 | A kind of malformation prediction technique excavated based on total factor |
| CN111473768A (en) * | 2020-03-20 | 2020-07-31 | 淮阴工学院 | Building safety intelligent detection system |
| CN111709592A (en) * | 2020-08-20 | 2020-09-25 | 北京大成国测科技有限公司 | Deep foundation pit deformation prediction method and system based on neural network and rough set classification |
| KR20200123537A (en) * | 2019-04-22 | 2020-10-30 | 공주대학교 산학협력단 | Method for detecting sinkhole using deep learning and data association and sinkhole detecting system using it |
-
2021
- 2021-01-13 CN CN202110040403.9A patent/CN112911532B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407545A (en) * | 2016-09-12 | 2017-02-15 | 辽宁工程技术大学 | Soft soil foundation ditch safety evaluation method based on fuzzy comprehensive judgment method |
| CN108830012A (en) * | 2018-06-29 | 2018-11-16 | 上海勘察设计研究院(集团)有限公司 | A kind of malformation prediction technique excavated based on total factor |
| KR20200123537A (en) * | 2019-04-22 | 2020-10-30 | 공주대학교 산학협력단 | Method for detecting sinkhole using deep learning and data association and sinkhole detecting system using it |
| CN111473768A (en) * | 2020-03-20 | 2020-07-31 | 淮阴工学院 | Building safety intelligent detection system |
| CN111709592A (en) * | 2020-08-20 | 2020-09-25 | 北京大成国测科技有限公司 | Deep foundation pit deformation prediction method and system based on neural network and rough set classification |
Non-Patent Citations (1)
| Title |
|---|
| 适用于砂土基坑变形分析的土体本构模型应用;程丽娟等;《人民长江》;20191228;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112911532A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112904756B (en) | Pipe network big data detection system | |
| Madhiarasan et al. | Analysis of artificial neural network: architecture, types, and forecasting applications | |
| CN113126676B (en) | Livestock and poultry house breeding environment parameter intelligent control system | |
| CN111461187B (en) | Intelligent building settlement detection system | |
| CN115016276B (en) | Intelligent water content adjustment and environment parameter Internet of things big data system | |
| CN112857658B (en) | Pressure detection system based on cloud platform | |
| CN113219871B (en) | Curing room environmental parameter detecting system | |
| CN115630101B (en) | Hydrologic parameter intelligent monitoring and water resource big data management system | |
| CN114548482A (en) | Creep type landslide kinetic energy change rate face-slip early warning method | |
| CN114397043A (en) | Multi-point temperature intelligent detection system | |
| CN116205513A (en) | Ship lock engineering monitoring method and system based on ISSA (integrated service and architecture) optimized BP (back propagation) network | |
| CN112911533B (en) | Temperature detection system based on remove end App | |
| Wei et al. | A three-stage multi-objective heterogeneous integrated model with decomposition-reconstruction mechanism and adaptive segmentation error correction method for ship motion multi-step prediction | |
| CN114911185A (en) | Security big data Internet of things intelligent system based on cloud platform and mobile terminal App | |
| Wang et al. | A DES-BDNN based probabilistic forecasting approach for step-like landslide displacement | |
| CN112911532B (en) | Foundation pit big data detection system | |
| CN114358244B (en) | Big data intelligent detection system of pressure based on thing networking | |
| CN115343784A (en) | Local air temperature prediction method based on seq2seq-attention model | |
| CN114995248A (en) | Intelligent maintenance and environmental parameter big data internet of things system | |
| Vrochidou et al. | Assessment and localization of structural damage in r/c structures through intelligent seismic signal processing | |
| CN114386672A (en) | Environment big data Internet of things intelligent detection system | |
| CN113255963A (en) | Road surface use performance prediction method based on road element splitting and deep learning model LSTM | |
| CN115905938B (en) | Storage tank safety monitoring method and system based on Internet of things | |
| Zhang et al. | Landslide displacement prediction based on optimized empirical mode decomposition and deep bidirectional long short-term memory network | |
| CN111473768A (en) | Building safety intelligent detection system |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230224 Address after: Room 103, Building 6, No. 16, Taizhou Road, Shinan District, Qingdao, Shandong 266071 Patentee after: Liu Peng Address before: 223005 Jiangsu Huaian economic and Technological Development Zone, 1 East Road. Patentee before: HUAIYIN INSTITUTE OF TECHNOLOGY |
|
| TR01 | Transfer of patent right |