CN116519055B - Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system - Google Patents
Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system Download PDFInfo
- Publication number
- CN116519055B CN116519055B CN202310490445.1A CN202310490445A CN116519055B CN 116519055 B CN116519055 B CN 116519055B CN 202310490445 A CN202310490445 A CN 202310490445A CN 116519055 B CN116519055 B CN 116519055B
- Authority
- CN
- China
- Prior art keywords
- slurry
- pipeline
- particles
- result
- model
- 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
- 239000002002 slurry Substances 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000002245 particle Substances 0.000 claims abstract description 75
- 238000001514 detection method Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000004088 simulation Methods 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 230000008878 coupling Effects 0.000 claims abstract description 7
- 238000010168 coupling process Methods 0.000 claims abstract description 7
- 238000005859 coupling reaction Methods 0.000 claims abstract description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 15
- 102100021807 ER degradation-enhancing alpha-mannosidase-like protein 1 Human genes 0.000 claims description 9
- 239000003795 chemical substances by application Substances 0.000 claims description 9
- 239000012530 fluid Substances 0.000 claims description 9
- 230000002068 genetic effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 101000895701 Homo sapiens ER degradation-enhancing alpha-mannosidase-like protein 1 Proteins 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 229910000278 bentonite Inorganic materials 0.000 claims description 3
- 239000000440 bentonite Substances 0.000 claims description 3
- SVPXDRXYRYOSEX-UHFFFAOYSA-N bentoquatam Chemical compound O.O=[Si]=O.O=[Al]O[Al]=O SVPXDRXYRYOSEX-UHFFFAOYSA-N 0.000 claims description 3
- 230000003749 cleanliness Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000006260 foam Substances 0.000 claims description 3
- 239000012535 impurity Substances 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 239000013049 sediment Substances 0.000 claims description 3
- 239000002893 slag Substances 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 3
- 230000005641 tunneling Effects 0.000 abstract description 4
- 238000010276 construction Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000001028 reflection method Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/12—Devices for removing or hauling away excavated material or spoil; Working or loading platforms
- E21D9/13—Devices for removing or hauling away excavated material or spoil; Working or loading platforms using hydraulic or pneumatic conveying means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses an intelligent early warning method for pipeline blockage of a slurry shield slurry circulation system, which comprises the following steps: firstly, detecting the flow field state in the pipeline and the movement track of particles by using a detection device, calculating the performance parameters of the model by using coupling simulation, and constructing a training data set together with the detection result of the detection device. Secondly, constructing a proxy model, substituting a training sample set into the proxy model for training, optimizing a weight threshold of the proxy model by using an optimization algorithm in the training process, evaluating model precision, storing the model after meeting precision requirements, predicting, and adjusting and early warning by a control system according to a prediction result so as to achieve the intelligent early warning effect of a muddy water circulating system pipeline and improve tunneling efficiency.
Description
Technical Field
The invention belongs to the technical field of intelligent monitoring of slurry shields, and particularly relates to an intelligent early warning method for pipeline blockage of a slurry circulation system of a slurry shield.
Background
Along with the acceleration of the urban process and the continuous expansion of traffic infrastructure construction, the slurry shield is also widely applied, wherein a slurry circulating system is used as an important component of the slurry balance shield machine, and soil particles are transmitted in a pipeline conveying mode, so that the slurry can be recycled, the construction efficiency of the shield machine is determined by the configuration of the slurry circulating system, and the working stability of the slurry circulating system has important significance for efficient tunneling and safe construction of the shield.
Because the slurry carries solid particles with different components such as gravel, pebbles and the like, the slurry circulation system is extremely easy to cause particle accumulation in a pipeline and further cause pipeline blockage. Once the pipeline is blocked, the muddy water circulating system is seriously influenced, and the pipeline pressure is possibly too high, pipe bursting and the like are caused, so that abnormal shutdown of shield tunneling work is caused, and finally, the construction efficiency is reduced and the cost is increased. In the existing pipeline blockage detection method, the detection method for detecting the pipeline based on the detection equipment has higher efficiency, but has higher use cost, so that the method for realizing intelligent early warning of pipeline blockage of the slurry shield slurry circulation system can monitor the running condition of the slurry circulation system in real time, and timely take corresponding adjustment measures, thereby having great significance in reducing energy consumption and improving tunneling efficiency.
Disclosure of Invention
Aiming at the problems that the construction condition of a slurry circulation pipeline is complex and the pipeline is extremely easy to generate particle blockage, the invention provides the intelligent early warning method for the blockage of the pipeline of the slurry shield slurry circulation system, which has scientific principle, easy operation, high intelligent degree and low operation cost.
In order to solve the technical problems, the invention adopts the following technical scheme: an intelligent early warning method for pipeline blockage of a slurry shield slurry circulating system comprises the following steps,
S1, detecting a flow field state in a pipeline and a movement track of particles by using a detection device, and displaying a detection result on a visual interface;
S2, performing multi-physical-field simulation calculation according to the operation parameter information of the slurry shield slurry circulation system under the real working condition collected by the detection device, and integrating the multi-physical-field simulation calculation results to construct a data set;
S3, substituting the formed training sample set into the agent model for training, testing after training, verifying the test result by using the verification sample set, and evaluating the prediction accuracy of the agent model; if the precision meets the requirement, predicting the motion state of the particles and outputting a prediction result; if the precision does not meet the requirement, optimizing the weight by using an optimization algorithm, predicting again, and outputting a prediction result after storing the network until the precision meets the requirement;
S4, transmitting the predicted result into a control system, and judging and adjusting the control system according to the predicted result, so that the real-time monitoring of the slurry shield slurry circulating system pipeline is achieved.
Further, the detection device is an X-ray beam, gamma rays or ultrasonic waves, the detection device is used for detecting the state of a flow field in a pipeline, the ultrasonic detection is taken as an example, the detection device is arranged at the inlet of a pulp inlet pipeline, the parameters such as the motion state, the speed, the size and the quantity of particles are detected, the flow velocity in the pipeline is measured by the electromagnetic flowmeter, and the specific detection steps are as follows:
s1.1, an ultrasonic transducer is arranged on one side of a pipeline, an ultrasonic driving circuit excites the ultrasonic transducer to generate ultrasonic waves, and the ultrasonic waves enter fluid;
S1.2, the echo signal receiving circuit finishes the processing of the ultrasonic echo reflected signal, including signal isolation, amplification, filtering and amplitude adjustment;
S1.3, detecting the state of particles in a pipeline by adopting a pulse refraction method, and assuming that the propagation speed of ultrasonic waves in an object is v and the time from emission to reflection of the particles is t, the sound path l of the particles is:
The received signals are displayed on a display screen in a pulse mode, the positions of particles are judged according to the amplitude and time in the display screen, the number of the particles can be directly determined by the number of pulse waves reflected by the particles, the distribution positions of the particles at the moments t 0 and t 1 are adopted respectively, the particle speed is calculated, and the detection result is displayed on a visual interface;
S1.4, an electromagnetic flowmeter, a pressure sensor, a density sensor and a viscosity sensor are arranged on the pipeline and are respectively used for measuring the flow rate, the pressure, the density and the viscosity in the pipeline;
and S1.5, displaying the detection result on a visual interface.
Further, the specific steps of step S2 are as follows:
s2.1, establishing a calculation model according to the pipeline shape through Creo modeling software;
s2.2, importing the calculation model into ICEM software grid division software, carrying out grid division on the established calculation model, checking the grid quality, and exporting a mesh grid file after the quality meets the requirement;
s2.3, importing the mesh file into EDEM software, and setting parameters of a particle motion model according to the collected parameters of the particle motion state;
S2.4, importing the mesh grid file into Fluent software, and setting boundary conditions and the like of a simulated calculation model by combining with actual working conditions; calculating momentum and energy exchange between the fluid and particles by iteration and passing the calculated data into the EDEM;
s2.5, in the EDEM software, calculating the speed and position information of the particles according to the flow field information calculated by the Fluent software, and transmitting the calculation result to the Fluent for further calculation;
S2.6, repeating the coupling calculation process until the movement state of the particles is approximately stable, and obtaining performance parameters such as slag carrying efficiency, particle accumulation and the like of the pipeline according to a simulation result;
S2.7 forming the monitored sample points into a sample point set, which may be expressed as { X 1,X2,X3,X4,X5,X6 } where X 1 represents the velocity of the particles, X 2 represents the size of the particles, X 3 represents the size of the particles, X 4 represents the velocity of the fluid, and the viscosity and density of the slurry, X 5 and X 6, respectively.
Further, in step S3, the agent model is used to predict the particle motion state, and an optimization algorithm is used to optimize the predicted result, taking a BP neural network as an example, and the sample point sets are used as input factors of the neural network, and the specific implementation steps are as follows:
S3.1 according to Kolmogrov theorem, a 3-layer neural network with n input units 2n+1 intermediate units and m output units can accurately represent any mapping, and can coordinate the capacity of the intermediate layers and training time; the structure for predicting pipeline blockage based on the BP neural network is divided into 3 layers, 6 input layers, 13 hidden layers and 3 output layers, which are called as a network structure of 6-13-3;
S3.2, the sizes of the selected sample points are different, normalization processing is needed to normalize the data to 0-1 in order to avoid that smaller data are submerged by larger data, and a normalization formula is as follows:
Wherein: x is an input factor, X min is the minimum value of the data, and X max is the maximum value of the data;
S3.3, according to the processed training data set, randomly extracting 200 data sample data sets, wherein 200 sample data sets are formed as input nodes of the BP neural network, and the result of coupling simulation is output as a training set sample set to train the neural network; randomly extracting 40 groups of samples to serve as a test set, testing and verifying test results by using a verification set;
s3.4, evaluating model accuracy of neural network prediction:
S3.5, optimizing the weight and the threshold by adopting a GA genetic algorithm, wherein each individual in the population comprises a weight and a threshold, the fitness of the individual is calculated by an fitness function, the GA genetic algorithm finds the individual corresponding to the optimal fitness through selection, crossing and mutation operation, and the BP neural network re-predicts the genetic algorithm optimizing weight and the threshold; and after training convergence, predicting the average flow speed of the slurry pipeline particles and the total particle number of the predicted samples.
Further, in step S4, the control system determines and adjusts the processing according to the prediction result specifically: if the possible occurrence of blockage is predicted, a signal early warning is sent and the shield front-end device is controlled to adjust, so that the occurrence of blockage is avoided; continuing to detect after the adjustment is completed; if the blockage is predicted not to occur, continuing to detect at the next moment;
The specific measures of the adjustment treatment are as follows:
S4.1, configuring proper high-quality slurry, adjusting the storage space of ground slurry and adjusting the viscosity of the slurry; preparing foam bentonite to be injected into a slurry shield slurry circulating system so as to improve the flow plasticity of the dregs;
s4.2, adjusting the proportion and flow of the slurry, and keeping the proper performance of the slurry; detecting and treating the slurry, removing impurities and sediments, and keeping the cleanliness of the slurry; and checking and maintaining equipment and pipelines in the mud recovery system to ensure the normal operation of the equipment and the pipelines.
By adopting the technical scheme, the invention has the main beneficial effects that:
According to the method, real data under various working conditions are utilized to carry out multi-physical-field simulation calculation, the simulation calculation result is used for training and predicting the pipeline agent model, and an optimization algorithm is adopted for optimizing the prediction result, so that the prediction accuracy is improved. And judging whether to alarm or not through the control system, thereby realizing the real-time monitoring of the pipeline blockage of the slurry shield slurry circulation system. Compared with the traditional detection method based on detection equipment for detecting the pipeline, the method can efficiently detect the movement condition of the particles in the pipeline of the slurry shield slurry circulation system, monitor in real time, reduce the monitoring maintenance cost and improve the construction efficiency.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a schematic diagram of measuring the flow field state of a pipeline by using a pulse reflection method;
FIG. 3 is a flow chart of a coupling simulation of the present invention;
fig. 4 is a flow chart of neural network prediction according to the present invention.
Detailed Description
As shown in FIG. 1, the intelligent early warning method for pipeline blockage of the slurry shield slurry circulation system comprises the following steps:
S1, detecting a flow field state in a pipeline and a movement track of particles by using a detection device, and displaying a detection result on a visual interface;
S2, performing multi-physical-field simulation calculation according to the operation parameter information of the slurry shield slurry circulation system under the real working condition collected by the detection device, and integrating the multi-physical-field simulation calculation results to construct a data set;
S3, substituting the formed training sample set into the agent model for training, testing after training, verifying the test result by using the verification sample set, and evaluating the prediction accuracy of the agent model; if the precision meets the requirement, predicting the motion state of the particles and outputting a prediction result; if the precision does not meet the requirement, optimizing the weight by using an optimization algorithm, predicting again, and outputting a prediction result after storing the network until the precision meets the requirement;
S4, transmitting the predicted result into a control system, and judging and adjusting the control system according to the predicted result, so that the real-time monitoring of the slurry shield slurry circulating system pipeline is achieved.
The detection device is an X-ray beam, gamma rays or ultrasonic waves, the detection device is used for detecting the flow field state in the pipeline, as shown in fig. 2, the detection device is installed at the inlet of the slurry inlet pipeline for detecting parameters such as the motion state, speed, size and quantity of particles, and the electromagnetic flowmeter is used for measuring the flow velocity in the pipeline, and the specific detection steps are as follows:
s1.1, an ultrasonic transducer is arranged on one side of a pipeline, an ultrasonic driving circuit excites the ultrasonic transducer to generate ultrasonic waves, and the ultrasonic waves enter fluid;
S1.2, the echo signal receiving circuit finishes the processing of the ultrasonic echo reflected signal, including signal isolation, amplification, filtering and amplitude adjustment;
S1.3, detecting the state of particles in a pipeline by adopting a pulse refraction method, and assuming that the propagation speed of ultrasonic waves in an object is v and the time from emission to reflection of the particles is t, the sound path l of the particles is:
The received signals are displayed on a display screen in a pulse mode, the positions of particles are judged according to the amplitude and time in the display screen, the number of the particles can be directly determined by the number of pulse waves reflected by the particles, the distribution positions of the particles at the moments t 0 and t 1 are adopted respectively, the particle speed is calculated, and the detection result is displayed on a visual interface;
S1.4, an electromagnetic flowmeter, a pressure sensor, a density sensor and a viscosity sensor are arranged on the pipeline and are respectively used for measuring the flow rate, the pressure, the density and the viscosity in the pipeline;
and S1.5, displaying the detection result on a visual interface.
As shown in fig. 3, the specific steps of step S2 are as follows:
s2.1, establishing a calculation model according to the pipeline shape through Creo modeling software;
s2.2, importing the calculation model into ICEM software grid division software, carrying out grid division on the established calculation model, checking the grid quality, and exporting a mesh grid file after the quality meets the requirement;
s2.3, importing the mesh file into EDEM software, and setting parameters of a particle motion model according to the collected parameters of the particle motion state;
S2.4, importing the mesh grid file into Fluent software, and setting boundary conditions and the like of a simulated calculation model by combining with actual working conditions; calculating momentum and energy exchange between the fluid and particles by iteration and passing the calculated data into the EDEM;
s2.5, in the EDEM software, calculating the speed and position information of the particles according to the flow field information calculated by the Fluent software, and transmitting the calculation result to the Fluent for further calculation;
S2.6, repeating the coupling calculation process until the movement state of the particles is approximately stable, and obtaining performance parameters such as slag carrying efficiency, particle accumulation and the like of the pipeline according to a simulation result;
S2.7 forming the monitored sample points into a sample point set, which may be expressed as { X 1,X2,X3,X4,X5,X6 } where X 1 represents the velocity of the particles, X 2 represents the size of the particles, X 3 represents the size of the particles, X 4 represents the velocity of the fluid, and the viscosity and density of the slurry, X 5 and X 6, respectively.
As shown in fig. 4, in step S3, the agent model is used to predict the particle motion state, and an optimization algorithm is used to optimize the predicted result, taking a BP neural network as an example, and using the sample point sets as input factors of the neural network, the specific implementation steps are as follows:
S3.1 according to Kolmogrov theorem, a 3-layer neural network with n input units 2n+1 intermediate units and m output units can accurately represent any mapping, and can coordinate the capacity of the intermediate layers and training time; the structure for predicting pipeline blockage based on the BP neural network is divided into 3 layers, 6 input layers, 13 hidden layers and 3 output layers, which are called as a network structure of 6-13-3;
S3.2, the sizes of the selected sample points are different, normalization processing is needed to normalize the data to 0-1 in order to avoid that smaller data are submerged by larger data, and a normalization formula is as follows:
Wherein: x is an input factor, X min is the minimum value of the data, and X max is the maximum value of the data;
S3.3, according to the processed training data set, randomly extracting 200 data sample data sets, wherein 200 sample data sets are formed as input nodes of the BP neural network, and the result of coupling simulation is output as a training set sample set to train the neural network; randomly extracting 40 groups of samples to serve as a test set, testing and verifying test results by using a verification set;
s3.4, evaluating model accuracy of neural network prediction:
S3.5, optimizing the weight and the threshold by adopting a GA genetic algorithm, wherein each individual in the population comprises a weight and a threshold, the fitness of the individual is calculated by an fitness function, the GA genetic algorithm finds the individual corresponding to the optimal fitness through selection, crossing and mutation operation, and the BP neural network re-predicts the genetic algorithm optimizing weight and the threshold; and after training convergence, predicting the average flow speed of the slurry pipeline particles and the total particle number of the predicted samples.
In step S4, the control system determines and adjusts the processing according to the prediction result specifically: if the possible occurrence of blockage is predicted, a signal early warning is sent and the shield front-end device is controlled to adjust, so that the occurrence of blockage is avoided; continuing to detect after the adjustment is completed; if the blockage is predicted not to occur, continuing to detect at the next moment;
The specific measures of the adjustment treatment are as follows:
S4.1, configuring proper high-quality slurry, adjusting the storage space of ground slurry and adjusting the viscosity of the slurry; preparing foam bentonite to be injected into a slurry shield slurry circulating system so as to improve the flow plasticity of the dregs;
s4.2, adjusting the proportion and flow of the slurry, and keeping the proper performance of the slurry; detecting and treating the slurry, removing impurities and sediments, and keeping the cleanliness of the slurry; and checking and maintaining equipment and pipelines in the mud recovery system to ensure the normal operation of the equipment and the pipelines.
The foregoing description is only illustrative of the preferred embodiments of the present invention, and although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements or changes may be made without departing from the spirit and principles of the present invention.
Claims (3)
1. An intelligent early warning method for pipeline blockage of a slurry shield slurry circulating system is characterized by comprising the following steps of: comprises the steps of,
S1, detecting a flow field state in a pipeline and a movement track of particles by using a detection device, and displaying a detection result on a visual interface;
S2, performing multi-physical-field simulation calculation according to the operation parameter information of the slurry shield slurry circulation system under the real working condition collected by the detection device, and integrating the multi-physical-field simulation calculation results to construct a data set;
the specific steps of the step S2 are as follows:
s2.1, establishing a calculation model according to the pipeline shape through Creo modeling software;
s2.2, importing the calculation model into ICEM software grid division software, carrying out grid division on the established calculation model, checking the grid quality, and exporting a mesh grid file after the quality meets the requirement;
s2.3, importing the mesh file into EDEM software, and setting parameters of a particle motion model according to the collected parameters of the particle motion state;
S2.4, importing the mesh grid file into Fluent software, and setting boundary conditions of the simulated calculation model by combining with actual working conditions; calculating momentum and energy exchange between the fluid and particles by iteration and passing the calculated data into the EDEM;
s2.5, in the EDEM software, calculating the speed and position information of the particles according to the flow field information calculated by the Fluent software, and transmitting the calculation result to the Fluent for further calculation;
S2.6, repeating the steps from S2.4 to S2.5 until the movement state of the particles is approximately stable, and obtaining the slag carrying efficiency and particle stacking performance parameters of the pipeline according to the simulation result;
S2.7 forming the monitored sample points into a sample point set, denoted as { X 1,X 2 ,X 3 ,X 4 ,X 5,X 6 }, wherein X 1 represents the speed of the particles, X 2 represents the size of the particles, X 3 represents the size of the particles, X 4 represents the speed of the fluid, and X 5 and X 6 represent the viscosity and density of the slurry, respectively;
S3, substituting the formed training sample set into the agent model for training, testing after training, verifying the test result by using the verification sample set, and evaluating the prediction accuracy of the agent model; if the precision meets the requirement, predicting the motion state of the particles and outputting a prediction result; if the precision does not meet the requirement, optimizing the weight by using an optimization algorithm, predicting again, and outputting a prediction result after storing the network until the precision meets the requirement;
s3, predicting the particle motion state by using a proxy model, optimizing a predicted result by using an optimization algorithm, adopting a BP neural network, and taking the sample point set as an input factor of the neural network, wherein the specific implementation steps are as follows:
s3.1, the structure for predicting pipeline blockage based on the BP neural network is divided into 3 layers, 13 hidden layers of 6 input layers and 3 output layers, which are called as a network structure of 6-13-3;
S3.2, the sizes of the selected sample points are different, normalization processing is needed to normalize the data to 0-1 in order to avoid that smaller data are submerged by larger data, and a normalization formula is as follows:
；
wherein: x is an input factor, X min is the minimum value of the data, and X max is the maximum value of the data;
S3.3, according to the processed training data set, randomly extracting 200 data sample data sets, wherein 200 sample data sets are formed as input nodes of the BP neural network, and the result of coupling simulation is output as a training set sample set to train the neural network; randomly extracting 40 groups of samples to serve as a test set, testing and verifying test results by using a verification set;
s3.4, evaluating model accuracy of neural network prediction:
；
S3.5, optimizing the weight and the threshold by adopting a GA genetic algorithm, wherein each individual in the population comprises a weight and a threshold, the fitness of the individual is calculated by an fitness function, the GA genetic algorithm finds the individual corresponding to the optimal fitness through selection, crossing and mutation operation, and the BP neural network re-predicts the genetic algorithm optimizing weight and the threshold; after training convergence, predicting the average flow speed of mud water pipeline particles and the total particle number of the predicted samples;
S4, transmitting the predicted result into a control system, and judging and adjusting the control system according to the predicted result, so that the real-time monitoring of the slurry shield slurry circulating system pipeline is achieved.
2. The intelligent early warning method for pipeline blockage of the slurry shield slurry circulation system according to claim 1 is characterized by comprising the following steps: the detection device is an X-ray beam, gamma rays or ultrasonic waves, the flow field state in the pipeline is detected by using the detection device, when the detection device is ultrasonic waves, the detection device is arranged at the inlet of the pulp inlet pipeline, the movement state, speed, size and quantity of particles are detected, the flow velocity in the pipeline is measured by using the electromagnetic flowmeter, and the specific detection steps are as follows:
s1.1, an ultrasonic transducer is arranged on one side of a pipeline, an ultrasonic driving circuit excites the ultrasonic transducer to generate ultrasonic waves, and the ultrasonic waves enter fluid;
S1.2, the echo signal receiving circuit finishes the processing of the ultrasonic echo reflected signal, including signal isolation, amplification, filtering and amplitude adjustment;
S1.3, detecting the state of particles in a pipeline by adopting a pulse refraction method, and assuming that the propagation speed of ultrasonic waves in an object is v and the time from emission to reflection of the particles is t, the sound path l of the particles is:
；
the received signals are displayed on a display screen in a pulse mode, the positions of particles are judged according to the amplitude and time in the display screen, the number of the particles can be directly determined by the number of pulse waves reflected by the particles, the distribution positions of the particles at the time t0 and the time t1 are adopted respectively, the particle speed is calculated, and the detection result is displayed on a visual interface;
S1.4, an electromagnetic flowmeter, a pressure sensor, a density sensor and a viscosity sensor are arranged on the pipeline and are respectively used for measuring the flow rate, the pressure, the density and the viscosity in the pipeline;
and S1.5, displaying the detection result on a visual interface.
3. The intelligent early warning method for pipeline blockage of the slurry shield slurry circulation system according to claim 1 is characterized by comprising the following steps: in step S4, the control system determines and adjusts the processing according to the prediction result specifically: if the possible occurrence of blockage is predicted, a signal early warning is sent and the shield front-end device is controlled to adjust, so that the occurrence of blockage is avoided; continuing to detect after the adjustment is completed; if the blockage is predicted not to occur, continuing to detect at the next moment;
The specific measures of the adjustment treatment are as follows:
S4.1, configuring proper high-quality slurry, adjusting the storage space of ground slurry and adjusting the viscosity of the slurry; preparing foam bentonite to be injected into a slurry shield slurry circulating system so as to improve the flow plasticity of the dregs;
s4.2, adjusting the proportion and flow of the slurry, and keeping the proper performance of the slurry; detecting and treating the slurry, removing impurities and sediments, and keeping the cleanliness of the slurry; and checking and maintaining equipment and pipelines in the mud recovery system to ensure the normal operation of the equipment and the pipelines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310490445.1A CN116519055B (en) | 2023-05-04 | 2023-05-04 | Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310490445.1A CN116519055B (en) | 2023-05-04 | 2023-05-04 | Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116519055A CN116519055A (en) | 2023-08-01 |
| CN116519055B true CN116519055B (en) | 2024-05-10 |
Family
ID=87407794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310490445.1A Active CN116519055B (en) | 2023-05-04 | 2023-05-04 | Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116519055B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3018602U (en) * | 1995-05-24 | 1995-11-28 | 大成建設株式会社 | Muddy water shield machine mud pipe blocking device |
| JPH1018763A (en) * | 1996-07-02 | 1998-01-20 | Ebara Corp | Blocking detecting method and blocking avoiding operating device for mud drain pipeline in mud shield construction system |
| CN108343442A (en) * | 2018-01-18 | 2018-07-31 | 浙江大学 | Slurry balance shield comprehensive simulation test platform mud and water balance control test system |
| CN115758864A (en) * | 2022-10-31 | 2023-03-07 | 北京交通大学 | Method for pre-judging and positioning blockage of slurry shield tunneling cutter head |
-
2023
- 2023-05-04 CN CN202310490445.1A patent/CN116519055B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3018602U (en) * | 1995-05-24 | 1995-11-28 | 大成建設株式会社 | Muddy water shield machine mud pipe blocking device |
| JPH1018763A (en) * | 1996-07-02 | 1998-01-20 | Ebara Corp | Blocking detecting method and blocking avoiding operating device for mud drain pipeline in mud shield construction system |
| CN108343442A (en) * | 2018-01-18 | 2018-07-31 | 浙江大学 | Slurry balance shield comprehensive simulation test platform mud and water balance control test system |
| CN115758864A (en) * | 2022-10-31 | 2023-03-07 | 北京交通大学 | Method for pre-judging and positioning blockage of slurry shield tunneling cutter head |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116519055A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103644457B (en) | A kind of localization method of line clogging and device | |
| CN105042339B (en) | One kind is based on nondimensional leakage of finished oil pipeline amount estimating system and method | |
| CN102944608B (en) | Device and method for ultrasonic testing of corrugated pipe duck grouting compactness | |
| CN104373821A (en) | Natural gas pipeline safety monitoring device based on acoustical science active spurring | |
| CN110952978A (en) | Drilling leakage fracture width prediction method based on neural network data mining | |
| CN105510959A (en) | Method for recognizing type of vibration source of tunnel, and vibration source positioning method | |
| CN108613645B (en) | A kind of Pb-Zn deposits absorbing well, absorption well surveying on sludge thickness method based on parameter Estimation | |
| CN109780447A (en) | A method of using stopping state in pulsed pressure wave detection pressure pipeline | |
| CN109063849B (en) | Real-time tracking and grading positioning system and method for in-pipeline detector | |
| CN112198515B (en) | Parametric array shallow-section difference frequency conversion performance optimization method | |
| CN109344784A (en) | A kind of leakage orienting method merging hydrophone and Wavelet Denoising Method | |
| CN116519055B (en) | Intelligent early warning method for pipeline blockage of slurry shield slurry circulation system | |
| CN111412959A (en) | Flow online monitoring calculation method, monitor and monitoring system | |
| Vaghefi et al. | A comparison among data mining algorithms for outlier detection using flow pattern experiments | |
| Li et al. | Influence of artificial sandbar on nonlinear wave transformation: Experimental investigation and parameterizations | |
| Jierula et al. | Detection of damage locations and damage steps in pile foundations using acoustic emissions with deep learning technology | |
| CN115406385A (en) | Method for monitoring fracture of prestressed reinforcement in cable-stayed bridge cable tower anchoring area | |
| CN104950859A (en) | Device and method for removing accumulated fluids in low-lying positions of pipeline and monitoring concentration of corrosion inhibitor on line | |
| Chavan et al. | Effect of downward seepage on turbulent flow characteristics and bed morphology around bridge piers | |
| CN117807877A (en) | Pipeline detection system based on digital twin, system construction method and detection method | |
| CN207036192U (en) | Gas liquid two purpose ultrasonic flowmeter | |
| CN113344275A (en) | Floating platform wave climbing online forecasting method based on LSTM model | |
| CN104596735B (en) | Optimal arrangement method of bridge group | |
| CN107587493A (en) | A kind of excavation of foundation pit monitoring and pre-alarming method based on neutral net | |
| CN116088050A (en) | Rock burst prediction method based on microseismic monitoring of space-time strong parameters of fracture source |
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 |