CN113267612A - Soil body water content detection method, detection system and penetration device - Google Patents
Soil body water content detection method, detection system and penetration device Download PDFInfo
- Publication number
- CN113267612A CN113267612A CN202110534793.5A CN202110534793A CN113267612A CN 113267612 A CN113267612 A CN 113267612A CN 202110534793 A CN202110534793 A CN 202110534793A CN 113267612 A CN113267612 A CN 113267612A
- Authority
- CN
- China
- Prior art keywords
- soil
- soil body
- bending element
- water content
- element sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
- G01N33/246—Earth materials for water content
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Food Science & Technology (AREA)
- Analytical Chemistry (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Medicinal Chemistry (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigation Of Foundation Soil And Reinforcement Of Foundation Soil By Compacting Or Drainage (AREA)
Abstract
The invention relates to a soil body water content detection method, a detection system and a penetration device, wherein the detection method comprises the following contents: obtaining soil body dry densities of different kinds of soil bodies, measuring the soil body dry densities, the soil penetration depths, the shear wave speeds under vertical pressure and the corresponding water contents of different soil body types, and corresponding the water contents, the soil body dry densities, the soil penetration depths, the soil body types, the vertical pressure and the shear wave speeds; and constructing an artificial neural network model by taking the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of the soil body as characteristic values and the water content as target values, and obtaining the water content of the soil body by using the trained artificial neural network model. The detection method can be applied to the measurement of the water content of the compacted road in field construction, realizes the prediction of the water content of different thicknesses, is convenient to detect, is suitable for industrial field use, and has high detection precision.
Description
Technical Field
The invention relates to a soil body water content detection method, a detection system and a penetration device based on a bending element sensor.
Background
In engineering construction, the water content is one of basic physical properties of a soil body, the strength and the deformation characteristics of a foundation are influenced seriously, and under the field condition, if the water content of the soil body with different depths can be measured quickly and accurately, the detection efficiency can be greatly improved, and precious time is saved for subsequent construction. The current commonly used soil moisture content measuring methods comprise a mass method, a ray method, a dielectric method, a remote sensing method, a ground penetrating radar method and the like.
The mass method determines the water content of the soil body by utilizing the mass change of the soil body, the measurement result is most accurate, but the time consumption is long, the method is not suitable for the soil with high organic matter content, and the rapid field measurement condition cannot be met; the ray method utilizes the change of rays passing through the soil body to measure the water content of the soil body, can meet the requirement of on-site high-precision and quick measurement, but has certain radiation hidden danger and is unfavorable for the health of operators; the dielectric method determines the water content through the relation between the water content and the dielectric property of the soil body, the measurement is convenient and accurate, the method can be used for on-site rapid measurement and in-situ monitoring, but is greatly influenced by temperature and salinity, and the existing equipment mainly depends on import and is expensive; the remote sensing method measures the time-space change of the surface soil moisture content by monitoring the spectral characteristics and the thermal properties of the soil surface, has the advantages of wide range and quick measurement, but only can monitor the moisture content of the surface soil body; the ground penetrating radar method can be used for rapidly measuring the water content of the soil body on site in a large range, is convenient and nondestructive, can be used for repeated detection, and is complex in data extraction and processing.
In conclusion, the existing detection means are difficult to rapidly measure the water content of soil bodies at different depths on site, and the use requirements cannot be met.
Disclosure of Invention
The invention provides a soil body water content detection method, a detection system and a penetration device based on a bending element sensor and an artificial neural network model, aiming at the problems of long measurement time, radiation hidden danger, high price, surface layer measurement and difficult data extraction of the existing water content test technology.
The technical scheme adopted by the invention for solving the technical problems is as follows:
in a first aspect, the invention provides a soil moisture content detection method, which comprises the following steps:
obtaining soil body dry densities of different kinds of soil bodies, measuring the soil body dry densities, the soil penetration depths, the shear wave speeds under vertical pressure and the corresponding water contents of different soil body types, and corresponding the water contents, the soil body dry densities, the soil penetration depths, the soil body types, the vertical pressure and the shear wave speeds to form a data set;
constructing an artificial neural network model by taking the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of a soil body as characteristic values and the water content as target values, and training the artificial neural network model by using a data set to obtain a trained artificial neural network model;
and inputting the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of the soil body to be detected into the trained artificial neural network model to obtain the water content of the soil body.
In a second aspect, the present invention provides a penetration device with a bending element sensor built therein, comprising: the soil-penetrating device comprises two vertical parallel probe rods (2) and a connecting rod (1) fixedly connected with the two parallel probe rods, and is characterized in that a graduated scale (4) is carved on each parallel probe rod, each probe rod (2) is a multilayer telescopic loop rod, loop rods of adjacent layers are connected through a spring buckle, the next loop rod connected to the spring buckle extends out after the spring buckle is pressed down, the graduated scale on the surface of each multilayer telescopic loop rod is continuous when the telescopic loop rods are all unfolded, the number of unfolded layers of the telescopic loop rods is changed according to the soil penetration depth, and the graduated range of the telescopic loop rods is guaranteed to be always larger than the soil penetration depth;
the hollow rod 11 is coaxially arranged in the probe rod 2, the hollow rod 11 is fixedly connected with the inner wall of the innermost sleeve rod, the screw rod 9 penetrates through the hollow rod and penetrates out of the probe rod 2, the screw rod is eccentrically installed, the bottom of the screw rod 9 is fixedly connected with a first triangular sliding block, the upper part of the screw rod is provided with a rotating nut 8, and the rotating nut 8 can control the screw rod to move up and down to drive a first triangular sliding block 12 at the bottom end of the screw rod (9) to move up and down;
a hole site for pushing out the bending element sensor is reserved on the upper pipe wall of the tail end probe rod, a guide rail (14) for moving the bending element sensor is arranged on the horizontal plane of the hole site, the guide rail is fixed inside the innermost layer loop bar and fixed with the inner wall of the innermost layer loop bar, the inner side of the bending element sensor is connected with a second triangular slide block, two inclined planes of the first triangular slide block and the second triangular slide block are in contact, the first triangular slide block extrudes the second triangular slide block through the inclined plane in the up-and-down moving process of the screw rod, the second triangular slide block moves in the horizontal direction along the guide rail (14) to push out the bending element sensor from the hole site, one bending element sensor on the two probe rods is used for receiving the bending element sensor, and the other bending element sensor is used for transmitting the bending element sensor.
In a third aspect, the invention provides a soil moisture content detection system based on a bending element sensor, which is characterized by comprising a penetration device with a built-in bending element sensor, an electric signal generation module, an electric signal receiving and processing module and a data management platform (S6); after the penetration device with the built-in bending element sensor reaches the target depth of a soil body, applying regular waveforms with set voltage and frequency to the transmitting bending element sensor through the electric signal generating module, forcing the transmitting bending element to drive the surrounding soil body to generate transverse vibration through piezoelectric effect, driving the receiving bending element sensor at the other end to vibrate through the soil body by shear waves generated in the direction vertical to the vibration, finally transmitting weak current generated by the receiving bending element sensor into the electric signal receiving and processing module, and interconnecting and communicating the electric signal receiving and processing module and data of the data management platform;
the data management platform is connected with the electric signal receiving and processing module through a 5G network to realize data interaction; in addition, both the transmitting and receiving bending element sensors need to be inserted into the soil body to be measured at the same depth.
The electric signal generating module is used for generating an electric signal;
the electric signal receiving and processing module comprises: a signal amplifier (S2), an oscilloscope (S3) and an embedded computer chip (S4); the input of the signal amplifier is connected with and receives the electrical signal of the bending element sensor, the oscilloscope is connected with the output of the signal amplifier and the output of the signal generator at the same time, the output of the oscilloscope is connected with the embedded computer chip, and the embedded computer chip is communicated with the data management platform (S6);
the data management platform is provided with a database related to soil body parameters and has the functions of data import, storage, modification, calculation, calling, export and visualization.
In a fourth aspect, the invention provides a soil moisture content detection method applied to soil moisture content detection after roadbed compaction, which is characterized by comprising the following steps:
1) preparation of test specimens
Selecting different types of soil bodies, screening, removing impurities, drying and weighing, measuring initial water content and dry density of the soil bodies, and controlling the water content in the soil bodies by changing the water adding amount to obtain test samples of the different soil bodies with different water contents;
2) collecting raw data
Applying different vertical pressures on the surfaces of different test samples aiming at the test samples, changing the penetration depth of the bending element sensor, measuring the shear wave velocity of the different test samples under different vertical pressures and different penetration depths, and taking the dry density, the penetration depth, the soil type, the vertical pressure, the shear wave velocity and the corresponding water content of the soil body as a group of data so as to obtain a plurality of groups of data of all the test samples to form a data set;
3) building artificial neural network model
Taking soil body dry density, soil penetration depth, shear wave velocity, soil body type and vertical pressure as characteristic values and water content as target values, performing round training on all data sets until errors meet limit values, determining the limit values according to precision required by field measurement, and obtaining a trained artificial neural network model, namely a shear wave velocity-water content prediction model; after data are preprocessed, a training set and a test set are divided according to a proportion, model parameters are adjusted, all samples are trained in turn until errors meet a limit value, the limit value is determined according to precision required by field measurement, the higher the precision requirement is, the lower the limit value is, specific numerical values are related to the super-parameter setting (learning rate, hidden layer number, neuron number and the like) of a limit value neural network model, and the shear wave velocity-water content prediction model is obtained.
4) Access data management platform
Writing the trained artificial neural network model into an embedded computer chip, accessing the embedded computer chip into a data management platform, obtaining soil body dry density, vertical pressure and soil body type from the data management platform, and inputting the soil body shear wave speed and the soil penetration depth measured on site to obtain the soil body water content of site construction;
and after the on-site roadbed is compacted, applying the trained artificial neural network model to predict the water content of the soil body, simultaneously carrying out water content sampling inspection periodically, recording the characteristic value and the sampling inspection true value of a corresponding sample during water content sampling inspection to form a new data set, and transmitting the new data set back to the data management platform for expanding the database of the data management platform and updating the artificial neural network model. A density testing instrument is arranged on a construction site, and the measured data and the data management platform are interconnected and communicated and can be directly called from the data management platform.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention uses the probe with the built-in bending element sensor to measure the shear wave velocity of the soil body, has no limit on the type and the depth of the soil body to be measured, has high measuring speed and is harmless to the health of operators. The penetration device is in a telescopic form, is more portable, is convenient to use and has high measurement precision.
2. According to the detection method, the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of the soil body are used as characteristic values, the water content is used as a target value, an artificial neural network model is constructed, the relation between the characteristic values and the water content of the soil body is obtained through training, the quantitative corresponding relation between the characteristic values and the target value is determined, and the measurement precision is high.
3. The detection method can be applied to field construction, the water content of the compacted road is measured, the compacted road is paved layer by layer and compacted layer by layer, the soil thickness of each layer is different, the depth is different, the water content prediction of different thicknesses is realized, the detection is convenient, and the method is suitable for industrial field use.
Drawings
FIG. 1 is a general flowchart of an embodiment of the measurement method of the present invention.
Fig. 2 is a block diagram of the measuring system of the present invention.
FIG. 3 is a schematic diagram of the internal and external structures of the penetration device with a bending element sensor built therein according to the present invention, wherein the left side is a schematic diagram of the internal structure and the right side is a schematic diagram of the external structure.
FIG. 4 is a schematic structural diagram of an artificial neural network model according to the present invention.
FIG. 5 is a flow chart of the artificial neural network construction of the present invention.
Fig. 6 is a detailed view of the retractable feeler lever spring catch.
Reference numerals:
s1-penetration device with built-in bending element sensor, S2-signal amplifier, S3-oscilloscope, S4-embedded computer chip, S5-signal generator, S6-data management platform.
The bending sensor comprises a connecting rod 1, a probe rod 2, a spring buckle 3, a graduated scale 4, a bending element sensor protection structure 5, a transmitting bending element sensor 6, a conical head 7, a nut 8, a screw rod 9, a connecting cable 10, a hollow rod 11, a sliding block 12, a receiving bending element sensor 13, a guide rail 14 and a spring 15.
Detailed Description
The present invention is further explained with reference to the following examples and drawings, but the scope of the present invention is not limited thereto.
The invention relates to a soil body water content measuring system based on a bending element sensor and an artificial neural network model, which comprises a penetration device S1 with a built-in bending element sensor, an electric signal generating module, an electric signal receiving and processing module and a data management platform (S6).
After the penetration device with the built-in bending element sensor reaches the target depth of a soil body, regular waveforms with certain voltage and frequency are applied to the transmitting bending element sensor through the electric signal generating module, the piezoelectric effect forces the transmitting bending element to drive the surrounding soil body to generate transverse vibration, shear waves generated in the direction perpendicular to the vibration drive the receiving bending element sensor at the other end to vibrate through the soil body, weak current generated by the receiving bending element sensor is finally transmitted into the electric signal receiving and processing module, and the electric signal receiving and processing module and the data management platform are in data interconnection and intercommunication. The electric signal generation module is connected with the transmitting bent element sensor through one end of a BNC connecting line, one end of the electric signal generation module is connected with the electric signal receiving and processing module, the other port of the electric signal receiving and processing module is connected with the receiving bent element sensor through the BNC connecting line, and the data management platform is in data interaction with the electric signal receiving and processing module through a 5G network. In addition, the transmitting and receiving bending elements are required to be inserted into the soil body to be measured at the same depth.
The electric signal generating module is used for generating electric signals and comprises: a signal generator (S5) for generating an electrical signal having a frequency, amplitude, and phase waveform;
the electric signal receiving and processing module comprises: a signal amplifier (S2), an oscilloscope (S3) and an embedded computer chip (S4); the input of the signal amplifier is connected with and receives the electrical signal of the bending element sensor, the oscilloscope is simultaneously connected with the output of the signal amplifier and the output of the signal generator, the output of the oscilloscope is connected with the embedded computer chip, and the embedded computer chip is communicated with the data management platform (S6).
The data management platform is a data platform with the functions of data import, storage, modification, calculation, calling, export, visualization and the like for soil body site construction, the data management platform stores data of soil body dry density, soil penetration depth, soil body type and the like of a soil body on a construction site, and a database related to soil body parameters is arranged in the data management platform (S6).
The penetration device with the built-in bending element sensor is improved from a probe rod with a fixed length to a telescopic probe rod, so that the portability is improved. The method comprises the following steps: two vertical parallel probe rods (2), connecting rod (1) of two parallel probe rods of fixed connection, scale (4) have all been carved with on every parallel probe rod, probe rod (2) are the scalable loop bar of multilayer, be provided with spring buckle (3) on the outer wall of every layer of loop bar, the loop bar of adjacent layer is connected to the spring buckle, its next layer loop bar of connecting on it stretches out after the spring buckle presses down, can adjust the length of scalable probe rod (2), scale on its surface is continuous when the scalable loop bar of multilayer is whole expandes, can be according to the expansion number of piles that the degree of depth of burying changes scalable loop bar, guarantee that scalable loop bar scale range is greater than the degree of depth of burying all the time. The hollow rod 11 is coaxially arranged in the probe rod 2, the hollow rod 11 is fixedly connected with the inner wall of the telescopic probe rod (2) in other modes such as welding or bolt fixing, the screw rod 9 penetrates through the hollow rod and penetrates out of the probe rod 2, the screw rod is eccentrically installed to provide a space for horizontal movement of the triangular sliding block, the hollow rod with the inner diameter slightly larger than that of the screw rod is arranged to further limit the moving space of the screw rod, shaking is avoided, meanwhile, a space for a cable can be reserved, the bottom of the screw rod 9 is fixedly connected with the first triangular sliding block, the upper part of the screw rod is provided with the rotating nut 8, the rotating nut 8 can control the screw rod to move up and down, and the first triangular sliding block 12 at the bottom end of the screw rod (9) is driven to move up and down;
a hole site for pushing out the bending element sensor is reserved on the upper pipe wall of the probe rod at the tail end, a guide rail (14) of the bending element sensor is arranged on the horizontal plane of the hole site, the guide rail is fixed in the probe rod and fixed with the inner wall of the probe rod, the inner side of the bending element sensor is connected with a second triangular slide block, two inclined planes of the first triangular slide block and the second triangular slide block are contacted, a spring is fixedly arranged between the second triangular slide block above the bending element sensor and the inner wall of the probe rod, the first triangular slide block extrudes the second triangular slide block through the inclined plane in the up-and-down moving process of the screw rod, so that the second triangular slide block moves along the guide rail (14) in the horizontal direction, namely, the horizontal displacement occurs, the bending element sensor is pushed out of the hole site, good contact with the soil body is ensured, the nut can be rotated reversely firstly when the bending element sensor is retracted, and the spring (15) releases the compression state, the second triangular sliding block is pushed inwards to reset. And the two bending element sensors on the probe rod are respectively a receiving bending element sensor and a transmitting bending element sensor.
Two bending element sensor protection structures (5) are symmetrically arranged on the pipe wall of the probe rod of the pushing hole position of the bending element sensor (6) up and down by taking the bending element sensor as the center.
The bending element sensor (6) is connected with a signal generator (S5) through a cable (10), and the cable (10) is placed in a reserved hollow rod (11). The sleeve rod at the bottommost layer of the probe rod (2) is provided with a conical head (7). During the use, press earlier and connect the loop bar spring buckle of lower floor, the loop bar of lower floor is connected the conical head and is popped out, when lower floor loop bar scale is not enough, press the spring buckle that the control upper story loop bar stretches out again to satisfy different depth of penetrating into the soil measurement needs.
In this embodiment, three loop bars are nested in proper order to constitute whole probe rod, all be provided with the spring buckle on the upper portion lateral wall of two loop bars except outermost loop bar, be provided with spacing hole about being provided with respectively on the upper portion of the last layer loop bar of the loop bar that is provided with the spring buckle and the lower part lateral wall, the spring buckle that is located spacing hole department as the loop bar of spring buckle can carry on spacingly to this loop bar, when the spring buckle is located spacing hole, press the spring buckle, the loop bar of lower floor stretches out, stop stretching out and fixed by the spring buckle once more in spacing hole position down. When the telescopic rod is retracted, the spring buckle at the lower limiting hole is pressed, and the telescopic rod can be retracted by pushing upwards with hand force.
The invention relates to a soil moisture content detection method, which comprises the following detailed steps:
the method comprises the following steps: preparation of test specimens
The method comprises the steps of collecting different types of soil bodies (generally, sandy soil, silt soil, cohesive soil and the like) outdoors, grinding the soil bodies, and sieving the ground soil bodies by a sieve of 2mm to remove impurities such as stones, grass roots and the like in the soil bodies. Weighing the soil body after sieving and impurity removal to obtain the mass M1, measuring the wet density rho of the soil body by using a cutting ring method or other methods, putting the soil body into a drying oven at 110 ℃ to dry until the mass is unchanged to obtain original samples of different types of soil bodies with the water content of 0, weighing the mass M2, and calculating the initial water content w of the soil body0And dry density ρd。
Calculation formula for initial water content of soil body
Formula for calculating dry density of soil body
Step two: collecting raw data
Firstly, taking a dried soil body with the mass of M, adding water into the dried soil body according to a water adding amount calculation formula, and uniformly mixing to ensure that the water content of the soil body is 1 percent
Water addition MwFormula for calculation
Wherein: w' is the preset water content of the soil body, w1The water content of the soil body before adding water.
Then, two probe rods with built-in bending element sensors (6) are vertically inserted into the soil body, the same penetration depth is ensured through a graduated scale (4) on the outer wall of the probe, and the penetration depth h is recorded. The two bent element sensor protection structures (5) extending out of the outer wall of the probe rod can ensure that the bent element sensor (6) is not damaged in the insertion process of the probe rod.
Two output ends of the signal generator (S5) are respectively connected with the transmitting bending element sensor (6) and the oscilloscope (S3), and the receiving bending element sensor (13) is connected with the oscilloscope (S3). And turning on a signal generator (S5) and an oscilloscope (S3), inputting waveform parameters, simultaneously displaying an output wave and a received wave by the oscilloscope, and reading out the time difference T between the first peaks of the two waveforms. Measuring the horizontal distance L between the two probes by using a graduated scale, calculating by using the following formula to obtain the shear wave velocity v of the soil body,
and then, weights are uniformly placed on the top of the container for containing the soil body, and vertical pressures of 5kPa, 10kPa, 20kPa, 50kPa, 100kPa and 200kPa are sequentially applied to the soil body by changing the mass of the weights. And under the same vertical pressure, measuring the shear wave velocity of the soil body under the water content by changing the penetration depth of the probe rod. And then sequentially removing the weights according to the sequence of 200kPa, 100kPa, 50kPa, 20kPa, 10kPa and 5kPa, changing the penetration depth of the probe rod under the same vertical pressure, measuring the shear wave speed of the soil body under the water content condition, and thus finishing the data acquisition work of a water content sample. And then adding water into the current soil body according to a water adding amount calculation formula, uniformly mixing, and measuring the shear wave velocity of the soil body with different vertical pressures and depths when the water content is 2%, 4%, 8%, 16%, 24%, 32%, 48%, 60%, 72%, 84% and 96% respectively.
And after all the processes are completed, replacing the soil body types, and repeating the steps until the soil body shear wave velocities corresponding to all the soil body types, the water content, the dry density, the soil penetration depth and the vertical pressure are measured.
Step three: building artificial neural network model
(1) The invention adopts a BP neural network model, and an input layer has five characteristic values, namely soil trunk density, soil penetration depth, shear wave velocity, soil type and vertical pressure; the output layer only has one target value, namely the water content of the soil body.
Respectively normalizing the soil body dry density, the soil body shear wave velocity, the soil penetration depth and the vertical pressure of the characteristic values measured in the first step and the second step to enable the soil bodies to be in a [0,1] interval, and attaching different data labels to different soil body types. And taking the characteristic values and the corresponding target values as a group of data, and forming a data set by a plurality of groups of data. The normalization formula is as follows:
wherein:
is a characteristic value xiValue after normalization, xmaxIs equal to xiMaximum value, x, of the same kind of characteristic valuesminIs equal to xiThe minimum value among the homogeneous characteristic values.
The data set was written using the leave-out method as 4: the proportion of 1 is divided into mutually exclusive training sets and test sets, and meanwhile, in order to ensure the consistency of data distribution, the training sets and the test sets are divided by adopting a layered sampling method, so that the influence of extra deviation introduced in the data dividing process on the model prediction effect is avoided.
Theoretical analysis proves that the BP neural network model with the single hidden layer can map all continuous functions, the characteristic values and the target values of the model are fewer, and the requirement can be met by only arranging one hidden layer. In order to avoid the phenomenon of 'overfitting' when the number of hidden nodes is too large and the prediction precision of the neural network model is low when the number is too small, the number of the hidden nodes is determined by the model by adopting a trial-and-error method, and the empirical formula is as follows
Wherein: m is the number of hidden nodes, n is the number of nodes of an input layer, l is the number of nodes of an output layer, and alpha is a constant between 1 and 10, so that the number of the nodes of the hidden layer of the neural network model is between 3 and 12, and finally determined to be 10.
(2) Training neural networks
1. Random numbers are given to a weight matrix V ═ V1, V2,. multidot.,. Vj.,. multidot.,. V10 between the input layer and the hidden layer and a weight matrix W ═ W1 between the hidden layer and the output layer, a sample pattern counter p and a training number counter q are set to 1, an error E is set to 0, and a learning rate η is set to (0, 1)]Fractional, precision after network training EMINSet to a positive decimal number.
2. With current sample Xp、dp，XpFor the p-th set of input vectors, dpFor the p-th set of desired output vectors, OkIs the output of the kth neuron of the output layer, yjIs the output of the jth neuron of the hidden layer, xiIs the ith characteristic value of the input layer;
the vector array X, d is assigned values, and the output vector Y of the hidden layer and the output vector O of the output layer are calculated using the following formula
ok＝f(netk)
yj＝f(netj)
Wherein: f (x) is a unipolar Sigmoid function, vijRepresents the weight value, w, of the ith eigenvalue and the jth neuron connection channel of the hidden layerjkAnd showing the weight of the j-th neuron and the k-th target value connecting channel of the hidden layer, wherein net is an intermediate variable of a function f (x).
3. Calculating error signals of each layer and adjusting weight of each layer
The error is defined as follows:
hidden layer:
an input layer:
calculating error signals of each layer
Wherein:
to output the error signal of the k-th neuron of the layer,
net is the intermediate variable of the function f (x) for the error signal of the jth neuron of the hidden layer;
adjust the weight of each layer
k＝1，2，…，l j＝1，2，…，m
j＝1，2，…，m i＝0，1，，…，n
Wherein: n is the number of characteristic values of the input layer, m is the number of nodes of the hidden layer, l is the number of target values of the output layer, and the number of the target values of the output layer is equal to the number of nodes of the output layer; eta is a learning rate coefficient, and is generally 0.001-0.01.
4. Calculating the total output error E of all samplesRME
Wherein: p is the total number of training samples,
is the desired output vector for the kth target value of the pth group,
is the output vector of the kth target value of the output layer of the pth group,
5. looping through steps 2-4 ensures that all samples complete the round (i.e., the steps of p +1 and q +1 in the flowchart).
6. Checking whether the total error of the network meets the precision requirement, if ERME＜EMINThe training is ended, otherwise the total error E is determinedRMEAnd (4) setting 0, setting the sample count p to 1, and retraining all samples according to the steps 2-5 until the error meets the precision requirement.
Step four: access data management platform
And writing the trained artificial neural network model into an embedded computer chip (S4), and connecting the input and output ends of the embedded computer chip with the interface of the data management platform (S6). The data management platform (S6) has the functions of data import, storage, modification, calculation, calling, export, visualization and the like.
When the water content of soil in a certain area needs to be measured, parameters such as the soil type, the dry density and the like of the area are called through an interface of a data management platform (S6).
Inserting a probe rod into the soil body to measure the shear wave velocity, and reading the penetration depth through a graduated scale (4) on the surface of the probe rod (2);
the vertical pressure can be obtained by conversion according to construction parameters of foundation treatment machines such as a road roller and the like, and the vertical pressure corresponding to the foundation treatment machines such as the road roller and the like is stored in a data management platform and can be directly called when needed or can be manually calculated and input.
And inputting the obtained soil type, soil dry density, soil shear wave velocity, soil penetration depth and vertical stress into the trained artificial neural network model by using the obtained soil type, soil dry density, soil shear wave velocity, soil penetration depth and vertical stress as characteristic values. After the artificial neural network model in the embedded computer chip (S4) obtains all the characteristic values, the water content of the soil body is automatically calculated, and all the characteristic values and the target values predicted by the model are uploaded to a data management platform (S6) through an interface for storage.
The measuring method can be applied to measuring the water content of the soil body after the roadbed is compacted on site, so that the introduction of the vertical pressure is necessary, and the vertical pressure can be obtained according to actual construction.
The soil moisture content detection system based on the bending element sensor is provided with manual input, data offline storage and model updating, when communication with a database of a data management platform (S6) related to soil parameters can not be obtained temporarily due to data transmission and the like, related characteristic values can be manually input through an external input device connected with an embedded computer chip, the model calculates target value moisture content and stores the data in a memory of the computer chip in an offline mode after calculating target value moisture content, a data set obtained in the measuring process is stored after data transmission is recovered, the data set and real values of a moisture content sampling sample within a period of time are uploaded to the data management platform (S6), expanded data can be used for training an artificial neural network model in real time, the updated artificial neural network model is written into the embedded computer chip (S4) again, and model prediction accuracy is improved, and self-updating of the database and the artificial neural network model is realized. In the field roadbed construction process, the water content of the soil body in the construction process is measured in time by using the artificial neural network model, a detection department randomly samples a part of predicted soil body on site to obtain a real water content value corresponding to the characteristic value of the soil sample, and the sampled characteristic value and real value are recorded as a new data set for updating the artificial neural network model.
Nothing in this specification is said to apply to the prior art.
Claims (9)
1. A soil moisture content detection method comprises the following steps:
obtaining soil body dry densities of different kinds of soil bodies, measuring the soil body dry densities, the soil penetration depths, the shear wave speeds under vertical pressure and the corresponding water contents of different soil body types, and corresponding the water contents, the soil body dry densities, the soil penetration depths, the soil body types, the vertical pressure and the shear wave speeds to form a data set;
constructing an artificial neural network model by taking the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of a soil body as characteristic values and the water content as target values, and training the artificial neural network model by using a data set to obtain a trained artificial neural network model;
and inputting the dry density, the penetration depth, the shear wave velocity, the soil type and the vertical pressure of the soil body to be detected into the trained artificial neural network model to obtain the water content of the soil body.
2. A curved element sensor embedded penetration device, comprising: the soil-penetrating device comprises two vertical parallel probe rods (2) and a connecting rod (1) fixedly connected with the two parallel probe rods, and is characterized in that a graduated scale (4) is carved on each parallel probe rod, each probe rod (2) is a multilayer telescopic loop rod, loop rods of adjacent layers are connected through a spring buckle, the next loop rod connected to the spring buckle extends out after the spring buckle is pressed down, the graduated scale on the surface of each multilayer telescopic loop rod is continuous when the telescopic loop rods are all unfolded, the number of unfolded layers of the telescopic loop rods is changed according to the soil penetration depth, and the graduated range of the telescopic loop rods is guaranteed to be always larger than the soil penetration depth;
a hollow rod is coaxially arranged in the probe rod, the hollow rod is fixedly connected with the inner wall of the innermost sleeve rod, a screw rod penetrates through the hollow rod and penetrates out of the probe rod, the screw rod is eccentrically arranged, the bottom of the screw rod is fixedly connected with a first triangular sliding block, a rotating nut is arranged at the upper part of the screw rod, and the rotating nut can control the screw rod to move up and down to drive the first triangular sliding block at the bottom end of the screw rod (9) to move up and down;
a hole site for pushing out the bending element sensor is reserved on the upper pipe wall of the tail end probe rod, a guide rail (14) for moving the bending element sensor is arranged on the horizontal plane of the hole site, the guide rail is fixed inside the innermost layer loop bar and fixed with the inner wall of the innermost layer loop bar, the inner side of the bending element sensor is connected with a second triangular slide block, two inclined planes of the first triangular slide block and the second triangular slide block are in contact, the first triangular slide block extrudes the second triangular slide block through the inclined plane in the up-and-down moving process of the screw rod, the second triangular slide block moves in the horizontal direction along the guide rail (14) to push out the bending element sensor from the hole site, one bending element sensor on the two probe rods is used for receiving the bending element sensor, and the other bending element sensor is used for transmitting the bending element sensor.
3. The penetration device according to claim 2, wherein a spring is fixedly installed between the second triangular sliding block above the bending element sensor and the inner wall of the probe rod, when the bending element sensor is retracted, the nut is rotated reversely, and when the spring (15) is released from a compressed state, the second triangular sliding block is pushed inwards to reset the bending element sensor.
4. The penetration device according to claim 2, wherein two bending element sensor protection structures (5) are symmetrically arranged on the probe tube wall of the push-out hole of the bending element sensor (6) up and down with the bending element sensor as the center.
5. The penetration device of claim 2, wherein the hollow rod has an inner diameter greater than the diameter of the threaded rod and is capable of receiving a cable.
6. A soil body moisture content detection system based on a bending element sensor is characterized by comprising a penetration device with a built-in bending element sensor, an electric signal generation module, an electric signal receiving and processing module and a data management platform (S6); after the penetration device with the built-in bending element sensor reaches the target depth of a soil body, applying regular waveforms with set voltage and frequency to the transmitting bending element sensor through the electric signal generating module, forcing the transmitting bending element to drive the surrounding soil body to generate transverse vibration through piezoelectric effect, driving the receiving bending element sensor at the other end to vibrate through the soil body by shear waves generated in the direction vertical to the vibration, finally transmitting weak current generated by the receiving bending element sensor into the electric signal receiving and processing module, and interconnecting and communicating the electric signal receiving and processing module and data of the data management platform;
the data management platform is connected with the electric signal receiving and processing module through a 5G network to realize data interaction; in addition, both the transmitting and receiving bending element sensors need to be inserted into the soil body to be measured at the same depth.
The electric signal generating module is used for generating an electric signal;
the electric signal receiving and processing module comprises: a signal amplifier (S2), an oscilloscope (S3) and an embedded computer chip (S4); the input of the signal amplifier is connected with and receives the electrical signal of the bending element sensor, the oscilloscope is connected with the output of the signal amplifier and the output of the signal generator at the same time, the output of the oscilloscope is connected with the embedded computer chip, and the embedded computer chip is communicated with the data management platform (S6);
the data management platform is provided with a database related to soil body parameters and has the functions of data import, storage, modification, calculation, calling, export and visualization.
7. The soil moisture content detection system according to claim 6, wherein the detection system adopts the penetration device with the built-in bending element sensor according to any one of claims 2 to 5 to measure the shear wave velocity of the soil.
8. A soil moisture content detection method is characterized by comprising the following steps:
1) preparation of test specimens
Selecting different types of soil bodies, screening, removing impurities, drying and weighing, measuring initial water content and dry density of the soil bodies, and controlling the water content in the soil bodies by changing the water adding amount to obtain test samples of the different soil bodies with different water contents;
2) collecting raw data
Applying different vertical pressures on the surfaces of different test samples aiming at the test samples, changing the penetration depth of the bending element sensor, measuring the shear wave velocity of the different test samples under different vertical pressures and different penetration depths, and taking the dry density, the penetration depth, the soil type, the vertical pressure, the shear wave velocity and the corresponding water content of the soil body as a group of data so as to obtain a plurality of groups of data of all the test samples to form a data set;
3) building artificial neural network model
Taking soil body dry density, soil penetration depth, shear wave velocity, soil body type and vertical pressure as characteristic values and water content as target values, performing round training on all data sets until errors meet limit values, determining the limit values according to precision required by field measurement, and obtaining a trained artificial neural network model, namely a shear wave velocity-water content prediction model;
4) access data management platform
Writing the trained artificial neural network model into an embedded computer chip, accessing the embedded computer chip into a data management platform, obtaining soil body dry density, vertical pressure and soil body type from the data management platform, and inputting the soil body shear wave speed and the soil penetration depth measured on site to obtain the soil body water content of site construction;
and after the on-site roadbed is compacted, applying the trained artificial neural network model to predict the water content of the soil body, simultaneously carrying out water content sampling inspection periodically, recording the characteristic value and the sampling inspection true value of a corresponding sample during water content sampling inspection to form a new data set, and transmitting the new data set back to the data management platform for expanding the database of the data management platform and updating the artificial neural network model.
9. The soil moisture content detection method according to claim 8, wherein the process of collecting the raw data is:
taking a part of dried soil with the mass of M, adding water into the dried soil according to a water adding amount calculation formula, and uniformly mixing to ensure that the water content of the soil is 1%;
water addition MwFormula for calculation
Wherein: w, water content preset for soil body, w1The water content of the soil body before adding water;
then vertically inserting the probe rods of the two built-in bending element sensors (6) into the soil body, ensuring the same penetration depth through a graduated scale (4) on the outer wall of the probe, and recording the penetration depth h;
two output ends of a signal generator (S5) are respectively connected with a transmitting bending element sensor (6) and an oscilloscope (S3), and a receiving bending element sensor (13) is connected with the oscilloscope (S3); opening a signal generator (S5) and an oscilloscope (S3), inputting waveform parameters, simultaneously displaying output waves and received waves by the oscilloscope, reading out the time difference T between the first wave crests of the two waveforms, measuring the horizontal distance L between the two probe rods by using a graduated scale, calculating to obtain the shear wave velocity v of the soil body by the following formula,
then, weights are uniformly placed on the top of the container for containing the soil body, and vertical pressures of 5kPa, 10kPa, 20kPa, 50kPa, 100kPa and 200kPa are sequentially applied to the soil body by changing the mass of the weights; under the same vertical pressure, measuring the shear wave velocity of the soil body under the water content by changing the penetration depth of the probe rod;
sequentially removing the weights according to the sequence of 200kPa, 100kPa, 50kPa, 20kPa, 10kPa and 5kPa, changing the penetration depth of the probe rod under the same vertical pressure, measuring the shear wave speed of the soil body under the water content condition, and thus finishing the data acquisition work of a water content sample;
adding water into the current soil body according to a water adding amount calculation formula, uniformly mixing, and measuring the shear wave velocities of the soil body with different vertical pressures and depths when the water contents are 2%, 4%, 8%, 16%, 24%, 32%, 48%, 60%, 72%, 84% and 96% respectively;
and after all the processes are completed, replacing the soil body types, and repeating the steps until the soil body shear wave velocities corresponding to all the soil body types, the water content, the dry density, the soil penetration depth and the vertical pressure are measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110534793.5A CN113267612B (en) | 2021-05-17 | 2021-05-17 | Soil moisture content detection method, detection system and penetration device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110534793.5A CN113267612B (en) | 2021-05-17 | 2021-05-17 | Soil moisture content detection method, detection system and penetration device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113267612A true CN113267612A (en) | 2021-08-17 |
| CN113267612B CN113267612B (en) | 2023-05-16 |
Family
ID=77231290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110534793.5A Active CN113267612B (en) | 2021-05-17 | 2021-05-17 | Soil moisture content detection method, detection system and penetration device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113267612B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229285A (en) * | 2023-05-06 | 2023-06-06 | 深圳大学 | Soil water content monitoring method integrating Internet of things data and space scene |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108007798A (en) * | 2017-10-24 | 2018-05-08 | 湖南大学 | Penetration type soil strength and velocity of wave joint test device and its application method |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
-
2021
- 2021-05-17 CN CN202110534793.5A patent/CN113267612B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108007798A (en) * | 2017-10-24 | 2018-05-08 | 湖南大学 | Penetration type soil strength and velocity of wave joint test device and its application method |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
Non-Patent Citations (3)
| Title |
|---|
| 于永堂等: "基于贯入阻力与含水率联测的黄土填方压实度检测方法", 《长江科学院院报》 * |
| 谢伟等: "含水率对路基压实土小应变剪切模量的影响规律", 《岩土力学》 * |
| 郭庆春等: "基于BP人工神经网络的土壤含水量预测模型的研究", 《山东农业科学》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229285A (en) * | 2023-05-06 | 2023-06-06 | 深圳大学 | Soil water content monitoring method integrating Internet of things data and space scene |
| CN116229285B (en) * | 2023-05-06 | 2023-08-04 | 深圳大学 | Soil water content monitoring method integrating Internet of things data and space scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113267612B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117540A (en) | A kind of probability statistical analysis method solving dam concrete mechanics parameter inverting nonuniqueness | |
| US20090112489A1 (en) | Methods and systems for modeling material behavior | |
| WO2009117784A1 (en) | System, apparatus and method for measuring soil moisture content | |
| CN103174122B (en) | Lateral stress pore pressure probe used for testing soil static lateral pressure coefficient | |
| Jaksa et al. | Geostatistical modelling of the spatial variation of the shear strength of a stiff, overconsolidated clay | |
| Evett et al. | Neutron scattering, capacitance, and TDR soil water content measurements compared on four continents | |
| CN108152235A (en) | The content of beary metal inversion method of external spectrum in a kind of joint soil chamber | |
| Fatehnia et al. | Correlation between shear wave velocity and SPT-N values for North Florida soils | |
| CN113267612B (en) | Soil moisture content detection method, detection system and penetration device | |
| CN110485409B (en) | Composite pile construction method based on ground universe full-period actual measurement data | |
| Scheuermann et al. | Fast time domain reflectometry (TDR) measurement approach for investigating the liquefaction of soils | |
| CN203361120U (en) | Pore pressure static sounding test device | |
| CN105277439A (en) | Geotechnical triaxial test sample radial deformation testing device and method | |
| DE102011001153A1 (en) | Measuring probe for measuring properties of substrate, has heating unit and temperature sensors that are arranged on main portion, to detect thermodynamic properties of to-be-examined substrate | |
| CN108692969A (en) | A kind of Sandy Soil Moisture monitoring method and system | |
| CN108593525A (en) | A kind of rock three-dimensional permeability real-time determining device and method | |
| CN110455712B (en) | Sample preparation device and test method for measuring adhesion force between special curved surface and soil interface by inverted sample preparation | |
| CN202809591U (en) | Static cone penetration system | |
| Xie et al. | Characterizing plant root parameters with deep learning-based heat pulse method | |
| CN113973403B (en) | Temperature-induced strain field redistribution intelligent sensing method based on structure discrete measurement point topology | |
| Heitor et al. | Assessment of the post-compaction characteristics of a silty sand | |
| CN103323569A (en) | Variable-rate pore pressure static sounding test device | |
| CN210037508U (en) | Simple and easy testing tool of ground body moisture content | |
| Yan et al. | Application of Spatial Time Domain Reflectometry for investigating moisture content dynamics in unsaturated sand | |
| CN112884739A (en) | Rapid detection method for rockfill filling compactness based on deep learning network |
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 |