CN113063930A - 3D printing concrete mechanical property online monitoring method based on neural network - Google Patents
3D printing concrete mechanical property online monitoring method based on neural network Download PDFInfo
- Publication number
- CN113063930A CN113063930A CN202110300250.7A CN202110300250A CN113063930A CN 113063930 A CN113063930 A CN 113063930A CN 202110300250 A CN202110300250 A CN 202110300250A CN 113063930 A CN113063930 A CN 113063930A
- Authority
- CN
- China
- Prior art keywords
- printing
- mechanical property
- neural network
- concrete
- layer
- 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
- 238000010146 3D printing Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 27
- 238000007639 printing Methods 0.000 claims abstract description 153
- 230000008859 change Effects 0.000 claims abstract description 39
- 238000003062 neural network model Methods 0.000 claims abstract description 27
- 238000010586 diagram Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 239000010410 layer Substances 0.000 claims description 80
- 239000000835 fiber Substances 0.000 claims description 53
- 239000000463 material Substances 0.000 claims description 46
- 238000012360 testing method Methods 0.000 claims description 23
- 238000001125 extrusion Methods 0.000 claims description 19
- 239000002356 single layer Substances 0.000 claims description 14
- 238000002156 mixing Methods 0.000 claims description 13
- 239000011229 interlayer Substances 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000003756 stirring Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 239000007921 spray Substances 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 3
- 230000001154 acute effect Effects 0.000 claims description 2
- 238000004088 simulation Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000011160 research Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
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
- G01N33/38—Concrete; Lime; Mortar; Gypsum; Bricks; Ceramics; Glass
- G01N33/383—Concrete or cement
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Ceramic Engineering (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
Abstract
The invention discloses a neural network-based 3D printing concrete mechanical property online monitoring method, which comprises the following steps: step one, training a neural network model: training a neural network to be mature by taking the mechanical property of the 3D printed concrete as an output value; step two, model input feature acquisition: inputting a constant characteristic value and acquiring a change characteristic value in real time; step three, monitoring the mechanical property on line: calculating the mechanical property of a 3D printing concrete printing finished product through a mature neural network model based on the collected characteristic data; step four, monitoring the result reaction: and evaluating the mechanical property state of the 3D printed concrete printing finished product based on the monitoring result, drawing a product mechanical property distribution diagram, formulating an adjusting scheme and realizing human-computer interaction. The method can realize the simulation and prediction of the mechanical property distribution of the printed finished product before 3D printing, the monitoring and evaluation of the mechanical property of the concrete 3D printed finished product in the 3D printing process and the drawing of the mechanical property distribution diagram of the product, and can be used for optimizing the printing path of the product and guiding the use of the product.
Description
Technical Field
The invention belongs to the technical field of 3D printed concrete, and particularly relates to a neural network-based 3D printed concrete mechanical property online monitoring method.
Background
The 3D printing concrete technology is a construction technology for building the whole component by moving an extrusion head to extrude in strips and superposing layer by layer according to a set three-dimensional path, and due to the construction mode that the 3D printing concrete technology is formed by stacking along the extrusion direction of a nozzle, the physical structure of the 3D printing concrete has directionality, and further the mechanical property, the durability, the microstructure and the like of a 3D printing concrete printing finished product have directionality, namely anisotropy, so that the difficulty is brought to the performance detection of the 3D printing concrete. The mechanical properties of ordinary concreting test piece only need detect arbitrary one orientation can, and 3D prints the mechanical properties of concrete and is different in 3 directions in three-dimensional space, so detect the mechanical properties of a 3D printing concrete test piece completely, need detect three groups of test pieces at least, this has increased the detection amount of labour undoubtedly.
The anisotropy of 3D printed concrete is influenced by printing materials, construction technology and construction environment, in one-time printing process, some of the influencing factors are constant, such as the length and diameter of fibers in the printing materials and the shape and diameter of an outlet of a printing nozzle, and some of the influencing factors can change along with the printing process, such as the time, extrusion pressure, environment temperature and the like of the printing materials after being mixed by adding water, and due to the complex influencing factors, the relation is difficult to express by depending on a certain specific formula, so that the difficulty is brought to the monitoring and control of the mechanical property of a 3D printed concrete finished product.
The neural network model is an artificial neural network model evolved based on the research result of human brain neuroscience in biology, has nonlinear processing capability and self-learning capability exceeding general physical mathematical formulas, and is suitable for processing complex nonlinear relations in the field of concrete material science.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a neural network-based 3D printed concrete mechanical property online monitoring method, which can be used for researching the influence factors and the influence rules of the 3D printed concrete mechanical property, realizing the simulation and prediction of the mechanical property distribution of a printed finished product before 3D printing, monitoring and evaluating the mechanical property of a concrete 3D printed concrete printed finished product in the 3D printing process, and drawing a product mechanical property distribution diagram, and can be used for optimizing a product printing path and guiding the use of a product.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a neural network-based 3D printing concrete mechanical property online monitoring method, which comprises the following steps:
step one, training a neural network model. Training a neural network model to be mature by taking the performance parameters of the printing material, the system printing parameters and the environmental parameters as training data and taking the mechanical property of the 3D printing concrete as an output value;
and step two, collecting model input characteristics. Acquiring a constant characteristic value, a time change characteristic value, a change characteristic value extracted from a printing path in real time and a change characteristic value acquired by a sensor in real time, and using the acquired data for online monitoring;
and step three, monitoring the mechanical property on line. Inputting the characteristic data collected in the second step into the trained neural network model in the first step to calculate the mechanical property of the 3D printing concrete printing finished product;
and step four, monitoring the result reaction. And evaluating the mechanical property state of the printed product based on the monitoring result of the step three, drawing a product mechanical property distribution diagram, formulating an adjustment scheme, realizing man-machine interaction and executing a selection scheme.
As a preferred technical solution, in the first step, the neural network model training data includes:
printing material performance parameters: the yield stress of the machine, the viscosity of the machine, the fluidity of the machine, the mixing amount of fibers, the length of the fibers, the diameter of the fibers, the elastic modulus of the fibers, the time for the material to be discharged, the mechanical property of a pouring test piece and the mechanical property of 3D printed concrete;
system printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, extrusion pressure, path crossing parameters of an upper layer and a lower layer, and printing time interval of the upper layer and the lower layer;
environmental parameters: temperature, humidity.
The yield stress, viscosity and fluidity of the printing material are the yield stress value, viscosity value and fluidity value of the printing material measured within 15min after water is added;
the fiber mixing amount, the length, the fiber diameter and the fiber elastic modulus are the mixing amount, the length, the diameter and the elastic modulus of the fibers mixed in the printing material, and the fiber length, the fiber diameter and the fiber elastic modulus are 0 when the fibers are not mixed in the printing material;
the material discharging time is the time period from the stirring of the printing material by adding water to the printing material to the extrusion of the printing material from the printing nozzle;
the mechanical properties of the pouring test piece comprise compressive strength, bending strength and tensile strength of the pouring test piece, the mechanical properties of the 3D printed concrete are characteristic values of an output layer of the neural network model, and the mechanical properties comprise three-direction compressive strength, three-direction bending strength and interlayer bonding strength of the 3D printed concrete.
The overlapping rate of the adjacent printing strips on the same layer is the ratio of the overlapping width of the adjacent printing strips on the same printing layer to the diameter of the outlet of the spray head, and when no overlapping exists, a constant 0 is taken;
the single-layer filling rate is a printing volume filling rate set by taking a layer as a unit, and can be replaced by a total volume filling rate which is not lower than 90%;
the extrusion pressure is the pressure of the printing strip on the inner wall of the printing nozzle when the printing strip is extruded from the printing nozzle;
the upper layer path cross parameter and the lower layer path cross parameter are cross angles between a certain printing layer printing strip and an adjacent lower layer printing strip, and the cross angles of the printing strips are acute angles or right angles which are not more than 90 degrees from vertical upward or vertical downward observation angles;
and the printing time interval of the upper layer and the lower layer is the time difference when the centers of the outlets of the spray heads sweep the same horizontal coordinate when the adjacent layers are printed.
As a preferred technical solution, in the second step, the collected features include:
constant eigenvalue: the yield stress, viscosity, fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, mechanical property of a pouring test piece, nozzle outlet size and nozzle outlet shape of the machine;
time-varying characteristic value: material out-of-machine time;
change feature values extracted in real time from the print path: printing layer height, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, path crossing parameters of an upper layer and a lower layer, and printing time interval of the upper layer and the lower layer;
the change characteristic value collected by the sensor in real time is as follows: extrusion pressure, temperature, humidity.
The constant characteristic value is result data obtained by detection according to relevant standards and is acquired by a manual import method;
the time change characteristic value is obtained by manually inputting the time for starting adding water and stirring the material, and calculating and collecting the time period from the beginning of adding water and stirring to the extrusion from the printing nozzle by a timer;
the change characteristic value extracted from the printing path in real time is data calculated by the characteristic acquisition module in real time according to the printing path;
the change characteristic value acquired by the sensor in real time is related data monitored by the sensor in real time in the printing process, and the extrusion pressure is monitored in real time by the pressure sensor attached to the inner wall of the printing nozzle.
As a preferred technical scheme, in the fourth step, the mechanical property data monitored on line in the third step is compared with the manually set mechanical property data, when the monitored value is greater than or equal to the set value, a mechanical property distribution diagram of the 3D printed concrete printing finished product is drawn, when the monitored value is lower than the set value, an alarm is given, an adjustment scheme is formulated, man-machine interaction is carried out, and the adjustment scheme is executed;
the mechanical property distribution diagram of the 3D printed concrete printing finished product comprises one compressive strength distribution diagram in three directions, one compressive strength anisotropic distribution diagram, one pair of flexural strength distribution diagrams in three directions, one flexural strength anisotropic distribution diagram and one interlayer bonding strength distribution diagram, and the change of the mechanical property is represented by the depth of color or the change of color;
and the adjusting scheme is obtained by calculation according to the difference value between the monitoring value and the set value. When the compressive strength or the flexural strength is low, the single-layer filling rate is increased; when the interlayer bonding strength is low, the printing time interval of the upper layer and the lower layer is reduced.
The method has the advantages that the printing path characteristic value is extracted from the planned printing path, the machine-exiting time is preset, the constant replaces the change characteristic value acquired by the sensor in real time, and the 3D printing concrete mechanical property online monitoring method based on the neural network can be used for predicting the mechanical property of the 3D printing concrete before printing.
The method has the advantages that the printing path characteristic value is extracted from the used printing path, the real time change characteristic value is input, the change characteristic value acquired by the sensor in real time is replaced by the constant, and the 3D printing concrete mechanical property online monitoring method based on the neural network can be used for calculating the mechanical property of the 3D printing concrete after printing.
Compared with the prior art, the invention has the beneficial effects that:
(1) the mechanical property of the 3D printing concrete material in all directions can be calculated by using the printing material performance parameters, the system printing parameters and the environment parameters, so that the detection process of the mechanical property of the 3D printing concrete is simplified, and manpower and material resources are saved.
(2) The method can preset printing process data before printing, further predict the mechanical property of the 3D printing concrete, and the prediction result can be used for guiding the optimization of the printing path and the printing material.
(3) The invention can monitor the mechanical property condition of the printing material in real time in the printing process, alarm abnormal conditions, formulate an adjustment scheme, interact man-machine and execute the adjustment scheme.
(4) The invention can be used for researching the influence factors and influence rules of the compressive strength, the breaking strength and the interlayer bonding strength of the 3D printed concrete.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the online monitoring method for mechanical properties of 3D printed concrete based on a neural network.
Fig. 2 is a characteristic value map required to be acquired by the invention.
FIG. 3 is a schematic diagram of neural network training according to the present invention.
FIG. 4 is a schematic diagram of the neural network calculation according to the present invention.
FIG. 5 is a schematic diagram of the mechanical property testing direction of the 3D printed concrete sample.
Wherein the reference numerals are specified as follows: the compressive strength in the Y direction is 1, the compressive strength in the X direction is 2, the compressive strength in the Z direction is 3, the flexural strength in the Y direction is 4, the flexural strength in the X direction is 5, the flexural strength in the Z direction is 6 and the interlayer bonding strength is 7.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
Example 1
The embodiment provides a method for monitoring mechanical properties of 3D printed concrete on line based on a neural network, which monitors the mechanical properties of the 3D printed concrete on line in the printing process and comprises the following steps:
step one, training a neural network model to be mature by taking the performance parameters of the printing material, the system printing parameters and the environmental parameters as training data and taking the mechanical property of the 3D printing concrete as an output value. The neural network model input data includes:
printing material performance parameters: the yield stress of the machine, the viscosity of the machine, the fluidity of the machine, the mixing amount of fibers, the length of the fibers, the diameter of the fibers, the elastic modulus of the fibers, the time for the material to be discharged, the mechanical property of a pouring test piece and the mechanical property of 3D printed concrete;
system printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, extrusion pressure, path crossing parameters of an upper layer and a lower layer, and printing time interval of the upper layer and the lower layer;
environmental parameters: temperature, humidity.
The neural network model output data comprises: y to compressive strength 1, X to compressive strength 2, Z to compressive strength 3, Y to rupture strength 4, X to rupture strength 5, Z to rupture strength 6, interlayer bonding strength 7, wherein the Z direction is for printing shower nozzle moving direction, and the Y direction is vertical range upon range of direction.
The mechanical property testing method of the pouring test piece and the 3D printed concrete test piece is carried out according to GB/T50081 and 2019 'test method standard for physical and mechanical properties of concrete'.
And step two, acquiring a constant characteristic value, a time change characteristic value, a change characteristic value extracted from the printing path in real time and a change characteristic value acquired by a sensor in real time, and using the acquired data for online monitoring.
Wherein the constant characteristic values include: the yield stress, viscosity, fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, mechanical property of a pouring test piece, nozzle outlet size and nozzle outlet shape of the machine; the time change characteristic value refers to the material machine-out time; the change characteristic values extracted in real time from the printing path include: printing layer height, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, path crossing parameters of an upper layer and a lower layer, and printing time interval of the upper layer and the lower layer; the change characteristic values acquired by the sensor in real time comprise: extrusion pressure, temperature, humidity.
And step three, inputting the characteristic data collected in the step two into the neural network model trained in the step one to calculate the mechanical property of the 3D printing concrete printing finished product.
Comparing the mechanical property data monitored on line in the step three with the manually set mechanical property data, drawing a mechanical property distribution map of a 3D printed concrete printing finished product when the monitored value is greater than or equal to the set value, alarming and reminding when the monitored value is lower than the set value, making an adjustment scheme, performing man-machine interaction, and executing the adjustment scheme;
the 3D printing concrete printing finished product mechanical property distribution diagram comprises: the three-direction compressive strength distribution diagram is one, the compressive strength anisotropy distribution diagram is one, the three-direction flexural strength distribution diagram is one, the flexural strength anisotropy distribution diagram is one, and the interlayer bonding strength distribution diagram is one. The change of the mechanical property is expressed by the shade or the change of the color;
and the adjusting scheme is obtained by calculation according to the difference value between the monitoring value and the set value. When the compressive strength or the flexural strength is low, the single-layer filling rate is increased; when the interlayer bonding strength is low, the printing time interval of the upper layer and the lower layer is reduced.
Example 2
The embodiment provides a neural network-based 3D printing concrete mechanical property online monitoring method, which is used for predicting the mechanical property of 3D printing concrete before printing, and comprises the following steps:
step one, training a neural network model to be mature by taking the performance parameters of the printing material and the system printing parameters as training data and taking the mechanical property of 3D printing concrete as an output value. The neural network model input data includes:
printing material performance parameters: the yield stress, viscosity, fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, mechanical properties of a pouring test piece and mechanical properties of 3D printed concrete;
system printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, upper and lower layer path crossing parameters and upper and lower layer printing time interval;
and step two, transmitting the constant characteristic value and the characteristic value extracted from the printing path to the neural network model trained in the step one, calculating the mechanical property of the 3D printing concrete printing finished product, and drawing a mechanical property distribution diagram of the 3D printing concrete printing finished product.
Wherein the constant characteristic values include: the yield stress, viscosity, fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, mechanical property of a pouring test piece, nozzle outlet size and nozzle outlet shape of the machine; the feature values extracted from the print path include: the printing layer height, the overlapping rate of adjacent printing strips on the same layer, the single-layer filling rate, the path crossing parameters of the upper layer and the lower layer and the printing time interval of the upper layer and the lower layer.
Example 3
The embodiment provides a method for monitoring mechanical properties of 3D printed concrete on line based on a neural network, which is used for calculating the mechanical properties of the 3D printed concrete after printing, and comprises the following steps:
step one, training a neural network model to be mature by taking the performance parameters of the printing material, the system printing parameters and the environmental parameters as training data and taking the mechanical property of the 3D printing concrete as an output value.
And step two, transmitting the actually printed constant characteristic value, the time change characteristic value, the characteristic value extracted from the printing path and the change characteristic value representative value acquired by the sensor to the neural network model trained in the step one, calculating the mechanical property of the 3D printed concrete finished product, and drawing a mechanical property distribution diagram of the 3D printed concrete finished product.
The representative value of the variation characteristic value collected by the sensor can be the median or mean value of extrusion pressure, temperature and humidity.
Example 4
The embodiment provides a method for monitoring mechanical properties of 3D printed concrete on line based on a neural network, which is used for researching mechanical property influence factors and influence rules of the 3D printed concrete, and comprises the following steps:
step one, training a neural network model to be mature by taking the performance parameters of the printing material, the system printing parameters and the environmental parameters as training data and taking the mechanical property of the 3D printing concrete as an output value. The neural network model input data includes:
printing material performance parameters: the yield stress of the machine, the viscosity of the machine, the fluidity of the machine, the mixing amount of fibers, the length of the fibers, the diameter of the fibers, the elastic modulus of the fibers, the time for the material to be discharged, the mechanical property of a pouring test piece and the mechanical property of 3D printed concrete;
system printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, extrusion pressure, path crossing parameters of an upper layer and a lower layer, and printing time interval of the upper layer and the lower layer;
environmental parameters: temperature, humidity.
The neural network model output data comprises: y to compressive strength 1, X to compressive strength 2, Z to compressive strength 3, Y to rupture strength 4, X to rupture strength 5, Z to rupture strength 6, interlayer bonding strength 7, wherein the Z direction is for printing shower nozzle moving direction, and the Y direction is vertical range upon range of direction.
The mechanical property testing method of the pouring test piece and the 3D printed concrete test piece is carried out according to GB/T50081 and 2019 'test method standard for physical and mechanical properties of concrete'.
And step two, taking a group of complete data, taking a certain input value in the neural network model as a research object, increasing or decreasing the value of the research object in a reasonable range, taking all other factors as constants to be input into the neural network model, and respectively calculating the mechanical property of the 3D printing concrete.
And step three, comparing the mechanical properties of the research object and the 3D printing concrete to obtain the rule of influence of the research object on the mechanical properties of the 3D printing concrete.
Although the present invention has been described in detail with respect to the above embodiments, it will be understood by those skilled in the art that modifications or improvements based on the disclosure of the present invention may be made without departing from the spirit and scope of the invention, and these modifications and improvements are within the spirit and scope of the invention.
Claims (10)
1. A3D printing concrete mechanical property online monitoring method based on a neural network is characterized by comprising the following steps:
step one, training a neural network model; training a neural network model to be mature by taking the performance parameters of the printing material, the system printing parameters and the environmental parameters as training data and taking the mechanical property of the 3D printing concrete as an output value;
secondly, collecting model input characteristics; acquiring a constant characteristic value, a time change characteristic value, a change characteristic value extracted from a printing path in real time and a change characteristic value acquired by a sensor in real time;
step three, monitoring the mechanical property on line; inputting the characteristic data collected in the second step into the trained neural network model in the first step to calculate the mechanical property of the 3D printing concrete printing finished product;
step four, monitoring result reaction; and evaluating the mechanical property state of the 3D printed concrete finished product based on the monitoring result of the step three, drawing a product mechanical property distribution diagram, formulating an adjustment scheme, realizing man-machine interaction and executing a selection scheme.
2. The method for on-line monitoring of mechanical properties of 3D printed concrete based on the neural network as claimed in claim 1, wherein in the first step, the training data of the neural network model comprises: printing material performance parameters, system printing parameters, and environmental parameters.
3. The online monitoring method for mechanical properties of 3D printed concrete based on the neural network as claimed in claim 2, wherein the printing material performance parameters include yield stress, viscosity, fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, material discharging time, mechanical properties of a pouring test piece, and mechanical properties of 3D printed concrete; the system printing parameters comprise printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, extrusion pressure, upper and lower layer path crossing parameters and upper and lower layer printing time interval; the environmental parameters comprise temperature and humidity.
4. The online monitoring method for the mechanical property of 3D printed concrete based on the neural network as claimed in claim 3, wherein the out-machine yield stress, out-machine viscosity and out-machine fluidity are material yield stress value, viscosity value and fluidity value measured within 15min after the printing material is added with water; the fiber mixing amount, the length, the fiber diameter and the fiber elastic modulus are the mixing amount, the length, the diameter and the elastic modulus of the fibers mixed in the printing material, and the fiber length, the fiber diameter and the fiber elastic modulus are 0 when the fibers are not mixed in the printing material; the material discharging time is the time period from the stirring of the printing material by adding water to the printing material to the extrusion of the printing material from the printing nozzle; the mechanical properties of the pouring test piece comprise compressive strength, flexural strength and tensile strength of the pouring test piece, and the mechanical properties of the 3D printed concrete are characteristic values of an output layer of the neural network model, and comprise three-direction compressive strength, three-direction flexural strength and interlayer bonding strength of the 3D printed concrete; the overlapping rate of the adjacent printing strips on the same layer is the ratio of the overlapping width of the adjacent printing strips on the same printing layer to the diameter of the outlet of the spray head, and when no overlapping exists, a constant 0 is taken; the single-layer filling rate is the printing volume filling rate set by taking a layer as a unit and is not lower than 90 percent; the extrusion pressure is the pressure of the printing strip on the inner wall of the printing nozzle when the printing strip is extruded from the printing nozzle; the upper layer path cross parameter and the lower layer path cross parameter are cross angles between a certain printing layer printing strip and an adjacent lower layer printing strip, and the cross angles of the printing strips are acute angles or right angles which are not more than 90 degrees from vertical upward or vertical downward observation angles; and the printing time interval of the upper layer and the lower layer is the time difference when the centers of the outlets of the spray heads sweep the same horizontal coordinate when the adjacent layers are printed.
5. The method for on-line monitoring of mechanical properties of 3D printed concrete based on the neural network as claimed in claim 1, wherein in the second step, the collected characteristics include: the system comprises a constant characteristic value, a time change characteristic value, a change characteristic value extracted from a printing path in real time and a change characteristic value acquired by a sensor in real time.
6. The neural network-based 3D printing concrete mechanical property online monitoring method as claimed in claim 5, wherein the constant characteristic values comprise output yield stress, output viscosity, output fluidity, fiber mixing amount, fiber length, fiber diameter, fiber elastic modulus, pouring test piece mechanical property, nozzle outlet size and nozzle outlet shape; the time change characteristic value comprises the material out-of-machine time; the change characteristic values extracted from the printing paths in real time comprise printing layer height, overlapping rate of adjacent printing strips on the same layer, single-layer filling rate, path crossing parameters of an upper layer and a lower layer, and printing time intervals of the upper layer and the lower layer; the change characteristic values acquired by the sensor in real time comprise extrusion pressure, temperature and humidity.
7. The on-line monitoring method for mechanical properties of 3D printed concrete based on the neural network as claimed in claim 5, wherein the constant characteristic value is result data obtained by detection and is collected by a manual importing method; the time change characteristic value is obtained by manually inputting the time for starting adding water and stirring the material, and calculating and collecting the time period from the beginning of adding water and stirring to the extrusion from the printing nozzle by a timer; the change characteristic value extracted from the printing path in real time is data calculated by the characteristic acquisition module in real time according to the printing path; the change characteristic value acquired by the sensor in real time is related data monitored by the sensor in real time in the printing process, and the extrusion pressure is monitored in real time by the pressure sensor attached to the inner wall of the printing nozzle.
8. The online monitoring method for mechanical properties of 3D printed concrete based on neural network as claimed in claim 1, wherein in step four, the mechanical property data of the 3D printed concrete printed finished product monitored online in step three is compared with the manually set mechanical property data, when the monitored value is greater than or equal to the set value, the mechanical property distribution map of the 3D printed concrete printed finished product is drawn, when the monitored value is lower than the set value, an alarm is given, an adjustment scheme is formulated, man-machine interaction is performed, and the adjustment scheme is executed.
9. The method for on-line monitoring of mechanical properties of 3D printed concrete based on neural network as claimed in claim 8, wherein the distribution map of mechanical properties of the 3D printed concrete comprises one of a distribution map of compressive strength in three directions, one of anisotropic distribution maps of compressive strength, one of each pair of a distribution map of flexural strength in three directions, one of anisotropic distribution maps of flexural strength, and one of a distribution map of interlayer bonding strength, and the change of mechanical properties is expressed by the shade or color change.
10. The online monitoring method for mechanical properties of 3D printed concrete based on the neural network as claimed in claim 8, wherein the adjustment scheme is calculated according to the difference between the monitored value and the set value, and when the compressive strength or the flexural strength is low, the single-layer filling rate is increased; when the interlayer bonding strength is low, the printing time interval of the upper layer and the lower layer is reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110300250.7A CN113063930B (en) | 2021-03-22 | 2021-03-22 | Neural network-based 3D printed concrete mechanical property online monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110300250.7A CN113063930B (en) | 2021-03-22 | 2021-03-22 | Neural network-based 3D printed concrete mechanical property online monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113063930A true CN113063930A (en) | 2021-07-02 |
| CN113063930B CN113063930B (en) | 2024-01-23 |
Family
ID=76563377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110300250.7A Active CN113063930B (en) | 2021-03-22 | 2021-03-22 | Neural network-based 3D printed concrete mechanical property online monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113063930B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884357A (en) * | 2021-10-08 | 2022-01-04 | 南京工业大学 | Characterization method of mechanical index of printed concrete based on extrusion forming process |
| CN114136820A (en) * | 2021-11-29 | 2022-03-04 | 东南大学 | Testing method for in-situ characterization of 3D printing concrete anisotropy |
| CN115306157A (en) * | 2022-08-30 | 2022-11-08 | 同济大学 | Concrete structure 5D printing method and printing system |
| WO2023107026A1 (en) * | 2021-12-10 | 2023-06-15 | Uray Esra | An optimization method of material mixture used in temporary concrete houses constructed with a 3d printer after disasters |
| CN117420011A (en) * | 2023-12-18 | 2024-01-19 | 南京建正建设工程质量检测有限责任公司 | Concrete brick multipoint compressive strength detection system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100774301B1 (en) * | 2007-02-13 | 2007-11-08 | 군산대학교산학협력단 | Method of predicting the compressive strength of concrete |
| JP2017087716A (en) * | 2015-09-30 | 2017-05-25 | 太平洋セメント株式会社 | Prediction method for concrete quality or concrete blending condition |
| CN109531769A (en) * | 2018-11-10 | 2019-03-29 | 东南大学 | A kind of anisotropic design of reduction 3D printing concrete and detection method |
| CN112252292A (en) * | 2020-10-15 | 2021-01-22 | 河北工业大学 | Real-time highway compactness monitoring method based on artificial neural network |
-
2021
- 2021-03-22 CN CN202110300250.7A patent/CN113063930B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100774301B1 (en) * | 2007-02-13 | 2007-11-08 | 군산대학교산학협력단 | Method of predicting the compressive strength of concrete |
| JP2017087716A (en) * | 2015-09-30 | 2017-05-25 | 太平洋セメント株式会社 | Prediction method for concrete quality or concrete blending condition |
| CN109531769A (en) * | 2018-11-10 | 2019-03-29 | 东南大学 | A kind of anisotropic design of reduction 3D printing concrete and detection method |
| CN112252292A (en) * | 2020-10-15 | 2021-01-22 | 河北工业大学 | Real-time highway compactness monitoring method based on artificial neural network |
Non-Patent Citations (5)
| Title |
|---|
| JIANJING ZHANG ET AL.: "Deep learning-based tensile strength prediction in fused deposition modeling", 《COMPUTERS IN INDUSTRY》 * |
| JIANJING ZHANG ET AL.: "Deep learning-based tensile strength prediction in fused deposition modeling", 《COMPUTERS IN INDUSTRY》, 31 December 2019 (2019-12-31), pages 11 - 21 * |
| KANG TAN: "Predicting Compressive Strength of Recycled Concrete for Construction 3D Printing Based on Statistical Analysis of Various Neural Networks", 《JOURNAL OF BUILDING CONSTRUCTION AND PLANNING RESEARCH》, pages 71 - 89 * |
| MUHAMMAD ARIF MAHMOOD ET AL.: "Artificial Neural Network Algorithms for 3D Printing", 《MATERIALS》, pages 1 - 27 * |
| 雷斌;马勇;熊悦辰;胡小荣;: "3D打印混凝土材料制备方法研究", 混凝土, no. 02, pages 145 - 153 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884357A (en) * | 2021-10-08 | 2022-01-04 | 南京工业大学 | Characterization method of mechanical index of printed concrete based on extrusion forming process |
| CN114136820A (en) * | 2021-11-29 | 2022-03-04 | 东南大学 | Testing method for in-situ characterization of 3D printing concrete anisotropy |
| CN114136820B (en) * | 2021-11-29 | 2024-02-02 | 东南大学 | Test method for in-situ characterization of 3D printing concrete anisotropy |
| WO2023107026A1 (en) * | 2021-12-10 | 2023-06-15 | Uray Esra | An optimization method of material mixture used in temporary concrete houses constructed with a 3d printer after disasters |
| CN115306157A (en) * | 2022-08-30 | 2022-11-08 | 同济大学 | Concrete structure 5D printing method and printing system |
| CN115306157B (en) * | 2022-08-30 | 2024-01-26 | 同济大学 | 5D printing method and system for concrete structure |
| WO2024045331A1 (en) * | 2022-08-30 | 2024-03-07 | 同济大学 | Concrete structure 5d printing method and system |
| CN117420011A (en) * | 2023-12-18 | 2024-01-19 | 南京建正建设工程质量检测有限责任公司 | Concrete brick multipoint compressive strength detection system |
| CN117420011B (en) * | 2023-12-18 | 2024-03-15 | 南京建正建设工程质量检测有限责任公司 | Concrete brick multipoint compressive strength detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113063930B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113063930B (en) | Neural network-based 3D printed concrete mechanical property online monitoring method | |
| CN108500498B (en) | Weld joint forming quality monitoring method | |
| CN109490072B (en) | Detection system for civil engineering building and detection method thereof | |
| CN108709856B (en) | Concrete structure crack monitoring and early warning system and early warning method | |
| CN103777627A (en) | Batch process online-monitoring method based on small number of batches | |
| CN102885392A (en) | Quality monitoring system and method of tobacco primary process | |
| CN106097819A (en) | Bridge for experimental teaching emulates detection method and system | |
| CN106918550A (en) | A kind of optical fiber sensing monitoring steel bar corrosion method | |
| CN106970036B (en) | A kind of determination method of pollution severity of insulators degree | |
| CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
| CN105243193B (en) | A kind of method for determining creep test prism test specimen compression strength conversion factor | |
| CN105400915A (en) | Method and system for quantitatively evaluating distribution of gas flows on blast furnace top | |
| CN101825646B (en) | Method for measuring flow rate of thin water flow by electrolyte tracing | |
| CN106570286A (en) | Bridge-ballastless track structure extreme temperature prediction method and system | |
| CN113340344A (en) | Hydraulic climbing mould intelligent monitoring control early warning system based on digital twin technology | |
| CN115563683A (en) | Hydraulic engineering automatic safety monitoring management system based on digital twins | |
| CN106932337A (en) | The data processing method of multi fiber grating steel reinforcement corrosion sensor system | |
| CN103353295A (en) | Method for accurately predicating vertical deformation of dam body | |
| CN106649202B (en) | Industrial process flexible measurement method based on diversity variable weighting PLSR model | |
| CN106709149B (en) | A kind of aluminium cell three-dimensional burner hearth shape real-time predicting method neural network based and system | |
| He et al. | Refined fatigue damage assessment of RC beam based on fractal characteristics of cracks | |
| CN116579214A (en) | Digital twinning-based three-dimensional visual bridge pier monitoring system and method | |
| CN102608303B (en) | Online rubber hardness measurement method | |
| CN107449828B (en) | A kind of rock-fill concrete structure space compactness inspection method and evaluation method | |
| CN107133473B (en) | Hydrologic design values estimation method in two variable hydrologic(al) frequency analysis under a kind of changing environment |
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 |