CN110715953A - System and method for testing heat-conducting property of film material based on machine learning - Google Patents
System and method for testing heat-conducting property of film material based on machine learning Download PDFInfo
- Publication number
- CN110715953A CN110715953A CN201910881533.8A CN201910881533A CN110715953A CN 110715953 A CN110715953 A CN 110715953A CN 201910881533 A CN201910881533 A CN 201910881533A CN 110715953 A CN110715953 A CN 110715953A
- Authority
- CN
- China
- Prior art keywords
- submicron
- film material
- nanometer
- tested
- data
- 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
- 239000000463 material Substances 0.000 title claims abstract description 123
- 238000012360 testing method Methods 0.000 title claims abstract description 52
- 238000010801 machine learning Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 238000009529 body temperature measurement Methods 0.000 claims abstract description 3
- 239000010408 film Substances 0.000 claims description 67
- 238000004088 simulation Methods 0.000 claims description 26
- 238000012937 correction Methods 0.000 claims description 19
- 230000003746 surface roughness Effects 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 12
- 239000010409 thin film Substances 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 7
- 238000002474 experimental method Methods 0.000 claims description 5
- 239000002120 nanofilm Substances 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000013179 statistical model Methods 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 3
- 238000010998 test method Methods 0.000 claims description 2
- 238000002076 thermal analysis method Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 2
- 238000012876 topography Methods 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000013473 artificial intelligence Methods 0.000 description 9
- 238000011160 research Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003121 nonmonotonic effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/20—Investigating or analyzing materials by the use of thermal means by investigating the development of heat, i.e. calorimetry, e.g. by measuring specific heat, by measuring thermal conductivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/30—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/20—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by using diffraction of the radiation by the materials, e.g. for investigating crystal structure; by using scattering of the radiation by the materials, e.g. for investigating non-crystalline materials; by using reflection of the radiation by the materials
- G01N23/2055—Analysing diffraction patterns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/08—Investigating strength properties of solid materials by application of mechanical stress by applying steady tensile or compressive forces
- G01N3/10—Investigating strength properties of solid materials by application of mechanical stress by applying steady tensile or compressive forces generated by pneumatic or hydraulic pressure
- G01N3/12—Pressure testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01Q—SCANNING-PROBE TECHNIQUES OR APPARATUS; APPLICATIONS OF SCANNING-PROBE TECHNIQUES, e.g. SCANNING PROBE MICROSCOPY [SPM]
- G01Q60/00—Particular types of SPM [Scanning Probe Microscopy] or microscopes; Essential components thereof
- G01Q60/24—AFM [Atomic Force Microscopy] or apparatus therefor, e.g. AFM probes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0014—Type of force applied
- G01N2203/0016—Tensile or compressive
- G01N2203/0019—Compressive
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/026—Specifications of the specimen
- G01N2203/0262—Shape of the specimen
- G01N2203/0278—Thin specimens
- G01N2203/0282—Two dimensional, e.g. tapes, webs, sheets, strips, disks or membranes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/0641—Indicating or recording means; Sensing means using optical, X-ray, ultraviolet, infrared or similar detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/067—Parameter measured for estimating the property
- G01N2203/0682—Spatial dimension, e.g. length, area, angle
Landscapes
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Crystallography & Structural Chemistry (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a system and a method for testing heat conductivity of a film material based on machine learning. The method comprises the steps of firstly, preprocessing a submicron or nanometer film material in a mode of pressurizing, thickness measuring, surface appearance and element composition analyzing, temperature and humidity condition simulating the application environment, and infrared accurate temperature measurement to obtain basic condition parameters; then, receiving data through a host of a cloud computing learning end, and constructing a model to calculate and predict the heat conductivity coefficient and the interface thermal resistance of the model by using a statistical machine learning method; and monitoring the cloud computing learning end in real time, continuously correcting the predicted model and algorithm, and finally obtaining the optimal submicron or nanometer heat conductivity coefficient and interface thermal resistance prediction result.
Description
Technical Field
The invention relates to the field of steady-state testing of thermophysical properties of materials, in particular to a system and a method for testing the heat-conducting property of a film material based on machine learning.
Background
Machine learning is the science of how to use computers to simulate or implement human learning activities, and is one of the most intelligent features in artificial intelligence, the most advanced research fields. Since the 80 s in the 20 th century, machine learning has attracted a great deal of interest in the artificial intelligence world as a way to implement artificial intelligence, and particularly, in recent decades, research work in the field of machine learning has been rapidly developing and has become an important subject of artificial intelligence. Machine learning has found wide application not only in knowledge-based systems, but also in many areas of natural language understanding, non-monotonic reasoning, machine vision, pattern recognition, and so on. Whether a system has learning capabilities has become an indicator of whether it has "intelligence". The study of machine learning is mainly divided into two categories of study directions: the first type is the research of traditional machine learning, which mainly researches the learning mechanism and focuses on exploring the learning mechanism of a dummy; the second type is the study of machine learning in big data environment, which mainly studies how to effectively utilize information, and focuses on obtaining hidden, effective and understandable knowledge from huge data.
At present, the heat conduction measurement aiming at the heat conduction coefficient and the interface thermal resistance value of the material with submicron or nanometer scale has difficulty. The machine learning function is introduced on the basis of an improved steady-state heat conduction testing method. Parameters are not required to be input, and parameters are automatically input by matching with a basic experimental testing device to obtain data of the heat conductivity coefficient and the interface thermal resistance.
Disclosure of Invention
The invention aims to solve the problems that the existing testing means is time-consuming and labor-consuming, and has large testing error and inaccurate result. An experimental measurement device is combined with a machine learning technology, and a system and a method for testing the heat conductivity of a film material based on machine learning are provided. By reasonably utilizing the artificial intelligent machine, the prediction precision of the heat conductivity coefficient and the interface thermal resistance of the submicron or nanometer grade material is effectively improved.
The invention discloses a steady-state testing system for thermal conductivity and interface thermal resistance of a deformation correction type film material based on artificial intelligence and machine learning.
The pressure loading end comprises a precise hydraulic device and can load corresponding actual pressure on the submicron or nanometer film material to be tested according to actual use conditions and service life; the deformation testing end comprises a laser thickness measuring device, and the deformation and thickness data of the submicron or nanometer film material to be tested before and after the loading pressure is obtained through testing according to the laser diffuse reflection principle; the surface scanning end comprises a surface roughness scanning and measuring device, such as but not limited to an atomic force microscope, and can test the surface appearance of the submicron or nanometer film material to be tested after being pressurized and deformed for roughness analysis; the material scanning end comprises a material analysis system, such as but not limited to an X-ray diffractometer, and can test the diffraction pattern of the submicron or nanometer film material to be tested to analyze the material components; the external environment simulation end comprises an external environment temperature and humidity simulation chamber and can simulate the temperature and humidity conditions of the application environment of the submicron or nanometer film material to be tested; the infrared temperature detection end comprises an infrared temperature measurement device, such as but not limited to a thermal infrared imager, and can be used for testing the sub-micron or nano-scale upper and lower surface temperature data of the sub-micron or nano-film material to be tested in the external environment temperature and humidity simulation cavity to perform surface thermal analysis; the cloud computing learning end comprises a host and a cloud service computer cluster, the host receives data of pressure, deformation, surface roughness, environment temperature and humidity and material components from a pressure loading end, a deformation testing end, a surface scanning end, a material scanning end, an external environment simulation end and an infrared temperature detection end, and upper and lower surface temperature data of the submicron and nanometer film materials to be tested, and the heat conductivity coefficient and interface thermal resistance of the film materials are predicted by using a statistical machine learning method and an optimization algorithm, such as but not limited to a decision tree, a Bayesian learning algorithm and the like, by using the cloud service computer cluster and according to a statistical model and parameters; the data output end comprises a monitoring and result output system, can monitor the computing condition of the cloud computing learning end, and flexibly distributes computing cluster node resources according to the computing amount; the result feedback correction end comprises a big data system and an actual test bed, and can compare the prediction result with the actual measurement experiment result, continuously correct the prediction model and the algorithm, and finally obtain the optimal heat conductivity coefficient and interface thermal resistance prediction result.
Preferably, the precision hydraulic device at the pressure loading end comprises a speed control system, and the speed control system can control the pressurizing speed and is used for simulating the impact wear condition of the material in the actual use process.
Preferably, the laser thickness measuring device at the deformation testing end tests the deformation quantity of the submicron or nanometer thin film material to be tested at the submicron or nanometer level by using a laser pulse signal and a reflection signal.
Preferably, the surface roughness scanning and measuring device at the surface scanning end is an atomic force microscope, and can obtain the nanometer-level morphology of the surface of the submicron or nanometer film material to be tested.
Preferably, the infrared temperature measuring device at the infrared temperature detecting end is a thermal infrared imager, so that the nano-scale space identification precision can be achieved, and the temperature difference between the upper surface and the lower surface of the submicron or nano-film material to be tested can be accurately distinguished.
Preferably, the material analysis system of the material scanning end is an X-ray diffractometer, and can accurately determine the diffraction pattern of the submicron or nanometer film material to be tested under the nanometer level size to perform material component analysis.
Preferably, the external environment temperature and humidity simulation chamber comprises a cold and heat source, an air supply system, and an environment temperature and humidity control and monitoring system.
The invention also discloses a test method of the system, which is characterized in that:
firstly, pressurizing the submicron or nanometer film material through a precise hydraulic device at a pressure loading end according to the actual use condition of the submicron or nanometer film material; meanwhile, the pressurizing rate and the impact rate of the pressurizing device are controlled, and the impact wear condition of the submicron or nanometer film material under the long-term pressurized condition is reproduced according to the actual use condition and the service life;
transferring the extruded and deformed submicron or nanometer film material to a deformation testing end, transmitting a laser light source by using a laser thickness measuring device, and collecting a laser diffuse reflection signal so as to obtain the deformation and thickness data of the submicron or nanometer film material to be tested before and after the pressurization of the precise hydraulic device;
then, the submicron or nanometer film material is transferred to a surface scanning end, and the upper and lower surface morphologies of the submicron or nanometer film material to be tested after being pressurized and deformed can be scanned and analyzed by utilizing a surface roughness scanning and measuring device, such as but not limited to an atomic force microscope, so as to obtain the surface roughness data of the submicron or nanometer film material;
then, transferring the submicron or nanometer film material to a material scanning end, and analyzing the nanometer-level diffraction pattern of the submicron or nanometer film material to be tested by using a material analysis system, such as but not limited to an X-ray diffractometer, so as to obtain element components contained in the material and content data of each component;
then, the submicron or nanometer film material is placed in an external environment temperature and humidity simulation cavity of an external environment simulation end, the external environment temperature and humidity simulation cavity comprises a cold and heat source, an air supply system and an environment temperature and humidity control and monitoring system, and the temperature and humidity conditions of the application environment of the submicron or nanometer film material to be tested can be simulated;
then, monitoring the sub-micron or nano-scale upper and lower surface temperature data of the sub-micron or nano-scale thin film material to be tested in the external environment temperature and humidity simulation cavity in real time by using an infrared temperature measuring device at an infrared temperature detection end, such as but not limited to a thermal infrared imager, and recording the temperature data in real time;
and then transmitting the data of pressure, deformation, surface roughness, environment temperature and humidity and material components obtained by the operations from the pressure loading end, the deformation testing end, the surface scanning end, the material scanning end, the external environment simulation end and the infrared temperature detection end, and the data of the upper surface temperature and the lower surface temperature of the submicron and nanometer film materials to be tested to a host of the cloud computing learning end, receiving the transmitted data by the host, and computing and predicting the thermal conductivity and the interface thermal resistance of the constructed model on the cloud service computer cluster by using the computing resources of the cloud service computer cluster and according to the statistical model and the parameters by using an optimization algorithm, such as but not limited to a decision tree, a Bayesian learning algorithm and the like, by using a statistical machine learning method. Then, the predicted data obtained by computing of the cloud computing learning end is displayed at the data output end, meanwhile, the data output end can monitor the computing condition of the cloud computing learning end, and computing cluster node resources are flexibly and reasonably distributed according to the computing amount; then the data output end feeds back the results of the heat conductivity coefficient and the interface thermal resistance of the submicron or nanometer film obtained by prediction to a feedback correction end, the feedback correction end is connected with a big data system on one hand, the data of the heat conductivity coefficient and the interface thermal resistance of various materials under different conditions can be obtained, and meanwhile, a feedback correction section is also connected with an actual test bed, and the heat conductivity coefficient and the interface thermal resistance value obtained by actual test can be obtained; the feedback correction end can compare the prediction result with big data and an actual measurement experiment result, the result deviation is fed back to a host of the cloud computing learning end, the host continuously corrects the predicted model and the algorithm to obtain an optimal thermal conductivity coefficient and interface thermal resistance prediction model, and the optimal thermal conductivity coefficient and interface thermal resistance prediction model is used for predicting the thermal conductivity coefficient and the interface thermal resistance of the submicron or nanometer film material.
Compared with the prior art, the invention has the following beneficial effects:
(1) the system does not need to input parameters, and data required by all models are obtained by experimental tests, so that the actual use conditions of submicron and nanometer film materials can be simulated, and accurate model parameters can be obtained;
(2) the system introduces variable parameters of deformation correction, considers the deformation conditions of submicron and nanometer film materials under the actual condition, and obtains more accurate heat conductivity coefficient and interface thermal resistance value;
(3) the system predicts the thermal conductivity and the interface thermal resistance of the submicron and nanometer film materials by artificial intelligence and mechanical learning means, and solves the defect that the traditional steady-state testing method can not test the thermal conductivity and the interface thermal resistance of the submicron and nanometer film materials;
(4) the system combines artificial intelligence, mechanical learning means and experimental testing means, avoids the manpower and time cost consumed by fussy steady-state heat conduction testing, and is more flexible and efficient;
(5) the artificial intelligence and mechanical learning means of the system consider the result to be compared with the experimental value, and correct the result, so that the predicted value is more accurate;
(6) the system has good expansibility and applicability, and can be applied to development and prediction of other test systems based on the system.
Drawings
FIG. 1 is a flow chart of a system and method for testing thermal conductivity of a film material based on machine learning.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
As shown in fig. 1, the system for testing the thermal conductivity and the interface thermal resistance of the deformation correction type thin film material based on artificial intelligence and machine learning in a stable state comprises a pressure loading end, a deformation testing end, a surface scanning end, a material scanning end, an external environment simulation end, an infrared temperature detection end, a cloud computing learning end, a data output end and a result feedback correction end.
Firstly, the submicron or nanometer film material is pressurized by a precise hydraulic device at a pressure loading end according to the actual use condition of the submicron or nanometer film material. Meanwhile, the pressurizing speed and the impact speed of the pressurizing device are controlled, and the impact wear condition of the submicron or nanometer film material under the long-term pressurized condition is reproduced according to the actual use condition and the service life. And then transferring the extruded and deformed submicron or nanometer film material to a deformation testing end, and emitting a laser light source by using a laser thickness measuring device. And collecting the signals of laser diffuse reflection so as to obtain the deformation and thickness data of the submicron or nanometer film material to be tested before and after the pressurization of the precise hydraulic device. The submicron or nanometer thin film material is then moved to the surface scanning end. The surface roughness scanning measuring device, such as but not limited to an atomic force microscope, can be used for scanning and analyzing the upper and lower surface appearances of the submicron or nanometer film material to be tested after being pressurized and deformed, so as to obtain the surface roughness data of the submicron or nanometer film material. And then, the submicron or nanometer thin-film material is transferred to a material scanning end, and a material analysis system, such as but not limited to an X-ray diffractometer, is used for analyzing the nanometer-level diffraction pattern of the submicron or nanometer thin-film material to be tested to obtain the element components contained in the material and the content data of each component. And then placing the submicron or nanometer film material in an external environment temperature and humidity simulation cavity of an external environment simulation end. The external environment temperature and humidity simulation chamber comprises a cold and heat source, an air supply system and an environment temperature and humidity control and monitoring system, and can simulate the temperature and humidity conditions of the application environment of the submicron or nanometer film material to be tested. And then, monitoring the sub-micron or nano-scale upper and lower surface temperature data of the sub-micron or nano-scale thin film material to be tested in the external environment temperature and humidity simulation cavity in real time by using an infrared temperature measuring device at the infrared temperature detection end, such as but not limited to a thermal infrared imager, and recording the temperature data in real time. And then transmitting the data of pressure, deformation, surface roughness, environment temperature, humidity and material composition, the upper and lower surface temperatures of the submicron and nanometer thin film materials to be detected and the like obtained by the operation from the pressure loading end, the deformation testing end, the surface scanning end, the material scanning end, the external environment simulation end and the infrared temperature detection end to a host of the cloud computing learning end. The host receives the transmitted parameters, and calculates and predicts the thermal conductivity and the interface thermal resistance of the constructed model on the cloud service computer cluster by using the calculation resources of the cloud service computer cluster and according to the statistical model and the parameters by using an optimization algorithm, such as but not limited to a decision tree, a Bayesian learning algorithm and the like, by using a statistical machine learning method. And then, the predicted data obtained by the cloud computing learning end is displayed at the data output end, and meanwhile, the data output end can monitor the computing condition of the cloud computing learning end, so that the computing cluster node resources are flexibly and reasonably distributed according to the computing amount. And then the data output end feeds back the results of the thermal conductivity coefficient and the interface thermal resistance of the submicron or nanometer film obtained by prediction to the feedback correction end. On one hand, the feedback correction end is connected with a big data system, and the data of the thermal conductivity and the interface thermal resistance of various materials under different conditions can be obtained. Meanwhile, the feedback correction end is also connected with an actual test bed, so that the heat conductivity coefficient and the interface thermal resistance value obtained through actual test can be obtained. Therefore, the feedback correction end can compare the prediction result with the big data and the actual measurement experiment result and feed the result deviation back to the host of the cloud computing learning end. Therefore, the predicted model and algorithm are continuously corrected, and finally the optimal submicron or nanometer heat conductivity coefficient and interface thermal resistance prediction result are obtained.
Those skilled in the art will appreciate that the drawings are only schematic illustrations of one preferred embodiment, and the above embodiment numbers are merely for description and do not represent the merits of the embodiments. The above embodiments are only preferred embodiments of the present invention, but the implementation manner of the present invention is not limited by the above embodiments, and any other modifications, substitutions, combinations, simplifications, improvements, etc. within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (8)
1. A film material heat-conducting property testing system based on machine learning is characterized by comprising a pressure loading end, a deformation testing end, a surface scanning end, a material scanning end, an external environment simulation end, an infrared temperature detection end, a cloud computing learning end, a data output end and a result feedback correction end;
the pressure loading end comprises a hydraulic device for loading pressure on the submicron or nanometer film material to be tested; the deformation testing end comprises a laser thickness measuring device and is used for testing the deformation and thickness data of the submicron or nanometer film material to be tested before and after loading pressure; the surface scanning end comprises a surface roughness scanning and measuring device, and is used for testing the surface appearance of the submicron or nanometer film material to be tested after being pressurized and deformed, and performing roughness analysis; the material scanning end comprises a material analysis system, and is used for testing the diffraction pattern of the submicron or nanometer film material to be tested and analyzing the material components; the external environment simulation end comprises an external environment temperature and humidity simulation chamber and is used for simulating the temperature and humidity conditions of the application environment of the submicron or nanometer film material to be tested; the infrared temperature detection end comprises an infrared temperature measurement device, and is used for testing the sub-micron or nano-level upper and lower surface temperature data of the sub-micron or nano-film material to be tested in the external environment temperature and humidity simulation cavity to perform surface thermal analysis; the cloud computing learning end comprises a host and a cloud service computer cluster, the host receives data of pressure, deformation, surface roughness, environment temperature and humidity and material components from the pressure loading end, the deformation testing end, the surface scanning end, the material scanning end, the external environment simulation end and the infrared temperature detection end, and upper and lower surface temperature data of the submicron and nanometer film materials to be tested, and the cloud service computer cluster is used for predicting the heat conductivity coefficient and the interface thermal resistance of the film materials by using a statistical machine learning method; the data output end comprises a monitoring and result output system, monitors the computing condition of the cloud computing learning end, and allocates computing cluster node resources according to the computing amount; the result feedback correction end comprises a big data system and an actual test bed, and compares the prediction result with the actual measurement experiment result to continuously correct the prediction model and the algorithm.
2. The system of claim 1, wherein the hydraulic means at the pressure loading end comprises a speed control system that controls the rate of pressurization for simulating impact wear of the material during actual use.
3. The system of claim 1, wherein the laser thickness measuring device of the deformation testing end uses laser pulse signals and reflected signals to test the deformation quantity of the submicron or nanometer thin film material to be tested in the submicron or nanometer level.
4. The system of claim 1, wherein the surface roughness scanning measuring device of the surface scanning end is an atomic force microscope, and can obtain the nanometer-scale topography of the surface of the submicron or nanometer thin film material to be tested.
5. The system of claim 1, wherein the infrared temperature measuring device at the infrared temperature detecting end is a thermal infrared imager, which can achieve nano-scale spatial recognition accuracy and accurately distinguish temperature differences between the upper and lower surfaces of the sub-micron or nano-film material to be tested.
6. The system of claim 1, wherein the material analysis system of the material scanning end is an X-ray diffractometer, which can precisely determine the diffraction pattern of the submicron or nanometer thin-film material to be tested at the nanometer level for material composition analysis.
7. The system of claim 1, wherein the external environmental temperature and humidity simulation chamber comprises a cold and heat source, an air supply system, and an environmental temperature and humidity control and monitoring system.
8. A method of testing the system of claim 1, characterized by:
firstly, pressurizing the submicron or nanometer film material through a hydraulic device at a pressure loading end according to the actual use condition of the submicron or nanometer film material; meanwhile, the pressurizing rate and the impact rate of the pressurizing device are controlled, and the impact wear condition of the submicron or nanometer film material under the long-term pressurized condition is reproduced according to the actual use condition and the service life;
transferring the extruded and deformed submicron or nanometer film material to a deformation testing end, transmitting a laser light source by using a laser thickness measuring device, and collecting signals of laser diffuse reflection so as to obtain the deformation and thickness data of the submicron or nanometer film material to be tested before and after the pressurization of the hydraulic device;
then transferring the submicron or nanometer film material to a surface scanning end, and scanning and analyzing the upper and lower surface appearances of the submicron or nanometer film material to be tested after the submicron or nanometer film material is pressurized and deformed by using a surface roughness scanning and measuring device to obtain the surface roughness data of the submicron or nanometer film material;
then transferring the submicron or nanometer film material to a material scanning end, and analyzing the nanometer-level diffraction pattern of the submicron or nanometer film material to be tested by using a material analysis system to obtain element components contained in the material and content data of each component;
then, the submicron or nanometer film material is placed in an external environment temperature and humidity simulation cavity of an external environment simulation end, and the temperature and humidity condition of the application environment of the submicron or nanometer film material to be tested is simulated;
then, monitoring the sub-micron or nano-scale upper and lower surface temperature data of the sub-micron or nano-scale thin film material to be tested in the external environment temperature and humidity simulation chamber in real time by using an infrared temperature measuring device at an infrared temperature detection end, and recording the temperature data in real time;
transmitting data from the pressure loading end, the deformation testing end, the surface scanning end, the material scanning end, the external environment simulation end and the infrared temperature detection end obtained by the operation and upper and lower surface temperature data of the submicron and nanometer film materials to be tested to a host of a cloud computing learning end, receiving the transmitted data by the host, computing and predicting the heat conductivity coefficient and the interface thermal resistance of the constructed model on the cloud service computer cluster by using a statistical machine learning method by utilizing computing resources of the cloud service computer cluster and according to a statistical model and parameters by adopting an optimization algorithm, displaying the predicted data obtained by computing of the cloud computing learning end at a data output end, monitoring the computing condition of the cloud computing learning end by the data output end, and distributing computing cluster node resources according to the computed quantity; then the data output end feeds back the results of the heat conductivity coefficient and the interface thermal resistance of the submicron or nanometer film obtained through prediction to a feedback correction end, the feedback correction end is connected with a big data system on one hand to obtain the data of the heat conductivity coefficient and the interface thermal resistance of various materials under different conditions, and meanwhile, a feedback correction section is also connected with an actual test bed to obtain the heat conductivity coefficient and the interface thermal resistance obtained through actual test; the feedback correction end compares the prediction result with the big data and the actual measurement experiment result, the result deviation is fed back to the host computer of the cloud computing learning end, and the host computer continuously corrects the predicted model and the algorithm to obtain the optimal heat conductivity coefficient and interface thermal resistance prediction model which is used for predicting the heat conductivity coefficient and the interface thermal resistance of the submicron or nanometer film material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910881533.8A CN110715953B (en) | 2019-09-18 | 2019-09-18 | System and method for testing heat-conducting property of film material based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910881533.8A CN110715953B (en) | 2019-09-18 | 2019-09-18 | System and method for testing heat-conducting property of film material based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110715953A true CN110715953A (en) | 2020-01-21 |
| CN110715953B CN110715953B (en) | 2020-07-21 |
Family
ID=69209917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910881533.8A Active CN110715953B (en) | 2019-09-18 | 2019-09-18 | System and method for testing heat-conducting property of film material based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110715953B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111812149A (en) * | 2020-07-20 | 2020-10-23 | 南京工业大学 | Adiabatic acceleration calorimetry method based on machine learning |
| CN114943186A (en) * | 2022-07-19 | 2022-08-26 | 数皮科技(湖北)有限公司 | Granite thermal conductivity limit lifting gradient prediction method based on whole-rock chemical data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
| CN101984348A (en) * | 2010-10-19 | 2011-03-09 | 东北大学 | Determination method of copperplate heat flux based on mass balance and heat balance continuous casting mould |
| CN106295852A (en) * | 2016-07-28 | 2017-01-04 | 大连民族大学 | Polyimide-based nano compound film disruptive field intensity forecast model and construction method thereof and application |
| CN109142434A (en) * | 2018-09-07 | 2019-01-04 | 哈尔滨工业大学 | A kind of transient state body heat source measurement method of thermal coefficient, thermal diffusivity |
| CN109918708A (en) * | 2019-01-21 | 2019-06-21 | 昆明理工大学 | A kind of Optimization of Material Property model building method based on heterogeneous integrated study |
-
2019
- 2019-09-18 CN CN201910881533.8A patent/CN110715953B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
| CN101984348A (en) * | 2010-10-19 | 2011-03-09 | 东北大学 | Determination method of copperplate heat flux based on mass balance and heat balance continuous casting mould |
| CN106295852A (en) * | 2016-07-28 | 2017-01-04 | 大连民族大学 | Polyimide-based nano compound film disruptive field intensity forecast model and construction method thereof and application |
| CN109142434A (en) * | 2018-09-07 | 2019-01-04 | 哈尔滨工业大学 | A kind of transient state body heat source measurement method of thermal coefficient, thermal diffusivity |
| CN109918708A (en) * | 2019-01-21 | 2019-06-21 | 昆明理工大学 | A kind of Optimization of Material Property model building method based on heterogeneous integrated study |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111812149A (en) * | 2020-07-20 | 2020-10-23 | 南京工业大学 | Adiabatic acceleration calorimetry method based on machine learning |
| CN111812149B (en) * | 2020-07-20 | 2021-10-15 | 南京工业大学 | Adiabatic acceleration calorimetry method based on machine learning |
| CN114943186A (en) * | 2022-07-19 | 2022-08-26 | 数皮科技(湖北)有限公司 | Granite thermal conductivity limit lifting gradient prediction method based on whole-rock chemical data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110715953B (en) | 2020-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6721667B2 (en) | Method and system for measuring properties of deformable material specimens | |
| CN110715953B (en) | System and method for testing heat-conducting property of film material based on machine learning | |
| Yeratapally et al. | A digital twin feasibility study (Part I): Non-deterministic predictions of fatigue life in aluminum alloy 7075-T651 using a microstructure-based multi-scale model | |
| Ramasamy et al. | Prediction of impact damage tolerance of drop impacted WGFRP composite by artificial neural network using acoustic emission parameters | |
| CN105809249A (en) | Double neural network-based PM2.5 concentration detection and prediction system and method | |
| CN105258642B (en) | Based on the relevant real-time optical extensometer measurement method of digital picture | |
| CN114004103A (en) | Collaborative operation test platform capable of supporting basic research of digital twin fully mechanized coal mining face | |
| CN115625894A (en) | Laser additive manufacturing life prediction method based on coaxial damage detection | |
| CN116664846B (en) | Method and system for realizing 3D printing bridge deck construction quality monitoring based on semantic segmentation | |
| CN104819694A (en) | Flexible board-shaped structural form sensing and reconfiguring experiment platform | |
| Wan et al. | Railway tracks defects detection based on deep convolution neural networks | |
| CN110568074B (en) | Wind turbine blade crack positioning method based on non-contact multipoint vibration measurement and Hilbert conversion | |
| CN115510732B (en) | Shelter infrared characteristic simulation rapid algorithm based on deep learning | |
| Feng et al. | Robust optimization for functional multiresponse in 3D printing process | |
| Brokarev et al. | Distributed data gathering system to analyze natural gas composition | |
| Boag | Measuring nematodes using a digitising tablet and microcomputer | |
| Hanna et al. | A self-supervised learning framework based on physics-informed and convolutional neural networks to identify local anisotropic permeability tensor from textiles 2D images for filling pattern prediction | |
| Catalanotti | Uncertainty quantification for advanced progressive damage models for composites by means of efficient emulators and bootstrapping | |
| CN114147380A (en) | Rotor welding method based on digital twin frame | |
| CN113973403A (en) | Temperature-induced strain field redistribution intelligent sensing method based on structure discrete measuring point topology | |
| Mahmoudi | Process monitoring and uncertainty quantification for laser powder bed fusion additive manufacturing | |
| Kruse et al. | Determination of the critical cross flow n-factor for the low-speed wind tunnel braunschweig (dnw-nwb) | |
| Szymanik et al. | Qualitative evaluation of 3D printed materials’ structure using active infrared thermography and signal analysis based on LSTM neural networks | |
| Zhang | Development and Experimental Validation of Dynamic Bayesian Networks for System Reliability Prediction | |
| JP7471031B2 (en) | DEFECT ESTIMATION DEVICE, DEFECT ESTIMATION METHOD, AND PROGRAM |
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 |