CN118209680B - Method, system, device and storage medium for testing flame retardance of heat insulating material - Google Patents
Method, system, device and storage medium for testing flame retardance of heat insulating material Download PDFInfo
- Publication number
- CN118209680B CN118209680B CN202410309630.0A CN202410309630A CN118209680B CN 118209680 B CN118209680 B CN 118209680B CN 202410309630 A CN202410309630 A CN 202410309630A CN 118209680 B CN118209680 B CN 118209680B
- Authority
- CN
- China
- Prior art keywords
- combustion
- flame retardant
- performance evaluation
- insulation material
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000011810 insulating material Substances 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000002485 combustion reaction Methods 0.000 claims abstract description 169
- 238000011156 evaluation Methods 0.000 claims abstract description 150
- RNFJDJUURJAICM-UHFFFAOYSA-N 2,2,4,4,6,6-hexaphenoxy-1,3,5-triaza-2$l^{5},4$l^{5},6$l^{5}-triphosphacyclohexa-1,3,5-triene Chemical compound N=1P(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP(OC=2C=CC=CC=2)(OC=2C=CC=CC=2)=NP=1(OC=1C=CC=CC=1)OC1=CC=CC=C1 RNFJDJUURJAICM-UHFFFAOYSA-N 0.000 claims abstract description 139
- 239000003063 flame retardant Substances 0.000 claims abstract description 139
- 239000012774 insulation material Substances 0.000 claims abstract description 95
- 238000013210 evaluation model Methods 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims description 32
- 230000015654 memory Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 239000000779 smoke Substances 0.000 claims description 10
- 238000009413 insulation Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 8
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 230000001988 toxicity Effects 0.000 claims description 5
- 231100000419 toxicity Toxicity 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 230000007774 longterm Effects 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 2
- 230000008033 biological extinction Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000004964 aerogel Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000005485 electric heating Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000006260 foam Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N31/00—Investigating or analysing non-biological materials by the use of the chemical methods specified in the subgroup; Apparatus specially adapted for such methods
- G01N31/12—Investigating or analysing non-biological materials by the use of the chemical methods specified in the subgroup; Apparatus specially adapted for such methods using combustion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Combustion & Propulsion (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Molecular Biology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a method, a system, a device and a storage medium for testing flame retardance of a heat insulating material, wherein in the method, combustion images and combustion data of the heat insulating material at a plurality of moments in a period from the beginning of combustion to the end of combustion are obtained; inputting the combustion images at a plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, combustion images at a plurality of moments and combustion data; and determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result. The combustion image and the combustion data of the heat insulation material in the combustion process are collected, then the corresponding performance evaluation results are respectively determined, and the two performance evaluation results are fused to obtain the final flame-retardant test result, so that quantitative flame-retardant capability evaluation can be provided, and the flame-retardant test efficiency is improved.
Description
Technical Field
The invention relates to the technical field of flame retardant capability test, in particular to a method, a system, a device and a storage medium for testing flame retardance of a heat insulation material.
Background
The flame retardant property of the material is the property that the material is not easy to burn or has slower burning speed when a fire disaster occurs, and the loss of life and property of people caused by the fire disaster can be effectively reduced, so the material is widely applied in the modern society.
In an application scene, the safety of the battery is at a great risk when the battery works under extreme conditions such as high temperature or short circuit, and therefore, the safety performance of the battery can be improved by covering the heat insulation material on the outer side of the battery. Therefore, it is necessary to test the flame retardant property of the heat insulating material, and the current testing method of the flame retardant property is usually completed manually, but the efficiency of the manual testing is low, and quantitative flame retardant capability evaluation cannot be provided.
Disclosure of Invention
The embodiment of the invention provides a method, a system, a device and a storage medium for testing flame retardance of a heat-insulating material, which are used for providing quantitative flame retardance evaluation and improving flame retardance testing efficiency.
In a first aspect, an embodiment of the present invention provides a method for testing flame retardance of a thermal insulation material, the method including:
acquiring combustion images and combustion data of the heat insulating material at a plurality of moments in a period from the start of combustion to the end of combustion;
Inputting the combustion images at the plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result;
Determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data;
and determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result.
Further, the heat insulation material is arranged around the simulated battery to form a closed test space;
the combustion images at the plurality of moments comprise flame combustion areas on the surface of the heat insulation material, physical changes of the heat insulation material and combustion conditions of the simulated battery.
Further, the training process of the flame retardant property evaluation model comprises the following steps:
Acquiring a combustion video frame sequence of a sample heat insulation material in the market from the beginning of combustion to the end of combustion, and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion;
Performing iterative training on a flame retardant property evaluation model according to the combustion video frame sequence of the sample heat insulation material and the property evaluation marking result;
The flame retardant performance evaluation model is formed by adding a gating mechanism and a memory unit on the basis of a cyclic neural network.
Further, the iterative training of the flame retardant property evaluation model according to the combustion video frame sequence of the sample heat insulation material and the property evaluation marking result comprises the following steps:
inputting the combustion video frame sequence of the sample heat insulation material into a flame retardant performance rating model, and outputting a performance evaluation prediction result;
Determining a sequence loss function value of the combustion video frame sequence according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function;
and performing iterative training on the flame retardant property evaluation model according to the sequence loss function value.
Further, the process of determining the sequence loss function value of the combustion video frame sequence according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function satisfies the following formula:
wherein L is the sequence loss function value, T is the T-th video frame, t=1, …, T is the total length of the combustion video frame sequence, and L (T) is the mean square error of the performance evaluation prediction result and the performance evaluation marking result in the T-th video frame.
Further, the determining the second performance evaluation result according to the correlation of the preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data includes:
determining the test relevance of the flame retardant evaluation indexes according to the combustion images and the combustion data at the plurality of moments;
Determining the degree of difference between the heat insulation material and a sample heat insulation material existing in the market according to the relevance of a plurality of preset flame retardant evaluation indexes and the test relevance of the plurality of flame retardant evaluation indexes;
And determining a second performance evaluation result according to the difference degree.
Further, the combustion data includes one or more of a flame-retardant duration, a combustion duration, a heat release amount, a smoke amount, or a smoke toxicity.
In a second aspect, embodiments of the present invention provide a thermal insulation material flame retardant test system, the system comprising:
The device comprises a heat insulation material flame-retardant testing device, a heat insulation material and a simulation battery;
The heat insulation material is arranged around the simulated battery to form a closed test space;
The heat insulation material flame-retardant testing device is used for acquiring combustion images and combustion data of the heat insulation material at a plurality of moments in a period from the beginning of combustion to the end of combustion; inputting the combustion images at the plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data; and determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result.
In a third aspect, an embodiment of the present invention provides a flame retardant testing device for a thermal insulation material, the device including:
An acquisition module for acquiring combustion images and combustion data of the heat insulating material at a plurality of moments in a period from the start of combustion to the end of combustion;
The performance evaluation module is used for inputting the combustion images at the plurality of moments into a flame retardant performance evaluation model and determining a first performance evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data;
And the result determining module is used for determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result.
In a fourth aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes a processor and a memory, where the memory is configured to store program instructions, and where the processor is configured to implement steps of any one of the methods for testing flame retardancy of an insulating material described above when executing a computer program stored in the memory.
In a fifth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the insulation flame retardant testing method described above.
The embodiment of the invention acquires the combustion images and the combustion data of the heat insulation material at a plurality of moments from the beginning of combustion to the end of combustion; inputting the combustion images at a plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, combustion images at a plurality of moments and combustion data; and determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result. According to the invention, the combustion image and the combustion data of the heat insulation material in the combustion process are collected, then the corresponding performance evaluation results are respectively determined, and the two performance evaluation results are fused to obtain the final flame-retardant test result, so that quantitative flame-retardant capability evaluation can be provided, and the flame-retardant test efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it will be apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic process diagram of a method for testing flame retardance of a heat insulating material according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a flame retardant testing device for heat insulation materials according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to provide quantitative flame retardant capability assessment and improve flame retardant test efficiency, the embodiment of the invention provides a method, a system, a device and a storage medium for testing flame retardant of a heat insulation material.
Example 1:
Fig. 1 is a schematic process diagram of a method for testing flame retardance of a heat insulating material according to an embodiment of the present invention, the process comprising the steps of:
s101: combustion images and combustion data of the heat insulating material at several times during the period from the start of combustion to the end of combustion are acquired.
S102: and inputting the combustion images at a plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result.
S103: and determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at a plurality of moments and the combustion data.
S104: and determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result.
According to the embodiment of the invention, the combustion image and the combustion data of the heat insulation material in the combustion process are collected, the corresponding performance evaluation results are respectively determined, and the two performance evaluation results are fused to obtain the final flame-retardant test result, so that quantitative flame-retardant capability evaluation can be provided, and the flame-retardant test efficiency is improved.
The heat-insulating material flame-retardant testing method provided by the embodiment of the invention is applied to a heat-insulating material flame-retardant testing device, wherein the heat-insulating material flame-retardant testing device can be electronic equipment, and particularly can be intelligent terminals, PCs, tablet computers and other equipment. The insulating material may include a heat insulating foam gel, a heat insulating aerogel, for example, which may be used for heat insulation of a battery.
In one possible testing scenario, the flame-retardant testing method of the heat-insulating material can be applied to the scenario when the heat abuse time of the battery occurs, so as to evaluate the flame-retardant performance of the heat-insulating material under the working condition (such as high temperature and electrochemical environment) of the battery, and ensure that the material can effectively slow down or prevent flame propagation when the heat abuse event of the battery occurs. By way of example, the thermal insulation material is placed around the simulated battery to form a closed test space that can simulate a battery thermal abuse scenario by heating the simulated battery. In this test scenario, the flame burning area of the surface of the insulating material, the physical change of the insulating material, and the simulated battery burning condition may be included in the burning images at several times in S101. The specific implementation process corresponding to the test scenario can be referred to the following embodiment.
In another possible testing scenario, the flame retardant testing method of the heat insulating material of the present invention may be applied to protect objects contained therein when combustion occurs outside, for example, when a fire occurs, to ensure that the heat insulating material slows down or prevents flame propagation to protect the internal battery of the electronic device.
The image of the flame burning area on the surface of the heat insulating material can represent the flame propagation speed, the area, the flame size and the like on the surface of the heat insulating material. The image of the physical change of the insulation material may represent the flame burning area of the insulation material surface, whether deformation, melting, corrosion, etc. of the insulation material occur. The image simulating the combustion condition of the battery can represent whether the battery burns, explodes, leaks, etc. during the combustion process.
The combustion data in S101 may include one or more of a flame retardant duration, a combustion duration, a heat release amount, a smoke generation amount, or smoke generation toxicity. The combustion image of the insulating material at several moments during the period from the start of combustion to the end of combustion can be acquired by the image acquisition device, and the combustion data at several moments can be acquired by the corresponding sensors, which are not indicated here.
The flame retardant property evaluation model in S102 described above may realize the evaluation of flame retardant property based on the combustion image. In one implementation, the training process of the flame retardant property evaluation model includes:
Acquiring a combustion video frame sequence of a sample heat insulation material in the market from the beginning of combustion to the end of combustion, and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion;
And performing iterative training on the flame retardant property evaluation model according to the combustion video frame sequence and the property evaluation marking result of the sample heat insulation material.
The flame retardant performance evaluation model may use a variety of neural network models, and the specific choice of which model depends on a variety of factors, such as the characteristics of the data, the complexity of the problem, and the limitation of computing resources, and when selecting the neural network model, the complexity of the model, the training time, and the performance of the model on the validation set and the test set need to be considered. Typically, the model most suitable for a particular task needs to be selected through experimentation and verification.
If the combustion image is sequence data, such as video frames, a recurrent neural network (Recurrent Neural Networks, RNNs) may be used to capture the time dependence. The recurrent neural network (Recurrent Neural Networks, RNNs) is a neural network model that is dedicated to processing sequence data. Unlike the conventional neural network model, RNNs has a memory function, and can capture the time dependence in the sequence data. In RNNs, the output of each time step (or referred to as each time instant) depends not only on the input at the current time instant, but also on the output at one or more previous time instants. This feature enables RNNs to process data with timing dependencies, such as text, speech, time series, etc. RNNs includes an input layer, a hidden layer, and an output layer. At each instant, the node of the input layer receives the input data at the current instant and passes it to the hidden layer. The nodes of the hidden layer receive not only the data from the input layer but also the output of the hidden layer at the last moment. This loop connection enables the hidden layer to remember the history information and apply it to the calculation of the current time. And finally, generating a prediction result at the current moment by the node of the output layer according to the output of the hidden layer. RNNs the training process typically employs a back propagation algorithm (Backpropagation Through Time, BPTT). And updating the weight parameters of the network by calculating errors between the predicted result and the actual result and back-propagating the errors to each node in the network. Thus RNNs can learn how to extract useful features from the sequence data and make accurate predictions.
In flame retardant performance evaluation of combustion images RNNs can be applied to process a continuous sequence of combustion video frames. By taking each frame of image as input data, RNNs can capture the evolution process of the flame and learn the changes of the characteristics of the flame, such as morphology, color, texture and the like, along with time. In this way RNNs is able to more accurately evaluate flame retardant properties, such as predicting the propagation speed, duration, etc. of the flame.
Further considering that RNNs may encounter problems with gradient extinction or gradient explosion when processing long sequences, this may result in the network not being able to learn long-term dependencies effectively. In order to solve the problem, the flame retardant performance evaluation model is to add a gating mechanism and a memory unit on the basis of a cyclic neural network so as to improve the processing capacity of long-term dependence. This improvement enables more efficient handling of long-term dependencies in long-sequence data, making these models better performing when handling complex tasks such as burning image sequences.
Gating mechanisms are a way to influence the internal state of an RNN by controlling the flow of information. In Long Short-Term Memory networks (LSTM), there are three types of gates: an input gate, a forget gate, and an output gate. These gates control the transfer of information through s igmoi d functions or other activation functions. For example, a forget gate determines which information should be forgotten or retained in the memory cell, an input gate determines which new information should be added to the memory cell, and an output gate determines which information should be passed on to the next time. This gating mechanism enables the LSTM to selectively retain and update information, thereby better capturing long-term dependencies.
The memory unit is a key component in the LSTM that is used to store and update long-term information in the network. Unlike the hidden state in conventional RNNs, the memory cell avoids the problem of gradient extinction or explosion by a carefully designed structure. At each instant, the memory unit updates its state based on the input gate, the forget gate and the current input. Thus, even if the sequence is long, LSTM can maintain memory of early information, thereby effectively handling long-term dependencies.
In the iterative training process, the following steps may be included: and calculating an error between the predicted result and the actual result, and reversely propagating the error and updating the weight parameters of the network. These processes are iterated a number of times, each iteration using a new set of sample data to calculate the error and update the weights. As the iteration proceeds, the predicted outcome of the network will gradually approach the actual outcome and the error will gradually decrease. When the error reaches an acceptable range or the iteration number reaches a preset upper limit, the training process is stopped, and a trained neural network model is obtained. Through the back propagation of errors and the updating of weight parameters, the neural network can gradually learn the correct mapping relation from input to output and accurately predict new unseen data.
For RNNs processing sequence data (e.g., machine translation, speech recognition, etc.), it may be necessary to consider the loss of the entire sequence, not just the loss of a single time step, and thus the sequence loss function may be employed in embodiments of the present invention. For example, when the flame retardant performance evaluation model is iteratively trained according to the combustion video frame sequence and the performance evaluation marking result of the sample heat insulation material, the combustion video frame sequence of the sample heat insulation material can be input into the flame retardant performance rating model, and the performance evaluation prediction result is output; determining a sequence loss function value of the combustion video frame sequence according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function; and performing iterative training on the flame retardant property evaluation model according to the sequence loss function value.
The sequence loss function may be calculated by summing or averaging the losses at each time step, for example, according to the performance evaluation marking result, the performance evaluation prediction result, and the sequence loss function, the process of determining the sequence loss function value of the sequence of burning video frames satisfies the following formula:
Wherein L is a sequence loss function value, T is a T-th video frame or a T-th time step, t=1, …, T is the total length of the combustion video frame sequence, and L (T) is the mean square error of the performance evaluation prediction result and the performance evaluation marking result in the T-th video frame.
In S103, the test relevance of the plurality of flame retardant evaluation indexes may be determined according to the combustion images and the combustion data at a plurality of moments; determining the degree of difference between the heat insulation material and the existing sample heat insulation material on the market according to the preset relevance of the flame retardant evaluation indexes and the test relevance of the flame retardant evaluation indexes; and determining a second performance evaluation result according to the difference degree. The device is preset with the relevance of a plurality of flame retardant evaluation indexes, for example, in the combustion process of the heat insulation material, the temperature, the heat degree, the smoke amount or the smoke toxicity of the surface of the heat insulation material can be relevant along with the size of the combustion area in the combustion process, that is, the sample heat insulation material on the market has the relevance of a plurality of corresponding flame retardant evaluation indexes. For the heat insulation material tested by the embodiment of the invention, the test relevance can be determined through the combustion data, then the test relevance is compared with the relevance of a plurality of preset flame retardant evaluation indexes, and the difference degree is determined, namely whether the heat insulation material accords with the characteristics of the sample heat insulation material or not and the difference degree when the heat insulation material accords with or does not accord with the characteristics of the sample heat insulation material, so that the corresponding performance evaluation result, namely the second performance evaluation result, is obtained. For example, the second performance evaluation result may be a score, e.g., when the insulation is consistent with the sample insulation, the degree of difference or score is 0, when the insulation is inconsistent with and inferior to the sample insulation, the degree of difference or score is negative, and when the insulation is inconsistent with and superior to the sample insulation, the degree of difference or score is positive.
The first performance evaluation result and the second performance evaluation result may be combined in S104 described above. In one implementation manner, in S104, it may be determined whether the electrical first performance evaluation result and the second performance evaluation result are consistent, if so, a flame retardant test result of the heat insulation material may be directly determined, and if not, a final flame retardant test result of the heat insulation material may be determined by means of cross validation, model fusion, expert judgment, and the like. In yet another implementation, weights may be assigned to the two performance evaluation results, and then the two performance evaluation results may be combined into a final score using weighted averaging or other suitable method as the final flame retardant test result for the insulation material.
Example 2:
On the basis of the embodiment, the embodiment of the invention provides a heat insulation material flame-retardant test system, which comprises a heat insulation material flame-retardant test device, a heat insulation material and a simulation battery;
The heat insulation material is arranged around the simulated battery to form a closed test space;
the heat insulation material flame-retardant testing device is used for realizing the steps of the heat insulation material flame-retardant testing method in the embodiment.
The test scenario is illustrated by way of example below:
Step 1: and (5) a preparation stage.
Samples of insulating material that fit the actual cell size were selected.
An analog battery, a built-in temperature sensor and a heat release measuring device were prepared.
Test environments including temperature, humidity, airflow rate, etc. are set to simulate the actual operating conditions of the battery.
Step 2: and a heating stage.
The insulating material sample is placed over or around the simulated cell to form a closed test space.
The analog battery is heated using an infrared heater or an electric heating plate or the like to simulate heat generated by an internal short circuit or thermal runaway of the battery.
The temperature change inside the simulated battery is monitored in real time through a temperature sensor.
Step 3: and (3) an ignition stage.
When the internal temperature of the simulated battery reaches the preset ignition temperature, the igniter is used for igniting the simulated battery.
The progress of the flame spread was recorded by a high speed camera and the flame spread speed and range were measured.
Step 4: flame retardant property evaluation stage:
The procedure was completed using the above examples. In this stage, the behavior of the insulating material under the action of flame can be observed, if the phenomena of combustion, melting or deformation occur; recording heat released in the flame spreading process by using a heat release measuring device, and evaluating the blocking effect of the heat insulating material on heat transfer; the flame retardant property of the flame retardant is comprehensively evaluated by combining the flame spreading speed, the heat release amount and the physical change of the heat insulation material.
Step 5: data analysis and reporting stage.
The data collected during the test are collated and analyzed, including temperature profile, flame spread rate, heat release, etc.
And generating detailed test reports according to the analysis result, wherein the detailed test reports comprise information such as flame retardant performance rating, improvement recommendation and use limitation.
Because of the different battery types and insulating material characteristics, the testing methods and evaluation criteria may need to be adjusted and optimized for the particular situation.
By the method, the flame retardant property of the heat insulation material in the field of batteries can be more comprehensively evaluated, and more reliable guarantee is provided for safe use of the batteries.
Example 3:
On the basis of the above embodiments, fig. 2 is a schematic structural diagram of a thermal insulation material flame retardant testing device according to an embodiment of the present invention, where the device includes:
An acquisition module 201 for acquiring combustion images and combustion data of the heat insulating material at several times during a period from the start of combustion to the end of combustion;
the performance evaluation module 202 is configured to input the combustion images at several moments into the flame retardant performance evaluation model, and determine a first performance evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, combustion images at a plurality of moments and combustion data;
The result determining module 203 is configured to determine a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result.
Further, the heat insulation material is arranged around the simulated battery to form a closed test space;
the combustion images at a plurality of moments comprise flame combustion areas on the surface of the heat insulation material, physical changes of the heat insulation material and the combustion conditions of the simulated battery.
Further, the method further comprises the following steps:
The training module is used for acquiring a combustion video frame sequence of the existing sample heat insulation material in the market from the beginning of combustion to the end of combustion and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion; performing iterative training on the flame retardant property evaluation model according to the combustion video frame sequence and the property evaluation marking result of the sample heat insulation material; wherein the flame retardant performance evaluation model is formed by adding a gating mechanism and a memory unit on the basis of a cyclic neural network.
Further, the training module is specifically used for inputting a combustion video frame sequence of the sample heat insulation material into the flame retardant performance rating model and outputting a performance evaluation prediction result; determining a sequence loss function value of the combustion video frame sequence according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function; and performing iterative training on the flame retardant property evaluation model according to the sequence loss function value.
Further, the training module is specifically configured to determine, according to the performance evaluation marking result, the performance evaluation prediction result, and the sequence loss function, that the process of determining the sequence loss function value of the combustion video frame sequence satisfies the following formula:
wherein L is a sequence loss function value, T is a T-th video frame, t=1, …, T is the total length of the burning video frame sequence, and L (T) is the mean square error of the performance evaluation prediction result and the performance evaluation marking result in the T-th video frame.
Further, the performance evaluation module 202 is specifically configured to determine a test relevance of a plurality of flame retardant evaluation indexes according to the combustion images and the combustion data at a plurality of moments; determining the degree of difference between the heat insulation material and the existing sample heat insulation material on the market according to the preset relevance of the flame retardant evaluation indexes and the test relevance of the flame retardant evaluation indexes; and determining a second performance evaluation result according to the difference degree.
Further, the combustion data includes one or more of a flame-retardant duration, a combustion duration, a heat release amount, a smoke amount, or a smoke toxicity.
Example 4:
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and on the basis of the foregoing embodiments, the embodiment of the present invention further provides an electronic device, which includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, where the processor 301, the communication interface 302, and the memory 303 complete communication with each other through the communication bus 304;
the memory 303 has stored therein a computer program which, when executed by the processor 301, causes the processor 301 to perform the steps of implementing the insulation material flame retardant test method as in the above embodiments.
Specific implementation process refers to the above embodiment, and the description of the similar points will not be repeated.
The communication bus mentioned above for the electronic device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface 302 is used for communication between the electronic device and other devices described above.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; but also digital instruction processors (DIGITAL SIGNAL Processing units, DSPs), application specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
Example 5:
On the basis of the above embodiments, the embodiments of the present invention also provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the steps of the insulation material flame retardant test method as in the above embodiments.
Specific implementation process refers to the above embodiment, and the description of the similar points will not be repeated.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. A method for flame retardant testing of a thermal insulation material, the method comprising:
acquiring combustion images and combustion data of the heat insulating material at a plurality of moments in a period from the start of combustion to the end of combustion;
Inputting the combustion images at the plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result;
Determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data;
determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result;
The training process of the flame retardant property evaluation model comprises the following steps:
Acquiring a combustion video frame sequence of a sample heat insulation material in the market from the beginning of combustion to the end of combustion, and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion;
Performing iterative training on a flame retardant property evaluation model according to the combustion video frame sequence of the sample heat insulation material and the property evaluation marking result;
The flame retardant performance evaluation model is formed by adding a gating mechanism and a memory unit on the basis of a cyclic neural network.
2. The method of claim 1, wherein the insulating material is disposed around the simulated cell to form a closed test space;
the combustion images at the plurality of moments comprise flame combustion areas on the surface of the heat insulation material, physical changes of the heat insulation material and combustion conditions of the simulated battery.
3. The method of claim 1, wherein said iteratively training a flame retardant performance evaluation model based on a sequence of combustion video frames of said sample insulation and said performance evaluation signature results comprises:
inputting the combustion video frame sequence of the sample heat insulation material into a flame retardant performance rating model, and outputting a performance evaluation prediction result;
Determining a sequence loss function value of the combustion video frame sequence according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function;
and performing iterative training on the flame retardant property evaluation model according to the sequence loss function value.
4. A method according to claim 3, wherein the process of determining the sequence loss function value of the sequence of burning video frames according to the performance evaluation marking result, the performance evaluation prediction result and the sequence loss function satisfies the following formula:
wherein, For the sequence loss function value, T is the T-th video frame, t=1, …, T is the total length of the sequence of burning video frames,And (3) performing mean square error on the performance evaluation marking result and the performance evaluation prediction result in the t-th video frame.
5. The method according to claim 1 or 2, wherein the determining the second performance evaluation result based on the correlation of the preset plurality of flame retardant evaluation indexes, the combustion images at the plurality of times, and the combustion data comprises:
determining the test relevance of the flame retardant evaluation indexes according to the combustion images and the combustion data at the plurality of moments;
Determining the degree of difference between the heat insulation material and a sample heat insulation material existing in the market according to the relevance of a plurality of preset flame retardant evaluation indexes and the test relevance of the plurality of flame retardant evaluation indexes;
And determining a second performance evaluation result according to the difference degree.
6. The method of claim 5, wherein the combustion data comprises one or more of a flame-retardant duration, a combustion duration, a heat release amount, a smoke amount, or a smoke toxicity.
7. The heat insulation material flame-retardant testing system is characterized by comprising a heat insulation material flame-retardant testing device, a heat insulation material and a simulation battery;
The heat insulation material is arranged around the simulated battery to form a closed test space;
The heat insulation material flame-retardant testing device is used for acquiring combustion images and combustion data of the heat insulation material at a plurality of moments in a period from the beginning of combustion to the end of combustion; inputting the combustion images at the plurality of moments into a flame retardant property evaluation model, and determining a first property evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data; determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result; and is also used for obtaining a flame retardant property evaluation model based on the following training process: acquiring a combustion video frame sequence of a sample heat insulation material in the market from the beginning of combustion to the end of combustion, and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion; performing iterative training on a flame retardant property evaluation model according to the combustion video frame sequence of the sample heat insulation material and the property evaluation marking result; the flame retardant performance evaluation model is formed by adding a gating mechanism and a memory unit on the basis of a cyclic neural network.
8. A flame retardant testing device for a thermal insulation material, the device comprising:
An acquisition module for acquiring combustion images and combustion data of the heat insulating material at a plurality of moments in a period from the start of combustion to the end of combustion;
The performance evaluation module is used for inputting the combustion images at the plurality of moments into a flame retardant performance evaluation model and determining a first performance evaluation result; determining a second performance evaluation result according to the relevance of a plurality of preset flame retardant evaluation indexes, the combustion images at the plurality of moments and the combustion data;
The result determining module is used for determining a flame retardant test result of the heat insulation material according to the first performance evaluation result and the second performance evaluation result;
Further comprises:
The training module is used for acquiring a combustion video frame sequence of the existing sample heat insulation material in the market from the beginning of combustion to the end of combustion and performance evaluation marking results of a plurality of flame retardant evaluation indexes during combustion; performing iterative training on the flame retardant property evaluation model according to the combustion video frame sequence and the property evaluation marking result of the sample heat insulation material; wherein the flame retardant performance evaluation model is formed by adding a gating mechanism and a memory unit on the basis of a cyclic neural network.
9. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the steps of the insulation material flame retardant testing method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309630.0A CN118209680B (en) | 2024-03-19 | 2024-03-19 | Method, system, device and storage medium for testing flame retardance of heat insulating material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410309630.0A CN118209680B (en) | 2024-03-19 | 2024-03-19 | Method, system, device and storage medium for testing flame retardance of heat insulating material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118209680A CN118209680A (en) | 2024-06-18 |
| CN118209680B true CN118209680B (en) | 2024-10-01 |
Family
ID=91448297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410309630.0A Active CN118209680B (en) | 2024-03-19 | 2024-03-19 | Method, system, device and storage medium for testing flame retardance of heat insulating material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118209680B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118518813B (en) * | 2024-07-23 | 2024-09-24 | 四川豪尔泰服饰有限公司 | A method, system and electronic equipment for detecting flame retardant properties of clothing |
| CN118937568B (en) * | 2024-10-14 | 2025-01-03 | 天津市全福车业有限公司 | Flame-retardant test platform for electric vehicle cushion |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564971A (en) * | 2022-07-18 | 2023-01-03 | 南京靖冯胜科技有限公司 | Woven tape flame retardant performance testing method based on gray level co-occurrence matrix |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021159430A1 (en) * | 2020-02-14 | 2021-08-19 | 苏州辉华新材料科技有限公司 | Test device for flame retardant property of textile materials |
| CN111929404B (en) * | 2020-09-23 | 2020-12-15 | 国网江苏省电力有限公司电力科学研究院 | A combined platform for the detection of fire-resistant materials for cables |
| CN116794215A (en) * | 2023-04-12 | 2023-09-22 | 浙江工业大学之江学院 | A lithium battery electrolyte flame retardant performance testing device |
| CN117434202A (en) * | 2023-08-14 | 2024-01-23 | 江苏和伟美科技发展有限公司 | Flame-retardant capability test method of flame-retardant polyamide |
-
2024
- 2024-03-19 CN CN202410309630.0A patent/CN118209680B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564971A (en) * | 2022-07-18 | 2023-01-03 | 南京靖冯胜科技有限公司 | Woven tape flame retardant performance testing method based on gray level co-occurrence matrix |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118209680A (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118209680B (en) | Method, system, device and storage medium for testing flame retardance of heat insulating material | |
| Wang et al. | Predicting transient building fire based on external smoke images and deep learning | |
| Deb et al. | A machine learning-based framework for cost-optimal building retrofit | |
| CN113591215B (en) | Abnormal satellite component layout detection method based on uncertainty | |
| CN114186405A (en) | Parameter uncertainty analysis method and system of nuclear power reactor system | |
| Omar et al. | Deep learning approach to predict forest fires using meteorological measurements | |
| KR20220051383A (en) | Method and apparatus for automatic modeling of target detection model | |
| Liu et al. | Modification of finite element models based on support vector machines for reinforced concrete beam vibrational analyses at elevated temperatures | |
| Hills et al. | Validation challenge workshop | |
| CN118604632B (en) | A method for predicting the service life of lithium batteries for embedded devices | |
| CN111428419A (en) | Suspended sediment concentration prediction method and device, computer equipment and storage medium | |
| CN114429246B (en) | A method and device for determining potential safety of power grid based on heterogeneous neural network | |
| CN109871642B (en) | Temperature field modeling method for internal structure of steam generator | |
| Yang et al. | Prediction of fire source heat release rate based on machine learning method | |
| CN115879378B (en) | Training method and device for expansion force prediction model of battery cell | |
| CN113191017A (en) | Virtual measurement model construction method, virtual measurement method, system, electronic device and computer-readable storage medium | |
| Wang et al. | Fitting a stochastic fire spread model to data | |
| CN118094537A (en) | An Zhuogao hidden type malicious software detection method and system based on dynamic API | |
| CN110865939B (en) | Application program quality monitoring method, device, computer equipment and storage medium | |
| CN118779751B (en) | Multi-heat output-oriented cable fire resistance performance test temperature real-time reconstruction method, system and storage medium | |
| CN112581250A (en) | Model generation method and device, computer equipment and storage medium | |
| CN117516969B (en) | Device testing method, device, computer device and storage medium | |
| CN111210105A (en) | Continuous work performance verification, apparatus, computer equipment and storage media | |
| CN113673102B (en) | Method, device and equipment for calculating predicted firing time of battery pack | |
| CN115879610B (en) | Contactor service life prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yi Jialin Inventor after: Chen Haoxuan Inventor before: Yi Jiajia Inventor before: Chen Haoxuan |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |