CN116555976B

CN116555976B - Preparation method and system of heat insulation material suitable for gun equipment

Info

Publication number: CN116555976B
Application number: CN202310542490.7A
Authority: CN
Inventors: 岳根基; 岳天赐; 朱学英; 高顺; 嵇晓杰
Original assignee: Suning Zhongyuan Textile Co ltd
Current assignee: Suning Zhongyuan Textile Co ltd
Priority date: 2023-05-15
Filing date: 2023-05-15
Publication date: 2023-10-13
Anticipated expiration: 2043-05-15
Also published as: CN116555976A

Abstract

A method for preparing heat insulating material suitable for artillery equipment and its system are disclosed. The method comprises the following steps: crushing and screening basalt raw materials to obtain rock particles; placing the rock particles in a high-temperature furnace for melting to obtain molten rock liquid; stretching the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments to obtain solidified fibers; collecting and grading the solidified fiber to obtain basalt fiber; and weaving and sewing the basalt fiber to prepare the heat-insulating fabric. In this way, a heat insulating material suitable for artillery equipment is produced.

Description

Preparation method and system of heat insulation material suitable for gun equipment

Technical Field

The application relates to the field of intelligent preparation, in particular to a preparation method and a system of a heat insulation material suitable for gun equipment.

Background

The gun is one of the weapons necessary for military operations, and has the characteristics of large power, long range and the like. However, after the gun is fired, the gun body is often in a high temperature state, which can lead to obvious thermal infrared imaging performance and is easily detected by enemy. In addition, in the use process of the artillery, the barrel body of the gun barrel can be damaged due to high temperature, and the accuracy and the service life of the artillery can be seriously influenced.

Accordingly, a thermal insulation material preparation scheme suitable for gun equipment is desired.

Disclosure of Invention

The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a preparation method and a system of a heat insulation material suitable for gun equipment. The method comprises the following steps: crushing and screening basalt raw materials to obtain rock particles; placing the rock particles in a high-temperature furnace for melting to obtain molten rock liquid; stretching the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments to obtain solidified fibers; collecting and grading the solidified fiber to obtain basalt fiber; and weaving and sewing the basalt fiber to prepare the heat-insulating fabric. In this way, a heat insulating material suitable for artillery equipment is produced.

According to an aspect of the present application, there is provided a method for producing a heat insulating material suitable for gun equipment, comprising:

crushing and screening basalt raw materials to obtain rock particles;

placing the rock particles in a high-temperature furnace for melting to obtain molten rock liquid;

Stretching the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments to obtain solidified fibers;

collecting and grading the solidified fiber to obtain basalt fiber; and

and weaving and sewing the basalt fiber to prepare the heat-insulating fabric.

In the above method for preparing a heat insulating material suitable for gun equipment, the method for preparing a solidified fiber by drawing the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments comprises the steps of:

acquiring internal temperature values of a spinning machine at a plurality of preset time points in a preset time period, cooling temperature values at the preset time points and drawing speed values at the preset time points;

arranging the internal temperature values of the spinning machine at a plurality of preset time points, the cooling temperature values at a plurality of preset time points and the stretching speed values at a plurality of preset time points into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector and a stretching speed value time sequence input vector according to a time dimension respectively;

the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector are respectively processed through a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector and a stretching speed time sequence feature vector;

Performing feature distribution optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain an optimized internal temperature time sequence feature vector, an optimized cooling temperature time sequence feature vector and an optimized stretching speed time sequence feature vector;

fusing the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector based on a Bayesian probability model to obtain a cooling temperature posterior probability feature vector; and

the cooling temperature posterior probability feature vector is passed through a classifier to obtain a classification result indicating that the cooling temperature value at the current point in time should be kept unchanged or should be reduced.

In the above method for preparing a heat insulating material suitable for gun equipment, the steps of passing the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector through a multi-scale one-dimensional convolution structure including a first convolution layer and a second convolution layer to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector and a stretching speed time sequence feature vector, respectively, include:

Checking the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector by using a first convolution layer of the multi-scale one-dimensional convolution structure through a one-dimensional convolution with a first length, so as to obtain a first scale internal temperature characteristic vector, a first scale cooling temperature characteristic vector and a first scale stretching speed characteristic vector;

checking the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector with a one-dimensional convolution layer of the multi-scale one-dimensional convolution structure by using a second convolution layer with a second length to obtain a second scale internal temperature characteristic vector, a second scale cooling temperature characteristic vector and a second scale stretching speed characteristic vector, wherein the second length is different from the first length; and

cascading the first-scale internal temperature feature vector and the second-scale internal temperature feature vector to obtain the internal temperature time sequence feature vector, cascading the first-scale cooling temperature feature vector and the second-scale cooling temperature feature vector to obtain the cooling temperature time sequence feature vector, and cascading the first-scale stretching speed feature vector and the second-scale stretching speed feature vector to obtain the stretching speed time sequence feature vector.

In the above preparation method of a heat insulating material suitable for gun equipment, performing feature distribution optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain an optimized internal temperature time sequence feature vector, an optimized cooling temperature time sequence feature vector and an optimized stretching speed time sequence feature vector, including:

calculating Helmholtz class free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain a first Helmholtz class free energy factor, a second Helmholtz class free energy factor and a third Helmholtz class free energy factor; and

and performing weighted optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector by taking the first Helmholtz type free energy factor, the second Helmholtz type free energy factor and the third Helmholtz type free energy factor as weighted weights to obtain the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector.

In the above method for preparing a heat insulating material suitable for gun equipment, calculating the helmholtz type free energy factors of the internal temperature timing feature vector, the cooling temperature timing feature vector, and the stretching speed timing feature vector to obtain a first helmholtz type free energy factor, a second helmholtz type free energy factor, and a third helmholtz type free energy factor, including:

calculating the Helmholtz class free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector according to the following optimization formula to obtain the first Helmholtz class free energy factor, the second Helmholtz class free energy factor and the third Helmholtz class free energy factor;

wherein, the optimization formula is:

wherein v is _1i Characteristic values, v, representing respective positions in the internal temperature time series characteristic vector _2i Characteristic values, v, representing respective positions in the cooling temperature time series characteristic vector _3i Representing the stretching speed time sequence characteristic vector, p ₁ 、p ₂ And p ₃ The classification probability values of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector are respectively represented, L is the length of the feature vector, log represents a logarithmic function based on 2, exp (·) represents exponential operation, and w ₁ 、w ₂ And w ₃ Representing the first helmholtz free energy factor, the second helmholtz free energy factor and the third helmholtz free energy factor, respectively.

In the above preparation method of a heat insulating material suitable for gun equipment, fusing the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector based on a bayesian probability model to obtain a cooling temperature posterior probability feature vector, including:

using the bayesian probability model to fuse the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector with the following bayesian probability formula to obtain the cooling temperature posterior probability feature vector;

wherein, the Bayesian probability formula is:

q _i ＝p _i *a _i /b _i

wherein q _i Characteristic values, p, representing respective positions in the optimum cooling temperature posterior probability characteristic vector _i Feature values, a, representing respective positions in the optimized internal temperature timing feature vector _i Characteristic values representing respective positions in the optimized drawing speed time sequence characteristic vector, b _i And the characteristic value of each position in the cooling temperature time sequence characteristic vector is represented.

In the above method for preparing a heat insulating material suitable for gun equipment, the step of passing the cooling temperature posterior probability feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the cooling temperature value of the current time point should be kept unchanged or should be reduced, and comprises the following steps:

performing full-connection coding on the cooling temperature posterior probability feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and

and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to another aspect of the present application, there is provided a heat insulating material preparation system suitable for gun equipment, comprising:

the crushing and screening module is used for crushing and screening basalt raw materials to obtain rock particles;

the melting module is used for placing the rock particles into a high-temperature furnace to be melted so as to obtain molten rock liquid;

the solidified fiber preparation module is used for drawing the molten rock liquid into filaments through a spinning machine and then cooling and solidifying the filaments to obtain solidified fibers;

the collecting and grading module is used for collecting and grading the solidified fiber to obtain basalt fiber; and

And the knitting and sewing module is used for knitting and sewing the basalt fiber to prepare the heat-insulating fabric.

In the above-mentioned heat insulating material preparation system suitable for artillery equipment, the fiber preparation module after solidification includes:

the data acquisition unit is used for acquiring internal temperature values of the spinning machine at a plurality of preset time points in a preset time period, cooling temperature values at the preset time points and stretching speed values at the preset time points;

an input vector arrangement unit for arranging the internal temperature values of the spinning machine at the plurality of predetermined time points, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector, and a drawing speed value time sequence input vector, respectively, according to a time dimension;

the multi-scale convolution unit is used for enabling the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector to respectively pass through a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer so as to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector and a stretching speed time sequence feature vector;

The characteristic distribution optimizing unit is used for carrying out characteristic distribution optimization on the internal temperature time sequence characteristic vector, the cooling temperature time sequence characteristic vector and the stretching speed time sequence characteristic vector to obtain an optimized internal temperature time sequence characteristic vector, an optimized cooling temperature time sequence characteristic vector and an optimized stretching speed time sequence characteristic vector;

the fusion unit is used for fusing the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector based on a Bayesian probability model to obtain a cooling temperature posterior probability feature vector; and

and the classification unit is used for passing the cooling temperature posterior probability characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the cooling temperature value of the current time point is unchanged or reduced.

In the above-mentioned heat insulating material preparation system suitable for artillery equipment, the multiscale convolution unit is used for:

Compared with the prior art, the preparation method and the system of the heat insulation material suitable for the gun equipment provided by the application comprise the following steps: crushing and screening basalt raw materials to obtain rock particles; placing the rock particles in a high-temperature furnace for melting to obtain molten rock liquid; stretching the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments to obtain solidified fibers; collecting and grading the solidified fiber to obtain basalt fiber; and weaving and sewing the basalt fiber to prepare the heat-insulating fabric. In this way, a heat insulating material suitable for artillery equipment is produced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art. The following drawings are not intended to be drawn to scale, emphasis instead being placed upon illustrating the principles of the application.

Fig. 1 is a flowchart of a method for manufacturing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 2 is an application scenario diagram of step S130 in a method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 3 is a flowchart of step S130 in the method for manufacturing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 4 is a schematic diagram of the structure of step S130 in the method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 5 is a flowchart of substep S133 of the method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 6 is a flowchart of substep S134 of the method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 7 is a flowchart of substep S136 of the method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application.

Fig. 8 is a block diagram of a heat insulating material preparation system suitable for gun equipment according to an embodiment of the present application.

Fig. 9 is a block diagram of the post-curing fiber preparation module in the heat insulating material preparation system suitable for gun equipment according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.

As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.

A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

As mentioned above, after the gun is fired, the gun body tends to be in a high temperature state, which results in obvious thermal infrared imaging performance and is easily detected by enemies. In addition, in the use process of the artillery, the barrel body of the gun barrel can be damaged due to high temperature, and the accuracy and the service life of the artillery can be seriously influenced. Accordingly, a thermal insulation material preparation scheme suitable for gun equipment is desired.

Specifically, in the technical scheme of the present application, a method for preparing a heat insulating material suitable for gun equipment is provided, as shown in fig. 1, which includes: s110, crushing and screening basalt raw materials to obtain rock particles; s120, placing the rock particles into a high-temperature furnace for melting to obtain molten rock liquid; s130, stretching the molten rock liquid into filaments by a spinning machine, and then cooling and solidifying the filaments to obtain solidified fibers; s140, collecting and grading the solidified fiber to obtain basalt fiber; and S150, weaving and sewing the basalt fiber to prepare the heat-insulating fabric. Particularly, in the technical scheme of the application, basalt fabric developed by a special technology is adopted, so that the shell of the gun barrel can be covered rapidly at high temperature, the leakage of heat infrared and the reconnaissance of air radar waves are prevented, meanwhile, the gun barrel is effectively protected, the fabric can be used repeatedly, and the use and operation of a warrior are facilitated.

Accordingly, it is considered that in drawing the molten rock liquid into filaments by a spinning machine, the temperature inside the spinning machine needs to be controlled so that the molten rock liquid is drawn into filaments smoothly, and at the same time, in order to avoid fiber breakage or crystallization, the drawing speed value of the machine needs to be appropriately adjusted. And, it is also necessary to control the cooling rate so that the fibers can gradually cool down and form a solid state. Too fast or too slow cooling affects the quality of the fibers, and cooling is usually controlled by cooling. Therefore, in the technical scheme of the application, the internal temperature value, the cooling temperature value and the drawing speed value of the spinning machine in the fiber drawing process are expected to be analyzed to carry out self-adaptive control on the cooling temperature value, so that the quality and the efficiency of the fiber are ensured. However, since the internal temperature value of the spinning machine, the cooling temperature value, and the drawing speed value have respective dynamic change rules in the time dimension, and the data have a time-series cooperative correlation relationship, it is necessary to sufficiently express the time-series correlation characteristics of the data so that the cooling temperature value can be precisely controlled in real time.

In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides a new solution idea and scheme for mining time sequence collaborative association dynamic change characteristic information of the internal temperature value, the cooling temperature value and the stretching speed value of the spinning machine.

Specifically, in the technical scheme of the present application, first, the internal temperature values of the spinning machine at a plurality of predetermined time points within a predetermined period of time, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points are obtained. Next, considering that the internal temperature value of the spinning machine, the cooling temperature value, and the drawing speed value all have a dynamic change law in the time dimension, in order to be able to extract the change characteristic information of the internal temperature value of the spinning machine, the cooling temperature value, and the drawing speed value in the time dimension, in the technical scheme of the present application, the internal temperature value of the spinning machine, the cooling temperature value, and the drawing speed value at the plurality of predetermined points in time must be first arranged as an internal temperature time series input vector, a cooling temperature value time series input vector, and a drawing speed value time series input vector, respectively, so as to integrate the distribution information of the internal temperature value of the spinning machine, the cooling temperature value, and the drawing speed value in time series, respectively.

Then, considering that the internal temperature value, the cooling temperature value and the drawing speed value all have different dynamic change regularity under different time period spans in the time dimension, in order to fully express time sequence dynamic change characteristics of the internal temperature value, the cooling temperature value and the drawing speed value of the spinning machine, in the technical scheme of the application, the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the drawing speed value time sequence input vector are further respectively processed by a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain an internal temperature time sequence characteristic vector, a cooling temperature time sequence characteristic vector and a drawing speed time sequence characteristic vector. In particular, here, the first convolution layer and the second convolution layer have one-dimensional convolution kernels of different scales, so that time-series multi-scale dynamic change characteristic information of the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value under different time spans is extracted respectively. Therefore, the time sequence change conditions of the key parameters such as temperature, cooling speed and stretching speed can be deeply analyzed, so that the time sequence change conditions of the parameters of the molten rock liquid wire drawing through the spinning machine in the corresponding time period can be better known, the preparation process can be optimized according to the time sequence characteristics of the parameters, and the quality and stability of the fabric can be improved.

Further, since there is a time-series correlation between the internal temperature value of the spinning machine, the cooling temperature value and the time-series dynamic variation characteristic between the drawing speed values, the conventional machine learning method often cannot fully utilize the correlation information. In order to fully express the time sequence cooperative correlation characteristic among the time sequence change characteristic of the internal temperature value of the spinning machine, the time sequence change characteristic of the cooling temperature value and the time sequence change characteristic of the stretching speed value, so as to improve the accuracy of cooling temperature control, in the technical scheme of the application, three time sequence characteristic vectors of the internal temperature, the cooling temperature and the stretching speed are fused based on a Bayesian probability model to obtain a cooling temperature posterior probability characteristic vector. It should be understood that the bayesian probabilistic model may take into account time-series correlation characteristic information of these parameters, and comprehensively reflect weights and roles of these parameter information in cooling temperature control by the obtained cooling temperature posterior probability characteristic vector, thereby improving prediction accuracy and stability of the cooling temperature.

And then, further classifying the cooling temperature posterior probability feature vector serving as a classification feature vector in a classifier to obtain a classification result that the cooling temperature value used for representing the current time point is kept unchanged or reduced. That is, in the technical solution of the present application, the labels of the classifier include that the cooling temperature value at the current time point should be increased (first label) and that the cooling temperature value at the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include the concept of artificial setting, and in fact, during the training process, the computer model does not have the concept of "the cooling temperature value at the current time point should be increased or should be decreased", which is only two kinds of classification tags and the probability that the output feature is under the two classification tags, i.e., the sum of p1 and p2 is one. Therefore, the classification result that the cooling temperature value should be increased or decreased is actually a class probability distribution converted by classifying the tag into two classes conforming to the natural law, and the physical meaning of the natural probability distribution of the tag is essentially used instead of the language text meaning that the cooling temperature value at the current time point should be increased or decreased. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a control policy label that the cooling temperature value of the current time point should be increased or decreased, so after the classification result is obtained, the cooling temperature value of the current time point may be adaptively adjusted to be increased or decreased based on the classification result, so as to ensure the quality and efficiency of the fiber.

Particularly, in the technical scheme of the application, when the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector are fused based on a Bayesian probability model to obtain the cooling temperature posterior probability feature vector, the Bayesian probability model is used for carrying out position-by-position Bayesian probability calculation on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector, noise disturbance of internal temperature values, cooling temperature values and stretching depth values on time sequence distribution is amplified by a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer, so that the distribution deviation among feature values of all positions of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector is caused, and accordingly the overall feature distribution of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector is in a class-weak correlation distribution instance relative to class labels of a classifier, that is in the class labels, namely, the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed sequence feature vector are subjected to the class labels, and the class labels are accurately influenced by the class labels under the class labels, and the class labels are calculated by the class labels, and the class labels are more accurate on the basis of the class labels.

Based on this, it is preferable to calculate the internal temperature timing characteristic vector V separately ₁ The cooling temperature time sequence characteristic vector V ₂ And the stretching speed time sequence characteristic vector V ₃ The helmholtz-like free energy factor of (c) is specifically:

p ₁ 、p ₂ and p ₃ Respectively represent the internal temperature time sequence characteristic vector V ₁ (v _1i ∈V ₁ ) The cooling temperature time sequence characteristic vector V ₂ (v _2i ∈V ₂ ) And the stretching speed time sequence characteristic vector V ₃ (v _3i ∈V ₃ ) And L is the length of the feature vector.

Here, the internal temperature timing feature vector V may be calculated based on the helmholtz free energy formula ₁ The cooling temperature time sequence characteristic vector V ₂ And the stretching speed time sequence characteristic vector V ₃ The respective feature value sets describe the energy value of the predetermined class label as the class free energy of the feature vector as a whole by using the energy value of the predetermined class label to time sequence the feature vector V to the internal temperature ₁ The cooling temperature time sequence characteristic vector V ₂ And the stretching speed time sequence characteristic vector V ₃ Weighting the internal temperature timing feature vector V ₁ The cooling temperature time sequence characteristic vector V ₂ And the stretching speed time sequence characteristic vector V ₃ Focusing on class-dependent prototype instance distributions of features overlapping with true instance distributions in class target domain to facilitate timing of feature vectors V at the internal temperature ₁ The cooling temperature time sequence characteristic vector V ₂ And the stretching speed time sequence characteristic vector V ₃ Under the condition that a class weak correlation distribution example exists in the integral feature distribution, incremental learning is realized by carrying out ambiguity labeling on the integral feature distribution, so that the compatibility of the integral feature distribution under class labels is improved, the convergence of the cooling temperature posterior probability feature vector calculated based on a Bayesian probability model under class labels of a classifier is improved, and the accuracy of a classification result obtained by the cooling temperature posterior probability feature vector through the classifier is improved. Therefore, the self-adaptive control of the cooling temperature value can be accurately performed in real time based on the actual condition in the fiber stretching process, so that the quality and the efficiency of the fiber are ensured.

Fig. 2 is an application scenario diagram of step S130 in a method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application. As shown in fig. 2, in this application scenario, first, the internal temperature values of the spinning machine at a plurality of predetermined time points (for example, D1 illustrated in fig. 2), the cooling temperature values at the plurality of predetermined time points (for example, D2 illustrated in fig. 2), and the drawing speed values at the plurality of predetermined time points (for example, D3 illustrated in fig. 2) are acquired for a predetermined period of time, then the internal temperature values of the spinning machine at the plurality of predetermined time points, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points are input to a server (for example, S illustrated in fig. 2) in which a heat insulating material preparation algorithm suitable for gun equipment is deployed, wherein the server is able to use the heat insulating material preparation algorithm suitable for gun equipment to spin the internal temperature values of the machine at the plurality of predetermined time points, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points are processed to obtain a result indicating that the current cooling temperature values are not to be set down or to be reduced.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

Fig. 3 is a flowchart of step S130 in the method for manufacturing a heat insulating material suitable for gun equipment according to an embodiment of the present application. As shown in fig. 3, in the method for preparing a heat insulating material suitable for gun equipment according to the embodiment of the present application, after the molten rock liquid is drawn into filaments by a spinning machine, cooling and solidifying processes are performed to obtain solidified fibers, including: s131, acquiring internal temperature values of a spinning machine at a plurality of preset time points in a preset time period, cooling temperature values at the preset time points and drawing speed values at the preset time points; s132, arranging the internal temperature values of the spinning machine at a plurality of preset time points, the cooling temperature values at a plurality of preset time points and the drawing speed values at a plurality of preset time points into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector and a drawing speed value time sequence input vector according to a time dimension respectively; s133, passing the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector through a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector and a stretching speed time sequence feature vector; s134, performing feature distribution optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain an optimized internal temperature time sequence feature vector, an optimized cooling temperature time sequence feature vector and an optimized stretching speed time sequence feature vector; s135, fusing the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector based on a Bayesian probability model to obtain a cooling temperature posterior probability feature vector; and S136, passing the cooling temperature posterior probability feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the cooling temperature value of the current time point is unchanged or reduced.

Fig. 4 is a schematic diagram of the structure of step S130 in the method for preparing a heat insulating material suitable for gun equipment according to an embodiment of the present application. As shown in fig. 4, in the network architecture, first, the internal temperature values of the spinning machine, the cooling temperature values at a plurality of predetermined time points within a predetermined period of time, and the drawing speed values at the plurality of predetermined time points are acquired; next, arranging the internal temperature values of the spinning machine at the plurality of preset time points, the cooling temperature values at the plurality of preset time points and the stretching speed values at the plurality of preset time points into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector and a stretching speed value time sequence input vector according to a time dimension respectively; then, the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector are respectively processed through a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector and a stretching speed time sequence feature vector; then, performing feature distribution optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain an optimized internal temperature time sequence feature vector, an optimized cooling temperature time sequence feature vector and an optimized stretching speed time sequence feature vector; then, fusing the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector based on a Bayesian probability model to obtain a cooling temperature posterior probability feature vector; finally, the cooling temperature posterior probability feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for representing that the cooling temperature value of the current time point is supposed to be unchanged or supposed to be reduced.

More specifically, in step S131, the internal temperature values of the spinning machine, the cooling temperature values at a plurality of predetermined time points within a predetermined period of time, and the drawing speed values at the plurality of predetermined time points are acquired. In drawing the molten rock liquid into filaments by a spinning machine, it is necessary to control the temperature inside the spinning machine so that the molten rock liquid is drawn into filaments smoothly, and at the same time, to avoid fiber breakage or crystallization, it is necessary to make proper adjustments to the drawing speed value of the machine. And, it is also necessary to control the cooling rate so that the fibers can gradually cool down and form a solid state. Too fast or too slow cooling affects the quality of the fibers, and cooling is usually controlled by cooling. Therefore, in the technical scheme of the application, the internal temperature value, the cooling temperature value and the drawing speed value of the spinning machine in the fiber drawing process are expected to be analyzed to carry out self-adaptive control on the cooling temperature value, so that the quality and the efficiency of the fiber are ensured.

More specifically, in step S132, the internal temperature values of the spinning machine at the plurality of predetermined time points, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points are arranged in time dimensions as an internal temperature time series input vector, a cooling temperature value time series input vector, and a drawing speed value time series input vector, respectively. Since the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value all have a dynamic change rule in the time dimension, in order to extract the change characteristic information of the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value in the time dimension, the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value at a plurality of preset time points need to be arranged into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector and a drawing speed value time sequence input vector according to the time dimension, so that the distribution information of the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value in the time sequence is integrated.

More specifically, in step S133, the internal temperature timing input vector, the cooling temperature value timing input vector, and the stretching speed value timing input vector are respectively passed through a multi-scale one-dimensional convolution structure including a first convolution layer and a second convolution layer to obtain an internal temperature timing feature vector, a cooling temperature timing feature vector, and a stretching speed timing feature vector. In order to fully express time sequence dynamic change characteristics of the internal temperature value, the cooling temperature value and the stretching speed value of the spinning machine, the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector are further respectively processed through a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain the internal temperature time sequence characteristic vector, the cooling temperature time sequence characteristic vector and the stretching speed time sequence characteristic vector. In particular, here, the first convolution layer and the second convolution layer have one-dimensional convolution kernels of different scales, so that time-series multi-scale dynamic change characteristic information of the internal temperature value of the spinning machine, the cooling temperature value and the drawing speed value under different time spans is extracted respectively. Therefore, the time sequence change conditions of the key parameters such as temperature, cooling speed and stretching speed can be deeply analyzed, so that the time sequence change conditions of the parameters of the molten rock liquid wire drawing through the spinning machine in the corresponding time period can be better known, the preparation process can be optimized according to the time sequence characteristics of the parameters, and the quality and stability of the fabric can be improved.

Accordingly, in one specific example, as shown in fig. 5, passing the internal temperature timing input vector, the cooling temperature value timing input vector, and the stretching speed value timing input vector through a multi-scale one-dimensional convolution structure including a first convolution layer and a second convolution layer to obtain an internal temperature timing feature vector, a cooling temperature timing feature vector, and a stretching speed timing feature vector, respectively, includes: s1331, performing one-dimensional convolution coding on the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector by using a first convolution layer of the multi-scale one-dimensional convolution structure and using a one-dimensional convolution layer with a first length to obtain a first scale internal temperature feature vector, a first scale cooling temperature feature vector and a first scale stretching speed feature vector; s1332, performing one-dimensional convolution coding on the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector by using a second convolution layer of the multi-scale one-dimensional convolution structure and a one-dimensional convolution check with a second length, so as to obtain a second scale internal temperature characteristic vector, a second scale cooling temperature characteristic vector and a second scale stretching speed characteristic vector, wherein the second length is different from the first length; and S1333, cascading the first-scale internal temperature feature vector and the second-scale internal temperature feature vector to obtain the internal temperature time sequence feature vector, cascading the first-scale cooling temperature feature vector and the second-scale cooling temperature feature vector to obtain the cooling temperature time sequence feature vector, and cascading the first-scale stretching speed feature vector and the second-scale stretching speed feature vector to obtain the stretching speed time sequence feature vector.

It should be appreciated that convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition and the like. The convolutional neural network may include an input layer, a hidden layer, and an output layer, where the hidden layer may include a convolutional layer, a pooling layer, an activation layer, a full connection layer, etc., where the previous layer performs a corresponding operation according to input data, outputs an operation result to the next layer, and obtains a final result after the input initial data is subjected to a multi-layer operation.

More specifically, in step S134, feature distribution optimization is performed on the internal temperature timing feature vector, the cooling temperature timing feature vector, and the stretching speed timing feature vector to obtain an optimized internal temperature timing feature vector, an optimized cooling temperature timing feature vector, and an optimized stretching speed timing feature vector.

Accordingly, in one specific example, as shown in fig. 6, performing feature distribution optimization on the internal temperature timing feature vector, the cooling temperature timing feature vector, and the stretching speed timing feature vector to obtain an optimized internal temperature timing feature vector, an optimized cooling temperature timing feature vector, and an optimized stretching speed timing feature vector, includes: s1341, calculating Helmholtz free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain a first Helmholtz free energy factor, a second Helmholtz free energy factor and a third Helmholtz free energy factor; and S1342, weighting and optimizing the internal temperature time series feature vector, the cooling temperature time series feature vector and the stretching speed time series feature vector with the first helmholtz type free energy factor, the second helmholtz type free energy factor and the third helmholtz type free energy factor as weighting weights to obtain the optimized internal temperature time series feature vector, the optimized cooling temperature time series feature vector and the optimized stretching speed time series feature vector.

Particularly, in the technical scheme of the application, when the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector are fused based on a Bayesian probability model to obtain the cooling temperature posterior probability feature vector, the Bayesian probability model is used for carrying out position-by-position Bayesian probability calculation on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector, noise disturbance of internal temperature values, cooling temperature values and stretching depth values on time sequence distribution is amplified by a multi-scale one-dimensional convolution structure comprising a first convolution layer and a second convolution layer, so that the distribution deviation among feature values of all positions of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector is caused, and accordingly the overall feature distribution of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector is in a class-weak correlation distribution instance relative to class labels of a classifier, that is in the class labels, namely, the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed sequence feature vector are subjected to the class labels, and the class labels are accurately influenced by the class labels under the class labels, and the class labels are calculated by the class labels, and the class labels are more accurate on the basis of the class labels. Based on this, it is preferable to calculate helmholtz-like free energy factors of the internal temperature timing characteristic vector, the cooling temperature timing characteristic vector, and the stretching speed timing characteristic vector, respectively.

Accordingly, in one specific example, calculating the helmholtz-like free energy factors of the internal temperature timing feature vector, the cooling temperature timing feature vector, and the stretching speed timing feature vector to obtain a first helmholtz-like free energy factor, a second helmholtz-like free energy factor, and a third helmholtz-like free energy factor includes: calculating the Helmholtz class free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector according to the following optimization formula to obtain the first Helmholtz class free energy factor, the second Helmholtz class free energy factor and the third Helmholtz class free energy factor; wherein, the optimization formula is:

Here, based on the helmholtz free energy formula, the respective feature value sets of the internal temperature time series feature vector, the cooling temperature time series feature vector and the stretching speed time series feature vector can be described by the free energy of the feature vector for the whole class of the predetermined class label, and by weighting the internal temperature time series feature vector, the cooling temperature time series feature vector and the stretching speed time series feature vector by the feature value sets, the internal temperature time series feature vector, the cooling temperature time series feature vector and the stretching speed time series feature vector can be focused on the class-related prototype instance distribution of the feature with overlapping property with the true value instance distribution in the class label domain, so that incremental learning is realized by fuzziness labeling on the internal temperature time series feature vector, the cooling temperature time series feature vector and the stretching speed time series feature vector under the condition that the class-weakly related distribution instance exists in the whole feature distribution of the internal temperature time series feature vector, thereby improving the compatibility of the whole feature distribution under the class label, and further improving the consistency of the class-posterior probability feature vector under the class label calculated based on the bayesian probability model, thereby obtaining the accurate classification result of the cooling temperature posterior feature vector by the classifier. Therefore, the self-adaptive control of the cooling temperature value can be accurately performed in real time based on the actual condition in the fiber stretching process, so that the quality and the efficiency of the fiber are ensured.

More specifically, in step S135, the optimized internal temperature timing feature vector, the optimized cooling temperature timing feature vector, and the optimized drawing speed timing feature vector are fused based on a bayesian probability model to obtain a cooling temperature posterior probability feature vector. In order to fully express the time sequence variation characteristic of the internal temperature value of the optimized spinning machine, the time sequence variation characteristic of the optimized cooling temperature value and the time sequence cooperative correlation characteristic between the time sequence variation characteristic of the optimized drawing speed value, so as to improve the accuracy of cooling temperature control, in the technical scheme of the application, three time sequence characteristic vectors of the internal temperature, the cooling temperature and the drawing speed are fused based on a Bayesian probability model to obtain a cooling temperature posterior probability characteristic vector.

It should be understood that the bayesian probabilistic model may take into account time-series correlation characteristic information of these parameters, and comprehensively reflect weights and roles of these parameter information in cooling temperature control by the obtained cooling temperature posterior probability characteristic vector, thereby improving prediction accuracy and stability of the cooling temperature.

Accordingly, in one specific example, fusing the optimized internal temperature timing feature vector, the optimized cooling temperature timing feature vector, and the optimized stretching speed timing feature vector based on a bayesian probability model to obtain a cooling temperature posterior probability feature vector includes: using the bayesian probability model to fuse the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector with the following bayesian probability formula to obtain the cooling temperature posterior probability feature vector; wherein, the Bayesian probability formula is:

q _i ＝p _i *a _i /b _i

wherein q _i Representing the optimized coolingCharacteristic value p of each position in temperature posterior probability characteristic vector _i Feature values, a, representing respective positions in the optimized internal temperature timing feature vector _i Characteristic values representing respective positions in the optimized drawing speed time sequence characteristic vector, b _i And the characteristic value of each position in the cooling temperature time sequence characteristic vector is represented.

More specifically, in step S136, the cooling temperature posterior probability feature vector is passed through a classifier to obtain a classification result indicating that the cooling temperature value at the current point in time should be kept unchanged or should be reduced. After the classification result is obtained, the cooling temperature value at the current time point can be adaptively adjusted to increase or decrease based on the classification result, so as to ensure the quality and efficiency of the fiber.

It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.

Accordingly, in one specific example, as shown in fig. 7, the cooling temperature posterior probability feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the cooling temperature value at the current time point should be kept unchanged or should be reduced, including: s1361, performing full-connection coding on the cooling temperature posterior probability feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and S1362, inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

In summary, according to the preparation method of the insulating material suitable for gun equipment according to the embodiment of the application, after the molten rock liquid is drawn into filaments by a spinning machine, cooling and solidifying are performed to obtain solidified fiber, firstly, internal temperature values of the spinning machine at a plurality of preset time points in a preset time period and cooling temperature values at the plurality of preset time points are obtained, and drawing speed values at the plurality of preset time points are obtained, then, the internal temperature values of the spinning machine at the plurality of preset time points and cooling temperature values at the plurality of preset time points are arranged into an internal temperature time sequence input vector, a cooling temperature value time sequence input vector and a drawing speed value time sequence input vector according to time dimensions, then, the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the drawing speed value time sequence input vector are respectively processed through a multi-dimensional convolution structure comprising a first convolution layer and a second convolution layer to obtain an internal temperature feature vector, a cooling temperature time sequence feature vector and a cooling temperature feature vector, and a cooling feature vector, and then, the internal temperature feature vector and cooling feature vector are obtained, and the internal temperature feature time sequence feature vector and the cooling feature time sequence feature vector are optimized, the internal temperature feature time sequence feature vector and the cooling feature vector and the drawing speed feature vector are optimized, and the cooling feature time sequence feature vector is optimized, and the internal feature vector is optimized, finally, the cooling temperature posterior probability feature vector is passed through a classifier to obtain a classification result for indicating that the cooling temperature value at the current time point should be kept unchanged or should be reduced.

Fig. 8 is a block diagram of a thermal insulation material preparation system 100 suitable for gun equipment according to an embodiment of the present application. As shown in fig. 8, a heat insulating material preparation system 100 suitable for gun equipment according to an embodiment of the present application includes: a crushing and screening module 110 for crushing and screening basalt raw materials to obtain rock particles; a melting module 120 for melting the rock particles in a high temperature furnace to obtain molten rock liquid; a solidified fiber preparation module 130, configured to cool and solidify the molten rock liquid after being drawn into filaments by a spinning machine, so as to obtain solidified fibers; the collecting and grading module 140 is used for collecting and grading the solidified fiber to obtain basalt fiber; and a knitting sewing module 150 for knitting and sewing the basalt fiber to manufacture a heat insulating fabric.

In one example, in the above-mentioned heat insulating material preparation system 100 suitable for gun equipment, as shown in fig. 9, the post-curing fiber preparation module 130 includes: a data acquisition unit 131 for acquiring internal temperature values of the spinning machine at a plurality of predetermined time points within a predetermined period of time, cooling temperature values at the plurality of predetermined time points, and drawing speed values at the plurality of predetermined time points; an input vector arrangement unit 132 for arranging the internal temperature values of the spinning machine at the plurality of predetermined time points, the cooling temperature values at the plurality of predetermined time points, and the drawing speed values at the plurality of predetermined time points into an internal temperature time series input vector, a cooling temperature value time series input vector, and a drawing speed value time series input vector, respectively, in a time dimension; the multi-scale convolution unit 133 is configured to pass the internal temperature time sequence input vector, the cooling temperature value time sequence input vector, and the stretching speed value time sequence input vector through a multi-scale one-dimensional convolution structure including a first convolution layer and a second convolution layer, respectively, so as to obtain an internal temperature time sequence feature vector, a cooling temperature time sequence feature vector, and a stretching speed time sequence feature vector; a feature distribution optimizing unit 134, configured to perform feature distribution optimization on the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector, and the stretching speed time sequence feature vector to obtain an optimized internal temperature time sequence feature vector, an optimized cooling temperature time sequence feature vector, and an optimized stretching speed time sequence feature vector; a fusion unit 135, configured to fuse the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector, and the optimized stretching speed time sequence feature vector based on a bayesian probability model to obtain a cooling temperature posterior probability feature vector; and a classification unit 136 for passing the cooling temperature posterior probability feature vector through a classifier to obtain a classification result indicating that the cooling temperature value at the current time point should be maintained or should be reduced.

In one example, in the above-described heat insulating material preparation system 100 suitable for artillery equipment, the multi-scale convolution unit 133 is configured to: checking the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector by using a first convolution layer of the multi-scale one-dimensional convolution structure through a one-dimensional convolution with a first length, so as to obtain a first scale internal temperature characteristic vector, a first scale cooling temperature characteristic vector and a first scale stretching speed characteristic vector; checking the internal temperature time sequence input vector, the cooling temperature value time sequence input vector and the stretching speed value time sequence input vector with a one-dimensional convolution layer of the multi-scale one-dimensional convolution structure by using a second convolution layer with a second length to obtain a second scale internal temperature characteristic vector, a second scale cooling temperature characteristic vector and a second scale stretching speed characteristic vector, wherein the second length is different from the first length; and cascading the first-scale internal temperature feature vector and the second-scale internal temperature feature vector to obtain the internal temperature time sequence feature vector, cascading the first-scale cooling temperature feature vector and the second-scale cooling temperature feature vector to obtain the cooling temperature time sequence feature vector, and cascading the first-scale stretching speed feature vector and the second-scale stretching speed feature vector to obtain the stretching speed time sequence feature vector.

In one example, in the above-described heat insulating material preparation system 100 adapted for gun equipment, the characteristic distribution optimizing unit 134 is configured to: calculating Helmholtz class free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector to obtain a first Helmholtz class free energy factor, a second Helmholtz class free energy factor and a third Helmholtz class free energy factor; and weighting and optimizing the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector by taking the first Helmholtz type free energy factor, the second Helmholtz type free energy factor and the third Helmholtz type free energy factor as weighting weights to obtain the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector.

In one example, in the above-described heat insulating material preparation system 100 suitable for gun equipment, calculating the helmholtz-type free energy factors of the internal temperature timing feature vector, the cooling temperature timing feature vector, and the drawing speed timing feature vector to obtain a first helmholtz-type free energy factor, a second helmholtz-type free energy factor, and a third helmholtz-type free energy factor includes: calculating the Helmholtz class free energy factors of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector according to the following optimization formula to obtain the first Helmholtz class free energy factor, the second Helmholtz class free energy factor and the third Helmholtz class free energy factor; wherein, the optimization formula is:

Wherein v is _1i Characteristic values, v, representing respective positions in the internal temperature time series characteristic vector _2i Characteristic values, v, representing respective positions in the cooling temperature time series characteristic vector _3i Representing the stretch rate timing characteristicsVector, p ₁ 、p ₂ And p ₃ The classification probability values of the internal temperature time sequence feature vector, the cooling temperature time sequence feature vector and the stretching speed time sequence feature vector are respectively represented, L is the length of the feature vector, log represents a logarithmic function based on 2, exp (·) represents exponential operation, and w ₁ 、w ₂ And w ₃ Representing the first helmholtz free energy factor, the second helmholtz free energy factor and the third helmholtz free energy factor, respectively.

In one example, in the above-mentioned heat insulating material preparation system 100 suitable for artillery equipment, the fusion unit 135 is configured to: using the bayesian probability model to fuse the optimized internal temperature time sequence feature vector, the optimized cooling temperature time sequence feature vector and the optimized stretching speed time sequence feature vector with the following bayesian probability formula to obtain the cooling temperature posterior probability feature vector; wherein, the Bayesian probability formula is:

q _i ＝p _i *a _i /b _i

In one example, in the above-described heat insulating material preparation system 100 adapted for gun equipment, the classifying unit 136 is configured to: performing full-connection coding on the cooling temperature posterior probability feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described heat insulating material preparation system 100 for gun equipment have been described in detail in the above description of the heat insulating material preparation method for gun equipment with reference to fig. 2 to 7, and thus, repetitive descriptions thereof will be omitted.

As described above, the heat insulating material preparation system 100 suitable for gun equipment according to the embodiment of the present application can be implemented in various wireless terminals, such as a server or the like having a heat insulating material preparation algorithm suitable for gun equipment. In one example, the insulating material preparation system 100 suitable for gun equipment according to an embodiment of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the insulating material preparation system 100 suitable for gun equipment may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the insulating material preparation system 100 suitable for gun equipment may also be one of the many hardware modules of the wireless terminal.

Alternatively, in another example, the insulating material preparation system 100 for artillery equipment and the wireless terminal may be separate devices, and the insulating material preparation system 100 for artillery equipment may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.

According to another aspect of the present application there is also provided a non-volatile computer readable storage medium having stored thereon computer readable instructions which when executed by a computer can perform a method as described above.

Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.

The application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.

Claims

1. A method of preparing a thermally insulating material suitable for use in artillery equipment, comprising:

crushing and screening basalt raw materials to obtain rock particles;

collecting and grading the solidified fiber to obtain basalt fiber; and

weaving and sewing the basalt fiber to prepare a heat-insulating fabric;

wherein, after the molten rock liquid is drawn into filaments by a spinning machine, cooling and solidifying treatment are carried out to obtain solidified fibers, comprising:

2. The method of manufacturing a heat insulating material suitable for gun equipment according to claim 1, wherein passing the internal temperature time series input vector, the cooling temperature value time series input vector, and the drawing speed value time series input vector through a multi-scale one-dimensional convolution structure including a first convolution layer and a second convolution layer to obtain an internal temperature time series feature vector, a cooling temperature time series feature vector, and a drawing speed time series feature vector, respectively, comprises:

3. The method for producing a heat insulating material suitable for gun equipment according to claim 2, wherein performing feature distribution optimization on the internal temperature time series feature vector, the cooling temperature time series feature vector, and the drawing speed time series feature vector to obtain an optimized internal temperature time series feature vector, an optimized cooling temperature time series feature vector, and an optimized drawing speed time series feature vector, comprises:

4. A method of preparing a thermally insulating material suitable for use in an artillery equipment according to claim 3, wherein calculating the helmholtz-like free energy factors of the internal temperature timing eigenvector, the cooling temperature timing eigenvector, and the drawing speed timing eigenvector to obtain a first helmholtz-like free energy factor, a second helmholtz-like free energy factor, and a third helmholtz-like free energy factor comprises:

wherein, the optimization formula is:

5. The method for producing a heat insulating material suitable for gun equipment according to claim 4, wherein fusing the optimized internal temperature time series eigenvector, the optimized cooling temperature time series eigenvector, and the optimized drawing speed time series eigenvector based on a bayesian probability model to obtain a cooling temperature posterior probability eigenvector, comprises:

wherein, the Bayesian probability formula is:

q _i ＝p _i *a _i /b _i

6. The method for manufacturing a heat insulating material suitable for gun equipment according to claim 5, wherein passing the cooling temperature posterior probability feature vector through a classifier to obtain a classification result indicating that a cooling temperature value at a current time point should be kept unchanged or should be reduced, comprises:

7. A heat insulating material preparation system suitable for gun equipment, comprising:

the braiding and sewing module is used for braiding and sewing the basalt fiber to prepare a heat-insulating fabric;

wherein, the fiber preparation module after solidification includes:

8. The thermal insulation material preparation system for an artillery equipment according to claim 7, wherein the multi-scale convolution unit is configured to: