CN117469970B - Accurate feeding system for smelting electron beam metal niobium - Google Patents
Accurate feeding system for smelting electron beam metal niobium Download PDFInfo
- Publication number
- CN117469970B CN117469970B CN202311786945.6A CN202311786945A CN117469970B CN 117469970 B CN117469970 B CN 117469970B CN 202311786945 A CN202311786945 A CN 202311786945A CN 117469970 B CN117469970 B CN 117469970B
- Authority
- CN
- China
- Prior art keywords
- smelting
- feeding
- speed
- electron beam
- difference value
- 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
- 238000003723 Smelting Methods 0.000 title claims abstract description 386
- 238000010894 electron beam technology Methods 0.000 title claims abstract description 125
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 30
- 239000002184 metal Substances 0.000 title claims abstract description 30
- 229910052758 niobium Inorganic materials 0.000 title claims abstract description 30
- 239000010955 niobium Substances 0.000 title claims abstract description 30
- GUCVJGMIXFAOAE-UHFFFAOYSA-N niobium atom Chemical compound [Nb] GUCVJGMIXFAOAE-UHFFFAOYSA-N 0.000 title claims abstract description 30
- 239000000463 material Substances 0.000 claims abstract description 88
- 238000012549 training Methods 0.000 claims abstract description 69
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 238000010801 machine learning Methods 0.000 claims abstract description 46
- 238000013441 quality evaluation Methods 0.000 claims description 69
- 238000000034 method Methods 0.000 claims description 51
- 238000011156 evaluation Methods 0.000 claims description 37
- 238000002844 melting Methods 0.000 claims description 35
- 230000008018 melting Effects 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 6
- 241001417490 Sillaginidae Species 0.000 claims description 3
- 230000000712 assembly Effects 0.000 claims 1
- 238000000429 assembly Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract 2
- 239000007769 metal material Substances 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 150000002739 metals Chemical class 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 description 2
- 229910045601 alloy Inorganic materials 0.000 description 2
- 239000000956 alloy Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000295 emission spectrum Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 229910052750 molybdenum Inorganic materials 0.000 description 2
- 239000011733 molybdenum Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010223 real-time analysis Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 2
- 229910052721 tungsten Inorganic materials 0.000 description 2
- 239000010937 tungsten Substances 0.000 description 2
- 229910000851 Alloy steel Inorganic materials 0.000 description 1
- 241001062472 Stokellia anisodon Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000011819 refractory material Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27B14/00—Crucible or pot furnaces
- F27B14/08—Details peculiar to crucible or pot furnaces
- F27B14/0806—Charging or discharging devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27B—FURNACES, KILNS, OVENS, OR RETORTS IN GENERAL; OPEN SINTERING OR LIKE APPARATUS
- F27B14/00—Crucible or pot furnaces
- F27B14/08—Details peculiar to crucible or pot furnaces
- F27B14/20—Arrangement of controlling, monitoring, alarm or like devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F27—FURNACES; KILNS; OVENS; RETORTS
- F27M—INDEXING SCHEME RELATING TO ASPECTS OF THE CHARGES OR FURNACES, KILNS, OVENS OR RETORTS
- F27M2003/00—Type of treatment of the charge
- F27M2003/13—Smelting
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Manufacture And Refinement Of Metals (AREA)
Abstract
The invention discloses a precise feeding system for smelting electron beam metal niobium, in particular to the technical field of electron beam smelting, which comprises a historical data acquisition module, a control module and a control module, wherein the historical data acquisition module is used for acquiring smelting training data in n smelting subareas in a smelting area; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data; the model training module is used for training a machine learning model for predicting the initial feeding speed based on smelting training data; the smelting monitoring module takes the initial feeding speed predicted by the trained machine learning model as the current feeding speed; the invention is beneficial to smelting materials in a smelting subarea in advance, analyzing the smelting condition of the materials in real time according to real-time smelting monitoring data, accurately adjusting the feeding speed, avoiding the condition of unqualified smelting quality caused by too high or too low speed, realizing accurate adjustment of the feeding speed, and further being beneficial to ensuring the high quality of the materials.
Description
Technical Field
The invention relates to the technical field of electron beam smelting, in particular to a precise feeding system for electron beam metal niobium smelting.
Background
Along with the continuous innovation and research and development of various novel technologies, the technical requirements of materials with higher standards are gradually put forward, and an electron beam melting furnace is used as special equipment for producing refractory materials, and in operation, the electron beam melting furnace is automatically controlled by fully coordinating and matching the large systems such as vacuum, cooling, machinery, electron beam guns and the like; the electron beam smelting is a vacuum smelting method for converting kinetic energy of high-speed electron beam current into heat energy as a heat source to smelt metal materials under high vacuum, and the heat source of the electron beam gun accurately bombards the metal materials to enable the metal materials to be molten to form a molten pool, so that the metal material smelting process is realized; electron beam melting can be used for melting high-melting metals such as niobium, tungsten, molybdenum and the like to prepare various metal products and alloys, the melting efficiency of the electron beam melting can greatly influence the quality of metal materials, and currently, in order to improve the metal melting quality, a plurality of enterprises have developed feeding mechanisms of electron beam melting furnaces, for example, application publication number CN105783523a discloses a monolithic feeding mechanism of the electron beam melting furnace; feeding the metal materials in a horizontal roller way pushing mode, swinging the front end of the horizontal roller way to adjust the melting position of the metal materials, and controlling the feeding speed and swinging speed through a servo motor; however, although the smelting quality of the metal materials is improved by the feeding mechanism, the feeding mechanism has some defects and problems in the practical use process, such as:
1. Before the metal materials are smelted by the electron beam, the feeding speed of the metal materials is not predicted, so that the feeding speed is controlled only by a human judgment mode in the smelting process, and the feeding speed is too high or too low, so that the smelting quality is affected;
2. when the electron beam is used for smelting the metal materials, accurate feeding is not performed according to the smelting progress of the metal materials, so that the smelting efficiency of the metal materials is reduced, and the risk of defects of the materials is increased.
Therefore, the invention provides a precise feeding system for smelting electron beam metal niobium.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides a precise feeding system for smelting electron beam metal niobium, so as to solve the problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions: accurate feeding system is used in electron beam niobium metal smelting includes:
the historical data acquisition module is used for acquiring smelting training data in n smelting subregions in the smelting region; n is an integer greater than or equal to 1; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
the model training module is used for training a machine learning model for predicting the initial feeding speed based on smelting training data;
The smelting monitoring module takes the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelts the materials in the smelting subareas and acquires smelting monitoring data of n smelting subareas in real time; extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
the judgment module is used for setting a smelting quality evaluation threshold, comparing the smelting quality evaluation coefficient with the smelting quality evaluation threshold and acquiring feeding adjustment information according to a comparison result;
the feeding speed adjusting module is used for extracting the current feeding speed of the corresponding feeding component of each smelting subarea according to feeding adjusting information and generating the adjusting feeding speed of the corresponding feeding component based on the current feeding speed of the corresponding feeding component;
generating an adjusted feed rate for the corresponding feed assembly, comprising:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly; calculating a second speed difference value corresponding to the current feeding speed of the feeding assembly and the current feeding speed of the adjacent feeding assembly;
Generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
and controlling the operation of the corresponding feeding assembly according to the adjusted feeding speed of the corresponding feeding assembly.
Further, the smelting characteristic data comprises electron beam energy density, material weight and smelting speed;
the energy density of the electron beam is the energy density output by the electron beam gun, and is calculated by acquiring the voltage, the current and the focal cross-sectional area output by the electron beam gun; the formula is as follows:
；
the weight of the material is obtained through a gravity sensor arranged below the feeding area;
the smelting speed is obtained by monitoring the moving speed of material smelting in real time through a camera;
the material type is used for determining the material composition by analyzing the spectral characteristics of a melting area through a spectrometer or a light beam induced emission spectrum;
the initial feeding speed is obtained by measuring the speed of pushing the material corresponding to the feeding area to the smelting subarea through a speed sensor, namely, when smelting characteristic data are obtained, the feeding speed of the material corresponding to the feeding area is collected at the same time.
Further, a machine learning model for predicting the initial feeding speed is trained based on smelting training data, and the training method comprises the following steps:
Taking each group of smelting characteristic data as input of a machine learning model, wherein the machine learning model takes initial feeding speeds predicted for each group of smelting characteristic data as output, takes initial feeding speeds corresponding to the smelting characteristic data in smelting training data as prediction targets, and takes prediction errors of all initial feeding speeds as training targets; training the machine learning model until the prediction error reaches convergence, stopping training, and training the machine learning model for outputting the predicted initial feeding speed according to smelting characteristic data; the machine learning model is one of a polynomial regression model or an SVM model;
further, the smelting monitoring data comprise real-time temperature, real-time depth and real-time electron beam power, and the smelting monitoring threshold comprises a temperature standard value, a depth standard value and an electron beam power standard value;
the method for analyzing smelting monitoring data by acquiring smelting monitoring thresholds of n smelting subregions comprises the following steps:
calculating a temperature difference value between the real-time temperature of each smelting subarea and a temperature standard value, and taking the temperature difference value as a temperature evaluation coefficient;
calculating a depth difference value between the real-time depth of each smelting subarea and a depth standard value, and taking the depth difference value as a depth evaluation coefficient;
Calculating an electron beam power difference value between the real-time electron beam power of each smelting subarea and an electron beam power standard value, and taking the electron beam power difference value as an electron beam power evaluation coefficient;
the temperature evaluation coefficient, the depth evaluation coefficient and the electron beam power evaluation coefficient are formulated to obtain a smelting quality evaluation coefficientThe calculation formula is as follows:
；
in the method, in the process of the invention,temperature evaluation coefficient for the nth smelting subregion, < ->Depth evaluation factor for the nth smelting subregion, < ->An electron beam power evaluation coefficient for the nth melting sub-region,>temperature weight factor representing the nth smelting subregion, < ->Depth weight factor representing the nth smelting subregion, < ->And represents the electron beam power weight factor of the nth smelting subregion.
Further, the method for comparing the smelting quality evaluation coefficient with the smelting quality evaluation threshold value and obtaining feeding adjustment information according to the comparison result comprises the following steps:
if the smelting quality evaluation coefficientIf the smelting quality evaluation threshold value is larger than or equal to the smelting quality evaluation threshold value, generating feeding unregulated information;
if the smelting quality evaluation coefficientAnd if the smelting quality evaluation threshold is smaller than the smelting quality evaluation threshold, generating feeding adjustment information.
Further, generating an adjusted feed rate for the respective feed assembly based on the current feed rate for the respective feed assembly, comprising:
Calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly; the standard feeding speed of the preset target feeding assembly is generated as follows:
acquiring the current feeding speed of a preset target feeding assembly;
calculating a difference value between a preset standard feeding speed of the preset target feeding component and a design feeding speed of the preset target feeding component, and marking the difference value between the preset standard feeding speed of the preset target feeding component and the design feeding speed of the preset target feeding component as a target speed difference value;
adjusting the current feeding speed of the preset target feeding component according to the target speed difference value to obtain the standard feeding speed of the preset target feeding component;
the pre-standard feeding speed is a feeding speed of a preset target feeding assembly, wherein the standard feeding speed of the preset target feeding assembly is influenced by friction force and feeding resistance.
Further, calculating a second speed difference corresponding to the current feed speed of the feed assembly and the current feed speed of an adjacent feed assembly, the adjacent feed assembly being the corresponding feed assembly for which the second speed difference is currently calculated;
Generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
the method of generating an adjusted feed rate for a corresponding feed assembly further comprises:
judging whether the first speed difference value is equal to a preset first speed threshold value or not, and judging whether the second speed difference value is equal to a preset second speed threshold value or not;
and if the first speed difference value is equal to the preset first speed threshold value and the second speed difference value is equal to the preset second speed threshold value, taking the first speed difference value or the second speed difference value as the adjusting feeding speed of the corresponding feeding component.
Further, the smelting area refers to an area for smelting materials in the electron beam furnace, and the smelting subarea is obtained by dividing the smelting area into equal-proportion rectangles; when the material is smelted, each smelting subarea corresponds to one electron beam gun;
the material feeding areas are material areas to be smelted, and when the materials in the n smelting areas are gradually smelted into material melt, the materials in the corresponding material feeding areas continuously move into the smelting areas.
In a second aspect, the invention provides a precise feeding method for smelting electron beam metal niobium, which is realized by using a precise feeding system based on the precise feeding method for smelting electron beam metal niobium, and comprises the following steps:
Acquiring smelting training data in n smelting subregions in a smelting region; n is an integer greater than or equal to 1; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
training a machine learning model for predicting the initial feeding speed based on smelting training data;
taking the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelting the materials in the smelting subareas, and collecting smelting monitoring data of n smelting subareas in real time;
extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
setting a smelting quality evaluation threshold, comparing a smelting quality evaluation coefficient with the smelting quality evaluation threshold, and acquiring feeding adjustment information according to a comparison result;
and extracting the current feeding speed of the corresponding feeding assembly of each smelting subarea according to the feeding regulation information, and generating the regulation feeding speed of the corresponding feeding assembly based on the current feeding speed of the corresponding feeding assembly.
In a third aspect, the present invention provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
The processor executes the steps in the precise feeding system for smelting the electron beam metal niobium by calling a computer program stored in the memory.
In a fourth aspect, the present invention provides a computer readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the steps in the precision feed system for electron beam niobium metal smelting described above.
The invention has the technical effects and advantages that:
according to the invention, smelting training data in n smelting subregions in a smelting region are obtained, a machine learning model for predicting initial feeding speed is trained based on the smelting training data, the initial feeding speed predicted by the trained machine learning model is used as the current feeding speed, materials in the smelting subregions are smelted, and smelting monitoring data of the n smelting subregions are acquired in real time; generating a smelting quality evaluation coefficient based on smelting monitoring data, comparing the smelting quality evaluation coefficient with a smelting quality evaluation threshold value, and judging whether to generate feeding regulation information according to a comparison result; based on the feeding adjustment information and the current feeding speed of the corresponding feeding assembly, adjusting the feeding speed of the corresponding feeding assembly; in an actual electron beam smelting process, the initial feeding speed trained based on a machine learning model is used as the current feeding speed, so that the material smelting of a smelting subarea is facilitated, real-time analysis is performed on the material smelting condition according to real-time smelting monitoring data, the feeding speed is accurately regulated, the condition that smelting quality is unqualified due to too high or too low speed is avoided, the feeding speed is accurately regulated, and further the high quality of materials is guaranteed.
Drawings
FIG. 1 is a schematic diagram of a system of example 1;
FIG. 2 is a schematic diagram of the smelting zone of example 1;
FIG. 3 is a flow chart of the method of example 2;
FIG. 4 is a schematic diagram of an electronic device in accordance with example 3;
fig. 5 is a schematic diagram of a computer-readable storage medium according to embodiment 4.
In the figure: 1. a feed zone; 2. smelting a subarea; 3. a gravity sensor.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and a similar second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The metals to be electron beam melted include, but are not limited to, metals such as niobium, tungsten, molybdenum, and high melting point metals such as high alloy steel of alloys thereof, and the following examples are given by taking niobium as an example, and how to accurately feed the raw materials of niobium during electron beam melting is described.
Example 1
Referring to fig. 1, the disclosure of the present embodiment provides a precise feeding system for smelting electron beam niobium, which is applied in an electron beam furnace, and includes:
the historical data acquisition module is used for acquiring smelting training data in n smelting subregions 2 in the smelting region; n is an integer greater than or equal to 1;
Referring to fig. 2, it should be noted that the smelting area refers to an area of a smelting material in the electron beam furnace, and the smelting sub-area 2 is obtained by dividing the smelting area into equal-proportion rectangles; when the materials are smelted, each smelting subarea 2 corresponds to one electron beam gun; it should be further noted that after n smelting subregions 2 are obtained, sequence number marking and sequencing are performed on each smelting subregion 2, and corresponding smelting routes are set according to the sequenced electron beam guns corresponding to each smelting subregion 2, so that the electron beam furnace performs data acquisition according to the preset smelting routes, and the data acquisition efficiency of the electron beam furnace is improved;
further, smelting training data are collected as material in the feed zone 1 is propelled into the smelting zone;
it should be noted that, the feeding area 1 is an area to be smelted of materials, and when the materials in the n smelting sub-areas 2 are gradually smelted into a material melt, the materials corresponding to the feeding assembly continuously move the feeding area 1 into the smelting sub-areas 2; it should also be explained that the control algorithm corresponding to the feeding assembly moving the material to the smelting sub-area 2 is not the main solution of the present invention, and there are also a series of existing control modes to achieve this function, so the present invention will not be repeated here.
The method for acquiring smelting training data in n smelting subregions 2 comprises the following steps:
specifically, the smelting training data comprises smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
in a preferred implementation, the smelting characteristics data includes electron beam energy density, material weight, and smelting speed;
the electron beam energy density is the energy density output by the electron beam gun, and the formula is as follows:
the current, the voltage and the focal cross-sectional area can be provided by an electron beam gun manufacturer, and the calculation of the electron beam energy density is the prior art and is not repeated here; the larger the electron beam energy density is, the faster the initial feeding speed is;
the weight of the material is obtained by a gravity sensor 3 arranged below the feeding area 1; when the material is charged into the material charging area 1, the weight of the material is automatically obtained according to the gravity sensor 3.
The smelting speed is obtained by monitoring the moving speed of material smelting in real time through a camera, and is calculated by following the position change of the front edge of material smelting, and the formula is as follows:
Wherein->For melting front position in unit time +.>Displacement in; the faster the smelting speed, the faster the initial feed speed;
the melting front position is a position on the surface of the material being melted when the electron beam gun melts the material, namely a boundary or interface position where the material is converted from a solid state to a liquid state, the position is a position where the electron beam focus is focused, and the material at the position is heated to a sufficiently high temperature by the high energy density of the electron beam gun so as to melt the material to form a material melt.
The initial feeding speed is obtained by measuring the speed of pushing the material corresponding to the feeding area 1 to the smelting subarea 2 through a speed sensor, namely, when smelting characteristic data are obtained, the feeding speed of the material corresponding to the feeding area 1 is collected.
The model training module is used for training a machine learning model for predicting the initial feeding speed based on smelting training data;
training a machine learning model for predicting an initial feeding speed based on smelting training data, wherein the training method comprises the following steps:
taking each group of smelting characteristic data as input of a machine learning model, wherein the machine learning model takes initial feeding speeds predicted for each group of smelting characteristic data as output, takes initial feeding speeds corresponding to the smelting characteristic data in smelting training data as prediction targets, and takes prediction errors of all initial feeding speeds as training targets; training the machine learning model until the prediction error reaches convergence, stopping training, and training the machine learning model for outputting the predicted initial feeding speed according to smelting characteristic data; the machine learning model is one of a polynomial regression model or an SVM model; the calculation formula of the prediction error is as follows:
Training a machine learning model with the goal of minimization, wherein +.>For group number of smelting characteristic data +.>In order to predict the error of the signal,is->Predicted initial feed rate corresponding to group smelting profile,/->Is->Actual primary smelting characteristic dataInitial feed rate.
It should be noted that, other model parameters of the machine learning model, such as the depth of the network model, the number of neurons in each layer, the activation function used by the network model, the convergence condition, the verification set proportion of the training set test set, the loss function and the like are all realized through actual engineering, and are obtained after experimental tuning is continuously performed;
the smelting monitoring module takes the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelts the materials in the smelting subareas 2 and acquires smelting monitoring data of n smelting subareas 2 in real time;
extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions 2 to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
in a preferred implementation, the melting monitoring data includes real-time temperature, real-time depth, and real-time electron beam power, and the melting monitoring threshold includes a temperature criterion value, a depth criterion value, and an electron beam power criterion value;
The real-time temperature is obtained by a temperature sensor arranged on the electron beam gun; the real-time depth is detected by measuring the reflected light of the smelting subregion 2 by a laser sensor mounted on the electron beam gun; the electron beam power is directly obtained through an electron beam gun; the process of smelting materials by the electron beam gun can be monitored in real time through the real-time temperature, the real-time depth and the real-time electron beam power;
specifically, the method for acquiring smelting monitoring thresholds of n smelting subregions 2 and analyzing smelting monitoring data comprises the following steps:
calculating a temperature difference value between the real-time temperature and a temperature standard value of each smelting subarea 2, and taking the temperature difference value as a temperature evaluation coefficient;
calculating a depth difference value between the real-time depth of each smelting subarea 2 and a depth standard value, and taking the depth difference value as a depth evaluation coefficient;
calculating an electron beam power difference value between the real-time electron beam power of each smelting subarea 2 and an electron beam power standard value, and taking the electron beam power difference value as an electron beam power evaluation coefficient;
further, the temperature evaluation coefficient, the depth evaluation coefficient and the electron beam power evaluation coefficient are subjected to formulated calculation to obtain a smelting quality evaluation coefficient The calculation formula is as follows:
；
in the method, in the process of the invention,temperature evaluation coefficient for n-th smelting subregion 2,/->For the depth evaluation coefficient of the nth smelting subregion 2,/->An electron beam power evaluation coefficient for the nth melting sub-region 2,/->Temperature weight factor representing n-th smelting subregion 2,/->Depth weight factor representing n-th smelting subregion 2,/->The electron beam power weighting factor for the nth melt sub-region 2 is represented.
The formulas related in the above are all formulas with dimensions removed and numerical values calculated, and are a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and weight factors in the formulas and various preset thresholds in the analysis process are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data; the size of the weight factor is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the weight factor depends on the number of sample data and the corresponding processing coefficient is preliminarily set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
The judgment module is used for setting a smelting quality evaluation threshold, comparing the smelting quality evaluation coefficient with the smelting quality evaluation threshold and acquiring feeding adjustment information according to a comparison result;
Specifically, the smelting quality evaluation coefficient is compared with a smelting quality evaluation threshold value, and the smelting quality evaluation coefficient is judgedWhether it is less than a smelting quality assessment threshold;
the method for acquiring the feeding regulation information according to the comparison result comprises the following steps:
if the smelting quality evaluation coefficientIf the feeding speed is larger than or equal to the smelting quality evaluation threshold value, feeding non-regulation information is generated, which indicates that the smelting quality of the material in the nth smelting subregion 2 is good, the current feeding speed of the corresponding feeding assembly is moderate, and the current feeding speed is not required to be regulated;
if the smelting quality evaluation coefficientIf the feeding speed is smaller than the smelting quality evaluation threshold value, feeding adjustment information is generated, and the defect of the smelting quality of the material in the nth smelting subregion 2 is indicated, and the current feeding speed of the corresponding feeding assembly is unsuitable and needs to be adjusted;
the feeding speed adjusting module is used for extracting the current feeding speed of the corresponding feeding component of each smelting subarea 2 according to the feeding adjusting information, and generating the adjusting feeding speed of the corresponding feeding component based on the current feeding speed of the corresponding feeding component;
specifically, generating an adjusted feed rate for a corresponding feed assembly includes:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly; wherein, randomly selecting a preset target feeding component as a feeding speed adjusting object, which is not limited herein;
Specifically, the generation process of the standard feeding speed of the preset target feeding assembly is as follows:
acquiring the current feeding speed of a preset target feeding assembly;
calculating a difference value between the preset standard feeding speed of the preset target feeding component and the design feeding speed of the preset target feeding component, and marking the difference value between the preset standard feeding speed of the preset target feeding component and the design feeding speed of the preset target feeding component as a target speed difference value;
the pre-standard feeding speed is a feeding speed of a preset target feeding component, wherein the standard feeding speed is influenced by friction force and feeding resistance.
It should be noted that, because the smelting speed in the smelting subregion 2 changes in real time, and the corresponding feeding component is affected by factors such as friction force or environmental resistance, for this reason, there may be a difference between the pre-standard feeding speed and the designed feeding speed, for this reason, the difference between the pre-standard feeding speed and the designed feeding speed is calculated as the target speed difference, so as to ensure the standard feeding speed accuracy of the preset target feeding component after correction and adjustment.
Adjusting the current feeding speed of the preset target feeding component according to the target speed difference value to obtain the standard feeding speed of the preset target feeding component;
Further, calculating a second speed difference corresponding to the current feed speed of the feed assembly and the current feed speed of an adjacent feed assembly, the adjacent feed assembly being the corresponding feed assembly for which the second speed difference is currently calculated;
generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
specifically, the method of generating an adjusted feed rate for a corresponding feed assembly further comprises:
judging whether the first speed difference value is equal to a preset first speed threshold value or not, and judging whether the second speed difference value is equal to a preset second speed threshold value or not;
if the first speed difference value is equal to a preset first speed threshold value and the second speed difference value is equal to a preset second speed threshold value, the first speed difference value or the second speed difference value is used as the adjusting feeding speed of the corresponding feeding component so as to obtain the adjusting feeding speed of the corresponding feeding component;
it should be noted that, the adjusted feeding speed of each corresponding feeding component refers to whether the adjusted feeding speed set for the feeding component corresponding to each smelting subregion 2 is determined according to the magnitude of the smelting quality evaluation coefficient, for example, if there is a smelting quality evaluation coefficient in one smelting subregion 2 that is greater than or equal to the smelting quality evaluation threshold, it is indicated that the current feeding speed of the corresponding feeding component is moderate, and according to the feeding non-adjustment information, the adjusted feeding speed of the feeding component corresponding to the smelting subregion 2 is zero; the method includes the steps that firstly, the current feeding speed of a corresponding feeding assembly is obtained, then, a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly is calculated, and a second speed difference value corresponding to the current feeding speed of the feeding assembly and the current feeding speed of an adjacent feeding assembly is calculated; then, judging whether the first speed difference value is equal to a preset first speed threshold value or not, and judging whether the second speed difference value is equal to a preset second speed threshold value or not; if the first speed difference value is equal to a preset first speed threshold value and the second speed difference value is equal to a preset second speed threshold value, the first speed difference value or the second speed difference value is used as the adjusting feeding speed of the corresponding feeding component; in contrast, the feeding speeds of the feeding components corresponding to the smelting quality evaluation coefficients are accurately adjusted through the operation of the same principle, and when the smelting quality of the materials is defective, the feeding speeds are accurately judged timely;
In one embodiment, if the first speed difference value is not equal to the preset first speed threshold value, judging that the speed regulation abnormality exists in the target feeding component, and informing an equipment maintainer to overhaul the target feeding component;
in another embodiment, if the second speed difference is not equal to the preset second speed threshold, calculating a third speed difference corresponding to the current feed speed of the feed assembly and the current feed speed of another adjacent feed assembly;
judging whether the third speed difference value is equal to a preset second speed threshold value, and if the third speed difference value is equal to the preset second speed threshold value, taking the first speed difference value or the third speed difference value as the adjusted feeding speed of the corresponding feeding assembly to obtain the adjusted feeding speed of the corresponding feeding assembly;
it should be further noted that if there are a plurality of differences corresponding to the current feeding speed of the feeding assembly and the current feeding speed of another adjacent feeding assembly, which are not equal to the preset speed threshold, it is determined that a serious feeding problem exists in the feeding assembly in the electron beam furnace, and equipment maintenance personnel are notified to overhaul the target feeding assembly.
And controlling each corresponding feeding component to push the materials to the smelting area according to the adjusting feeding speed of each corresponding feeding component, and stopping feeding until the materials are pushed.
According to the invention, smelting training data in n smelting subregions 2 in a smelting region are obtained, a machine learning model for predicting initial feeding speed is trained based on the smelting training data, the initial feeding speed predicted by the trained machine learning model is used as the current feeding speed, materials in the smelting subregions 2 are smelted, and smelting monitoring data of the n smelting subregions 2 are acquired in real time; generating a smelting quality evaluation coefficient based on smelting monitoring data, comparing the smelting quality evaluation coefficient with a smelting quality evaluation threshold value, and judging whether to generate feeding regulation information according to a comparison result; based on the feeding adjustment information and the current feeding speed of the corresponding feeding assembly, adjusting the feeding speed of the corresponding feeding assembly; in an actual electron beam smelting process, the initial feeding speed trained based on a machine learning model is used as the current feeding speed, so that the smelting of the materials in the smelting subarea 2 is facilitated, the real-time analysis is performed on the smelting conditions of the materials according to real-time smelting monitoring data, the feeding speed is accurately regulated, the condition that the smelting quality is unqualified due to too high or too low speed is avoided, the accurate regulation of the feeding speed is realized, and further the high quality of the materials is facilitated to be ensured.
Example 2
Referring to fig. 3, the embodiment provides a precise feeding method for smelting electron beam niobium metal, which includes:
acquiring smelting training data in n smelting subregions 2 in a smelting region; n is an integer greater than or equal to 1; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
training a machine learning model for predicting the initial feeding speed based on smelting training data;
taking the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelting the materials in the smelting subareas 2, and collecting smelting monitoring data of n smelting subareas 2 in real time; extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions 2 to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
setting a smelting quality evaluation threshold, comparing a smelting quality evaluation coefficient with the smelting quality evaluation threshold, and acquiring feeding adjustment information according to a comparison result;
extracting the current feeding speed of a corresponding feeding assembly of each smelting subarea 2 according to feeding regulation information, and generating the regulation feeding speed of the corresponding feeding assembly based on the current feeding speed of the corresponding feeding assembly;
Generating an adjusted feed rate for the corresponding feed assembly, comprising:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly; calculating a second speed difference value corresponding to the current feeding speed of the feeding assembly and the current feeding speed of the adjacent feeding assembly;
generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
and controlling the operation of the corresponding feeding assembly according to the adjusted feeding speed of the corresponding feeding assembly.
Further, the smelting characteristic data includes electron beam energy density, material weight, smelting speed and material type;
the energy density of the electron beam is the energy density output by the electron beam gun, and is calculated by acquiring the voltage, the current and the focal cross-sectional area output by the electron beam gun; the formula is as follows:
；
the weight of the material is obtained by a gravity sensor 3 arranged below the feeding area 1;
the smelting speed is obtained by monitoring the moving speed of material smelting in real time through a camera;
the material type is used for determining the material composition by analyzing the spectral characteristics of a melting area through a spectrometer or a light beam induced emission spectrum;
The initial feeding speed is obtained by measuring the speed of pushing the material corresponding to the feeding area 1 to the smelting subarea 2 through a speed sensor, namely, when smelting characteristic data are obtained, the feeding speed of the material corresponding to the feeding area 1 is collected.
Further, a machine learning model for predicting the initial feeding speed is trained based on smelting training data, and the training method comprises the following steps:
taking each group of smelting characteristic data as input of a machine learning model, wherein the machine learning model takes initial feeding speeds predicted for each group of smelting characteristic data as output, takes initial feeding speeds corresponding to the smelting characteristic data in smelting training data as prediction targets, and takes prediction errors of all initial feeding speeds as training targets; training the machine learning model until the prediction error reaches convergence, stopping training, and training the machine learning model for outputting the predicted initial feeding speed according to smelting characteristic data; the machine learning model is one of a polynomial regression model or an SVM model;
further, the smelting monitoring data comprise real-time temperature, real-time depth and real-time electron beam power, and the smelting monitoring threshold comprises a temperature standard value, a depth standard value and an electron beam power standard value;
The method for analyzing smelting monitoring data by acquiring smelting monitoring thresholds of n smelting subregions 2 comprises the following steps:
calculating a temperature difference value between the real-time temperature and a temperature standard value of each smelting subarea 2, and taking the temperature difference value as a temperature evaluation coefficient;
calculating a depth difference value between the real-time depth of each smelting subarea 2 and a depth standard value, and taking the depth difference value as a depth evaluation coefficient;
calculating an electron beam power difference value between the real-time electron beam power of each smelting subarea 2 and an electron beam power standard value, and taking the electron beam power difference value as an electron beam power evaluation coefficient;
the temperature evaluation coefficient, the depth evaluation coefficient and the electron beam power evaluation coefficient are formulated to obtain a smelting quality evaluation coefficientThe calculation formula is as follows:
；
in the method, in the process of the invention,temperature evaluation coefficient for n-th smelting subregion 2,/->For the depth evaluation coefficient of the nth smelting subregion 2,/->An electron beam power evaluation coefficient for the nth melting sub-region 2,/->Temperature weight factor representing n-th smelting subregion 2,/->Depth weight factor representing n-th smelting subregion 2,/->The electron beam power weighting factor for the nth melt sub-region 2 is represented.
Further, the method for comparing the smelting quality evaluation coefficient with the smelting quality evaluation threshold value and obtaining feeding adjustment information according to the comparison result comprises the following steps:
if the smelting quality evaluation coefficientIf the smelting quality evaluation threshold value is larger than or equal to the smelting quality evaluation threshold value, generating feeding unregulated information;
if the smelting quality evaluation coefficientAnd if the smelting quality evaluation threshold is smaller than the smelting quality evaluation threshold, generating feeding adjustment information.
Further, generating an adjusted feed rate for the respective feed assembly based on the current feed rate for the respective feed assembly, comprising:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly; the standard feeding speed of the preset target feeding assembly is generated as follows:
acquiring the current feeding speed of a preset target feeding assembly;
calculating a difference value between a preset standard feeding speed of the preset target feeding component and a design feeding speed of the preset target feeding component, and marking the difference value as a target speed difference value;
adjusting the current feeding speed of the preset target feeding component according to the target speed difference value to obtain the standard feeding speed of the preset target feeding component;
The pre-standard feeding speed is a feeding speed of a preset target feeding assembly, wherein the standard feeding speed of the preset target feeding assembly is influenced by friction force and feeding resistance.
Further, calculating a second speed difference corresponding to the current feed speed of the feed assembly and the current feed speed of an adjacent feed assembly, the adjacent feed assembly being the corresponding feed assembly for which the second speed difference is currently calculated;
the method for generating the adjusting feeding speed of the corresponding feeding assembly according to the first speed difference value and the second speed difference value comprises the following steps:
judging whether the first speed difference value is equal to a preset first speed threshold value or not, and judging whether the second speed difference value is equal to a preset second speed threshold value or not;
and if the first speed difference value is equal to the preset first speed threshold value and the second speed difference value is equal to the preset second speed threshold value, taking the first speed difference value or the second speed difference value as the adjusting feeding speed of the corresponding feeding component.
The smelting area refers to an area for smelting materials in the electron beam furnace, and the smelting subarea 2 is obtained by dividing the smelting area into equal-proportion rectangles; when the materials are smelted, each smelting subarea 2 corresponds to one electron beam gun;
The feeding area 1 is a material to-be-smelted area, and when the materials in the n smelting subareas 2 are gradually smelted into material melt, the materials in the feeding area 1 are continuously moved into the smelting subareas 2 by the corresponding feeding assembly.
Example 3
Referring to fig. 4, an electronic device includes: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the steps in the precise feeding system for smelting the electron beam metal niobium by calling a computer program stored in the memory.
Example 4
Referring to fig. 5, a computer readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the precision feed system for electron beam niobium metal smelting described above.
The formulas related in the above are all formulas with dimensions removed and numerical values calculated, and are a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and weight factors in the formulas and various preset thresholds in the analysis process are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data; the size of the weight factor is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the weight factor depends on the number of sample data and the corresponding processing coefficient is preliminarily set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, from one website site, computer, server, or data center over a wired network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. Accurate feeding system is used in electron beam niobium smelting, its characterized in that includes:
the historical data acquisition module is used for acquiring smelting training data in n smelting subregions (2) in the smelting region; n is an integer greater than or equal to 1; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
the model training module is used for training a machine learning model for predicting the initial feeding speed based on smelting training data;
the smelting monitoring module takes the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelts the materials in the smelting subareas (2), and collects smelting monitoring data of n smelting subareas (2) in real time; extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions (2) to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
The judgment module is used for setting a smelting quality evaluation threshold, comparing the smelting quality evaluation coefficient with the smelting quality evaluation threshold and acquiring feeding adjustment information according to a comparison result;
the feeding speed adjusting module is used for extracting the current feeding speed of the corresponding feeding assembly of each smelting subarea (2) according to feeding adjusting information and generating the adjusted feeding speed of the corresponding feeding assembly based on the current feeding speed of the corresponding feeding assembly;
a method of generating an adjusted feed rate for a corresponding feed assembly, comprising:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly;
calculating a second speed difference value corresponding to the current feeding speed of the feeding assembly and the current feeding speed of the adjacent feeding assembly;
generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
and controlling the operation of the corresponding feeding assembly according to the adjusted feeding speed of the corresponding feeding assembly.
2. The precision feed system for electron beam niobium metal melting of claim 1, wherein the melting characteristic data comprises electron beam energy density, material weight, and melting speed;
The energy density of the electron beam is the energy density output by the electron beam gun, and is calculated by acquiring the voltage, the current and the focal cross-sectional area output by the electron beam gun; the formula is as follows:
；
the weight of the materials is obtained by a gravity sensor (3) arranged below the feeding area (1);
the smelting speed is obtained by monitoring the moving speed of material smelting in real time through a camera;
the initial feeding speed is obtained by measuring the speed of pushing the material corresponding to the feeding area (1) to the smelting subarea (2) through a speed sensor, namely, when smelting characteristic data are obtained, the feeding speed of the material corresponding to the feeding area (1) is collected at the same time.
3. The accurate feeding system for electron beam niobium metal melting according to claim 2, wherein a machine learning model for predicting an initial feeding speed is trained based on melting training data, and the training method comprises:
taking each group of smelting characteristic data as input of a machine learning model, wherein the machine learning model takes initial feeding speeds predicted for each group of smelting characteristic data as output, takes initial feeding speeds corresponding to the smelting characteristic data in smelting training data as prediction targets, and takes prediction errors of all initial feeding speeds as training targets; training the machine learning model until the prediction error reaches convergence, stopping training, and training the machine learning model for outputting the predicted initial feeding speed according to smelting characteristic data; the machine learning model is one of a polynomial regression model or an SVM model.
4. The precision feed system for electron beam metal niobium melting of claim 3, wherein the melting monitoring data comprises real-time temperature, real-time depth and real-time electron beam power, and the melting monitoring threshold comprises a temperature standard value, a depth standard value and an electron beam power standard value;
the method for analyzing smelting monitoring data by acquiring smelting monitoring thresholds of n smelting subregions (2) comprises the following steps:
calculating a temperature difference value between the real-time temperature and a temperature standard value of each smelting subarea (2), and taking the temperature difference value as a temperature evaluation coefficient;
calculating a depth difference value between the real-time depth of each smelting subarea (2) and a depth standard value, and taking the depth difference value as a depth evaluation coefficient;
calculating an electron beam power difference value between the real-time electron beam power of each smelting subarea (2) and an electron beam power standard value, and taking the electron beam power difference value as an electron beam power evaluation coefficient;
the temperature evaluation coefficient, the depth evaluation coefficient and the electron beam power evaluation coefficient are formulated to obtain a smelting quality evaluation coefficientThe calculation formula is as follows:
；
in the method, in the process of the invention,for the temperature evaluation coefficient of the nth smelting subregion (2), +. >For the depth evaluation coefficient of the nth smelting subregion (2), +.>For the n-th melting sub-region (2) of the electron beam power evaluation coefficient,/for the electron beam power evaluation coefficient>Temperature weighting factor representing the nth smelting subregion (2), is described in terms of>Depth weight factor representing the nth smelting subregion (2), ->And represents the electron beam power weight factor of the nth smelting subregion (2).
5. The precise feed system for electron beam niobium metal melting as claimed in claim 4, wherein the method for comparing the melting quality evaluation coefficient with the melting quality evaluation threshold and obtaining the feed adjustment information according to the comparison result comprises:
if the smelting quality evaluation coefficientIf the smelting quality evaluation threshold value is larger than or equal to the smelting quality evaluation threshold value, generating feeding unregulated information;
if the smelting quality evaluation coefficientAnd if the smelting quality evaluation threshold is smaller than the smelting quality evaluation threshold, generating feeding adjustment information.
6. The precise feed system for electron beam niobium metal melting as claimed in claim 5, wherein the standard feed speed of the preset target feed assembly is generated as follows:
acquiring the current feeding speed of a preset target feeding assembly;
calculating a difference value between a preset standard feeding speed of the preset target feeding component and a design feeding speed of the preset target feeding component, and marking the difference value as a target speed difference value;
Adjusting the current feeding speed of the preset target feeding component according to the target speed difference value to obtain the standard feeding speed of the preset target feeding component;
the pre-standard feeding speed is a feeding speed of a preset target feeding component, wherein the standard feeding speed is influenced by friction force and feeding resistance;
the method for generating the adjusting feeding speed of the corresponding feeding assembly according to the first speed difference value and the second speed difference value comprises the following steps:
judging whether the first speed difference value is equal to a preset first speed threshold value or not, and judging whether the second speed difference value is equal to a preset second speed threshold value or not;
and if the first speed difference value is equal to the preset first speed threshold value and the second speed difference value is equal to the preset second speed threshold value, taking the first speed difference value or the second speed difference value as the adjusting feeding speed of the corresponding feeding component.
7. The precise feeding system for smelting the electron beam metal niobium according to claim 6, wherein the smelting area is an area for smelting materials in an electron beam furnace, and the smelting subarea (2) is obtained by dividing the smelting area into equal-proportion rectangles; when materials are smelted, each smelting subarea (2) corresponds to one electron beam gun;
The feeding areas (1) are areas to be smelted of materials, and when the materials in the n smelting subareas (2) are gradually smelted into material melt, the materials corresponding to the feeding assemblies continuously move the feeding areas (1) to enter the smelting subareas (2).
8. The precise feeding method for electron beam metal niobium smelting, which is realized by using the precise feeding system for electron beam metal niobium smelting based on any one of claims 1 to 7, is characterized by comprising the following steps:
smelting training data in n smelting subregions (2) in a smelting region are acquired; n is an integer greater than or equal to 1; the smelting training data comprise smelting characteristic data and initial feeding speeds corresponding to the smelting characteristic data;
training a machine learning model for predicting the initial feeding speed based on smelting training data;
taking the initial feeding speed predicted by the trained machine learning model as the current feeding speed, smelting the material in the smelting subareas (2), and collecting smelting monitoring data of n smelting subareas (2) in real time; extracting smelting monitoring data, and acquiring smelting monitoring thresholds of n smelting subregions (2) to analyze the smelting monitoring data so as to acquire smelting quality evaluation coefficients;
Setting a smelting quality evaluation threshold, comparing a smelting quality evaluation coefficient with the smelting quality evaluation threshold, and acquiring feeding adjustment information according to a comparison result;
extracting the current feeding speed of a corresponding feeding assembly of each smelting subarea (2) according to feeding regulation information, and generating the regulation feeding speed of the corresponding feeding assembly based on the current feeding speed of the corresponding feeding assembly;
a method of generating an adjusted feed rate for a corresponding feed assembly, comprising:
calculating a first speed difference value corresponding to the current feeding speed of the feeding assembly and the standard feeding speed of a preset target feeding assembly;
calculating a second speed difference value corresponding to the current feeding speed of the feeding assembly and the current feeding speed of the adjacent feeding assembly;
generating an adjusted feed speed for the corresponding feed assembly according to the first speed difference and the second speed difference;
and controlling the operation of the corresponding feeding assembly according to the adjusted feeding speed of the corresponding feeding assembly.
9. An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor performs the steps in the precision feed system for electron beam metal niobium smelting of any one of claims 1-7 by invoking a computer program stored in the memory.
10. A computer readable storage medium storing instructions that when run on a computer cause the computer to perform the steps in the precision feed system for electron beam metal niobium smelting of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311786945.6A CN117469970B (en) | 2023-12-25 | 2023-12-25 | Accurate feeding system for smelting electron beam metal niobium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311786945.6A CN117469970B (en) | 2023-12-25 | 2023-12-25 | Accurate feeding system for smelting electron beam metal niobium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117469970A CN117469970A (en) | 2024-01-30 |
| CN117469970B true CN117469970B (en) | 2024-03-12 |
Family
ID=89639883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311786945.6A Active CN117469970B (en) | 2023-12-25 | 2023-12-25 | Accurate feeding system for smelting electron beam metal niobium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117469970B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897354A (en) * | 2018-07-13 | 2018-11-27 | 广西大学 | A kind of aluminium fusion process fire box temperature prediction technique based on depth confidence network |
| CN113916000A (en) * | 2021-09-27 | 2022-01-11 | 共享智能铸造产业创新中心有限公司 | Method for accelerating feeding and batching speed of electromagnetic chuck |
| CN114265885A (en) * | 2021-12-28 | 2022-04-01 | 中南大学 | Automatic control method and system for moisture of sintering return powder |
| CN114801050A (en) * | 2022-04-26 | 2022-07-29 | 健大电业制品（昆山）有限公司 | Feeding device of injection molding machine and operation method thereof |
| CN115582522A (en) * | 2022-10-03 | 2023-01-10 | 湖南塑源特科技有限公司 | High-precision chromium alloy continuous casting molding monitoring method and system |
-
2023
- 2023-12-25 CN CN202311786945.6A patent/CN117469970B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897354A (en) * | 2018-07-13 | 2018-11-27 | 广西大学 | A kind of aluminium fusion process fire box temperature prediction technique based on depth confidence network |
| CN113916000A (en) * | 2021-09-27 | 2022-01-11 | 共享智能铸造产业创新中心有限公司 | Method for accelerating feeding and batching speed of electromagnetic chuck |
| CN114265885A (en) * | 2021-12-28 | 2022-04-01 | 中南大学 | Automatic control method and system for moisture of sintering return powder |
| CN114801050A (en) * | 2022-04-26 | 2022-07-29 | 健大电业制品（昆山）有限公司 | Feeding device of injection molding machine and operation method thereof |
| CN115582522A (en) * | 2022-10-03 | 2023-01-10 | 湖南塑源特科技有限公司 | High-precision chromium alloy continuous casting molding monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117469970A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108290219B (en) | Additive manufacturing method and apparatus | |
| Xiong et al. | Control of deposition height in WAAM using visual inspection of previous and current layers | |
| Cox et al. | Application of neural computing in basic oxygen steelmaking | |
| CN1048672C (en) | Prediction and control of quality of continuously cast article | |
| JPH11320261A (en) | Method and device for providing index for special property on workpiece characteristic | |
| SE520140C2 (en) | Method and device for arc welding and use, computer program product and computer-readable medium | |
| US10714304B2 (en) | Charged particle beam apparatus | |
| Prasanna et al. | Optimizing the process parameters of electrical discharge machining on AA7075-SiC alloys | |
| Ledford et al. | Real time monitoring of electron emissions during electron beam powder bed fusion for arbitrary geometries and toolpaths | |
| CN111886105A (en) | System and method for monitoring and controlling build quality during e-beam manufacturing | |
| CN117469970B (en) | Accurate feeding system for smelting electron beam metal niobium | |
| DE102012224184A1 (en) | Method for the prediction, control and / or regulation of steelworks processes | |
| Botnikov et al. | Development of the metal temperature prediction model for steel-pouring and tundish ladles used at the casting and rolling complex | |
| CN116822342A (en) | Process identification and performance prediction method for zirconium alloy laser cutting | |
| CN113092527B (en) | Multi-dimensional test system for high-temperature oxidation behavior and flame retardance of multi-flame-retardant-element magnesium alloy | |
| US5930284A (en) | Multiple input electrode gap controller | |
| JP2005242818A (en) | Quality effect factor analyzing method, quality forecasting method, quality control method, quality effect factor analyzing device, quality forecasting device, quality control device, quality effect factor analyzing system, quality forecasting system, quality control system, and computer program | |
| Kuo et al. | Prediction of heat-affected zone using Grey theory | |
| CN117612651A (en) | Method for predicting manganese content of converter endpoint | |
| Botnikov et al. | Development of a steel temperature prediction model in a steel ladle and tundish in a casting and rolling complex | |
| JP2002081992A (en) | Plasma ash melting furnace and method for operating the same | |
| CN117332705B (en) | Electron beam nickel-niobium smelting method and system based on scanning track control | |
| RU2812444C1 (en) | System and method for controlling material distribution based on predicting material layer thickness | |
| KR100905659B1 (en) | A thickness-compensation controller for the rear-end of a rolling strip | |
| CN112084688B (en) | Cathode life prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |