CN112091162A - Cylindrical forging spray set based on BP neural network - Google Patents
Cylindrical forging spray set based on BP neural network Download PDFInfo
- Publication number
- CN112091162A CN112091162A CN202010870930.8A CN202010870930A CN112091162A CN 112091162 A CN112091162 A CN 112091162A CN 202010870930 A CN202010870930 A CN 202010870930A CN 112091162 A CN112091162 A CN 112091162A
- Authority
- CN
- China
- Prior art keywords
- neural network
- tank body
- control center
- computer control
- main tank
- 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.)
- Pending
Links
- 238000005242 forging Methods 0.000 title claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 17
- 239000007921 spray Substances 0.000 title claims abstract description 6
- 238000005507 spraying Methods 0.000 claims abstract description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 15
- 230000009467 reduction Effects 0.000 claims abstract description 6
- 238000001816 cooling Methods 0.000 claims description 29
- 239000003638 chemical reducing agent Substances 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 11
- 238000010080 roll forging Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 239000003595 mist Substances 0.000 description 8
- 210000002569 neuron Anatomy 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000003754 machining Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- FGRBYDKOBBBPOI-UHFFFAOYSA-N 10,10-dioxo-2-[4-(N-phenylanilino)phenyl]thioxanthen-9-one Chemical compound O=C1c2ccccc2S(=O)(=O)c2ccc(cc12)-c1ccc(cc1)N(c1ccccc1)c1ccccc1 FGRBYDKOBBBPOI-UHFFFAOYSA-N 0.000 description 1
- TVEXGJYMHHTVKP-UHFFFAOYSA-N 6-oxabicyclo[3.2.1]oct-3-en-7-one Chemical compound C1C2C(=O)OC1C=CC2 TVEXGJYMHHTVKP-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 229910001563 bainite Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 229910000734 martensite Inorganic materials 0.000 description 1
- 150000001247 metal acetylides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21K—MAKING FORGED OR PRESSED METAL PRODUCTS, e.g. HORSE-SHOES, RIVETS, BOLTS OR WHEELS
- B21K29/00—Arrangements for heating or cooling during processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a cylindrical forge piece spraying device based on a BP (back propagation) neural network, which comprises a main box body and a computer control center, wherein the computer control center based on the trained BP neural network is installed at one side of the main box body, and is characterized in that: the main tank body mid-mounting has the backing roll, backing roll one end is equipped with the bearing, computer control center one side is provided with the reduction gear, reduction gear one side is provided with driving motor, the main tank body upper end is equipped with the inlet tube, inlet tube one side is equipped with fan nozzle, thereby the nozzle can the flexible angle change nozzle size change the water spray volume, fan nozzle one end is equipped with atomizing nozzle master switch, temperature acquisition equipment is installed to the main tank body upper end, under the prerequisite that does not influence the forging performance, makes the cold stage of fog avoid the cold defect that forms unusual tissue influence machinability easily of high temperature fog for the forging quality improves greatly to simple structure, convenient to use.
Description
Technical Field
The invention relates to the technical field of controlled cooling of forged parts after forging, in particular to a cylindrical forging spraying device based on a BP (back propagation) neural network.
Background
The working procedures of the cylindrical forgings such as the small and medium-sized rollers (1-10 t) and the like are various, the quality of the forgings is difficult to control, the production process of the cylindrical forgings is scientifically and reasonably controlled in each production link, and the cooling modes of the cylindrical forgings such as the rollers and the like after forging are mainly mist-cooled, air-cooled or air-cooled to room temperature. Under the condition that the finish forging temperature of the forged piece is higher than 850 ℃, a proper cooling method is required to be adopted, and different cooling processes are required to be formulated for cylindrical forged pieces such as rollers with different diameters, so that the cooling quality of the forged product is ensured. Taking a roller as an example, an enterprise only produces a cooling process by using a roller with a part of diameter at present, no proper reference standard exists for making a cooling process for the roller with the diameter outside the existing diameter, the cooling quality after the roller forging cannot be guaranteed, and the production efficiency of the enterprise and the qualification rate of the product quality are influenced.
Therefore, the invention discloses a cylindrical forge piece spraying device based on a BP neural network, which is necessary to solve the problems.
Disclosure of Invention
The invention aims to provide a cylindrical forge piece spraying device based on a BP (back propagation) neural network, which aims to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme by taking a roller as an example: the utility model provides a cylindrical forging spray set based on BP neural network, includes the main tank body and computer control center, main tank body one side is installed the computer control center based on BP neural network algorithm, its characterized in that: the improved temperature control device is characterized in that a supporting roller is mounted in the middle of the main box body, a bearing is arranged at one end of the supporting roller, a speed reducer is arranged on one side of the computer control center, a driving motor is arranged on one side of the speed reducer, a water inlet pipe is arranged at the upper end of the main box body, a fan-shaped nozzle is arranged on one side of the water inlet pipe, an atomizing nozzle main switch is arranged at one end of the fan-shaped nozzle, and.
Preferably, the supporting roll, the driving motor, the bearing and the speed reducer are connected through a chain, the supporting roll rotates anticlockwise or clockwise under the transmission of the driving motor, and meanwhile the forging piece is driven to rotate clockwise or anticlockwise.
Preferably, one end of the water inlet pipe is fixedly connected with the water storage tank.
Preferably, the computer control center is wirelessly connected with the temperature acquisition equipment, so that the structure of the roller core made of the specific material and the cooling water spraying speed margin can be predicted.
Preferably, the temperature acquisition device detects the temperature of the forging from the beginning to the end of fog cooling.
The invention has the technical effects and advantages that:
the invention applies a BP neural network model to the traditional processing by arranging a driving motor, a speed reducer, a computer control center, an atomizing nozzle main switch, a temperature acquisition device, a water inlet pipe, a fan-shaped nozzle, a main box body, a supporting roller, a bearing and a chain, and searches the optimal fog cooling process meeting all targets by inputting parameters such as material, temperature, diameter and the like of a roller. The method has the advantages that various indexes of the roller forging with any diameter after mist cooling are predicted through the trained three-layer BP neural network model, the core structure of the forging can be predicted after the computer control center receives relevant parameters such as the temperature of the forging, the diameter of the forging and the like, meanwhile, reasonable water spraying speed is given, the fault tolerance rate of the mist cooling process after roller forging is improved, meanwhile, the temperature detection of the forging at the beginning and the end of mist cooling is increased, on the premise of not influencing the performance of the forging, the defect that abnormal structures easily formed by high-temperature mist cooling affect the machining performance is avoided in the mist cooling stage, the quality of the forging is greatly improved, the structure is simple, and the use is convenient.
Drawings
Fig. 1 is a schematic view of the overall structure of the present invention.
Fig. 2 is a front view of the present invention.
FIG. 3 is a schematic diagram of the prediction of the three-layer BP neural network according to the present invention.
In the figure: the device comprises a driving motor 1, a speed reducer 2, a computer control center 3, a main atomizing nozzle switch 4, a temperature acquisition device 5, a water inlet pipe 6, a fan-shaped nozzle 7, a main box body 8, a supporting roller 9, a bearing 10 and a chain 11.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a cylindrical forge piece spraying device based on a BP (back propagation) neural network, which comprises a main box body 8 and a computer control center 3, wherein the computer control center 3 is installed at one side of the main box body 8, and the device is characterized in that: 8 mid-mounting of the main tank body has backing roll 9, 9 one end of backing roll is equipped with bearing 10, 3 one sides of computer control center are provided with reduction gear 2, 2 one sides of reduction gear are provided with driving motor 1, 8 upper ends of the main tank body are equipped with inlet tube 6, 6 one sides of inlet tube are equipped with fan nozzle 7, 7 one ends of fan nozzle are equipped with atomizing nozzle master switch 4, temperature acquisition equipment 5 is installed to 8 upper ends of the main tank body.
Further, in the above technical solution, the support roller 9, the driving motor 1, the bearing 10 and the speed reducer 2 are linked by a chain 11;
further, in the above technical scheme, one end of the water inlet pipe 6 is fixedly connected with a water storage tank;
further, in the above technical solution, the computer control center 3 is wirelessly connected to a temperature acquisition device 5;
further, in the above technical solution, the 5 detects the forging temperature at the start and the end of the fog cooling.
It should be noted that the cylindrical forging spraying device based on the BP neural network of the present invention takes the MC5 cold roll forging as an example:
step one, placing a forged MC5 cold roll forging on a supporting roll 9 of the device for air cooling;
step two, monitoring the air cooling process of the MC5 cold roll in the step one by using a temperature detector 5 on a main box body 8;
step three, predicting other indexes such as temperature margin and the like of the structure defect which is easily formed by the mist cooling of the MC5 cold roll through the information received by the computer control center 3, controlling the air cooling process, and reducing the temperature of the MC5 cold roll forge piece in the step two to 500 +/-20 ℃;
step four, starting the motor 1 to drive the MC5 cold roll forging to rotate while the supporting roll 9 rotates;
step five, turning on a main switch 4 of an atomizing nozzle, and controlling the mist cooling process of the MC5 cold roll forging through the water spraying speed predicted in the step three;
step six, predicting the final fog cooling temperature through a computer control center 3 according to the technical requirements, and fog cooling the MC5 cold roll forging in the step five to 200 +/-20 ℃;
step seven, taking the MC5 cold roll forging subjected to spray cooling in the step six out of the basket, and air-cooling to room temperature;
and step eight, performing quality inspection on the cooled MC5 cold roll.
According to the prediction result of the three-layer BP neural network model, the temperature of the MC5 cold roll forging is reduced to 500 +/-20 ℃ in the third step, and then fog cooling is carried out, so that the problem that the surface of the MC5 cold roll forging generates martensite, bainite and other abnormal structure defects during fog cooling at a high temperature stage and is not beneficial to subsequent machining is solved. And step four to step six, the MC5 cold roll forging is subjected to mist cooling at 500 +/-20 ℃ to 200 +/-20 ℃, so that the formation of reticular carbides is reduced, the structure stress is eliminated, the structure is refined, the machining performance is improved, and the setting of the subsequent heat treatment process of the MC5 cold roll forging is facilitated.
It should be noted that: the BP network adopts an input layer, a hidden layer and an output layer, wherein the upper layer and the lower layer are in full connection, namely, each neuron of the lower layer is in full connection with each neuron of the upper layer, each layer of neurons is not connected, specifically, the roller material, the diameter and the temperature of the input layer are not connected, the hidden layer is connected with each neuron of the input layer, the water spraying speed, the core tissue and the hardness of the output layer are not connected, the hidden layer is connected with each neuron of the hidden layer, a database is established through data obtained through simulation or specific physical experiments, such as the material, the diameter and the temperature of an input data roller, the corresponding output data hardness, the water spraying speed, the core tissue and the like, and the established database is utilized to train the algorithm for N times. After the input data is provided for the trained algorithm network, the activation function values of the neurons are sequentially transmitted from the input layer to the output layer through the intermediate hidden layer, and the neurons of the output layer obtain the input response of the network after calculation to obtain corresponding output data. Then, the network weight is adjusted according to the direction of reducing the error between the actual output and the target output of the network, each connection weight is corrected layer by layer from the output layer through the middle hidden layer, and finally, the connection weight returns to the input layer. The algorithm approaches the fit accuracy target step by continuously adjusting the network weights and closed values in a direction that decreases relative to the error function gradient.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (5)
1. The utility model provides a cylindrical forging spray set based on BP neural network, includes main tank body (8) and computer control center (3), its characterized in that are installed to main tank body (8) one side: the utility model discloses a temperature monitoring device, including main tank body (8), backing roll (9) one end is equipped with bearing (10), computer control center (3) one side is provided with reduction gear (2), reduction gear (2) one side is provided with driving motor (1), main tank body (8) upper end is equipped with inlet tube (6), inlet tube (6) one side is equipped with fan nozzle (7), fan nozzle (7) one end is equipped with atomizing nozzle master switch (4), temperature acquisition equipment (5) are installed to main tank body (8) upper end.
2. The cylindrical forging spraying device based on the BP neural network as claimed in claim 1, wherein: the supporting roller (9), the driving motor (1), the bearing (10) and the speed reducer (2) are connected through a chain (11).
3. The cylindrical forging spraying device based on the BP neural network as claimed in claim 1, wherein: one end of the water inlet pipe (6) is fixedly connected with the water storage tank.
4. The cylindrical forging spraying device based on the BP neural network as claimed in claim 1, wherein: the computer control center (3) is in wireless connection with the temperature acquisition equipment (5).
5. The cylindrical forging spraying device based on the BP neural network as claimed in claim 1, wherein: the temperature acquisition equipment (5) detects the temperature of the forge piece from the beginning to the end of fog cooling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870930.8A CN112091162A (en) | 2020-08-26 | 2020-08-26 | Cylindrical forging spray set based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870930.8A CN112091162A (en) | 2020-08-26 | 2020-08-26 | Cylindrical forging spray set based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112091162A true CN112091162A (en) | 2020-12-18 |
Family
ID=73756590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010870930.8A Pending CN112091162A (en) | 2020-08-26 | 2020-08-26 | Cylindrical forging spray set based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112091162A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0762426A (en) * | 1993-08-19 | 1995-03-07 | Nishihira:Kk | Method and device for quenching and cooling shaft-like work |
| CN201416022Y (en) * | 2009-05-31 | 2010-03-03 | 湖南楊子冶金實業有限公司 | Ejection quencher |
| CN102151704A (en) * | 2010-02-11 | 2011-08-17 | 宝山钢铁股份有限公司 | Stelmor line cooling method of high-speed wire by taking temperature as direct-control parameter |
| CN104195302A (en) * | 2014-08-21 | 2014-12-10 | 宜兴市永昌轧辊有限公司 | Novel jet quenching device for cold rolls |
| CN105063302A (en) * | 2015-07-25 | 2015-11-18 | 宜兴市永昌轧辊有限公司 | Novel spray quenching cooling device |
| CN205710844U (en) * | 2016-07-06 | 2016-11-23 | 马鞍山平文锻造有限公司 | Roll spray cooling device |
| CN210945699U (en) * | 2019-08-16 | 2020-07-07 | 常州市同友机械科技有限公司 | Roller spray quenching device |
-
2020
- 2020-08-26 CN CN202010870930.8A patent/CN112091162A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0762426A (en) * | 1993-08-19 | 1995-03-07 | Nishihira:Kk | Method and device for quenching and cooling shaft-like work |
| CN201416022Y (en) * | 2009-05-31 | 2010-03-03 | 湖南楊子冶金實業有限公司 | Ejection quencher |
| CN102151704A (en) * | 2010-02-11 | 2011-08-17 | 宝山钢铁股份有限公司 | Stelmor line cooling method of high-speed wire by taking temperature as direct-control parameter |
| CN104195302A (en) * | 2014-08-21 | 2014-12-10 | 宜兴市永昌轧辊有限公司 | Novel jet quenching device for cold rolls |
| CN105063302A (en) * | 2015-07-25 | 2015-11-18 | 宜兴市永昌轧辊有限公司 | Novel spray quenching cooling device |
| CN205710844U (en) * | 2016-07-06 | 2016-11-23 | 马鞍山平文锻造有限公司 | Roll spray cooling device |
| CN210945699U (en) * | 2019-08-16 | 2020-07-07 | 常州市同友机械科技有限公司 | Roller spray quenching device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100383796C (en) | Copper-alloy pipe-material casting-milling technology parameter designing and optimizing method | |
| CN102699102B (en) | Production process method of small-caliber cold-drawing seamless steel tube used for boiler | |
| CN103567225B (en) | Mandrel cooling device | |
| CN105032952B (en) | A kind of pipe line steel slab kowtows nose control method | |
| CN102363835B (en) | Intermediate frequency induction heat treatment device for steel tubes, and heat treatment method of the same | |
| CN107971351B (en) | Production device and production method for steel pipe online cooling | |
| CN107971345B (en) | Process control system and control method for steel pipe on-line cooling | |
| CN101078043A (en) | Medium frequency induction heating treatment system for steel pipe, petroleum well pipe and drill pipe | |
| CN106350643A (en) | Thermal treatment method of large die steel | |
| CN108165716A (en) | A kind of online EDC water-baths toughening processing method of high intensity bridge cable zinc-coated wire gren rod | |
| CN110055394A (en) | A kind of heat treatment cooling technique of railway wheel | |
| CN112091162A (en) | Cylindrical forging spray set based on BP neural network | |
| CN105400945A (en) | Thermal treatment system for large-diameter skew rolling ball-milling steel balls | |
| CN108998634B (en) | Production device for ultrahigh-strength steel plate | |
| CN113604649A (en) | Heat treatment method for 42CrMo alloy structural steel hollow shaft type forge piece and hollow shaft type forge piece prepared by heat treatment method | |
| CN109513766A (en) | A kind of manufacturing method of high concentricity martensitic stainless steel seamless pipe material | |
| CN109593933A (en) | A kind of slab automatic on-line quenching unit and method | |
| CN110883105B (en) | Method for adjusting parameters of controlled cooling optimizing water tank of hot-rolled deformed steel bar in real time after rolling | |
| CN108531920A (en) | A kind of pre-treating technology of hydraulic plunger workpiece | |
| CN106623547B (en) | A kind of spiral semicanal automatic winding system | |
| CN102586565B (en) | Rapid cooling method and device after medium and thick plate heat treatment furnace | |
| CN203923298U (en) | A kind of injection cooling apparatus of long chi rail press quenching unit | |
| CN205295412U (en) | Oblique milling ball -milling steel ball guenching unit | |
| CN204918689U (en) | Seamless steel pipe segmentation guenching unit | |
| CN103805763B (en) | A kind of deformation heat treatment method of refinement roll textura epidermoidea |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201218 |
|
| RJ01 | Rejection of invention patent application after publication |