CN116533419A - Air cooler control method of multilayer co-extrusion film forming machine - Google Patents
Air cooler control method of multilayer co-extrusion film forming machine Download PDFInfo
- Publication number
- CN116533419A CN116533419A CN202310663096.9A CN202310663096A CN116533419A CN 116533419 A CN116533419 A CN 116533419A CN 202310663096 A CN202310663096 A CN 202310663096A CN 116533419 A CN116533419 A CN 116533419A
- Authority
- CN
- China
- Prior art keywords
- moment
- value
- overflow
- light transmittance
- air cooler
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001125 extrusion Methods 0.000 title claims abstract description 39
- 238000002834 transmittance Methods 0.000 claims abstract description 55
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 238000001816 cooling Methods 0.000 claims description 24
- 230000035699 permeability Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013459 approach Methods 0.000 claims description 8
- 108091008143 L ribosomal proteins Proteins 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims 1
- 239000000463 material Substances 0.000 abstract description 4
- 230000006978 adaptation Effects 0.000 abstract description 3
- 230000002688 persistence Effects 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 13
- 101100478237 Caenorhabditis elegans ost-1 gene Proteins 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 8
- 239000012768 molten material Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000010096 film blowing Methods 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C35/00—Heating, cooling or curing, e.g. crosslinking or vulcanising; Apparatus therefor
- B29C35/007—Tempering units for temperature control of moulds or cores, e.g. comprising heat exchangers, controlled valves, temperature-controlled circuits for fluids
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C35/00—Heating, cooling or curing, e.g. crosslinking or vulcanising; Apparatus therefor
- B29C35/16—Cooling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C55/00—Shaping by stretching, e.g. drawing through a die; Apparatus therefor
- B29C55/28—Shaping by stretching, e.g. drawing through a die; Apparatus therefor of blown tubular films, e.g. by inflation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C35/00—Heating, cooling or curing, e.g. crosslinking or vulcanising; Apparatus therefor
- B29C35/16—Cooling
- B29C2035/1658—Cooling using gas
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Thermal Sciences (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Extrusion Moulding Of Plastics Or The Like (AREA)
Abstract
The invention belongs to the technical field of data acquisition and intelligent production, and provides an air cooler control method of a multilayer co-extrusion film forming machine, which comprises the following steps of: arranging a light transmittance tester, and measuring in real time through the light transmittance tester to obtain an actual measurement value; and the measured values obtained by the light transmittance testers are combined to form state data; then the state data at each moment is formed into a near-end observation sequence and a far-end observation sequence; and calculating the overflow approaching level for the near-end observation sequence and the loss level for the far-end observation sequence respectively, and finally realizing the air cooler adjustment according to the overflow approaching level and the loss level. When the temperature of the air cooler at each position of the tubular film is repeatedly changed or converted, the adaptation degree between the air speed of the air cooler and the temperature of the extruded material of the die head is precisely quantized, so that the risk of deformation or loss of the die head can be effectively reduced, and the application persistence of the working die head is enhanced.
Description
Technical Field
The invention belongs to the technical field of data acquisition and intelligent preparation, and particularly relates to an air cooler control method of a multilayer co-extrusion film forming machine.
Background
A multilayer coextrusion film machine is an apparatus for producing a multilayer composite film by extruding and superposing molten materials of different materials together to form a multilayer film structure. The multi-layer co-extrusion film forming machine has the advantages that multi-layer films with different characteristics and functions, such as barrier property, strength, transparency, high transparency, puncture resistance, high toughness, good low-temperature cutting property, good compound fastness, curling resistance and the like, can be produced, and according to various different purposes, different proportions of molten materials are often required so that the multi-layer co-extrusion film can achieve the planned target function or achieve the estimated target performance. The equipment is widely applied to the fields of food packaging, medical use, agricultural covering films and the like, and meets the requirements of different industries on the multifunctional composite films.
In the running process of the multilayer co-extrusion film forming machine, after a plurality of extruders respectively melt and extrude the molten materials with different functions, the molten materials are conveyed to a die head in respectively distributed runners and are converged, and then the molten materials are blown up by a film blowing machine and are cooled. However, in the process of extruding a tubular parison through a die head with each flow passage, unstable laminar flow caused by repeated change of the temperature of the die head due to uncertainty or melting instability of a molten liquid flow often occurs, especially if the set of the blowing ratio of the multilayer coextruded film product according to a target function or target performance is low, front-back pressure imbalance in an extrusion channel of the die head is easily caused by the unstable laminar flow, further, repeated change of the temperature of molten material at an extrusion port of the die head is caused, and when a cooling fan or a cooling fan of a film blowing machine adopts a fixed wind speed to perform a film blowing process, insufficient matching degree between the temperature of the molten material at the extrusion port and the wind speed of the cooling fan is formed, deformation of the extrusion channel or the extrusion port of the die head is accelerated due to insufficient matching degree, vicious circulation is formed, the service life of the die head is greatly reduced, and even the machine production is failed, so that industrial production is influenced. The light transmittance of the film can timely reflect the problem of insufficient matching degree, and the matching degree between the wind speed and the temperature of the cooling fan can be quantized by utilizing the light transmittance, so that the service life and the application accuracy of the die head can be prolonged by timely and dynamically adjusting the cooling fan or the cooling fan.
Disclosure of Invention
The invention aims to provide an air cooler control method of a multilayer co-extrusion film forming machine, which aims to solve one or more technical problems in the prior art and at least provides a beneficial selection or creation condition.
In order to achieve the above object, according to an aspect of the present invention, there is provided an air cooler control method of a multi-layer co-extrusion film machine, the method comprising the steps of:
s100, arranging a light transmittance tester, and measuring in real time through the light transmittance tester to obtain an actual measurement value;
s200, combining measured values obtained by the light transmittance testers to form state data;
s300, the state data at each moment is formed into a near-end observation sequence and a far-end observation sequence;
s400, calculating an overflow tending level for a near-end observation sequence;
s500, calculating a loss level for a far-end observation sequence;
and S600, realizing air cooler adjustment according to the overflow trend and the loss level.
Further, in step S100, a light transmittance tester is arranged, and the method for obtaining the measured value by real-time measurement of the light transmittance tester is as follows: the height of the position, where the film cooling area is connected with the air cooling belt, from the ground is HF, wherein the film cooling area is positioned below the air cooling belt, the air cooling belt is a region where a molten tubular blank is rapidly deformed, the film cooling area is a region of a tubular film formed by a shaped film, and the arrangement height of a light transmittance tester is defined as HS, HS epsilon [ HF-3cm, HF-6cm ]; at least 6-12 light transmittance testers are equidistantly arranged at the position from the ground HS, so that the measurement direction of each light transmittance tester points to the central axis of the tubular film and the distances between each light transmittance tester and the central axis of the tubular film are equal; each light transmittance tester measures the light transmittance of the film in real time as an actual measurement value.
Further, in step S200, the method for composing the status data by combining the measured values obtained by the respective light transmittance testers is: the arithmetic average value, the minimum value and the maximum value of each measured value obtained by measuring each light transmittance tester at the same time are respectively used as a parallel uniformity Pex, a same-row low value Pbv and a same-row high value Ptv; pex, pbv and Ptv are formed into one tuple and are denoted as state data PTup.
Further, in step S300, the method for constructing the state data of each time into the near-end observation sequence and the far-end observation sequence is as follows: the time one minute before the current time is recorded as StT, and a time period is set as a reference length FdLen, fdLen epsilon [0.5,3] hours; the minimum value of the parallelism obtained from StT to the current moment is marked as ExrdLow, the minimum value of the parallelism obtained from StT to FdLen before the moment is marked as CurdLow, the moment obtained by CurdLow is marked as MdT, and a sequence is formed according to the state data obtained in the time period from StT to MdT and is marked as a near-end observation sequence RPLs; traversing the parallelism of all the moments in reverse time sequence from the moment MdT until the moment with the parallelism larger than the ExrdLow is obtained for the first time and is recorded as FnT; the sequence constituted according to the respective status data obtained in the period from MdT to FnT is referred to as a far-end observation sequence FPLs.
Further, in step S400, the approach to calculating the overflow level for the near-end observation sequence is: calculating the same high-rise ratio PHOv and the same low-rise ratio PLOv corresponding to each moment according to the same-row low value and the same-row high value respectively, wherein PHOv= (Pbv-Pbv ')/Pbv', PLOv= (Ptv-Ptv ')/Ptv'; wherein Pbv 'and Ptv' represent the same-row low value and the same-row high value, respectively, at the previous time; taking the arithmetic average value of the high expansion ratio at each moment as the high expansion ratio uniformity, taking the arithmetic average value of the same low expansion ratio at each moment as the same low expansion ratio uniformity, if the high expansion ratio at one moment is larger than the high expansion ratio uniformity and the first low expansion ratio is larger than the same low expansion ratio, defining the moment as an overflow tending mark moment, and taking the larger value of the high expansion ratio and the same low expansion ratio at the overflow tending mark moment as the overflow tending mark degree OFN at the moment; taking the difference value of the parallel uniformity between one moment and the previous moment as the step-to-step difference PGp of the moment, calculating the overflow-tending level OFDg,
where α is the cumulative variable, NHds is the total number of overflow-seeking tag moments within the near-end observation sequence, PGp α And OFN α Representing the inter-step difference and the overflow-seeking mark degree at the alpha-th overflow-seeking mark moment in the near-end observation sequence respectively, wherein exp () is a logarithmic function with a natural constant e as a base.
The overflow-seeking level OFDg calculation process only uses data in the near-end observation sequence, and all variables including the same low expansion ratio uniformity, the overflow-seeking level and the like are based on the data in the near-end observation sequence.
Since there is a data screening step in the above approach to overflow level, which results in a problem of too high sensitivity to overflow level, which is particularly pronounced when the proposed blow-up ratio is set low, however the prior art does not solve the problem of gradually increasing or even overfitting the sensitivity, in order to make the problem better and solve, the problem of gradually tending to excessive sensitivity is eliminated, so the present invention proposes a more preferable scheme as follows:
preferably, in step S400, the approach to calculating the overflow level for the near-end observation sequence is: the difference between the same-row high value and the same-row low value at the same moment is recorded as the field transmission difference SiDs at the moment, and the field transmission difference SiDs corresponding to each moment are obtained according to the state data of each moment in the near-end observation sequence; the sequence formed by the field permeability difference SiDs at each moment is marked as DsLst, the maximum value and the median in the DsLst are respectively marked as DsLst.Mx and DsLst.Md, and the moment for obtaining the DsLst.Mx is marked as DLMT_1; defining a low field difference time when the field permeability difference at one time is less than or equal to DsLst.Md, and starting from the DLMT_1 time, searching for the first low field difference time from the front and back respectively, and recording the two low field difference times as a first low field difference time DLLT_1 and a second low field difference time DLLT_2 respectively;
taking the difference value of the parallelism between one moment and the previous moment as the inter-step difference PGp of the moment, and recording the arithmetic average value of the inter-step differences of all the moments as an inter-step difference reference PGp.Bs; if one moment meets PGp not less than PGp.Bs, defining that the moment generates inter-step difference events, and recording the total quantity of the moments of which the inter-step difference events occur in each moment as OvBN; if the field permeability difference SiDs at one moment is larger than or equal to the field permeability difference at the previous moment, defining that a field permeability difference event occurs at the moment, and recording the total amount of the moments when the inter-high-step difference event occurs and the field permeability difference event occurs in each moment as BsDN;
calculating an overflow-seeking level OFDg, ofdg=ln (ffl×sfl); wherein FFL is a first overflow tending feature, and the calculation method comprises the following steps:SFL is the second overflow tending feature, and the calculation method is as follows: sfl=ovbn/BsDN; NOTMS<>The time calculator is used for calculating the number of times between two times, and is positive if the two times are input in accordance with the time sequence, and is negative if the two times are input in accordance with the time sequence, wherein each time participating in the operation in the process of calculating the overflow approaching level is in a time range corresponding to the near-end observation sequence.
The beneficial effects are that: the overflow approaching level is calculated according to the transmittance of each position around the tubular film, so that the transmittance change characteristics of each position around the tubular film can be effectively extracted, the temperature repetition characteristics in each direction and the current air speed of the air cooler in the process of extruding molten materials from the die head are further quantified in numerical value, and the comprehensive analysis of the data climbing section near the history is further used for scientifically adjusting the air cooler for data preparation and reference, so that the risk of deformation or loss of the die head is reduced.
Further, in step S500, the method for calculating the loss level for the far-end observation sequence is: taking the difference value of the parallelism between one moment and the previous moment as the inter-step difference PGp of the moment, marking the arithmetic average value of the inter-step differences at all moments as PGp.Ex, marking the parallelism corresponding to the moment MdT and the moment FnT as PMd and PFn respectively, and calculating to obtain the inter-step permeability base difference GpStd:
GpStd＝(PFn－PMd)÷(NOTms<MdT：FnT>－1)；
wherein NOTms < MdT: fnT > represents the number of times between MdT and FnT when state data is obtained; the maximum value and the minimum value in the inter-step difference at each moment are respectively marked as PGp.Tp and PGp.Bt, and the loss level DCDg is obtained through calculation:
wherein exp () is a logarithmic function with a natural constant e as a base, dcWt is a weight index, dcWt ε [0.4,0.7].
Wherein the calculation of the loss level DCDg uses only data within the far-end observation sequence.
When the loss level is obtained, the situation that all data of the light transmittance foldback process are taken into operation exists, and meanwhile, the problem of timeliness deficiency can be caused because the data segment is relatively far away from the current moment, but the timeliness problem cannot be simply solved in the prior art, and in order to effectively solve the problem and reduce the phenomenon of timeliness deficiency, the invention provides a more preferable scheme as follows:
preferably, in step S500, the method for calculating the loss level for the far-end observation sequence is: taking the difference value of the parallel uniformity between one moment and the previous moment as the inter-step difference PGp of the moment, respectively marking the parallel uniformity corresponding to the moment MdT and the moment FnT as PMd and PFn, and calculating to obtain the inter-step permeability base difference GpStd:
GpStd＝(PFn－PMd)÷(NOTms<MdT：FnT>－1)；
wherein NOTms < MdT: fnT > represents the number of times between MdT and FnT when state data is obtained; the maximum value of the step-to-step differences at each time is designated as PGp.Tp;
defining the moment as a first threshold crossing moment if the step-to-step difference between the moment and the moment before the moment and the moment after the moment is equal to or greater than the step-to-step transmission base difference, and defining the moment as a second threshold crossing moment if the step-to-step difference between the moment and the moment before the moment and the moment after the moment is equal to or less than the step-to-step transmission base difference;
traversing each time in reverse time sequence from MdT time until searching for the first threshold time and designating the time as OsT _1, traversing each time in reverse time sequence from FnT time until searching for the first second threshold time and designating the time as OsT _2, and designating the time period between OsT _1 and OsT _2 as callback reference region;
calculating the depth PDph of a step difference domain at one moment, namely, taking the moment of needing to calculate the depth of the step difference domain as the current step depth moment, taking the minimum value in the same-row low values of the current step depth moment, the previous moment and the next moment as DP_1, and taking the maximum value in the same-row high values of the current step depth moment, the previous moment and the next moment as DP_2, wherein the depth of the step difference domain at the current step depth moment is as follows: pdph=dp_2-dp_1; the loss level DCDg is calculated:
wherein NOTMS<OsT_1,OsT_2>Representing the number of times between OsT _1 and OsT _2 when status data is obtained, PGp β And PDph β Representing the inter-step difference and the step difference domain depth at the beta-th moment in the callback reference region respectively.
And each moment participating in the calculation in the process of obtaining the loss level is in a moment range corresponding to the remote observation sequence.
The beneficial effects are that: the loss level is calculated according to the light transmittance change speed at each moment of the remote observation sequence, so that the adaptation degree between the air speed of the air cooler and the temperature of the extruded material of the die head during the temperature callback or conversion of the die head can be accurately quantified, and the data preparation and the reference are further carried out on the working state of the air cooler for scientific adjustment, so that the risk of deformation or loss of the die head can be effectively reduced, and the application persistence of the working die head is enhanced.
Further, in step S600, the method for implementing the air cooler adjustment according to the approach level and the loss level is: after the multilayer co-extrusion film forming machine operates for at least 1 hour, the difference value between the overflow tending level at the current moment and the minimum value in the overflow tending levels at all moments in the previous hour is recorded as overflow tending difference GainLv; the difference value between the loss level at the current moment and the minimum value in the loss levels at all moments in the previous hour is recorded as a loss difference LoseLv; gainLv 'and LoseLv' are respectively used for representing the overflow tending difference and the loss difference of the moment one hour before the current moment; when GainLv is less than GainLv 'and LoseLv is less than LoseLv', the power of the air cooler is increased by 0.5% -2%, when GainLv is more than GainLv 'and LoseLv is more than LoseLv', the power of the air cooler is reduced by 0.5% -2%, and the power of the current air cooler is maintained under the rest conditions.
Preferably, all undefined variables in the present invention, if not explicitly defined, may be thresholds set manually.
The invention also provides an air cooler control system of the multilayer co-extrusion film forming machine, which comprises: the method comprises the steps of an air cooler control method of the multilayer co-extrusion film forming machine when the processor executes the computer program, wherein an air cooler control system of the multilayer co-extrusion film forming machine can be operated in a computing device such as a desktop computer, a notebook computer, a palm computer and a cloud data center, and the operable system can comprise, but is not limited to, a processor, a memory and a server cluster, and the processor executes the computer program to be operated in the following units of the system:
the data acquisition unit is used for arranging a light transmittance tester, and obtaining an actual measurement value through real-time measurement of the light transmittance tester;
the element group construction unit is used for combining measured values obtained by each light transmittance tester to form state data;
the sequence interception unit is used for forming the state data of each moment into a near-end observation sequence and a far-end observation sequence;
the overflow tending analysis unit is used for calculating overflow tending level for the near-end observation sequence;
a loss analysis unit for calculating a loss level for the far-end observation sequence;
and the fan adjusting unit is used for realizing the air cooler adjustment according to the overflow approaching level and the loss level.
The beneficial effects of the invention are as follows: the invention provides an air cooler control method of a multilayer co-extrusion film forming machine, which is used for effectively extracting the light transmittance change characteristics of all positions around a tubular film, comprehensively analyzing a near-side data ascending section and a far-end callback section to further scientifically adjust the air cooler for data analysis, so that when the temperature of a die head is repeatedly changed or converted by the air cooler at all positions of the tubular film, the adaptation degree between the air speed of the air cooler and the temperature of extrusion materials of the die head is accurately quantized, the risk of deformation or loss of the die head can be effectively reduced, and the application persistence of a working die head is enhanced.
Drawings
The above and other features of the present invention will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present invention, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
FIG. 1 is a flow chart of a method of controlling an air cooler of a multilayer coextrusion film machine;
FIG. 2 is a block diagram of an air cooler control system for a multilayer coextrusion film forming machine.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
Referring to fig. 1, which is a flowchart illustrating a method for controlling an air cooler of a multi-layer co-extrusion film forming machine, a method for controlling an air cooler of a multi-layer co-extrusion film forming machine according to an embodiment of the present invention will be described with reference to fig. 1, and the method includes the steps of:
s100, arranging a light transmittance tester, and measuring in real time through the light transmittance tester to obtain an actual measurement value;
s200, combining measured values obtained by the light transmittance testers to form state data;
s300, the state data at each moment is formed into a near-end observation sequence and a far-end observation sequence;
s400, calculating an overflow tending level for a near-end observation sequence;
s500, calculating a loss level for a far-end observation sequence;
and S600, realizing air cooler adjustment according to the overflow trend and the loss level.
Further, in step S100, a light transmittance tester is arranged, and the method for obtaining the measured value by real-time measurement of the light transmittance tester is as follows: the height of the position, where the film cooling area is connected with the air cooling belt, from the ground is HF, wherein the film cooling area is positioned below the air cooling belt, the air cooling belt is a region where a molten tubular blank is rapidly deformed, the film cooling area is a region of a tubular film formed by a shaped film, and the arrangement height of a light transmittance tester is defined as HS, HS epsilon [ HF-3cm, HF-6cm ]; at least 6-12 light transmittance testers are equidistantly arranged at the position from the ground HS, so that the measurement direction of each light transmittance tester points to the central axis of the tubular film and the distances between each light transmittance tester and the central axis of the tubular film are equal; each light transmittance tester measures the light transmittance of the film in real time as an actual measurement value.
Further, in step S200, the method for composing the status data by combining the measured values obtained by the respective light transmittance testers is: the arithmetic average value, the minimum value and the maximum value of each measured value obtained by measuring each light transmittance tester at the same time are respectively used as a parallel uniformity Pex, a same-row low value Pbv and a same-row high value Ptv; pex, pbv and Ptv are formed into one tuple and are denoted as state data PTup.
Further, in step S300, the method for constructing the state data of each time into the near-end observation sequence and the far-end observation sequence is as follows: the time one minute before the current time is recorded as StT, and a time period is set as a reference length FdLen, fdLen epsilon [0.5,3] hours; the minimum value of the parallelism obtained from StT to the current moment is marked as ExrdLow, the minimum value of the parallelism obtained from StT to FdLen before the moment is marked as CurdLow, the moment obtained by CurdLow is marked as MdT, and a sequence is formed according to the state data obtained in the time period from StT to MdT and is marked as a near-end observation sequence RPLs; traversing the parallelism of all the moments in reverse time sequence from the moment MdT until the moment with the parallelism larger than the ExrdLow is obtained for the first time and is recorded as FnT; the sequence constituted according to the respective status data obtained in the period from MdT to FnT is referred to as a far-end observation sequence FPLs.
Further, in step S400, the approach to calculating the overflow level for the near-end observation sequence is: calculating the same high-rise ratio PHOv and the same low-rise ratio PLOv corresponding to each moment according to the same-row low value and the same-row high value respectively, wherein PHOv= (Pbv-Pbv ')/Pbv', PLOv= (Ptv-Ptv ')/Ptv'; wherein Pbv 'and Ptv' represent the same-row low value and the same-row high value, respectively, at the previous time; taking the arithmetic average value of the high expansion ratio at each moment as the high expansion ratio uniformity, taking the arithmetic average value of the same low expansion ratio at each moment as the same low expansion ratio uniformity, if the high expansion ratio at one moment is larger than the high expansion ratio uniformity and the second low expansion ratio is larger than the same low expansion ratio uniformity, defining the moment as an overflow tending mark moment, and taking the larger value of the high expansion ratio and the same low expansion ratio at the overflow tending mark moment as the overflow tending mark degree OFN at the moment; taking the difference value of the parallel uniformity between one moment and the previous moment as the step-to-step difference PGp of the moment, calculating the overflow-tending level OFDg,
where α is the cumulative variable, NHds is the total number of overflow-seeking tag moments within the near-end observation sequence, PGp α And OFN α Representing the inter-step difference and the overflow-tending marker degree at the alpha-th overflow-tending marker moment, respectively, exp () is a logarithmic function with the natural constant e as a base.
Preferably, in step S400, the approach to calculating the overflow level for the near-end observation sequence is: the difference between the same-row high value and the same-row low value at the same moment is recorded as the field transmission difference SiDs at the moment, and the field transmission difference SiDs corresponding to each moment are obtained according to the state data of each moment in the near-end observation sequence; the sequence formed by the field permeability difference SiDs at each moment is marked as DsLst, the maximum value and the median in the DsLst are respectively marked as DsLst.Mx and DsLst.Md, and the moment for obtaining the DsLst.Mx is marked as DLMT_1; defining a low field difference time when the field permeability difference at one time is less than or equal to DsLst.Md, and starting from the DLMT_1 time, searching for the first low field difference time from the front and back respectively, and recording the two low field difference times as a first low field difference time DLLT_1 and a second low field difference time DLLT_2 respectively;
taking the difference value of the parallelism between one moment and the previous moment as the inter-step difference PGp of the moment, and recording the arithmetic average value of the inter-step differences of all the moments as an inter-step difference reference PGp.Bs; if one moment meets PGp not less than PGp.Bs, defining that the moment generates inter-step difference events, and recording the total quantity of the moments of which the inter-step difference events occur in each moment as OvBN; if the field permeability difference SiDs at one moment is larger than or equal to the field permeability difference at the previous moment, defining that a field permeability difference event occurs at the moment, and recording the total amount of the moments when the inter-high-step difference event occurs and the field permeability difference event occurs in each moment as BsDN;
calculating an overflow-seeking level OFDg, ofdg=ln (ffl×sfl); wherein ln () is a logarithmic function with a natural constant e as a base, FFL is a first overflow-seeking feature, and the calculation method is as follows:SFL is the second overflow tending feature, and the calculation method is as follows: sfl=ovbn/BsDN; wherein, each moment participating in the calculation in the process of calculating the overflow approaching level is in a moment range corresponding to the near-end observation sequence.
Further, in step S500, the method for calculating the loss level for the far-end observation sequence is: taking the difference value of the parallelism between one moment and the previous moment as the inter-step difference PGp of the moment, marking the arithmetic average value of the inter-step differences at all moments as PGp.Ex, marking the parallelism corresponding to the moment MdT and the moment FnT as PMd and PFn respectively, and calculating to obtain the inter-step permeability base difference GpStd:
GpStd＝(PFn－PMd)÷(NOTms<MdT：FnT>－1)；
wherein NOTms < MdT: fnT > represents the number of times between MdT and FnT when state data is obtained; the maximum value and the minimum value in the inter-step difference at each moment are respectively marked as PGp.Tp and PGp.Bt, and the loss level DCDg is obtained through calculation:
wherein exp () is a logarithmic function with a natural constant e as a base, dcWt is a weight index, dcWt ε [0.4,0.7].
Preferably, in step S500, the method for calculating the loss level for the far-end observation sequence is: taking the difference value of the parallel uniformity between one moment and the previous moment as the inter-step difference PGp of the moment, respectively marking the parallel uniformity corresponding to the moment MdT and the moment FnT as PMd and PFn, and calculating to obtain the inter-step permeability base difference GpStd:
GpStd＝(PFn－PMd)÷(NOTms<MdT：FnT>－1)；
wherein NOTms < MdT: fnT > represents the number of times between MdT and FnT when state data is obtained; the maximum value of the step-to-step differences at each time is designated as PGp.Tp;
defining the moment as a first threshold crossing moment if the step-to-step difference between the moment and the moment before the moment and the moment after the moment is equal to or greater than the step-to-step transmission base difference, and defining the moment as a second threshold crossing moment if the step-to-step difference between the moment and the moment before the moment and the moment after the moment is equal to or less than the step-to-step transmission base difference;
traversing each time in reverse time sequence from MdT time until searching for the first threshold time and designating the time as OsT _1, traversing each time in reverse time sequence from FnT time until searching for the first second threshold time and designating the time as OsT _2, and designating the time period between OsT _1 and OsT _2 as callback reference region;
calculating the depth PDph of a step difference domain at one moment, namely, taking the moment of needing to calculate the depth of the step difference domain as the current step depth moment, taking the minimum value in the same-row low values of the current step depth moment, the previous moment and the next moment as DP_1, and taking the maximum value in the same-row high values of the current step depth moment, the previous moment and the next moment as DP_2, wherein the depth of the step difference domain at the current step depth moment is as follows: pdph=dp_2-dp_1; the loss level DCDg is calculated:
wherein NOTMS<OsT_1,OsT_2>Representing the number of times between OsT _1 and OsT _2 when status data is obtained, PGp β And PDph β Representing the inter-step difference and the step difference domain depth at the beta-th moment in the callback reference region respectively.
Further, in step S600, the method for implementing the air cooler adjustment according to the approach level and the loss level is: after the multilayer co-extrusion film forming machine operates for at least 1 hour, the difference value between the overflow tending level at the current moment and the minimum value in the overflow tending levels at all moments in the previous hour is recorded as overflow tending difference GainLv; the difference value between the loss level at the current moment and the minimum value in the loss levels at all moments in the previous hour is recorded as a loss difference LoseLv; gainLv 'and LoseLv' are respectively used for representing the overflow tending difference and the loss difference of the moment one hour before the current moment; when GainLv is less than GainLv 'and LoseLv is less than LoseLv', the power of the air cooler is increased by 0.5% -2%, when GainLv is more than GainLv 'and LoseLv is more than LoseLv', the power of the air cooler is reduced by 0.5% -2%, and the power of the current air cooler is maintained under the rest conditions.
An embodiment of the present invention provides an air cooler control system of a multi-layer co-extrusion film forming machine, as shown in fig. 2, which is a structural diagram of the air cooler control system of the multi-layer co-extrusion film forming machine, where the air cooler control system of the multi-layer co-extrusion film forming machine includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of one embodiment of an air cooler control system for a multilayer co-extrusion film machine described above when the computer program is executed.
The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of the following system:
the data acquisition unit is used for arranging a light transmittance tester, and obtaining an actual measurement value through real-time measurement of the light transmittance tester;
the element group construction unit is used for combining measured values obtained by each light transmittance tester to form state data;
the sequence interception unit is used for forming the state data of each moment into a near-end observation sequence and a far-end observation sequence;
the overflow tending analysis unit is used for calculating overflow tending level for the near-end observation sequence;
a loss analysis unit for calculating a loss level for the far-end observation sequence;
and the fan adjusting unit is used for realizing the air cooler adjustment according to the overflow approaching level and the loss level.
The air cooler control system of the multilayer coextrusion film forming machine can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The air cooler control system of the multi-layer co-extrusion film forming machine can comprise an operational system including, but not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the examples are merely examples of an air cooler control system for a multi-layer co-extrusion film machine and are not limiting of an air cooler control system for a multi-layer co-extrusion film machine, and may include more or fewer components than examples, or may combine certain components, or different components, such as an air cooler control system for a multi-layer co-extrusion film machine may also include input and output devices, network access devices, buses, and the like.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (DigiDCDg Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of an air cooler control system operation system of the multi-layer co-extrusion film forming machine, and various interfaces and lines are used to connect various parts of the air cooler control system operation system of the whole multi-layer co-extrusion film forming machine.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the air cooler control system of the multilayer coextrusion film machine by running or executing the computer program and/or module stored in the memory, and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid state storage device.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.
Claims (8)
1. An air cooler control method of a multilayer co-extrusion film forming machine is characterized by comprising the following steps of:
s100, arranging a light transmittance tester, and measuring in real time through the light transmittance tester to obtain an actual measurement value;
s200, combining measured values obtained by the light transmittance testers to form state data;
s300, the state data at each moment is formed into a near-end observation sequence and a far-end observation sequence;
s400, calculating an overflow tending level for a near-end observation sequence;
s500, calculating a loss level for a far-end observation sequence;
and S600, realizing air cooler adjustment according to the overflow trend and the loss level.
2. The method according to claim 1, wherein in step S100, a light transmittance tester is arranged, and the actually measured value is obtained by real-time measurement by the light transmittance tester: the height of the position, which is connected with the air cooling zone, of the film cooling zone from the ground is HF, wherein the film cooling zone is positioned below the air cooling zone, the air cooling zone is a zone in which a molten tubular blank rapidly deforms after being extruded from a die head, the film cooling zone is a zone of a tubular film formed by a shaped film, the height of the position, which is arranged by defining a light transmittance tester, from the ground is HS, HS epsilon [ HF-3cm, HF-6cm ]; at least 6-12 light transmittance testers are equidistantly arranged at the position from the ground HS, so that the measurement direction of each light transmittance tester points to the central axis of the tubular film and the distances between each light transmittance tester and the central axis of the tubular film are equal; each light transmittance tester measures the light transmittance of the film in real time as an actual measurement value.
3. The method according to claim 1, wherein in step S200, the method for composing the status data by combining the measured values obtained by the respective light transmittance testers is: the arithmetic average value, the minimum value and the maximum value of each measured value obtained by measuring each light transmittance tester at the same time are respectively used as a parallel uniformity Pex, a same-row low value Pbv and a same-row high value Ptv; pex, pbv and Ptv are formed into one tuple and are denoted as state data PTup.
4. The method according to claim 1, wherein in step S300, the method for forming the state data of each time into the near-end observation sequence and the far-end observation sequence is: the time one minute before the current time is recorded as StT, and a time period is set as a reference length FdLen, fdLen epsilon [0.5,3] hours; the minimum value of the parallelism obtained from StT to the current moment is marked as ExrdLow, the minimum value of the parallelism obtained from StT to FdLen before the moment is marked as CurdLow, the moment obtained by CurdLow is marked as MdT, and the state data obtained in the time period from StT to MdT are orderly formed into a sequence and are marked as a near-end observation sequence RPLs; traversing the parallelism of all the moments in reverse time sequence from the moment MdT until the moment with the parallelism larger than the ExrdLow is obtained for the first time and is recorded as FnT; the sequence of the respective state data obtained in the period MdT to FnT in order is referred to as a far-end observation sequence FPLs.
5. The method according to claim 1, wherein in step S400, the method for calculating the overflow tending level for the near-end observation sequence is: calculating the same high-rise ratio PHOv and the same low-rise ratio PLOv corresponding to each moment according to the same-row low value and the same-row high value respectively, wherein PHOv= (Pbv-Pbv ')/Pbv', PLOv= (Ptv-Ptv ')/Ptv'; wherein Pbv 'and Ptv' represent the same-row low value and the same-row high value, respectively, at the previous time; taking the arithmetic average value of the high expansion ratio at each moment as the high expansion ratio uniformity, taking the arithmetic average value of the same low expansion ratio at each moment as the same low expansion ratio uniformity, if the high expansion ratio at one moment is larger than the high expansion ratio uniformity and the same low expansion ratio is larger than the same low expansion ratio uniformity, defining the moment as an overflow tending mark moment, and taking the larger value of the high expansion ratio and the same low expansion ratio at the overflow tending mark moment as the overflow tending mark degree OFN at the moment; taking the difference value of the parallel uniformity between one moment and the previous moment as the step-to-step difference PGp of the moment, calculating the overflow-tending level OFDg,
where α is the accumulation variable, NHds is the total number of overflow-seeking mark times, PGp α And OFN α Representing the inter-step difference and the overflow-seeking mark degree at the alpha-seeking mark moment respectively.
6. The method according to claim 1, wherein in step S500, the method for calculating the loss level for the remote observation sequence is: taking the difference value of the parallelism between one moment and the previous moment as the inter-step difference PGp of the moment, marking the arithmetic average value of the inter-step differences at all moments as PGp.Ex, marking the parallelism corresponding to the moment MdT and the moment FnT as PMd and PFn respectively, and calculating to obtain the inter-step permeability base difference GpStd:
GpStd＝(PFn－PMd)÷(NOTms<MdT：FnT>－1)；
wherein NOTms < MdT: fnT > represents the number of times between MdT and FnT when the state data is acquired; the maximum value and the minimum value in the inter-step difference at each moment are respectively marked as PGp.Tp and PGp.Bt, and the loss level DCDg is obtained through calculation:
wherein DcWt is a weight index, dcWt is [0.4,0.7].
7. The method according to claim 1, wherein in step S600, the method for achieving air cooler adjustment according to the approach level and the loss level is: after the multilayer co-extrusion film forming machine continuously runs for at least 1 hour, the difference value of the minimum value in the overflow trend level at the current moment and the overflow trend level at each moment in the first half hour is recorded as overflow trend difference GainLv; the difference between the current loss level and the minimum value in the loss levels at all times in the first half hour is recorded as a loss difference LoseLv; gainLv 'and LoseLv' are respectively used for representing the overflow tending difference and the loss difference of the moment one hour before the current moment; when GainLv is less than GainLv 'and LoseLv is less than LoseLv', the power of the air cooler is increased by 0.5% -2%; when GainLv is larger than GainLv 'and LoseLv is larger than LoseLv', the power of the air cooler is reduced by 0.5% -2%; the rest of the conditions maintain the power of the current air cooler.
8. An air cooler control system of a multilayer co-extrusion film forming machine, characterized in that the air cooler control system of the multilayer co-extrusion film forming machine comprises: a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the air cooler control method of a multilayer co-extrusion film machine according to any one of claims 1 to 7 when the computer program is executed, and the air cooler control system of the multilayer co-extrusion film machine is operated in a computing device of a desktop computer, a notebook computer, a palm computer and a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310663096.9A CN116533419B (en) | 2023-06-06 | 2023-06-06 | Air cooler control method of multilayer co-extrusion film forming machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310663096.9A CN116533419B (en) | 2023-06-06 | 2023-06-06 | Air cooler control method of multilayer co-extrusion film forming machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116533419A true CN116533419A (en) | 2023-08-04 |
| CN116533419B CN116533419B (en) | 2023-10-20 |
Family
ID=87443599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310663096.9A Active CN116533419B (en) | 2023-06-06 | 2023-06-06 | Air cooler control method of multilayer co-extrusion film forming machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116533419B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR1427792A (en) * | 1964-12-10 | 1966-02-11 | Ethylene Plastique Sa | Improvements to the extrusion process of films or sheaths of thermoplastic materials |
| JP2004181863A (en) * | 2002-12-05 | 2004-07-02 | Toyobo Co Ltd | Heat shrinkable polyester type film roll and its manufacturing process |
| JP2010008331A (en) * | 2008-06-30 | 2010-01-14 | Kobe Steel Ltd | Photothermal conversion measuring instrument and its method |
| US20110194113A1 (en) * | 2009-02-27 | 2011-08-11 | Mitsubishi Heavy Industries, Ltd. | Thin-film inspection apparatus and inspection method |
| JP2012047732A (en) * | 2010-07-30 | 2012-03-08 | Hoya Corp | Transmittance measuring instrument, photomask transmittance inspection device, transmittance inspection method, photomask manufacturing method, pattern transfer method, and photomask product |
| TW201832902A (en) * | 2016-09-05 | 2018-09-16 | 日商理研科技股份有限公司 | Method for producing multilayer film |
| CN110077067A (en) * | 2019-03-12 | 2019-08-02 | 常州斯威克光伏新材料有限公司 | Anti- polarization type EVA compound cutan of double-layer coextrusion and preparation method thereof |
| CN115855886A (en) * | 2022-11-25 | 2023-03-28 | 广东汇发塑业科技有限公司 | Uniformity detection method for multilayer co-extrusion film making |
-
2023
- 2023-06-06 CN CN202310663096.9A patent/CN116533419B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR1427792A (en) * | 1964-12-10 | 1966-02-11 | Ethylene Plastique Sa | Improvements to the extrusion process of films or sheaths of thermoplastic materials |
| JP2004181863A (en) * | 2002-12-05 | 2004-07-02 | Toyobo Co Ltd | Heat shrinkable polyester type film roll and its manufacturing process |
| JP2010008331A (en) * | 2008-06-30 | 2010-01-14 | Kobe Steel Ltd | Photothermal conversion measuring instrument and its method |
| US20110194113A1 (en) * | 2009-02-27 | 2011-08-11 | Mitsubishi Heavy Industries, Ltd. | Thin-film inspection apparatus and inspection method |
| JP2012047732A (en) * | 2010-07-30 | 2012-03-08 | Hoya Corp | Transmittance measuring instrument, photomask transmittance inspection device, transmittance inspection method, photomask manufacturing method, pattern transfer method, and photomask product |
| TW201832902A (en) * | 2016-09-05 | 2018-09-16 | 日商理研科技股份有限公司 | Method for producing multilayer film |
| CN110077067A (en) * | 2019-03-12 | 2019-08-02 | 常州斯威克光伏新材料有限公司 | Anti- polarization type EVA compound cutan of double-layer coextrusion and preparation method thereof |
| CN115855886A (en) * | 2022-11-25 | 2023-03-28 | 广东汇发塑业科技有限公司 | Uniformity detection method for multilayer co-extrusion film making |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116533419B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107247989A (en) | A kind of neural network training method and device | |
| CN116011894B (en) | Aluminum alloy rod production data management system | |
| CN107067164A (en) | A kind of index Method of fast estimating and system | |
| CN116533419B (en) | Air cooler control method of multilayer co-extrusion film forming machine | |
| CN112817755A (en) | Edge cloud cooperative deep learning target detection method based on target tracking acceleration | |
| CN109147324B (en) | Traffic jam probability forecasting method based on user feedback mechanism | |
| CN115855886B (en) | Uniformity detection method for multilayer co-extrusion film | |
| CN106651966A (en) | Picture color identification method and system | |
| Idri et al. | Evaluating software project similarity by using linguistic quantifier guided aggregations | |
| CN116811085B (en) | Real-time evaluation method for running state of multilayer coextrusion film blowing machine | |
| CN117332620B (en) | Corrosion-resistant material optimization method and system based on atmospheric corrosion data | |
| CN114357644A (en) | Health degree evaluation method based on air separation equipment | |
| CN116612389B (en) | Building construction progress management method and system | |
| CN109034372A (en) | A kind of neural networks pruning method based on probability | |
| RU2701841C1 (en) | Defuzzification device based on area ratio method | |
| CN108922191B (en) | Travel time calculation method based on soft set | |
| Azman et al. | Ranking fuzzy numbers by centroid method | |
| CN107274036A (en) | A kind of determination method and system of optimal trend yield model | |
| Chistyakova et al. | Data mining system for predicting quality of polymeric films | |
| CN106291497A (en) | Solution velocity ambiguity algorithm based on quick look-up table | |
| CN106802792B (en) | Interactive interface operation request queue processing method based on BP neural network | |
| Attarzadeh et al. | Soft computing approach for software cost estimation | |
| KR970006030B1 (en) | Local linear regression model structure | |
| CN116757025B (en) | Automatic ship cabin pattern pickup method based on DXF format | |
| CN110569816A (en) | Traffic sign classification algorithm based on new activation function |
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 |