CN117212182A - Low-pulse pulp pump for papermaking pulp and detection method - Google Patents
Low-pulse pulp pump for papermaking pulp and detection method Download PDFInfo
- Publication number
- CN117212182A CN117212182A CN202311471464.6A CN202311471464A CN117212182A CN 117212182 A CN117212182 A CN 117212182A CN 202311471464 A CN202311471464 A CN 202311471464A CN 117212182 A CN117212182 A CN 117212182A
- Authority
- CN
- China
- Prior art keywords
- pulp
- assembly
- paper pulp
- impeller
- cutting
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 229920001131 Pulp (paper) Polymers 0.000 claims description 124
- 239000000835 fiber Substances 0.000 claims description 110
- 238000005520 cutting process Methods 0.000 claims description 65
- 238000012549 training Methods 0.000 claims description 34
- 230000002159 abnormal effect Effects 0.000 claims description 32
- 238000010801 machine learning Methods 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 239000000126 substance Substances 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 239000012528 membrane Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 239000012780 transparent material Substances 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000004904 shortening Methods 0.000 claims description 2
- 238000004537 pulping Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 229920002522 Wood fibre Polymers 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 2
- 239000002253 acid Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000032258 transport Effects 0.000 description 2
- 239000002025 wood fiber Substances 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 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
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011978 dissolution method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229920002313 fluoropolymer Polymers 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 239000011241 protective layer Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/50—Reuse, recycling or recovery technologies
- Y02W30/64—Paper recycling
Landscapes
- Paper (AREA)
Abstract
The application discloses a low-pulse pulp pump for papermaking pulp and a detection method, which belong to the technical field of pulping, and comprise a pulp pump main body, wherein an impeller assembly is arranged in the pulp pump main body, the impeller assembly comprises an impeller chassis and impeller blades, one side of the impeller chassis is provided with a plurality of through holes, the impeller blades are fixedly connected between every two through holes, and the other side of the impeller chassis is fixedly connected with a containing assembly.
Description
Technical Field
The application belongs to the technical field of pulping, and particularly relates to a low-pulse pulp pump for papermaking pulp and a detection method.
Background
The pulp pump is a device for conveying pulp, and is generally used in pulp making and paper making industry, the main function of the pulp pump is to transfer pulp from one position to another position so as to meet the conveying requirement of the pulp, the pulp enters an inlet of the pulp pump, is pushed by rotation of an impeller and is discharged through an outlet of the pulp pump, and in the process of conveying the pulp by the pulp pump, the pulp impacts and collides with the surface of the impeller, so that the service life of the impeller is reduced, and in the prior art, a protective structure is generally arranged on the surface of the impeller so as to improve the service life of the impeller.
For example, the application document with application publication number CN106122035a discloses a papermaking process pump with a structure for reducing pump wear, the papermaking process pump comprises a pump body, an impeller and a wear-resistant lining plate, an elastic layer is further arranged between the wear-resistant lining plate and the impeller, the wear-resistant lining plate is used for bearing the impact of paper pulp instead of the impeller, and a certain buffer effect is realized through the elastic layer, so that the wear degree of the impeller is reduced, but the following defects are present:
the above patent has no essential difference from the arrangement of the wear-resistant lining plate on the impeller and the coating of the protective layer on the surface of the impeller, namely, the impact of paper pulp is born by replacing the impeller by other materials, the impact of the paper pulp is not weakened fundamentally, the paper pulp is divided into mechanical paper pulp and chemical paper pulp, the principle of damage to the impeller caused by the mechanical paper pulp and the chemical paper pulp is different, and the arrangement of the wear-resistant lining plate cannot achieve targeted protection.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
In order to solve the problems, the application adopts the following technical scheme.
The low-pulse pulp pump for papermaking pulp comprises a pulp pump main body, wherein an impeller assembly is arranged in the pulp pump main body and comprises an impeller chassis and impeller blades, one side of the impeller chassis is provided with a plurality of through holes, the impeller blades are fixedly connected between every two through holes, and the other side of the impeller chassis is fixedly connected with a containing assembly;
the fiber diameter detection module is arranged on the surface of the pulp pump body and is used for acquiring the diameter of fibers in the pulp;
the numerical value detection module is arranged on the inner wall of the pulp pump main body and is used for acquiring a pulp temperature value and a pulp pH value;
the classification module inputs the fiber diameter, the pulp temperature value and the pulp pH value into the pulp discrimination model to obtain pulp types;
a central processing unit for determining whether to generate an adjustment instruction based on the pulp type;
the telescopic component is arranged on one side of the accommodating component, stretches and contracts according to the adjusting instruction, and the cutting component is arranged at one end of the telescopic component and cuts off the fiber according to the adjusting instruction.
Preferably, the inside of pulp pump main part has seted up the working chamber, and the pulp entry communicating with the outside has been seted up to one side of working chamber, and the pulp export has been seted up on the top of working chamber, and the detection hole has been seted up on the top of pulp entry, and the top of detection hole is provided with fiber diameter detection module, and the inner wall fixedly connected with water proof membrane of detection hole, the inner wall of pulp entry is provided with numerical value detection module.
Preferably, the waterproof membrane is made of transparent material, and the numerical detection module is a temperature PH sensor.
Preferably, the accommodating component comprises an accommodating disc and supporting columns, the accommodating disc is fixedly connected with the other side of the impeller chassis through a plurality of supporting columns, a telescopic component is arranged between every two supporting columns, one end of the telescopic component is provided with a cutting component, and the position of the cutting component corresponds to the position of the through hole.
Preferably, the extension of the telescopic component drives the cutting component to penetrate through the through hole and enter the area formed between the two impeller blades, and the resetting of the telescopic component drives the cutting component to penetrate through the through hole and exit the area formed by the two impeller blades.
A detection method of papermaking pulp is realized by using the low-pulse pulp pump, and comprises the following steps:
acquiring real-time characteristic data of paper pulp, wherein the real-time characteristic data comprise fiber diameter, paper pulp temperature value and paper pulp pH value;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain the paper pulp category;
based on the pulp category, judging whether to generate an adjustment instruction, wherein the adjustment instruction comprises a first adjustment instruction and a second adjustment instruction;
the expansion assembly expands based on the first adjustment instruction, the cutting assembly cuts the fiber based on the first adjustment instruction, the expansion assembly shortens based on the second adjustment instruction, and the cutting assembly stops cutting the fiber based on the second adjustment instruction.
Preferably, the pulp category includes mechanical pulp and chemical pulp, the central processor generating a first adjustment instruction when the pulp is mechanical pulp and generating a second adjustment instruction when the pulp is chemical pulp.
Preferably, the training mode of the pulp discrimination model is as follows:
obtaining a plurality of groups of paper pulp in an experimental environment, detecting each group of paper pulp to obtain each group of paper pulp characteristic data, generating a corresponding actual mark according to the collected paper pulp types, wherein the actual mark is 1 when the paper pulp types are mechanical paper pulp, and the actual mark is 0 when the paper pulp types are chemical paper pulp; each set of pulp characteristic data is taken as input of a first machine learning model which is marked as output by prediction of each set of pulp characteristic data and is marked as prediction target in practiceTarget, take the sum of the prediction accuracy of the minimum pulp characteristic data as training target; the calculation formula of the prediction accuracy is as follows:wherein->Numbering pulp characteristic data>For prediction accuracy, < >>Is->Predictive label value corresponding to group pulp characteristic data, < + >>Is->Grouping actual labeling values corresponding to pulp characteristic data; and training the first machine learning model until the sum of the prediction accuracy reaches convergence, stopping training, taking the first machine learning model obtained by training as a pulp discrimination model, wherein the first machine learning model is one of a naive Bayesian model and a support vector machine model.
Preferably, the central processor obtains a prediction label corresponding to the pulp category, generates the first adjustment instruction when the prediction label is equal to 1, and generates the second adjustment instruction when the prediction label is equal to 0.
Preferably, step one, acquiring real-time characteristic data of pulp and the abnormal ratio of fiber diameter;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain a paper pulp class, switching to the third step if the paper pulp class is mechanical paper pulp, and switching to the fourth step if the paper pulp class is chemical paper pulp;
step three, inputting the abnormal fiber diameter ratio into a power regulation model to obtain a power index, and turning to step five;
step four, generating a second adjusting instruction when the pulp type is chemical pulp, shortening the telescopic component based on the second adjusting instruction, and stopping cutting the fiber by the cutting component based on the second adjusting instruction;
and fifthly, generating a first adjustment instruction when the pulp type is mechanical pulp, stretching the telescopic component based on the first adjustment instruction, cutting the fiber by the cutting component based on the first adjustment instruction and the power index, and taking the power index as the output power of the cutting component.
Preferably, the training mode of the power adjustment model is as follows:
collecting training data, wherein the training data comprise fiber diameter abnormal duty ratio and power index, the fiber diameter abnormal duty ratio and the power index are used as sample sets, the sample sets are divided into training sets and test sets, a second machine learning model is built, the fiber diameter abnormal duty ratio in the training sets is used as input data, the power index in the training sets is used as output data, the second machine learning model is trained, an initial second machine learning model is obtained, the second machine learning model is tested by using the test sets, the second machine learning model meeting the preset accuracy is output as a power adjustment model, and the second machine learning model is a neural network model.
Preferably, the abnormal fiber diameter ratio is the ratio of the number of fibers with abnormal diameters to the total number of fibers, the total number of fibers is the total number of fibers obtained by one measurement, the number of fibers with abnormal diameters is the total number of fibers with abnormal diameter marks, and the power index is the output power level of the cutting assembly.
Compared with the prior art, the application has the beneficial effects that:
(1) According to the application, the fed paper pulp is subjected to real-time detection to obtain real-time characteristic data, the types of the paper pulp are obtained through the real-time characteristic data, the paper pulp is divided into mechanical paper pulp and chemical paper pulp, and as the principle that the mechanical paper pulp and the chemical paper pulp damage the impeller is different, different adjustment instructions can be generated through the types of the paper pulp, the telescopic component stretches or shortens according to the different adjustment instructions, and meanwhile, the cutting component starts to cut or stops cutting fibers in the paper pulp according to the different adjustment instructions, so that the impeller component can be protected in a targeted manner, and the service life of the impeller component can be prolonged;
(2) According to the application, the impeller assembly is protected, meanwhile, the problem of blockage of the pulp pump is considered, then the fiber diameter is required to be compared and analyzed with the preset diameter threshold before the imported paper pulp is classified, if the fiber diameter is larger than or equal to the preset diameter threshold, the fiber diameter in the imported paper pulp is too large, the blockage of the pulp pump is easy to be caused, then the paper pulp is not required to be classified, the central processing unit directly sends a first adjustment instruction to the telescopic assembly and the cutting assembly, the fibers in the paper pulp are cut up, the probability of the blockage of the pulp pump is reduced, and if the fiber diameter is smaller than the preset diameter threshold, the fiber diameter in the imported paper pulp is required to be further classified.
Drawings
FIG. 1 is a schematic view of the internal structure of a pulp pump;
FIG. 2 is a side view of the impeller assembly and the containment assembly;
FIG. 3 is a schematic view of the impeller assembly and the containment assembly when separated;
FIG. 4 is a front view of the impeller assembly;
FIG. 5 is a schematic view of the structure of the severing assembly within the impeller assembly;
FIG. 6 is an enlarged schematic view of the structure shown at A in FIG. 1;
FIG. 7 is an enlarged schematic view of the structure at B in FIG. 1;
FIG. 8 is a schematic view of the structure of the severing assembly;
FIG. 9 is a schematic view of a pulp pump body with an electrical control box;
FIG. 10 is a schematic view of the internal structure of the electronic control box;
fig. 11 is a flow chart of a method of detecting papermaking pulp.
The correspondence between the reference numerals and the component names in the drawings is as follows:
10. a pulp pump body; 11. a pulp inlet; 12. a pulp outlet; 13. a waterproof membrane; 14. an electric control box; 15. a central processing unit; 16. a classification module; 20. a numerical value detection module; 30. an impeller assembly; 31. an impeller chassis; 32. impeller blades; 33. a through hole; 40. a housing assembly; 41. a storage tray; 42. a support column; 50. a telescoping assembly; 60. cutting off the assembly; 70. and a fiber diameter detection module.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
The embodiment provides a detection method of papermaking pulp, which is applied to a low-pulse pulp pump, and comprises the following steps:
s10: acquiring real-time characteristic data of paper pulp;
it should be noted that, the real-time characteristic data of the pulp include a fiber diameter, a pulp temperature value and a pulp PH value, the fiber diameter is obtained by the fiber diameter detection module 70, and the pulp temperature value and the pulp PH value are obtained by the numerical detection module 20;
specifically, as shown in fig. 1, 6 and 7, the low pulse pulp pump for papermaking pulp comprises a pulp pump main body 10, a working cavity is formed in the pulp pump main body 10, a pulp inlet 11 communicated with the outside is formed in one side of the working cavity, a pulp outlet 12 is formed in the top end of the working cavity, a detection hole is formed in the top end of the pulp inlet 11, a fiber diameter detection module 70 is arranged at the top end of the detection hole, a waterproof membrane 13 is fixedly connected to the inner wall of the detection hole, the fiber diameter detection module 70 can obtain the diameter of fibers in the pulp through the detection hole, a numerical detection module 20 is arranged on the inner wall of the pulp inlet 11, and the numerical detection module 20 is used for obtaining the temperature value and the pH value of the pulp;
it will be appreciated that the fiber diameter detection module 70 may be an ultrasonic sensor, the fiber diameter detection module 70 may also be composed of an optical profiler and a pulp analyzer, the optical profiler obtains a cross-sectional image perpendicular to the pulp inlet 11, and the pulp analyzer analyzes the cross-sectional image to obtain the diameter of the fiber in the pulp, it will be appreciated that a plurality of fiber diameter data can be obtained at one time, and the average value of the plurality of fiber diameter data is obtained finally, while the waterproof membrane 13 is also made of a transparent material, such as fluorocarbon polymer, which has both water repellency and transparency, the numerical detection module 20 may be a temperature PH sensor, which can detect the temperature and PH value of the pulp, and the embodiment will not be repeated.
S20: inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain the paper pulp category;
it should be noted that, as shown in fig. 9 and 10, the classification module 16 classifies the fed pulp according to the real-time characteristic data of the pulp, the pulp category includes mechanical pulp and chemical pulp, the mechanical pulp is obtained by separating wood fibers by a mechanical processing method, the mechanical pulp generally has larger diameter fibers and lower fiber structure damage, the fibers in the mechanical pulp easily impact and rub the surface of the impeller assembly 30 of the pulp pump when the pulp pump transports the mechanical pulp, so that the surface abrasion of the impeller assembly 30 is serious, the chemical pulp is obtained by separating wood fibers by using a chemical dissolution method, the chemical pulp generally has smaller diameter fibers, but more gas exists inside, the gas impacts and forms vortex on the surface of the impeller assembly 30 when the pulp pump transports the chemical pulp, so that the cavitation phenomenon on the surface of the impeller assembly 30 is serious, preferably, one side of the pulp pump body 10 is fixedly connected with the electronic control box 14, the central processor 15 and the classification module 16 are arranged inside the electronic control box 14, so that the data transmission between the central processor 15 and the classification module 16 is convenient;
the chemical pulp preparation process generally uses alkaline or acid solution to carry out fiber decomposition and remove unwanted substances, so the chemical pulp is alkaline or acid, the mechanical pulp preparation process does not involve a large amount of chemicals, and therefore, the pH value of the chemical pulp preparation process is generally close to neutral, meanwhile, the chemical pulp preparation process is generally carried out in a high-temperature environment, and the mechanical pulp is generally carried out in a normal-temperature environment, so that the temperature value of the mechanical pulp is lower than that of the chemical pulp;
the training mode of the pulp discrimination model is as follows:
generating a corresponding actual label according to the collected pulp type of each group of pulp characteristic data, wherein the actual label is 1 when the pulp type is mechanical pulp, and is 0 when the pulp type is chemical pulp; taking each group of pulp characteristic data as input of a first machine learning model, wherein the first machine learning model takes prediction labeling of each group of pulp characteristic data as output, takes actual labeling as a prediction target, and takes the sum of prediction accuracy of all pulp characteristic data as a training target; the calculation formula of the prediction accuracy is as follows:wherein->Numbering pulp characteristic data>For prediction accuracy, < >>Is->Predictive label value corresponding to group pulp characteristic data, < + >>Is->Grouping actual labeling values corresponding to pulp characteristic data; and training the first machine learning model until the sum of the prediction accuracy reaches convergence, stopping training and taking the first machine learning model obtained by training as a pulp discrimination model, wherein the first machine learning model can be preferably one of a naive Bayesian model and a support vector machine model.
S30: based on the pulp category, judging whether to generate an adjustment instruction, wherein the adjustment instruction comprises a first adjustment instruction and a second adjustment instruction;
the central processing unit 15 obtains a prediction mark corresponding to the pulp category, and when the prediction mark is equal to 1, the pulp category is equivalent to mechanical pulp, a first adjustment instruction is generated, and when the prediction mark is equal to 0, the pulp category is equivalent to chemical pulp, a second adjustment instruction is generated;
it should be noted that, instead of generating an adjustment command at each moment, the central processing unit 15 needs to determine whether to generate an adjustment command, and only when the pulp type introduced into the pulp pump changes, for example, the adjustment command is generated only when the pulp type introduced into the pulp pump changes, for example, when the pulp pump starts to operate, the central processing unit 15 generates a first adjustment command, the telescopic assembly 50 stretches according to the first adjustment command, and drives the cutting assembly 60 to move into the impeller assembly 30, the cutting assembly 60 cuts off fibers in the mechanical pulp according to the first adjustment command, the pulp pump directly cuts off fibers in the mechanical pulp, the central processing unit 15 obtains a prediction flag corresponding to the pulp type, at this time, the central processing unit 15 does not generate a command until the pulp type introduced into the pulp pump is chemical pulp, the central processing unit 15 obtains a prediction flag corresponding to the pulp type and becomes 0, the central processing unit 15 generates a second adjustment command, the telescopic assembly 50 shortens according to the second adjustment command, and drives the cutting assembly 60 to move out from the impeller assembly 30, and simultaneously drives the cutting assembly 60 to stop cutting off fibers according to the second adjustment command, so that the pulp type is cut off fibers in the mechanical pulp pump does not change to the pulp type, and the pulp type is not generated by the central processing unit 15, and the adjustment command is changed to the pulp type is not generated.
S40: the telescoping assembly 50 stretches based on the first adjustment command and the severing assembly 60 cuts the fibers based on the first adjustment command;
specifically, as shown in fig. 2, fig. 3, fig. 4 and fig. 5, one side of the impeller assembly 30 is fixedly connected with the accommodating assembly 40, the impeller assembly 30 comprises an impeller chassis 31 and impeller blades 32, one side of the impeller chassis 31 is provided with a plurality of through holes 33, the impeller blades 32 are fixedly connected between every two through holes 33, the accommodating assembly 40 comprises a containing disc 41 and a supporting column 42, the containing disc 41 is fixedly connected with the other side of the impeller chassis 31 through the plurality of supporting columns 42, a telescopic assembly 50 is arranged between every two supporting columns 42, one end of the telescopic assembly 50 is provided with a cutting assembly 60, the position of the cutting assembly 60 corresponds to the position of the through holes 33, after the telescopic assembly 50 receives a first adjusting instruction, the telescopic assembly 50 starts to stretch and drives the cutting assembly 60 to move towards the position of the through holes 33, meanwhile, the cutting assembly 60 receives the first adjusting instruction to start rotating, and the surface of the cutting assembly 60 is provided with blades for cutting fibers;
it will be appreciated that, as shown in fig. 8, the telescopic assembly 50 in this embodiment is preferably a waterproof micro telescopic arm, a micro power source is disposed inside the waterproof micro telescopic arm and does not need to be powered on with the outside, the micro power source may be a lithium polymer battery, the cutting assembly 60 includes a micro motor, the micro motor drives the blade to rotate according to the first adjustment command to cut the fiber in the mechanical pulp, the micro power source may also supply power to the micro motor, although the impeller assembly 30 rotates in the same way, the accommodating assembly 40 is fixedly connected with the impeller assembly 30, which means that the accommodating assembly 40 and the impeller assembly 30 are relatively stationary, so that the telescopic assembly 50 can drive the cutting assembly 60 to enter the space formed by the two impeller blades 32 through the through hole 33.
S50: the telescoping assembly 50 shortens based on the second adjustment command and the severing assembly 60 stops severing the fiber based on the second adjustment command;
specifically, when chemical pulp is introduced into the pulp pump, after the telescopic component 50 receives the second adjustment command, the telescopic component 50 starts to shorten and drives the cutting component 60 to move towards the position of the accommodating disc 41, meanwhile, the cutting component 60 receives the second adjustment command to stop rotating, as the telescopic component 50 shortens, the cutting component 60 passes through the through hole 33 and exits from the space formed by the two impeller blades 32, the telescopic component 50 always shortens and brings the cutting component 60 back to the initial position, the initial position is the space formed by the accommodating disc 41 and the impeller chassis 31, so that the chemical pulp causes serious cavitation phenomenon on the surface of the impeller component 30, because the gas impacts the surface of the impeller component 30 and forms vortex when the pulp pump conveys the chemical pulp, the area for generating vortex is the space formed by the two impeller blades 32, the through hole 33 is formed on the impeller chassis 31, the flow and the pressure distribution of the gas in the interior of the impeller component 30 are controlled by the through hole 33, the aggregation of the gas in the space formed by the two impeller blades 32 can be reduced, and thus the impact of the gas on the surface of the impeller blades 32 can be reduced, and the cavitation damage on the surface of the impeller component 30 can be alleviated;
it will be appreciated that the purpose of this embodiment is to purposefully protect the impeller assembly 30 according to the type of pulp, and if the pulp is not classified, the cutting assembly 60 will affect the flow of gas in the space formed by the two impeller blades 32 and will accelerate the formation of vortex during rotation of the cutting assembly 60 when the pulp is chemical.
Example 2
Referring to fig. 11, this embodiment is further modified from embodiment 1;
step one, acquiring real-time characteristic data of paper pulp;
step two, comparing and analyzing the fiber diameter with a preset diameter threshold, if the fiber diameter is larger than or equal to the preset diameter threshold, turning to step five, and if the fiber diameter is smaller than the preset diameter threshold, turning to step three;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain the paper pulp category;
step four, judging whether to generate an adjustment instruction based on the pulp category, wherein the adjustment instruction comprises a first adjustment instruction and a second adjustment instruction;
step five, the stretching assembly 50 stretches based on the first adjustment instruction, and the cutting assembly 60 cuts the fiber based on the first adjustment instruction;
step six, the telescopic assembly 50 shortens based on the second adjustment instruction, and the cutting assembly 60 stops cutting the fiber based on the second adjustment instruction;
it should be noted that, in the embodiment, the first step, the third step, the fourth step, the fifth step and the sixth step are the same as those in the embodiment 1, but in the embodiment 1, the step two is set on the basis of the embodiment 1, and the impeller assembly 30 is purposefully protected by classifying the pulp, so that the abrasion or cavitation suffered by the impeller assembly 30 in the working process is reduced, but in the working process of the pulp pump, not only the protection of the impeller assembly 30 is considered, but also the problem of blockage of the pulp pump is considered, and the biggest factor of the blockage of the pulp pump is that the diameter of the fiber in the pulp is too large, so that the embodiment needs to compare and analyze the fiber diameter with the preset diameter threshold before classifying the pulp;
if the fiber diameter is greater than or equal to the preset diameter threshold, it indicates that the diameter of the fiber in the fed pulp is too large, and the blockage of the pulp pump is easily caused, so that the pulp is not required to be classified, the central processing unit 15 directly sends a first adjustment instruction to the telescopic component 50 and the cutting component 60, after receiving the first adjustment instruction, the telescopic component 50 starts to stretch and drives the cutting component 60 to move towards the position of the through hole 33, and meanwhile, the cutting component 60 receives the first adjustment instruction and starts to rotate to cut the fiber, so that the probability of blockage of the pulp pump is reduced, if the fiber diameter is smaller than the preset diameter threshold, it indicates that the diameter of the fiber in the fed pulp is in a reasonable range, the pulp pump is not easy to block, the pulp is further required to be classified, and the impeller component 30 is further protected in a targeted manner.
Example 3
This example was further modified on the basis of example 1;
step one, acquiring real-time characteristic data of paper pulp, and simultaneously acquiring an abnormal fiber diameter ratio;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain a paper pulp class, switching to the third step if the paper pulp class is mechanical paper pulp, and switching to the fourth step if the paper pulp class is chemical paper pulp;
step three, inputting the abnormal fiber diameter ratio into a power regulation model to obtain a power index;
step four, judging whether to generate an adjustment instruction based on the pulp category, wherein the adjustment instruction comprises a first adjustment instruction and a second adjustment instruction;
step five, the stretching assembly 50 stretches based on the first adjustment instruction, and the cutting assembly 60 cuts the fiber based on the first adjustment instruction and the power index;
step six, the telescoping assembly 50 shortens based on the second adjustment command, and the cutting assembly 60 stops cutting the fibers based on the second adjustment command.
In embodiment 1, diameter data of a plurality of fibers are obtained simultaneously and averaged as fiber diameters in the real-time characteristic data, whereas in this embodiment, the plurality of fiber diameters are compared with a preset abnormal diameter threshold value respectively;
if the fiber diameter is greater than or equal to a preset abnormal diameter threshold, marking the fiber diameter as an abnormal diameter;
if the fiber diameter is smaller than a preset abnormal diameter threshold, marking as a normal diameter;
the abnormal fiber diameter ratio is the ratio of the number of fibers with abnormal diameters to the total number of fibers, the total number of fibers is the total number of fibers obtained by one measurement, the number of fibers with abnormal diameters is the total number of fibers with abnormal diameter marks, the power index is the output power grade of the cutting assembly 60, the cutting assembly 60 adjusts the output power according to the power index, the higher the power index is, the higher the output power of the cutting assembly 60 is, the higher the rotating speed of the cutting assembly 60 is, which means that the cutting assembly 60 cuts the fibers in the paper pulp, and the pulp pump can adjust the output power of the cutting assembly 60 according to the abnormal fiber diameter ratio in the paper pulp in the embodiment;
the training mode of the power regulation model is as follows:
collecting training data, wherein the training data comprise fiber diameter abnormal duty ratio and power index, taking the fiber diameter abnormal duty ratio and the power index as sample sets, dividing the sample sets into training sets and test sets, constructing a second machine learning model, taking the fiber diameter abnormal duty ratio in the training sets as input data, taking the power index in the training sets as output data, training the second machine learning model to obtain an initial second machine learning model, testing the second machine learning model by utilizing the test sets, and outputting the second machine learning model meeting the preset accuracy as a power adjustment model, wherein the second machine learning model is preferably a neural network model.
The preset parameters, weights and threshold selections in the above are set by those skilled in the art according to the actual situation.
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 embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. 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, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless 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.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A low pulse pulp pump for papermaking pulp, comprising a pulp pump body (10), characterized in that: an impeller assembly (30) is arranged in the pulp pump main body (10), the impeller assembly (30) comprises an impeller chassis (31) and impeller blades (32), a plurality of through holes (33) are formed in one side of the impeller chassis (31), the impeller blades (32) are fixedly connected between every two through holes (33), and a containing assembly (40) is fixedly connected with the other side of the impeller chassis (31);
a fiber diameter detection module (70) which is arranged on the surface of the pulp pump main body (10) and is used for acquiring the diameter of the fiber in the pulp;
the numerical value detection module (20) is arranged on the inner wall of the pulp pump main body (10) and is used for acquiring a pulp temperature value and a pulp pH value;
a classification module (16) for inputting the fiber diameter, the pulp temperature value and the pulp pH value into a pulp discrimination model to obtain pulp types;
a central processing unit (15) that determines whether or not to generate an adjustment instruction based on the pulp type;
the telescopic assembly (50) is arranged on one side of the accommodating assembly (40), stretches and contracts according to the adjusting instruction, and the cutting assembly (60) is arranged at one end of the telescopic assembly (50) and cuts the fiber according to the adjusting instruction.
2. The low pulse pulp pump of claim 1, wherein: the inside of pulp pump main part (10) has seted up the working chamber, and pulp entry (11) communicating with the outside have been seted up to one side of working chamber, and pulp export (12) have been seted up on the top of working chamber, and the detection hole has been seted up on the top of pulp entry (11), and the top of detection hole is provided with fiber diameter detection module (70), and the inner wall fixedly connected with water proof membrane (13) of detection hole, and the inner wall of pulp entry (11) is provided with numerical value detection module (20).
3. The low pulse pulp pump of claim 2, wherein: the waterproof film (13) is made of transparent material, and the numerical detection module (20) is a temperature PH sensor.
4. The low pulse pulp pump of claim 1, wherein: the accommodating assembly (40) comprises an accommodating disc (41) and supporting columns (42), the accommodating disc (41) is fixedly connected with the other side of the impeller chassis (31) through a plurality of supporting columns (42), a telescopic assembly (50) is arranged between every two supporting columns (42), one end of the telescopic assembly (50) is provided with a cutting assembly (60), and the position of the cutting assembly (60) corresponds to the position of the through hole (33).
5. The low pulse pulp pump of claim 4, wherein: the telescopic component (50) stretches to drive the cutting component (60) to penetrate through the through hole (33) and enter a region formed between the two impeller blades (32), and the telescopic component (50) resets to drive the cutting component (60) to penetrate through the through hole (33) and exit the region formed by the two impeller blades (32).
6. A method for detecting papermaking pulp, which is characterized by comprising the following steps: use of a low pulse pulp pump as claimed in any one of claims 1-5, comprising:
acquiring real-time characteristic data of paper pulp, wherein the real-time characteristic data comprise fiber diameter, paper pulp temperature value and paper pulp pH value;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain the paper pulp category;
based on the pulp category, judging whether to generate an adjustment instruction, wherein the adjustment instruction comprises a first adjustment instruction and a second adjustment instruction;
the expansion module (50) expands based on the first adjustment command, the cutting module (60) cuts the fibers based on the first adjustment command, the expansion module (50) shortens based on the second adjustment command, and the cutting module (60) stops cutting the fibers based on the second adjustment command.
7. The method for detecting papermaking pulp according to claim 6, wherein: the pulp category includes mechanical pulp and chemical pulp, and when the pulp is mechanical pulp, the central processor (15) generates a first adjustment instruction, and when the pulp is chemical pulp, the central processor (15) generates a second adjustment instruction.
8. The method for detecting papermaking pulp according to claim 7, wherein the training mode of the pulp discrimination model is as follows:
obtaining a plurality of groups of paper pulp in an experimental environment, detecting each group of paper pulp to obtain each group of paper pulp characteristic data, generating a corresponding actual mark according to the collected paper pulp types, wherein the actual mark is 1 when the paper pulp types are mechanical paper pulp, and the actual mark is 0 when the paper pulp types are chemical paper pulp; taking each group of pulp characteristic data as input of a first machine learning model, wherein the first machine learning model takes prediction labeling of each group of pulp characteristic data as output, takes actual labeling as a prediction target, and takes the sum of prediction accuracy of all pulp characteristic data as a training target; the calculation formula of the prediction accuracy is as follows:wherein->Numbering pulp characteristic data>For prediction accuracy, < >>Is->Predictive label value corresponding to group pulp characteristic data, < + >>Is->Grouping actual labeling values corresponding to pulp characteristic data; and training the first machine learning model until the sum of the prediction accuracy reaches convergence, stopping training, taking the first machine learning model obtained by training as a pulp discrimination model, wherein the first machine learning model is one of a naive Bayesian model and a support vector machine model.
9. The method for detecting papermaking pulp according to claim 8, wherein: the central processing unit (15) obtains a prediction mark corresponding to the pulp category, generates a first adjustment instruction when the prediction mark is equal to 1, and generates a second adjustment instruction when the prediction mark is equal to 0.
10. The method for detecting papermaking pulp according to claim 9, wherein:
step one, acquiring real-time characteristic data of paper pulp and an abnormal fiber diameter ratio;
inputting the real-time characteristic data of the paper pulp into a paper pulp discriminating model to obtain a paper pulp class, switching to the third step if the paper pulp class is mechanical paper pulp, and switching to the fourth step if the paper pulp class is chemical paper pulp;
step three, inputting the abnormal fiber diameter ratio into a power regulation model to obtain a power index, and turning to step five;
step four, generating a second adjustment instruction when the pulp type is chemical pulp, shortening the telescopic component (50) based on the second adjustment instruction, and stopping cutting the fiber by the cutting component (60) based on the second adjustment instruction;
and fifthly, generating a first adjustment command when the pulp type is mechanical pulp, extending the telescopic component (50) based on the first adjustment command, cutting the fiber by the cutting component (60) based on the first adjustment command and the power index, and taking the power index as the output power of the cutting component (60).
11. The method for detecting papermaking pulp according to claim 10, wherein the training mode of the power adjustment model is as follows:
collecting training data, wherein the training data comprise fiber diameter abnormal duty ratio and power index, the fiber diameter abnormal duty ratio and the power index are used as sample sets, the sample sets are divided into training sets and test sets, a second machine learning model is built, the fiber diameter abnormal duty ratio in the training sets is used as input data, the power index in the training sets is used as output data, the second machine learning model is trained, an initial second machine learning model is obtained, the second machine learning model is tested by using the test sets, the second machine learning model meeting the preset accuracy is output as a power adjustment model, and the second machine learning model is a neural network model.
12. The method according to claim 11, wherein the abnormal fiber diameter ratio is a ratio of a number of fibers having an abnormal diameter to a total number of fibers, the total number of fibers being a total number of fibers obtained by one measurement, and the number of fibers having an abnormal diameter being a total number of fibers having an abnormal diameter mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471464.6A CN117212182B (en) | 2023-11-07 | 2023-11-07 | Low-pulse pulp pump for papermaking pulp and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471464.6A CN117212182B (en) | 2023-11-07 | 2023-11-07 | Low-pulse pulp pump for papermaking pulp and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117212182A true CN117212182A (en) | 2023-12-12 |
| CN117212182B CN117212182B (en) | 2024-01-26 |
Family
ID=89051425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311471464.6A Active CN117212182B (en) | 2023-11-07 | 2023-11-07 | Low-pulse pulp pump for papermaking pulp and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117212182B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104514724A (en) * | 2013-09-27 | 2015-04-15 | 江苏尚宝罗泵业有限公司 | Paper pulp cutting pump |
| CN107478656A (en) * | 2017-08-09 | 2017-12-15 | 齐鲁工业大学 | Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system |
| CN110500283A (en) * | 2018-05-17 | 2019-11-26 | 尚宝罗江苏节能科技股份有限公司 | Paper pulp cutting pump |
| CN213298296U (en) * | 2020-07-04 | 2021-05-28 | 河北腾达泵阀有限公司 | Single shell sediment stuff pump |
| CN114217657A (en) * | 2021-12-15 | 2022-03-22 | 黑龙江省琼冰建筑设计有限公司 | Intelligent construction and operation and maintenance control system for ice and snow building |
-
2023
- 2023-11-07 CN CN202311471464.6A patent/CN117212182B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104514724A (en) * | 2013-09-27 | 2015-04-15 | 江苏尚宝罗泵业有限公司 | Paper pulp cutting pump |
| CN107478656A (en) * | 2017-08-09 | 2017-12-15 | 齐鲁工业大学 | Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system |
| CN110500283A (en) * | 2018-05-17 | 2019-11-26 | 尚宝罗江苏节能科技股份有限公司 | Paper pulp cutting pump |
| CN213298296U (en) * | 2020-07-04 | 2021-05-28 | 河北腾达泵阀有限公司 | Single shell sediment stuff pump |
| CN114217657A (en) * | 2021-12-15 | 2022-03-22 | 黑龙江省琼冰建筑设计有限公司 | Intelligent construction and operation and maintenance control system for ice and snow building |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117212182B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model | |
| Bordoloi et al. | Identification of suction flow blockages and casing cavitations in centrifugal pumps by optimal support vector machine techniques | |
| US20120253694A1 (en) | Method and apparatus for judging status of mechanical system | |
| KR101539896B1 (en) | Method for diagnosis of induction motor fault | |
| CN117212182B (en) | Low-pulse pulp pump for papermaking pulp and detection method | |
| US6338029B1 (en) | Method for determining when an electric motor is acceptable | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| Song et al. | Intelligent diagnosis method for machinery by sequential auto-reorganization of histogram | |
| CN116257747A (en) | Early abnormality detection method for rotor system of fusion kurtosis and convolution self-encoder | |
| CN112148517A (en) | Fault diagnosis method for rotating equipment | |
| Vamsi et al. | Damage monitoring of pultruded GFRP composites using wavelet transform of vibration signals | |
| KR20230170727A (en) | Methods for estimating component wear | |
| KR20170140588A (en) | Apparatus and method for determining state of power plant | |
| Ha et al. | Degradation trend estimation and prognostics for low speed gear lifetime | |
| CN108982106A (en) | Effective method for rapidly detecting kinetic mutation of complex system | |
| CN116147878A (en) | Large-scale low-temperature wind tunnel safety interlocking method, device and storage medium | |
| EP3712577B1 (en) | Apparatus for equipment monitoring | |
| Decker et al. | Does your model think like an engineer? explainable ai for bearing fault detection with deep learning | |
| Lu et al. | Effects of extrinsic noise factors on machine learning–based chatter detection in machining | |
| JP2020177378A (en) | Abnormality sign detecting device and abnormality sign detecting method | |
| Leite et al. | A robust fleet-based anomaly detection framework applied to wind turbine vibration data | |
| Joshuva et al. | Implementation of rule based classifiers for wind turbine blade fault diagnosis using vibration signals | |
| Park et al. | Prediction of the CNC tool wear using the machine learning technique | |
| Elbestawi et al. | Tool condition monitoring in machining | |
| CN113030726A (en) | Motor state monitoring method and system based on data driving |
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 |