Paper pulp concentration intelligent production line regulation and control method and system based on AI algorithm

Abstract

The invention discloses a paper pulp concentration intelligent production line regulation and control method and system based on an AI algorithm, and relates to the technical field of paper pulp concentration control. Comprising the following steps: establishing a feeding model, and obtaining a paper pulp addition amount and a water addition amount under a test paper pulp concentration and when a standard loading volume is v; the step of obtaining the test paper pulp concentration comprises the following steps that a plurality of connecting pipes are connected to each height in the stirring barrel, outlets of the connecting pipes are fixedly communicated with the top of the stirring barrel, and pipe bodies of the connecting pipes are connected with detectors and liquid pumps. The feeding model is arranged, the target concentration can be determined according to the papermaking quality requirement and the application requirement of a user for paper, the target concentration is input into the paper pulp addition amount model and the water addition amount model, the target paper pulp addition amount and the target water addition amount are obtained respectively, and after mixing is completed, the target concentration is obtained. The paper pulp batching system does not need to be customized in advance.

Description

Technical Field

[0001] The present invention relates to the technical field of pulp concentration control, and in particular to a method and system for controlling pulp concentration in an intelligent production line based on an AI algorithm. Background Art

[0002] The papermaking process of household paper mainly includes pulping, refining, mixing, forming, pressing, drying, corrugating and winding.

[0003] In the pulping process, pulp concentration directly affects the quality of paper formation. Too low concentration will lead to fiber agglomeration, increase the mobility of fibers, and increase the time required to form a flocculated state, thus affecting the uniformity and overall quality of the paper. On the contrary, too high concentration may increase the viscosity and fluidity of the pulp, resulting in difficulty in the flow of pulp in the pipe, or even block the pipe, and is not conducive to the uniform dispersion of fibers. At the same time, the level of pulp concentration also determines the mechanical strength of the paper. Too low or too high concentration will weaken the toughness of the paper and make it easy to break. In addition, real-time measurement and control of pulp concentration can prevent strong fluctuations in pulp concentration during the papermaking process, thereby ensuring the stability and continuity of the production process, which helps to improve production efficiency and reduce production costs. At the same time, precise concentration control can also help to achieve consistency and stability in product quality to meet customer needs and expectations.

[0004] The Chinese invention patent, application publication number CN106283806A, discloses a pulp quality control method and system for a high-concentration refining system. The method is based on the high-concentration disc refiner input and output related data measured by sensors on a chemical mechanical pulping production line, combines the AIC criterion to determine the sub-model order and uses the forgetting factor least squares method to obtain the sub-model parameters, and combines the mechanism model of the pulp quality freeness index to establish the Wiener model structure of the high-concentration refining system, and uses the sequential quadratic programming algorithm to optimize the secondary performance index to achieve effective control of the pulping output pulp quality index - freeness.

[0005] The existing technology and existing pulp batching system still have certain defects in practical applications, such as:

[0006] Based on the quality of papermaking and the different uses of paper, customers need to adjust the pulp concentration during production. The existing pulp batching system is generally customized in advance according to user needs, lacking sufficient flexibility and unable to quickly adapt to the different requirements of different customers or different products for pulp concentration;

[0007] After the pulp concentration is adjusted, separate pulping is required, and paper can be reproduced only after the pulping is completed, which results in poor production continuity and reduced production efficiency.

[0008] In the process of preparing pulp, the pulp mixture is generally stirred and mixed by an agitator in a stirring barrel. However, the agitator consumes a large amount of power when stirring the pulp mixture, which is not conducive to energy saving of the system and increases production costs. Summary of the invention

[0009] The purpose of the present invention is to provide a method and system for intelligent production line control of pulp concentration based on AI algorithm to solve the problems raised in the above background technology.

[0010] To achieve the above object, the present invention provides the following technical solution: a method for controlling pulp concentration intelligent production line based on AI algorithm, comprising:

[0011] Establishing a feeding model to obtain the pulp addition amount and water addition amount at the test pulp concentration and when the standard containing volume is v;

[0012] Obtaining the test pulp consistency includes the following steps:

[0013] A plurality of connecting pipes are connected at each height in the mixing barrel, the outlets of the connecting pipes are fixedly connected to the top of the mixing barrel, and the pipe bodies of the connecting pipes are connected to detectors and liquid pumps;

[0014] The water at different heights in the mixing barrel is pumped into the corresponding connecting pipes by a liquid pump, and the pulp concentration is detected by a detector to obtain concentration sets at different heights: [(a011, a012, ..., a01N), (a021, a022, ..., a02N), ..., (a0N1, a0N2, ..., a0NN)];

[0015] Calculate the average of all detected concentrations on the same horizontal plane to obtain a detected concentration data set (a01, a02, ..., a0N);

[0016] According to different detection heights, the data in the detection concentration data set are weighted averaged to obtain the test pulp concentration c, c=e1×a01+e2×a02+...+eN×a0N;

[0017] Based on the feeding model, a pulp addition amount model and a water addition amount model are obtained, and the target concentration is input into the pulp addition amount model and the water addition amount model to obtain the target pulp addition amount and the target water addition amount respectively;

[0018] A stirring model is established to obtain a stirring time model of the stirrer, and the target concentration is input into the stirring time model of the stirrer to obtain a target stirring time of the stirring barrel stirrer;

[0019] A refining model is established, and the target concentration is input into the refining model to obtain the target refining time of the refiner.

[0020] Furthermore, the establishment of the feeding model includes the following steps:

[0021] Weigh several portions of pulp, the weights of which are m1, m2, ..., mN, respectively, to obtain a set of pulp weights;

[0022] Get the standard capacity of the mixing barrel in the production line, the standard capacity is v;

[0023] Weigh a number of portions of water (volume v) equal to the amount of pulp;

[0024] Add water to the stirring barrel respectively, then add the pulp in the pulp weight set to the stirring barrel respectively, after sufficient stirring, measure the total volume of the pulp and water as v1, v2, ..., vN, measure the test pulp concentration in the stirring barrel as ρ1, ρ2, ..., ρN, and obtain the total volume set of the pulp and water and the test pulp concentration set respectively;

[0025] Subtract the total volume of the pulp and water from the standard holding volume of the mixing barrel to obtain a set of volume increases, which are: v1-v, v2-v, ..., vN-v;

[0026] The data in the volume increase set are divided by the data in the total volume set of pulp and water to obtain a volume change ratio set. The volume change ratios are: (v1-v) / v1, (v2-v) / v2, ..., (vN-v) / vN;

[0027] The data in the pulp weight set are multiplied by the data in the volume change ratio set to obtain the pulp reduction amount set, which are: m1×(v1-v) / v1, m2×(v2-v) / v2, ..., mN×(vN-v) / vN, and then the pulp addition amount set is obtained, which are: m1×[1-(v1-v) / v1], m2×[1-(v2-v) / v2], ..., mN×[1-(vN-v) / vN];

[0028] The mixed liquids with volume increases of v1-v, v2-v, ..., vN-v are taken out, and the volume of water in the mixed liquid is obtained by evaporation to obtain a set of water reduction volumes, which are: p1, p2, ..., pN, and then the water added volumes are: v-p1, v-p2, ..., v-pN, and then the water added amount set is obtained, which is: ρwater×(v-p1), ρwater×(v-p2), ..., ρwater×(v-pN).

[0029] Furthermore, a linear fit is performed on the test pulp concentration set and the pulp addition amount set to obtain a pulp addition amount model;

[0030] The test pulp concentration set and the water addition amount set were linearly fitted to obtain the water addition amount model.

[0031] Furthermore, the establishment of the stirring model includes the following steps:

[0032] Obtain the number of storage tanks n, the storage capacity q of the storage tanks and the discharge time t of each storage tank, where (the number of storage tanks n-1) × the storage capacity q of the storage tank = the standard holding capacity v of the mixing barrel;

[0033] The residence time of water and pulp in the mixing barrel is calculated as T = (the number of storage tanks n-1) × the discharge time t of each storage tank;

[0034] The concentrations of water and pulp in the stirring barrel are measured to obtain the stirring time of the stirring barrel stirrer at the test pulp concentration.

[0035] Furthermore, when the test pulp concentration is reached, the stirring time of the stirring drum agitator is determined by:

[0036] Obtain the stirring time jx of the stirrer when the pulp and water mixture in the stirring barrel reaches the test pulp concentration, and obtain its set as [j1, j2, ..., jN];

[0037] The test pulp concentration set and the stirring time set of the stirrer are linearly fitted to obtain the stirring time model of the stirrer.

[0038] Furthermore, the method for establishing the refining model of the refiner is:

[0039] Subtract the residence time T of water and pulp in the mixing barrel from the stirring time jx of the agitator under the test pulp concentration to obtain a set of gap times, calculate the average of the gap times, and obtain the average gap time X;

[0040] Obtain the power consumption per unit time of the refiner P1 and the power consumption per unit time of the agitator P2, and calculate P1 / P2=k, (k<1);

[0041] If the average gap time X>2×the stirring time jx of the agitator at the test pulp concentration, the target refining time tx of the refiner = jx / (k×2);

[0042] If the stirring time jx of the stirrer at the test pulp concentration is ≤ the average gap time X ≤ 2× the stirring time jx of the stirrer at the test pulp concentration, the target stirring time tx of the stirrer is = k×P2×jx / (P1×2.5);

[0043] If the average gap time X < the stirring time jx of the agitator under the test pulp concentration, the target refining time tx of the refiner = k×P2×jx / (P1×3).

[0044] Furthermore, the method further comprises:

[0045] Determine the maneuvering time b for the mixing barrel to replenish the storage tank, and calculate the residence time of water and pulp in the mixing barrel T = (the number of storage tanks n-1) × the discharge time t of each storage tank - the maneuvering time b.

[0046] A pulp concentration intelligent production line control system based on AI algorithm, using a pulp concentration intelligent production line control method, including:

[0047] The data acquisition module acquires the data of pulp concentration detected by each detector in the mixing barrel, the number of storage tanks n, the storage volume q of the storage tanks, the discharge time t of each storage tank, and the maneuvering time b of the mixing barrel to replenish the storage tank;

[0048] A calculation module is provided to establish a feeding model, obtain the pulp addition amount and water addition amount under the test pulp concentration and the standard containing volume v, obtain a pulp addition amount model and a water addition amount model based on the feeding model, input the target concentration into the pulp addition amount model and the water addition amount model, respectively obtain the target pulp addition amount and the target water addition amount, establish a stirring model, obtain a stirring time model of the stirrer, input the target concentration into the stirring time model of the stirrer, obtain the target stirring time of the stirring barrel stirrer, establish a refining model, input the target concentration into the refining model, and obtain the target refining time of the refiner;

[0049] The AI ​​algorithm module is based on deep learning and training of the model in the calculation module to achieve intelligent production line control of pulp concentration.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The AI ​​algorithm-based pulp concentration intelligent production line control method and system is provided with a feeding model, which can determine the target concentration according to the quality requirements of papermaking and the user's demand for paper usage, and input the target concentration into the pulp addition model and the water addition model to obtain the target pulp addition and the target water addition respectively. After mixing, a mixed liquid with a standard filling volume at the target concentration is obtained. The pulp batching system does not need to be customized in advance, can quickly adapt to the different requirements of different customers or different products for pulp concentration, and has good flexibility.

[0052] At the same time, the concentration of the mixed liquid gradually increases during the stirring process. In this solution, the amount of pulp and water is controlled based on the standard containing volume, so that the target concentration is achieved under the conditions of maximum water volume and minimum pulp volume, which effectively saves pulp and reduces production costs.

[0053] In addition, a plurality of storage barrels are provided, through which materials are fed to the Yankee dryer in sequence, thereby achieving uninterrupted feeding and increasing production efficiency. In addition, if the target concentration needs to be changed during the operation, it is only necessary to use up the mixed liquid of the previous target concentration contained in the storage barrel, and mix the materials according to the changed target concentration within the residence time T of the water and pulp in the stirring barrel, thereby ensuring good production continuity of the pulp mixing system and improving production efficiency.

[0054] In addition, a refining model is provided, which can adjust the refining time of the refiner according to the residence time T of water and pulp in the mixing barrel and the interval time. Under the condition of ensuring the pulp concentration, the stirring time of the agitator is reduced, thereby reducing the energy consumption of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of the present invention;

[0056] Figure 2 This is a front view of the pulp concentration tester of the present invention;

[0057] Figure 3 A top view of the distribution of the pulp concentration test detector of the present invention;

[0058] Figure 4 It is a schematic diagram of the connection between the stirring barrel and the storage tank of the present invention;

[0059] Figure 5 is a power consumption diagram of the agitator and grinder of the present invention;

[0060] Figure 6 The graph is a variation curve of the pulp concentration in the stirring barrel when the stirrer of the present invention works alone and when the stirrer and the grinder work simultaneously.

[0061] In the figure: 1. Detector; 2. Liquid pump; 3. Water inlet pipe; 4. Pulp inlet pipe; 5. Electric control valve; 6. Yankee dryer. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] like Figure 1-Figure 6 As shown, the present invention provides a technical solution: a method for controlling pulp concentration intelligent production line based on AI algorithm, comprising:

[0064] A feeding model is established to obtain the pulp addition amount and water addition amount under the test pulp concentration and when the standard containing volume is v, wherein the establishment of the feeding model includes the following steps:

[0065] Weigh several portions of pulp. The pulp in this scheme is obtained by breaking the pulp plate through a pulper. The particle size control range of the broken pulp includes -2μm content 65%, -45μm content 100%, and the weights of the pulps are m1, m2, ..., mN, respectively, to obtain a pulp weight set (m1, m2, ..., mN).

[0066] The standard holding capacity of the mixing barrel in the production line is obtained. The standard holding capacity refers to the maximum amount of solution that the mixing barrel can mix at a single time. The standard holding capacity is v. Weigh several portions of water with a volume of v equal to the amount of pulp, add the water into the mixing barrel respectively, and then add the pulp in the pulp weight set into the mixing barrel respectively. After sufficient stirring, the total volume of the pulp and water is measured as v1, v2, ..., vN, and the test pulp concentration in the mixing barrel is measured as ρ1, ρ2, ..., ρN. The total volume set of pulp and water (v1, v2, ..., vN) and the test pulp concentration set (ρ1, ρ2, ..., ρN) are obtained respectively. In this scheme, sufficient stirring means that the concentration of the mixed liquid of pulp and water in the mixing barrel reaches the corresponding test pulp concentration.

[0067] like Figure 2 and Figure 3 As shown, obtaining the test pulp concentration includes the following steps:

[0068] A number of connecting pipes are connected at each height in the mixing barrel, and the outlets of the connecting pipes are fixedly connected to the top of the mixing barrel, a detector 1 is connected to the pipe body of each connecting pipe, and a liquid pump 2 is connected to the main pipe. When the liquid pump 2 is started, the liquid in the mixing barrel circulates in the connecting pipe, and the pulp concentration is detected by the detector 1. The detector can be a spectrometer or other device that can test the pulp concentration of the mixed liquid.

[0069] like Figure 4As shown, the water inlet pipe 3 is arranged at the bottom of the mixing barrel for injecting water into the mixing barrel, and the pulper is arranged at the top of the mixing barrel and connected to the mixing barrel through the pulp inlet pipe 4. In this way, when the agitator in the mixing barrel stirs the solution, the concentration of the solution at the top of the mixing barrel will be lower than the concentration of the solution at the bottom. Therefore, in this scheme, three groups of connecting pipes are arranged at different heights, and the distance between the topmost connecting pipe group and the liquid surface is 1 / 5 of the overall height of the liquid surface, the distance between the middle connecting pipe group and the liquid surface is 3 / 5 of the overall height of the liquid surface, and the distance between the bottommost connecting pipe group and the liquid surface is 4 / 5 of the overall height of the liquid surface. To ensure accuracy, each group of connecting pipes includes three connecting pipes for detecting mixed liquids at different positions at the same height.

[0070] The water at different heights in the mixing barrel is pumped into the corresponding connecting pipes by a liquid pump, and the pulp concentration is detected by a detector to obtain concentration sets at different heights: [(a011, a012, ..., a01N), (a021, a022, ..., a02N), ..., (a0N1, a0N2, ..., a0NN)], and the average values ​​of all detected concentrations on the same horizontal plane are calculated to obtain a detection concentration data set (a01, a02, ..., a0N). Finally, according to different detection heights, the data in the detection concentration data set are weighted averaged to obtain the test pulp concentration c, c=e1×a01+e2×a02+...+eN×a0N. In this scheme, since there are three connecting pipe groups arranged in the height direction, c=e1×a01+e2×a02+e3×a03.

[0071] like Figure 4 As shown, in this scheme, the mixed solution enters the storage barrel through the corresponding pipeline, and then is sequentially transported to the cylinder surface of the Yankee dryer through the storage barrel and a series of precisely controlled conveying equipment. During the liquid circulation process, the pulp concentration in the liquid will gradually increase, thereby reaching the test pulp concentration. In this way, there is no need to directly stir the pulp concentration to the test pulp concentration in the stirring barrel, thereby reducing the energy consumption of the system. In addition, since the concentration value in the middle of the stirring barrel can best represent the overall pulp concentration (the concentration is higher towards the bottom), therefore, in this scheme, the weights e1, e2 and e3 are set to 0.15, 0.6 and 0.25 respectively. Assuming that the test pulp concentration is 30%, when the weighted average pulp concentration obtained by the stirrer in the stirring barrel is 20% during the stirring process, the stirrer in the stirring barrel will continue to stir the mixed liquid. When the weighted average pulp concentration is 18%, the concentration deviation value is 10% at this time, and the concentration deviation value of 10% can be compensated in the subsequent liquid transportation (verified by personnel in this technical field through limited experiments). At this time, the controller controls the stirrer to stop working.

[0072] Subtract the total volume of pulp and water obtained from the standard holding capacity of the mixing barrel to obtain a set of volume increases. The specific volume increases are: v1-v, v2-v, ..., vN-v. Divide the data in the set of volume increases by the data in the total volume set of pulp and water to obtain a set of volume change ratios. The volume change ratios are: (v1-v) / v1, (v2-v) / v2, ..., (vN-v) / vN.

[0073] Multiply the data in the pulp weight set with the data in the volume change ratio set to obtain the pulp reduction amount set, which are: m1×(v1-v) / v1, m2×(v2-v) / v2, ..., mN×(vN-v) / vN. Then, the pulp addition amount set is obtained, which are: m1×[1-(v1-v) / v1], m2×[1-(v2-v) / v2], ..., mN×[1-(vN-v) / vN].

[0074] The mixed liquids with volume increases of v1-v, v2-v, ..., vN-v are taken out, and the volume of water in the mixed liquid is obtained by evaporation to obtain a set of water reduction volumes, which are: p1, p2, ..., pN, and then the water added volumes are: v-p1, v-p2, ..., v-pN, and then the water added amount set is obtained, which is: ρwater×(v-p1), ρwater×(v-p2), ..., ρwater×(v-pN).

[0075] Finally, a linear fit is performed on the test pulp concentration set and the pulp addition amount set to obtain a pulp addition amount model, and a linear fit is performed on the test pulp concentration set and the water addition amount set to obtain a water addition amount model.

[0076] Before production, the target concentration is determined according to the quality requirements of papermaking and the user's demand for the use of paper, and the target concentration is input into the pulp addition model and the water addition model to obtain the target pulp addition and the target water addition, respectively. For example, if the user sets the pulp concentration to 30%, the target concentration of 30% is input into the pulp addition model and the water addition model to obtain a pulp amount of 25kg and a water amount of 100kg. The water directly enters the mixing barrel through the water inlet pipe 3, and the pulp is ground to the set particle size and enters the mixing barrel through the pulp inlet pipe 4. After mixing, a mixed liquid with a standard holding volume at the target concentration is obtained.

[0077] In addition, it can be understood that the concentration of the mixed liquid gradually increases during the stirring process. In this solution, the amount of pulp and water is controlled based on the standard containing volume, so that the target concentration is achieved under the conditions of maximum water volume and minimum pulp volume, which effectively saves pulp and reduces production costs.

[0078] A stirring model is established to obtain a stirring time model of the stirrer, and the target concentration is input into the stirring time model of the stirrer to obtain a target stirring time of the stirring barrel stirrer.

[0079] The establishment of the stirring model includes the following steps:

[0080] Obtain the number n of storage tanks, the storage capacity q of the storage tanks and the discharge time t of each storage tank, where (the number n-1 of storage tanks) × the storage capacity q of the storage tank = the standard holding capacity v of the mixing barrel. Calculate the residence time T of water and pulp in the mixing barrel = (the number n-1 of storage tanks) × the discharge time t of each storage tank. Measure the concentration of water and pulp in the mixing barrel, and obtain the stirring time of the agitator in the mixing barrel when the test pulp concentration is reached. It can be known that the stirring time is when both water and pulp are added, and the agitator stirs the mixed liquid to reach the stirring time under the corresponding test pulp concentration.

[0081] In addition, to improve the accuracy of the system, the method also includes determining the maneuvering time b for the mixing barrel to replenish the storage tank, the maneuvering time b includes the material pump start-up time and the feeding time, and calculating the residence time of water and pulp in the mixing barrel T = (the number of storage tanks n-1) × the discharge time t of each storage tank-the maneuvering time b.

[0082] In a specific embodiment of the present scheme, four storage barrels are provided, and electric-controlled valves 5 are connected to the pipelines on both sides of each storage barrel. In the initial state, the four storage barrels are all full of slurry. During operation, the electric-controlled valves 5 are opened in sequence from top to bottom. When the three storage barrels are all empty, the electric-controlled valve on the left side of the empty storage barrel is opened and the storage valve on the right side of the empty storage barrel is closed, and the three storage barrels are replenished at the same time. After the three storage barrels are replenished, the mixing barrel is empty. At this time, water is injected into the mixing barrel and pulp is added according to the target concentration.

[0083] In this solution, multiple storage barrels are provided, and materials are fed to the Yankee dryer in turn through the storage barrels, thereby achieving uninterrupted feeding and increasing production efficiency. In addition, if the target concentration needs to be changed during the operation, it is only necessary to use up the mixed liquid of the previous target concentration contained in the storage barrel, and within the residence time T of water and pulp in the stirring barrel, the ingredients can be mixed according to the changed target concentration, thereby ensuring good production continuity of the pulp mixing system and improving production efficiency.

[0084] The stirring time of the agitator will be different for different pulp concentrations. In this solution, the stirring time of the agitator in the mixing barrel is determined as follows:

[0085] Obtain the stirring time jx of the agitator when the pulp and water mixture in the stirring barrel reaches the test pulp concentration, and obtain its set as [j1, j2, ..., jN]. Perform linear fitting on the test pulp concentration set and the stirring time set of the agitator to obtain the target stirring time of the agitator in the stirring barrel at the target concentration.

[0086] like Figure 5 and Figure 6 As shown, it can be understood that the more dispersed the pulp particles are and the smaller the particle size is, the shorter the stirring time is under the same stirring environment. Figure 6 ② is the time-concentration curve of the mixed liquid stirred by the agitator after the pulp is ground for a certain period of time, and ① is the time-concentration curve of the mixed liquid stirred by the agitator at the initial pulp particle size. The power consumption per unit time of the agitator is greater than that of the refiner. Considering the correlation between the residence time T of water and pulp in the stirring barrel and the stirring time of the agitator, in this scheme, a refining model is established, and the target concentration is input into the refining model to obtain the target refining time of the refiner.

[0087] Specifically, the method for establishing the refinement model of the refiner is as follows:

[0088] The residence time T of water and pulp in the mixing barrel is subtracted from the stirring time jx of the agitator under the test pulp concentration to obtain the gap time set. Considering that a long gap time has little impact on the entire system, in order to facilitate the subsequent data processing, the average gap time is calculated to obtain the average gap time X, and the power consumption per unit time of the pulper P1 and the power consumption per unit time of the agitator P2 are obtained, and it is calculated that P1 / P2=k, (k<1).

[0089] If the average gap time X>2×the stirring time jx of the agitator at the test pulp concentration, the target refining time of the refiner is tx=jx / (k×2); if the stirring time jx of the agitator at the test pulp concentration is ≤the average gap time X≤2×the stirring time jx of the agitator at the test pulp concentration, the target stirring time of the agitator is tx=jx / (k×2.5); if the average gap time X<the stirring time jx of the agitator at the test pulp concentration, the target refining time of the refiner is tx=jx=jx / (k×3).

[0090] In the three cases, the coefficients in the denominator of the formula for the target refining time tx of the refiner are different. This is to take into account the transportation time of the pulp particles and the time for them to fall to the water surface through the pulp inlet pipe, as well as the maximum dissolution time of the pulp after it falls on the water surface, so as to prevent insufficient pulp mixing while minimizing the stirring time of the agitator.

[0091] This solution also discloses a pulp concentration intelligent production line control system based on AI algorithm, using a pulp concentration intelligent production line control method, including:

[0092] The data acquisition module acquires the data of pulp concentration detected by each detector in the mixing barrel, the number of storage tanks n, the storage volume q of the storage tanks, the discharge time t of each storage tank, and the maneuvering time b of the mixing barrel to replenish the storage tank;

[0093] A calculation module is provided to establish a feeding model, obtain the pulp addition amount and water addition amount under the test pulp concentration and the standard containing volume v, obtain a pulp addition amount model and a water addition amount model based on the feeding model, input the target concentration into the pulp addition amount model and the water addition amount model, respectively obtain the target pulp addition amount and the target water addition amount, establish a stirring model, obtain a stirring time model of the stirrer, input the target concentration into the stirring time model of the stirrer, obtain the target stirring time of the stirring barrel stirrer, establish a refining model, input the target concentration into the refining model, and obtain the target refining time of the refiner;

[0094] The AI ​​algorithm module is based on deep learning and training of the model in the calculation module to achieve intelligent production line control of pulp concentration.

[0095] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A method for controlling pulp concentration in an intelligent production line based on an AI algorithm, characterized in that: include: Establishing a feeding model to obtain the pulp addition amount and water addition amount at the test pulp concentration and when the standard containing volume is v; Obtaining the test pulp consistency includes the following steps: A plurality of connecting pipes are connected at each height in the mixing barrel, the outlets of the connecting pipes are fixedly connected to the top of the mixing barrel, and the pipe bodies of the connecting pipes are connected to detectors and liquid pumps; The water at different heights in the mixing barrel is pumped into the corresponding connecting pipes by a liquid pump, and the pulp concentration is detected by a detector to obtain concentration sets at different heights: [(a011, a012, ..., a01N), (a021, a022, ..., a02N), ..., (a0N1, a0N2, ..., a0NN)]; Calculate the average of all detected concentrations on the same horizontal plane to obtain a detected concentration data set (a01, a02, ..., a0N); According to different detection heights, the data in the detection concentration data set are weighted averaged to obtain the test pulp concentration c, c=e1×a01+e2×a02+...+eN×a0N; Based on the feeding model, a pulp addition amount model and a water addition amount model are obtained, and the target concentration is input into the pulp addition amount model and the water addition amount model to obtain the target pulp addition amount and the target water addition amount respectively; A stirring model is established to obtain a stirring time model of the stirrer, and the target concentration is input into the stirring time model of the stirrer to obtain a target stirring time of the stirring barrel stirrer; A refining model is established, and the target concentration is input into the refining model to obtain the target refining time of the refiner.

2. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 1, characterized in that: The establishment of the feeding model comprises the following steps: Weigh several portions of pulp, the weights of which are m1, m2, ..., mN, respectively, to obtain a set of pulp weights; Get the standard capacity of the mixing barrel in the production line, the standard capacity is v; Weigh several portions of water with a volume v equal to the amount of pulp; Add water to the stirring barrel respectively, then add the pulp in the pulp weight set to the stirring barrel respectively, after sufficient stirring, measure the total volume of the pulp and water as v1, v2, ..., vN, measure the test pulp concentration in the stirring barrel as ρ1, ρ2, ..., ρN, and obtain the total volume set of the pulp and water and the test pulp concentration set respectively; Subtract the total volume of the pulp and water from the standard holding capacity of the mixing barrel to obtain a set of volume increases, which are: v1-v, v2-v, ..., vN-v; The data in the volume increase set are divided by the data in the total volume set of pulp and water to obtain a volume change ratio set. The volume change ratios are: (v1-v) / v1, (v2-v) / v2, ..., (vN-v) / vN; The data in the pulp weight set are multiplied by the data in the volume change ratio set to obtain the pulp reduction amount set, which are: m1×(v1-v) / v1, m2×(v2-v) / v2, ..., mN×(vN-v) / vN, and then the pulp addition amount set is obtained, which are: m1×[1-(v1-v) / v1], m2×[1-(v2-v) / v2], ..., mN×[1-(vN-v) / vN]; The mixed liquids with volume increases of v1-v, v2-v, ..., vN-v are taken out, and the volume of water in the mixed liquid is obtained by evaporation to obtain a set of water reduction volumes, which are: p1, p2, ..., pN, and then the water added volumes are: v-p1, v-p2, ..., v-pN, and then the water added amount set is obtained, which is: ρwater×(v-p1), ρwater×(v-p2), ..., ρwater×(v-pN).

3. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 2, characterized in that: Perform linear fitting on the test pulp concentration set and the pulp addition amount set to obtain a pulp addition amount model; The test pulp concentration set and the water addition amount set were linearly fitted to obtain the water addition amount model.

4. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 2, characterized in that: The establishment of the stirring model comprises the following steps: Obtain the number of storage tanks n, the storage capacity q of the storage tanks and the discharge time t of each storage tank, where (the number of storage tanks n-1) × the storage capacity q of the storage tank = the standard holding capacity v of the mixing barrel; The residence time of water and pulp in the mixing barrel is calculated as T = (the number of storage tanks n-1) × the discharge time t of each storage tank; The concentrations of water and pulp in the stirring barrel are measured to obtain the stirring time of the stirring barrel stirrer at the test pulp concentration.

5. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 3, characterized in that: The method for determining the stirring time of the stirring drum agitator to reach the test pulp concentration is as follows: Obtain the stirring time jx of the stirrer when the pulp and water mixture in the stirring barrel reaches the test pulp concentration, and obtain its set as [j1, j2, ..., jN]; The test pulp concentration set and the stirring time set of the stirrer are linearly fitted to obtain the stirring time model of the stirrer.

6. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 5, characterized in that: The method for establishing the refining model of the refiner is as follows: Subtract the residence time T of water and pulp in the mixing barrel from the stirring time jx of the agitator under the test pulp concentration to obtain a set of gap times, calculate the average of the gap times, and obtain the average gap time X; Obtain the power consumption per unit time of the refiner P1 and the power consumption per unit time of the agitator P2, and calculate P1 / P2=k, (k<1); If the average gap time X>2×the stirring time jx of the agitator at the test pulp concentration, the target refining time tx of the refiner = jx / (k×2); If the stirring time jx of the stirrer at the test pulp concentration is ≤ the average gap time X ≤ 2× the stirring time jx of the stirrer at the test pulp concentration, the target stirring time tx of the stirrer is = k×P2×jx / (P1×2.5); If the average gap time X < the stirring time jx of the agitator under the test pulp concentration, the target refining time tx of the refiner = k×P2×jx / (P1×3).

7. The method for controlling pulp concentration in an intelligent production line based on an AI algorithm according to claim 4, characterized in that: The method further comprises: Determine the maneuvering time b for the mixing barrel to replenish the storage tank, and calculate the residence time of water and pulp in the mixing barrel T = (the number of storage tanks n-1) × the discharge time t of each storage tank - the maneuvering time b.

8. A pulp concentration intelligent production line control system based on AI algorithm, using the pulp concentration intelligent production line control method according to any one of claims 1 to 7, characterized in that: include: The data acquisition module acquires the data of pulp concentration detected by each detector in the mixing barrel, the number of storage tanks n, the storage volume q of the storage tanks, the discharge time t of each storage tank, and the maneuvering time b of the mixing barrel to replenish the storage tank; A calculation module is provided to establish a feeding model, obtain the pulp addition amount and water addition amount under the test pulp concentration and the standard containing volume v, obtain a pulp addition amount model and a water addition amount model based on the feeding model, input the target concentration into the pulp addition amount model and the water addition amount model, respectively obtain the target pulp addition amount and the target water addition amount, establish a stirring model, obtain a stirring time model of the stirrer, input the target concentration into the stirring time model of the stirrer, obtain the target stirring time of the stirring barrel stirrer, establish a refining model, input the target concentration into the refining model, and obtain the target refining time of the refiner; The AI ​​algorithm module is based on deep learning and training of the model in the calculation module to achieve intelligent production line control of pulp concentration.

Images