Mud treatment formula online adjustment method and device based on radar belt weigher

Abstract

The invention relates to the technical field of mud treatment in solid waste recovery, in particular to a mud treatment formula online adjusting method and device based on a radar belt weigher. The invention discloses a radar belt scale-based mud treatment formula online adjustment method. The method comprises the following steps of S1, acquiring raw material characteristics; s2, constructing a prediction model; s3, production line application; and S4, formula adjustment and optimization. According to the invention, the dosage of the curing agent and the admixture is dynamically adjusted according to the real-time feeding amount, the curing effect and the product quality are improved, the dynamic adjustment of the formula, the accurate control of the formula, the reduction of the waste of the curing agent and the admixture and the reduction of the production cost are realized, and the feedback and optimization module is arranged to dynamically adjust the formula according to the curing effect. The mud treatment quality and consistency are further improved, the problems of abrasion and errors of a traditional contact type sensor are solved through the arranged radar belt scale, and the feeding amount detection precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sludge treatment in solid waste recycling, and particularly to an online adjustment method and device for a sludge treatment formula based on a radar belt scale. Background Art

[0002] In the field of solid waste recycling and reuse, especially in the curing granulation production process in the sludge treatment field, the accurate control of the muck feed rate and formula is a key factor affecting the quality of the final product. Traditional curing granulation systems usually adopt a feeding method of timed feeding. The distribution of muck on the belt is affected by the transfer machine and is usually uneven. Timed feeding cannot obtain the feed rate information in real time and accurately. Traditional formula adjustment methods cannot dynamically adjust the dosages of curing agents and admixtures according to the real-time feed rate, resulting in unstable curing effects, uneven product quality, low automation degree, and often causing waste of curing agents and admixtures due to the inability to accurately control the formula, increasing the production cost. Summary of the Invention

[0003] Other features and advantages of the present invention will be described in the following specification, and will be partially obvious from the specification, or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the specification and other specification drawings.

[0004] The objective of the present invention is to overcome the above deficiencies, and provide an online adjustment method and device for a sludge treatment formula based on a radar belt scale, which dynamically adjusts the dosages of curing agents and admixtures according to the real-time feed rate, ensures the accurate matching of the sludge treatment formula, improves the curing effect and product quality, realizes dynamic adjustment of the formula and accurate control of the formula, reduces the waste of curing agents and admixtures, reduces the production cost, and sets up a feedback and optimization module to dynamically adjust the formula according to the curing effect, further improving the quality and consistency of sludge treatment. The set radar belt scale can accurately measure the flow rate and weight of muck raw materials with different distributions on the conveyor belt in a non-contact manner, avoiding the wear and error problems of traditional contact sensors and improving the detection accuracy of the feed rate.

[0005] The present invention provides an online adjustment method for a sludge treatment formula based on a radar belt scale, including: S1. Obtain raw material characteristics: During the process of the radar belt scale transporting raw materials, extract the raw material characteristics according to the raw material data. The raw material characteristics specifically include the mass of the soil body and the mass of the water body; S2. Construct a prediction model: Construct a prediction model for the sludge treatment production formula based on a neural network, and train the prediction model with training data to obtain a mature prediction model for the sludge treatment production formula. The training data is an array formed by the screened raw material characteristics and the corresponding production formula data; S3. Production line application: Input the raw material characteristics obtained during the production process of the production line into the mature prediction model for the mud treatment production formula to obtain the predicted value of the production formula, and determine whether the strength of the recycled material obtained meets the standard; S4. Formula adjustment and optimization: If the strength of the produced recycled material meets the standard, proceed to the subsequent production steps. If the strength of the produced recycled material does not meet the standard, trace the production formula of the corresponding batch of recycled material, adjust the production formula, and use it as training data to be verified again through the prediction model, and optimize until the strength of the produced recycled material meets the standard.

[0006] In some embodiments, in step S1, the specific steps for obtaining the mass of the soil body and the mass of the water body are as follows: S11. Obtain the mass distribution data of the muck raw materials and the water content distribution data of the muck raw materials on the radar belt scale; S12. Obtain the displacement data of the belt; S13. Obtain the mass of the soil body through the mass distribution data of the muck raw materials and the displacement data, and obtain the mass of the water body through the water content distribution data of the muck raw materials and the displacement data.

[0007] In some embodiments, in step S2, the specific steps for screening the training data are as follows: Judge the strength of the recycled material after solidification granulation to determine whether it meets the specified standard, screen out the recycled material that meets the strength requirements, trace the corresponding historical production raw material characteristics and historical production formula data, and when the raw material characteristics of multiple batches of recycled materials are the same, select the historical production formula data of the corresponding batch with the highest strength of the recycled material as the training data.

[0008] In some embodiments, in step S2, the production formula data specifically includes the mass of the curing agent, the mass of the admixture, and the mass of tap water produced by the granulator in one production.

[0009] In some embodiments, in step S2, the prediction model for the mud treatment production formula uses a fully connected neural network. The specific structure of the fully connected neural network includes an input layer, a first hidden layer, a second hidden layer, and an output layer. Among them, the number of neurons in the first hidden layer is 64, the number of neurons in the second hidden layer is 32, the activation function is ReLU, and the number of neurons in the output layer = the number of types of curing agents + the number of types of admixtures + 1.

[0010] In some embodiments, the optimizer in the training process of the fully connected neural network uses the Adam optimizer, and the loss function uses the mean absolute error evaluation.

[0011] An on-line adjustment device for the mud treatment formula based on a radar belt scale, the device includes: A conveyor belt for transporting raw materials; A high-precision radar belt scale is provided on the conveyor belt and is used to measure the mass distribution data of the muck raw materials on the conveyor belt; A water content detection component is provided on the conveyor belt and is used to detect the water content of the raw materials; A ranging component is provided on the conveyor belt and is used to collect the displacement data of the conveyor belt in real time. The ranging component includes a meter wheel and an encoder; A control center is electrically connected to the high-precision radar belt scale, the water content detection component, and the ranging component.

[0012] In some embodiments, the control center includes a raw material detection module, a model construction module, a formula adjustment module, and a feedback and optimization module. The raw material detection module stores the data obtained from the high-precision radar belt scale, the water content detection component, and the ranging component and integrates the data to obtain raw material characteristics. The model construction module uses training data to train a prediction model to form a mature prediction model for the mud treatment production formula. The formula adjustment module stores the mature prediction model for the mud treatment production formula. After inputting an array, it outputs the predicted value of the production formula. According to the predicted formula, the curing agent, admixture, and tap water are accurately dosed. The feedback and optimization module obtains the strength data of the cured granulated recycled material after curing through a strength detector and feeds the data back to the model construction module.

[0013] By adopting the above technical solutions, the beneficial effects of the present invention are as follows: The present invention establishes an online adjustment method for the mud treatment formula based on a radar belt scale, dynamically adjusts the dosages of the curing agent and admixture according to the real-time feeding amount, ensures the accurate matching of the mud treatment formula, improves the curing effect and product quality, realizes the dynamic adjustment of the formula and the precise control of the formula, reduces the waste of the curing agent and admixture, reduces the production cost, and sets a feedback and optimization module to dynamically adjust the formula according to the curing effect, further improving the quality and consistency of the mud treatment. The provided radar belt scale can accurately measure the flow rate and weight of the muck raw materials with different distributions on the conveyor belt in a non-contact manner, avoiding the wear and error problems of traditional contact sensors and improving the detection accuracy of the feeding amount.

[0014] It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present disclosure.

[0015] Undoubtedly, such objects of the present invention and other objects will become more apparent after the details of the preferred embodiments described in the following with multiple drawings and illustrations.

[0016] To make the above and other objects, features, and advantages of the present invention more obvious and understandable, the following specifically gives one or several preferred embodiments and, in conjunction with the shown drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention.

[0018] In the drawings, the same components are denoted by the same reference numerals, and the drawings are schematic and not necessarily drawn to scale.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only one or several embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on such drawings.

[0020] Figure 1 Schematic diagram of the overall process of the formula online adjustment method in some embodiments of the present invention; Figure 2 Schematic diagram of the internal process of the control center in some embodiments of the present invention; Figure 3 Schematic diagram of the internal structure of the readable medium in some embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the following further describes the present invention in detail in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0022] In addition, in the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "axial", "radial", "circumferential", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0023] In the present invention, unless otherwise clearly defined or limited, terms such as "installed", "connected", "linked", "fixed", etc. shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two components or the interaction relationship between two components. However, indicating a direct connection means that there is no connection relationship constructed through a transition structure between the two connected main bodies, and they are only connected through the connection structure to form a whole. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] In the present invention, unless otherwise clearly defined or limited, the first feature being "above" or "below" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0025] Refer to Figure 1 , Figure 1 is a schematic diagram of the overall process of the formula online adjustment method in some embodiments of the present invention.

[0026] According to some embodiments of the present invention, the present invention provides an online adjustment method for the mud treatment formula based on a radar belt scale, which is characterized by including: S1. Obtain raw material characteristics: During the process of the radar belt scale transporting raw materials, extract the raw material characteristics according to the raw material data, and the raw material characteristics specifically include the soil mass and the water mass; The specific steps for obtaining the soil mass and the water mass are: S11. Obtain the mass distribution data of the muck raw materials and the water content distribution data of the muck raw materials on the radar belt scale; S12. Obtain the displacement data of the belt; S13. Obtain the soil mass through the mass distribution data of the muck raw materials and the displacement data, and obtain the water mass through the water content distribution data of the muck raw materials and the displacement data.

[0027] S2. Build a prediction model: Build a prediction model for the mud treatment production formula based on a neural network. Use the training data to train the prediction model to obtain a mature prediction model for the mud treatment production formula. The training data is an array formed by the screened raw material characteristics and the corresponding production formula data. The production formula data specifically includes the mass of the curing agent, the mass of the admixture, and the mass of tap water produced by the granulator in one production. The types of the curing agent and the admixture are determined by the formula used in the actual production process. The prediction model for the mud treatment production formula uses a fully connected neural network. The specific structure of the fully connected neural network includes an input layer, a first hidden layer, a second hidden layer, and an output layer. Among them, the number of neurons in the first hidden layer is 64, the number of neurons in the second hidden layer is 32, the activation function is ReLU, and the number of neurons in the output layer = the number of types of curing agents + the number of types of admixtures + 1; The optimizer used in the training process of the fully connected neural network is the Adam optimizer, and the loss function uses the mean absolute error for evaluation. The specific steps for screening the training data are as follows: Judge the strength of the recycled material after curing and granulation to determine whether it meets the specified standard. Screen out the recycled materials that meet the strength requirements, and trace their corresponding historical production raw material characteristics and historical production formula data. When the raw material characteristics of multiple batches of recycled materials are the same, select the historical production formula data of the corresponding batch with the highest strength of the recycled material as the training data. S3. Application in the production line: Input the raw material characteristics obtained during the production process of the production line into the mature prediction model for the mud treatment production formula to obtain the predicted value of the production formula, and judge whether the strength of the obtained recycled material meets the standard. S4. Formula adjustment and optimization: If the strength of the produced recycled material meets the standard, enter the subsequent production steps. If the strength of the produced recycled material does not meet the standard, trace the production formula of the corresponding batch of recycled materials, adjust the production formula and use it as training data to verify through the prediction model again, and optimize until the strength of the produced recycled material meets the standard; The strength data is obtained by the producer through a strength detector.

[0028] Refer to Figure 2 , Figure 2 It is a schematic diagram of the internal process of the control center in some embodiments of the present invention.

[0029] According to some embodiments of the present invention, optionally, the present invention further provides an on-line adjustment device for the mud treatment formula based on a radar belt scale. The device includes: A conveyor belt for transporting raw materials. A high-precision radar belt scale is installed on the conveyor belt and is used to measure the mass distribution data of the muck raw materials on the conveyor belt. The radar belt scale can accurately measure the flow rate and weight of the muck raw materials with different distributions on the conveyor belt in a non-contact manner, avoiding the wear and error problems of traditional contact sensors. A water content detection component is installed on the conveyor belt and is used to detect the water content of the raw materials. A ranging component is installed on the conveyor belt and is used to collect the displacement data of the conveyor belt in real time. The ranging component includes a length measuring wheel and an encoder. A control center is electrically connected to the high-precision radar belt scale, the water content detection component, and the ranging component. The control center includes a raw material detection module, a model construction module, a formula adjustment module, and a feedback and optimization module. The raw material detection module stores the data obtained from the high-precision radar belt scale, the water content detection component, and the ranging component, integrates the data to obtain raw material characteristics, and transmits the data to the formula adjustment system module. The model construction module trains the prediction model with training data to form a mature prediction model for the mud treatment production formula. The formula adjustment module stores the mature prediction model for the mud treatment production formula, outputs the predicted value of the production formula after inputting the array, and at the same time accurately dispenses the curing agent, admixture, and tap water according to the predicted formula to realize the real-time adjustment of the formula. The feedback and optimization module obtains the strength data of the cured granulated recycled material after curing through a strength detector and feeds the data back to the model construction module. The model construction module dynamically optimizes the formula prediction model according to the updated training data to further improve the quality and stability of the mud treatment and curing granulation.

[0030] Refer to Figure 3 , Figure 3 which is a schematic internal structure diagram of a readable medium in some embodiments of the present invention.

[0031] According to some embodiments of the present invention, optionally, the invention further provides a computer-readable storage medium, on which a computer program is stored. The program applies the above-mentioned online adjustment method for the mud treatment formula based on a radar belt scale. The internal structure of the computer-readable storage medium is as Figure 3 shown.

[0032] It should be understood that the embodiments disclosed in the present invention are not limited to the specific processing steps or materials disclosed herein, but should extend to equivalent alternatives of such features understood by those of ordinary skill in the relevant art. It should also be understood that the terms used herein are only for the purpose of describing specific embodiments and do not mean to limit.

[0033] As used in the specification, "embodiment" means that a particular feature or characteristic described in connection with an embodiment is included in at least one embodiment of the present invention. Thus, the phrase "an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment.

[0034] In addition, the described features or characteristics may be combined in any other suitable manner in one or more embodiments. In the above description, some specific details such as thickness, quantity, etc. are provided to provide a comprehensive understanding of the embodiments of the present invention. However, those skilled in the relevant art will understand that the present invention can be implemented without one or more of the above specific details or can also be implemented using other methods, components, materials, etc.

Claims

1. A method for online adjustment of mud treatment formula based on radar belt scale, characterized in that: include S1. Obtaining raw material characteristics: During the process of conveying raw materials by radar belt scale, the raw material characteristics are extracted according to the raw material data, and the raw material characteristics specifically include soil quality and water quality; S2. Constructing a prediction model: constructing a prediction model for mud treatment production formula based on a neural network, using training data to train the prediction model, and obtaining a mature mud treatment production formula prediction model, wherein the training data is an array formed by combining the screened raw material characteristics and the corresponding production formula data; S3. Production line application: Input the raw material characteristics obtained during the production process of the production line into the mature mud treatment production formula prediction model to obtain the production formula prediction value and determine whether the strength of the recycled material obtained meets the standard; S4. Formula adjustment and optimization: If the strength of the produced recycled materials meets the standards, the subsequent production steps will be entered. If the strength of the produced recycled materials does not meet the standards, the production formula of the corresponding batch of recycled materials will be traced, the production formula will be adjusted and used as training data to verify the prediction model again, and the optimization will be carried out until the strength of the produced recycled materials meets the standards.

2. The method for online adjustment of mud treatment formula based on radar belt scale according to claim 1 is characterized in that: In step S1, the specific steps for obtaining soil mass and water mass are: S11, obtaining the mass distribution data of the slag raw material and the moisture content distribution data of the slag raw material on the radar belt scale; S12, obtaining displacement data of the belt; S13. Obtain soil quality through mass distribution data and displacement data of slag raw materials, and obtain water quality through moisture content distribution data and displacement data of slag raw materials.

3. The method for online adjustment of mud treatment formula based on radar belt scale according to claim 1 is characterized in that: In step S2, the specific steps for screening the training data are: judging the strength of the recycled materials after solidification and granulation to determine whether they meet the specified standards, screening out the recycled materials that meet the strength requirements, tracing back their corresponding historical production raw material characteristics and historical production formula data, and when there are multiple batches of recycled materials with the same raw material characteristics, selecting the corresponding batch of historical production formula data with the highest recycled material strength as training data.

4. The method for online adjustment of mud treatment formula based on radar belt scale according to claim 1 is characterized in that: In step S2, the production formula data specifically includes the quality of the curing agent, the quality of the admixture and the quality of the tap water produced by the granulator at one time.

5. The method for online adjustment of mud treatment formula based on radar belt scale according to claim 4 is characterized in that: In step S2, the mud treatment production formula prediction model adopts a fully connected neural network. The specific structure of the fully connected neural network includes an input layer, a first hidden layer, a second hidden layer, and an output layer. The number of neurons in the first hidden layer is 64, the number of neurons in the second hidden layer is 32, the activation function is ReLU, and the number of neurons in the output layer = the number of curing agent types + the number of admixture types + 1.

6. The method for online adjustment of mud treatment formula based on radar belt scale according to claim 5 is characterized in that: The optimizer used in the fully connected neural network training process is the Adam optimizer, and the loss function is evaluated using the mean absolute error.

7. A mud treatment formula online adjustment device based on radar belt scale, characterized in that: The method for adjusting mud treatment formula online based on radar belt scale according to any one of claims 1 to 6 is applied, and the device comprises Conveyor belts, which are used to transfer raw materials; A high-precision radar belt scale, which is arranged on the conveyor belt and used to measure the mass distribution data of the slag raw material on the conveyor belt; A moisture content detection component is arranged on the conveyor belt and is used to detect the moisture content of the raw material; A distance measuring component is arranged on the conveyor belt and is used to collect displacement data of the conveyor belt in real time, and the distance measuring component includes a meter wheel and an encoder; A control center is electrically connected to the high-precision radar belt scale, the moisture content detection component and the distance measurement component.

8. The on-line adjustment device for mud treatment formula based on radar belt scale according to claim 7 is characterized in that: The control center includes a raw material detection module, a model building module, a formula adjustment module and a feedback and optimization module. The raw material detection module stores the data obtained from the high-precision radar belt scale, the moisture content detection component and the ranging component, and integrates the data to obtain the raw material characteristics. The model building module uses the training data to train the prediction model to form a mature mud treatment production formula prediction model. The formula adjustment module stores a mature mud treatment production formula prediction model, outputs the predicted value of the production formula after inputting the array, and accurately adds the curing agent, admixture and tap water according to the predicted formula. The feedback and optimization module obtains the strength data of the cured granulated recycled material after curing through the strength detector, and feeds the data back to the model building module.

Images