Intelligent biodiesel batching system and working method

Abstract

The intelligent biodiesel batching system comprises a batching storage bin, a metering assembly, a control module, a data acquisition module, a data preprocessing module, an optimization module, a control module and a batching mixing module, the metering assembly is connected with the ingredient storage bin, the data acquisition module is connected with sensors in all the assemblies, and the data acquisition module is used for acquiring data in the production process in real time; the optimization module is connected with the preprocessing module, and the optimization module generates a prediction model by using the historical sample data; the optimization module is used for determining an optimal ingredient ratio; the control module is respectively connected with the optimization module, the metering assembly and the ingredient mixing module; the optimization module provides the optimal ingredient ratio for the control module, the metering assembly is used for controlling the discharging amount of the ingredient storage bin, and the ingredient mixing module is used for mixing ingredients. By setting the machine learning module and the optimization module, the batching system generates a quality prediction model by using historical sample data.

Description

Technical Field

[0001] The invention relates to the field of biodiesel, and in particular to a biodiesel intelligent batching system and a working method. Background Art

[0002] In the existing biodiesel process, in the existing production, the existing production equipment cannot monitor and adjust the input amount of raw materials in real time, which makes it difficult to achieve personalized intelligent regulation under different parameters. The traditional ingredient ratio mainly relies on experiments and manual experience, lacking targeted ratio combinations according to specific scenarios and environments, resulting in inaccurate raw material ratios, affecting the performance of the final biodiesel. At the same time, since the production process of biodiesel has high requirements for the processing of raw materials, the traditional process does not take into account the differences in raw materials and cannot adjust the formula in time, resulting in large fluctuations in the quality of biodiesel production. Therefore, in order to solve the above problems, a biodiesel intelligent ingredient system and working method are needed. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention proposes a biodiesel intelligent batching system and a working method, wherein a specific technical scheme of a biodiesel intelligent batching system is as follows:

[0004] A biodiesel intelligent batching system, characterized by:

[0005] It includes a batching storage bin, a metering component, a control module, a data acquisition module, a data preprocessing module, an optimization module, a control module and a batching mixing module;

[0006] The metering component is connected to the ingredient storage bin, and the data acquisition module is connected to the sensors in each component, and the data acquisition module is used to collect data in the production process in real time;

[0007] The optimization module is connected to the preprocessing module, and the optimization module generates a prediction model using historical sample data;

[0008] The optimization module is used to determine the optimal ingredient ratio;

[0009] The control module is respectively connected with the optimization module, the metering component and the ingredient mixing module;

[0010] The optimization module provides the optimal ingredient ratio to the control module, the metering component is used to control the amount of material discharged from the ingredient storage bin, and the ingredient mixing module is used to mix the ingredients.

[0011] In order to better realize the present invention, it can be further:

[0012] The data preprocessing module is used for cleaning, normalizing and feature extraction of collected data.

[0013] Further:

[0014] The optimization module adopts a Bayesian model.

[0015] Further:

[0016] The ingredient storage bin includes a plurality of storage units, each of which has an independent discharge port, and each of which is connected to a group of metering components.

[0017] Among them, a specific technical scheme of the working method of a biodiesel intelligent batching system is as follows:

[0018] A working method of a biodiesel intelligent batching system, characterized by:

[0019] The steps include:

[0020] S1: The data acquisition module collects production data in real time, and sends the collected production data to the data preprocessing module;

[0021] S2: the data preprocessing module preprocesses the collected production data, and the data preprocessing module inputs the preprocessed production data into the optimization module;

[0022] S3: The optimization module is provided with a prediction model trained by using samples, and the optimization module selects preset ingredients based on production data;

[0023] S4: The prediction model adopts a Bayesian optimization model, and the optimization module takes the preset ingredients as the starting point and gradually adjusts the ratio to obtain the optimal ingredient ratio;

[0024] S5: The control module controls the corresponding metering component according to the optimized optimal ingredient ratio, and the metering component realizes the quantitative delivery of the corresponding ingredients, so that each ingredient enters the ingredient mixing module according to the optimized ratio;

[0025] S6: The ingredient mixing module mixes different ingredients to generate final biodiesel.

[0026] In order to better realize the present invention, it can be further:

[0027] The S3 comprises the following steps:

[0028] S3-1: The data preprocessing module preprocesses the collected production data to obtain an input vector B;

[0029] S3-2: The input vector B includes a batching ratio vector x, a material parameter vector a and an environmental parameter vector e. The optimization module optimizes the biodiesel index y through a Bayesian optimization model.p :

[0030] y p =f(B)

[0031] Among them, the input vector B = [x, a, e]

[0032] x=[x1,x2,...,x n ] indicates the ingredient ratio;

[0033] a=[a1,a2,...,a n ] indicates material parameters;

[0034] e=[e1,e2,...,e m ] represents environmental parameters;

[0035] Further:

[0036] The S4 comprises the following steps:

[0037] S4-1: Select historical samples as training data set, which includes samples x0, x1, ..., x n and the corresponding indices y0,y1,...,y n ;

[0038] S4-2: The Bayesian model uses a Gaussian process as a proxy model to perform modeling using a training data set;

[0039] S4-3: The Bayesian model finds matching data covering different combinations in the defined search space, and the Bayesian model calculates the expected improvement function EI(x) for each matching combination found;

[0040] Where EI(x) = E[max(0,y(x)-y b )];

[0041] y(x) is the predicted value of the indicator of the current input vector;

[0042] y b is the best indicator value currently known;

[0043] S4-4: The Bayesian model finds the maximum EI(x) and obtains the improved matching vector x in the current search space i ;

[0044] S4-5: Improve the matching vector x i Add to the training data set and repeat the process from S4-1 to S4-5 until the optimal matching vector x is found p .

[0045] The beneficial effects of the present invention are as follows: the present invention sets a machine learning module and an optimization module, and the batching system generates a quality prediction model using historical sample data, and determines the optimal batching ratio based on real-time collected production data and a Bayesian optimization model. The optimization module uses Bayesian optimization to gradually adjust the ratio through an algorithm to obtain the optimal batching ratio. The data acquisition module is combined with the control module to realize fully automated batching control and achieve adaptive regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is the overall block diagram of the present invention;

[0047] Figure 2 It is the work flow chart of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] In the description of the present invention, it should be noted that the terms "vertical", "upper", "lower", "horizontal", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present invention. In addition, "first", "second", "third", and "fourth" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] like Figure 1 As shown:

[0051] A biodiesel intelligent batching system, comprising a batching storage bin, a metering component, a control module, a data acquisition module, a data preprocessing module, an optimization module, a control module and a batching mixing module;

[0052] The data preprocessing module is used for cleaning, normalizing and feature extraction of the collected data.

[0053] The metering component is connected to the ingredient storage bin, and the data acquisition module is connected to the sensors in each component, and the data acquisition module is used to collect data in the production process in real time;

[0054] Specifically, the ingredient storage bin includes a plurality of storage units, each of the storage units has an independent discharge port, and each of the storage units is connected to a group of metering components.

[0055] The optimization module is connected to the preprocessing module, and the optimization module generates a prediction model using historical sample data;

[0056] The optimization module adopts a Bayesian model, and the optimization module is used to determine the optimal ingredient ratio;

[0057] The control module is respectively connected with the optimization module, the metering component and the ingredient mixing module;

[0058] The optimization module provides the optimal ingredient ratio to the control module, the metering component is used to control the amount of material discharged from the ingredient storage bin, and the ingredient mixing module is used to mix the ingredients.

[0059] like Figure 2 As shown:

[0060] Among them, a specific technical scheme of the working method of a biodiesel intelligent batching system is as follows:

[0061] A working method of a biodiesel intelligent batching system, characterized by:

[0062] The steps include:

[0063] S1: The data acquisition module collects production data in real time, and sends the collected production data to the data preprocessing module;

[0064] S2: the data preprocessing module preprocesses the collected production data, and the data preprocessing module inputs the preprocessed production data into the optimization module;

[0065] S3: The optimization module is provided with a prediction model trained by using samples, and the optimization module selects preset ingredients based on production data.

[0066] Wherein, the S3 comprises the following steps:

[0067] S3-1: The data preprocessing module preprocesses the collected production data to obtain an input vector B;

[0068] S3-2: The input vector B includes a batching ratio vector x, a material parameter vector a and an environmental parameter vector e. The optimization module optimizes the biodiesel index y through a Bayesian optimization model. p :

[0069] y p =f(B)

[0070] Among them, the input vector B = [x, a, e]

[0071] x=[x1,x2,...,x n ] indicates the ingredient ratio;

[0072] a=[a1,a2,...,a n ] indicates material parameters;

[0073] e=[e1,e2,…,e m ] represents environmental parameters;

[0074] S4: The prediction model adopts a Bayesian optimization model, and the optimization module takes the preset ingredients as the starting point and gradually adjusts the ratio to obtain the optimal ingredient ratio;

[0075] Wherein, the S4 comprises the following steps:

[0076] S4-1: Select historical samples as training data set, which includes samples x0, x1, ..., x n and the corresponding indices y0,y1,...,y n ;

[0077] S4-2: The Bayesian model uses a Gaussian process as a proxy model to perform modeling using a training data set;

[0078] S4-3: The Bayesian model finds matching data covering different combinations in the defined search space, and the Bayesian model calculates the expected improvement function EI(x) for each matching combination found;

[0079] Where EI(x) = E[max(0,y(x)-y b )];

[0080] y(x) is the predicted value of the indicator of the current input vector;

[0081] y b is the best indicator value currently known;

[0082] S4-4: The Bayesian model finds the maximum EI(x) and obtains the improved matching vector x in the current search space i ;

[0083] S4-5: Improve the matching vector x i Add to the training data set and repeat the process from S4-1 to S4-5 until the optimal matching vector x is found p .

[0084] S5: The control module controls the corresponding metering component according to the optimized optimal ingredient ratio, and the metering component realizes the quantitative delivery of the corresponding ingredients, so that each ingredient enters the ingredient mixing module according to the optimized ratio;

[0085] S6: The ingredient mixing module mixes different ingredients to generate final biodiesel.

[0086] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0087] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A biodiesel intelligent batching system, characterized by: It includes a batching storage bin, a metering component, a control module, a data acquisition module, a data preprocessing module, an optimization module, a control module and a batching mixing module; The metering component is connected to the ingredient storage bin, and the data acquisition module is connected to the sensors in each component, and the data acquisition module is used to collect data in the production process in real time; The optimization module is connected to the preprocessing module, and the optimization module generates a prediction model using historical sample data; The optimization module is used to determine the optimal ingredient ratio; The control module is respectively connected with the optimization module, the metering component and the ingredient mixing module; The optimization module provides the optimal ingredient ratio to the control module, the metering component is used to control the amount of material discharged from the ingredient storage bin, and the ingredient mixing module is used to mix the ingredients.

2. According to claim 1, a biodiesel intelligent batching system is characterized by: The data preprocessing module is used for cleaning, normalizing and feature extraction of collected data.

3. A biodiesel intelligent batching system according to claim 2, characterized in that: The optimization module adopts a Bayesian model.

4. A biodiesel intelligent batching system according to claim 3, characterized in that: The ingredient storage bin includes a plurality of storage units, each of which has an independent discharge port, and each of which is connected to a group of metering components.

5. A working method of a biodiesel intelligent batching system according to any one of claims 1 to 4, characterized in that: The steps include: S1: The data acquisition module collects production data in real time, and sends the collected production data to the data preprocessing module; S2: the data preprocessing module preprocesses the collected production data, and the data preprocessing module inputs the preprocessed production data into the optimization module; S3: The optimization module is provided with a prediction model trained by using samples, and the optimization module selects preset ingredients based on production data; S4: The prediction model adopts a Bayesian optimization model, and the optimization module takes the preset ingredients as the starting point and gradually adjusts the ratio to obtain the optimal ingredient ratio; S5: The control module controls the corresponding metering component according to the optimized optimal ingredient ratio, and the metering component realizes the quantitative delivery of the corresponding ingredients, so that each ingredient enters the ingredient mixing module according to the optimized ratio; S6: The ingredient mixing module mixes different ingredients to generate final biodiesel.

6. A method for intelligently proportioning biodiesel according to any one of claims 7, characterized in that: The S3 comprises the following steps: S3-1: The data preprocessing module preprocesses the collected production data to obtain an input vector B; S3-2: The input vector B includes a batching ratio vector x, a material parameter vector a and an environmental parameter vector e. The optimization module optimizes the biodiesel index y through a Bayesian optimization model. p : y p =f(B) Among them, the input vector B = [x, a, e] x=[x1,x2,...,x n ] indicates the ingredient ratio; a=[a1,a2,...,a n ] indicates material parameters; e=[e1,e2,...,e m ] indicates environmental parameters.

7. The adaptive batching control system and working method according to claim 6, characterized in that: The S4 comprises the following steps: S4-1: Select historical samples as training data set, which includes samples x0, x1, ..., x n and the corresponding indices y0,y1,...,y n ; S4-2: The Bayesian model uses a Gaussian process as a proxy model to perform modeling using a training data set; S4-3: The Bayesian model finds matching data covering different combinations in the defined search space, and the Bayesian model calculates the expected improvement function EI(x) for each matching combination found; Where EI(x) = E[max(0,y(x)-y b )]; y(x) is the indicator prediction value of the current input vector; y b is the best indicator value currently known; S4-4: The Bayesian model finds the maximum EI(x) and obtains the improved matching vector x in the current search space i ; S4-5: Improve the matching vector x i Add to the training data set and repeat the process from S4-1 to S4-5 until the optimal matching vector x is found p .

Images