Soft measurement method for granularity of common powder in production process of high-temperature electrical-grade magnesium oxide powder

Abstract

The invention discloses a common powder granularity soft measurement method in a production process of high-temperature electrical-grade magnesium oxide powder. The method comprises the following steps: establishing a sample set; standardizing the sample data, performing dimension reduction processing by using a PCA method, and eliminating a redundant relationship between auxiliary variables; an XGBoost modeling method is adopted, an initialized objective function considering a loss function and model complexity is established for the kth output variable, and second-order Taylor expansion is utilized to transform the objective function; defining a decision tree, introducing the structure of the tree into a target function, constructing an optimal tree by using a greedy algorithm, repeating the process for tk times, finally generating tk decision trees, and obtaining an ideal soft measurement model; according to the ideal model, the outputs of the decision trees are added together to serve as the prediction output of the common powder granularity soft measurement result in the production process of the high-temperature electrical-grade magnesium oxide powder; and correcting the ideal model for the soft measurement of the common powder granularity by adopting a method of combining deviation compensation correction and instant learning. According to the soft measurement model correction method, online real-time correction can be carried out on the soft measurement model, and the soft measurement model correction method has self-adaptive capacity to change of working conditions.

Description

Technical Field

[0001] The invention relates to the field of advanced control technology for a high-temperature electrical grade magnesium oxide powder production process, in particular to a general powder particle size soft measurement method for a high-temperature electrical grade magnesium oxide powder production process. Background Art

[0002] Fused magnesium oxide crushing and screening is an important process in the production of high-temperature electrical grade magnesium oxide powder. It crushes larger blocky fused magnesium oxide into finer powder, and then screens out fused magnesium oxide powder with a suitable particle size range for subsequent high-temperature calcination and modification processes.

[0003] The crushing and screening process of fused magnesium oxide is as follows: Figure 1 As shown. The vibrating feeder feeds the blocky fused magnesium oxide into the hammer crusher for crushing. The crushed fused magnesium oxide powder is sent to a high place by a bucket elevator and then sent to the vibrating screen. The vibrating screen classifies the fused magnesium oxide powder according to the particle size. The coarser particles are returned to the hammer crusher for further crushing, and the finer particles are collected by the bag. The particles with the appropriate particle size enter the airflow classifier for further screening. The airflow classifier further screens the fused magnesium oxide powder with the appropriate particle size. The coarser particles are used as the fused magnesium oxide powder with the appropriate particle size. They are sent to a high place by a bucket elevator for magnetic separation and iron removal, and then collected and sent to the high-temperature furnace calcination process. The other part of the finer particles are collected after screening by the collector, and the remaining very small part of the finer powder is collected by the electric dust collector.

[0004] The quality index reflecting the crushing and screening process of fused magnesium oxide is the particle size distribution of the fused magnesium oxide powder collected after magnetic separation and iron removal (the mass fraction distributed in the range of +35 mesh, -35 mesh to +325 mesh, -325 mesh), also known as "general powder particle size". At present, the general powder particle size detection method of high-temperature electrical grade magnesium oxide powder production enterprises is: manually sample the fused magnesium oxide powder once every half an hour, and use a slap-type standard vibrating screen machine to perform offline detection on the sample to obtain the general powder particle size. This detection method has the problems of too long sampling cycle and large lag, which makes it difficult to provide timely guidance for production, and also hinders the implementation of advanced control.

[0005] With the development of science and technology, soft measurement technology provides a feasible solution for the online measurement of general powder particle size. Establishing a soft measurement method for general powder particle size with strong generalization ability and measuring the general powder particle size online are of great significance for stabilizing the production of the crushing and screening process and implementing advanced control of the crushing and screening process. Summary of the invention

[0006] In view of the problem that the general powder particle size cannot be detected online during the production process of high-temperature electrical grade magnesium oxide powder, the technical problem to be solved by the present invention is to provide a soft measurement method for the general powder particle size in the production process of high-temperature electrical grade magnesium oxide powder, which can continuously give the general powder particle size measurement value online, has strong generalization ability and is adaptable.

[0007] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0008] A soft measurement method for the general powder particle size in the production process of high-temperature electrical grade magnesium oxide powder is provided. The following steps are performed to obtain an ideal soft measurement model and perform real-time correction, which is used for soft measurement prediction of the unknown general powder particle size in the production process of unknown high-temperature electrical grade magnesium oxide powder. The method comprises the following steps:

[0009] Establish a sample set: select auxiliary variables in the crushing and screening process of fused magnesium oxide, measure the particle size of general powder as a label, and establish a sample set with {auxiliary variables as input and fitting labels as output};

[0010] Data preprocessing: standardize the sample data, use the PCA method to reduce the dimension, and eliminate the redundant relationship between auxiliary variables;

[0011] Establish a soft sensor model based on the XGBoost method: Use the XGBoost modeling method to establish an initialization objective function that takes into account the loss function and model complexity for the k-th output variable, and use the second-order Taylor expansion to transform the objective function; define a decision tree, and introduce the tree structure into the objective function, use the greedy algorithm to build the optimal tree, and repeat the above process t k times, and finally generates t k decision trees to obtain an ideal soft measurement model; the ideal model uses the outputs of these decision trees added together as the predicted output of the soft measurement results of the general powder particle size in the production process of high-temperature electrical grade magnesium oxide powder;

[0012] Soft measurement model correction: The ideal soft measurement model of general powder particle size is corrected by combining deviation compensation correction with real-time learning.

[0013] The auxiliary variables include original particle size, hardness, feed amount, crusher current, return amount, and air classifier speed; the fitting label is the manual detection value under the output two particle size distribution ranges.

[0014] The standardization adopts the normalization method to carry out the following steps:

[0015]

[0016] In the formula, u ij ′ represents the jth sample value of the ith input variable, is the sample mean of the i-th input variable, σi ′ is the sample standard deviation of the i-th input variable, u ij for u ij ′ is the standardized value, i=1,2,…,6; j=1,2,…,N; N is the number of samples.

[0017] The dimensionality reduction process using the PCA method is as follows:

[0018] Calculate the new input variable matrix X = UP after data preprocessing; where U∈R N×6 is the matrix formed by the input data after standardization, and the matrix P is the first s columns of the feature matrix P0;

[0019] Let the tth value of the kth output variable k The formula for initializing the objective function of a decision tree is as follows:

[0020]

[0021] Among them, the loss function of the i-th (i=1,2,...,N) sample is y ki represents the i-th sample value of the k-th output variable; represents the first t of the k-th output k The predicted value of the i-th sample by all decision trees; Ω ka (f ka ) represents the model complexity of the a-th tree of the k-th output.

[0022] The initial objective function is transformed, and the constant term is removed after Taylor expansion simplification to obtain the objective function:

[0023]

[0024] Defining a decision tree

[0025] Bundle Defined as in Represents the result of a tree, assuming that the tree has leaf nodes, used to convert the input x i ∈R s Mapped to a leaf node, Is the length A one-dimensional vector representing the weight of the leaf node, that is, the predicted value of the decision tree;

[0026] The following formula is used to measure the complexity of a tree:

[0027]

[0028] in, and are all hyperparameters that control the degree of penalty, and their value range is in the interval [0,1]. The objective function shown in formula (8) is transformed into:

[0029]

[0030] All samples x belonging to the jth leaf node i , is classified into a leaf node sample set, mathematically expressed as: Calculate the loss of all leaf node samples as make The objective function becomes To minimize the objective function, let right The partial derivative of is zero, so

[0031] Will Substitute into the objective function and get the objective function

[0032] Using the greedy algorithm to construct the optimal tree includes:

[0033] Determination of candidate split points: For the range of values ​​of each new input variable, select three points or four points according to the number of samples, and each point is a candidate split point;

[0034] A greedy algorithm is used to split the tree nodes: consider all new input variables and split them at each candidate split point of each new input variable; after each split, the original leaf node continues to split into two left and right child leaf nodes, and the sample set in the original leaf node will be dispersed to the left and right leaf nodes based on the comparison between the node and the value at the candidate split point; after a new node is split, it is tested whether this split will bring gain to the loss function. The gain is defined as follows:

[0035]

[0036] The L subscript is the optimal value of the objective function when the value is divided into the left subtree, and the R subscript is the optimal value of the objective function when the value is divided into the right subtree;

[0037] If Gain < 0, stop the split; if the number of samples of any leaf node is lower than the threshold Nu min , stopping this split, where Nu min The value range is [1, 10]; if the depth of the tree reaches the maximum value dep max , stop this split, where dep maxThe value range is a positive integer in the interval [3, 9]. Otherwise, after all candidate split points have completed splitting, the candidate split point with Gain>0 and the largest value is selected as the best split point for this round of splitting. Then, at the next leaf node, all candidate split points of all new input variables are considered, and the above process is repeated to perform the next round of splitting on the leaf node until the condition for stopping splitting is met. The final number of leaf nodes is obtained as Substitute into the objective function.

[0038] The form of the soft sensor model based on the XGBoost method is:

[0039]

[0040] Among them, u I Represents the input data u I The results after standardization are t represents the kth output variable k The sum of the outputs of the decision trees is the soft measurement result of the kth output variable of the general powder particle size in the production process of high-temperature electrical grade magnesium oxide obtained based on the input data.

[0041] The soft sensor model correction includes:

[0042] a) comparing the artificial detection value of the general powder particle size with the soft measurement result, if the absolute value of the error is less than a predefined first threshold, the original soft measurement model is kept unchanged and continues to be used;

[0043] b) if the absolute value of the error is greater than the first threshold value and less than the second threshold value, a deviation compensation method is used for correction, and the actual error is added to the result of the soft measurement as the final soft measurement result;

[0044] c) If the absolute values ​​of the errors are all greater than the second threshold, select Z sample data with the highest similarity to the new input data, preprocess the new input data, re-establish the soft measurement model using the XGBoost method, and add the new input and output data to the training samples.

[0045] The present invention has the following advantages and beneficial effects:

[0046] 1. It can measure the "general powder particle size" index which is difficult to detect online by traditional methods but is very important, providing the prerequisite for the implementation of advanced control in the production process of high-temperature electrical grade magnesium oxide powder;

[0047] 2. The XGBoost method is used to establish a soft measurement model, which enhances the generalization ability of the model and overcomes the risk of overfitting;

[0048] 3. Soft measurement model correction can perform online real-time correction on the soft measurement model and has the ability to adapt to changes in working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is the schematic diagram of the crushing and screening process in the production process of high-temperature electrical grade magnesium oxide;

[0050] Figure 2 This is the flow chart of the soft measurement process of general powder particle size. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation method of the present invention is further described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the invention, so the present invention is not limited by the specific implementation disclosed below.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0053] 1. Selection of auxiliary variables:

[0054] Through a comprehensive analysis of the crushing and screening process of fused magnesium oxide in the production process of high-temperature electrical grade magnesium oxide powder, it is determined that there are six important parameters affecting the particle size of general powder (distributed in the mass fraction of +35 mesh, -35 mesh ~ +325 mesh, -325 mesh range) in two particle size ranges y1 (mass fraction of +35 mesh range) and y2 (mass fraction of -35 mesh ~ +325 mesh range): the original particle size, hardness, feed amount of fused magnesium oxide, crusher current, return amount, and air classifier speed. Therefore, these six variables are used as auxiliary variables of the soft sensor model and are represented by u1′~u6′ respectively.

[0055] 2. Data preprocessing:

[0056] The training samples are standardized and the input variables are PCA dimension reduced.

[0057] (1) Standardization:

[0058] The regularization method is used to standardize the training samples.

[0059]

[0060] In the formula, u ij′ represents the i-th input variable u i ′ is the jth sample value, is the i-th input variable u i The sample mean of ′, σ i ′ is the i-th input variable u i The sample standard deviation of ′, u ij for u ij ′ is the standardized value, i=1,2,…,6; j=1,2,…,N; N is the number of samples.

[0061] (2) PCA dimensionality reduction of input variables:

[0062] Suppose the matrix formed by the data after U' is standardized is U∈R N×6 . Follow these steps:

[0063] Step 1: Calculate the covariance matrix

[0064] Step 2: Find the eigenvalues ​​and corresponding eigenvectors of the covariance matrix C, and arrange the eigenvalues ​​from large to small. Let the arranged eigenvalues ​​and their corresponding eigenvectors be θ i and p i , i=1,2,…,6.

[0065] Step 3: Calculation s is the number of new input variables obtained after the input variables are reduced in dimension. The specific value needs to be solved according to the inequality on the left.

[0066] Step 4: Arrange the eigenvectors in columns from left to right according to the corresponding eigenvalues ​​to form the characteristic matrix P0, and take the first s columns of P0 to form the matrix P.

[0067] Step 5: Calculate X = UP. X is the new input variable matrix after data preprocessing.

[0068] 3. Soft sensor modeling based on XGBoost method:

[0069] Follow these steps:

[0070] Step 1: Set k = 1 and go to Step 2;

[0071] Step 2: Let t k =1, go to Step 3:

[0072] Step 3: Initialize and construct the objective function.

[0073] Let the tth value of the kth output variable k The objective function formula of a decision tree is as follows:

[0074]

[0075] Among them, the loss function of the i-th (i=1,2,...,N) sample is y ki represents the i-th sample value of the k-th output variable; represents the first t of the k-th output k The predicted value of the i-th sample by all decision trees; Ω ka (f ka ) represents the model complexity of the a-th tree of the k-th output. Go to Step 4;

[0076] Step 4: Objective function transformation.

[0077] Substituting formula (5) into formula (4), we can get

[0078]

[0079] Among them, x i represents the i-th row of X, And is a constant. Taylor expansion of equation (6) yields

[0080]

[0081] in They are all constants. After simplification and removing the constant term, the objective function is equation (8). Go to Step 5.

[0082]

[0083] Step 5: Define a decision tree and introduce the tree into the objective function.

[0084] The expression of a decision tree is defined as follows: Bundle Defined as in Represents the result of a tree, which is used to convert the input x i ∈R s Mapped to a leaf node (assuming the tree has leaf nodes), Is the length A one-dimensional vector representing the weight of the leaf node (i.e., the predicted value of the decision tree).

[0085] The following formula is used to measure the complexity of a tree:

[0086]

[0087] in, and Both are hyperparameters that control the degree of penalty, and their value range is [0,1]. for No. Therefore, the objective function is transformed into:

[0088]

[0089] All samples x belonging to the jth leaf node i , is classified into a leaf node sample set, mathematically expressed as: Calculate the loss of all leaf node samples can be make

[0090]

[0091] Then the objective function becomes To minimize the objective function, let right The partial derivative of is zero, so we have

[0092] Will Substituting into the objective function, we get

[0093] Go to Step 6;

[0094] Step 6: Build the optimal tree.

[0095] Determination of candidate split points: For the range of values ​​of each new input variable, select three points or four points according to the number of samples, and each point is a candidate split point;

[0096] Use the greedy algorithm to split the tree nodes:

[0097] Starting from the depth of the tree being 0, a round of splitting is attempted for each leaf node in the tree, that is, considering all new input variables, splitting is performed at each candidate splitting point of each new input variable; after each split, the original leaf node continues to split into two left and right child leaf nodes, and the sample set in the original leaf node will be dispersed to the left and right leaf nodes according to the judgment rule of the node (that is, compared with the value at the candidate splitting point); after a new node is split, it is detected whether this split will bring gain to the loss function. The gain is defined as follows:

[0098]

[0099] The L subscript is the optimal value of the objective function when the value is divided into the left subtree, and the R subscript is the optimal value of the objective function when the value is divided into the right subtree. If Gain < 0, stop the split; if the number of samples of any leaf node is lower than the threshold Nu min , stopping this split, where Nu min The value range is [1, 10]; if the depth of the tree reaches the maximum value dep max , stop this split, where dep max The value range is a positive integer in the interval [3, 9]; otherwise, after all candidate split points have completed splitting, the candidate split point with Gain>0 and the largest value is selected as the best split point for this round of splitting. Then, at the next leaf node, consider all candidate split points of all new input variables, repeat the above process, and perform the next round of splitting on the leaf node until the condition for stopping splitting is met. The final number of leaf nodes is Go to Step 7;

[0100] Step 7: Determine t k Whether the maximum value t is reached kmax , t kmax The value range is a positive integer in the interval [1, 10]. If it is reached, go to Step 8, otherwise let t k =t k +1, go to Step 2;

[0101] Step 8: Determine whether k reaches 2. If so, the soft sensor model is established and go to Step 9. Otherwise, set k = k + 1 and go to Step 1.

[0102] Step 9:

[0103]

[0104] When the new input data u I When ′ arrives, the soft measurement result of the kth (k = 1, 2) output variable (i.e., the mass fraction distributed in the range of +35 mesh and -35 mesh to +325 mesh) is obtained using formula (13), and the mass fraction distributed in the range of -325 mesh is obtained using Then we can get. Among them, u I Represents the newly arrived input data u I ′The result after standardization, f ka (u I P) represents the output of the a-th decision tree of the k-th output variable, t represents the kth output variable k The sum of the outputs of the decision trees is the soft measurement result of the kth output variable of the general powder particle size in the production process of high-temperature electrical grade magnesium oxide obtained based on the input data.

[0105] 4. Correction of soft sensor model:

[0106] The soft measurement model of general powder particle size is corrected by combining deviation compensation correction with real-time learning. The artificial detection value of general powder particle size is compared with the soft measurement result. If the absolute value of the error is less than the pre-defined threshold 1, the original soft measurement model is kept unchanged and the original soft measurement model is continued to be used; if the absolute value of the error is greater than threshold 1 and less than threshold 2, the deviation compensation method is used for correction, that is, the actual error is added to the soft measurement result as the final soft measurement result; if the absolute value of the error is greater than threshold 2, the Z sample data with the highest similarity to the newly arrived input data are selected, the newly arrived input data are preprocessed, the soft measurement model is re-established using the XGBoost method, and the newly arrived input and output data are added to the training samples.

[0107] Among them, the threshold 1 range of the mass score distributed in the range of +35 mesh is between [0.5%, 1.5%], the threshold 2 range is between (1.5%, 2.5%], the threshold 1 range of the mass score distributed in the range of -35 mesh to +325 mesh is between [3%, 6%], the threshold 2 range is between (6%, 10%], and the similarity is calculated using formula (14). The value range of Z is between 100 and 200.

[0108]

[0109] in

[0110] It should be noted that the present invention is not limited to the embodiments described above. The above specific embodiments are merely illustrative and not restrictive. Without departing from the scope of the present invention and the scope of protection of the claims, a person of ordinary skill in the art may make many forms of specific changes under the guidance of the present invention, which all fall within the scope of protection of the present invention.

Claims

1. A soft measurement method for the particle size of general powder in the production process of high-temperature electrical grade magnesium oxide powder, characterized in that: The following steps are performed to obtain an ideal soft-sensing model and calibrate it in real time, which is used for soft-sensing prediction of unknown general powder particle size in the production process of unknown high-temperature electrical grade magnesium oxide powder. The method includes the following steps: Establish a sample set: select auxiliary variables in the crushing and screening process of fused magnesium oxide, measure the particle size of general powder as a label, and establish a sample set with {auxiliary variables as input and fitting labels as output}; Data preprocessing: standardize the sample data, use the PCA method to reduce the dimension, and eliminate the redundant relationship between auxiliary variables; Establish a soft sensor model based on the XGBoost method: Use the XGBoost modeling method to establish an initialization objective function that takes into account the loss function and model complexity for the k-th output variable, and use the second-order Taylor expansion to transform the objective function; define a decision tree, and introduce the tree structure into the objective function, use the greedy algorithm to build the optimal tree, and repeat the above process t k times, and finally generates t k decision trees to obtain an ideal soft measurement model; the ideal model uses the outputs of these decision trees added together as the predicted output of the soft measurement results of the general powder particle size in the production process of high-temperature electrical grade magnesium oxide powder; Soft measurement model correction: The ideal soft measurement model of general powder particle size is corrected by combining deviation compensation correction with real-time learning.

2. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1 is characterized in that: The auxiliary variables include original particle size, hardness, feed amount, crusher current, return amount, and air classifier speed; the fitting label is the manual detection value under the output two particle size distribution ranges.

3. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1 is characterized in that: The standardization is performed using the regularization method: In the formula, u ij ′ represents the jth sample value of the ith input variable, is the sample mean of the i-th input variable, σ i ′ is the sample standard deviation of the i-th input variable, u ij for u ij ′ is the standardized value, i=1,2,…,6; j=1,2,…,N; N is the number of samples.

4. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1 is characterized in that: The dimensionality reduction process using the PCA method is as follows: Calculate the new input variable matrix X = UP after data preprocessing; where U∈R N×6 It is the matrix formed by the input data after standardization, and the matrix P is the first s columns of the feature matrix P0.

5. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1 is characterized in that The tth value of the kth output variable k The formula for initializing the objective function of a decision tree is as follows: Among them, the loss function of the i-th (i=1,2,...,N) sample is y ki represents the i-th sample value of the k-th output variable; represents the first t of the k-th output k The predicted value of the i-th sample by all decision trees; Ω ka (f ka ) represents the model complexity of the a-th tree of the k-th output.

6. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1, characterized in that: The initial objective function is transformed, and the constant term is removed after Taylor expansion simplification to obtain the objective function:

7. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1 is characterized in that: Defining a decision tree Bundle Defined as in Represents the result of a tree, assuming that the tree has leaf nodes, used to convert the input x i ∈R s Mapped to a leaf node, Is the length A one-dimensional vector representing the weight of the leaf node, that is, the predicted value of the decision tree; The following formula is used to measure the complexity of a tree: in, and are all hyperparameters that control the degree of penalty, and their value range is in the interval [0,1]. The objective function shown in formula (8) is transformed into: All samples x belonging to the jth leaf node i , is classified into a leaf node sample set, mathematically expressed as: Calculate the loss of all leaf node samples as make The objective function becomes To minimize the objective function, let right The partial derivative of is zero, so Will Substitute into the objective function and get the objective function 8. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1, characterized in that: Using the greedy algorithm to construct the optimal tree includes: Determination of candidate split points: For the range of values ​​of each new input variable, select three points or four points according to the number of samples, and each point is a candidate split point; A greedy algorithm is used to split the tree nodes: consider all new input variables and split them at each candidate split point of each new input variable; after each split, the original leaf node continues to split into two left and right child leaf nodes, and the sample set in the original leaf node will be dispersed to the left and right leaf nodes based on the comparison between the node and the value at the candidate split point; after a new node is split, it is tested whether this split will bring gain to the loss function. The gain is defined as follows: The L subscript is the optimal value of the objective function when the value is divided into the left subtree, and the R subscript is the optimal value of the objective function when the value is divided into the right subtree; If Gain < 0, stop the split; if the number of samples of any leaf node is lower than the threshold Nu min , stopping this division, where Nu min The value range is [1, 10]; if the depth of the tree reaches the maximum value dep max , stop this split, where dep max The value range is a positive integer in the interval [3, 9]. Otherwise, after all candidate split points have completed splitting, the candidate split point with Gain>0 and the largest value is selected as the best split point for this round of splitting. Then, at the next leaf node, all candidate split points of all new input variables are considered, and the above process is repeated to perform the next round of splitting on the leaf node until the condition for stopping splitting is met. The final number of leaf nodes is obtained as Substitute into the objective function.

9. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1, characterized in that: The form of the soft sensor model based on the XGBoost method is: Among them, u I Represents the input data u I The results after standardization are t represents the kth output variable k The sum of the outputs of the decision trees is the soft measurement result of the kth output variable of the general powder particle size in the production process of high-temperature electrical grade magnesium oxide obtained based on the input data.

10. The soft measurement method for general powder particle size in the production process of high temperature electrical grade magnesium oxide powder according to claim 1, characterized in that: The soft measurement model correction includes: a) comparing the artificial detection value of the general powder particle size with the soft measurement result, if the absolute value of the error is less than a predefined first threshold, keeping the original soft measurement model unchanged, and continuing to use the original soft measurement model; b) if the absolute value of the error is greater than the first threshold and less than the second threshold, using a deviation compensation method to perform correction, adding the actual error to the soft measurement result as the final soft measurement result; c) if the absolute values ​​of the errors are greater than the second threshold, selecting Z sample data with the highest similarity to the new input data, preprocessing the new input data, re-establishing the soft measurement model using the XGBoost method, and adding the new input and output data to the training samples.

Images