A method, device and equipment for controlling parameters of a refining unit

Abstract

The present application relates to a method, device and equipment for controlling parameters of a refining and chemical device. The main technical solutions include: obtaining target parameter data and process operation data of the refining and chemical device within a preset time, determining a steady-state time period during which the process operation parameters affecting the target parameters are in a steady state according to the target parameter data and the process operation data, constructing a state space model for evaluating the influence of the process operation parameters on the target parameters based on the steady-state time period, determining the delay time of the process operation parameters according to the target parameter data, the process operation data and the state space model, determining the device control parameters of the refining and chemical device according to the delay time of the process operation parameters and the state space model, and verifying the rationality of the state space model and the rationality of the device control parameters, which can accurately evaluate the influence of the process operation parameters on the target parameters and reduce the evaluation cost.

Description

Technical Field

[0001] The present application relates to the technical field of industrial production, and particularly to a method, device and equipment for controlling parameters of a refining and chemical device. Background Art

[0002] Petroleum refining is a complex process, mainly through physical and chemical processing of crude oil to produce gasoline, kerosene, diesel and various basic petrochemical products, involving units such as atmospheric and vacuum distillation, fluid catalytic cracking, delayed coking, continuous reforming, hydrogenation, hydrogen production, ethylene cracking, aromatics extraction, isomerization, etc. During the transformation and upgrading process of traditional refineries, it is necessary to cope with complex and changeable production demands and improve the automation level, production efficiency and product quality of refining and chemical devices.

[0003] Multivariable Predictive Control (MPC) can reduce fluctuations in production by precisely controlling the key parameters affecting product quality in a refining and chemical device, thereby improving the conversion rate of raw materials and the product yield. At the same time, MPC can also predict and compensate for external disturbances and internal changes in the system. In order for the control system of a refining and chemical device to predict and learn the influence of process operation parameters on target parameters, a large amount of sample data is required, and in a real production environment, changes in the properties of raw materials may cause different degrees of deviation in the model parameters of the control system, which not only makes it difficult for the control system to accurately evaluate the influence of process operation parameters on target parameters, but also has a high evaluation cost and cannot accurately control the relevant parameters in the refining and chemical device. Summary of the Invention

[0004] Based on this, the present application provides a method, device and equipment for controlling parameters of a refining and chemical device to solve the technical problems that the control system is difficult to accurately evaluate the influence of process operation parameters on target parameters and has a high evaluation cost.

[0005] In a first aspect, a method for controlling parameters of a refining and chemical device is provided, and the method includes:

[0006] Obtain target parameter data and process operation data of a refining and chemical device within a preset time period, where both the target parameter data and the process operation data are time series data, the target parameter data includes target parameters, and the process operation data includes process operation parameters;

[0007] Determine a steady-state time period during which the process operation parameters affecting the target parameters are in a steady state according to the target parameter data and the process operation data;

[0008] Construct a state space model for evaluating the influence of process operation parameters on target parameters based on the steady-state time period;

[0009] Determine the delay time of the process operation parameters according to the target parameter data, process operation data, and state space model;

[0010] Determine the device control parameters of the refining device according to the delay time of the process operation parameters and the state space model;

[0011] Verify the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, process operation data, delay time, state space model, and device control parameters of the refining device.

[0012] According to an implementable manner in the embodiment of the present application, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state according to the target parameter data and process operation data, including:

[0013] Determine the outlier time points of the process operation parameters based on a preset sliding window according to the process operation data, where the determination formula for the outlier time points is expressed as the following formula:

[0014]

[0015] where w i,t represents the value of the process operation parameter i at time t, represents the average value of the process operation parameter i within the time period [t - δ, t - 1], represents the average value of the process operation parameter i within the time period [t + δ, t + 1], σ(w i,t-δ:t-1 ) represents the standard deviation of the process operation parameter i within the time period [t - δ, t - 1], σ(w i,t+δ:t+1 ) represents the standard deviation of the process operation parameter i within the time period [t + δ, t + 1], and δ represents the length of the preset sliding window;

[0016] Determine the effective time period in the process operation data according to the outlier time points of the process operation parameters;

[0017] Determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state within the effective time period according to the target parameter data and process operation data.

[0018] According to an implementable manner in the embodiment of the present application, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state according to the target parameter data and process operation data, including:

[0019] Determine the set of change points where the process operation parameters have jumps according to the target parameter data and process operation data satisfying t1 < t2 <..., based on the preset time interval δ j Determine the steady-state points corresponding to each change point in the set of change points, denoted as t j + δj , the steady state point satisfies t j +δ j <t j+1 ;

[0020] Based on the steady state points corresponding to each change point in the change point set, determine the initial steady state point set of the process operation parameters based on the first-order autoregressive model;

[0021] If the time distance between the current steady state point and the next steady state point in the initial steady state point set is less than the preset time interval, remove the current steady state point. If the time distance between the current steady state point and the next steady state point in the initial steady state point set is greater than the preset time interval, retain the current steady state point and the next steady state point to obtain the final steady state point set;

[0022] According to the final steady state point set, determine the steady state time period during which the process operation parameters affecting the target parameter are in a steady state.

[0023] According to an implementable manner in the embodiments of the present application, based on the steady state time period, construct a state space model for evaluating the influence of process operation parameters on the target parameter, including:

[0024] The state space model is expressed as:

[0025]

[0026] where y t is the target parameter, obtained by summing all hidden processes plus noise, is the reference point of the target parameter, obtained from the previous steady state point before time t, that is is the final steady state point set, x i,t represents the hidden process affected by the process operation parameter i at time t, which is an unknown variable, x i,t-k represents the hidden process affected by the process operation parameter i at time t - k, k represents the number of past time points, w i,t-θi represents the value of the process parameter i at time t - θi, represents the reference point of the process parameter i at time t - θi, obtained from the previous steady state point before time t, that is θi represents the delay value of the i-th process operation parameter, d is the number of process operation parameters i, α i,k , β i , c i are the parameters of the autoregressive model, ∈ i，t , ε t are the noise of the hidden process and the observation noise respectively, and respectively follow a normal distribution with a mean of 0 and a variance of ω 2 , σ 2 respectively, where ω 2According to the process parameters w i,t-θi Calculate the variance, σ 2 is based on the hidden process x i,t Calculate the variance; x d+1,t , x d+1,t-1 The influencing factors of the unknown variables hidden in the raw material properties at time t and time t-1, is the magnitude of its mean shift, x i,0 is the initial hiding process, μ i，0 For x i,t The mean of .

[0027] According to an achievable method in an embodiment of the present application, determining the delay time of the process operation parameter according to the target parameter data, the process operation data and the state space model includes:

[0028] According to the process operation data, the delay upper bound and delay lower bound of the process operation parameters are set, which are expressed as Satisfy 0≤θ i，min ≤θ i，max ;

[0029] Based on the delay upper bound, delay lower bound and preset delay interval g i , determine the delay time candidate set of process operation parameters

[0030] Based on the state space model and the delay time candidate set, the mean absolute effect value of each variable in the process operation parameter is calculated by the following formula:

[0031]

[0032] in, is the estimated value of the state space model at time t+s given time 1 to t, For the state space model, excluding the current variable w′ at given time 1 to t i After the influence of , the estimated value at time t+s, that is, the variable values corresponding to the period [t+1, t+s] are all 0, s is the pre-selected step length, and T is the time length of the target parameter data and process operation data;

[0033] The delay time corresponding to the variable with the largest mean absolute effect value is determined as the delay time of the process operation parameter.

[0034] According to an achievable method in an embodiment of the present application, determining the delay time of the process operation parameter according to the target parameter data, the process operation data and the state space model includes:

[0035] Using the state - space model as the surrogate model and the root - mean - square error between the predicted value and the true value of the preset future duration of the target parameter as the objective function, optimize the objective function through the surrogate model to obtain the objective function value;

[0036] Based on historical production data, determine the search interval of the delay time of the influence of process operation parameters on the target parameter, and perform Bayesian optimization iteration on the delay time within the search interval;

[0037] When the delay time reaches a certain number of iterations or the objective function value is less than the preset threshold, select the delay time of the process operation parameter corresponding to the minimum value of the objective function as the delay time of the process operation parameter.

[0038] According to an implementable manner in the embodiments of the present application, determine the device control parameters of the refining device according to the delay time of the process operation parameter and the state - space model, including:

[0039] Convert the state - space model into a differential - equation model;

[0040] Calculate the first - order derivative function and the second - order derivative function of the state - space model;

[0041] Substitute the first - order derivative function and the second - order derivative function into the differential - equation model to obtain the target differential - equation model;

[0042] Adjust the parameters of the state - space model according to the state - space model and the target differential - equation model;

[0043] According to the parameters of the state - space model, determine the device control parameters of the refining device, and the device control parameters are expressed by the following formula:

[0044]

[0045] Among them, K i represents the influence degree of the process operation parameter on the target parameter. If K i > 0, it represents a positive influence. If K i < 0, it represents a negative influence. τ i and ζ i represent the speed of the influence of the process operation parameter on the target parameter. β i , α i,1 , α i,2 are the parameters of the autoregressive model, and Δ represents the sampling interval.

[0046] According to an implementable manner in the embodiments of the present application, verify the rationality of the state - space model and the rationality of the device control parameters according to the target parameter data, process operation data, state - space model, delay time, and device control parameters of the refining device, including:

[0047] Predict the time series values of the target parameters in a future time period according to process operation data, a state space model, and a delay time;

[0048] Verify the rationality of the state space model and the rationality of the device control parameters according to the error and trend between the time series values and the true values.

[0049] In a second aspect, a parameter control device for a refining device is provided, and the device includes:

[0050] An acquisition module, configured to acquire target parameter data and process operation data of the refining device within a preset time, where both the target parameter data and the process operation data are time series data, the target parameter data includes target parameters, and the process operation data includes process operation parameters;

[0051] A determination module, configured to determine a steady state time period in which the process operation parameters affecting the target parameters are in a steady state according to the target parameter data and the process operation data;

[0052] A construction module, configured to construct a state space model for evaluating the influence of process operation parameters on target parameters based on the steady state time period;

[0053] The determination module is further configured to determine the delay time of the process operation parameters according to the target parameter data, the process operation data, and the state space model;

[0054] The determination module is further configured to determine the device control parameters of the refining device according to the delay time of the process operation parameters and the state space model;

[0055] A verification module, configured to verify the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, the process operation data, the delay time, the state space model, and the device control parameters of the refining device.

[0056] In a third aspect, a computer device is provided, including:

[0057] At least one processor; and

[0058] A memory communicatively connected to the at least one processor; wherein,

[0059] The memory stores computer instructions executable by the at least one processor, and the computer instructions are executed by the at least one processor so that the at least one processor can execute the method involved in the first aspect above.

[0060] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, and characterized in that the computer instructions are used to cause a computer to execute the method involved in the first aspect above.

[0061] According to the technical content provided by the embodiments of the present application, by obtaining the target parameter data and process operation data of a refining device within a preset time, where both the target parameter data and the process operation data are time series data, the target parameter data includes target parameters, and the process operation data includes process operation parameters. Based on the target parameter data and the process operation data, determine the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state. Based on the steady-state time period, construct a state space model for evaluating the influence of process operation parameters on the target parameters. According to the target parameter data, the process operation data, and the state space model, determine the delay time of the process operation parameters. According to the delay time of the process operation parameters and the state space model, determine the device control parameters of the refining device. According to the target parameter data, the process operation data, the delay time, the state space model, and the device control parameters of the refining device, verify the rationality of the state space model and the rationality of the device control parameters, which can accurately evaluate the influence of process operation parameters on the target parameters and reduce the evaluation cost. Description of the Drawings

[0062] Figure 1 It is a schematic flowchart of a method for controlling parameters of a refining device in an embodiment;

[0063] Figure 2 It is a structural block diagram of a device for controlling parameters of a refining device in an embodiment;

[0064] Figure 3 It is a schematic structural diagram of a computer device in an embodiment. Detailed Embodiments

[0065] The following further details the present application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] Figure 1 The schematic flowchart of a method for controlling parameters of a refining device provided by an embodiment of the present application is shown. As Figure 1 shown, the method may include the following steps:

[0067] S110, obtain the target parameter data and process operation data of the refining device within a preset time.

[0068] Among them, the target parameter data includes target parameters, target parameter types, and the values corresponding to the target parameters at each time point, etc., and may include side draw temperature, product flow rate, etc. The process operation data includes process operation parameters, process operation parameter types, and the values corresponding to the process operation parameters at each time point, etc., and may include temperature, pressure, flow rate, composition ratio, and time, etc. The target parameters are usually affected by multiple process operation parameters, and different process operation parameters have different degrees of influence on the target parameters.

[0069] The preset time can be determined according to the sample size of the acquired historical data. For example, the preset time is set to three months, which is not limited here.

[0070] Obtain the target parameter data of the refining device within three months and use it as time series data, denoted as Collect the changes in the process operation parameters of the device within three months. After centralizing the changes in the process operation parameters, denote them as T is the time length of the target parameter data and the process operation data. d is the number of process operation parameters. For example, the target parameter is Y, and there are the following 15 process operation parameters: W1, W2, W3, W4, W5, W6, W7, W8, W9, W10, W11, W12, W13, W14, W15. There are a total of 100,000 data points in the main data during these three months. Divide them into 80,000 for the training set and 20,000 for the test set.

[0071] S120. According to the target parameter data and the process operation data, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state.

[0072] Remove the outliers from the process operation parameter data and use the average value for filling. For each process operation parameter, run the PELT algorithm on it to detect its change points. If there are no change points in a continuous time period, it is considered that the process operation parameter remains in a steady state during this time period. If all process operation parameters remain in a steady state in a time period, it is considered that this time period is a steady state, that is, the steady-state time period.

[0073] S130. Based on the steady-state time period, construct a state space model for evaluating the influence of process operation parameters on the target parameter.

[0074] Combined with the steady-state points within the steady-state time period, establish a state space model to describe the influence of process operation parameters on the target parameter. The state space model includes a hidden process affected by the process operation parameters. The target parameter can be obtained by summing all the hidden processes plus noise. Each hidden process can be represented by a second-order autoregressive model with external variables.

[0075] S140. According to the target parameter data, the process operation data, and the state space model, determine the delay time of the process operation parameters.

[0076] For each process operation parameter, combine the existing knowledge and practical experience to determine the upper and lower bounds of the delay time of the process operation parameter. The granularity of the delay time can be determined according to the requirements of its own computing power and accuracy, and further obtain the alternative set of the delay time of the process operation parameter.

[0077] The contribution of each variable to the estimation of the target parameter is represented by calculating the average absolute effect of each variable. Since there will be strong collinearity among different variables generated by the same process operation parameters after processing, the delay corresponding to the variable that is most useful for estimating the target parameter at this time is more likely to be the true delay. For multiple variables corresponding to a process operation parameter, the delay time corresponding to the variable with the largest average absolute effect is determined as the delay time of the process operation parameter, that is, the optimal delay time.

[0078] S150. Determine the device control parameters of the refining device according to the delay time of the process operation parameter and the state space model.

[0079] Convert the model parameters of the state space model into the parameters of the differential equation, substitute the delay time of the process operation parameter into the state space model, and obtain the parameter representing the influence degree of the current process operation parameter on the target parameter and the parameter representing the influence speed of the current process operation parameter on the target parameter.

[0080] S160. Verify the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, process operation data, delay time, state space model, and device control parameters of the refining device.

[0081] Substitute the target parameter data, process operation data, and optimal delay time divided into the test set into the state space model, calculate the root mean square error of different prediction steps, and evaluate the model coefficients obtained by converting the state space model into a differential equation in combination with actual experience to determine whether the obtained coefficients are reasonable.

[0082] It can be seen that in the embodiment of the present application, by obtaining the target parameter data and process operation data within the preset time of the refining device, where the target parameter data and process operation data are both time series data, the target parameter data includes target parameters, and the process operation data includes process operation parameters, according to the target parameter data and process operation data, determine the steady-state time period when the process operation parameter affecting the target parameter is in a steady state. Based on the steady-state time period, construct a state space model for evaluating the influence of the process operation parameter on the target parameter. According to the target parameter data, process operation data, and state space model, determine the delay time of the process operation parameter. According to the delay time of the process operation parameter and the state space model, determine the device control parameters of the refining device. According to the target parameter data, process operation data, delay time, state space model, and device control parameters of the refining device, verify the rationality of the state space model and the rationality of the device control parameters, which can accurately evaluate the influence of the process operation parameter on the target parameter and reduce the evaluation cost.

[0083] As an implementable approach, according to the target parameter data and process operation data, determining the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state, including:

[0084] Based on the process operation data, determining the outlier time points of the process operation parameters based on a preset sliding window. The determination formula for the outlier time points is expressed as the following formula:

[0085]

[0086] where, W i,t represents the value of the process operation parameter i at time t, represents the average value of the process operation parameter i within the time period [t - δ, t - 1], represents the average value of the process operation parameter i within the time period [t + δ, t + 1], σ(w i,t-δ:t-1 ) represents the standard deviation of the process operation parameter i within the time period [t - δ, t - 1], σ(w i,t+δ:t+1 ) represents the standard deviation of the process operation parameter i within the time period [t + δ, t + 1], and δ represents the length of the preset sliding window;

[0087] Based on the outlier time points of the process operation parameters, determining the valid time period in the process operation data;

[0088] Based on the target parameter data and process operation data, determining the steady-state time period that is in a steady state within the valid time period affecting the target parameter.

[0089] Among them, formula (1) represents that this point must be an extreme point, which excludes false alarms caused by large changes in parameters in a short time. Formula (2) represents that the difference of this point compared with the left and right time windows exceeds a certain threshold. Since the parameter may change greatly in a short time, therefore, the standard deviations at both ends of this point are simultaneously examined, and several times the maximum value of the standard deviation is taken as the threshold, and it is appropriate to take 3 times the maximum value of the standard deviation as the threshold. When time t simultaneously satisfies formula (1) and formula (2), then time t is considered an outlier value to prevent false alarms.

[0090] Eliminating the outlier time points of the process operation parameters to obtain the valid time period in the process operation data. For each process operation parameter, formulas (1) and (2) are used to retrieve and eliminate the outlier values.

[0091] According to the target parameter data and process operation data, find the time period during which the target parameter and process operation parameters remain in a steady state. For each process operation parameter, first find all the time points at which the process operation parameter is in a steady state. Then, if all process operation parameters do not change significantly within a certain period of time, it is considered that the system reaches a steady state during this period of time.

[0092] As an implementable way, according to the target parameter data and process operation data, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state, including:

[0093] According to the target parameter data and process operation data, determine the set of change points where the process operation parameters have jumps Satisfying t1 < t2 <..., based on the preset time interval δ j Determine the steady-state points corresponding to each change point in the set of change points, denoted as t j +δ j , the steady-state points satisfy t j +δ j <t j+1 ;

[0094] According to the steady-state points corresponding to each change point in the set of change points, determine the initial set of steady-state points of the process operation parameters based on the first-order autoregressive model;

[0095] If the time distance between the current steady-state point and the next steady-state point in the initial set of steady-state points is less than the preset time interval, remove the current steady-state point. If the time distance between the current steady-state point and the next steady-state point in the initial set of steady-state points is greater than the preset time interval, retain the current steady-state point and the next steady-state point to obtain the final set of steady-state points;

[0096] According to the final set of steady-state points, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state.

[0097] For each process operation parameter, the algorithm for change point detection can be used to find the points where the process operation parameter has jumps. The change point detection algorithm can adopt the PELT algorithm to obtain the set of change points where the process operation parameter has jumps. At this time, the steady-state points can appear in the time period where there is no significant change for some time after the change point. Based on the process operation data, the set of change points of the process operation parameter is obtained through the PELT algorithm. Since the condition for the steady-state point to hold is that the time when it appears is before the time when the next change point appears, the steady-state points need to satisfy t j +δ j <t j+1 .

[0098] For the preset time interval δ j , it can be determined using the enumeration algorithm, and at the same time, the first-order autoregressive model is used to judge the time period [tj , t j +δ j whether there is no change in trend. Use the hypothesis testing method to test whether the model parameter β of the first-order autoregressive is non-zero. If β is non-zero, then it is considered that the system has not reached a steady state. Otherwise, it is considered that the system has reached a steady state and the enumeration is terminated. Denote the set of initial steady state points of a single process operation parameter found by this algorithm as

[0099] Take the union of all sets of initial steady state points , and denote it as If the time distance between the current steady state point and the next steady state point in the set of initial steady state points is less than the preset time interval, it means that the current steady state point and the next steady state point are too close, indicating that the previous steady state point is only for a single process operation parameter to reach a steady state, while the system has not reached a steady state. Therefore, remove the previous steady state point. If the time distance between the current steady state point and the next steady state point in the set of initial steady state points is greater than the preset time interval, it indicates that the distance between the current steady state point and the next steady state point is appropriate and the system has reached a steady state. Retain the current steady state point and the next steady state point to obtain the final set of steady state points.

[0100] Obtain the time points when the process operation parameters affecting the target parameter are in a steady state according to the final set of steady state points, and determine the time period during which all process operation parameters have not changed significantly from the time points when the process operation parameters are in a steady state, that is, the steady state time period.

[0101] As an implementable way, based on the steady state time period, construct a state space model for evaluating the influence of process operation parameters on the target parameter, including:

[0102] The state space model is expressed as:

[0103]

[0104] where, y t is the target parameter, obtained by summing all hidden processes plus noise, is the reference point of the target parameter, obtained from the previous steady state point before time t, that is is the final set of steady state points, x i,t represents the hidden process affected by process operation parameter i at time t, which is an unknown variable, x i,t-k represents the hidden process affected by process operation parameter i at time t - k, k represents the number of past time points, w i,t-θi represents the value of process parameter i at time t - θi, represents the reference point of process parameter i at time t - θi, obtained from the previous steady state point before time t, that is θi represents the delay value of the i-th process operation parameter, d is the number of process operation parameters i, α i,k ,β i ,c i is the parameter of the autoregressive model, ∈ i，t , ε t They are the noise of the hidden process and the observation noise, respectively, with mean 0 and variance ω 2 , σ 2 The normal distribution of 2 According to the process parameters w i,t-θi Calculate the variance, σ 2 is based on the hidden process x i,t Calculate the variance; x d+1,t , x d+1,t-1 The influencing factors of the unknown variables hidden in the raw material properties at time t and time t-1, is the magnitude of its mean shift, x i,0 is the initial hiding process, μ i，0 For x i,t The mean of .

[0105] As an achievable approach, the delay time of the process operation parameter is determined according to the target parameter data, the process operation data and the state space model, including:

[0106] According to the process operation data, the delay upper bound and delay lower bound of the process operation parameters are set, which are expressed as Satisfy 0≤θ i，min ≤θ i，max ;

[0107] Based on the delay upper bound, delay lower bound and preset delay interval g i , determine the delay time candidate set of process operation parameters

[0108] Based on the state space model and the delay time candidate set, the mean absolute effect value of each variable in the process operation parameter is calculated by the following formula:

[0109]

[0110] in, is the estimated value of the state space model at time t+s given time 1 to t, For the state space model, excluding the current variable w′ at given time 1 to t i After the influence of , the estimated value at time t+s, that is, the variable values corresponding to the period [t+1, t+s] are all 0, s is the pre-selected step length, and T is the time length of the target parameter data and process operation data;

[0111] Determine the delay time corresponding to the variable with the largest average absolute effect value as the delay time of the process operation parameter.

[0112] According to the setting requirements and practical experience in the field, set the upper bound and lower bound of the delay of the process operation parameter. Determine the granularity of the delay according to the requirements of its own computing power and precision, that is, preset the delay interval g i . Based on actual production experience, a recommended range for the delay of process operation parameters is given, and rough screening is carried out with a granularity of 5. For example, if the recommended delay range of process operation parameter W4 is 5 - 20, we will generate four variables with delays of 5, 10, 15, and 20 from W4 and include these four variables in the training process. The same method is adopted for other process operation parameters. Finally, 48 variables corresponding to process operation parameters and different delays are obtained in the state space model.

[0113] Define L i as the set size of alternatives for the i-th process operation parameter. At this time, for the delay time in the delay time alternative set, it is expressed as Process the existing w1 to transform it into a time series containing L1 variables satisfying . Similar processing is carried out for all the remaining d - 1 variables. Finally, after removing all time points containing blank values, a set of size, where L = ∑L i is the total number of variables. Keep the target parameter y at the same time points as w′ to obtain Model and solve (w′, y′) using the state space model to obtain the estimated model parameters.

[0114] By calculating the contribution of each variable to the estimated target parameter, determine the best delay time for each process operation parameter. After processing, there will be strong collinearity among the different variables generated by the same process operation parameter. Then, the delay time corresponding to the variable that is most useful for the estimation of the target parameter is more likely to be the true delay time.

[0115] Calculate the average absolute effect value of each variable in the process operation parameter through formula (7), and select the delay time corresponding to the variable with the largest average absolute effect among them, that is, the best delay time as the delay time of the process operation parameter.

[0116] Exemplarily, after the model training is completed, we calculated the AAME of all 48 variables, as shown in Table 1. The AAME of each variable represents the contribution of the corresponding process operation parameter with a specific delay in estimating the target parameter. For each process operation parameter, we select the delay time with the largest AAME. According to Table 1, the selected delays are {W1Lag0, W9Lag5, W2Lag5, W10Lag0, W3Lag5, W11Lag15, W4Lag5, W12Lag10, W5Lag0, W13Lag30, W6Lag5, W14Lag15, W7Lag25, W15Lag0, W8Lag0}, and we define this combination as Setting 1.

[0117] Table 1 AAME values of process operation parameters at a granularity of 5

[0118]

[0119] As an achievable way, according to the target parameter data, process operation data, and state space model, to determine the delay time of the process operation parameter, including:

[0120] Taking the state space model as a surrogate model, using the root mean square error between the predicted value and the true value of the preset future duration of the target parameter as the objective function, and optimizing the objective function through the surrogate model to obtain the objective function value;

[0121] Based on historical production data, determine the search interval for the delay time of the influence of the process operation parameter on the target parameter, and perform Bayesian optimization iteration on the delay time within the search interval;

[0122] When the delay time reaches a certain number of iterations or the objective function value is less than the preset threshold, select the delay time of the process operation parameter corresponding to the minimum value of the objective function as the delay time of the process operation parameter.

[0123] In addition to the above method of determining the optimal delay time by calculating the average absolute effect value, the method of Bayesian optimization can also be used to achieve the selection of the optimal delay time. In Bayesian optimization, taking the state space model as a surrogate model, using the root mean square error between the predicted value and the true value of the preset future duration of the target parameter as the objective function, and optimizing the objective function through the surrogate model, the optimized objective function is the root mean square difference RMSE value of the target parameter prediction result.

[0124] Historical production data are the configuration data of target parameters and process operation parameters in the past production process, which contain certain production experience and have good reference value. Give an initial delay value for a set of process parameters and define the search interval for the delay of process operation parameters according to production experience, and perform optimization iteration in combination with its own computing power. When a certain number of iterations is reached or the objective function value is less than a certain threshold, select the delay time of the process operation parameter corresponding to the minimum value of the objective function as the delay time of the process operation parameter.

[0125] As an achievable way, determine the device control parameters of the refining device according to the delay time of the process operation parameter and the state space model, including:

[0126] Convert the state space model into a differential equation model;

[0127] Calculate the first derivative function and the second derivative function of the state space model;

[0128] Substitute the first derivative function and the second derivative function into the differential equation model to obtain the target differential equation model;

[0129] Adjust the parameters of the state space model according to the state space model and the target differential equation model;

[0130] Determine the device control parameters of the refining device according to the parameters of the state space model. The device control parameters can be expressed by the following formula:

[0131]

[0132] Among them, K i represents the influence degree of the process operation parameter on the target parameter. If K i > 0, it represents a positive influence. If K i < 0, it represents a negative influence. τ i and ζ i represent the speed at which the process operation parameter affects the target parameter. β i , α i,1 , α i,2 are the parameters of the autoregressive model, and Δ represents the sampling interval.

[0133] Convert the state space model into a differential equation model. The differential equation model can be expressed as:

[0134]

[0135] Among them, K i represents the influence degree of the process operation parameter on the target parameter. If K i > 0, it represents a positive influence. If K i < 0, it represents a negative influence. τi and ζ i represents the speed at which process operation parameters affect the target parameter, θ i represents the delay time of the process operation parameter affecting the target parameter.

[0136] In the state - space model, x i，t+1 -x i，t can be used to approximate the first - order derivative function x′ i (t), and at the same time, x i，t+2 -2x i，t+1 +x i，t is used to approximate the second - order derivative function x″ i (t). Substituting the first - order derivative function and the second - order derivative function into the differential - equation model, the target differential - equation model can be obtained. Comparing the target differential - equation model with the state - space transfer model can obtain the expression equations of β i , α i,1 , α i,2 . Solving the simultaneous equations can obtain the control parameters.

[0137] Setting 1 is the optimal delay time we selected. Under this delay - time setting, using the training - set data for training, the corresponding state - space model parameters can be used to calculate the corresponding differential - equation parameters through formula (8). The specific differential - equation parameters calculated for each process operation parameter are shown in Table 2 below.

[0138] Table 2 Differential - equation coefficients for different process operation parameters

[0139]

[0140] As an implementable method, according to the target - parameter data, process - operation data, state - space model, delay time, and the device - control parameters of the refining unit, verify the rationality of the state - space model and the device - control parameters, including:

[0141] Predict the time - series values of the target parameter in the future time period according to the process - operation data, state - space model, and delay time;

[0142] Verify the rationality of the state - space model and the device - control parameters according to the error and trend between the time - series values and the true values.

[0143] Based on the process - operation data, state - space model, and delay time, predict the time - series values of the target parameter in the future time period. The time - series values are the numerical values of the target parameter arranged in chronological order and are the RMSE values for different prediction steps.

[0144] Verify the rationality of the state space model and the rationality of the device control parameters based on the error between the time series value and the true value and the trend. If the error between the time series value and the true value is small and the trend is basically the same, it indicates that the state space model and the device control parameters are set reasonably. Otherwise, the state space model and the device control parameters are set unreasonably.

[0145] For example, apply the training model with a set delay time of 1 to the last 20,000 test set data, calculate the predicted values of the target parameters for different prediction steps Y, and calculate the RMSE values between the predicted values and the true values. The results are shown in Table 3:

[0146] Table 3 RMSE results of the predicted values corresponding to setting 1

[0147]

[0148] It can be seen that the finally selected delay time has a good effect.

[0149] The above method can be applied not only to refining devices, but also to other devices involved in the oil refining process, which is not limited here.

[0150] It should be understood that although Figure 1 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this application, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 1 at least a part of the steps in

[0151] Figure 2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps. Figure 1 Figure 2 Figure 2 Figure 2

[0152] The acquisition module 210 is used to acquire the target parameter data and process operation data of the refining device within a preset time. Among them, both the target parameter data and the process operation data are time series data. The target parameter data includes target parameters, and the process operation data includes process operation parameters.

[0153] A determination module 220, configured to determine a steady-state time period during which process operation parameters affecting a target parameter are in a steady state according to target parameter data and process operation data;

[0154] A construction module 230, configured to construct a state space model for evaluating the influence of process operation parameters on a target parameter based on the steady-state time period;

[0155] The determination module 220 is further configured to determine a delay time of the process operation parameters according to the target parameter data, the process operation data, and the state space model;

[0156] The determination module 220 is further configured to determine device control parameters of a refining device according to the delay time of the process operation parameters and the state space model;

[0157] A verification module 240, configured to verify the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, the process operation data, the delay time, the state space model, and the device control parameters of the refining device.

[0158] As an implementable manner, the determination module 220 is specifically configured to: determine an outlier time point of the process operation parameters based on a preset sliding window according to the process operation data, where a determination formula for the outlier time point is expressed as the following formula:

[0159]

[0160] where, W i,t represents the value of the process operation parameter i at time t, represents the average value of the process operation parameter i within the time period [t - δ, t - 1], represents the average value of the process operation parameter i within the time period [t + δ, t + 1], σ(w i,t-δ:t-1 ) represents the standard deviation of the process operation parameter i within the time period [t - δ, t - 1], σ(w i,t+δ:t+1 ) represents the standard deviation of the process operation parameter i within the time period [t + δ, t + 1], and δ represents the length of the preset sliding window;

[0161] Determine a valid time period in the process operation data according to the outlier time point of the process operation parameters;

[0162] Determine a steady-state time period that is in a steady state within the valid time period affecting the target parameter according to the target parameter data and the process operation data.

[0163] As an implementable manner, the determination module 220 is specifically configured to: determine a set of change points at which the process operation parameters jump according to the target parameter data and the process operation data Satisfy \(t_1 \lt t_2 \lt \cdots\), based on the preset time interval \(\delta\). j Determine the steady-state points corresponding to each change point in the change point set, denoted as \(t\). j +\(\delta\) j , and the steady-state points satisfy \(t\). j +\(\delta\) j \(\lt t\). j+1 ;

[0164] Based on the steady-state points corresponding to each change point in the change point set, determine the initial steady-state point set of the process operation parameters based on the first-order autoregressive model;

[0165] If the time distance between the current steady-state point and the next steady-state point in the initial steady-state point set is less than the preset time interval, remove the current steady-state point. If the time distance between the current steady-state point and the next steady-state point in the initial steady-state point set is greater than the preset time interval, retain the current steady-state point and the next steady-state point to obtain the final steady-state point set;

[0166] Based on the final steady-state point set, determine the steady-state time period during which the process operation parameters affecting the target parameter are in a steady state.

[0167] As an implementable manner, construct module 230, specifically for: The state space model is expressed as:

[0168]

[0169] Where \(y\). t Is the target parameter, obtained by summing all hidden processes plus noise, Is the reference point of the target parameter, obtained from the previous steady-state point before time \(t\), that is Is the final steady-state point set, \(x\). i,t Represents the hidden process affected by process operation parameter \(i\) at time \(t\), which is an unknown variable, \(x\). i,t-k Represents the hidden process affected by process operation parameter \(i\) at time \(t - k\), \(k\) represents the number of past time points, \(w\). i,t-θi Represents the value of process parameter \(i\) at time \(t-\theta_i\), Represents the reference point of process parameter \(i\) at time \(t-\theta_i\), obtained from the previous steady-state point before time \(t\), that is \(\theta_i\) represents the delay value of the \(i\)-th process operation parameter, \(d\) is the number of process operation parameters \(i\), \(\alpha\). i,k , \(\beta\). i , \(c\). i Are the parameters of the autoregressive model, \(\in\). i，t , \(\epsilon\). t Are the noise of the hidden process and the observation noise respectively, and both follow a normal distribution with a mean of 0 and a variance of \(\omega\). 2 , \(\sigma\). 2 Of the normal distribution, where \(\omega\).2 According to the process parameters w i,t-θi Calculate the variance, σ 2 is based on the hidden process x i,t Calculate the variance; x d+1,t , x d+1,t-1 The influencing factors of the unknown variables hidden in the raw material properties at time t and time t-1, is the magnitude of its mean shift, x i,0 is the initial hiding process, μ i，0 For x i,t The mean of .

[0170] As an implementable manner, the determination module 220 is specifically used to: set the delay upper bound and the delay lower bound of the process operation parameter according to the process operation data, which are respectively expressed as Satisfy 0≤θ i，min ≤θ i，max ;

[0171] Based on the delay upper bound, delay lower bound and preset delay interval g i , determine the delay time candidate set of process operation parameters

[0172] Based on the state space model and the delay time candidate set, the mean absolute effect value of each variable in the process operation parameter is calculated by the following formula:

[0173]

[0174] in, is the estimated value of the state space model at time t+s given time 1 to t, For the state space model, excluding the current variable w′ at given time 1 to t i After the influence of , the estimated value at time t+s, that is, the variable values corresponding to the period [t+1, t+s] are all 0, s is the pre-selected step length, and T is the time length of the target parameter data and process operation data;

[0175] The delay time corresponding to the variable with the largest mean absolute effect value is determined as the delay time of the process operation parameter.

[0176] As an achievable manner, the determination module 220 is specifically used to: use the state space model as a proxy model, use the root mean square error between the predicted value of the preset future duration of the target parameter and the true value as the objective function, optimize the objective function through the proxy model, and obtain the objective function value;

[0177] Based on historical production data, determine the search interval of the delay time of the impact of process operation parameters on target parameters, and perform Bayesian optimization iteration on the delay time in the search interval;

[0178] When the delay time reaches a certain number of iterations or the objective function value is less than a preset threshold, the delay time of the process operation parameters corresponding to the minimum value of the objective function is selected as the delay time of the process operation parameters.

[0179] As an implementable way, the determination module 220 is specifically used for: converting the state space model into a differential equation model;

[0180] Calculating the first derivative function and the second derivative function of the state space model;

[0181] Substituting the first derivative function and the second derivative function into the differential equation model to obtain the target differential equation model;

[0182] Adjusting the parameters of the state space model according to the state space model and the target differential equation model;

[0183] According to the parameters of the state space model, determining the device control parameters of the refining device, and the device control parameters are expressed by the following formula:

[0184]

[0185] Among them, K i represents the influence degree of the process operation parameters on the target parameter. If K i >0 represents a positive influence, K i <0 represents a negative influence, τ i and ζ i represent the speed of the process operation parameters affecting the target parameter, β i , α i,1 , α i,2 are the parameters of the autoregressive model, and Δ represents the sampling interval.

[0186] As an implementable way, the verification module 240 is specifically used for: predicting the time series values of the target parameter in the future time period according to the process operation data, the state space model, and the delay time;

[0187] Verifying the rationality of the state space model and the rationality of the device control parameters according to the error and trend between the time series value and the true value.

[0188] For the same and similar parts among the above embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0189] It should be noted that in the embodiments of the present application, the use of user data may be involved. In practical applications, within the scope permitted by applicable laws and regulations in the country where it is located (such as when the user clearly consents, gives actual notice to the user, and the user clearly authorizes, etc.), user-specific personal data can be used in the solutions described herein within the scope permitted by applicable laws and regulations.

[0190] According to an embodiment of the present application, the present application also provides a computer device and a computer-readable storage medium.

[0191] As Figure 3 shown, it is a block diagram of a computer device according to an embodiment of the present application. The computer device is intended to represent various forms of digital computers or mobile devices. Among them, the digital computer may include a desktop computer, a portable computer, a workbench, a personal digital assistant, a server, a mainframe computer, and other suitable computers. The mobile device may include a tablet computer, a smart phone, a wearable device, etc.

[0192] As Figure 3 shown, the computer device 300 includes a computing unit 301, a ROM 302, a RAM 303, a bus 304, and an input / output (I / O) interface 305. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0193] The computing unit 301 can execute various processes in the method embodiments of the present application according to the computer instructions stored in the read-only memory (ROM) 302 or the computer instructions loaded from the storage unit 308 into the random access memory (RAM) 303. The computing unit 301 can be various general-purpose and / or dedicated processing components with processing and computing capabilities. The computing unit 301 may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. In some embodiments, the method provided by the embodiments of the present application can be implemented as a computer software program, which is tangibly included in a computer-readable storage medium, such as the storage unit 308.

[0194] The RAM 303 can also store various programs and data required for the operation of the computer device 300. Part or all of the computer programs can be loaded and / or installed onto the computer device 300 via the ROM 302 and / or the communication unit 309.

[0195] The input unit 306, output unit 307, storage unit 308, and communication unit 309 in the computer device 300 can be connected to the I / O interface 305. Among them, the input unit 306 can be, for example, a keyboard, mouse, touch screen, microphone, etc.; the output unit 307 can be, for example, a display, speaker, indicator light, etc. The computer device 300 can exchange information, data, etc. with other devices through the communication unit 309.

[0196] It should be noted that the device may also include other components necessary for normal operation. It may also only include the components necessary to implement the solution of this application, and does not necessarily include all the components shown in the figure.

[0197] The various embodiments of the systems and technologies described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof.

[0198] The computer instructions for implementing the method of this application can be written in any combination of one or more programming languages. These computer instructions can be provided to the computing unit 301, so that when the computer instructions are executed by a computing unit 301 such as a processor, the steps involved in the method embodiments of this application are executed.

[0199] The computer-readable storage medium provided by this application can be a tangible medium, which can contain or store computer instructions for executing the steps involved in the method embodiments of this application. The computer-readable storage medium can include, but is not limited to, storage media in the forms of electronic, magnetic, optical, electromagnetic, etc.

[0200] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for controlling parameters of a refining unit, characterized in that The method includes: Obtain the target parameter data and process operation data of the refining unit within a preset time. Among them, both the target parameter data and the process operation data are time series data. The target parameter data includes target parameters, and the process operation data includes process operation parameters; According to the target parameter data and the process operation data, determine the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state; Based on the steady-state time period, construct a state space model for evaluating the influence of process operation parameters on target parameters: According to the target parameter data, the process operation data, and the state space model, determine the delay time of the process operation parameters; According to the delay time of the process operation parameters and the state space model, determine the device control parameters of the refining unit; According to the target parameter data, the process operation data, the delay time, the state space model, and the device control parameters of the refining unit, verify the rationality of the state space model and the rationality of the device control parameters.

2. The method according to claim 1, characterized in that, The step of determining the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state according to the target parameter data and the process operation data includes: Based on the process operation data, determine the outlier time points of the process operation parameters based on a preset sliding window. The determination formula for the outlier time points is expressed as the following formula: Among them, W i，t represents the value of the process operation parameter i at time t, represents the average value of the process operation parameter i within the time period [t - δ, t - 1], represents the average value of the process operation parameter i within the time period [t + δ, t + 1], σ(w i，t-δ：t-1 ) represents the standard deviation of the process operation parameter i within the time period [t - δ, t - 1], σ(w i，t+δ：t+1 ) represents the standard deviation of the process operation parameter i within the time period [t + δ, t + 1], and δ represents the length of the preset sliding window; According to the outlier time points of the process operation parameters, determine the effective time period in the process operation data; According to the target parameter data and the process operation data, determine the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state within the effective time period.

3. The method according to claim 2, characterized in that The step of determining the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state according to the target parameter data and the process operation data includes: Determine a set of change points where the process operation parameters have jumps based on the target parameter data and the process operation data Satisfying t1 < t2 < …, based on a preset time interval δ j Determine the steady-state points corresponding to each change point in the set of change points, denoted as t j +δ j , the steady-state point satisfies t j +δ j <t j+1 ; According to the steady-state points corresponding to each change point in the change point set, determine the initial steady-state point set of the process operation parameters based on the first-order autoregressive model; If the time distance between the current steady-state point and the next steady-state point in the initial steady-state point set is less than the preset time interval, remove the current steady-state point. If the time distance between the current steady-state point and the next steady-state point in the initial steady-state point set is greater than the preset time interval, retain the current steady-state point and the next steady-state point to obtain the final steady-state point set; According to the final steady-state point set, determine the steady-state time period during which the process operation parameters affecting the target parameters are in a steady state.

4. The method according to claim 1, wherein The step of constructing a state space model for evaluating the influence of process operation parameters on target parameters based on the steady-state time period includes: The state space model is expressed as: Among them, y t is the target parameter, which is obtained by summing all hidden processes plus noise, is the reference point of the target parameter, which is obtained from the previous steady-state point before time t, that is is the set of final steady-state points, x i，t represents the hidden process affected by the process operation parameter i at time t, which is an unknown variable, x i，t-k represents the hidden process affected by the process operation parameter i at time t - k, where k represents the number of past time points used, w i，t-θi represents the value of the process parameter i at time t - θi, is the reference point of the process parameter i at time t - θi, which is obtained from the previous steady-state point before time t, that is θi represents the delay value of the i-th process operation parameter, d is the number of process operation parameters i, α i，k , β i , c i are the parameters of the autoregressive model, ∈ i，t , ε t and ε 2 are the noise of the hidden process and the observation noise respectively, and they respectively follow a normal distribution with a mean of 0 and a variance of ω 2 , σ d+1，t , x d+1，t-1 are the influence factors brought by the unknown variables hidden in the raw material properties at time t and time t - 1, is the magnitude of the mean shift, x i，0 is the initial hidden process, μ i，0 is the mean of x i，t .

5. The method according to claim 1, wherein According to the target parameter data, the process operation data, and the state space model, determine the delay time of the process operation parameters, including: Set an upper bound and a lower bound for the delay of the process operation parameters according to the process operation data, respectively expressed as Satisfying 0 ≤ θ i，min ≤ θ i，max ; Based on the upper bound of the delay, the lower bound of the delay, and a preset delay interval g i , determine an alternative set of delay times for the process operation parameters Based on the state space model and the delay time alternative set, calculate the average absolute effect value of each variable in the process operation parameters through the following formula: in, is the estimated value of the state space model at time t+s given time 1 to t, For the state space model, excluding the current variable w′ at given time 1 to t i The estimated value at time t+s after the influence of , that is, the variable values corresponding to the period [t+1, t+s] are all 0, s is the pre-selected step length, and T is the time length of the target parameter data and the process operation data; Determine the delay time corresponding to the variable with the largest average absolute effect value as the delay time of the process operation parameters.

6. The method according to claim 1, wherein Determining the delay time of the process operation parameters according to the target parameter data, the process operation data, and the state space model includes: Taking the state space model as a surrogate model, taking the root mean square error between the predicted value and the true value of the preset future duration of the target parameter as the objective function, and optimizing the objective function through the surrogate model to obtain the objective function value; Based on historical production data, determining the search interval of the delay time of the influence of the process operation parameters on the target parameter, and performing Bayesian optimization iteration on the delay time within the search interval; When the delay time reaches a certain number of iterations or the objective function value is less than the preset threshold, selecting the delay time of the process operation parameter corresponding to the minimum value of the objective function as the delay time of the process operation parameter.

7. The method according to claim 1, characterized in that, Determining the device control parameters of the refining device according to the delay time of the process operation parameter and the state space model includes: Converting the state space model into a differential equation model; Calculating the first derivative function and the second derivative function of the state space model; Substituting the first derivative function and the second derivative function into the differential equation model to obtain the target differential equation model; Adjusting the parameters of the state space model according to the state space model and the target differential equation model; Determining the device control parameters of the refining device according to the parameters of the state space model, and the device control parameters are expressed by the following formula: Among them, K i represents the influence degree of process operation parameters on the target parameter. If K i > 0, it represents a positive influence. If K i < 0, it represents a negative influence. τ i and ζ i represent the speed at which process operation parameters affect the target parameter. β i , α i，1 , α i，2 are the parameters of the autoregressive model, and Δ represents the sampling interval.

8. The method according to claim 1, characterized in that, Verifying the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, the process operation data, the state space model, the delay time, and the device control parameters of the refining device includes: Predicting the time series values of the target parameter within a future time period according to the process operation data, the state space model, and the delay time; Verifying the rationality of the state space model and the rationality of the device control parameters according to the error and trend between the time series values and the true values.

9. A parameter control device for a refining unit, characterized in that, The device includes: An acquisition module, configured to acquire target parameter data and process operation data of a refining device within a preset time, where the target parameter data and the process operation data are both time series data, the target parameter data includes target parameters, and the process operation data includes process operation parameters; A determination module, configured to determine a steady state time period in which the process operation parameters affecting the target parameter are in a steady state according to the target parameter data and the process operation data; A construction module, configured to construct a state space model for evaluating the influence of process operation parameters on target parameters based on the steady state time period; The determination module is further configured to determine the delay time of the process operation parameter according to the target parameter data, the process operation data, and the state space model; The determination module is further configured to determine the device control parameters of the refining device according to the delay time of the process operation parameter and the state space model; A verification module, configured to verify the rationality of the state space model and the rationality of the device control parameters according to the target parameter data, the process operation data, the delay time, the state space model, and the device control parameters of the refining device.

10. A computer device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores computer instructions executable by the at least one processor, and the computer instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-8.

Images