Coke extraction temperature prediction method and equipment of intelligent coke extraction system, medium and product

Through the Kalman filtering method of the intelligent coking system, the state estimation and covariance matrix update are used to use multiple factors, which solves the problem of difficult control of the coking temperature in dry coking quenching, realizes continuous prediction and optimization of temperature, and improves the Production efficiency and product quality.

CN119088129AActive Publication Date: 2024-12-06ANSHAN HUATAI ENVIRONMENTAL ENERGY ENG TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411180778.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-12-06
Estimated Expiration
2044-08-26

AI Technical Summary

Technical Problem

During the dry coking quenching process, it is difficult to control the coking discharge temperature, resulting in thermal energy loss, equipment burning or increasing fan load, affecting continuous production.

Method used

Using the Kalman filtering method of intelligent coking system, state estimation and covariance matrix update are performed to obtain equipment data, including coke drop speed, circulating gas distribution and flow rate, system structure and materials, gas composition and temperature, etc., and predict dryness. The coke quenching and discharge temperature achieves continuous control of temperature.

Benefits of technology

The dry coke quenching process is optimized, production efficiency and product quality are improved, production costs are reduced, economic benefits are improved, and the stability of coke discharge temperature and equipment safety are ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088129A_ABST
    Figure CN119088129A_ABST
Patent Text Reader

Abstract

The invention discloses a coke extraction temperature prediction method and device of an intelligent coke extraction system, a medium and a product, and relates to the field of intelligent coke extraction system control. Determining an initial state estimation value and a covariance matrix corresponding to the initial state estimation value according to the equipment data; according to the initial state estimation value and the covariance matrix corresponding to the initial state estimation value, predicting to obtain a state estimation value at the current moment and a covariance matrix corresponding to the state estimation value at the current moment; determining a Kalman gain; and updating the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment, and carrying out recursive iteration on the updated state estimation value at the current moment and the updated covariance matrix corresponding to the state estimation value at the current moment to obtain the coke dry quenching and discharging prediction temperature. According to the method, continuous prediction of the coke discharge temperature of dry quenching can be achieved, and then the coke discharge temperature is well controlled.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent defocusing system control, and in particular to a method, equipment, medium and product for predicting defocusing temperature of an intelligent defocusing system. Background Art

[0002] Coke Dry Quenching (CDQ) is a new coke quenching method compared to wet coke quenching. The coke dry quenching and waste heat power generation system uses inert gas nitrogen as a carrier, which is passed into the dry quenching furnace to cool the hot coke, cooling the coke from 1000℃ to below 180℃ before being discharged. The heat of the circulating inert hot gas is recovered to generate steam for power generation.

[0003] During the coking process, the coke oven discharges coke intermittently, and dry coke quenching is a continuous coke discharge. The coke discharge temperature is an important indicator to ensure the safety of dry coke quenching and continuous production. Controlling the coke discharge temperature is a very important task. If the coke discharge temperature is too high, it will cause heat energy loss and may burn the coke discharge and coke transportation equipment, making it impossible to achieve the purpose of continuous production; if the temperature is too low, it will increase the fan load and reduce production.

[0004] Therefore, how to control the decoking temperature has become a technical problem that needs to be solved urgently in this field. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, medium and product for predicting the coke discharge temperature of an intelligent coke discharge system, which can realize continuous prediction of the dry coke quenching coke discharge temperature and thus control the coke discharge temperature.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] In a first aspect, the present invention provides a method for predicting the defocusing temperature of an intelligent defocusing system, the method comprising:

[0008] Obtain equipment data; the equipment data includes: coke discharge temperature at several moments and corresponding related factors; the related factors include: coke descent speed and distribution, circulating gas distribution and flow rate, system internal structure and materials, circulating gas composition and temperature, and operation and control.

[0009] According to the equipment data, an initial state estimate and a covariance matrix corresponding to the initial state estimate are determined; the initial state estimate is a state estimate at a previous moment; and the covariance matrix corresponding to the initial state estimate is a matrix determined according to process noise and observation noise.

[0010] According to the initial state estimation value and the covariance matrix corresponding to the initial state estimation value, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are predicted.

[0011] The Kalman gain is determined according to the covariance matrix, the observation matrix and the observation noise covariance corresponding to the state estimation value at the current moment; the observation matrix is ​​a scalar; and the observation noise covariance is a known condition of the filter.

[0012] According to the state estimation value at the current moment, the covariance matrix corresponding to the state estimation value at the current moment, the observation value at the current moment and the Kalman gain, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are updated to obtain the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment.

[0013] The updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment are recursively iterated to obtain the dry coke quenching coke discharge prediction temperature.

[0014] Optionally, before the step of determining the initial state estimation value and the covariance matrix corresponding to the initial state estimation value according to the device data, the method for predicting the defocusing temperature of the intelligent defocusing system further includes:

[0015] The device data is processed; the data processing includes: data cleaning, data aggregation and correlation analysis.

[0016] Optionally, based on the initial state estimate and the covariance matrix corresponding to the initial state estimate, the expression of the state estimate at the current moment and the covariance matrix corresponding to the state estimate at the current moment is predicted as follows:

[0017] x_k^-=F*x_{k-1};

[0018] P_k^-=F*P_{k-1}*F'+Q;

[0019] Among them, x_k^- is the state estimate at the current moment, F is the state transfer matrix, x_{k-1} is the state estimate at the previous moment, P_k^- is the covariance matrix corresponding to the state estimate at the current moment, P_{k-1} is the covariance matrix corresponding to the state estimate at the previous moment, and Q is the process noise covariance.

[0020] Optionally, the expression of the Kalman gain is:

[0021] K_k=P_k^-*H'*(H*P_k^-*H'+R)^-1;

[0022] Among them, K_k is the Kalman gain, P_k^- is the covariance matrix corresponding to the state estimate at the current moment, H is the observation matrix, and R is the observation noise covariance.

[0023] Optionally, according to the state estimate value at the current moment, the covariance matrix corresponding to the state estimate value at the current moment, the observation value at the current moment and the Kalman gain, the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment are updated, and the expression of the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment is obtained as follows:

[0024] x_k_l=x_k^-+K_k*(z_k_l-H*x_k^-);

[0025] P_k=(1-K_k*H)*P_k^-;

[0026] Among them, x_k_l is the updated state estimate at the current moment, x_k^- is the state estimate at the current moment, K_k is the Kalman gain, z_k_l is the observation value at the current moment, H is the observation matrix, P_k is the covariance matrix corresponding to the updated state estimate at the current moment, and P_k^- is the covariance matrix corresponding to the state estimate at the current moment.

[0027] Optionally, recursively iterating the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment to obtain the dry coke quenching coke discharge prediction temperature specifically includes:

[0028] Determine whether the current moment is the predicted moment and obtain a determination result.

[0029] If the judgment result is no, the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment are used as the initial state estimate value and the covariance matrix corresponding to the initial state estimate value, and the step of predicting the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment is returned based on the initial state estimate value and the covariance matrix corresponding to the initial state estimate value.

[0030] If the judgment result is yes, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are input into the dry quenching and coking temperature system model to obtain the dry quenching and coking predicted temperature; the dry quenching and coking temperature system model includes a state equation and an observation equation.

[0031] Optionally, the expression of the CDQ coke discharge temperature system model is:

[0032] x_k=F*x_{k-1}+B*u_k+w_k+a*(Δt*CokeDischarge_k+b);

[0033] z_k=H*x_k+v_k;

[0034] Among them, x_k is the state equation, F is the state transfer matrix, x_{k-1} is the state estimate at the previous moment, B is the control matrix, u_k is the control vector, w_k is the process noise, a is the first model parameter determined by experiments or data fitting, Δt is the time period, CokeDischarge_k is the coke discharge per unit time, b is the second model parameter determined by experiments or data fitting, z_k is the observation equation, H is the observation matrix, and v_k is the observation noise.

[0035] In a second aspect, the present invention provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for predicting the defocusing temperature of an intelligent defocusing system.

[0036] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for predicting the defocusing temperature of an intelligent defocusing system.

[0037] In a fourth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting the defocusing temperature of an intelligent defocusing system.

[0038] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0039] The present invention provides a method, device, medium and product for predicting the coke discharge temperature of an intelligent coke discharge system. The method first acquires device data, fully considers the coke discharge temperature of dry coke quenching and corresponding associated factors, and then determines an initial state estimation value and a covariance matrix corresponding to the initial state estimation value according to the device data. By predicting and updating the initial state estimation value and the covariance matrix corresponding to the initial state estimation value, the dry coke quenching predicted temperature can be obtained, thereby controlling the coke discharge temperature, optimizing the dry coke quenching process, improving production efficiency and product quality, reducing production costs and improving economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic flow chart of a method for predicting defocusing temperature of an intelligent defocusing system provided in one embodiment of the present invention.

[0042] Figure 2 A schematic diagram of the working principle of a dry quenching furnace provided in one embodiment of the present invention.

[0043] Figure 3 A schematic diagram of a coke removal plan provided in one embodiment of the present invention.

[0044] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0047] The scheme adopted by the present invention comprises:

[0048] (1) Establish a system model.

[0049] Kalman filtering is a recursive filtering algorithm used to estimate the true state of a system from a series of incomplete and noisy observations. Kalman filtering is based on the state equation and observation equation of the system, and gradually improves the accuracy of the estimation by iteratively updating the estimated value and covariance matrix. In matrix Kalman filtering, both the state and observation are multidimensional vectors, so matrices are used to represent the parameters of the state equation and observation equation.

[0050] Assuming that the CDQ decoking temperature system is a linear system, its state changes can be described by linear equations.

[0051] The state is estimated and filtered by operating and updating the matrix.

[0052] Establish state equation and observation equation. The state equation describes the change law of system state over time, and the observation equation describes the relationship between the observed value and the system state.

[0053] (2) Initialize filter parameters.

[0054] Set the initial state estimates and their covariance matrix.

[0055] According to the system characteristics and actual conditions, the covariance matrix of process noise and observation noise is set.

[0056] (3) Prediction step:

[0057] The state estimate and its corresponding covariance matrix at the previous moment are used to predict the state estimate and its corresponding covariance matrix at the current moment.

[0058] (4) Update step.

[0059] The Kalman gain is calculated based on the covariance matrix corresponding to the state estimate at the current moment.

[0060] Using the Kalman gain and observations, update the current state estimate and its corresponding covariance matrix.

[0061] (5) Recursive iteration.

[0062] The updated state estimation value and its corresponding covariance matrix are used as the initial value at the next moment, and the prediction step and the update step are repeated to achieve continuous prediction of the CDQ discharge temperature.

[0063] In an exemplary embodiment, Figure 1 As shown, a method for predicting the defocusing temperature of an intelligent defocusing system is provided, which is executed by a computer device. In an embodiment of the present invention, the following steps S1 to S6 are included. Among them:

[0064] S1: Obtain equipment data; the equipment data includes: coke discharge temperature at several moments and corresponding related factors; the related factors include: coke descent speed and distribution, circulating gas distribution and flow rate, system internal structure and materials, circulating gas composition and temperature, and operation and control.

[0065] Among them, according to the process analysis of the dry quenching system, the related factors of the dry quenching coke discharge temperature include:

[0066] 1) The falling speed and distribution of coke.

[0067] The falling speed and distribution of coke in the CDQ furnace have a significant impact on the coke discharge temperature. For example, an unreasonable installation depth of the CDQ furnace regulating rod may cause uneven coke falling and coke deflection to a certain area, thus affecting the uniformity of the coke discharge temperature.

[0068] like Figure 2 As shown, in order to monitor whether the temperature of coke inside the CDQ furnace cooling section is uniform, 4 thermocouple thermometers are installed on the upper part of the furnace wall of the CDQ furnace cooling section, namely T4A, T4B, T4C and T4D (not shown in the figure), and 4 thermocouple thermometers are installed on the lower part of the furnace wall, namely T3A, T3B, T3C and T3D (not shown in the figure). Uneven coke descent may lead to a large temperature difference of coke on the same level, such as the temperature of T3C point of the CDQ furnace is about 50℃ higher than that of T3A, B, and D, and the temperature of T4C point is about 150℃ higher than that of T4A, B, and D.

[0069] 2) Distribution and flow rate of circulating gas.

[0070] Deviation in the distribution of circulating gas will affect the coke discharge temperature. The cooling circulating gas in the CDQ furnace is usually distributed according to the central and peripheral air intake, but the deflection of coke may cause the air flow distribution to change, affecting the coke discharge temperature.

[0071] The flow rate of circulating gas will also affect the coke discharge temperature. For example, during the annual maintenance of CDQ, the “bull leg” size becomes wider, which may cause the resistance of circulating gas at the chute to increase and the flow rate to increase, thus affecting the coke discharge temperature.

[0072] 3) System internal structure and materials.

[0073] Severe wear of the refractory materials on the inner wall of the furnace chamber may lead to a reduction in the ventilation area of ​​the ramp area, affecting the circulating air volume and further affecting the coke discharge temperature.

[0074] If the system runs for a long time, the accumulated coke powder may block the ventilation holes, further reducing the ventilation area, forming a vicious cycle and causing the coke discharge temperature to be too high.

[0075] 4) Composition and temperature of circulating gas.

[0076] A high level of combustible gas content (H2, CO) in the circulating gas or the introduction of a large amount of air may cause the boiler inlet temperature T6 to rise sharply, thereby affecting the coke discharge temperature.

[0077] The inlet temperature of the circulating gas will also affect the coke discharge temperature. For example, an inlet temperature exceeding the design temperature may result in a higher coke discharge temperature.

[0078] 5) Operation and control.

[0079] Untimely operation or improper control by the operator may also lead to poor control of the coke discharge temperature, exceeding the maximum coke discharge temperature required by the design.

[0080] In summary, the discharge temperature of CDQ is closely related to many factors, including the falling speed and distribution of coke, the distribution and flow rate of circulating gas, the internal structure and materials of the system, the composition and temperature of circulating gas, and operation and control.

[0081] S2: Determine the initial state estimate and the covariance matrix corresponding to the initial state estimate based on the device data; the initial state estimate is the state estimate at the previous moment; the covariance matrix corresponding to the initial state estimate is a matrix determined based on process noise and observation noise.

[0082] S3: According to the initial state estimation value and the covariance matrix corresponding to the initial state estimation value, predict the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment.

[0083] S4: Determine the Kalman gain according to the covariance matrix, observation matrix and observation noise covariance corresponding to the state estimate value at the current moment; the observation matrix is ​​a scalar; and the observation noise covariance is a known condition of the filter.

[0084] S5: According to the state estimation value at the current moment, the covariance matrix corresponding to the state estimation value at the current moment, the observation value at the current moment and the Kalman gain, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are updated to obtain the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment.

[0085] S6: recursively iterate the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment to obtain the CDQ coke discharge prediction temperature.

[0086] The implementation of the above steps S1 to S6 can realize the continuous prediction of the dry coke quenching discharge temperature, thereby controlling the coke discharge temperature, optimizing the dry coke quenching process, improving production efficiency and product quality, thereby reducing production costs and improving economic benefits.

[0087] In another exemplary embodiment of the present invention, before step S2, the method for predicting the defocusing temperature of the intelligent defocusing system further includes:

[0088] The device data is processed; the data processing includes: data cleaning, data aggregation and correlation analysis.

[0089] In this embodiment, the device data within a set time range is obtained, and the data is stored and processed.

[0090] a) Data storage.

[0091] The associated items may include coke particle size, coke descent velocity, cooling gas velocity distribution, circulating air volume, inlet gas temperature, combustible gas composition in the circulating gas, etc.

[0092] Store the coke pushing plan and make a coke removal plan based on the coke pushing plan, such as Figure 3 shown.

[0093] b) Data processing.

[0094] Data cleaning:

[0095] Remove duplicate, erroneous or invalid data records.

[0096] Check the integrity of the data to ensure that there are no missing values ​​in key fields (such as exhaust temperature, timestamp, etc.).

[0097] Data Aggregation:

[0098] As needed, perform aggregate calculations on the defocusing temperature and its related item data, such as the average value, maximum value, minimum value, standard deviation, etc.

[0099] Association analysis:

[0100] Analyze the correlation between defocusing temperature and related items.

[0101] Statistical methods (such as correlation coefficient, regression analysis, etc.) can be used to quantify the degree of association.

[0102] That is, the method for predicting the defocusing temperature of the intelligent defocusing system includes:

[0103] S1: Acquire equipment data; the equipment data includes: coke discharge temperature at several moments and corresponding associated factors; the associated factors include: coke drop speed and distribution, circulation gas distribution and flow rate, system internal structure and materials, circulation gas composition and temperature, and operation and control;

[0104] S2: Process the device data; the data processing includes: data cleaning, data aggregation and correlation analysis.

[0105] S3: Determine the initial state estimate and the covariance matrix corresponding to the initial state estimate based on the device data; the initial state estimate is the state estimate at the previous moment; the covariance matrix corresponding to the initial state estimate is a matrix determined based on process noise and observation noise.

[0106] S4: According to the initial state estimation value and the covariance matrix corresponding to the initial state estimation value, predict the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment.

[0107] S5: Determine the Kalman gain according to the covariance matrix, observation matrix and observation noise covariance corresponding to the state estimation value at the current moment; the observation matrix is ​​a scalar; and the observation noise covariance is a known condition of the filter.

[0108] S6: According to the state estimation value at the current moment, the covariance matrix corresponding to the state estimation value at the current moment, the observation value at the current moment and the Kalman gain, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are updated to obtain the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment.

[0109] S7: recursively iterate the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment to obtain the CDQ coke discharge prediction temperature.

[0110] In another exemplary embodiment of the present invention, a training set is used to define a model to obtain a dry quenching and coke discharge temperature system model, and a test set is transferred to the dry quenching and coke discharge temperature system model to predict the dry quenching and coke discharge temperature to obtain a predicted value of the coke discharge temperature.

[0111] Specifically, define the state variables:

[0112] Assuming x is the exhaust temperature, the state variable can be expressed as x_k, where k is the time step (for example, one time step every 5 minutes) and k-1 represents the previous time step.

[0113] Equation of state:

[0114] Create a model to describe how the exhaust temperature changes over time. This is usually based on physical principles or historical data. A simple linear model can be expressed as:

[0115] x_k=F*x_{k-1}+B*u_k+w_k+a*(Δt*CokeDischarge_k+b);

[0116] Where x_k is the state equation, F is the state transfer matrix (in the univariate case, it is a scalar close to 1 but may be slightly different to reflect natural changes in temperature), x_{k-1} is the state estimate at the previous moment, B is the control matrix (0 if there is no external control input), u_k is the control vector (0 if there is no external control input), w_k is the process noise (usually assumed to be Gaussian), a is the first model parameter determined by experiments or data fitting, Δt is the time period, CokeDischarge_k is the amount of coke discharged per unit time, and b is the second model parameter determined by experiments or data fitting.

[0117] Observation equation:

[0118] In this embodiment, there is a temperature sensor to measure the decoking temperature. The observation equation describes the relationship between the actual state and the observed value:

[0119] z_k=H*x_k+v_k;

[0120] Where z_k is the observation equation, H is the observation matrix (in the univariate case, it is a scalar, usually 1), and v_k is the observation noise (assumed to be Gaussian).

[0121] Matrix Kalman filter equation:

[0122] In step S3, based on the initial state estimate and the covariance matrix corresponding to the initial state estimate, the expression of the state estimate at the current moment and the covariance matrix corresponding to the state estimate at the current moment is predicted as follows:

[0123] x_k^-=F*x_{k-1};

[0124] P_k^-=F*P_{k-1}*F'+Q;

[0125] Among them, x_k^- is the state estimate at the current moment (prior state estimate, that is, the result at moment k predicted based on the optimal estimate at the previous moment {k-1 moment}), F is the state transfer matrix, x_{k-1} is the state estimate at the previous moment, P_k^- is the covariance matrix corresponding to the state estimate at the current moment (prior estimation error covariance), P_{k-1} is the covariance matrix corresponding to the state estimate at the previous moment, and Q is the process noise covariance. This parameter is used to represent the error between the state transition matrix and the actual process, and is the state variable used by the Kalman filter to estimate the discrete-time process.

[0126] In step S4, the expression of the Kalman gain is:

[0127] K_k=P_k^-*H'*(H*P_k^-*H'+R)^-1;

[0128] Among them, K_k is the Kalman gain, P_k^- is the covariance matrix corresponding to the state estimate at the current moment, H is the observation matrix, and R is the observation noise covariance. When the filter is actually implemented, the measurement noise covariance R can generally be observed and is a known condition of the filter.

[0129] In step S5, according to the state estimate value at the current moment, the covariance matrix corresponding to the state estimate value at the current moment, the observation value at the current moment and the Kalman gain, the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment are updated, and the expression of the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment is obtained:

[0130] x_k_l=x_k^-+K_k*(z_k_l-H*x_k^-);

[0131] P_k=(1-K_k*H)*P_k^-;

[0132] Among them, x_k_l is the updated state estimate at the current moment (the posterior state estimate, also called the optimal estimate, is one of the results of filtering), x_k^- is the state estimate at the current moment, K_k is the Kalman gain, z_k_l is the observation value at the current moment (i.e., the sensor reading), H is the observation matrix, P_k is the covariance matrix corresponding to the updated state estimate at the current moment (the posterior estimation error covariance, representing the uncertainty of the state, is one of the results of the filter), and P_k^- is the covariance matrix corresponding to the state estimate at the current moment.

[0133] In another exemplary embodiment of the present invention, in step S6, specifically including:

[0134] S61: Determine whether the current moment is the predicted moment and obtain a determination result.

[0135] S62: If the judgment result is no, then the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment are used as the initial state estimate value and the covariance matrix corresponding to the initial state estimate value, and the step of predicting the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment is returned based on the initial state estimate value and the covariance matrix corresponding to the initial state estimate value.

[0136] S63: If the judgment result is yes, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are input into the dry quenching and coking temperature system model to obtain the dry quenching and coking temperature prediction; the dry quenching and coking temperature system model includes a state equation and an observation equation.

[0137] For example, predict the decoking temperature after 30 minutes.

[0138] If the time step is 5 minutes, then you need to predict the state after 6 time steps. Starting from the current state, repeatedly apply the prediction equation 6 times to get the predicted value after 30 minutes.

[0139] In summary, the beneficial effects of the present invention are as follows:

[0140] Improvement of production stability and equipment safety: The CDQ coke discharge temperature should be controlled at 180-200°C, which helps to fully absorb the sensible heat of red coke, improve thermal energy utilization, and ensure uniform coke discharge temperature, which can reduce the load of the circulating fan for circulating air volume and reduce adverse effects on the temperature and pressure of the gas circulation system.

[0141] Product quality: Appropriate coke discharge temperature is conducive to ensuring the quality of coke. Too high or too low temperature may affect the physical and chemical properties of coke.

[0142] Economic benefits: Controlling the coke discharge temperature can optimize the dry quenching process, improve production efficiency and product quality, thereby reducing production costs and improving economic benefits.

[0143] The present invention also provides an application scenario, which applies the above-mentioned intelligent defocusing system defocusing temperature prediction method. Specifically: the intelligent defocusing system defocusing temperature prediction method provided in this embodiment can be applied in the intelligent defocusing scenario. The intelligent defocusing scenario includes an equipment data acquisition link, a data prediction update link, and a recursive iteration link; after acquiring the equipment data, it enters the data prediction update link, and after the matrix Kalman filter, the updated data is obtained, and then by repeating the data prediction update link, the dry coke quenching defocusing prediction temperature can be obtained.

[0144] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store device data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the defocusing temperature of an intelligent defocusing system is implemented.

[0145] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0146] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above-mentioned method embodiments are implemented when the processor executes the computer program.

[0147] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0148] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0150] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0151] The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0152] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting the de-coking temperature of an intelligent de-coking system, characterized in that: The method for predicting the de-coking temperature of the intelligent de-coking system includes: Acquire equipment data; the equipment data includes: coke discharge temperature at several moments and corresponding related factors; the related factors include: coke drop rate and distribution, circulation gas distribution and flow rate, system internal structure and materials, circulation gas composition and temperature, and operation and control; Determine, based on the device data, an initial state estimate and a covariance matrix corresponding to the initial state estimate; the initial state estimate is a state estimate at a previous moment; the covariance matrix corresponding to the initial state estimate is a matrix determined based on process noise and observation noise; Predicting the current state estimate and the covariance matrix corresponding to the current state estimate based on the initial state estimate and the covariance matrix corresponding to the initial state estimate; Determine the Kalman gain based on the covariance matrix, the measurement matrix, and the observation noise covariance corresponding to the state estimate at the current moment; the measurement matrix is ​​a scalar; and the observation noise covariance is a known condition of the filter; According to the state estimate value at the current moment, the covariance matrix corresponding to the state estimate value at the current moment, the observation value at the current moment, and the Kalman gain, the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment are updated to obtain the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment; Recursive iteration is performed on the updated state estimation value at the current moment and the covariance matrix corresponding to the updated state estimation value at the current moment to obtain the CDQ coke discharge prediction temperature.

2. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 1, characterized in that: Before the step of determining the initial state estimation value and the covariance matrix corresponding to the initial state estimation value based on the device data, the method for predicting the defocusing temperature of the intelligent defocusing system further includes: The device data is processed; the data processing includes: data cleaning, data aggregation and correlation analysis.

3. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 1, characterized in that: According to the initial state estimate and the covariance matrix corresponding to the initial state estimate, the expression of the state estimate at the current moment and the covariance matrix corresponding to the state estimate at the current moment is predicted as follows: x_k^-=F*x_{k-1}; P_k^-=F*P_{k-1}*F'+Q; Among them, x_k^- is the state estimate at the current moment, F is the state transfer matrix, x_{k-1} is the state estimate at the previous moment, P_k^- is the covariance matrix corresponding to the state estimate at the current moment, P_{k-1} is the covariance matrix corresponding to the state estimate at the previous moment, and Q is the process noise covariance.

4. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 1, characterized in that: The expression of the Kalman gain is: K_k=P_k^-*H'*(H*P_k^-*H'+R)^-1; Where K_k is the Kalman gain, P_k^- is the covariance matrix corresponding to the state estimate at the current moment, H is the observation matrix, and R is the observation noise covariance.

5. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 1, characterized in that: According to the state estimate value at the current moment, the covariance matrix corresponding to the state estimate value at the current moment, the observation value at the current moment and the Kalman gain, the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment are updated, and the expression of the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment is obtained: x_k_l=x_k^-+K_k*(z_k_l-H*x_k^-); P_k=(1-K_k*H)*P_k^-; Among them, x_k_l is the updated state estimate at the current moment, x_k^- is the state estimate at the current moment, K_k is the Kalman gain, z_k_l is the observation value at the current moment, H is the observation matrix, P_k is the covariance matrix corresponding to the updated state estimate at the current moment, and P_k^- is the covariance matrix corresponding to the state estimate at the current moment.

6. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 1, characterized in that: Recursively iterating the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment to obtain the CDQ coke discharge prediction temperature specifically includes: Determine whether the current moment is the predicted moment, and obtain a determination result; If the judgment result is no, the updated state estimate value at the current moment and the covariance matrix corresponding to the updated state estimate value at the current moment are used as the initial state estimate value and the covariance matrix corresponding to the initial state estimate value, and the step of predicting the state estimate value at the current moment and the covariance matrix corresponding to the state estimate value at the current moment is returned based on the initial state estimate value and the covariance matrix corresponding to the initial state estimate value; If the judgment result is yes, the state estimation value at the current moment and the covariance matrix corresponding to the state estimation value at the current moment are input into the dry quenching and coke discharge temperature system model to obtain the dry quenching and coke discharge predicted temperature; the dry quenching and coke discharge temperature system model includes a state equation and an observation equation.

7. The method for predicting the de-coking temperature of an intelligent de-coking system according to claim 6, characterized in that: The expression of the CDQ coke discharge temperature system model is: x_k=F*x_{k-1}+B*u_k+w_k+a*(Δt*CokeDischarge_k+b); z_k=H*x_k+v_k; Where x_k is the state equation, F is the state transfer matrix, x_{k-1} is the state estimate at the previous moment, B is the control matrix, u_k is the control vector, w_k is the process noise, a is the first model parameter determined by experiments or data fitting, Δt is the time period, CokeDischarge_k is the coke discharge per unit time, b is the second model parameter determined by experiments or data fitting, z_k is the observation equation, H is the observation matrix, and v_k is the observation noise.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the defocusing temperature of the intelligent defocusing system according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the defocusing temperature of the intelligent defocusing system according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the defocusing temperature of the intelligent defocusing system according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Temperature and pressure control method of dry quenched coke circulating system

    CN102314184A

  • Dry quenching system prediction control method based on mechanism and data fusion

    CN116859727A

  • Controller, method, and program

    JP2023025646A

  • Treatment device, treatment method, and program

    JP2023039669A