Adaptive and self-updating coal gasification simulation method and system based on digital twin

Abstract

The digital twin-based adaptive self-updating coal gasification simulation method and system belong to the field of digital twin technology. The method of the present invention includes: collecting coal gasification field data from a server or database, the coal gasification field data includes process parameters and equipment parameters; constructing a data processing flow, processing the collected coal gasification field data, and obtaining steady-state data; based on the operation mechanism of each device, respectively constructing a steady-state mechanism model, and obtaining model output data based on the steady-state mechanism model and the coal gasification field data, and performing a deviation comparison between the model output data and the coal gasification field data, and fitting the equipment characteristic curve or verifying and updating the equipment operation mechanism in the steady-state mechanism model according to the deviation comparison result; based on the coal gasification process and the steady-state mechanism model, constructing a mechanism dynamic model, and updating the mechanism dynamic model based on the equipment characteristic curve. The present invention can adapt to the characteristic changes of the field equipment and ensure the effect of operation training.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and in particular to a digital twin-based adaptive and self-updating coal gasification simulation method and system. Background Art

[0002] Since there are many safety hazards in the coal gasification production process, a coal gasification process simulation system is generally built to train on-the-job personnel on system startup and shutdown and accident operation. The coal gasification simulation system has characteristic parameters corresponding to the on-site equipment and can truly reflect the operation of the on-site equipment.

[0003] However, as the operating time of on-site equipment increases, its characteristics often change. For example, the use of liquid slag removal in the gasification process causes large valve losses in the slag removal system, and the raw coal gas generated by the gasifier carries a certain amount of coal slag ash, which is more likely to cause pipeline blockage in the synthesis gas washing system and slag water treatment section. As the operating time goes by, the characteristics of the equipment have changed dramatically, so the simulation system built based on a certain stage is no longer applicable to the current operating status of the device.

[0004] Therefore, as the running time of on-site equipment increases, the simulation system built in the early stage cannot accurately reflect the actual status of the current on-site equipment, affecting the effect of operation training. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the above-mentioned prior art and to provide an adaptive and self-updating coal gasification simulation method and system based on digital twins, which can adapt to the characteristic changes of on-site equipment and ensure the effect of operation training.

[0006] The objective of the present invention is achieved through the following technical solutions: The adaptive and self-updating coal gasification simulation method based on digital twins includes: Collect coal gasification field data from the server or database, including process parameters and equipment parameters; Construct a data processing flow to process the collected coal gasification field data and obtain steady-state data; Based on the operation mechanism of each equipment, a steady-state mechanism model is constructed respectively, and the model output data is obtained based on the steady-state mechanism model and the coal gasification field data. The deviation is compared between the model output data and the coal gasification field data. According to the deviation comparison results, the equipment characteristic curve is fitted or the equipment operation mechanism in the steady-state mechanism model is verified and updated; Based on the coal gasification process and steady-state mechanism model, a mechanism dynamic model is constructed, and the mechanism dynamic model is updated based on the equipment characteristic curve.

[0007] Preferably, the data processing method used in constructing the data processing flow includes: Outlier processing: identifying and marking outliers in coal gasification field data, and deleting or replacing outliers; Missing value processing: detect missing values ​​in coal gasification field data and supplement them; Noise filtering: noise filtering of coal gasification field data; Data clustering, using clustering algorithms to group coal gasification field data; Steady-state screening, based on the set steady-state threshold, screens out the coal gasification field data within the steady-state threshold range.

[0008] Preferably, the device characteristic curve is fitted or the device operation mechanism in the steady-state mechanism model is verified and updated according to the deviation comparison result, including: if the deviation comparison result is greater than a set ratio, the device operation mechanism in the steady-state mechanism model is verified and updated; otherwise, the device characteristic curve is fitted.

[0009] Preferably, the fitting to obtain the device characteristic curve comprises: Input multiple sets of field input data into the steady-state mechanism model respectively to obtain multiple model output data; Based on a plurality of field input data and a plurality of model output data, a plurality of coordinate points of a characteristic curve are formed; Based on multiple coordinate points, a characteristic curve is fitted.

[0010] Preferably, the constructing of the mechanism dynamic model includes: based on the mechanism dynamic model bit number and the DCS control system bit number, transmitting data to the DCS control system and receiving a control command of the DCS control system.

[0011] The embodiments of this specification also provide a coal gasification simulation system that can be adaptively and self-updated based on digital twins, including: A collection module is used to collect coal gasification field data from a server or database, where the coal gasification field data includes process parameters and equipment parameters; The steady-state screening module is used to provide multiple data processing units, construct a data processing flow by selecting the data processing units, process the collected coal gasification field data, and obtain steady-state data; The equipment verification module is used to construct steady-state mechanism models based on the operating mechanism of each device, obtain model output data based on the steady-state mechanism model and coal gasification field data, compare the deviations between the model output data and the coal gasification field data, and obtain the equipment characteristic curve by fitting or verify the equipment operating mechanism in the updated steady-state mechanism model based on the deviation comparison results; The mechanism simulation module is used to construct a mechanism dynamic model based on the coal gasification process and steady-state mechanism model, and to update the mechanism dynamic model based on the equipment characteristic curve.

[0012] Preferably, the steady-state screening module comprises: An outlier processing unit is used to identify and mark outliers in the coal gasification field data, and delete or replace the outliers; Missing value processing unit, used to detect missing values ​​in coal gasification field data and supplement them; A noise filtering unit, used for performing noise filtering on coal gasification field data; A data clustering unit, used to group coal gasification field data using a clustering algorithm; The steady-state screening unit is used to screen out the coal gasification field data within the steady-state threshold range based on the set steady-state threshold.

[0013] Preferably, the device verification module comprises: The steady-state mechanism model unit is used to construct a steady-state mechanism model based on the operating mechanism of each device; The equipment characteristic verification unit is used to obtain the model output data based on the steady-state mechanism model and the coal gasification field data, and to compare the deviations between the model output data and the coal gasification field data. If the deviation comparison result is greater than the set ratio, the equipment operation mechanism in the steady-state mechanism model is verified and updated; otherwise, the equipment characteristic curve is obtained by fitting.

[0014] Preferably, the device characteristic verification unit comprises: The model output subunit is used to input multiple sets of field input data into the steady-state mechanism model to obtain multiple model output data; A coordinate acquisition subunit, used for forming a plurality of coordinate points of a characteristic curve based on a plurality of field input data and a plurality of model output data; The curve fitting subunit is used to fit a characteristic curve based on multiple coordinate points.

[0015] Preferably, the mechanism simulation module comprises: Mechanism dynamic model unit, used to build a mechanism dynamic model based on the coal gasification process and steady-state mechanism model; A dynamic model updating unit, used for updating the mechanism dynamic model based on the equipment characteristic curve; A virtual controller unit for simulating a real hardware controller using software; The data communication unit is used to transmit data to the DCS control system based on the mechanism dynamic model bit number and the DCS control system bit number, and receive control commands from the DCS control system.

[0016] The advantages of the present invention are: 1. Through the deviation between the operation data of the steady-state mechanism model and the field data, the characteristic curve is verified and fitted, and the characteristic curve is used to correct the mechanism dynamic model to ensure the matching degree between the simulation system and the real equipment and guarantee the operation training effect; 2. Through the two-way data interaction between the mechanism dynamic model and the DCS control system, the operation interface and control logic of the DCS control system are utilized to further improve the authenticity of the operation training, thereby improving the effect of the operation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a digital twin-based adaptive and self-updating coal gasification simulation method provided in an embodiment of this specification; Figure 2 A block diagram of an adaptive and self-updating coal gasification simulation system based on digital twins provided in an embodiment of this specification. DETAILED DESCRIPTION

[0018] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0019] like Figure 1 As shown, this embodiment provides a coal gasification simulation method that can be adaptively and self-updated based on digital twins, including: Step 100, collect the coal gasification field data in the server or database, the coal gasification field data includes process parameters and equipment parameters, process parameters such as oxygen flow, coal slurry flow, gasifier temperature, gasifier pressure, high flash pressure, chilled water flow, etc., equipment parameters such as valve opening, heat exchanger area, centrifugal pump frequency, etc. Among them, the server is generally a DCS historical trend server, the database is generally a SUPOS real-time database, the collected field data includes historical data and real-time data, the collected data will be saved in the redis database, in addition, the .CSV format data can be directly imported into the redis database.

[0020] Step 102, constructing a data processing flow to process the collected coal gasification field data to obtain steady-state data; wherein the data processing method generally includes: Outlier processing: identifying and marking outliers in field data, specifically using statistical methods, Z-score, etc., and deleting or replacing outliers; Missing value processing: detect missing values ​​in field data and supplement them. The supplementation methods can be mean filling, mode filling, interpolation, etc. Noise filtering: Filter the noise of field data by using low-pass filtering, high-pass filtering, etc. to ensure the quality and accuracy of the data; Data clustering, using clustering algorithms, such as K-Means and DBSCAN, to group field data; Steady-state screening, based on the set steady-state threshold, screens out field data within the steady-state threshold range to remove interference caused by instantaneous changes.

[0021] The data collected from different field devices are different, and the required processing methods are also different. Therefore, this step can select different data processing methods and sequences for different field devices to separately build corresponding processing flows to more efficiently obtain stable and effective data.

[0022] Step 104, based on the operating mechanism of each device, respectively construct a steady-state mechanism model, and obtain model output data based on the steady-state mechanism model and the coal gasification field data, perform deviation comparison between the model output data and the coal gasification field data, and according to the deviation comparison result, fit the device characteristic curve or verify and update the device operating mechanism in the steady-state mechanism model. Among them, the steady-state mechanism model can be constructed through corresponding unit modules according to the field equipment and process data. It is mainly used to simulate the operating status of the field equipment, including the relevant mechanism algorithms of different equipment, so as to use the field input data to input the steady-state mechanism model, obtain the model output data, and compare it with the actual output data of the field equipment to understand whether the current steady-state mechanism model still matches the field equipment. If there is no deviation, the current steady-state mechanism model matches the field equipment. If there is a deviation, the size of the deviation is judged. When the deviation is within the set ratio, such as 5%, it is considered that the deviation is relatively small and can be calibrated through the equipment characteristic curve. The equipment characteristic curve is the conversion curve between the field data and the output data of the steady-state mechanism model, so that the output data of the steady-state mechanism model is the same as the output data of the field equipment; otherwise, it is considered that the deviation is large and it is difficult to calibrate through the equipment curve, and the equipment operation mechanism in the steady-state mechanism model needs to be verified and updated, that is, the steady-state mechanism model needs to be rebuilt. Specifically, the method of fitting to obtain the equipment characteristic curve specifically includes: Step 1040, inputting multiple sets of field input data into the steady-state mechanism model respectively to obtain multiple model output data; Step 1042, constructing a plurality of coordinate points of a characteristic curve based on a plurality of field input data and a plurality of model output data; Step 1044: fitting a characteristic curve based on the multiple coordinate points.

[0023] Based on the above method of fitting the characteristic curve of the equipment, take valve calibration as an example: first, obtain the on-site valve opening value and valve outlet pressure, and associate them with the valve opening and valve outlet pressure in the steady-state mechanism model. The steady-state model calculates the valve flow and valve inlet pressure, and writes the on-site data of valve outlet pressure and valve opening into the steady-state corresponding model parameters. Then, fix the flow, inlet and outlet pressures and opening in the valve model corresponding to the steady-state mechanism model. Next, run the steady-state mechanism model to calculate the CV value corresponding to the on-site input data, and form a coordinate point in the characteristic curve with the input valve on-site opening value (input valve opening value, calculate valve CV value). Finally, by inputting multiple sets of on-site working conditions, multiple sets of coordinate points can be obtained, and finally the valve characteristic curve is obtained.

[0024] Step 106, based on the coal gasification process and the steady-state mechanism model, a mechanism dynamic model is constructed, and the mechanism dynamic model is updated based on the equipment characteristic curve. Among them, different from the steady-state mechanism model, the mechanism dynamic model not only simulates the unit modules of each device, but also includes the coordination relationship between each unit module to simulate the process flow. For the unit modules corresponding to each field device in the process flow, it is necessary to update based on the equipment characteristic curve obtained in step 104 to ensure that the mechanism dynamic model can truly reflect the process flow of the field. In addition, the field equipment is controlled by the DCS control system. In order to make the simulation system more realistic, the mechanism dynamic model and the real DCS control system are bidirectionally interacted with each other. Specifically, the bidirectional data interaction between the two can be realized through the mechanism dynamic model bit number and the DCS control system bit number. The data of the mechanism dynamic model is transmitted to the DCS control system, and the DCS control system sends the control command to the mechanism dynamic model, that is, the simulation system adopts the operation interface and control logic of the real DCS control system.

[0025] To summarize, this embodiment first uses mechanism modeling software to build a digital twin simulation system of the gasification device, obtains historical data or real-time data of the field device through the data collection system, and screens out the steady-state data of the field device after data processing. The steady-state data is input into the equipment verification system to perform field data verification on equipment such as valve characteristics of valves and heat transfer coefficients of heat exchangers, so that the verification results are consistent with the actual operating characteristics of the device. The verification results are then returned to the mechanism simulation system to update the mechanism simulation system, thereby realizing the self-adaptation and self-update of the mechanism simulation system, solving the problem that the simulation system cannot match the field conditions due to the long-term operation characteristics of the field equipment of the gasification device, and extending the service life of the simulation system of the gasification device.

[0026] like Figure 2As shown, the embodiment of this specification also provides an adaptive and self-updating coal gasification simulation system based on digital twins, including an acquisition module, a steady-state screening module, an equipment verification module and a mechanism simulation module. Each module is introduced in detail below.

[0027] The acquisition module is used to collect gasification field data from the server or database. The gasification field data includes process parameters and equipment parameters. Among them, the server is generally a DCS historical trend server, and the database is generally a SUPOS real-time database. The collected field data includes historical data and real-time data. The collected data will be saved in the redis database. In addition, data in .CSV format can be directly imported into the redis database.

[0028] The steady-state screening module is used to provide multiple data processing units, construct a data processing flow by selecting data processing units, process the collected coal gasification field data, and obtain steady-state data; specifically, it includes: An outlier processing unit is used to identify and mark outliers in field data, specifically by using statistical methods, Z-score, etc., and to delete or replace outliers; Missing value processing unit, used to detect missing values ​​in field data and supplement them. The supplementation methods can be mean filling, mode filling, interpolation, etc. Noise filtering unit, used to filter noise from field data, specifically low-pass filtering, high-pass filtering, etc., to ensure the quality and accuracy of the data; A data clustering unit, used to group field data using clustering algorithms, such as K-Means, DBSCAN, etc.; The steady-state screening unit is used to screen out field data within the steady-state threshold range based on the set steady-state threshold and remove interference caused by instantaneous changes.

[0029] The data collected from different field devices are different, and the required processing methods are also different. Therefore, this step can select different data processing units and sequences for different field devices to separately build corresponding processing flows to more efficiently obtain stable and effective data.

[0030] The equipment verification module is used to construct a steady-state mechanism model based on the operating mechanism of each device, and obtain the model output data based on the steady-state mechanism model and the coal gasification field data, and compare the deviation between the model output data and the coal gasification field data. According to the deviation comparison results, the equipment characteristic curve is fitted or the equipment operating mechanism in the steady-state mechanism model is verified and updated; specifically, it includes: The steady-state mechanism model unit is used to construct steady-state mechanism models based on the operating mechanism of each device to simulate the operating status of the field equipment; The equipment characteristic verification unit is used to provide mechanism algorithms for different equipment, so as to use the field input data to input the steady-state mechanism model to obtain the model output data, and compare it with the actual output data of the field equipment to understand whether the current steady-state mechanism model still matches the field equipment. If there is no deviation, the current steady-state mechanism model matches the field equipment. If there is a deviation, the size of the deviation is judged. When the deviation is within the set ratio, such as 5%, it is considered that the deviation is relatively small and can be calibrated through the equipment characteristic curve. The equipment characteristic curve is the conversion curve between the field data and the output data of the steady-state mechanism model, so that the output data of the steady-state mechanism model is the same as the output data of the field equipment; otherwise, it is considered that the deviation is large and it is difficult to calibrate through the equipment curve, and it is necessary to verify and update the equipment operation mechanism in the steady-state mechanism model, that is, it is necessary to rebuild the steady-state mechanism model.

[0031] The equipment characteristic verification unit includes: The model output subunit is used to input multiple sets of field input data into the steady-state mechanism model to obtain multiple model output data; A coordinate acquisition subunit, used for forming a plurality of coordinate points of a characteristic curve based on a plurality of field input data and a plurality of model output data; The curve fitting subunit is used to fit a characteristic curve based on multiple coordinate points.

[0032] The mechanism simulation module is used to build a mechanism dynamic model based on the coal gasification process and steady-state mechanism model, and update the mechanism dynamic model based on the equipment characteristic curve; specifically includes: The mechanism dynamic model unit is used to construct a mechanism dynamic model based on the coal gasification process and the steady-state mechanism model. Different from the steady-state mechanism model, in addition to simulating the unit modules of each device, the mechanism dynamic model also includes the coordination relationship between the unit modules to simulate the process flow; Dynamic model updating unit, used to update the mechanism dynamic model based on the equipment characteristic curve to ensure that the mechanism dynamic model can truly reflect the on-site process flow; Virtual controller unit, used to simulate the real hardware controller with software, and control the data interaction between the dynamic model of the control mechanism and the DCS control system; The data communication unit is used to realize two-way data interaction between the mechanism dynamic model and the DCS control system through the mechanism dynamic model bit number and the DCS control system bit number, that is, the data of the mechanism dynamic model is transmitted to the DCS control system, and the DCS control system sends the control command to the mechanism dynamic model, that is, this simulation system adopts the operation interface and control logic of the real DCS control system.

[0033] The working principle of this embodiment is as follows: first, a digital twin simulation system of the gasification unit is built using the mechanism modeling software, and the historical data or real-time data of the on-site device is obtained through the data collection system. After data processing, the steady-state data of the on-site device is screened out, and the steady-state data is input into the equipment verification system to perform on-site data verification on equipment such as valve characteristics of valves and heat transfer coefficients of heat exchangers, so that the verification results are consistent with the actual operating characteristics of the device. Then, the verification results are returned to the mechanism simulation system to update the mechanism simulation system, thereby realizing the self-adaptation and self-update of the mechanism simulation system, solving the problem that the simulation system cannot match the on-site conditions due to the long-term operation characteristics of the on-site equipment of the gasification unit, and extending the service life of the simulation system of the gasification unit.

[0034] The above is only a preferred specific embodiment of the present invention, which is an implementation method based on the overall concept of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An adaptive and self-updating coal gasification simulation method based on digital twins, characterized in that: include: Collect coal gasification field data from the server or database, including process parameters and equipment parameters; Construct a data processing flow to process the collected coal gasification field data and obtain steady-state data; Based on the operation mechanism of each equipment, a steady-state mechanism model is constructed respectively, and the model output data is obtained based on the steady-state mechanism model and the coal gasification field data. The deviation is compared between the model output data and the coal gasification field data. According to the deviation comparison results, the equipment characteristic curve is fitted or the equipment operation mechanism in the steady-state mechanism model is verified and updated; Based on the coal gasification process and steady-state mechanism model, a mechanism dynamic model is constructed, and the mechanism dynamic model is updated based on the equipment characteristic curve.

2. The digital twin-based adaptive and self-updating coal gasification simulation method according to claim 1 is characterized in that: The data processing flow is constructed, and the data processing method adopted includes: Outlier processing: identifying and marking outliers in coal gasification field data, and deleting or replacing outliers; Missing value processing: detect missing values ​​in coal gasification field data and supplement them; Noise filtering: noise filtering of coal gasification field data; Data clustering, using clustering algorithms to group coal gasification field data; Steady-state screening, based on the set steady-state threshold, screens out the coal gasification field data within the steady-state threshold range.

3. The digital twin-based adaptive and self-updating coal gasification simulation method according to claim 1 is characterized in that: The device characteristic curve is fitted or the device operation mechanism in the steady-state mechanism model is verified and updated according to the deviation comparison result, including: if the deviation comparison result is greater than a set ratio, the device operation mechanism in the steady-state mechanism model is verified and updated; otherwise, the device characteristic curve is fitted.

4. The digital twin-based adaptive and self-updating coal gasification simulation method according to claim 1 is characterized in that: The fitting obtains the device characteristic curve, including: Input multiple sets of field input data into the steady-state mechanism model respectively to obtain multiple model output data; Based on a plurality of field input data and a plurality of model output data, a plurality of coordinate points of a characteristic curve are formed; Based on multiple coordinate points, a characteristic curve is fitted.

5. The digital twin-based adaptive and self-updating coal gasification simulation method according to claim 1 is characterized in that: The construction of the mechanism dynamic model includes: based on the mechanism dynamic model bit number and the DCS control system bit number, transmitting data to the DCS control system and receiving a control command of the DCS control system.

6. The digital twin-based adaptive and self-updating coal gasification simulation system is characterized by: include: A collection module is used to collect coal gasification field data from a server or database, where the coal gasification field data includes process parameters and equipment parameters; The steady-state screening module is used to provide multiple data processing units, construct a data processing flow by selecting the data processing units, process the collected coal gasification field data, and obtain steady-state data; The equipment verification module is used to construct steady-state mechanism models based on the operating mechanism of each device, obtain model output data based on the steady-state mechanism model and coal gasification field data, compare the deviations between the model output data and the coal gasification field data, and obtain the equipment characteristic curve by fitting or verify the equipment operating mechanism in the updated steady-state mechanism model based on the deviation comparison results; The mechanism simulation module is used to construct a mechanism dynamic model based on the coal gasification process and steady-state mechanism model, and to update the mechanism dynamic model based on the equipment characteristic curve.

7. The digital twin-based adaptive and self-updating coal gasification simulation system according to claim 6 is characterized in that: The steady-state screening module comprises: An outlier processing unit is used to identify and mark outliers in the coal gasification field data, and delete or replace the outliers; Missing value processing unit, used to detect missing values ​​in coal gasification field data and supplement them; A noise filtering unit, used for performing noise filtering on coal gasification field data; A data clustering unit, used to group coal gasification field data using a clustering algorithm; The steady-state screening unit is used to screen out the coal gasification field data within the steady-state threshold range based on the set steady-state threshold.

8. The digital twin-based adaptive and self-updating coal gasification simulation system according to claim 6 is characterized in that: The equipment verification module comprises: The steady-state mechanism model unit is used to construct a steady-state mechanism model based on the operating mechanism of each device; The equipment characteristic verification unit is used to obtain the model output data based on the steady-state mechanism model and the coal gasification field data, and to compare the deviations between the model output data and the coal gasification field data. If the deviation comparison result is greater than the set ratio, the equipment operation mechanism in the steady-state mechanism model is verified and updated; otherwise, the equipment characteristic curve is obtained by fitting.

9. The digital twin-based adaptive and self-updating coal gasification simulation system according to claim 8 is characterized in that: The device characteristic verification unit comprises: The model output subunit is used to input multiple sets of field input data into the steady-state mechanism model to obtain multiple model output data; A coordinate acquisition subunit, used for forming a plurality of coordinate points of a characteristic curve based on a plurality of field input data and a plurality of model output data; The curve fitting subunit is used to fit a characteristic curve based on multiple coordinate points.

10. The digital twin-based adaptive and self-updating coal gasification simulation system according to claim 6, characterized in that: The mechanism simulation module includes: Mechanism dynamic model unit, used to build a mechanism dynamic model based on the coal gasification process and steady-state mechanism model; A dynamic model updating unit, used for updating the mechanism dynamic model based on the equipment characteristic curve; A virtual controller unit for simulating a real hardware controller using software; The data communication unit is used to transmit data to the DCS control system based on the mechanism dynamic model bit number and the DCS control system bit number, and receive control commands from the DCS control system.

Images