Air cooling state control method and system for refining heating furnace monitoring system

Abstract

The embodiment of the invention provides a refining heating furnace monitoring system air cooling state control method and system, and belongs to the technical field of equipment temperature control. The method comprises the following steps: acquiring operation data of the refining heating furnace, and constructing a digital twinborn model of the refining heating furnace based on the operation data; identifying state information of each monitoring system of the refining heating furnace in the digital twin model, and determining cooling demand information of each monitoring system based on the state information; based on the cooling demand information, simulating an air cooling correction scheme of each monitoring system in the digital twin model to obtain an optimal correction scheme; and based on the optimal correction scheme, executing air cooling state correction of each monitoring system. According to the scheme, refined control over the whole air cooling system is achieved, it is guaranteed that the monitoring system can be supported to operate stably, and therefore refined control over the whole refining heating furnace is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment temperature control, and in particular to a method for controlling an air cooling state of a monitoring system for a refinery heating furnace and a control system for controlling an air cooling state of a monitoring system for a refinery heating furnace. Background Art

[0002] Refining heating furnace is a very important refining equipment in refining enterprises. Among them, the most widely used is the tubular heating furnace, which is a kind of thermal heating equipment. It uses the high-temperature flame and flue gas generated by the combustion of fuel in the furnace as the heat source to heat the medium flowing at high speed in the furnace tube to reach the temperature specified by the refining process. Refining heating furnace accounts for a very high proportion of energy consumption in the entire refining enterprise. How to improve the thermal efficiency of refining heating furnace and realize efficient use of energy is the common direction of all refining enterprises.

[0003] In order to improve the thermal efficiency of the refining heating furnace, it is essential to achieve refined control of the heating furnace. In order to achieve refined operation of the heating furnace, full perception of the corresponding system operation status is also essential. In the existing solution, in order to improve the perception effect of the entire heating furnace, a variety of monitoring systems are set up in the entire heating furnace to monitor the equipment operation data in real time during the operation of the heating furnace, so as to achieve full perception of the operation status of the entire heating furnace.

[0004] Although adding a large number of monitoring systems is conducive to the realization of refined control of the heating furnace, because the heating furnace itself is a high-temperature operating equipment, its monitoring environment is extremely harsh, and the monitoring system needs to continue to work under high temperature conditions, which places extremely high requirements on the operating stability of the monitoring system. In order to ensure the stable operation of the independent monitoring system, it is necessary to configure a corresponding cooling device for the monitoring system, and the air cooling device is one of the most widely used devices. Just as the heating furnace itself requires refined control, in order to ensure that the monitoring system continues to work stably, the air cooling device and the heating furnace itself need to be refined. The existing linkage control scheme based on temperature execution cannot meet the needs. Sudden abnormalities may occur in the furnace at any time, and the existing linkage rules based on temperature conditions cannot cope with such sudden abnormalities. In view of the problem of poor response timeliness of the existing air cooling state control method, it is necessary to create a new air cooling state control scheme for the refining heating furnace monitoring system. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for controlling the air cooling state of a refining heating furnace monitoring system, so as to at least solve the problem of poor response timeliness in the existing air cooling state control method.

[0006] In order to achieve the above-mentioned objectives, the first aspect of the present invention provides a method for controlling the air cooling state of a refining heating furnace monitoring system, the method comprising: collecting operating data of the refining heating furnace, and constructing a digital twin model of the refining heating furnace based on the operating data; identifying status information of each monitoring system of the refining heating furnace in the digital twin model, and determining cooling requirement information of each monitoring system based on the status information; based on the cooling requirement information, simulating an air cooling correction scheme of each monitoring system in the digital twin model to obtain an optimal correction scheme; based on the optimal correction scheme, executing air cooling state correction of each monitoring system.

[0007] Optionally, the collecting of the operating data of the refining heating furnace includes: based on the DCS system of the refining enterprise, collecting the operating data of the refining heating furnace itself and the operating data of preset related equipment to obtain initial data; performing data preprocessing on the initial data to obtain valid data; collecting the historical operating data of the current refining heating furnace, and fusing it with the valid data to obtain constructed data, and using the constructed data as the operating data of the refining heating furnace.

[0008] Optionally, the status information of each monitoring system includes: temperature information and real-time operation information of the location of the monitoring system; wherein, the temperature information at the location includes real-time temperature information and predicted temperature information within a preset future time period obtained based on the digital twin model.

[0009] Optionally, determining the cooling requirement information of each monitoring system based on the status information includes: generating a corresponding status data matrix based on the status information of each monitoring system, and generating a corresponding eigenvector based on the status data matrix; importing the eigenvector into a preset nonlinear mapping function to obtain a mapping result; obtaining simulated temperature information of each monitoring system based on the mapping result; and determining the cooling requirement information of each monitoring system based on the preset normal temperature information and the simulated temperature information.

[0010] Optionally, the monitoring system includes: one or more of an infrared sensor, a gas concentration monitor, an image acquisition device, and a sound sensor.

[0011] Optionally, based on the cooling demand information, an air cooling correction scheme of each monitoring system is simulated in the digital twin model to obtain an optimal correction scheme, including: taking the cooling demand information as the optimization target, taking the current operating parameters and the interference parameters determined by the user as the initial state information, simulating the air cooling correction scheme in the digital twin model to obtain multiple candidate schemes; and screening the multiple candidate schemes to obtain the optimal correction scheme.

[0012] Optionally, the correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction and filter element adjustment.

[0013] Optionally, the cooling air types include: instrument air, industrial air and dry air-conditioning air.

[0014] Optionally, the screening of multiple candidate solutions to obtain the optimal revised solution includes: determining whether there are candidate solutions with the same cooling air type as the current cooling air type among the multiple candidate solutions, and if so, filtering out candidate solutions that are different from the current cooling air type, and forming a first filtered candidate set based on the remaining candidate solutions; otherwise, retaining all candidate solutions, and forming a first filtered candidate set based on all candidate solutions; based on the digital twin model, simulating the execution process of each candidate solution in the first filtered candidate set, and reading the power consumption after execution; comparing the power consumption of each candidate solution, and screening out the candidate solution with the lowest power consumption as the optimal revised solution.

[0015] The second aspect of the present invention provides an air cooling state control system for a refining heating furnace monitoring system, the system comprising: an acquisition unit, used to acquire operating data of the refining heating furnace, and construct a digital twin model of the refining heating furnace based on the operating data; a processing unit, used to identify status information of each monitoring system of the refining heating furnace in the digital twin model, and determine cooling requirement information of each monitoring system based on the status information; a simulation unit, used to simulate the air cooling correction scheme of each monitoring system in the digital twin model based on the cooling requirement information to obtain an optimal correction scheme; and an execution unit, used to execute air cooling state correction of each monitoring system based on the optimal correction scheme.

[0016] Optionally, the correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction and filter element selection; the cooling air types include: instrument air, industrial air and dry air conditioning air; the execution unit includes: a cooling air type switching module, used to switch the cooling air type based on the cooling air type determined by the correction scheme; a cooling air pressure adjustment module, used to adjust the cooling air pressure based on the cooling air pressure determined by the correction scheme; a cooling air path correction module, used to correct the cooling air path based on the cooling air path determined by the correction scheme; a filter element adjustment module, used to adjust the filter element based on the filter element type determined by the correction scheme.

[0017] On the other hand, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the above-mentioned air cooling state control method of the refining heating furnace monitoring system.

[0018] Through the above technical scheme, the scheme of the present invention constructs a corresponding digital twin model based on the operating data of the refining heating furnace, and realizes a full simulation of the entire system working condition through the constructed digital twin model, and synchronously perceives the future operating state of the existing operating state. Then, the air cooling state is predicted based on the perceived operating state, and the expected air cooling state is determined. Based on the digital twin model, the correction scheme is simulated and verified through the expected air cooling state, and the optimal correction scheme is output. Subsequently, the air cooling state is adjusted based on the optimal correction scheme to achieve refined control of the entire air cooling system, ensuring that it can support the stable operation of the monitoring system, thereby achieving refined control of the entire refining heating furnace.

[0019] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0021] Figure 1 It is a flowchart of the steps of a method for controlling the air cooling state of a refining heating furnace monitoring system provided by one embodiment of the present invention;

[0022] Figure 2 It is a system structure diagram of an air cooling state control system of a refining heating furnace monitoring system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0023] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0024] Refining heating furnace is a very important refining equipment in refining enterprises. Among them, the most widely used is the tubular heating furnace, which is a kind of thermal heating equipment. It uses the high-temperature flame and flue gas generated by the combustion of fuel in the furnace as the heat source to heat the medium flowing at high speed in the furnace tube to reach the temperature specified by the refining process. Refining heating furnace accounts for a very high proportion of energy consumption in the entire refining enterprise. How to improve the thermal efficiency of refining heating furnace and realize efficient use of energy is the common direction of all refining enterprises.

[0025] In order to improve the thermal efficiency of the refining heating furnace, it is essential to achieve refined control of the heating furnace. In order to achieve refined operation of the heating furnace, full perception of the corresponding system operation status is also essential. In the existing solution, in order to improve the perception effect of the entire heating furnace, a variety of monitoring systems are set up in the entire heating furnace to monitor the equipment operation data in real time during the operation of the heating furnace, so as to achieve full perception of the operation status of the entire heating furnace.

[0026] Although adding a large number of monitoring systems is conducive to the realization of refined control of the heating furnace, because the heating furnace itself is a high-temperature operating equipment, its monitoring environment is extremely harsh, and the monitoring system needs to continue to work under high temperature conditions, which places extremely high demands on the operating stability of the monitoring system. In order to ensure the stable operation of the independent monitoring system, it is necessary to configure a corresponding cooling device for the monitoring system, and the air cooling device is one of the most widely used devices. Just as the heating furnace itself requires refined control, in order to ensure that the monitoring system continues to work stably, the air cooling device and the heating furnace itself need to be refined. The existing linkage control scheme based on temperature execution cannot meet the needs. Sudden abnormalities may occur in the furnace at any time, and the existing linkage rules based on temperature conditions cannot cope with such sudden abnormalities.

[0027] In view of the problem of poor response timeliness in the existing air cooling state control methods, the present invention proposes a new air cooling state control method for the refining heating furnace monitoring system. The present invention constructs a corresponding digital twin model based on the operating data of the refining heating furnace, and uses the constructed digital twin model to fully simulate the entire system working conditions, and synchronously perceive the future operating state of the existing operating state. Then, based on the perceived operating state, the air cooling state is predicted to determine the expected air cooling state. Based on the digital twin model, the correction scheme is simulated and verified through the expected air cooling state, and the optimal correction scheme is output. Subsequently, the air cooling state is adjusted based on the optimal correction scheme to achieve refined control of the entire air cooling system, ensuring that it can support the stable operation of the monitoring system, thereby achieving refined control of the entire refining heating furnace.

[0028] Figure 1 1 is a method flow chart of a method for controlling the air cooling state of a refining heating furnace monitoring system provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for controlling the air cooling state of a refining heating furnace monitoring system, the method comprising:

[0029] Step S10: collecting the operating data of the refining heating furnace, and constructing a digital twin model of the refining heating furnace based on the real-time operating data.

[0030] Specifically, the purpose of the scheme of the present invention is to achieve refined control of the air cooling system and ensure that it supports the stable operation of the corresponding monitoring system during the operation of the heating furnace. Furthermore, it is possible to predict the operating status of the entire heating furnace, and then perform pre-regulation based on the prediction results to ensure that the system has the ability to cope with sudden abnormalities. Based on this, if you want to achieve the above-mentioned technical effects, it is essential to have an accurate sense of the operating status of the heating furnace. In existing schemes, the operating information of the refining heating furnace is often fully collected, and then the operating condition is restored based on the collected information. This method requires the operating condition to be restored at each moment, and the restored operating condition can only represent the operating status at the current moment. First, in order to achieve state prediction, a corresponding simulation model needs to be built. And as the equipment ages, the simulation model also needs to be corrected in a targeted manner, otherwise its prediction accuracy will become lower and lower.

[0031] In response to the above problems, the solution of the present invention constructs a digital twin model of the refining heating furnace to sense and predict the operating status of the heating furnace. As an important enabling way to achieve digital transformation and promote intelligent upgrading, digital twins have always attracted attention from all walks of life and have moved from theoretical research to practical application. Digital twins are driven by multi-dimensional virtual models and fused data, and through virtual-real closed-loop interaction, they realize actual functional services and application needs such as monitoring, simulation, prediction, and optimization. The construction of a digital twin model is a prerequisite for the implementation of digital twin applications.

[0032] Digital twins are designed around a two-way information flow. This information flow first appears when the object sensor provides relevant data to the system processor. Then, the information flow appears again when the processor shares its insights with the original source object. Therefore, it has good real-time performance. It can directly use the monitoring data of each monitoring system in the refining heating furnace, and then generate the corresponding digital twin model based on the monitoring data to simulate the air-cooled state, and finally feedback to the monitoring system. When implementing the solution, there is no need to build a new system separately, it can be built directly based on the existing system.

[0033] Embodiment 1:

[0034] Preferably, the collecting of the operating data of the refining heating furnace includes: based on the DCS system of the refining enterprise, collecting the operating data of the refining heating furnace itself and the operating data of preset related equipment to obtain initial data; performing data preprocessing on the initial data to obtain valid data; collecting the historical operating data of the current refining heating furnace, and fusing it with the valid data to obtain constructed data, and using the constructed data as the operating data of the refining heating furnace.

[0035] In an embodiment of the present invention, in order to improve the efficiency of collecting operating data, the scheme of the present invention directly collects data based on the enterprise DCS system, and uses the existing monitoring system to collect data, without the need to configure sensors separately, thereby reducing the cost of system construction. In addition, the operating status of the heating furnace and other refining equipment have a mutually influential relationship. If the operating parameters of the heating furnace itself are collected separately, although its operating status can be fully perceived, when predicting its operating status, it is difficult to achieve its own operating parameters. It is necessary to link the operating parameters of other related equipment and predict them as a whole, so that the prediction results are more in line with expectations. Based on this, the scheme of the present invention will also collect the operating data of preset related equipment.

[0036] In the embodiment of the present invention, DCS is the abbreviation of Distributed Control System, which is also called distributed control system in the domestic automatic control industry. The so-called distributed control system, or distributed system in some materials, is a new type of computer control system relative to the centralized control system. It is developed and evolved on the basis of the centralized control system. It is a multi-level computer system composed of process control level and process monitoring level with communication network as the link, integrating 4C technologies such as computer, communication, display and control, and its basic idea is decentralized control, centralized operation, hierarchical management, flexible configuration and convenient configuration. Distributed control system (DCS) is a new type of control system based on microprocessor, with dangerous decentralized control, centralized operation and management as its characteristics, integrating advanced computer technology, communication technology, CRT technology and control technology, namely 4C technology. With the rapid development of modern computer and communication network technology, DCS is developing towards diversification, networking, openness and integrated management, so that different types of DCS can be interconnected and exchange data, and the DCS system and factory management network can be connected through Ethernet to realize real-time data access to the Internet, becoming the mainstream of process industry automatic control. It can not only realize full detection of the operating status, but also has corresponding control advantages when performing subsequent air cooling status correction.

[0037] Furthermore, if only real-time operation data is collected, it can only represent the current operating status of the system. If the digital twin model is constructed only with this data, the accuracy of the model is bound to be problematic. Because if the current state happens to be in an abnormal state, then the digital twin model constructed based on the abnormal data itself is also abnormal. In order to avoid this situation, when collecting operation data, corresponding historical data will be collected at the same time as the existing data collected. These historical operation data hide the operating rules of the current heating furnace, which is a long-term stable operating state. By integrating historical data, the possibility of accidental errors affecting the accuracy of the digital twin model can be greatly reduced.

[0038] Embodiment 2:

[0039] Preferably, in another possible implementation, when the historical operation data and the effective data are fused, in order to reflect the aging of the equipment, the accuracy of constructing the digital twin model is further guaranteed. First, the effective data is reviewed based on the historical data to determine whether it conforms to the aging law. If the deviation between it and the historical data is too large (greater than the preset deviation threshold), it means that the data is abnormal. When performing data fusion, the data can be re-collected or directly constructed based on the historical data. If the deviation between the two is less than the preset deviation threshold, it means that the current data conforms to the normal situation. When performing data fusion, the weight of the real-time data is increased. Because the current data is the most consistent with the current equipment status, by increasing its proportion in all data, it can be ensured that the final fused data is closer to the current equipment status. Then, when the equipment is aging, the aging influencing factor can be coupled to the data, and the subsequent digital twin model constructed based on the data will also be more in line with expectations.

[0040] Step S20: Identify the status information of each monitoring system in the digital twin model, and determine the cooling requirement information of each monitoring system based on the status information.

[0041] Specifically, the status information of each monitoring system includes: temperature information at the location and real-time operation information; wherein the temperature information at the location includes real-time temperature information and predicted temperature information within a preset future time period obtained based on the digital twin model.

[0042] In an embodiment of the present invention, the premise for correcting the air-cooling state is that the current air-cooling state can no longer meet the existing cooling demand or will soon be unable to meet the cooling demand under the predicted state. The former needs to be corrected immediately, and the latter needs to complete the system pre-regulation before the predicted time arrives. Whether the current air-cooling state meets expectations, that is, whether the current air-cooling state can guarantee the cooling demand of the corresponding monitoring system. Different monitoring systems have different functions and different setting locations, so the working environments they face may also be different. For example, in order to ensure the accuracy of the image acquisition device for furnace flame monitoring, it is best that there is no obstruction between it and the flame, which means that the camera needs to face the flame directly, so the high-temperature environment it faces will be very harsh and changeable. In order to ensure the refined monitoring of the corresponding air-cooling state of each monitoring system, it is essential to achieve differentiated control for the working states of different monitoring system setting locations.

[0043] For the monitoring system, the sources of high temperature include the high temperature produced by the heating furnace and the problems produced by the monitoring equipment during operation. The air cooling system needs to process these two temperatures at the same time. The temperatures at different monitoring system locations are different, and the corresponding temperatures affected by the heating furnace are also different. Therefore, when collecting temperature, it is necessary to collect the temperature information and real-time operation information of each monitoring system location.

[0044] Embodiment 3:

[0045] Preferably, determining the cooling requirement information of each monitoring system based on the status information includes: generating a corresponding status data matrix based on the status information of each monitoring system, and generating a corresponding eigenvector based on the status data matrix; importing the eigenvector into a preset nonlinear mapping function to obtain a mapping result; obtaining the simulated temperature information of each monitoring system based on the mapping result; and determining the cooling requirement information of each monitoring system based on the preset normal temperature information and the simulated temperature information.

[0046] In the embodiment of the present invention, because the temperature influence of a device is not a simple superposition of the influence temperature and the operating temperature, when air cooling control is performed, whether the temperature position of the monitoring system can be at the expected temperature is not a direct difference between the expected temperature and the current temperature. The air cooling uses different cooling media, different paths, and different exhaust conditions, and the corresponding air cooling effects are all different. It is a process of multiple factors jointly affecting. In order to efficiently realize the simulation of this coupling situation, the scheme of the present invention uses nonlinear mapping to simulate temperature prediction.

[0047] Existing machine learning solutions often require that the training data be perfectly linearly separable, but the state of the simulated temperature of each detection system cannot be linearly mapped. It is a coupling situation of multiple influencing factors, and the temperature cannot be directly read based on a simple linear mapping. Nonlinear mapping can solve this problem well. Through dimensionality reduction technology, nonlinear problems can be converted into corresponding linear problems, which can efficiently and accurately simulate temperature.

[0048] Before performing nonlinear mapping, the collected data needs to be processed into a data matrix, and the corresponding eigenvectors are further generated. The temperature is mapped through the nonlinear mapping function to obtain the accurate temperature under the current comprehensive factors. Because the corresponding air cooling conditions have been considered during the temperature simulation, the subsequent determination of the cooling demand information based on the difference between the simulated temperature and the expected temperature also couples all the influencing factors, and its accuracy is significantly higher than the simple superposition method of the existing solution.

[0049] Preferably, the monitoring system includes: one or more of an infrared sensor, a gas concentration monitor, an image acquisition device, and a sound sensor.

[0050] Step S30: Based on the cooling demand information, the air cooling correction scheme of each monitoring system is simulated in the digital twin model to obtain the optimal correction scheme.

[0051] Specifically, based on the cooling demand information, the air cooling correction scheme of each monitoring system is simulated in the digital twin model to obtain the optimal correction scheme, including: taking the cooling demand information as the optimization target, taking the current operating parameters and the interference parameters determined by the user as the initial state information, simulating the air cooling correction scheme in the digital twin model to obtain multiple candidate schemes; screening the multiple candidate schemes to obtain the optimal correction scheme.

[0052] Embodiment 4:

[0053] Preferably, the correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction, and filter element adjustment.

[0054] Preferably, the cooling air types include: instrument air, industrial air and dry air-conditioning air.

[0055] In an embodiment of the present invention, the scheme of the present invention has a variety of cooling medium options, which correspond to different demand scenarios and have corresponding advantages. Industrial wind has relatively low maintenance costs, but because there are impurities in the wind, in order to avoid dust accumulation, the wind needs to be filtered. Instrument wind is relatively clean, but its cooling effect is limited. Dry air conditioning wind has the best cooling effect, but its maintenance cost is high. Therefore, the ideal state is that for monitoring systems with low cooling requirements and low dust accumulation requirements, they can use the lowest cost industrial wind for cooling. For monitoring systems with low cooling requirements but high dust accumulation performance requirements, they can use instrument wind for cooling. For monitoring systems with high cooling requirements, dry air conditioning wind is used for cooling. The monitoring system is in different periods, and its requirements may change. Therefore, in order to ensure stable cooling of each monitoring system under various conditions and reduce costs as much as possible, each monitoring system is configured with multiple cooling media, and then the corresponding electric control valve is configured to switch the cooling medium based on demand. Of course, cooling media can also be mixed and used, and any combination can be made based on actual conditions.

[0056] Preferably, the screening of multiple candidate solutions to obtain the optimal revised solution includes: determining whether there are candidate solutions with the same cooling air type as the current cooling air type among the multiple candidate solutions, and if so, filtering out candidate solutions that are different from the current cooling air type, and forming a first filtered candidate set based on the remaining candidate solutions; otherwise, retaining all candidate solutions, and forming a first filtered candidate set based on all candidate solutions; based on the digital twin model, simulating the execution process of each candidate solution in the first filtered candidate set, and reading the power consumption after the execution is completed; comparing the power consumption of each candidate solution, and screening out the candidate solution with the lowest power consumption as the optimal revised solution.

[0057] Step S40: Based on the correction scheme, the air cooling state of each monitoring system is corrected.

[0058] Specifically, after obtaining the optimal correction scheme, control instructions for the air cooling system corresponding to each detection system are generated based on the optimal correction scheme, and these instructions are synchronously sent to the corresponding execution module. The corresponding execution module corrects the air cooling state based on the control instructions.

[0059] Embodiment 5:

[0060] Figure 2 This is a system structure diagram of an air cooling state control system for a refining heating furnace monitoring system provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an air cooling state control system for a refining heating furnace monitoring system, the system comprising:

[0061] The collection unit is used to collect the operating data of the refining heating furnace and build a digital twin model of the refining heating furnace based on the real-time operating data.

[0062] Specifically, the purpose of the scheme of the present invention is to achieve refined control of the air cooling system and ensure that it supports the stable operation of the corresponding monitoring system during the operation of the heating furnace. Furthermore, it is possible to predict the operating status of the entire heating furnace, and then perform pre-regulation based on the prediction results to ensure that the system has the ability to cope with sudden abnormalities. Based on this, if you want to achieve the above-mentioned technical effects, it is essential to have an accurate sense of the operating status of the heating furnace. In existing schemes, the operating information of the refining heating furnace is often fully collected, and then the operating condition is restored based on the collected information. This method requires the operating condition to be restored at each moment, and the restored operating condition can only represent the operating status at the current moment. First, in order to achieve state prediction, a corresponding simulation model needs to be built. And as the equipment ages, the simulation model also needs to be corrected in a targeted manner, otherwise its prediction accuracy will become lower and lower.

[0063] In response to the above problems, the solution of the present invention constructs a digital twin model of the refining heating furnace to sense and predict the operating status of the heating furnace. As an important enabling way to achieve digital transformation and promote intelligent upgrading, digital twins have always attracted attention from all walks of life and have moved from theoretical research to practical application. Digital twins are driven by multi-dimensional virtual models and fused data, and through virtual-real closed-loop interaction, they realize actual functional services and application needs such as monitoring, simulation, prediction, and optimization. The construction of a digital twin model is a prerequisite for the implementation of digital twin applications.

[0064] Digital twins are designed around a two-way information flow. This information flow first appears when the object sensor provides relevant data to the system processor. Then, the information flow appears again when the processor shares its insights with the original source object. Therefore, it has good real-time performance. It can directly use the monitoring data of each monitoring system in the refining heating furnace, and then generate the corresponding digital twin model based on the monitoring data to simulate the air-cooled state, and finally feedback to the monitoring system. When implementing the solution, there is no need to build a new system separately, it can be built directly based on the existing system.

[0065] Preferably, the collecting of the operating data of the refining heating furnace includes: based on the DCS system of the refining enterprise, collecting the operating data of the refining heating furnace itself and the operating data of preset related equipment to obtain initial data; performing data preprocessing on the initial data to obtain valid data; collecting the historical operating data of the current refining heating furnace, and fusing it with the valid data to obtain constructed data, and using the constructed data as the operating data of the refining heating furnace.

[0066] In an embodiment of the present invention, in order to improve the efficiency of collecting operating data, the scheme of the present invention directly collects data based on the enterprise DCS system, and uses the existing monitoring system to collect data, without the need to configure sensors separately, thereby reducing the cost of system construction. In addition, the operating status of the heating furnace and other refining equipment have a mutually influential relationship. If the operating parameters of the heating furnace itself are collected separately, although its operating status can be fully perceived, when predicting its operating status, it is difficult to achieve its own operating parameters. It is necessary to link the operating parameters of other related equipment and predict them as a whole, so that the prediction results are more in line with expectations. Based on this, the scheme of the present invention will also collect the operating data of preset related equipment.

[0067] In the embodiment of the present invention, DCS is the abbreviation of Distributed Control System, which is also called distributed control system in the domestic automatic control industry. The so-called distributed control system, or distributed system in some materials, is a new type of computer control system relative to the centralized control system. It is developed and evolved on the basis of the centralized control system. It is a multi-level computer system composed of process control level and process monitoring level with communication network as the link, integrating 4C technologies such as computer, communication, display and control, and its basic idea is decentralized control, centralized operation, hierarchical management, flexible configuration and convenient configuration. Distributed control system (DCS) is a new type of control system based on microprocessor, with dangerous decentralized control, centralized operation and management as its characteristics, integrating advanced computer technology, communication technology, CRT technology and control technology, namely 4C technology. With the rapid development of modern computer and communication network technology, DCS is developing towards diversification, networking, openness and integrated management, so that different types of DCS can be interconnected and exchange data, and the DCS system and factory management network can be connected through Ethernet to realize real-time data access to the Internet, becoming the mainstream of process industry automatic control. It can not only realize full detection of the operating status, but also has corresponding control advantages when performing subsequent air cooling status correction.

[0068] Furthermore, if only real-time operation data is collected, it can only represent the current operating status of the system. If the digital twin model is constructed only with this data, the accuracy of the model is bound to be problematic. Because if the current state happens to be in an abnormal state, then the digital twin model constructed based on the abnormal data itself is also abnormal. In order to avoid this situation, when collecting operation data, corresponding historical data will be collected at the same time as the existing data collected. These historical operation data hide the operating rules of the current heating furnace, which is a long-term stable operating state. By integrating historical data, the possibility of accidental errors affecting the accuracy of the digital twin model can be greatly reduced.

[0069] Preferably, in another possible implementation, when the historical operation data and the effective data are fused, in order to reflect the aging of the equipment, the accuracy of constructing the digital twin model is further guaranteed. First, the effective data is reviewed based on the historical data to determine whether it conforms to the aging law. If the deviation between it and the historical data is too large (greater than the preset deviation threshold), it means that the data is abnormal. When performing data fusion, the data can be re-collected or directly constructed based on the historical data. If the deviation between the two is less than the preset deviation threshold, it means that the current data conforms to the normal situation. When performing data fusion, the weight of the real-time data is increased. Because the current data is the most consistent with the current equipment status, by increasing its proportion in all data, it can be ensured that the final fused data is closer to the current equipment status. Then, when the equipment is aging, the aging influencing factor can be coupled to the data, and the subsequent digital twin model constructed based on the data will also be more in line with expectations.

[0070] A processing unit is used to identify the status information of each monitoring system in the digital twin model, and determine the cooling requirement information of each monitoring system based on the status information.

[0071] Specifically, the status information of each monitoring system includes: temperature information at the location and real-time operation information; wherein the temperature information at the location includes real-time temperature information and predicted temperature information within a preset future time period obtained based on the digital twin model.

[0072] In an embodiment of the present invention, the premise for correcting the air-cooling state is that the current air-cooling state can no longer meet the existing cooling demand or will soon be unable to meet the cooling demand under the predicted state. The former needs to be corrected immediately, and the latter needs to complete the system pre-regulation before the predicted time arrives. Whether the current air-cooling state meets expectations, that is, whether the current air-cooling state can guarantee the cooling demand of the corresponding monitoring system. Different monitoring systems have different functions and different setting locations, so the working environments they face may also be different. For example, in order to ensure the accuracy of the image acquisition device for furnace flame monitoring, it is best that there is no obstruction between it and the flame, which means that the camera needs to face the flame directly, so the high-temperature environment it faces will be very harsh and changeable. In order to ensure the refined monitoring of the corresponding air-cooling state of each monitoring system, it is essential to achieve differentiated control for the working states of different monitoring system setting locations.

[0073] For the monitoring system, the sources of high temperature include the high temperature produced by the heating furnace and the problems produced by the monitoring equipment during operation. The air cooling system needs to process these two temperatures at the same time. The temperatures at different monitoring system locations are different, and the corresponding temperatures affected by the heating furnace are also different. Therefore, when collecting temperature, it is necessary to collect the temperature information and real-time operation information of each monitoring system location.

[0074] Preferably, determining the cooling requirement information of each monitoring system based on the status information includes: generating a corresponding status data matrix based on the status information of each monitoring system, and generating a corresponding eigenvector based on the status data matrix; importing the eigenvector into a preset nonlinear mapping function to obtain a mapping result; obtaining the simulated temperature information of each monitoring system based on the mapping result; and determining the cooling requirement information of each monitoring system based on the preset normal temperature information and the simulated temperature information.

[0075] In the embodiment of the present invention, because the temperature influence of a device is not a simple superposition of the influence temperature and the operating temperature, when air cooling control is performed, whether the temperature position of the monitoring system can be at the expected temperature is not a direct difference between the expected temperature and the current temperature. The air cooling uses different cooling media, different paths, and different exhaust conditions, and the corresponding air cooling effects are all different. It is a process of multiple factors jointly affecting. In order to efficiently realize the simulation of this coupling situation, the scheme of the present invention uses nonlinear mapping to simulate temperature prediction.

[0076] Existing machine learning solutions often require that the training data be perfectly linearly separable, but the state of the simulated temperature of each detection system cannot be linearly mapped. It is a coupling situation of multiple influencing factors, and the temperature cannot be directly read based on a simple linear mapping. Nonlinear mapping can solve this problem well. Through dimensionality reduction technology, nonlinear problems can be converted into corresponding linear problems, which can efficiently and accurately simulate temperature.

[0077] Before performing nonlinear mapping, the collected data needs to be processed into a data matrix, and the corresponding eigenvectors are further generated. The temperature is mapped through the nonlinear mapping function to obtain the accurate temperature under the current comprehensive factors. Because the corresponding air cooling conditions have been considered during the temperature simulation, the subsequent determination of the cooling demand information based on the difference between the simulated temperature and the expected temperature also couples all the influencing factors, and its accuracy is significantly higher than the simple superposition method of the existing solution.

[0078] Preferably, the monitoring system includes: one or more of an infrared sensor, a gas concentration monitor, an image acquisition device, and a sound sensor.

[0079] The simulation unit is used to simulate the air cooling correction scheme of each monitoring system in the digital twin model based on the cooling demand information to obtain the optimal correction scheme.

[0080] Specifically, based on the cooling demand information, the air cooling correction scheme of each monitoring system is simulated in the digital twin model to obtain the optimal correction scheme, including: taking the cooling demand information as the optimization target, taking the current operating parameters and the interference parameters determined by the user as the initial state information, simulating the air cooling correction scheme in the digital twin model to obtain multiple candidate schemes; screening the multiple candidate schemes to obtain the optimal correction scheme.

[0081] Preferably, the correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction, and filter element adjustment.

[0082] Preferably, the cooling air types include: instrument air, industrial air and dry air-conditioning air.

[0083] In an embodiment of the present invention, the scheme of the present invention has a variety of cooling medium options, which correspond to different demand scenarios and have corresponding advantages. Industrial wind has relatively low maintenance costs, but because there are impurities in the wind, in order to avoid dust accumulation, the wind needs to be filtered. Instrument wind is relatively clean, but its cooling effect is limited. Dry air conditioning wind has the best cooling effect, but its maintenance cost is high. Therefore, the ideal state is that for monitoring systems with low cooling requirements and low dust accumulation requirements, they can use the lowest cost industrial wind for cooling. For monitoring systems with low cooling requirements but high dust accumulation performance requirements, they can use instrument wind for cooling. For monitoring systems with high cooling requirements, dry air conditioning wind is used for cooling. The monitoring system is in different periods, and its requirements may change. Therefore, in order to ensure stable cooling of each monitoring system under various conditions and reduce costs as much as possible, each monitoring system is configured with multiple cooling media, and then the corresponding electric control valve is configured to switch the cooling medium based on demand. Of course, cooling media can also be mixed and used, and any combination can be made based on actual conditions.

[0084] Preferably, the screening of multiple candidate solutions to obtain the optimal revised solution includes: determining whether there are candidate solutions with the same cooling air type as the current cooling air type among the multiple candidate solutions, and if so, filtering out candidate solutions that are different from the current cooling air type, and forming a first filtered candidate set based on the remaining candidate solutions; otherwise, retaining all candidate solutions, and forming a first filtered candidate set based on all candidate solutions; based on the digital twin model, simulating the execution process of each candidate solution in the first filtered candidate set, and reading the power consumption after the execution is completed; comparing the power consumption of each candidate solution, and screening out the candidate solution with the lowest power consumption as the optimal revised solution.

[0085] The execution unit is used to execute the air cooling state correction of each monitoring system based on the correction scheme.

[0086] Specifically, after obtaining the optimal correction scheme, control instructions for the air cooling system corresponding to each detection system are generated based on the optimal correction scheme, and these instructions are synchronously sent to the corresponding execution module. The corresponding execution module corrects the air cooling state based on the control instructions.

[0087] Preferably, the correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction, and filter element selection; the cooling air types include: instrument air, industrial air, and dry air conditioning air; the execution unit includes: a cooling air type switching module, used to switch the cooling air type based on the cooling air type determined by the correction scheme; a cooling air pressure adjustment module, used to adjust the cooling air pressure based on the cooling air pressure determined by the correction scheme; a cooling air path correction module, used to correct the cooling air path based on the cooling air path determined by the correction scheme; a filter element adjustment module, used to adjust the filter element based on the filter element type determined by the correction scheme.

[0088] The embodiment of the present invention further provides a computer-readable storage medium, on which instructions are stored, which, when executed on a computer, enable the computer to execute the above-mentioned air cooling state control method of the refining heating furnace monitoring system.

[0089] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0090] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0091] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for controlling the air cooling state of a refining heating furnace monitoring system, characterized in that: The method comprises: Collecting operation data of a refining heating furnace, and building a digital twin model of the refining heating furnace based on the operation data; Identifying status information of each monitoring system of the refining heating furnace in the digital twin model, and determining cooling demand information of each monitoring system based on the status information; Based on the cooling demand information, simulating the air cooling correction scheme of each monitoring system in the digital twin model to obtain the optimal correction scheme; Based on the optimal correction scheme, the air cooling state correction of each monitoring system is performed.

2. The method according to claim 1, characterized in that The operation data of the refining heating furnace is collected including: Based on the DCS system of the refinery, the operation data of the refinery heating furnace itself and the operation data of the preset related equipment are collected to obtain the initial data; Performing data preprocessing on the initial data to obtain valid data; The historical operation data of the current refining and heating furnace is collected and merged with the effective data to obtain the construction data, and the construction data is used as the operation data of the refining and heating furnace.

3. The method according to claim 1, characterized in that The status information of each monitoring system includes: Monitor the temperature information and real-time operation information of the location of the system; The temperature information at the location includes real-time temperature information and predicted temperature information within a future preset time period obtained based on the digital twin model.

4. The method according to claim 1, characterized in that The determining the cooling requirement information of each monitoring system based on the state information includes: Generate a corresponding state data matrix based on the state information of each monitoring system, and generate a corresponding feature vector based on the state data matrix; Importing the feature vector into a preset nonlinear mapping function to obtain a mapping result; Based on the mapping results, simulated temperature information of each monitoring system is obtained; Based on the preset normal temperature information and the simulated temperature information, the cooling requirement information of each monitoring system is determined.

5. The method according to claim 1, characterized in that The monitoring system comprises: One or more of infrared sensor, gas concentration monitor, image acquisition device, sound sensor.

6. The method according to claim 1, characterized in that Based on the cooling demand information, simulating the air cooling correction scheme of each monitoring system in the digital twin model to obtain the optimal correction scheme includes: Taking the cooling demand information as the optimization target, taking the current operating parameters and the interference parameters determined by the user as the initial state information, simulating the air cooling correction scheme in the digital twin model, and obtaining multiple candidate schemes; Screen multiple candidate solutions and obtain the optimal revised solution.

7. The method according to claim 1, characterized in that The amendments include: One or more of cooling air type switching, cooling air pressure adjustment, cooling air path correction and filter element adjustment.

8. The method according to claim 7, characterized in that The cooling air types include: Instrument air, industrial air and dry air conditioning air.

9. The method according to claim 7, characterized in that: The method of screening multiple candidate solutions to obtain the optimal revised solution includes: Determine whether there is a candidate solution with the same cooling air type as the current one among the multiple candidate solutions. If yes, filter out the candidate solutions with different cooling air types from the current one, and form a first filtering candidate set based on the remaining candidate solutions; otherwise, retain all candidate solutions, and form a first filtering candidate set based on all candidate solutions; Based on the digital twin model, the execution process of each candidate solution in the first filtering candidate set is simulated respectively, and the power consumption after the execution is completed is read; The power consumption of each candidate solution is compared, and the candidate solution with the lowest power consumption is selected as the optimal correction solution.

10. A wind cooling state control system for a refining heating furnace monitoring system, characterized in that: The system comprises: A collection unit, used for collecting operation data of the refining heating furnace, and building a digital twin model of the refining heating furnace based on the operation data; A processing unit, configured to identify status information of each monitoring system of the refining heating furnace in the digital twin model, and determine cooling demand information of each monitoring system based on the status information; A simulation unit, used to simulate the air cooling correction scheme of each monitoring system in the digital twin model based on the cooling demand information to obtain an optimal correction scheme; An execution unit is used to execute the air cooling state correction of each monitoring system based on the optimal correction scheme.

11. The system according to claim 10, characterized in that The correction scheme includes: one or more of: cooling air type switching, cooling air pressure adjustment, cooling air path correction and filter element selection; The cooling air types include: instrument air, industrial air and dry air conditioning air; The execution unit comprises: A cooling air type switching module, used for switching the cooling air type based on the cooling air type determined by the correction scheme; A cooling air pressure adjustment module, used for adjusting the cooling air pressure based on the cooling air pressure determined by the correction scheme; A cooling air path correction module, used to correct the cooling air path based on the cooling air path determined by the correction scheme; The filter element adjustment module is used to adjust the filter element based on the filter element type determined by the correction plan.

12. A computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the air cooling state control method of a refining heating furnace monitoring system as described in any one of claims 1 to 9.

Images