RCO system catalyst activity intelligent regulation and control method, system, medium and equipment

Abstract

The invention discloses an RCO system catalyst activity intelligent regulation and control method, system, medium and equipment. The method comprises the following steps: acquiring working condition monitoring data of an RCO system; correspondingly outputting different fuzzy strategies according to the working condition monitoring data by utilizing a PID (Proportion Integration Differentiation) algorithm; when the multiple fuzzy strategies are triggered at the same time, PID parameters are dynamically adjusted, and a working condition stability maintaining control instruction is output to an execution mechanism according to the dynamically-adjusted PID parameters; and under the condition that the working condition is stable, catalyst regeneration is executed according to the working condition monitoring data. Therefore, different fuzzy strategies can be output according to actual working condition fluctuation, and then intelligent and accurate regulation and control of the RCO system catalyst activity are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of regenerative catalytic combustion, and in particular to a method, system, medium and equipment for intelligently controlling the activity of a catalyst in an RCO system. Background Art

[0002] Regenerative catalytic combustion (RCO) technology is one of the highly effective solutions for volatile organic compounds (VOCs) treatment. It combines the technical advantages of regenerative thermal oxidation (RTO) and catalytic combustion (CO), and features high purification efficiency, low energy consumption, and strong environmental performance.

[0003] Regenerative Thermal Oxidation (RTO): Recovers the heat of high-temperature flue gas after combustion through a ceramic thermal storage body (heat exchange medium) (the recovery rate can reach over 90%), preheats the incoming low-temperature VOCs exhaust gas, and significantly reduces fuel consumption.

[0004] Catalytic combustion (CO): Under the action of catalysts (such as platinum, palladium and other precious metals), VOCs undergo flameless oxidation reaction at a relatively low temperature (usually 250-400℃), decomposing into CO2 and H2O, avoiding secondary pollution such as nitrogen oxides (NOx) produced by high-temperature combustion.

[0005] Regarding catalytic combustion, existing RCO systems often use fixed parameters to control catalyst activity, failing to adjust in real time to fluctuations in operating conditions (such as fluctuating exhaust gas concentrations and temperatures). This can lead to high energy consumption and the risk of catalyst deactivation. Furthermore, manual intervention and adjustments are subject to lag and rely on operator skill, making precise control of regenerative catalytic combustion difficult. Summary of the Invention

[0006] The present invention provides a method, system, medium and equipment for intelligent control of catalyst activity in an RCO system, which can output different fuzzy strategies according to actual operating condition fluctuations, thereby realizing intelligent and precise control of catalyst activity in the RCO system.

[0007] In a first aspect, a method for intelligently controlling catalyst activity in an RCO system is provided, comprising the following steps: Obtain the operating condition monitoring data of the RCO system; Utilize the PID algorithm to output different fuzzy strategies according to the working condition monitoring data; When multiple fuzzy strategies are triggered simultaneously, the PID parameters are dynamically adjusted, and working condition stabilization control instructions are output to the actuator according to the dynamically adjusted PID parameters; Under stable operating conditions, catalyst regeneration is performed according to the operating condition monitoring data.

[0008] In some embodiments, the step of outputting different fuzzy strategies according to the working condition monitoring data using the PID algorithm includes: The operating condition monitoring data includes: temperature deviation, gas concentration change rate and catalyst bed pressure difference trend; The operating condition monitoring data is designed to be three-level fuzzy. According to the combination results of different levels of fuzziness corresponding to the temperature deviation, the gas concentration change rate and the catalyst bed pressure difference trend, the PID algorithm is used to output the corresponding fuzzy strategy according to the combination results.

[0009] In some embodiments, the step of outputting a corresponding fuzzy strategy according to the combination result using a PID algorithm includes: When the temperature deviation is at a high level of fuzziness, the gas concentration change rate is at a fast rising level of fuzziness, and the catalyst bed pressure difference trend is at a high level of fuzziness, the proportional parameter is increased and the integral parameter is decreased; When the temperature deviation is high-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, the proportional parameter is increased, the integral parameter is maintained, and the differential parameter is increased; When the temperature deviation is high-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is reduced and the differential parameter is increased; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is rapidly rising fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, then the proportional parameter is medium, the integral parameter is reduced, and the differential parameter is reduced; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is maintained, the integral parameter is increased, and the differential parameter is maintained; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, the proportional parameter is increased, the integral parameter is maintained, and the differential parameter is increased; When the temperature deviation is low-level fuzzy, the gas concentration change rate is rapidly rising fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is increased and the integral parameter is decreased; When the temperature deviation is low-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, then the medium proportional parameter, medium integral parameter, and differential parameter are maintained; When the temperature deviation is low-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, the proportional parameter is reduced, the integral parameter is increased, and the differential parameter is reduced.

[0010] In some embodiments, when multiple fuzzy strategies are triggered simultaneously, the PID parameters are dynamically adjusted, and the working condition stabilization control instructions are output to the actuator according to the dynamically adjusted PID parameters, including: Traverse all fuzzy strategies, calculate the membership values ​​of different levels of fuzziness corresponding to each fuzzy strategy based on the mixed membership function, and select the minimum membership value as the activation weight of each fuzzy strategy; The PID parameters are dynamically adjusted according to the activation weight of each fuzzy strategy, the activation weight corresponding to each fuzzy strategy is normalized, and the normalization result and the dynamically adjusted PID parameters are weighted averaged to generate the working condition stabilization control instructions.

[0011] In some embodiments, after the step of dynamically adjusting the PID parameters according to the activation weight of each fuzzy strategy, normalizing the activation weight corresponding to each fuzzy strategy, and performing weighted averaging of the normalized result and the dynamically adjusted PID parameters to generate the working condition stabilization control instruction, the following steps are included: When the working condition stabilization control instruction is greater than or equal to the preset limit value, the working condition stabilization control instruction is compensated, and the compensation method is shown in the following formula:

[0012] Where u cmd It is the original working condition stabilization control instruction; final It is the control instruction for maintaining stability of working condition after compensation; u max is the maximum allowable input of the actuator; K is the compensation coefficient; tanh is the hyperbolic tangent function.

[0013] In some embodiments, the step of performing catalyst regeneration according to the operating condition monitoring data includes: When the pressure difference of the catalyst bed is detected to be greater than the pressure difference threshold, the exhaust gas solenoid valve is controlled to close and the spare catalyst bed is activated; Control the furnace temperature to heat; Control the introduction of oxygen-containing regeneration gas and maintain the furnace temperature within the preset time; Control the flow of normal temperature air; Control the opening of the exhaust solenoid valve, switch back to the main catalyst bed, and gradient load the exhaust gas volume.

[0014] In some embodiments, after outputting different fuzzy strategies according to the working condition monitoring data using the PID algorithm, the method includes: The network model is trained according to the catalyst activity historical data, and the fuzzy strategy is optimized using the trained network model.

[0015] In the second aspect, an intelligent control system for catalyst activity of an RCO system is provided, comprising: Data acquisition module, used to obtain the working condition monitoring data of the RCO system; A fuzzy strategy output module is in communication with the data acquisition module and is used to output different fuzzy strategies according to the working condition monitoring data using a PID algorithm; A working condition stabilization instruction module is in communication with the fuzzy strategy output module and is used to dynamically adjust the PID parameters when multiple fuzzy strategies are triggered simultaneously, and output working condition stabilization control instructions to the actuator according to the dynamically adjusted PID parameters; The regeneration execution module is in communication with the working condition stabilization instruction module and is used to execute catalyst regeneration according to the working condition monitoring data under the working condition stabilization condition.

[0016] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for intelligently controlling the catalyst activity of the RCO system as described above is implemented.

[0017] In a fourth aspect, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein the processor implements the above-described method for intelligently controlling the catalyst activity of the RCO system when executing the computer program. Compared with the existing technology, the advantages of the present invention are as follows: the PID algorithm is used to output different fuzzy strategies according to the actual operating condition fluctuations, and the PID parameters are dynamically adjusted to output the operating condition stabilization control instructions. Under stable operating conditions, catalyst regeneration is executed according to the operating condition monitoring data, thereby realizing intelligent and precise control of the catalyst activity of the RCO system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of an embodiment of a method for intelligently controlling catalyst activity in an RCO system according to the present invention; Figure 2 This is a flow chart of another embodiment of a method for intelligently controlling catalyst activity in an RCO system according to the present invention; Figure 3 It is a schematic structural diagram of the catalyst regeneration execution of the present invention; Figure 4 It is a structural schematic diagram of an RCO system catalyst activity intelligent control system of the present invention. DETAILED DESCRIPTION

[0019] Reference will now be made in detail to specific embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Although the present invention will be described in conjunction with specific embodiments, it will be understood that the present invention is not intended to be limited to those embodiments. On the contrary, it is intended to cover variations, modifications, and equivalents within the spirit and scope of the present invention as defined by the appended claims. It should be noted that the method steps described herein can be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0020] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Note: The following example is only a specific example and is not intended to limit the embodiments of the present invention to the following specific steps, values, conditions, data, sequence, etc. Those skilled in the art can apply the concepts of the present invention to construct more embodiments not described in this specification by reading this specification.

[0022] Because existing RCO systems mostly use fixed parameters to control catalyst activity, they are unable to make real-time adjustments based on actual operating conditions (such as exhaust gas concentration and temperature changes), which in turn leads to high energy consumption or the risk of catalyst deactivation. Furthermore, manual intervention and adjustment have lags and rely on the operator's skill level, making it difficult to achieve precise control of regenerative catalytic combustion. Based on the above problems, the present invention proposes an intelligent control method for catalyst activity in an RCO system. Figure 1 As shown, the method includes: S100: Acquire operating condition monitoring data of the RCO system.

[0023] By integrating monitoring devices such as temperature sensors, gas concentration detectors, and catalyst bed pressure difference, the operating data of the RCO system can be collected in real time.

[0024] S200: Utilize a PID algorithm to output different fuzzy strategies according to the working condition monitoring data.

[0025] The fuzzy PID algorithm is used to integrate multi-dimensional data such as temperature, concentration, and pressure difference, and outputs different fuzzy strategies accordingly. The details are as follows: Input variables: temperature deviation (ΔT), gas concentration change rate (dC / dt), catalyst bed pressure difference trend (ΔP / Δt).

[0026] The working condition monitoring data is designed to be three-level fuzzy, specifically: The temperature deviation is low, medium and high; the gas concentration change rate is stable, slowly rising and rapidly rising; the catalyst bed pressure difference trend is: low, medium and high.

[0027] Output variables: PID parameters (Kp, Ti, Td).

[0028] According to the changes in the input variables temperature deviation (ΔT), concentration change rate (dC / dt), and pressure difference trend (ΔP / Δt), different levels of fuzzy combination results are generated, and several fuzzy strategies / rules are established based on the combination results using the PID algorithm.

[0029] Rule 1: When the temperature deviation is at a high level of fuzziness, the gas concentration change rate is at a rapidly rising level of fuzziness, and the catalyst bed pressure difference trend is at a high level of fuzziness, increase the proportional parameter and decrease the integral parameter; Rule 2: When the temperature deviation is high-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, then increase the proportional parameter, maintain the integral parameter, and increase the differential parameter; Rule 3: When the temperature deviation is high-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, then reduce the proportional parameter and increase the differential parameter; Rule 4: When the temperature deviation is medium-level fuzzy, the gas concentration change rate is rapidly rising, and the catalyst bed pressure difference trend is medium-level fuzzy, then adjust the proportional parameter, reduce the integral parameter, and reduce the differential parameter. Rule 5: When the temperature deviation is medium-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, maintain the proportional parameter, increase the integral parameter, and maintain the differential parameter; Rule 6: When the temperature deviation is medium-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, increase the proportional parameter, maintain the integral parameter, and increase the differential parameter; Rule 7: When the temperature deviation is low-level fuzzy, the gas concentration change rate is rapidly rising, and the catalyst bed pressure difference trend is low-level fuzzy, increase the proportional parameter and decrease the integral parameter; Rule 8: When the temperature deviation is low-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, then the medium proportional parameter, medium integral parameter, and differential parameter are maintained; Rule 9: When the temperature deviation is low-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, reduce the proportional parameter, increase the integral parameter, and reduce the differential parameter.

[0030] The above 9 fuzzy rules are intuitively reflected in the following Table 1: Table 1

[0031] S300, when multiple fuzzy strategies are triggered simultaneously, the PID parameters are dynamically adjusted, and working condition stabilization control instructions are output to the actuator according to the dynamically adjusted PID parameters.

[0032] The temperature deviation ΔT, concentration change rate dC / dt and pressure difference trend ΔP / Δt of the controlled object are collected in real time through sensors; Each input variable is fuzzified at three levels. For each fuzzy rule's antecedent condition (such as "ΔT = high and dC / dt = slowly rising and ΔP / Δt = high"), a mixed membership function is used to calculate the three membership values ​​of each fuzzy rule's antecedent condition (i.e., fuzzy set). The minimum value is taken as the activation weight of the fuzzy rule, that is:

[0033] The triangular membership function is used for ΔT, and the mathematical expression is as follows:

[0034] Using Gaussian membership function for dC / dt and ΔP / Δt, the mathematical expressions are as follows:

[0035] Then, the PID parameters are dynamically adjusted according to the activation weight of each fuzzy strategy, the activation weight corresponding to each fuzzy strategy is normalized, and the normalization result and the dynamically adjusted PID parameters are weighted averaged to generate the working condition stabilization control instructions.

[0036] The PID parameters of each fuzzy rule are dynamically adjusted as follows:

[0037] Where α, β, and γ are adjustable gain coefficients; the adjustment values ​​ΔKp, ΔTi, and ΔTd of the proportional coefficient Kp, integral time Ti, and differential time Td can be generated according to the activation weight.

[0038] The specific formula for normalization is as follows:

[0039] The formula for weighted average is as follows:

[0040] Where u i is the output value of the PID parameters of the i-th fuzzy rule after dynamic adjustment; ucmd It is the output working condition stabilization control instruction.

[0041] The method further comprises the following steps: dynamically adjusting the PID parameters according to the activation weight of each fuzzy strategy, normalizing the activation weight corresponding to each fuzzy strategy, and performing weighted averaging of the normalization result and the dynamically adjusted PID parameters to generate the working condition stabilization control instruction; and When the working condition stabilization control instruction is greater than or equal to the preset limit value, the working condition stabilization control instruction is compensated, and the compensation method is shown in the following formula: ; Where u cmd It is the original working condition stabilization control instruction; final It is the control instruction for maintaining stability of working condition after compensation; u max is the maximum allowable input of the actuator; K is the compensation coefficient; tanh is the hyperbolic tangent function.

[0042] Therefore, when multiple rules are triggered at the same time, the minimum value of the membership values ​​of all antecedent conditions is taken as the weight, the PID parameters are dynamically adjusted through the fuzzy inference engine, and control instructions are output to the actuator (such as variable frequency fan speed, electric heating power, fresh air valve opening, high temperature valve opening, etc.).

[0043] S400, see also Figure 2 Right now Figure 3 As shown, under stable operating conditions, catalyst regeneration is performed according to the operating condition monitoring data. The specific method is as follows: S410, pre-regeneration preparation: When the pressure difference of the catalyst bed is detected to be greater than the pressure difference threshold (regeneration is triggered when ΔP>2kPa), the exhaust gas solenoid valve is controlled to close and the spare catalyst bed is activated; S420, heating stage: control the heating of the furnace; raise the furnace temperature to 350-450℃ (depending on the catalyst type) through burner / electric heating; heating rate: 3-5℃ / min (to prevent thermal shock).

[0044] S430, oxidation regeneration stage: controlling the introduction of oxygen-containing regeneration gas and maintaining the furnace temperature within a preset time; Introduce oxygen-containing regeneration gas (oxygen concentration 5-10%) and maintain the temperature at 400±20℃ for 2-4 hours; Key parameter monitoring: while T<450 and CO concentration>50ppm: adjust the fuel valve opening (±5%); adjust the fan frequency (Hz±2); adjust the valve switching time (±10s).

[0045] S440, purge cooling stage: control the introduction of room temperature air; Switch to room temperature air purge, cooling rate: ≤10℃ / min, target temperature: ≤150℃~250℃ (depending on the catalyst type).

[0046] S450, system recovery: control to open the exhaust solenoid valve, switch back to the main catalyst bed, and gradient load the exhaust volume (20% / 10min).

[0047] After the PID algorithm is used to output different fuzzy strategies according to the working condition monitoring data in step S200, the method includes: S500: Train the network model based on the catalyst activity history data, and optimize the fuzzy strategy using the trained network model, thereby optimizing the control strategy to adapt to different operating scenarios. The specific method is as follows: Import the catalyst activity historical data into the SQL database; Fill numeric fields with mean / median and categorical fields with mode or "unknown" label (Pandas, PySpark in Python); The data was standardized and classified (FeatureTools, TSFresh).

[0048] Model construction and training: First, supervised data learning is used to prioritize equipment failure prediction using LSTM and Transformer time series models. Then, algorithms such as Q-Learning and PPO are used to optimize control strategies for key equipment within the system. During the training process, A / B testing is used to verify the effectiveness of new strategies. For example, the reward function is used to maximize heat recovery (Q = ΔT × flow rate) and minimize natural gas consumption. The operating condition analysis function is used to shorten valve switching cycles and improve combustion efficiency under high-concentration conditions. Under low-concentration conditions, intermittent combustion is used to reduce natural gas consumption. A catalyst activity compensation function is also used. Finally, a microservices architecture is built and the model is deployed on an IoT platform (including edge computing nodes) or the cloud for offline management and control.

[0049] Deployment implementation process: Phase 1: Offline training of historical data prediction model.

[0050] Phase 2: Digital twin simulation verifies the safety of the control strategy.

[0051] Phase 3: Grayscale launch of edge devices (trial run with 10% traffic).

[0052] Phase 4: Full deployment and cloud-based monitoring of model drift (KS test).

[0053] Therefore, by introducing a dynamic evaluation model of catalyst activity, traditional empirical parameters are converted into quantifiable control variables; a full-process automated control link of "monitoring-decision-execution" is constructed to achieve unmanned intelligent regulation.

[0054] The key technical points of the present invention are as follows: 1. Multi-parameter fusion catalyst activity monitoring module: including sensor selection and configuration and data fusion algorithm; 2: Adaptive control algorithm: covers the composite algorithm architecture and parameter optimization rules of fuzzy PID and model predictive control; 3: Closed-loop control logic: fan / heating module linkage control strategy triggered by activity index threshold; 4: Cloud data interaction mechanism: supports OTA update function of remote monitoring and control strategy.

[0055] Technical advantages: 1: It can improve the utilization rate of catalyst and reduce the energy consumption of the system; 2: Reduce the frequency of manual intervention and avoid the risk of catalyst sintering caused by parameter lag; 3: Compatible with RCO devices of different specifications and has strong scalability.

[0056] See also Figure 4 As shown, an embodiment of the present invention provides an RCO system catalyst activity intelligent control system, comprising: Data acquisition module, used to obtain the working condition monitoring data of the RCO system; A fuzzy strategy output module is in communication with the data acquisition module and is used to output different fuzzy strategies according to the working condition monitoring data using a PID algorithm; A working condition stabilization instruction module is in communication with the fuzzy strategy output module and is used to dynamically adjust the PID parameters when multiple fuzzy strategies are triggered simultaneously, and output working condition stabilization control instructions to the actuator according to the dynamically adjusted PID parameters; The regeneration execution module is in communication with the working condition stabilization instruction module and is used to execute catalyst regeneration according to the working condition monitoring data under the working condition stabilization condition.

[0057] In summary, the present invention can utilize the PID algorithm to output different fuzzy strategies according to the actual operating condition fluctuations, dynamically adjust the PID parameters, output operating condition stabilization control instructions, and perform catalyst regeneration according to the operating condition monitoring data under stable operating conditions, thereby realizing intelligent and precise regulation of the catalyst activity of the RCO system.

[0058] Specifically, this embodiment corresponds one-to-one to the above method embodiment, and the functions of each module have been described in detail in the corresponding method embodiment, so they will not be repeated here.

[0059] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.

[0060] The present invention may implement all or part of the above-described method processes by instructing related hardware through a computer program. The computer program may be stored in a computer-readable storage medium. When executed by a processor, the computer program may implement the steps of each of the above-described method embodiments. The computer program includes computer program code, which may be in source code form, object code form, an executable file, or some intermediate form. Computer-readable media may include any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunications signals, and software distribution media. It should be noted that the content of a computer-readable medium may be appropriately expanded or reduced based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media do not include electric carrier signals or telecommunications signals.

[0061] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.

[0062] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of a computer device, connecting all parts of the entire computer device using various interfaces and circuits.

[0063] The memory can be used to store computer programs and / or modules. The processor implements the various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (e.g., a sound playback function, an image playback function, etc.); the data storage area may store data generated based on the use of the mobile phone (e.g., audio data, video data, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0064] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, servers, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage) containing computer-usable program code.

[0065] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), servers, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0068] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for intelligently controlling catalyst activity in an RCO system, characterized in that: The following steps are involved: Obtain the operating condition monitoring data of the RCO system; Utilize the PID algorithm to output different fuzzy strategies according to the working condition monitoring data; When multiple fuzzy strategies are triggered simultaneously, the PID parameters are dynamically adjusted, and working condition stabilization control instructions are output to the actuator according to the dynamically adjusted PID parameters; Under stable operating conditions, catalyst regeneration is performed according to the operating condition monitoring data.

2. The RCO system catalyst activity intelligent control method according to claim 1, characterized in that: The steps of outputting different fuzzy strategies according to the working condition monitoring data using the PID algorithm include: The operating condition monitoring data includes: temperature deviation, gas concentration change rate and catalyst bed pressure difference trend; The operating condition monitoring data is designed to be three-level fuzzy. According to the combination results of different levels of fuzziness corresponding to the temperature deviation, the gas concentration change rate and the catalyst bed pressure difference trend, the PID algorithm is used to output the corresponding fuzzy strategy according to the combination results.

3. The RCO system catalyst activity intelligent control method according to claim 2, characterized in that: The step of outputting a corresponding fuzzy strategy according to the combination result using the PID algorithm includes: When the temperature deviation is at a high level of fuzziness, the gas concentration change rate is at a fast rising level of fuzziness, and the catalyst bed pressure difference trend is at a high level of fuzziness, the proportional parameter is increased and the integral parameter is decreased; When the temperature deviation is high-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, the proportional parameter is increased, the integral parameter is maintained, and the differential parameter is increased; When the temperature deviation is high-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is reduced and the differential parameter is increased; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is rapidly rising fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, then the proportional parameter is medium, the integral parameter is reduced, and the differential parameter is reduced; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is maintained, the integral parameter is increased, and the differential parameter is maintained; When the temperature deviation is medium-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, the proportional parameter is increased, the integral parameter is maintained, and the differential parameter is increased; When the temperature deviation is low-level fuzzy, the gas concentration change rate is rapidly rising fuzzy, and the catalyst bed pressure difference trend is low-level fuzzy, the proportional parameter is increased and the integral parameter is decreased; When the temperature deviation is low-level fuzzy, the gas concentration change rate is slowly rising-level fuzzy, and the catalyst bed pressure difference trend is high-level fuzzy, then the medium proportional parameter, medium integral parameter, and differential parameter are maintained; When the temperature deviation is low-level fuzzy, the gas concentration change rate is stable-level fuzzy, and the catalyst bed pressure difference trend is medium-level fuzzy, the proportional parameter is reduced, the integral parameter is increased, and the differential parameter is reduced.

4. The RCO system catalyst activity intelligent control method according to claim 2, characterized in that: When multiple fuzzy strategies are triggered simultaneously, the PID parameters are dynamically adjusted, and the working condition stabilization control instructions are output to the actuator according to the dynamically adjusted PID parameters, including: Traverse all fuzzy strategies, calculate the membership values ​​of different levels of fuzziness corresponding to each fuzzy strategy based on the mixed membership function, and select the minimum membership value as the activation weight of each fuzzy strategy; The PID parameters are dynamically adjusted according to the activation weight of each fuzzy strategy, the activation weight corresponding to each fuzzy strategy is normalized, and the normalization result and the dynamically adjusted PID parameters are weighted averaged to generate the working condition stabilization control instructions.

5. The RCO system catalyst activity intelligent control method according to claim 4, characterized in that: The method further comprises the following steps: dynamically adjusting the PID parameters according to the activation weight of each fuzzy strategy, normalizing the activation weight corresponding to each fuzzy strategy, and performing weighted averaging of the normalization result and the dynamically adjusted PID parameters to generate the working condition stabilization control instruction; and When the working condition stabilization control instruction is greater than or equal to the preset limit value, the working condition stabilization control instruction is compensated, and the compensation method is shown in the following formula: Where u cmd It is the original working condition stabilization control instruction; final It is the control instruction for maintaining stability of working condition after compensation; u max is the maximum allowable input of the actuator; K is the compensation coefficient; tanh is the hyperbolic tangent function.

6. The RCO system catalyst activity intelligent control method according to claim 1, characterized in that: The step of performing catalyst regeneration according to the operating condition monitoring data includes: When the pressure difference of the catalyst bed is detected to be greater than the pressure difference threshold, the exhaust gas solenoid valve is controlled to close and the spare catalyst bed is activated; Control the furnace temperature to heat; Control the introduction of oxygen-containing regeneration gas and maintain the furnace temperature within the preset time; Control the flow of normal temperature air; Control the opening of the exhaust solenoid valve, switch back to the main catalyst bed, and gradient load the exhaust gas volume.

7. The RCO system catalyst activity intelligent control method according to claim 1, characterized in that: After the PID algorithm is used to output different fuzzy strategies according to the working condition monitoring data, the method includes: The network model is trained according to the catalyst activity historical data, and the fuzzy strategy is optimized using the trained network model.

8. An intelligent control system for catalyst activity of an RCO system, characterized in that: include: Data acquisition module, used to obtain the working condition monitoring data of the RCO system; A fuzzy strategy output module is in communication with the data acquisition module and is used to output different fuzzy strategies according to the working condition monitoring data using a PID algorithm; A working condition stabilization instruction module is in communication with the fuzzy strategy output module, and is used to dynamically adjust the PID parameters when multiple fuzzy strategies are triggered simultaneously, and output working condition stabilization control instructions to the actuator according to the dynamically adjusted PID parameters; The regeneration execution module is in communication with the working condition stabilization instruction module and is used to execute catalyst regeneration according to the working condition monitoring data under the working condition stabilization condition.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for intelligently controlling catalyst activity of an RCO system according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein: When the processor runs the computer program, the method for intelligently controlling catalyst activity of the RCO system according to any one of claims 1 to 7 is implemented.

Images