Catalyst activity prediction method, device and computer readable storage medium

Abstract

Embodiments of the present disclosure provide a catalyst activity prediction method, device, and computer-readable storage medium. The method includes: obtaining the historical reaction rate of the reactant catalyzed by the catalyst; calculating the historical true activity of the catalyst based on the historical reaction rate and a preset mechanism model; using the historical true activity of the catalyst and the historical activity influencing parameters of the catalyst to train a preset catalytic activity model to obtain a target catalytic activity model; inputting the current activity influencing parameters of the catalyst into the target catalytic activity model to obtain the current predicted activity of the catalyst. In this way, a catalytic activity model can be constructed using mechanisms and data, so that the current predicted activity of the catalyst can be accurately obtained using the target catalytic activity model, thereby intelligently managing the activity of the catalyst.

Description

Technical Field

[0001] The present disclosure relates to the field of catalysts, and in particular to the field of catalytic activity technology. Background Art

[0002] At present, chemical industry production processes mostly involve catalytic reactions, among which precious metal catalysts have the advantages of high catalytic efficiency, good selectivity, and high strength, and are widely used in the continuous production process of the chemical industry, such as propane dehydrogenation, hydrogen chloride oxidation, acrylic acid oxidation, SCR denitrification and other fields. Due to the use of precious metals, the catalyst cost is high, and during the use of the catalyst active metal due to high temperature, catalyst poisons, coking and other reasons, the catalyst activity gradually decreases. The reduction in catalyst activity leads to a reduction in reaction conversion rate or selectivity, resulting in reduced economic benefits of the device production or unqualified environmental protection indicators, such as excessive nitrogen oxides in the exhaust gas after SCR catalysis.

[0003] Therefore, how to accurately predict catalyst activity, manage catalyst activity based on the catalyst activity prediction results, and adopt appropriate methods to improve catalytic activity to significantly improve the economic benefits of plant operation has become an urgent problem to be solved. Summary of the invention

[0004] The present disclosure provides a catalyst activity prediction method, device and storage medium.

[0005] According to a first aspect of the present disclosure, a method for predicting catalyst activity is provided. The method comprises: obtaining a historical reaction rate of a reactant catalyzed by the catalyst;

[0006] Calculating the historical real activity of the catalyst according to the historical reaction rate and the preset mechanism model;

[0007] Using the historical real activity of the catalyst and the historical activity influencing parameters of the catalyst, a preset catalytic activity model is trained to obtain a target catalytic activity model;

[0008] The current activity influencing parameters of the catalyst are input into the target catalytic activity model to obtain the current predicted activity of the catalyst.

[0009] According to the above aspects and any possible implementation, an implementation is further provided, wherein obtaining the historical reaction rate of the reactant catalyzed by the catalyst comprises:

[0010] The historical reaction rate is calculated based on the historical reactant concentration at the inlet position and the historical product concentration at the outlet position of the catalyst reactor where the catalyst is located.

[0011] According to the above aspects and any possible implementation, an implementation is further provided, wherein the historical real activity of the catalyst is calculated according to the historical reaction rate and a preset mechanism model, comprising:

[0012] The historical true activity of the catalyst is calculated based on the historical reaction rate, the historical concentration of the reactant, the historical reaction temperature, the reaction pre-exponential factor A of the catalyst, the activation energy E and the preset mechanism model.

[0013] According to the aspects described above and any possible implementation method, an implementation method is further provided, which calculates the reaction pre-exponential factor A and the activation energy E according to the reactant concentration and product concentration of the catalyst reactor where the catalyst is located at different test temperatures.

[0014] According to the above aspects and any possible implementation, an implementation is further provided, wherein the use of the historical real activity of the catalyst and the historical activity influencing parameter of the catalyst to train a preset catalytic activity model to obtain a target catalytic activity model includes:

[0015] Inputting the historical activity influencing parameters of the catalyst into the preset catalytic activity model to obtain the historical predicted activity of the catalyst;

[0016] According to the historical real activity and the historical predicted activity of the catalyst, it is judged whether the preset catalytic activity model has been trained to obtain the target catalytic activity model.

[0017] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0018] After obtaining the current predicted activity of the target catalytic activity model, the current activity influencing parameters are optimized using an optimization algorithm and the current predicted activity, under the condition that the reactant catalyzed by the catalyst can obtain an optimal conversion rate and the optimal conversion rate remains unchanged, so as to determine the optimal activity influencing parameters when the current predicted activity output by the target catalytic activity model reaches the best;

[0019] Determining the optimal temperature rise curve corresponding to the catalyst according to the optimal activity influencing parameter;

[0020] The catalytic temperature of the catalyst is controlled according to the optimal temperature rise curve.

[0021] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0022] determining a deactivation rate of the catalyst based on a current predicted activity of the catalyst and a historical predicted activity output by the target catalytic activity model;

[0023] If the deactivation rate of the catalyst is higher than a preset deactivation threshold, a deactivation warning is issued.

[0024] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0025] Inputting the current activity influencing parameters of the catalyst into the preset mechanism model to calculate the current real activity of the catalyst;

[0026] If the activity difference between the current actual activity and the current predicted activity is greater than a preset activity difference, a model distortion warning is issued for the target catalytic activity model.

[0027] According to a second aspect of the present disclosure, an electronic device is provided. The electronic device includes: a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0028] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect and / or the second aspect of the present disclosure is implemented.

[0029] In the present disclosure, a preset mechanism model can be used to automatically calculate the historical true activity of the catalyst, and then the preset catalytic activity model can be trained using the historical true activity of the catalyst and the historical activity influencing parameters of the catalyst, so as to automatically obtain a target catalytic activity model that can more accurately reflect the catalytic activity, and then the current activity influencing parameters of the catalyst are automatically input into the target catalytic activity model, so as to accurately obtain the current predicted activity of the catalyst, so as to facilitate the intelligent management of the activity of the catalyst.

[0030] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0032] Figure 1A flow chart of a catalyst activity prediction method according to an embodiment of the present disclosure is shown;

[0033] Figure 2 A flow chart of a method for optimizing catalyst activity according to an embodiment of the present disclosure is shown;

[0034] Figure 3 shows a schematic diagram of a catalyst reactor according to an embodiment of the present disclosure;

[0035] Figure 4 A schematic diagram showing the comparison of catalyst activity before and after optimization according to an embodiment of the present disclosure is shown;

[0036] Figure 5 A schematic diagram showing PCA analysis results of parameters affecting the historical activity of a catalyst according to an embodiment of the present disclosure is shown;

[0037] Figure 6 A schematic diagram showing a catalyst temperature rise curve according to an embodiment of the present disclosure is shown;

[0038] Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0040] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0041] Figure 1 A flow chart of a catalyst activity prediction method 100 according to an embodiment of the present disclosure is shown. The method 100 may include:

[0042] Step 110, obtaining the historical reaction rate of the reactant catalyzed by the catalyst;

[0043] Step 120, calculating the historical real activity of the catalyst according to the historical reaction rate and a preset mechanism model;

[0044] Step 130, using the historical real activity of the catalyst and the historical activity influencing parameter of the catalyst, training a preset catalytic activity model to obtain a target catalytic activity model;

[0045] Since the number of physical quantities of historical activity influencing parameters / current activity influencing parameters is large, PCA dimensionality reduction can be performed on the historical activity influencing parameters / current activity influencing parameters (for example, the current activity influencing parameters may originally have 50 variables, but after dimensionality reduction, there may be only 18 variables), thereby reducing the input to the target catalytic activity model and making the calculation of predicted activity faster.

[0046] The input multi-dimensional variables (i.e. historical activity influencing parameters / current activity influencing parameters) are processed with dimensionality reduction to reduce the model input. The main implementation steps are as follows:

[0047] 1. Standardization of indicator data;

[0048] 2. Determine the correlation between indicators;

[0049] 3. Determine the number of principal components m;

[0050] 4. Expression of principal component Fi;

[0051] 5. The principal component is named Fi, where p represents the total number of original variables before dimensionality reduction.

[0052] F p =a 1i *Z X1 +a 2i *Z X2 +…+a pi *Z Xp

[0053] where a 1i , a 2i ……,a pi (i=1,2,…m) is the eigenvector corresponding to the eigenvalue of each input variable, Z X1 , Z X2 ,Z X3 ,……Z Xp (i=1,2,…p) is the value of the eigenvalue of the original variable after orthogonal standardization.

[0054] Then the variable F after dimension reduction is p Input to the target catalytic activity model.

[0055] The training process of the catalytic activity model ESN is as follows:

[0056] The network structure is the input layer, whose input is u(t), the reserve pool x(t) and the output layer f(t).

[0057] The reserve pool is the middle part. The advantages of the ESN network are: (1) the connection state of the neurons in the reserve pool is random; (2) the connection weights in the reserve pool are fixed, which reduces the amount of training calculations and avoids the local minimum that occurs in the gradient descent optimization algorithm, making it suitable for predictions involving time series.

[0058] ESN construction process: initialization, training and use (testing):

[0059] Assume that this echo state network has N intermediate nodes, that is, the number of neurons in the reserve pool is N, and the number of neurons in the input layer and the output layer is D. Let u(t)∈RD, x(t)∈RN, f(t)∈RD represent the input, network state (state of the reserve pool) and output at time t respectively; V∈RN×D, R∈RN×N, W∈RD×N represent the input weight, intermediate weight and output weight matrix respectively, and tanh(h) is the activation function. Then the state update method of the reserve pool and the output of the network are:

[0060] x(t)=tanh(Rx(t-1)+Vu(t)). The training of this model is to determine W. The purpose of determining W is to get the output x(t) and then get R and V.

[0061] f(t)=Wx(t)

[0062] The method for determining the weights, that is, the goal to be optimized is:

[0063]

[0064] Derivative the above formula, set its derivative to 0, and solve for W to get:

[0065] W=YX T (XX T +λI) -1 , X is the input after dimensionality reduction, Y is the predicted true value, i.e. r A The value of , λ is a preset coefficient, which is generally less than 1, and I is a preset unit matrix.

[0066] Step 140: input the current activity influencing parameters of the catalyst into the target catalytic activity model to obtain the current predicted activity of the catalyst.

[0067] After obtaining the historical reaction rates of the reactants, since the preset mechanism model is closely related to the temperature and reactant concentration that affect the catalyst activity, the preset mechanism model can be used to automatically calculate the historical true activity of the catalyst, and then the preset catalytic activity model can be trained using the historical true activity of the catalyst and the historical activity influencing parameters of the catalyst, so as to automatically obtain a target catalytic activity model that can more accurately reflect the catalytic activity, and then the current activity influencing parameters of the catalyst are automatically input into the target catalytic activity model, so as to accurately obtain the current predicted activity of the catalyst, so as to facilitate the intelligent management of the catalyst activity.

[0068] In some embodiments, obtaining the historical reaction rate of the reactant catalyzed by the catalyst comprises:

[0069] The historical reaction rate is calculated based on the historical reactant concentration at the inlet position and the historical product concentration at the outlet position of the catalyst reactor where the catalyst is located.

[0070] Based on the inlet and outlet concentrations of the catalyst reactor, the historical reaction rate can be automatically and accurately calculated.

[0071] In some embodiments, the calculating the historical real activity of the catalyst according to the historical reaction rate and the preset mechanism model includes:

[0072] The historical true activity of the catalyst is calculated based on the historical reaction rate, the historical concentration of the reactant, the historical reaction temperature, the reaction pre-exponential factor A of the catalyst, the activation energy E and the preset mechanism model.

[0073] By automatically inputting the historical reaction rate, the historical concentration of the reactant, the historical reaction temperature, the catalyst's pre-exponential factor A, and the activation energy E into the preset mechanism model, the catalyst's true historical activity can be automatically calculated. Compared with the prior art method of predicting catalyst activity using pure data, this hybrid mechanism- and data-driven approach can more accurately reflect the catalyst's true activity and better predict catalytic activity.

[0074] For example: The preset mechanism model can be

[0075] r A In the catalytic process, C can be calculated based on the concentration of reactants at the inlet position of the catalyst reactor and the concentration of products at the outlet position. A is the concentration of the reactant, n is fixed, x A is the conversion rate of reactants in the catalytic process, F Ais the amount of reactants at the inlet position during the catalytic process, W is the mass of the catalyst, which is constant, θ is the catalyst activity, and x A0 is the conversion rate of the reactants when using fresh catalyst (i.e. the conversion rate of the reactants when the catalyst is first used), F A0 is the amount of reactants at the inlet position when using fresh catalyst, R = 8.314, A is the reaction pre-exponential factor, E is the activation energy, and T is the catalytic time.

[0076] Initial reaction:

[0077] Running:

[0078] In some embodiments, the reaction pre-exponential factor A and the activation energy E are calculated based on the reactant concentration and product concentration of the catalyst reactor where the catalyst is located at different test temperatures.

[0079] By configuring a sample containing a marker (i.e., reactant), using a fresh catalyst to measure the inlet and outlet concentrations, and repeating the above operation at different temperatures, the catalyst kinetic parameters can be fitted according to the inlet and outlet conversion rates at different temperatures, thereby accurately obtaining the reaction pre-exponential factor A and activation energy E; Among them, it should be noted that during the small-scale test, a catalyst with the same space velocity and particle size as the actual industrial device should be used to eliminate the influence of external diffusion and internal diffusion.

[0080] In some embodiments, the use of the historical real activity of the catalyst and the historical activity influencing parameters of the catalyst to train a preset catalytic activity model to obtain a target catalytic activity model includes:

[0081] Inputting the historical activity influencing parameters of the catalyst into the preset catalytic activity model to obtain the historical predicted activity of the catalyst;

[0082] According to the historical real activity and the historical predicted activity of the catalyst, it is judged whether the preset catalytic activity model has been trained to obtain the target catalytic activity model.

[0083] When training the preset catalytic activity model, the historical actual activity of the catalyst and the historical predicted activity of the catalyst can be used to obtain at least one of MAE (mean absolute error), MSE (mean square error), and RMSE (root mean square error) to determine whether the historical predicted activity output by the preset catalytic activity model is accurate, that is, whether the preset catalytic activity model has been automatically trained, thereby obtaining a more accurate target catalytic activity model.

[0084] In some embodiments, the method further comprises:

[0085] After obtaining the current predicted activity of the target catalytic activity model, the current activity influencing parameters are optimized using an optimization algorithm and the current predicted activity, under the condition that the reactant catalyzed by the catalyst can obtain an optimal conversion rate and the optimal conversion rate remains unchanged, so as to determine the optimal activity influencing parameters when the current predicted activity output by the target catalytic activity model reaches the best;

[0086] The current activity influencing parameters can be multi-dimensional variables, which can include the reaction temperature of the catalyst. Of course, the catalyst can also include different beds, that is, the multi-dimensional variables can include the temperature of catalysts in different beds, so that it is convenient to obtain the optimal heating curve of catalysts in different beds, and then comprehensively and accurately extend the life of catalysts in different beds.

[0087] Determining the optimal temperature rise curve corresponding to the catalyst according to the optimal activity influencing parameter;

[0088] The catalytic temperature of the catalyst is controlled according to the optimal temperature rise curve.

[0089] By using the optimization algorithm and the current predicted activity, the current activity influencing parameters can be automatically optimized, and then the optimal activity influencing parameters when the current predicted activity output by the target catalytic activity model reaches the best are determined. The optimal activity influencing parameters are composed of temperature and other physical variables (such as inlet and outlet flow / composition, inlet and outlet pressure, circulating gas flow / composition, etc.). Therefore, the suitable temperature of the catalyst can be determined according to the optimal activity influencing parameters, thereby forming the optimal heating curve of the catalyst, and then the catalytic temperature of the catalyst is automatically controlled using the optimal heating curve to achieve optimization of the heating rate curve of each section of the catalyst while ensuring the reaction conversion rate, so as to optimize the overall operation time of the catalyst bed or maximize the economic benefits.

[0090] The process of optimizing the current activity influencing parameters may be:

[0091] Under the condition that the optimal conversion rate remains unchanged, the maximum activity formula maxf(x1,x2,x3,…) is established, x j is the variable of the jth dimension in the current activity influencing parameter, θ j is the current predicted activity output by the target catalytic activity model during the j-th optimization.

[0092] Establish the objective function:

[0093]

[0094] Using mean square error as the loss function, we optimize the parameters to make h(θ) have the minimum (maximum) value.

[0095]

[0096] Derivative of the mean square error:

[0097]

[0098] Update the next set of parameter values ​​in the reverse direction:

[0099]

[0100] Under the premise of ensuring the export conversion rate, the reaction kinetics equation and the heat balance equation are combined to solve the temperature sequence (T1, T2, T3, T4, T5...) to make the catalyst life longest (the deactivation rate lowest); the heat balance equation is simulated by general process software or the corresponding enthalpy is obtained from the literature to obtain the heat load.

[0101] In some embodiments, the method further comprises:

[0102] determining a deactivation rate of the catalyst based on a current predicted activity of the catalyst and a historical predicted activity output by the target catalytic activity model;

[0103] If the deactivation rate of the catalyst is higher than a preset deactivation threshold, a deactivation warning is issued.

[0104] The deactivation rate of the catalyst can be calculated based on the current predicted activity of the catalyst and the historical predicted activity output by the target catalytic activity model. If the deactivation rate of the catalyst is higher than the preset deactivation threshold, it means that the catalyst is deactivated too quickly. Therefore, a deactivation warning can be automatically issued to provide feedback to the operator to check the operating conditions such as catalyst poisons in the feed and operating temperature. After confirming the influence of the operating factors, the catalytic activity model will be automatically updated according to the error situation to match the actual operating conditions.

[0105] In some embodiments, the method further comprises:

[0106] Inputting the current activity influencing parameters of the catalyst into the preset mechanism model to calculate the current real activity of the catalyst;

[0107] If the activity difference between the current actual activity and the current predicted activity is greater than a preset activity difference, a model distortion warning is issued for the target catalytic activity model.

[0108] By inputting the current activity influencing parameters of the catalyst into the preset mechanism model, the current true activity of the catalyst can be automatically calculated. Then, if the activity difference between the current true activity and the current predicted activity is greater than the preset activity difference, it means that the current predicted activity output by the target catalytic activity model is no longer accurate. Therefore, a model distortion warning can be automatically issued to remind the DCS operator to check the imported material status, operating temperature, measuring instruments, etc., so that the activity influencing parameters of the input model are more accurate, thereby improving the accuracy of the target catalytic activity model output, and facilitating the optimization training of the target catalytic activity model again.

[0109] The technical solution of the present disclosure will be further described in detail below with reference to the embodiments:

[0110] like Figure 2 As shown, the present disclosure provides an online closed-loop control method for an intelligent control strategy and applied to the production and operation of an actual device, which mainly includes a model layer, an APC layer and a bottom loop control layer. The model layer belongs to the upper layer, and the optimal operating parameters (T1-T5) are obtained by solving the objective function through a deep learning model (ESN network) and combining the catalyst state and real-time operating parameters, and the operating parameter setting values ​​are transmitted to the middle APC layer through the OPC protocol; the APC transmits the set MV value (operating parameter setting value) to the bottom layer through the controller to make the controlled variable track the setting value, so as to make the process run in the optimal state as much as possible.

[0111] The technical solution of the present disclosure will be further described below in conjunction with other embodiments:

[0112] First, the laboratory measured the outlet conversion rate of the catalyst at different temperatures and obtained the reaction A of 4.5×10 4 mol / g·min·kPa and K is 69.3KJ / mol. For this case, the air velocity is maintained at 0.02m / s to keep it the same as the industrial device and eliminate the influence of external diffusion. The temperature range includes the initial and later use temperature range of the catalyst 380-430.0℃. Because the actual production device involves 4 beds, 8 multi-point thermocouples are set in the radial direction, each bed contains 5 temperature measurement points (numbered 1, 2, 3, 4, 5), and the entire reactor involves a total of 40 temperature monitoring points. The schematic diagram of the device production is attached. Figure 3 shown.

[0113] At the same time, the real-time data also includes 50 variables, including fresh feed inlet and outlet flow / composition, inlet and outlet pressure, circulating gas flow / composition, oxygen flow, inlet and outlet temperature, etc. Figure 4 shown.

[0114] Because the overall system is large, in order to eliminate the influence of system lag, the response time of the system is determined to be 5 minutes based on the device step test. Therefore, the time series of relevant operating data is processed to reflect the influence of real parameters on the operating results. The principal component analysis method is used to reduce the dimensionality of the above 50 variables. According to the PCA analysis results, 18-dimensional variables can contribute more than 95%. 18 variables are determined to reduce the input, model training and real-time online response time of subsequent models. After processing, the main variables are the temperatures of 1-4 bed layers, specifically the 3 and 4 positions of the first bed layer; the 1 and 2 positions of the second bed layer; the 1 and 4 positions of the third bed layer; the 4 and 5 temperature positions of the fourth bed layer, and the relevant material in and out state parameters, a total of 18 variables, forming a data set Sp = {S1, S2, ..., Sm} (m = 19) containing the operating time. The PCA analysis results of historical data are as follows Figure 5 shown.

[0115] The above variables are used as the input of the ESN network, with 18 variables in the input layer and 2 variables in the output layer; the intermediate reserve layer N is set to 60. The program language is Python. The data division principle selected for model training is random division, with the training set accounting for 85-95% and the test set accounting for 5-15%. The model training effect is comprehensively judged by MAE (mean absolute error), MSE (mean square error), and RMSE (root mean square error). The training results of this embodiment are: test set RMSE = 0.98, MAE = 0.25, which meets the modeling requirement of MAE < 0.5. The model is reliable and the model is saved. Then call the optimization program to calculate the optimal yield of the optimization variable within the constraint interval and the variable operation suggestions through the optimization algorithm. The temperature optimization suggestion adjustment during operation is as follows: Figure 6 According to the decreasing trend of catalyst activity after adjustment, it is estimated that the catalyst life will be extended by 100 days, accounting for 1 / 5 of the total life, with a significant effect.

[0116] The operation suggestions of the output items are used as the input of the APC control system, that is, the temperature target value, and the APC control system is used to achieve stable and automatic adjustment of the target optimal value.

[0117] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0118] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0119] The catalyst activity prediction device according to an embodiment of the present disclosure includes:

[0120] A first acquisition module, used to acquire the historical reaction rate of the reactant catalyzed by the catalyst;

[0121] A calculation module, used to calculate the historical real activity of the catalyst according to the historical reaction rate and a preset mechanism model;

[0122] A training module, used to train a preset catalytic activity model using the historical real activity of the catalyst and the historical activity influencing parameters of the catalyst to obtain a target catalytic activity model;

[0123] The second acquisition module is used to input the current activity influencing parameters of the catalyst into the target catalytic activity model to obtain the current predicted activity of the catalyst.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0125] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium storing computer instructions.

[0126] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0127] The device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0128] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0129] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0132] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0135] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0137] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for predicting catalyst activity, characterized in that: include: Obtaining a historical reaction rate of a reactant catalyzed by the catalyst; Calculating the historical real activity of the catalyst according to the historical reaction rate and the preset mechanism model; Using the historical real activity of the catalyst and the historical activity influencing parameters of the catalyst, a preset catalytic activity model is trained to obtain a target catalytic activity model; Inputting the current activity influencing parameters of the catalyst into the target catalytic activity model to obtain the current predicted activity of the catalyst; The obtaining of the historical reaction rate of the reactant catalyzed by the catalyst comprises: Calculating the historical reaction rate according to the historical reactant concentration at the inlet position and the historical product concentration at the outlet position of the catalyst reactor where the catalyst is located; The calculating the historical real activity of the catalyst according to the historical reaction rate and the preset mechanism model comprises: The historical true activity of the catalyst is calculated based on the historical reaction rate, the historical concentration of the reactant, the historical reaction temperature, the reaction pre-exponential factor A of the catalyst, the activation energy E and the preset mechanism model.

2. The method according to claim 1, characterized in that The reaction pre-exponential factor A and the activation energy E are calculated according to the reactant concentration and product concentration of the catalyst reactor where the catalyst is located at different test temperatures.

3. The method according to claim 1, characterized in that: The method of training a preset catalytic activity model by using the historical real activity of the catalyst and the historical activity influencing parameter of the catalyst to obtain a target catalytic activity model includes: Inputting the historical activity influencing parameters of the catalyst into the preset catalytic activity model to obtain the historical predicted activity of the catalyst; According to the historical real activity and the historical predicted activity of the catalyst, it is judged whether the preset catalytic activity model has been trained to obtain the target catalytic activity model.

4. The method according to claim 1, characterized in that: The method further comprises: After obtaining the current predicted activity of the target catalytic activity model, the current activity influencing parameters are optimized using an optimization algorithm and the current predicted activity, under the condition that the reactant catalyzed by the catalyst can obtain an optimal conversion rate and the optimal conversion rate remains unchanged, so as to determine the optimal activity influencing parameters when the current predicted activity output by the target catalytic activity model reaches the best; Determining the optimal temperature rise curve corresponding to the catalyst according to the optimal activity influencing parameter; The catalytic temperature of the catalyst is controlled according to the optimal temperature rise curve.

5. The method according to claim 1, characterized in that The method further comprises: determining a deactivation rate of the catalyst based on a current predicted activity of the catalyst and a historical predicted activity output by the target catalytic activity model; If the deactivation rate of the catalyst is higher than a preset deactivation threshold, a deactivation warning is issued.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Inputting the current activity influencing parameters of the catalyst into the preset mechanism model to calculate the current real activity of the catalyst; If the activity difference between the current actual activity and the current predicted activity is greater than a preset activity difference, a model distortion warning is issued for the target catalytic activity model.

7. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images