Method and device for predicting melt index in polyformaldehyde production, equipment and medium

Abstract

The invention relates to a method and a device for predicting a melt index in polyformaldehyde production, equipment and a medium, and relates to the field of polyformaldehyde production, and the method comprises the following steps: generating different time delay information by using a wolf pack algorithm; performing modeling training on the process data with the obtained time delay information through a support vector regression model to obtain root-mean-square errors generated by training data corresponding to different time delay information; optimizing the time delay information by taking the root-mean-square error as an evaluation criterion and by means of a wolf pack algorithm to obtain optimal time delay information; and establishing a soft measurement model by using the obtained optimal time delay information and process data through a radial basis function neural network, and predicting according to the soft measurement model to obtain an estimated melt index. According to the method provided by the invention, the optimal time lag information in polyformaldehyde production is obtained based on the combination of the wolf pack algorithm and the support vector regression, and then the prediction model is established by the time lag information and the production data through the radial basis function neural network, so that efficient and accurate prediction of the melt index is realized, and efficient production of polyformaldehyde is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of polyoxymethylene production, and in particular to a method and device, equipment and medium for predicting a melt index in polyoxymethylene production, and in particular to a method and device, equipment and medium for predicting a melt index with time lag estimation for a polyoxymethylene process. Background Art

[0002] At present, polyoxymethylene is a thermoplastic, highly crystalline polymer with a regular molecular structure. Due to its excellent mechanical and electrical properties, it is widely used in the machinery industry and electronic and electrical industries.

[0003] Melt index is an important indicator for monitoring product quality during the production process of polyoxymethylene, but it is difficult to achieve real-time online measurement through equipment. It is often obtained through intermittent sampling and laboratory testing. This method has a long time interval and untimely feedback. In the case of unstable process, not only can the product quality not be guaranteed, but a large number of substandard products may even be produced, causing waste.

[0004] For example, CN118408911A discloses a method for determining the melt index of polyformaldehyde powder using a near-infrared spectrometer, comprising collecting a wide range of polyformaldehyde powder samples from a process production line, performing melt indexer analysis, and determining the melt index value of the polyformaldehyde powder; scanning different polyformaldehyde powder samples using a near-infrared spectrometer and collecting spectra; analyzing the spectra by analogy and establishing an analysis data model; using the data model to analyze the polyformaldehyde powder samples analyzed by the melt indexer, determining the analysis error with the melt indexer, optimizing the model, and improving the accuracy of the model.

[0005] Soft sensing technology can effectively solve this problem, but the polymerization process of formaldehyde is a process with strong nonlinearity, large time lag and complex dynamics. It is difficult to achieve practical results by simply establishing a prediction model, so the time lag process must be taken into account. The search for time lag is often estimated by the correlation coefficient method. This method is effective for processes with weaker nonlinearity, but it is slightly mediocre for processes such as formaldehyde polymerization that have strong nonlinearity and complex dynamics.

[0006] In summary, there is currently a lack of a melt index prediction method that takes time lag into account in the polyoxymethylene production process, which is not conducive to the efficient production of polyoxymethylene. Summary of the invention

[0007] In view of the problems existing in the prior art, the purpose of the present invention is to provide a method and device, equipment and medium for predicting the melt index in the production of polyoxymethylene, so as to realize the prediction of the melt index taking into account the time lag in the production process of polyoxymethylene and improve the production efficiency of polyoxymethylene.

[0008] To achieve this object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a method for predicting the melt index in polyoxymethylene production, the prediction method comprising:

[0010] S1, using wolf pack algorithm to generate different time delay information;

[0011] S2, modeling and training the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information;

[0012] S3, using the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information;

[0013] S4. A soft measurement model is established with the aid of a radial basis function neural network using the obtained optimal time-delay information and process data, and an estimated melting index is obtained based on the prediction of the soft measurement model.

[0014] The prediction method provided by the present invention performs preliminary soft measurement modeling of the formaldehyde polymerization process based on a method combining a wolf pack algorithm with support vector regression with the goal of estimating time lag information, combines the obtained time lag information with production data, and establishes a soft measurement model through a radial basis function neural network, thereby achieving efficient and accurate prediction of the melt index, which is beneficial to the efficient production of polyoxymethylene.

[0015] As a preferred technical solution of the present invention, the generation of different time delay information using the wolf pack algorithm includes: randomly initializing the time delay parameters in a uniformly distributed manner to generate the time delay information, and determining the maximum evolutionary generation and the maximum allowable error of the model.

[0016] As a preferred technical solution of the present invention, the walking step length Step of the roaming wolf in the wolf pack algorithm is as follows:

[0017] Step=rand·||x i -x lead ||2

[0018] In the formula, rand is a random number between [0,1], x i Indicates the current location of the wolf, x lead Indicates the position of the alpha wolf.

[0019] As a preferred technical solution of the present invention, the regression function of the support vector regression model is as follows:

[0020]

[0021] In the formula, x is the sample data, ω is the normal vector of the hyperplane, b is the deviation, L is the number of sample training, and α i is the optimal solution to the dual problem, b * is the optimal deviation, x i is the feature vector of the i-th training sample, x j is the feature vector to be predicted currently, σ>0.

[0022] As a preferred technical solution of the present invention, the modeling training of the process data with the obtained time delay information through the support vector regression model includes: establishing a measurement model based on the support vector regression model using randomly initialized delay parameters, and calculating the estimated value and modeling error of the model.

[0023] As a preferred technical solution of the present invention, the optimization includes: performing optimization based on a wolf pack algorithm, generating a new population of time delay τ, selecting process control parameter data and product indicator result data according to the time delay, and then re-establishing the soft measurement model under the new time domain estimation value, calculating the model estimation value, and when the root mean square error is less than 0.05% or the number of iterations is greater than 200 times, the optimization ends and the optimal time delay information is output.

[0024] As a preferred technical solution of the present invention, the process data includes the amount of initiator, the amount of methylal, the first stage reaction temperature, the second stage reaction temperature and the third stage reaction temperature.

[0025] Preferably, the parameters that need to be determined in the radial basis neural network include the number of hidden layer nodes m, the center of the basis function c, the width of the radial basis function around the center point, and the weight w of the output unit.

[0026] Preferably, the number m of hidden layer nodes in the radial basis neural network is 1 / 3-2 / 3 of the total number of samples.

[0027] In a second aspect, the present invention provides a device for predicting the melt index in polyoxymethylene production, the prediction device comprising:

[0028] A time-delay information acquisition module is used to generate different time-delay information using a wolf pack algorithm;

[0029] A root mean square error acquisition module is used to perform modeling training on the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information;

[0030] The optimal time-delay information acquisition module is used to use the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information;

[0031] The melt index prediction module is used to establish a soft measurement model with the aid of a radial basis function neural network using the obtained optimal time lag information and process data, and to predict the estimated melt index based on the soft measurement model.

[0032] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0033] at least one processor; and a memory communicatively coupled to the at least one processor;

[0034] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the melt index in the production of polyoxymethylene described in the first aspect.

[0035] In a fourth aspect, the present invention provides a computer storage medium having computer executable instructions stored therein, and when the computer executable instructions are executed by a processor, the method for predicting the melt index in the production of polyoxymethylene described in the first aspect is implemented.

[0036] Compared with the prior art solutions, the present invention has the following beneficial effects:

[0037] The prediction method provided by the present invention establishes a preliminary soft measurement model by using a support vector regression model to better capture complex dynamic relationships and improve the accuracy of time delay estimation, and estimates the time lag information in combination with a wolf pack algorithm. Finally, a more accurate radial basis function neural network is used to establish a prediction model, which has higher accuracy and adaptability than the existing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention provides a flowchart of a method for predicting the melt index in polyoxymethylene production according to an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of a device for predicting the melt index in polyoxymethylene production provided by an embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of an electronic device provided by an embodiment of the present invention;

[0041] Figure 4 This is a diagram of the prediction results obtained in Example 1 of the present invention.

[0042] In the figure: 10 - electronic device, 11 - processor, 12 - ROM, 13 - RAM, 14 - bus, 15 - I / O interface, 16 - input unit, 17 - output unit, 18 - storage unit, 19 - communication unit.

[0043] The present invention is further described in detail below. However, the following examples are only simplified examples of the present invention and do not represent or limit the scope of protection of the present invention. The scope of protection of the present invention shall be subject to the claims. DETAILED DESCRIPTION

[0044] To better illustrate the present invention and facilitate understanding of the technical solution of the present invention, typical but non-limiting embodiments of the present invention are as follows:

[0045] This embodiment provides a method for predicting the melt index in polyoxymethylene production, and the flow chart is as follows: Figure 1 As shown, the prediction method includes:

[0046] S1, using wolf pack algorithm to generate different time delay information;

[0047] S2, modeling and training the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information;

[0048] S3, using the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information;

[0049] S4. A soft measurement model is established with the aid of a radial basis function neural network using the obtained optimal time-delay information and process data, and an estimated melting index is obtained based on the prediction of the soft measurement model.

[0050] The method of generating different time-delay information by using the wolf pack algorithm includes: randomly initializing the time-delay parameters in a uniformly distributed manner to generate the time-delay information, and determining the maximum evolutionary generation and the maximum allowed error of the model.

[0051] Among them, the walking step length Step of the roaming wolf in the wolf pack algorithm is as follows:

[0052] Step=rand·||x i -x lead ||2

[0053] In the formula, rand is a random number between [0,1], x i Indicates the current location of the wolf, x lead Indicates the position of the alpha wolf.

[0054] Exemplarily, in the wolf pack algorithm, the wolf pack is actually an N×D Euclidean space, where N is the total number of artificial wolves and D is the number of variables to be optimized. Each generation of wolf pack is an N×D space, where D corresponds to a vector composed of time-delay information between different operating variables and output results, and N is the N above vectors. After each generation of wolf pack is trained by the support vector regression model, N errors will be returned. The vector corresponding to the smallest error is more likely to be retained to the next generation, and the internal data of the vectors corresponding to other errors will be close to the vector corresponding to the smallest error.

[0055] The regression function of the support vector regression model is as follows:

[0056]

[0057] In the formula, x is the sample data, ω is the normal vector of the hyperplane, b is the deviation, L is the number of sample training, and α i is the optimal solution to the dual problem, b * is the optimal deviation, x i is the feature vector of the i-th training sample, x j is the feature vector to be predicted currently, σ>0.

[0058] The method of training the process data with the obtained time delay information through a support vector regression model includes: establishing a measurement model based on the support vector regression model by using randomly initialized time delay parameters, and calculating the estimated value and modeling error of the model.

[0059] Exemplarily, the operating variables and results in the actual production data are matched one-to-one through time lag information (for example, after the feed rate changes, the estimated result will change after 5 minutes (time lag information), then the feed rate data when the feed rate changes and the result data after 5 minutes are combined into an input / training data and submitted to the support vector regression model for training), to obtain a training set, and the training set is submitted to the support vector regression model for training to obtain the root mean square error generated by the training data corresponding to different time lag information.

[0060] Among them, the optimization includes: performing optimization based on the wolf pack algorithm, generating a new population of time delay τ, selecting process control parameter data and product indicator result data according to the time delay, and then re-establishing the soft measurement model under the new time domain estimation value, calculating the model estimation value, when the root mean square error is less than 0.05% or the number of iterations is greater than 200 times, the optimization ends and the optimal time delay information is output.

[0061] The process data include the amount of initiator, the amount of methylal, the first stage reaction temperature, the second stage reaction temperature and the third stage reaction temperature.

[0062] The parameters that need to be determined in the radial basis neural network include the number of hidden layer nodes m, the center of the basis function c, the width of the radial basis function around the center point, and the weight w of the output unit.

[0063] The number of hidden layer nodes m in the radial basis neural network is 1 / 3-2 / 3 of the total number of samples.

[0064] Furthermore, this embodiment provides a device for predicting the melt index in polyoxymethylene production, such as Figure 2 As shown, the prediction device comprises:

[0065] A time-delay information acquisition module is used to generate different time-delay information using a wolf pack algorithm;

[0066] A root mean square error acquisition module is used to perform modeling training on the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information;

[0067] The optimal time-delay information acquisition module is used to use the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information;

[0068] The melt index prediction module is used to establish a soft measurement model with the aid of a radial basis function neural network using the obtained optimal time lag information and process data, and to predict the estimated melt index based on the soft measurement model.

[0069] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0070] Further, the present invention provides an electronic device, which 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 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0071] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0072] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0073] The processor 11 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting a melt index in polyoxymethylene production.

[0074] In some embodiments, the method for predicting the melt index in the production of polyoxymethylene can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting the melt index in the production of polyoxymethylene described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for predicting the melt index in the production of polyoxymethylene in any other appropriate manner (for example, by means of firmware).

[0075] 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.

[0076] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program 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.

[0077] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0078] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0079] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend 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), a blockchain network, and the Internet.

[0080] 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 client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0081] The server provided in this embodiment includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for predicting the melt index in the production of polyoxymethylene is implemented.

[0082] Unless otherwise specifically stated, terms such as processing, computing, calculating, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate and convert data represented as physical (e.g., electronic) quantities within registers or memories of a processing system into other data similarly represented as physical quantities within memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0083] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments of the present invention may all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described around their functions. Whether such functions are implemented as hardware or software depends on the specific application and the design constraints imposed on the entire system. A skilled person may implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0084] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0085] For software implementation, the techniques described in the present invention can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in the present application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0086] Further, in order to illustrate the prediction effect that can be achieved by the method for predicting the melt index in the production of polyoxymethylene provided by the present invention, the following actual example is used for exemplary description, as follows:

[0087] Example 1

[0088] This example provides a prediction of the melt index of a copolymerization oxymethylene production process in a certain factory, as follows:

[0089] The initiator dosage, methylal dosage, first stage reaction temperature, second stage reaction temperature and third stage reaction temperature were selected as input data, and the melt index was selected as output data. The input data was collected every 30 seconds, and the output data was sampled and tested every four hours by the process personnel. A total of 50,266 sets of input data and 768 sets of output data were obtained. According to the suggestions of the process personnel, the delay range was set to [0,100]min.

[0090] After training, the delay information is [90.0, 3.9, 2.3, 66.9, 68.2] min. The original data and the predicted results are shown in Figure 4 As shown in the figure, T is time, MFR is melt index, Test is actual experimental data, and forecast is simulated prediction data. It can be seen from the figure that the melt index obtained according to the prediction process of the present invention is highly similar to the actual data, that is, the prediction method of the present invention can achieve accurate prediction of the melt index taking into account the time lag, which is beneficial to guiding the production of polyoxymethylene.

[0091] The preferred embodiments of the present invention are described in detail above. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, a variety of simple modifications can be made to the technical solution of the present invention, and these simple modifications all belong to the protection scope of the present invention.

[0092] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0093] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for predicting melt index in polyoxymethylene production, characterized in that: The prediction method comprises: S1, using wolf pack algorithm to generate different time delay information; S2, modeling and training the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information; S3, using the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information; S4. A soft measurement model is established with the aid of a radial basis function neural network using the obtained optimal time-delay information and process data, and an estimated melting index is obtained based on the prediction of the soft measurement model.

2. The prediction method according to claim 1, characterized in that: The method of generating different time delay information by using the wolf pack algorithm includes: randomly initializing the time delay parameters in a uniformly distributed manner to generate the time delay information, and determining the maximum evolutionary generation and the maximum allowed error of the model.

3. The prediction method according to claim 1 or 2, characterized in that: The walking step length Step of the roaming wolf in the wolf pack algorithm is as follows: Step=rand·||x i -x lead ||2 In the formula, rand is a random number between [0,1], x i Indicates the current location of the wolf, x lead Indicates the position of the alpha wolf.

4. The prediction method according to any one of claims 1 to 3, characterized in that: The regression function of the support vector regression model is as follows: In the formula, x is the sample data, ω is the normal vector of the hyperplane, b is the deviation, L is the number of sample training, and α i is the optimal solution to the dual problem, b * is the optimal deviation, x i is the feature vector of the i-th training sample, x j is the feature vector to be predicted currently, σ>0.

5. The prediction method according to any one of claims 1 to 4, characterized in that: The method of training the process data with the obtained time delay information through the support vector regression model includes: establishing a measurement model based on the support vector regression model by using randomly initialized time delay parameters, and calculating the estimated value and modeling error of the model.

6. The prediction method according to any one of claims 1 to 5, characterized in that: The optimization includes: performing optimization based on a wolf pack algorithm to generate a new population of time delay τ, selecting process control parameter data and product indicator result data according to the time delay, and then re-establishing a soft measurement model under a new time domain estimation value, calculating the model estimation value, and when the root mean square error is less than 0.05% or the number of iterations is greater than 200 times, the optimization ends and the optimal time delay information is output.

7. The prediction method according to any one of claims 1 to 6, characterized in that: The process data include the amount of initiator, the amount of methylal, the first stage reaction temperature, the second stage reaction temperature and the third stage reaction temperature; Preferably, the parameters that need to be determined in the radial basis neural network include the number of hidden layer nodes m, the center of the basis function c, the width of the radial basis function around the center point, and the weight w of the output unit; Preferably, the number m of hidden layer nodes in the radial basis neural network is 1 / 3-2 / 3 of the total number of samples.

8. A device for predicting melt index in polyoxymethylene production, characterized in that: The prediction device comprises: A time-delay information acquisition module is used to generate different time-delay information using a wolf pack algorithm; A root mean square error acquisition module is used to perform modeling training on the process data with the obtained time lag information through a support vector regression model to obtain the root mean square error generated by the training data corresponding to different time lag information; The optimal time-delay information acquisition module is used to use the root mean square error generated by the training data corresponding to different time-delay information as an evaluation standard to optimize the time-delay information with the help of the wolf pack algorithm to obtain the optimal time-delay information; The melt index prediction module is used to establish a soft measurement model with the aid of a radial basis function neural network using the obtained optimal time lag information and process data, and to predict the estimated melt index based on the soft measurement model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the melt index in the production of polyoxymethylene according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the method for predicting the melt index in polyoxymethylene production according to any one of claims 1 to 7 is implemented.

Images