A parameter correction method and device, electronic equipment and storage medium

Abstract

The application discloses a parameter correction method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining the fitness value of any generation in the iteration process of a preset optimization algorithm, and a pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient comprises a positive correction coefficient and a negative correction coefficient; further, determining a target correction coefficient based on the fitness value in the positive correction coefficient and the negative correction coefficient, correcting the fitness value based on the target correction coefficient to determine a fitness correction value, updating the preset optimization algorithm based on each fitness correction value, improving the adaptability of the preset optimization algorithm, thereby improving the optimization accuracy of the preset optimization algorithm; further, performing parameter optimization on the carbon load model based on the optimization algorithm with high optimization accuracy, improving the accuracy of the model parameters, thereby making the error of the target carbon load value estimated by the carbon load model smaller, and improving the estimation accuracy of the carbon load value.

Description

Technical Field

[0001] This invention relates to the field of engine technology, and in particular to a parameter correction method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, adding a Diesel Particulate Filter (DPF) is the simplest and most effective way for engines to meet particulate matter emission standards. As the DPF collects more and more particles, the back pressure of the aftertreatment system increases, affecting engine performance. Diesel fuel is injected into the aftertreatment system, and the oxidation process of the diesel oxidation catalyst (DOC) raises the inlet temperature of the DPF. This high temperature burns off the carbon particles in the DPF; this process is called DPF regeneration. The key trigger for DPF regeneration is the carbon loading of the DPF, that is, the mass of carbon particles captured inside the DPF.

[0003] Due to the complexity of actual engine operating conditions, it is difficult to accurately determine DPF regeneration based on the carbon load model. Therefore, it is necessary to introduce a suitable optimization algorithm to improve the estimated value of the carbon load model in order to improve the accuracy of DPF regeneration control.

[0004] In related technologies, the inventors discovered that during the optimization iteration process of the optimization algorithm, the importance or priority of multiple objectives (model parameters) are equal, which is inconsistent with actual engineering and leads to a large error in the estimated carbon loading value. Summary of the Invention

[0005] This invention provides a parameter correction method, apparatus, electronic device, and storage medium to improve the accuracy of carbon loading estimation and solve the problem of large errors in carbon loading estimation.

[0006] According to one aspect of the present invention, a parameter correction method is provided, comprising:

[0007] Obtain the fitness value of any generation during the iteration of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient;

[0008] Based on the fitness value, a target correction coefficient is determined from the positive and negative correction coefficients, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value;

[0009] The preset optimization algorithm is updated based on each fitness correction value, and the carbon loading model is optimized by parameters based on the updated optimization algorithm. The target carbon loading value is determined based on the carbon loading model after parameter optimization.

[0010] According to another aspect of the present invention, a parameter correction device is provided, comprising:

[0011] The data acquisition module is used to acquire the fitness value of any generation during the iteration of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient.

[0012] A data correction module is used to determine a target correction coefficient based on the fitness value among the positive correction coefficient and the negative correction coefficient, and to correct the fitness value based on the target correction coefficient to obtain a fitness correction value.

[0013] The parameter optimization module is used to update the preset optimization algorithm based on each fitness correction value, optimize the parameters of the carbon loading model based on the updated optimization algorithm, and determine the target carbon loading value based on the carbon loading model after parameter optimization.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the parameter correction method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the parameter correction method described in any embodiment of the present invention.

[0019] The technical solution of this invention obtains the fitness value of any generation in the iteration process of a preset optimization algorithm, as well as pre-calibrated fitness correction coefficients, wherein the fitness correction coefficients include positive correction coefficients and negative correction coefficients. Further, a target correction coefficient is determined from the positive and negative correction coefficients based on the fitness value, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value. The preset optimization algorithm is updated based on each fitness correction value, thereby improving the fitness of the preset optimization algorithm and thus improving its optimization accuracy. Furthermore, the carbon loading model is optimized based on the optimization algorithm with high optimization accuracy, improving the accuracy of the model parameters, thereby reducing the error in the target carbon loading value estimated by the carbon loading model and improving the estimation accuracy of the carbon loading value.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a parameter correction method provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a parameter correction method provided in Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of a priority correction algorithm applicable to Embodiment 2 of the present invention;

[0025] Figure 4 This is a schematic diagram of a parameter correction device according to Embodiment 3 of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the parameter correction method of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "target," "current," "historical," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 The flowchart of a parameter correction method provided in Embodiment 1 of the present invention is applicable to the case of parameter optimization for an engine carbon load model. This method can be executed by a parameter correction device, which can be implemented in hardware and / or software and can be configured in a computer terminal. Figure 1 As shown, the method includes:

[0031] S110. Obtain the fitness value of any generation in the iteration process of the preset optimization algorithm, and the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient.

[0032] In this embodiment, a preset optimization algorithm can be used to find the optimal parameters of the system or model, bringing the system or model to its best state. The model can be a multi-input multi-objective model. During the iteration process, the preset optimization algorithm can obtain the fitness value determined by the fitness function. The fitness correction coefficient refers to a pre-calibrated priority correction coefficient, which may include, but is not limited to, positive and negative correction coefficients. Positive correction coefficients can be used to decrease the current fitness value, while negative correction coefficients can be used to increase the current fitness value, making the priority of the current fitness value closer to the actual working condition. It can be understood that the fitness value is a measure of an individual's advantage in the population, used to distinguish the quality of model parameters; a larger fitness value indicates better model parameters.

[0033] Specifically, the electronic device can obtain the fitness value of any generation in the iteration process of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, from the preset storage location or path.

[0034] S120. Based on the fitness value, determine the target correction coefficient among the positive correction coefficient and the negative correction coefficient, and correct the fitness value based on the target correction coefficient to obtain the fitness correction value.

[0035] In this embodiment, a positive or negative correction coefficient can be selected based on the fitness value. The fitness value is then corrected based on the selected positive or negative correction coefficient to obtain a fitness correction value. This improves the adaptability of the preset optimization algorithm and thus improves the optimization accuracy of the preset optimization algorithm.

[0036] Based on the above embodiments, the step of correcting the fitness value based on the target correction coefficient to obtain a fitness correction value includes: determining the absolute value of the fitness difference based on the fitness value; and multiplying the target correction coefficient by the absolute value of the fitness difference to obtain the fitness correction value.

[0037] Specifically, the absolute value of the difference between the fitness value and the target value can be multiplied by the target correction coefficient to obtain the fitness correction value, where the target value can be the fitness value corresponding to the weighed carbon loading value.

[0038] S130. Update the preset optimization algorithm based on each fitness correction value, and perform parameter optimization on the carbon loading model based on the updated optimization algorithm, and determine the target carbon loading value based on the carbon loading model after parameter optimization.

[0039] In this embodiment, the carbon loading model is optimized based on an optimization algorithm with high optimization accuracy, which improves the accuracy of the model parameters. As a result, the target carbon loading value estimated by the carbon loading model has a smaller error and the estimation accuracy of the carbon loading value is improved.

[0040] For example, the model parameters of the carbon loading model may include, but are not limited to, the transient carbon loading correction map, the passive regeneration map, and the passive regeneration correction curve. In this embodiment, the carbon loading model parameters are optimized using an optimization algorithm to obtain the optimal transient carbon loading correction map, the passive regeneration map, and the passive regeneration correction curve. Based on the optimal transient carbon loading correction map, the passive regeneration map, and the passive regeneration correction curve, the estimated carbon loading value is corrected to obtain an estimated carbon loading value that is close to the true carbon loading value.

[0041] Based on the above embodiments, the preset optimization algorithm includes an adaptive evaluation function and a selection probability function, wherein the adaptive evaluation function and the selection probability function are respectively:

[0042]

[0043] Among them, z i(x) represents the adaptive evaluation function, and x represents the carbon loading model parameters. Let f represent the maximum and minimum values ​​of the k-th fitness function, respectively. k (x) represents the k-th fitness function; p i Let represent the selection probability function, i represent the target dimension, q represent the number of fitness functions, and r represent the number of parameters in the carbon loading model, i.e., the population size.

[0044] For example, the optimization algorithm can be a genetic algorithm. In the iterative process of the genetic algorithm, the maximum and minimum values ​​of the fitness function can be calculated first:

[0045]

[0046] Among them, z + z represents the vector of maximum values ​​of the fitness function. - This represents the minimum value vector of the fitness function, where the fitness function can be a carbon loading model. Let q represent the maximum and minimum values ​​of the k-th fitness function, respectively, and let 1, 2, ..., q represent the number of fitness functions.

[0047] Furthermore, the cumulative probability L i for:

[0048]

[0049] Specifically, generate a random number r in the interval [0,1]. i If the cumulative probability of a certain chromosome is L at the end j For the ratio r j If the minimum value is the largest, then the chromosome is retained in the next generation, where the chromosome can be a parameter of the carbon load model.

[0050] For example, the carbon loading model can be globally optimized using the genetic algorithm toolbox built into Matlab software. The specific steps for optimization using the genetic algorithm are as follows: First, encode the carbon loading model parameters into genes to generate an initial population; Second, calculate and correct the individual fitness, and then perform population optimization; Third, determine whether the convergence requirement is met. If yes, execute the fourth step of chromosome decoding to output the optimal carbon loading model parameters and end the global optimization; if not, execute the fifth step of selection, crossover, and mutation in sequence; Sixth, after selection, crossover, and mutation, recalculate the individual fitness and perform population optimization; Seventh, generate the K+1 generation population and return to the third step to determine whether the convergence requirement is met again.

[0051] In some embodiments, the preset optimization algorithm can be applied to products that meet China VI emission standards or are not China IV emission standards and use DPF technology to optimize carbon loading model values, especially to improve the accuracy of carbon loading model values ​​that are close to the regeneration threshold.

[0052] The technical solution of this invention obtains the fitness value of any generation in the iteration process of a preset optimization algorithm, as well as pre-calibrated fitness correction coefficients, wherein the fitness correction coefficients include positive correction coefficients and negative correction coefficients. Further, a target correction coefficient is determined from the positive and negative correction coefficients based on the fitness value, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value. The preset optimization algorithm is updated based on each fitness correction value, thereby improving the fitness of the preset optimization algorithm and thus improving its optimization accuracy. Furthermore, the carbon loading model is optimized based on the optimization algorithm with high optimization accuracy, improving the accuracy of the model parameters, thereby reducing the error in the target carbon loading value estimated by the carbon loading model and improving the estimation accuracy of the carbon loading value.

[0053] Example 2

[0054] Figure 2 This is a flowchart of a parameter correction method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment refines the step of "determining a target correction coefficient based on the fitness value among the positive and negative correction coefficients". Optionally, the fitness value includes an estimated fitness value and a measured fitness value; correspondingly, determining the target correction coefficient based on the fitness value among the positive and negative correction coefficients includes: determining a fitness difference based on the estimated fitness value and the measured fitness value; if the fitness difference does not exceed the average difference, then the negative correction coefficient is determined as the target correction coefficient, and a fitness correction value is determined based on the fitness difference and the target correction coefficient; if the fitness difference exceeds the average difference, then the positive correction coefficient is determined as the target correction coefficient, and a fitness correction value is determined based on the fitness difference and the target correction coefficient.

[0055] like Figure 2 As shown, the method includes:

[0056] S210. Obtain the fitness value of any generation in the iteration process of the preset optimization algorithm, and the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient.

[0057] S220. Determine the fitness difference based on the estimated fitness value and the measured fitness value.

[0058] In this embodiment, the fitness value may include an estimated fitness value and a measured fitness value. The estimated fitness value may be a fitness value determined by a fitness function, and the measured fitness value refers to the target fitness value corresponding to the weighed carbon loading value.

[0059] S230. If the fitness difference does not exceed the average difference, the negative correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient.

[0060] S240. If the fitness difference exceeds the average difference, the positive correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient.

[0061] In this embodiment, the average difference can be the average of a preset number of fitness differences. For example, the estimated fitness value and the measured fitness value are obtained, and the difference between the estimated fitness value and the measured fitness value is taken as the absolute value to obtain the fitness difference. It is understood that any generation in the preset optimization algorithm iteration process may include multiple fitness values, and the average difference between the fitness values ​​corresponding to multiple fitness values ​​can be obtained.

[0062] For example, Figure 3 This is a schematic diagram of a priority correction algorithm applicable to an embodiment of the present invention. During the iteration process of the preset optimization algorithm, the absolute values ​​of the differences between the n estimated fitness values ​​and the measured fitness values ​​in the current generation can be calculated, and the average value is obtained. For the absolute value of the fitness value difference (i.e., the fitness difference), if the fitness difference exceeds the average value, the absolute value of the fitness value difference is multiplied by a positive correction coefficient to obtain the fitness correction value; if the fitness difference does not exceed the average value, the absolute value of the fitness value difference is multiplied by a negative correction coefficient to obtain the fitness correction value. Optionally, the positive correction coefficient ranges from (0,1), and the negative correction coefficient ranges from (1,2). For example, as shown in Table 1:

[0063] Table 1 Recommended Setting of Correction Factors

[0064]

[0065] S250. The fitness value is corrected based on the target correction coefficient to obtain the fitness correction value.

[0066] S260. Update the preset optimization algorithm based on each fitness correction value, and perform parameter optimization on the carbon loading model based on the updated optimization algorithm, and determine the target carbon loading value based on the carbon loading model after parameter optimization.

[0067] In this embodiment, during the optimization iteration process of the preset optimization algorithm (e.g., genetic algorithm), the fitness value of each generation is corrected based on a correction coefficient, which can achieve higher optimization accuracy for high-priority fitness values. This preset optimization algorithm can be applied to automatic carbon loading calibration to improve the accuracy of carbon loading model values ​​close to the regeneration threshold.

[0068] The technical solution of this invention obtains the fitness value of any generation in the iteration process of a preset optimization algorithm, as well as pre-calibrated fitness correction coefficients, wherein the fitness correction coefficients include positive correction coefficients and negative correction coefficients. Further, a fitness difference is determined based on the estimated fitness value and the measured fitness value. If the fitness difference does not exceed the average difference, the negative correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient. If the fitness difference exceeds the average difference, the positive correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient. This achieves the correction of fitness priority, enabling high-priority fitnesss to obtain higher optimization accuracy. Furthermore, the carbon loading model is optimized based on an optimization algorithm with high optimization accuracy, improving the accuracy of the model parameters. This results in a smaller error in the target carbon loading value estimated by the carbon loading model, thus improving the estimation accuracy of the carbon loading value.

[0069] Example 3

[0070] Figure 4 This is a schematic diagram of a parameter correction device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0071] The data acquisition module 310 is used to acquire the fitness value of any generation in the iteration process of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient.

[0072] The data correction module 320 is used to determine a target correction coefficient based on the fitness value among the positive correction coefficient and the negative correction coefficient, and to correct the fitness value based on the target correction coefficient to obtain a fitness correction value;

[0073] The parameter optimization module 330 is used to update the preset optimization algorithm based on each fitness correction value, optimize the parameters of the carbon loading model based on the updated optimization algorithm, and determine the target carbon loading value based on the carbon loading model after parameter optimization.

[0074] The technical solution of this invention obtains the fitness value of any generation in the iteration process of a preset optimization algorithm, as well as pre-calibrated fitness correction coefficients, wherein the fitness correction coefficients include positive correction coefficients and negative correction coefficients. Further, a target correction coefficient is determined from the positive and negative correction coefficients based on the fitness value, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value. The preset optimization algorithm is updated based on each fitness correction value, thereby improving the fitness of the preset optimization algorithm and thus improving its optimization accuracy. Furthermore, the carbon loading model is optimized based on the optimization algorithm with high optimization accuracy, improving the accuracy of the model parameters, thereby reducing the error in the target carbon loading value estimated by the carbon loading model and improving the estimation accuracy of the carbon loading value.

[0075] Optionally, the fitness value includes an estimated fitness value and a measured fitness value.

[0076] Correspondingly, the data correction module 320 includes:

[0077] A fitness difference determination unit is used to determine the fitness difference based on the estimated fitness value and the measured fitness value;

[0078] A negative correction unit is used to determine the negative correction coefficient as the target correction coefficient if the fitness difference does not exceed the average difference value, and to determine the fitness correction value based on the fitness difference and the target correction coefficient.

[0079] A positive correction unit is used to determine the positive correction coefficient as the target correction coefficient if the fitness difference exceeds the average difference, and to determine the fitness correction value based on the fitness difference and the target correction coefficient.

[0080] Optionally, the average difference is the average of a preset number of fitness differences.

[0081] Optionally, the positive correction coefficient has a value range of (0,1), and the negative correction coefficient has a value range of (1,2).

[0082] Optionally, the preset optimization algorithm includes an adaptive evaluation function and a selection probability function, wherein the adaptive evaluation function and the selection probability function are respectively:

[0083]

[0084] Among them, z i (x) represents the adaptive evaluation function, and x represents the carbon loading model parameters. Let f represent the maximum and minimum values ​​of the k-th fitness function, respectively. k (x) represents the k-th fitness function; pi Let i represent the selection probability function, and let i represent the target dimension of 0 degrees.

[0085] Optionally, the data correction module 320 is also used for:

[0086] The absolute value of the fitness difference is determined based on the fitness value;

[0087] The fitness correction value is obtained by multiplying the target correction coefficient by the absolute value of the fitness difference.

[0088] The parameter correction device provided in the embodiments of the present invention can execute the parameter correction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0089] Example 4

[0090] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0091] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0093] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a parameter correction method, which includes:

[0094] Obtain the fitness value of any generation during the iteration of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient;

[0095] Based on the fitness value, a target correction coefficient is determined from the positive and negative correction coefficients, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value;

[0096] The preset optimization algorithm is updated based on each fitness correction value, and the carbon loading model is optimized by parameters based on the updated optimization algorithm. The target carbon loading value is determined based on the carbon loading model after parameter optimization.

[0097] In some embodiments, the parameter correction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the parameter correction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the parameter correction method by any other suitable means (e.g., by means of firmware).

[0098] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0101] To provide interaction with a user, the systems and techniques described herein can 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0103] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A parameter correction method, characterized in that, include: Obtain the fitness value of any generation during the iteration of the preset optimization algorithm, and the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient; Based on the fitness value, a target correction coefficient is determined from the positive and negative correction coefficients, and the fitness value is corrected based on the target correction coefficient to obtain a fitness correction value; The preset optimization algorithm is updated based on each fitness correction value, and the carbon loading model is optimized based on the updated optimization algorithm. The target carbon loading value is determined based on the carbon loading model after parameter optimization. The carbon loading model is used to determine the carbon loading of the particulate trap. The model parameters of the carbon loading model include the carbon loading transient correction Map, the passive regeneration Map, and the passive regeneration correction Curve. The fitness value includes an estimated fitness value and a measured fitness value. The estimated fitness value is determined by a fitness function, and the measured fitness value refers to the target fitness value corresponding to the weighed carbon loading value. Accordingly, the step of determining a target correction coefficient based on the fitness value among the positive and negative correction coefficients, and correcting the fitness value based on the target correction coefficient to obtain a fitness correction value, includes: The fitness difference is determined based on the estimated fitness value and the measured fitness value; If the fitness difference does not exceed the average difference, then the negative correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient. If the fitness difference exceeds the average difference, the positive correction coefficient is determined as the target correction coefficient, and the fitness correction value is determined based on the fitness difference and the target correction coefficient. The preset optimization algorithm includes an adaptive evaluation function and a selection probability function, wherein the selection probability function is: ； in, This represents the adaptive evaluation function. Indicates the parameters of the carbon loading model. This represents the probability function of selection. This indicates the number of parameters in the carbon loading model, where i represents the i-th parameter among the r carbon loading model parameters. The step of correcting the fitness value based on the target correction coefficient to obtain a fitness correction value includes: The absolute value of the fitness difference is determined based on the fitness value; The fitness correction value is obtained by multiplying the target correction coefficient by the absolute value of the fitness difference.

2. The method according to claim 1, characterized in that, The average difference is the average of a preset number of fitness differences.

3. The method according to claim 1, characterized in that, The positive correction coefficient has a value range of (0,1), and the negative correction coefficient has a value range of (1,2).

4. A parameter correction device, characterized in that, include: The data acquisition module is used to acquire the fitness value of any generation during the iteration of the preset optimization algorithm, as well as the pre-calibrated fitness correction coefficient, wherein the fitness correction coefficient includes a positive correction coefficient and a negative correction coefficient. A data correction module is used to determine a target correction coefficient based on the fitness value among the positive correction coefficient and the negative correction coefficient, and to correct the fitness value based on the target correction coefficient to obtain a fitness correction value. The parameter optimization module is used to update the preset optimization algorithm based on each fitness correction value, and to perform parameter optimization on the carbon loading model based on the updated optimization algorithm, and to determine the target carbon loading value based on the parameter-optimized carbon loading model; wherein, the carbon loading model is used to determine the carbon loading of the particulate trap; the model parameters of the carbon loading model include a transient correction map for carbon loading and a passive regeneration map and a passive regeneration correction curve; The fitness value includes an estimated fitness value and a measured fitness value. The estimated fitness value is determined by a fitness function, and the measured fitness value refers to the target fitness value corresponding to the weighed carbon loading value. Accordingly, the data correction module includes: A fitness difference determination unit is used to determine the fitness difference based on the estimated fitness value and the measured fitness value; A negative correction unit is used to determine the negative correction coefficient as the target correction coefficient if the fitness difference does not exceed the average difference value, and to determine the fitness correction value based on the fitness difference and the target correction coefficient. A positive correction unit is used to determine the positive correction coefficient as the target correction coefficient if the fitness difference exceeds the average difference, and to determine the fitness correction value based on the fitness difference and the target correction coefficient. The preset optimization algorithm includes an adaptive evaluation function and a selection probability function, wherein the selection probability function is: ； in, This represents the adaptive evaluation function. Indicates the parameters of the carbon loading model. This represents the probability function of selection. This indicates the number of parameters in the carbon loading model, where i represents the i-th parameter among the r carbon loading model parameters. The data correction module is further configured to: The absolute value of the fitness difference is determined based on the fitness value; The fitness correction value is obtained by multiplying the target correction coefficient by the absolute value of the fitness difference.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the parameter correction method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the parameter correction method according to any one of claims 1-3.

Images