CN114991923B

CN114991923B - Particle catcher differential pressure determination method, device, equipment and medium

Info

Publication number: CN114991923B
Application number: CN202210924433.0A
Authority: CN
Inventors: 王秀雷; 文武红
Original assignee: Weichai Power Co Ltd
Current assignee: Weichai Power Co Ltd
Priority date: 2022-08-03
Filing date: 2022-08-03
Publication date: 2022-11-29
Anticipated expiration: 2042-08-03
Also published as: CN114991923A

Abstract

The invention discloses a method, a device, equipment and a medium for determining differential pressure of a particle catcher. According to the method, a current differential pressure prediction parameter and a historical differential pressure prediction parameter of a target particle trap are obtained, the current differential pressure of the target particle trap is predicted according to a pre-trained differential pressure prediction model, the front-end air inlet temperature, the rear-end exhaust temperature, the current transient exhaust gas volume flow and the carbon loading capacity are used as parameters for predicting the differential pressure, differential pressure detection is achieved, the problem of signal interference in a fault mode can be solved, the problem that differential pressure signals measured by a differential pressure sensor are unreliable due to mechanical faults is solved, the estimation accuracy of the differential pressure is improved, the differential pressure at the current moment is predicted through the historical differential pressure prediction parameter, the predicted differential pressure can accord with a change rule, and the prediction accuracy of the differential pressure of the particle trap is further improved.

Description

Particle catcher differential pressure determination method, device, equipment and medium

Technical Field

The invention relates to the technical field of engines, in particular to a method, a device, equipment and a medium for determining differential pressure of a particle catcher.

Background

Currently, a DPF (Particulate Filter) usually uses a differential pressure sensor to measure a differential pressure signal between a front end and a rear end of the DPF, and the differential pressure signal is mainly used for estimating carbon loading of the DPF, diagnosing faults and the like.

However, when the engine has mechanical faults, such as burnout, cracks, leakage, blockage, etc., the signal measured by the differential pressure sensor is unreliable, and there is no corresponding fault diagnosis algorithm to identify, which in turn affects the effectiveness of DPF control and diagnosis.

In the process of implementing the invention, at least the following technical problems are found in the prior art: the differential pressure signal measured by the differential pressure sensor is unreliable due to mechanical failure, thereby affecting the control and diagnosis effect of the particle catcher.

Disclosure of Invention

The invention provides a method, a device, equipment and a medium for determining differential pressure of a particle catcher, and aims to solve the technical problem that a differential pressure signal measured by a differential pressure sensor is unreliable.

According to an aspect of the present invention, there is provided a method of determining a particle trap pressure differential, comprising:

acquiring current differential pressure prediction parameters and historical differential pressure prediction parameters of a target particle trap, wherein the current differential pressure prediction parameters comprise current front-end air inlet temperature, current rear-end exhaust temperature, current transient exhaust gas volume flow and current carbon loading capacity, and the historical differential pressure prediction parameters comprise historical front-end air inlet temperature, historical rear-end exhaust temperature, historical transient exhaust gas volume flow and historical carbon loading capacity;

and determining the current pressure difference of the target particle trap based on the current pressure difference prediction parameters, the historical pressure difference prediction parameters and a pre-trained pressure difference prediction model.

According to another aspect of the present invention, there is provided a particle trap pressure differential determining apparatus comprising:

the parameter acquisition module is used for acquiring current differential pressure prediction parameters and historical differential pressure prediction parameters of the target particle trap, wherein the current differential pressure prediction parameters comprise current front-end intake air temperature, current rear-end exhaust air temperature, current transient exhaust gas volume flow and current carbon loading capacity, and the historical differential pressure prediction parameters comprise historical front-end intake air temperature, historical rear-end exhaust air temperature, historical transient exhaust gas volume flow and historical carbon loading capacity;

and the pressure difference prediction module is used for determining the current pressure difference of the target particle trap based on the current pressure difference prediction parameter, the historical pressure difference prediction parameter and a pre-trained pressure difference prediction model.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a particle trap pressure differential determination method according to any embodiment of the present invention.

According to another aspect of the invention, there is provided a computer readable storage medium having stored thereon computer instructions for causing a processor to execute a method of determining a particle trap pressure differential according to any of the embodiments of the invention.

According to the technical scheme of the embodiment of the invention, the current pressure difference prediction parameters such as the current front-end air inlet temperature, the current rear-end exhaust temperature, the current transient exhaust gas volume flow and the current carbon loading capacity of the target particle trap and the historical pressure difference prediction parameters such as the history front-end air inlet temperature, the historical rear-end exhaust temperature, the historical transient exhaust gas volume flow and the historical carbon loading capacity are obtained, and then the current pressure difference of the target particle trap is predicted according to a pre-trained pressure difference prediction model.

It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic flow chart illustrating a method for determining a differential pressure in a particulate trap according to an embodiment of the present invention;

FIG. 2 is a diagram of a model structure of a differential pressure prediction model according to an embodiment of the present invention;

FIG. 3 is a flow chart illustrating a method for determining a pressure differential across a particle trap according to a second embodiment of the present disclosure;

FIG. 4 is a schematic process diagram of a method for determining a pressure differential across a particle trap according to a second embodiment of the present invention;

FIG. 5 is a flow chart illustrating a method for determining a pressure differential across a particle trap according to a third embodiment of the present disclosure;

FIG. 6 is a schematic illustration of a particle trap pressure differential determining apparatus according to a fourth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.

Detailed Description

In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a schematic flow chart of a method for determining a particle trap pressure difference according to an embodiment of the present invention, where the embodiment is applicable to a particle trap, and a condition of the particle trap pressure difference at a current time is predicted according to a relevant parameter of the particle trap at the current time and relevant parameters of historical times, and the method may be implemented by a particle trap pressure difference determining device, where the particle trap pressure difference determining device may be implemented in hardware and/or software, and the particle trap pressure difference determining device may be configured in an Electronic device such as an ECU (Electronic Control Unit). As shown in fig. 1, the method includes:

and S110, acquiring a current differential pressure prediction parameter and a historical differential pressure prediction parameter of the target particle trap.

The current differential pressure prediction parameters comprise current front-end air inlet temperature, current rear-end exhaust temperature, current transient exhaust gas volume flow and current carbon loading capacity, and the historical differential pressure prediction parameters comprise historical front-end air inlet temperature, historical rear-end exhaust temperature, historical transient exhaust gas volume flow and historical carbon loading capacity.

In this embodiment, the current pressure difference prediction parameter may be a parameter of interest of the target particulate trap at the current time for pressure difference prediction.

The current front-end air inlet temperature and the current rear-end exhaust temperature are respectively the temperatures of a front-end air inlet and a rear-end air outlet of the target particle trap at the current moment; the current front end intake air temperature and the current rear end exhaust air temperature can be acquired through the temperature sensor. The current transient exhaust gas volumetric flow may be a transient exhaust gas volumetric flow of the front-end intake of the target particulate trap at the current time.

The current carbon load can be obtained by multiplying the steady-state emission of the engine by transient correction, then subtracting passive regeneration and correction, and finally integrating to obtain the carbon load. Or the current carbon loading capacity can be obtained through a current estimated pressure difference and a preset pressure difference carbon loading Map, wherein the current estimated pressure difference can be acquired based on a pressure difference sensor, and the preset pressure difference carbon loading Map can be a three-dimensional pressure difference Map and is used for describing a steady-state mapping relation between the pressure difference and the carbon loading capacity. For example, the X-axis of the preset pressure difference carbon loading map is each pressure difference in a steady state, the Y-axis is each volume flow of the exhaust gas, and the Z-axis is the corresponding carbon loading. In this embodiment, the current carbon loading corresponding to the current pressure difference can be queried in the preset pressure difference carbon loading map through the current pressure difference.

In this embodiment, the historical pressure differential prediction parameters may be parameters of interest to the target particulate trap at historical times for making pressure differential predictions. Specifically, historical differential pressure prediction parameters can be obtained according to a preset delay time step; alternatively, a historical pressure differential prediction parameter generated by the target particulate trap over the last driving cycle is obtained directly.

Optionally, the historical pressure difference prediction parameter of the target particle trap may be obtained by: acquiring a preset delay time step; and acquiring historical differential pressure prediction parameters generated at historical time points within the preset delay time step before the current moment based on the preset delay time step.

The preset delay time step may represent the number of historical time points for which prediction parameters need to be obtained. For example, if the preset delay time step is 8, the historical differential pressure prediction parameter generated every second within the previous 8 seconds before the current time can be acquired.

Through setting the preset delay time step length, the historical differential pressure prediction parameters are obtained through the preset delay time step length, data with adjacent time can be input among all data in the model, and the differential pressure output by the model can be guaranteed to accord with the change rule.

It should be noted that the preset delay time step may be set according to the prediction efficiency requirement and the prediction accuracy requirement. Specifically, considering that the prediction accuracy can be improved and the model calculation amount can be improved when the preset delay time step is long, and the model calculation amount can be reduced and the prediction accuracy can be reduced when the preset delay time step is small, a reasonable preset delay time step can be selected on the basis of ensuring the model prediction accuracy by combining the memory of the electronic device that needs to execute the pressure difference determination method provided by the embodiment, such as the memory of the ECU (electronic control unit) of the vehicle, the engine control unit, and the like, which is not limited in the embodiment.

And S120, determining the current pressure difference of the target particle trap based on the current pressure difference prediction parameters, the historical pressure difference prediction parameters and a pre-trained pressure difference prediction model.

The pre-trained differential pressure prediction model can be a model for differential pressure prediction according to input prediction parameters; such as a neural network model. For example, the pressure difference prediction model may be a back propagation model, a long-short term neural network, or a non-linear autoregressive model.

It should be noted that, in the present embodiment, the front end intake air temperature, the rear end exhaust air temperature, the transient exhaust gas volume flow rate, and the current carbon carrying amount are selected, and the purpose of performing the differential pressure prediction is to: the exhaust temperature can affect the microscopic morphology of the original discharged soot deposited in the particulate trap, and the microscopic morphology has an effect on the pressure difference; the transient exhaust gas volume flow affects the differential pressure; carbon loading is directly related to differential pressure as a direct indication of the deposition of the original exhaust soot in the particulate trap.

Therefore, the pressure difference prediction is carried out through the front-end air inlet temperature, the rear-end exhaust temperature, the transient exhaust gas volume flow and the current carbon carrying capacity, the mapping relation between each input and each output can be established, and then the virtual pressure difference signal sensor is established, so that the problem of signal interference in a fault mode is solved.

In addition, the embodiment predicts the differential pressure by combining the current differential pressure prediction parameters and the historical differential pressure prediction parameters, and compared with a mode of determining the differential pressure only by using some parameters at the current moment, the method can ensure that the predicted differential pressure accords with the change rule, avoid the occurrence of singular points, and further improve the estimation precision of the differential pressure.

In one specific embodiment, determining the current pressure difference of the target particle trap based on the current pressure difference prediction parameter, the historical pressure difference prediction parameter and a pre-trained pressure difference prediction model may include the following steps:

step 1, inputting a current differential pressure prediction parameter and a historical differential pressure prediction parameter into a differential pressure prediction model, so that each hidden layer node in the differential pressure prediction model determines node input data of each hidden layer node based on the current differential pressure prediction parameter, the historical differential pressure prediction parameter, a target weight corresponding to each input layer node and a target threshold corresponding to each hidden layer node;

step 2, aiming at each hidden layer node, determining node output data based on a hidden layer transfer function and node input data, and determining input data corresponding to each output layer node according to the node output data of each hidden layer node, target weights corresponding to each hidden layer node respectively and target thresholds corresponding to each output layer node in a differential pressure prediction model;

and 3, determining the current pressure difference output by the pressure difference prediction model based on the input data and the output layer transfer function respectively corresponding to each output layer node.

The differential pressure prediction model comprises an input layer, a hidden layer and an output layer, wherein the input layer comprises at least one input layer node, the hidden layer comprises at least one hidden layer node, and the output layer comprises at least one output layer node. Aiming at each input layer node, respectively connecting with each hidden layer node, namely connecting each hidden layer node with all input layer nodes; and aiming at each hidden layer node, the output layer nodes are respectively connected, namely each output layer node is connected with all the hidden layer nodes.

For example, the pressure difference prediction model may employ a modified non-linear autoregressive model (NARX). It should be noted that the differential pressure prediction model in this embodiment is different from the conventional non-linear autoregressive model in that the differential pressure prediction model provided in this embodiment eliminates an output delay feedback structure, where the output delay feedback structure takes the output at the current time as the input of the prediction at the next time, and this is set to: according to the method provided by the embodiment, the historical differential pressure prediction parameters are adopted to predict the differential pressure, so that the predicted differential pressure can meet the change rule, and the requirement of the differential pressure prediction precision is met. In addition, in the scenario of integrating the differential pressure determination method and the pre-trained differential pressure prediction model provided by the embodiment in the ECU or embedded system, the output delay feedback structure is cancelled, the parameters required by the model calculation are reduced, the output accuracy can be ensured, and the integration of the ECU or embedded system is facilitated, so that the implementation of differential pressure prediction is facilitated.

Specifically, the target weight corresponding to the input layer node may be a weight of a connection hidden layer node obtained after model training. The target weights for each input level node, which are oriented to different hidden level nodes, may be the same or different. The target weight corresponding to the hidden layer node may be a weight of a node connected to the output layer, which is obtained after model training, and the target threshold corresponding to the hidden layer node may be a node input threshold obtained after model training. The target weights for each hidden layer node, which are oriented to different output layer nodes, may be the same or different. The target threshold corresponding to the hidden layer node may be a node input threshold obtained after model training.

In this embodiment, the current differential pressure prediction parameter and the historical differential pressure prediction parameter may be input to each input layer node in the differential pressure prediction model together. For example, in the present embodiment, the number of current differential pressure prediction parameters is 4, and when the preset delay time step is 9, the number of historical differential pressure prediction parameters is 4 × 9=36, then 40 parameters may be input to each input layer node respectively.

Further, each input layer node transmits the received parameters to each hidden layer node. Taking a hidden layer node as an example, input data for determining the hidden layer node is described: the input data of each input layer node can be multiplied by the target weight corresponding to the input layer node, the multiplication results of all the input layer nodes are accumulated, and the target threshold corresponding to the hidden layer node is added to the accumulated result, so that the node input data corresponding to the hidden layer node can be obtained.

Further, in step 2, each hidden layer node may calculate the node input data through its internal hidden layer transfer function, obtain node output data, and transmit the node output data to each output layer node. Taking an output layer node as an example, input data for determining the output layer node is described as follows: the output data of each hidden layer node can be multiplied by the target weight corresponding to the hidden layer node, the multiplication results of all the hidden layer nodes are accumulated, and the target threshold corresponding to the output layer node is added to the accumulated result, so that the input data corresponding to the output layer node can be obtained.

After the input data corresponding to each output layer node is obtained, each output layer node can calculate the input data through the internal output layer transfer function of the output layer node to obtain the output data. If the number of the output layer nodes is one, the output data of the output layer nodes can be directly used as the current carbon capacity; if the number of the output layer nodes is multiple, the current carbon carrying capacity can be determined according to the target weight corresponding to each output layer node and the output data of each output layer node, or the current pressure difference can be determined directly according to the average value of the output data of each output layer node.

In the above embodiment, the target weights respectively corresponding to the input layer nodes and the target thresholds respectively corresponding to the hidden layer nodes obtained through pre-training are used to determine the input data respectively corresponding to the hidden layer nodes, the input data respectively corresponding to the output layer nodes are determined through the hidden layer transfer function, the target weights respectively corresponding to the hidden layer nodes and the target thresholds respectively corresponding to the output layer nodes, the current pressure difference is obtained through the output layer transfer function, and the pressure difference prediction is performed by establishing the mapping relationship between the input current relevant parameters, the historical relevant parameters and the output pressure difference, so that the pressure difference prediction accuracy of the particle trap is improved.

It should be noted that, if the model provided in the present embodiment needs to be integrated into the ECU to predict the differential pressure in real time, the computational power requirement and the memory occupation need to be considered. Therefore, in addition to ensuring the prediction accuracy of the pressure difference, the number of parameters input into the model, the number of hidden layers in the model, the number of neurons, and the size of the preset delay time step need to be reduced as much as possible.

In order to reduce the computational power requirement on the embedded system and the pressure of memory occupation, the present embodiment further adopts an optimization algorithm (such as a genetic algorithm) to optimize the number of neurons, the number of layers of hidden layers, and a preset delay time step in the model. Illustratively, the fitting degree of the model optimized by the optimization algorithm is 0.912, the memory occupies about 6k, and the requirement of embedded system integration is met.

Fig. 2 shows a model structure diagram of a differential pressure prediction model. The preset delay time step can be 1 m, which means that the pressure difference prediction parameters of previous m historical moments adjacent to the current moment can be obtained, the number of the hidden layer nodes is n, that is, the number of the neurons is n, and the preset delay time step and the hidden layer nodes can be obtained through an optimization algorithm. The number of the current differential pressure prediction parameters may be 4, that is, the number of x (t) is 4, which are the current front end intake air temperature, the current rear end exhaust air temperature, the current transient exhaust gas volume flow, and the current carbon loading amount, respectively. Specifically, the current differential pressure prediction parameter and the historical differential pressure prediction parameter obtained according to the preset delay time step length can be input into the model, then the input data of each hidden layer node is calculated according to each target weight W and a target threshold b, then the output data of each hidden layer node is input into the output layer, the input data of the output layer node is calculated according to each target weight W and a target threshold b, and finally the current differential pressure y (t) is obtained, wherein the number of the output data is 1.

According to the technical scheme of the embodiment, the current pressure difference prediction parameters such as the current front-end air inlet temperature, the current rear-end exhaust temperature, the current transient exhaust gas volume flow and the current carbon loading capacity of the target particle trap and the historical pressure difference prediction parameters such as the history front-end air inlet temperature, the historical rear-end exhaust temperature, the historical transient exhaust gas volume flow and the historical carbon loading capacity are obtained, and then the current pressure difference of the target particle trap is predicted according to a pre-trained pressure difference prediction model.

Example two

Fig. 3 is a schematic flow chart of a method for determining a pressure difference of a particle trap according to a second embodiment of the present invention, which is based on the above embodiments, and in this embodiment, after determining a current pressure difference of a target particle trap, a first-order complementary filtering process may be performed on the current pressure difference to improve accuracy of a predicted pressure difference. As shown in fig. 3, the method includes:

s210, obtaining a current pressure difference prediction parameter and a historical pressure difference prediction parameter of the target particle trap.

S220, determining the current pressure difference of the target particle catcher based on the current pressure difference prediction parameters, the historical pressure difference prediction parameters and a pre-trained pressure difference prediction model.

And S230, acquiring a preset filter coefficient, performing first-order complementary filtering processing on the current pressure difference based on the preset filter coefficient, and updating the current pressure difference based on a filtering processing result.

The preset filter coefficient may be a time coefficient of first-order complementary filtering, and the first-order complementary filtering may be PT1 filtering. Specifically, the preset filter coefficient may represent a time between two sampling intervals. Illustratively, the preset filter coefficient T1=550.

Specifically, the first-order complementary filtering processing is performed on the current pressure difference based on the preset filtering coefficient, and the current pressure difference is updated based on the filtering processing result, which may be: and determining a historical pressure difference corresponding to the previous sampling time based on a preset filter coefficient and the current time, determining a filtering processing result based on the current pressure difference corresponding to the current time, the weight corresponding to the current pressure difference and the historical pressure difference corresponding to the previous sampling time, and updating the current pressure difference based on the filtering processing result. The historical differential pressure corresponding to the previous sampling time may also be the differential pressure predicted by the differential pressure prediction model for the previous sampling time.

In a specific implementation manner, before obtaining a preset filter coefficient, performing first-order complementary filtering processing on the current pressure difference based on the preset filter coefficient, and updating the current pressure difference based on a filtering processing result, the method provided in this embodiment further includes: acquiring a preset pressure difference range; and judging whether the current pressure difference is within a preset pressure difference range, and if not, updating the current pressure difference based on a critical value of the preset pressure difference range.

Wherein the preset differential pressure range may be a theoretical range in which the differential pressure is located. For example, the preset differential pressure range is [0,100]. The critical value of the preset pressure difference range includes a minimum value and a maximum value in the preset pressure difference range. Specifically, if the current differential pressure exceeds the preset differential pressure range, the current differential pressure may be updated according to a critical value of the preset differential pressure range, for example, when the current differential pressure is greater than a maximum value in the preset differential pressure range, the current differential pressure is updated according to the maximum value in the preset differential pressure range, and when the current differential pressure is less than a minimum value in the preset differential pressure range, the current differential pressure is updated according to a minimum value in the preset differential pressure range.

The current pressure difference is updated by adopting the preset pressure difference range, so that the current pressure difference is limited in the preset pressure difference range, the current pressure difference exceeding the preset pressure difference range is prevented from being output, and the pressure difference prediction precision is further improved.

Referring to fig. 4, a process schematic of a method for determining a differential pressure in a particle trap is shown. First, the pressure difference test data may be input to the offline training module in advance, so that the offline training module learns the target weight and the target threshold of the pressure difference prediction network based on the pressure difference test data to obtain the pressure difference prediction model. Then, the current differential pressure prediction parameter at the current time and the historical differential pressure prediction parameter may be input to the differential pressure prediction model to obtain the current differential pressure predicted by the differential pressure prediction model, and the unit of the current differential pressure may be hPa. Further, the current differential pressure is limited within a preset differential pressure range, and PT1 filtering (a preset filtering coefficient may be T1= 550) is performed on the current differential pressure, so as to obtain a final current differential pressure.

According to the technical scheme of the embodiment, after the current differential pressure is determined based on the pre-trained differential pressure prediction model, the current differential pressure output by the model is subjected to first-order complementary filtering processing according to the preset filtering coefficient, and the current differential pressure is updated according to the filtering processing result, so that a zero drift point in the predicted differential pressure at each moment is avoided, and the precision of the predicted differential pressure is further improved.

EXAMPLE III

Fig. 5 is a schematic flow chart of a method for determining a differential pressure of a particle trap according to a third embodiment of the present invention, and this embodiment exemplarily illustrates a training process of a differential pressure prediction model based on the foregoing embodiments. As shown in fig. 5, the method includes:

s310, constructing a differential pressure prediction network, wherein the differential pressure prediction network comprises each input layer node, each hidden layer node and each output layer node.

Wherein the differential pressure prediction network may employ a modified NARX network. And each input layer node in the differential pressure prediction network is connected with each hidden layer node, and each hidden layer node is connected with each output layer node. In this embodiment, the number of output layer nodes may be one or more, which is not limited in this embodiment.

S320, obtaining differential pressure test data, wherein the differential pressure test data comprise front-end air inlet temperature, rear-end air outlet temperature, transient waste gas volume flow, actual carbon loading capacity and actual differential pressure of the sample at the current moment and the historical moment of the sample.

Wherein, the pressure difference test data can be obtained by testing the engine. Specifically, the differential pressure test data includes the front-end intake air temperature, the rear-end exhaust air temperature, the transient exhaust gas volume flow and the actual carbon loading capacity of the sample at the current moment, and the front-end intake air temperature, the rear-end exhaust air temperature, the transient exhaust gas volume flow, the differential pressure and the actual carbon loading capacity of the sample at the historical moment, and the differential pressure test data further includes the actual differential pressure of the sample at the current moment, namely, the sample label.

S330, training the differential pressure prediction network based on differential pressure test data to obtain target weights corresponding to the input layer nodes, target weights corresponding to the hidden layer nodes, target thresholds corresponding to the hidden layer nodes and target thresholds corresponding to the output layer nodes, and determining a differential pressure prediction model.

In this embodiment, the front-end intake air temperature, the rear-end exhaust air temperature, the transient exhaust gas volume flow, and the actual carbon carrying amount at the current time and the historical time of the sample in the differential pressure test data may be input to the differential pressure prediction network, and then, according to the prediction result output by the differential pressure prediction network and the actual differential pressure at the current time of the sample, the weights corresponding to the nodes of each input layer, the weights corresponding to the nodes of each hidden layer, the thresholds corresponding to the nodes of each hidden layer, and the thresholds corresponding to the nodes of each output layer are adjusted until a training cutoff condition is satisfied, so as to obtain the target weights corresponding to the nodes of each input layer, the target weights and the target thresholds corresponding to the nodes of each hidden layer, and the target thresholds corresponding to the nodes of each output layer, and use the differential pressure prediction network as a differential pressure prediction model.

In a specific embodiment, training a differential pressure prediction network based on differential pressure test data to obtain a target weight corresponding to each input layer node, a target weight corresponding to each hidden layer node, a target threshold corresponding to each hidden layer node, and a target threshold corresponding to each output layer node includes the following steps:

step 1, determining a first initial weight corresponding to each input layer node, a second initial weight corresponding to each hidden layer node, a second initial threshold corresponding to each hidden layer node and a third initial threshold corresponding to each output layer node;

step 2, determining a first weight correction quantity corresponding to each input layer node, a second weight correction quantity corresponding to each hidden layer node, a second threshold correction quantity corresponding to each hidden layer node and a third threshold correction quantity corresponding to each output layer node based on the differential pressure test data, each first initial weight, each second initial threshold and each third initial threshold;

and 3, updating the first initial weight based on the first weight correction quantity, updating the second initial weight and the second initial threshold respectively based on the second weight correction quantity and the second threshold correction quantity, updating the third initial threshold based on the third threshold correction quantity, and returning to execute the operation of determining the first weight correction quantity corresponding to each input layer node, the second weight correction quantity corresponding to each hidden layer node, the second threshold correction quantity corresponding to each hidden layer node and the third threshold correction quantity corresponding to each output layer node respectively until a training cutoff condition is met.

In step 1, the first initial weights, the second initial thresholds, and the third initial thresholds may be preset or default values in the differential pressure prediction network.

Specifically, the predicted result corresponding to the differential pressure test data may be calculated according to the first initial weight, each second initial threshold, and each third initial threshold, and then each first weight correction amount, each second threshold correction amount, and each third threshold correction amount may be determined according to the predicted result and the sample label, the corresponding initial weight or initial threshold may be corrected according to the correction amounts, and then the above step 3302 may be performed again until the training cutoff condition is satisfied.

The training cutoff condition may be that the calculation result of the loss function converges, or that the training times reach a preset time threshold.

For example, in step 3302, the first weight correction amount, the second threshold correction amount, and the third threshold correction amount may be calculated by the following formulas:

；

；

；

；

in the above-mentioned formula, the first and second,

a first weight modifier representing a connection of the jth input level node to the ith hidden level node,

a second threshold modifier representing the ith hidden layer node,

a second weight modifier representing the connection of the ith hidden layer node to the kth output layer node,

a third threshold modifier representing a kth output level node.

Indicating the number of nodes in the hidden layer,

indicating the amount of differential pressure test data,

being the inverse of the implicit layer transfer function,

which is the inverse of the transfer function of the output layer,

to learn the rate, the learning rate may be set to 0.04.

May be a sample label and may be a network predictor.

Representing data input to the jth input level node,

representing data input to the ith hidden layer node.

In the above-mentioned formula,

、

the input data of the input layer node and the input data of the hidden layer node can be obtained by the following formula:

；

；

；

；

wherein,

a weight indicating that the jth input level node is connected to the ith hidden level node,

and M is equal to the product of the input number and the preset delay time step.

The output data representing the ith hidden layer node,

representing the hidden layer transfer function.

The weight connecting the kth output layer node for the ith hidden layer node,

is the threshold of the kth output layer node.

Representing the output data of the kth output layer node,

representing the output layer transfer function.

Through the steps 1 to 3, the target weights and the target thresholds can be determined based on the learning correction amount, and the accuracy of the target weights and the target thresholds is improved.

Optionally, for step 2, based on the differential pressure test data, each first initial weight, each second initial threshold, and each third initial threshold, determining a first weight correction amount corresponding to each input layer node, a second weight correction amount corresponding to each hidden layer node, a second threshold correction amount corresponding to each hidden layer node, and a third threshold correction amount corresponding to each output layer node, may include the following steps:

step 21, determining the current error square sum based on the differential pressure test data, the first initial weights, the second initial thresholds and the third initial thresholds;

step 22, determining a current momentum factor and a current learning rate based on the current error square sum and the error square sum of the previous training;

and step 23, determining a first weight correction amount corresponding to each input layer node in the current training round, a second weight correction amount corresponding to each hidden layer node in the current training round, a second threshold correction amount corresponding to each hidden layer node in the current training round and a third threshold correction amount corresponding to each output layer node in the current training round according to the current momentum factor, the current learning rate and each correction information of the previous training round.

In the step 21, the current sum of squares of errors may be determined by calculating a network predicted value according to the differential pressure test data, the first initial weights, the second initial thresholds, and the third initial thresholds, and further calculating the current sum of squares of errors according to the network predicted value and a sample label in the differential pressure test data.

In step 22, after calculating the current sum of squares of errors, if the current sum of squares of errors is smaller than the sum of squares of errors in the previous training, the current momentum factor may be determined to be a first factor, for example, the first factor may be 0.95. If the current sum of squared errors is greater than the set multiple of the sum of squared errors of the previous training round, the current momentum factor may be determined to be the second factor, e.g., the second factor may be 0, and the set multiple may be 1.04. If the two conditions are not met, the current momentum factor can take other set values. For example, the current momentum factor may be determined by the following equation:

；

wherein,

for the purpose of the current momentum factor,

is the sum of the squares of the current errors,

the sum of the squares of the errors of the previous round of training.

In the above step 22, if the current sum of squared errors is smaller than the sum of squared errors of the previous training round, the current learning rate may be a first multiple of the learning rate of the previous training round, for example, the first multiple may be 1.05. If the current sum of squared errors is greater than a set multiple of the sum of squared errors of the previous training round, it may be determined that the current learning rate is a second multiple of the learning rate of the previous training round, the second multiple being less than the first multiple, e.g., the second multiple being 0.7. If the two conditions are not met, the current learning rate can take other set values. For example, the current learning rate may be determined by the following formula:

；

wherein,

is the current learning rate.

After the current momentum factor and the current learning rate are determined, according to the above step 23, the correction amounts of the current training round can be determined according to the current momentum factor, the current learning rate, and the first weight correction amounts, the second threshold correction amounts, and the third threshold correction amounts obtained in the previous training round.

For example, the respective correction amounts of the current training round can be calculated by the following formula:

；

；

wherein,

is the first weight correction for the current training round,

a second threshold modifier for the current training round,

a second weight modifier for the current training round,

is at presentAnd a third threshold correction amount of the training round.

In the above-mentioned formula,

respectively the correction values obtained in the previous training round.

Is the mean square error of the current training round,

is an input.

In the above steps 21 to 23, on the basis of gradient descent, learning of the weight and the threshold is performed by introducing a variable momentum factor and a variable learning rate, so that a local optimal solution can be skipped and the training precision is improved.

S340, obtaining a current differential pressure prediction parameter and a historical differential pressure prediction parameter of the target particle trap, and inputting the current differential pressure prediction parameter and the historical differential pressure prediction parameter into a differential pressure prediction model, so that each hidden layer node in the differential pressure prediction model determines node input data of each hidden layer node based on the current differential pressure prediction parameter, the historical differential pressure prediction parameter, a target weight corresponding to each input layer node and a target threshold corresponding to each hidden layer node.

S350, for each hidden layer node, determining node output data based on the hidden layer transfer function and the node input data, and determining input data corresponding to each output layer node according to the node output data of each hidden layer node, the target weight corresponding to each hidden layer node and the target threshold corresponding to each output layer node in the differential pressure prediction model.

And S360, determining the current pressure difference output by the pressure difference prediction model based on the input data and the output layer transfer function respectively corresponding to each output layer node.

The method for determining the pressure difference of the particle trap can construct the mapping relation between each input and the pressure difference based on the target weights and the target thresholds obtained through learning, and further predict the pressure difference according to the mapping relation to establish the pressure difference signal virtual sensor, solve the problem of signal interference in a failure mode, improve the performance of a pressure difference signal related control module, reduce the failure rate of the DPF, and save service cost.

In a practical application scenario, if the computation capacity of the ECU integrated with the pressure difference prediction model is limited, the amount of computation required by the ECU to calculate the current carbon loading may be large, and the pressure difference prediction efficiency of the ECU may be affected, so that the number of parameters for inputting to the model to perform the pressure difference prediction may be reduced appropriately in order to ensure the pressure difference prediction efficiency. For example, the current differential pressure prediction parameter may also only include the current front-end intake air temperature, the current rear-end exhaust air temperature, and the current transient exhaust gas volume flow rate, and the historical differential pressure prediction parameter may only include the historical front-end intake air temperature, the historical rear-end exhaust air temperature, and the historical transient exhaust gas volume flow rate, so that the ECU performs differential pressure prediction through the front-end intake air temperature, the rear-end exhaust air temperature, the transient exhaust gas volume flow rate, and the differential pressure prediction model at the current time and the preset delay time step, reduces the memory and the amount of calculation, and improves the differential pressure prediction efficiency. Referring to table 1, the relative error contrast for different input parameters is shown.

TABLE 1 relative error contrast for different input parameters

When the input number is 2, the relevant parameters input into the model comprise the front-end intake temperature and the transient exhaust gas volume flow; when the input number is 3, the relevant parameters input into the model are represented to comprise front-end air inlet temperature, rear-end exhaust temperature and transient exhaust gas volume flow; when the input number is 4, the relevant parameters input into the model comprise front-end air inlet temperature, rear-end exhaust temperature, transient exhaust gas volume flow and carbon capacity.

According to the technical scheme of the embodiment, a pressure difference prediction network comprising each input layer node, each hidden layer node and each output layer node is constructed, and then the pressure difference prediction network is trained through pressure difference test data to obtain a target weight corresponding to each input layer node, a target weight and a target threshold corresponding to each hidden layer node and a target threshold corresponding to each output layer node, so that pressure difference prediction is carried out based on each target weight and each target threshold in a pressure difference prediction model, the determination of the mapping relation between the output pressure difference and each input relevant parameter is realized, and then the pressure difference prediction is carried out based on the mapping relation, the front and back exhaust temperatures, the exhaust gas flow and the carbon carrying capacity in the model, so that the pressure difference prediction method can adapt to the states of oil products and components, and the pressure difference estimation accuracy is improved.

Example four

FIG. 6 is a schematic diagram of a pressure differential determining apparatus for a particle trap according to a fourth embodiment of the present invention. As shown in fig. 6, the apparatus includes a parameter acquisition module 410 and a differential pressure prediction module 420, wherein:

a parameter obtaining module 410, configured to obtain a current differential pressure prediction parameter and a historical differential pressure prediction parameter of the target particulate trap, where the current differential pressure prediction parameter includes a current front-end intake air temperature, a current rear-end exhaust air temperature, a current transient exhaust gas volume flow, and a current carbon loading amount, and the historical differential pressure prediction parameter includes a historical front-end intake air temperature, a historical rear-end exhaust air temperature, a historical transient exhaust gas volume flow, and a historical carbon loading amount;

a pressure difference prediction module 420 for determining a current pressure difference of the target particulate trap based on the current pressure difference prediction parameter, the historical pressure difference prediction parameter, and a pre-trained pressure difference prediction model.

On the basis of the above embodiment, optionally, the apparatus further includes a differential pressure filtering module, where the differential pressure filtering module is configured to obtain a preset filtering coefficient; and performing first-order complementary filtering processing on the current pressure difference based on the preset filtering coefficient, and updating the current pressure difference based on a filtering processing result.

On the basis of the above embodiment, optionally, the apparatus further includes a differential pressure filtering module, where the differential pressure filtering module is configured to obtain a preset differential pressure range; and judging whether the current pressure difference is in the preset pressure difference range, if not, updating the current pressure difference based on a critical value of the preset pressure difference range.

On the basis of the foregoing embodiment, optionally, the differential pressure prediction module 420 includes an hidden layer calculation unit, an output layer calculation unit, and a differential pressure calculation unit, where;

a hidden layer calculation unit, configured to input the current differential pressure prediction parameter and the historical differential pressure prediction parameter into the differential pressure prediction model, so that each hidden layer node in the differential pressure prediction model determines node input data of each hidden layer node based on the current differential pressure prediction parameter, the historical differential pressure prediction parameter, a target weight corresponding to each input layer node, and a target threshold corresponding to each hidden layer node;

an output layer calculation unit, configured to determine, for each hidden layer node, node output data based on a hidden layer transfer function and the node input data, and determine, according to the node output data of each hidden layer node, a target weight corresponding to each hidden layer node, and a target threshold corresponding to each output layer node in the differential pressure prediction model, input data corresponding to each output layer node;

and the pressure difference calculation unit is used for determining the current pressure difference output by the pressure difference prediction model based on the input data and the output layer transfer function respectively corresponding to each output layer node.

On the basis of the above embodiment, optionally, the apparatus further includes a model training module, where the model training module includes a network construction unit, a data acquisition unit, and a training unit;

the network construction unit is used for constructing a differential pressure prediction network, and the differential pressure prediction network comprises each input layer node, each hidden layer node and each output layer node;

the data acquisition unit is used for acquiring differential pressure test data, wherein the differential pressure test data comprises front-end air inlet temperature, rear-end air outlet temperature, transient waste gas volume flow, actual carbon loading capacity and actual differential pressure of a sample at the current moment and the historical moment of the sample;

and the training unit is used for training the differential pressure prediction network based on the differential pressure test data to obtain a target weight corresponding to each input layer node, a target weight corresponding to each hidden layer node, a target threshold corresponding to each hidden layer node and a target threshold corresponding to each output layer node, and determining the differential pressure prediction model.

On the basis of the above embodiment, optionally, the training unit is specifically configured to:

determining a first initial weight corresponding to each input layer node, a second initial weight corresponding to each hidden layer node, a second initial threshold corresponding to each hidden layer node, and a third initial threshold corresponding to each output layer node; determining, based on the carbon capacity test data, the first initial weights, the second initial thresholds and the third initial thresholds, first weight corrections corresponding to the input layer nodes, second weight corrections corresponding to the hidden layer nodes, second threshold corrections corresponding to the hidden layer nodes and third threshold corrections corresponding to the output layer nodes; updating the first initial weight based on the first weight correction quantity, updating the second initial weight and the second initial threshold based on the second weight correction quantity and the second threshold correction quantity respectively, updating the third initial threshold based on the third threshold correction quantity, and returning to execute the operation of determining the first weight correction quantity corresponding to each input layer node, the second weight correction quantity corresponding to each hidden layer node, the second threshold correction quantity corresponding to each hidden layer node and the third threshold correction quantity corresponding to each output layer node respectively until a training cutoff condition is met.

On the basis of the foregoing embodiment, optionally, the training unit is further configured to determine a current sum of squares of errors based on the carbon capacity test data, the first initial weights, the second initial thresholds, and the third initial thresholds; determining a current momentum factor and a current learning rate based on the current sum of squares of errors and the sum of squares of errors of the previous training round; according to the current momentum factor, the current learning rate and each correction information of previous training, determining a first weight correction quantity respectively corresponding to each input layer node in the current training round, a second weight correction quantity respectively corresponding to each hidden layer node in the current training round, a second threshold correction quantity respectively corresponding to each hidden layer node in the current training round and a third threshold correction quantity respectively corresponding to each output layer node in the current training round.

The particle trap pressure difference determining device provided by the embodiment of the invention can execute the particle trap pressure difference determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method.

EXAMPLE five

Fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, 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 meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 7, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read only memory 12, a random access memory 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the read only memory 12 or the computer program loaded from the storage unit 18 into the random access memory 13. In the random access memory 13, various programs and data necessary for the operation of the electronic device 10 can also be stored. The processor 11, the read only memory 12 and the random access memory 13 are connected to each other via a bus 14. An input/output interface 15 is also connected to the bus 14.

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

The processor 11 may be a variety of general and/or special purpose processing components having 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 specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the particle trap pressure differential determination method.

In some embodiments, the particle trap pressure differential determination method may be implemented as a computer program tangibly embodied 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 onto the electronic device 10 via the read only memory 12 and/or the communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the particle trap pressure differential determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the particle trap pressure differential determination method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the particle trap pressure differential determination method 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

EXAMPLE six

Sixth, an embodiment of the present invention further provides a computer readable storage medium storing computer instructions for causing a processor to execute a method for particle trap pressure differential determination, the method comprising:

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a 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 may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

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

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method of determining a differential pressure in a particle trap, comprising:

acquiring current differential pressure prediction parameters and historical differential pressure prediction parameters of a target particle trap, wherein the historical differential pressure prediction parameters are generated in the last driving cycle of the target particle trap or are obtained according to a preset delay time step, the current differential pressure prediction parameters comprise current front-end air inlet temperature, current rear-end exhaust temperature, current transient exhaust gas volume flow and current carbon loading capacity, and the historical differential pressure prediction parameters comprise historical front-end air inlet temperature, historical rear-end exhaust temperature, historical transient exhaust gas volume flow and historical carbon loading capacity;

determining the current pressure difference of the target particle catcher based on the current pressure difference prediction parameters, the historical pressure difference prediction parameters and a pre-trained pressure difference prediction model so as to enable the current pressure difference to accord with a change rule;

wherein the differential pressure prediction model comprises an input layer, a hidden layer and an output layer.

2. The method of claim 1, wherein after determining the current pressure differential of the target particulate trap based on the current pressure differential prediction parameter, the historical pressure differential prediction parameter, and a pre-trained pressure differential prediction model, the method further comprises:

acquiring a preset filter coefficient;

and performing first-order complementary filtering processing on the current pressure difference based on the preset filtering coefficient, and updating the current pressure difference based on a filtering processing result.

3. The method according to claim 2, wherein before the first-order complementary filtering processing is performed on the current pressure difference based on the preset filter coefficient, and the current pressure difference is updated based on a filtering processing result, the method further comprises:

acquiring a preset pressure difference range;

and judging whether the current pressure difference is in the preset pressure difference range, if not, updating the current pressure difference based on the critical value of the preset pressure difference range.

4. The method of claim 1, wherein determining a current pressure differential of the target particulate trap based on the current pressure differential prediction parameter, the historical pressure differential prediction parameter, and a pre-trained pressure differential prediction model comprises:

inputting the current differential pressure prediction parameter and the historical differential pressure prediction parameter into the differential pressure prediction model, so that each hidden layer node in the differential pressure prediction model determines node input data of each hidden layer node based on the current differential pressure prediction parameter, the historical differential pressure prediction parameter, the target weight corresponding to each input layer node and the target threshold corresponding to each hidden layer node;

determining node output data based on a hidden layer transfer function and the node input data for each hidden layer node, and determining input data corresponding to each output layer node according to the node output data of each hidden layer node, target weights corresponding to each hidden layer node respectively and target thresholds corresponding to each output layer node in the differential pressure prediction model respectively;

and determining the current differential pressure output by the differential pressure prediction model based on the input data and the output layer transfer function respectively corresponding to each output layer node.

5. The method of claim 4, further comprising:

constructing a differential pressure prediction network, wherein the differential pressure prediction network comprises each input layer node, each hidden layer node and each output layer node;

acquiring differential pressure test data, wherein the differential pressure test data comprises front-end air inlet temperature, rear-end air outlet temperature, transient waste gas volume flow, actual carbon loading capacity and actual differential pressure of a sample at the current moment and the historical moment of the sample;

and training the differential pressure prediction network based on the differential pressure test data to obtain target weights respectively corresponding to all the input layer nodes, target weights respectively corresponding to all the hidden layer nodes, target thresholds respectively corresponding to all the hidden layer nodes and target thresholds respectively corresponding to all the output layer nodes, and determining the differential pressure prediction model.

6. The method of claim 5, wherein training the differential pressure prediction network based on the differential pressure test data to obtain a target weight corresponding to each of the input layer nodes, a target weight corresponding to each of the hidden layer nodes, a target threshold corresponding to each of the hidden layer nodes, and a target threshold corresponding to each of the output layer nodes comprises:

determining a first initial weight corresponding to each input layer node, a second initial weight corresponding to each hidden layer node, a second initial threshold corresponding to each hidden layer node, and a third initial threshold corresponding to each output layer node;

determining a first weight correction quantity corresponding to each input layer node, a second weight correction quantity corresponding to each hidden layer node, a second threshold correction quantity corresponding to each hidden layer node and a third threshold correction quantity corresponding to each output layer node based on the differential pressure test data, each first initial weight, each second initial threshold and each third initial threshold;

updating the first initial weight based on the first weight correction quantity, updating the second initial weight and the second initial threshold based on the second weight correction quantity and the second threshold correction quantity respectively, updating the third initial threshold based on the third threshold correction quantity, and returning to execute the operation of determining the first weight correction quantity corresponding to each input layer node, the second weight correction quantity corresponding to each hidden layer node, the second threshold correction quantity corresponding to each hidden layer node and the third threshold correction quantity corresponding to each output layer node respectively until a training cutoff condition is met.

7. The method of claim 6, wherein determining a first weight modifier for each of the input layer nodes, a second weight modifier for each of the hidden layer nodes, a second threshold modifier for each of the hidden layer nodes, and a third threshold modifier for each of the output layer nodes based on the differential pressure test data, each of the first initial weights, each of the second initial thresholds, and each of the third initial thresholds comprises:

determining a current sum of squares error based on the differential pressure test data, each of the first initial weights, each of the second initial thresholds, and each of the third initial thresholds;

determining a current momentum factor and a current learning rate based on the current sum of squares of errors and the sum of squares of errors of the previous training round;

according to the current momentum factor, the current learning rate and each correction information of previous training, determining a first weight correction quantity respectively corresponding to each input layer node in the current training round, a second weight correction quantity respectively corresponding to each hidden layer node in the current training round, a second threshold correction quantity respectively corresponding to each hidden layer node in the current training round and a third threshold correction quantity respectively corresponding to each output layer node in the current training round.

8. A particle trap pressure differential determining apparatus, comprising:

the parameter acquisition module is used for acquiring current differential pressure prediction parameters and historical differential pressure prediction parameters of the target particle trap, wherein the historical differential pressure prediction parameters are generated in the last driving cycle of the target particle trap or are obtained according to preset delay time step lengths, the current differential pressure prediction parameters comprise current front-end air inlet temperature, current rear-end air outlet temperature, current transient exhaust gas volume flow and current carbon loading capacity, and the historical differential pressure prediction parameters comprise historical front-end air inlet temperature, historical rear-end air outlet temperature, historical transient exhaust gas volume flow and historical carbon loading capacity;

the pressure difference prediction module is used for determining the current pressure difference of the target particle trap based on the current pressure difference prediction parameters, the historical pressure difference prediction parameters and a pre-trained pressure difference prediction model so as to enable the current pressure difference to accord with a change rule;

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; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the particle trap pressure differential determination method of any of claims 1-7.

10. A computer readable storage medium having stored thereon computer instructions for causing a processor to execute the method of any of claims 1-7 for determining a particle trap pressure differential.