CN116557521B

CN116557521B - Data processing and related device for high-speed transmission

Info

Publication number: CN116557521B
Application number: CN202310834259.5A
Authority: CN
Inventors: 秦强; 李宛蔚; 秦博
Original assignee: Dedian Beidou Electric Vehicle Co ltd
Current assignee: Anhui C E Cars Yangzi Automobile Co ltd
Priority date: 2023-07-10
Filing date: 2023-07-10
Publication date: 2023-09-01
Anticipated expiration: 2043-07-10
Also published as: CN116557521A

Abstract

The invention relates to the field of data processing, and discloses a data processing and related device for a high-speed transmission, which is used for improving the data processing accuracy of the high-speed transmission. The method comprises the following steps: performing curve division on the first performance relation curve and the second performance relation curve respectively to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range; extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values; inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, so as to obtain optimal gear-shifting points corresponding to each vehicle speed gradient range; and constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, acquiring second vehicle speed data of the target vehicle, and performing intelligent shift of the high-speed transmission through the mapping relation model.

Description

Data processing and related device for high-speed transmission

Technical Field

The invention relates to the field of data processing, in particular to data processing and related devices for a high-speed transmission.

Background

Currently, there is an increasing demand for automobiles, and high-speed variators have become an integral component of many vehicles. Accordingly, continuous research and improvement of data processing methods for high-speed transmissions has become an important subject in the automotive industry. And the data analysis method based on artificial intelligence can utilize machine learning and other algorithms to optimize the performance of the high-speed transmission and generate accurate results in the shortest time.

The traditional high-speed transmission control system is mostly based on experience or manual design, is difficult to adapt to complex driving requirements and road condition changes under different conditions, has the problems of setbacks and vibration during gear shifting, influences driving experience and safety, can only realize basic gear shifting functions, and cannot be intelligently adjusted and optimized according to real-time performance conditions.

Disclosure of Invention

The invention provides a data processing and related device for a high-speed transmission, which is used for improving the data processing accuracy of the high-speed transmission.

The first aspect of the present invention provides a data processing method for a high-speed transmission, the data processing method for a high-speed transmission including:

Acquiring first vehicle speed data of a target vehicle, and acquiring rotating speed data and response time data of a high-speed changer in the target vehicle;

performing curve fitting on the first vehicle speed data and the rotating speed data to obtain a first performance relation curve, and performing curve construction on the first vehicle speed data and the response time data to obtain a second performance relation curve;

according to a plurality of preset vehicle speed gradient ranges, respectively carrying out curve division on the first performance relation curve and the second performance relation curve to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range;

extracting curve characteristic points from the first sub-relation curve and the second sub-relation curve of each vehicle speed gradient range to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range;

inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range into a preset high-speed transmission gear shifting analysis model to perform optimal gear shifting point calculation, and obtaining optimal gear shifting points corresponding to each vehicle speed gradient range;

and constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, acquiring second vehicle speed data of the target vehicle, and performing intelligent shift of the high-speed transmission through the mapping relation model.

With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the acquiring first vehicle speed data of the target vehicle, and acquiring rotational speed data and response time data of a high speed transmission in the target vehicle includes:

setting a preset sensor group, a target vehicle and a high-speed transmission of the target vehicle, and configuring a data transmission interface of the sensor group to obtain a target data transmission interface;

the sensor group is used for collecting test data of the target vehicle and the high-speed transmission, and the data transmission is carried out through the target data transmission interface to obtain target test data;

and carrying out cluster analysis on the target test data based on a preset vehicle speed data label, a preset rotating speed data label and a preset reaction time data label to obtain first vehicle speed data, first rotating speed data and first reaction time data.

With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, performing curve fitting on the first vehicle speed data and the rotational speed data to obtain a first performance relationship curve, and performing curve construction on the first vehicle speed data and the reaction time data to obtain a second performance relationship curve, where the method includes:

Performing discretization distribution processing on the first vehicle speed data to obtain a vehicle speed discrete sequence, acquiring first timestamp data of the vehicle speed discrete sequence, performing discretization distribution processing on the rotating speed data to obtain a rotating speed discrete sequence, acquiring second timestamp data of the rotating speed discrete sequence, performing discretization distribution processing on the reaction time data to obtain a reaction time discrete sequence, and acquiring third timestamp data of the reaction time discrete sequence;

according to the first timestamp data and the second timestamp data, carrying out data alignment on the vehicle speed discrete sequence and the rotating speed discrete sequence, and constructing a plurality of vehicle speed and rotating speed relation point pairs;

according to the first timestamp data and the third timestamp data, carrying out data alignment on the vehicle speed discrete sequence and the reaction time discrete sequence, and constructing a plurality of vehicle speed and reaction time relation point pairs;

and calling a first relation distribution function to perform curve fitting on the plurality of vehicle speed and rotating speed relation point pairs to obtain a first performance relation curve, and calling a second relation distribution function to perform curve fitting on the plurality of vehicle speed and reaction time relation point pairs to obtain a second performance relation curve.

With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, according to a plurality of preset vehicle speed gradient ranges, curve division is performed on the first performance relationship curve and the second performance relationship curve respectively, so as to obtain a first sub-relationship curve and a second sub-relationship curve of each vehicle speed gradient range, where the method includes:

according to a preset vehicle speed gradient threshold value, performing vehicle speed gradient division on the first vehicle speed data to obtain a plurality of vehicle speed gradient ranges;

extracting end values of each vehicle speed gradient range to obtain two end values corresponding to each vehicle speed gradient range;

performing curve segment extraction on the first performance relation curve based on two end point values corresponding to each vehicle speed gradient range to obtain a plurality of first sub-relation curves corresponding to each vehicle speed gradient range, and performing curve segment extraction on the second performance relation curve based on two end point values corresponding to each vehicle speed gradient range to obtain a plurality of second sub-relation curves corresponding to each vehicle speed gradient range;

and carrying out corresponding matching on the vehicle speed gradient ranges of the plurality of first sub-relation curves and the plurality of second sub-relation curves to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range.

With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the extracting curve feature points from the first sub-relationship curve and the second sub-relationship curve of each vehicle speed gradient range to obtain a plurality of first curve feature values and a plurality of second curve feature values corresponding to each vehicle speed gradient range includes:

extracting original curve values of the first sub-relation curves of each vehicle speed gradient range to obtain a plurality of first original curve values, and extracting original curve values of the second sub-relation curves to obtain a plurality of second original curve values;

calculating standard deviations of the plurality of first original curve values to obtain first standard deviations, and calculating standard deviations of the plurality of second original curve values to obtain second standard deviations;

comparing the plurality of first original curve values with the first standard deviation respectively to obtain a first comparison result of each first original curve value, and comparing the plurality of second original curve values with the second standard deviation respectively to obtain a second comparison result of each second original curve value;

and determining a plurality of first curve characteristic values corresponding to each vehicle speed gradient range according to the first comparison result of each first original curve value, and determining a plurality of second curve characteristic values corresponding to each vehicle speed gradient range according to the second comparison result of each second original curve value.

With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, inputting the plurality of first curve feature values and the plurality of second curve feature values corresponding to each vehicle speed gradient range into a preset high speed transmission gear shift analysis model to perform an optimal gear shift point calculation, to obtain an optimal gear shift point corresponding to each vehicle speed gradient range includes:

vector code conversion is carried out on a plurality of first curve characteristic values corresponding to each vehicle speed gradient range to obtain a first initial vector, and vector code conversion is carried out on a plurality of second curve characteristic values to obtain a second initial vector;

vector fusion is carried out on the first initial vector and the second initial vector to obtain a target fusion vector;

inputting the target fusion vector into a preset high-speed transmission gear shift analysis model, wherein the high-speed transmission gear shift analysis model comprises: a bidirectional long and short time memory network, an encoder and a decoder;

extracting features of the target fusion vector through the bidirectional long-short-term memory network to obtain a target feature vector;

inputting the target feature vector into the encoder for feature coding to obtain a target coding vector;

And inputting the target coding vector into the decoder to calculate an optimal shift point, and obtaining the optimal shift point corresponding to each vehicle speed gradient range.

With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, obtaining second vehicle speed data of the target vehicle, and performing intelligent shift of the high speed transmission through the mapping relation model includes:

constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range;

acquiring second vehicle speed data of the target vehicle, and acquiring a vehicle speed gradient range corresponding to the second vehicle speed data;

inputting a vehicle speed gradient range corresponding to the second vehicle speed data into the mapping relation model to perform shift point matching to obtain a target shift point;

and based on the target shift point, intelligent shift is performed on the high-speed transmission.

A second aspect of the present invention provides a data processing apparatus for a high-speed transmission, the data processing apparatus for a high-speed transmission including:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring first vehicle speed data of a target vehicle and acquiring rotating speed data and response time data of a high-speed changer in the target vehicle;

The construction module is used for performing curve fitting on the first vehicle speed data and the rotating speed data to obtain a first performance relation curve, and performing curve construction on the first vehicle speed data and the response time data to obtain a second performance relation curve;

the dividing module is used for respectively carrying out curve division on the first performance relation curve and the second performance relation curve according to a plurality of preset vehicle speed gradient ranges to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range;

the extraction module is used for extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve of each vehicle speed gradient range to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range;

the calculation module is used for inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range into a preset high-speed transmission gear-shifting analysis model to calculate an optimal gear-shifting point, so as to obtain an optimal gear-shifting point corresponding to each vehicle speed gradient range;

and the processing module is used for constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, acquiring second vehicle speed data of the target vehicle and performing intelligent shift of the high-speed transmission through the mapping relation model.

A third aspect of the present invention provides a data processing apparatus for a high-speed transmission, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the data processing apparatus for a high speed transmission to perform the data processing method for a high speed transmission described above.

A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the data processing method for a high-speed transmission described above.

In the technical scheme provided by the invention, the first performance relation curve and the second performance relation curve are respectively subjected to curve division to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range; extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values; inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, so as to obtain optimal gear-shifting points corresponding to each vehicle speed gradient range; the method comprises the steps of constructing a mapping relation model of an optimal gear shifting point and each vehicle speed gradient range, acquiring second vehicle speed data of a target vehicle, performing intelligent gear shifting of the high-speed transmission through the mapping relation model, effectively reducing gear shifting setbacks and vibration problems through intelligent gear shifting and optimizing performance parameters, improving response speed and sensitivity of the transmission, determining the optimal gear shifting point by comprehensively considering vehicle speed, rotating speed and load condition factors, adapting to different road conditions and driving requirements, and extracting characteristic values to perform optimal gear shifting point calculation through establishing a vehicle speed and performance relation curve, so that data processing accuracy of the high-speed transmission is improved.

Drawings

FIG. 1 is a schematic diagram of one embodiment of a data processing method for a high speed transmission in an embodiment of the present invention;

FIG. 2 is a flow chart of curve construction in an embodiment of the present invention;

FIG. 3 is a flow chart of curve partitioning in an embodiment of the present invention;

FIG. 4 is a flow chart of curve feature point extraction in an embodiment of the invention;

FIG. 5 is a schematic diagram of an embodiment of a data processing apparatus for a high speed transmission in accordance with an embodiment of the present invention;

fig. 6 is a schematic diagram of an embodiment of a data processing apparatus for a high-speed transmission in an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a data processing and related device for a high-speed transmission, which are used for improving the data processing accuracy of the high-speed transmission. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation 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 or inherent to such process, method, article, or apparatus.

For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, and an embodiment of a data processing method for a high speed transmission according to the embodiment of the present invention includes:

s101, acquiring first vehicle speed data of a target vehicle, and acquiring rotating speed data and response time data of a high-speed changer in the target vehicle;

it will be appreciated that the execution subject of the present invention may be a data processing apparatus for a high speed transmission, or may be a terminal or a server, and is not limited thereto. The embodiment of the invention is described by taking a server as an execution main body as an example.

Specifically, the server prepares a preset sensor group and connects it to the target vehicle and the high-speed transmission. The sensor group should include sensors that measure vehicle speed, rotational speed, and reaction time. These sensors may include a vehicle speed sensor, an engine speed sensor, a reaction time sensor, and the like. The server configures a data transmission interface of the sensor group. This involves setting up a physical connection between the sensor and the data acquisition system, for example using a cable or a wireless connection. The server also needs to ensure the stability of the transmission interface and the accuracy of the data for subsequent data transmission and analysis. Once the sensor group and the data transmission interface are set, the server performs test data acquisition. And testing the target vehicle and the high-speed transmission by using the sensor group, and recording data such as vehicle speed, rotating speed, reaction time and the like. The data can be transmitted to the data acquisition system in real time, or can be stored in the memory of the sensor group for later transmission. And the server transmits the collected test data to the data collection system through the target data transmission interface. The data acquisition system will receive and store this data for subsequent analysis and processing. This ensures the integrity and accessibility of the data. And the server performs cluster analysis on the target test data by using a preset vehicle speed data tag, a preset rotating speed data tag and a preset reaction time data tag. Cluster analysis is a method of classifying data according to similar features. Through cluster analysis, the server classifies and sorts the test data according to the characteristics of vehicle speed, rotating speed, reaction time and the like. Finally, the server extracts first vehicle speed data, rotating speed data and response time data from the target test data through cluster analysis. These data can be used for further analysis, modeling and optimization. They provide important information about the performance characteristics and operating conditions of the target vehicle. For example, suppose a server is researching the performance of a high speed transmission for an electric vehicle. The server is configured with a suitable sensor group including a vehicle speed sensor, a motor rotation speed sensor, and a reaction time sensor, and is connected with a transmission of the electric vehicle. By configuring the data transmission interface, the server ensures that the sensor data can be accurately transmitted to the data acquisition system. The server performs a series of tests on the electric automobile and records the speed, the motor rotation speed and the response time data under different speeds. The server transmits the data to the data acquisition system via the target data transmission interface. In the data acquisition system, a server performs cluster analysis on target test data by using a preset vehicle speed data tag, a preset rotating speed data tag and a preset reaction time data tag. Through cluster analysis, the server classifies and sorts the test data according to the characteristics of vehicle speed, rotating speed, reaction time and the like. For example, through cluster analysis, the server may obtain different clusters of data representing different operating conditions and performance characteristics. One of the clusters may represent a low speed driving condition, with a lower vehicle speed and rotational speed, and a relatively longer reaction time. Another cluster may represent a high speed driving condition, with higher vehicle speed and rotational speed, and shorter reaction time. Through cluster analysis, the server successfully extracts the first vehicle speed data, the rotating speed data and the response time data.

S102, performing curve fitting on first vehicle speed data and rotation speed data to obtain a first performance relation curve, and performing curve construction on the first vehicle speed data and reaction time data to obtain a second performance relation curve;

specifically, the server performs discretization distribution processing on the first vehicle speed data, and converts the first vehicle speed data into a vehicle speed discrete sequence. This may be achieved by discretizing the continuous vehicle speed data, for example by grouping at intervals or speed ranges, to obtain discrete vehicle speed data points. The server obtains first time stamp data for a discrete sequence of vehicle speed, the time stamp data representing the acquisition time of each vehicle speed data point. The server performs similar discretization distribution processing on the rotating speed data and converts the rotating speed data into a rotating speed discrete sequence. The server obtains second timestamp data of the rotational speed discrete sequence, representing the acquisition time of each rotational speed data point. And the server performs discretization distribution processing on the reaction time data to obtain a reaction time discrete sequence. The server obtains third timestamp data of the discrete sequence of reaction times representing the acquisition time of each reaction time data point. And the server performs data alignment on the vehicle speed discrete sequence and the rotating speed discrete sequence through the first time stamp data and the second time stamp data. This means that corresponding vehicle speed and rotation speed data are matched according to the time stamp, and a plurality of vehicle speed and rotation speed relation point pairs are constructed. And the server performs data alignment on the vehicle speed discrete sequence and the reaction time discrete sequence through the first timestamp data and the third timestamp data, and a plurality of vehicle speed and reaction time relation point pairs are constructed. The server invokes a first relationship distribution function to perform curve fitting on a plurality of vehicle speed and rotating speed relationship point pairs. This may be done using a suitable fitting algorithm, such as least squares, to find the best curve fit, resulting in a first performance relationship. Similarly, the server invokes a second relationship distribution function to curve fit a plurality of vehicle speed and reaction time relationship point pairs. The server fits these pairs of relationship points to a second performance relationship using a suitable fitting algorithm. Through these steps, the server obtains a first performance relationship and a second performance relationship that will provide important information about the relationship between vehicle speed, rotational speed, and reaction time. For example, suppose a server is researching transmission performance for an automobile. The server collects first vehicle speed data, rotation speed data and response time data of the vehicle at different vehicle speeds. The server discretizes the first vehicle speed data and acquires first timestamp data. The server performs discretization processing on the rotation speed data to obtain a rotation speed discrete sequence, and acquires second timestamp data. In addition, the server performs discretization processing on the reaction time data to obtain a reaction time discrete sequence, and acquires third timestamp data. And the server performs data alignment on the vehicle speed discrete sequence and the rotating speed discrete sequence by using the first time stamp data and the second time stamp data, and establishes a plurality of vehicle speed and rotating speed relation point pairs. For example, at a vehicle speed of 30km/h, the corresponding rotational speed is 2000rpm; at a vehicle speed of 50km/h, the corresponding rotational speed is 3000rpm, and so on. And utilizing the first timestamp data and the third timestamp data, and carrying out data alignment on the vehicle speed discrete sequence and the reaction time discrete sequence by the server to construct a plurality of vehicle speed and reaction time relation point pairs. For example, at a vehicle speed of 30km/h, the corresponding reaction time is 0.2 seconds; at a vehicle speed of 50km/h, the corresponding reaction time is 0.15 seconds, and so on. The server fits the vehicle speed and rotation speed relation point pair by using a proper curve fitting method, such as polynomial fitting or curve fitting algorithm, so as to obtain a first performance relation curve. The server knows the relation between the speed and the rotation speed, and further analyzes and optimizes the performance of the high-speed transmission. And fitting the relation point pair of the vehicle speed and the reaction time by using the same curve fitting method to obtain a second performance relation curve. The server knows the relation between the speed and the reaction time and provides a reference basis for intelligent gear shifting of the high-speed transmission. For example, assuming that the server fits a first performance relationship for a vehicle, the rotational speed is found to increase linearly with increasing vehicle speed. This means that every 10km/h of vehicle speed is increased, the rotational speed is increased by 1000rpm. This relationship may help the server predict desired rotational speeds at different vehicle speeds to achieve higher fuel efficiency and performance. The server fits the second performance relationship and finds that the higher the vehicle speed, the shorter the reaction time. For example, at a vehicle speed of 60km/h, the reaction time is 0.1 seconds; at a vehicle speed of 100km/h, the reaction time was 0.08 seconds. This relationship may be used for optimization of the intelligent shift system to provide faster shift response times. By curve fitting the first vehicle speed data and the rotating speed data and constructing the curve of the first vehicle speed data and the response time data, the server can deeply understand the relation among the vehicle speed, the rotating speed and the response time, so that the performance and the gear shifting strategy of the high-speed transmission are optimized. This will improve the driving experience and fuel efficiency of the vehicle and provide a basis for intelligent shift algorithms for high speed variators.

S103, respectively carrying out curve division on the first performance relation curve and the second performance relation curve according to a plurality of preset vehicle speed gradient ranges to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range;

the server divides the first vehicle speed data into a plurality of vehicle speed gradient ranges according to a preset vehicle speed gradient threshold value. For example, the server sets a vehicle speed gradient threshold of 20km/h, then for vehicle speed data [30,40,50,60,70,80,90,100] km/h, it will be divided into three vehicle speed gradient ranges: [30-50] km/h, [60-80] km/h, [90-100] km/h. And extracting end points of each vehicle speed gradient range, namely acquiring the minimum value and the maximum value of each vehicle speed gradient range. For example, in the case of a gradient of vehicle speed in the range of [30-50] km/h, the minimum value is 30km/h and the maximum value is 50km/h. Based on the minimum value and the maximum value of each vehicle speed gradient range, the server performs curve segment extraction on the first performance relation curve to obtain a plurality of first sub-relation curves corresponding to each vehicle speed gradient range. For example, in the case where the gradient range of the vehicle speed is [30-50] km/h, the server extracts a curve segment within the range from the first performance relationship curve. And based on the minimum value and the maximum value of each vehicle speed gradient range, the server performs curve segmentation extraction on the second performance relation curve to obtain a plurality of second sub-relation curves corresponding to each vehicle speed gradient range. And for each vehicle speed gradient range, carrying out corresponding matching on the vehicle speed gradient range on the first sub-relation curve and the second sub-relation curve. The server obtains a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range, and the first sub-relation curve and the second sub-relation curve respectively represent the relation between the vehicle speed, the rotating speed and the reaction time in the range. For example, assume that the server has a first performance relationship for a vehicle that represents the relationship between vehicle speed and rotational speed. The gradient range of the vehicle speed set by the server is [40-60] km/h and [70-90] km/h, and the rotating speed data of the vehicle are as follows: [2000,2500,3000,3500,4000] rpm. The server divides the first vehicle speed data into two vehicle speed gradient ranges according to the vehicle speed gradient threshold value: [40-60] km/h and [70-90] km/h. For the first vehicle speed gradient range [40-60] km/h, it is assumed that the corresponding minimum value is 40km/h and the maximum value is 60km/h. The server extracts curve segments within the range from the first performance relationship, representing a first sub-relationship for a first vehicle speed gradient range. For the second vehicle speed gradient range [70-90] km/h, the corresponding minimum value is assumed to be 70km/h and the maximum value is assumed to be 90km/h. The server extracts curve segments within the range from the first performance relationship, representing a first sub-relationship for a second vehicle speed gradient range. Similarly, the server may also perform curve segment extraction according to the second performance relationship curve, and obtain a second sub-relationship curve corresponding to each vehicle speed gradient range. In this way, the server divides the first performance relationship and the second performance relationship into a plurality of sub-relationships, respectively, each of which represents a performance characteristic over a particular vehicle speed gradient. Such a partitioning and extraction process may help the server more accurately understand vehicle performance characteristics over different vehicle speed ranges and provide a more specific reference basis for further data analysis and optimization.

S104, extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve of each vehicle speed gradient range to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range;

specifically, an original curve value is extracted from a first sub-relation curve of each vehicle speed gradient range, and a plurality of first original curve values are obtained. And extracting original curve values from the second sub-relation curves to obtain a plurality of second original curve values. And calculating standard deviations of the plurality of first original curve values to obtain first standard deviations. And calculating standard deviations of a plurality of second original curve values to obtain second standard deviations. And comparing the plurality of first original curve values with the first standard deviation respectively to obtain a first comparison result of each first original curve value. And comparing the plurality of second original curve values with the second standard deviation to obtain a second comparison result of each second original curve value. And determining a plurality of first curve characteristic values corresponding to each vehicle speed gradient range according to the first comparison result of each first original curve value. And determining a plurality of second curve characteristic values corresponding to each vehicle speed gradient range according to a second comparison result of each second original curve value. By the method, the server extracts curve characteristic points from the first sub-relation curve and the second sub-relation curve of each vehicle speed gradient range, and determines curve characteristic values of each vehicle speed gradient range based on comparison results. These curve characteristic values can be used for further analysis and evaluation to better understand and optimize the performance characteristics of the high speed transmission. For example, assume that the server has a first sub-relationship curve with a vehicle speed gradient in the range of [40-60] km/h, and the raw curve values extracted from the curve include [50,52,55,53,51]. The standard deviation of these original curve values is calculated, resulting in a first standard deviation. And comparing each original curve value with the first standard deviation to obtain a corresponding first comparison result. Assuming a first standard deviation of 2, the comparison result may be expressed as [ -1,0,1, -1, -1]. Based on the comparison results, the server determines that the first curve characteristic value corresponding to the gradient range [40-60] km/h of the vehicle speed is [55]. Similarly, the server performs the same steps for the second sub-relationship. Assuming that the original curve values extracted from the second sub-relation curve of the gradient range [40-60] km/h of the vehicle speed are [0.6,0.8,0.7,0.9,0.5], the standard deviation of the original curve values is calculated to obtain a second standard deviation. And comparing each original curve value with the second standard deviation to obtain a second comparison result. Assuming that the second standard deviation is 0.1, the comparison result can be expressed as [ -1,0,1, -1]. Based on the comparison results, the server determines that the second curve characteristic value corresponding to the gradient range [40-60] km/h of the vehicle speed is [0.8,0.7,0.9]. By such a curve feature point extraction method, the server obtains a plurality of feature values of the first sub-relationship curve and the second sub-relationship curve for each vehicle speed gradient range. These characteristic values may provide quantitative information about the performance characteristics of the high speed transmission, such as the relationship between vehicle speed and rotational speed, the relationship between vehicle speed and reaction time, and the like. This helps to further analyze and optimize the shift performance of the high speed transmission and provides a basis for the development and improvement of intelligent shift algorithms.

S105, inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values corresponding to each vehicle speed gradient range into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, and obtaining an optimal gear-shifting point corresponding to each vehicle speed gradient range;

specifically, the server performs vector code conversion on a plurality of first curve characteristic values corresponding to each vehicle speed gradient range to obtain a first initial vector. For example, in the gradient range of vehicle speed [20-40] km/h, the characteristic value of the first curve is [0.9,0.7,0.8], and the characteristic value is subjected to vector code conversion to obtain a first initial vector [0.9,0.7,0.8]. And performing vector code conversion on the plurality of second curve characteristic values to obtain a second initial vector. The second curve characteristic value is [0.5,0.6,0.4] which is assumed to be in the gradient range [20-40] km/h of the vehicle speed, and the second initial vector [0.5,0.6,0.4] is obtained by vector code conversion. And carrying out vector fusion on the first initial vector and the second initial vector to obtain a target fusion vector. The target fusion vector is obtained by combining the two vectors element by element [0.9,0.7,0.8,0.5,0.6,0.4]. And inputting the target fusion vector into a preset high-speed transmission gear shifting analysis model. The model includes a bi-directional long and short time memory network (BiLSTM), an encoder and a decoder. And then, performing feature extraction on the target fusion vector by using a bidirectional long-short-term memory network to obtain a target feature vector. This feature extraction process may capture time-dependent and contextual information in the vector. And inputting the target feature vector into an encoder for feature coding to obtain a target coding vector. The encoder may further extract the features and convert them into a form suitable for processing by the decoder. And inputting the target coding vector into a decoder to perform optimal shift point calculation. The decoder can predict the optimal shift point from the input feature vector by learning the shift pattern and performance characteristics of the high speed transmission. For example, assume that the first curve characteristic value is [0.9,0.7,0.8] and the second curve characteristic value is [0.5,0.6,0.4] in the vehicle speed gradient range [20-40] km/h. And obtaining a target fusion vector [0.9,0.7,0.8,0.5,0.6,0.4] through vector code conversion and fusion. And inputting the fusion vector into a preset high-speed transmission gear shifting analysis model. And extracting the characteristics of the fusion vector through a bidirectional long-short-time memory network to obtain a target characteristic vector. The feature vector can capture time-dependent and contextual information in the fusion vector. And inputting the target feature vector into an encoder, and performing feature coding to obtain a target coding vector. The encoder performs further feature extraction and conversion of the feature vector into a form suitable for processing by the decoder. And inputting the target coding vector into a decoder, and calculating an optimal shift point. The decoder predicts the optimal shift point corresponding to each vehicle speed gradient range according to the input feature vector by using the learned shift mode and performance feature of the high-speed transmission.

S106, constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, acquiring second vehicle speed data of the target vehicle, and performing intelligent shift of the high-speed transmission through the mapping relation model.

Specifically, a mapping relation model of the optimal gear shifting point and each vehicle speed gradient range is constructed. This model may be built based on historical data, empirical rules, and machine learning methods. By analyzing the optimal shift point data in different vehicle speed gradient ranges, a mapping relationship can be established, so that the corresponding optimal shift point can be predicted in the given vehicle speed gradient range. And acquiring second vehicle speed data of the target vehicle, and determining the vehicle speed gradient range to which the second vehicle speed data belongs. This may be achieved by monitoring the speed of the vehicle in real time and comparing it to a preset vehicle speed gradient range. And inputting a vehicle speed gradient range corresponding to the second vehicle speed data into the mapping relation model, and performing shift point matching. The model can find the corresponding optimal gear shifting point according to the input vehicle speed gradient range. This matching process may be accomplished by a look-up table, a function approximation, or a machine learning algorithm. Based on the target shift point, intelligent shifting is performed for the high speed transmission. And controlling the high-speed transmission to perform gear shifting operation at proper time according to the predicted optimal gear shifting point so as to optimize vehicle performance and fuel economy. For example, assume that the map model predicts that the optimal shift point is 50km/h in the case of a gradient range of vehicle speed [40-60] km/h. When the second vehicle speed data of the target vehicle is in the range, the intelligent gear shifting system controls the high-speed transmission to perform gear shifting operation at 50km/h according to the output of the mapping relation model. By constructing a mapping relation model of an optimal shift point and a vehicle speed gradient range and performing intelligent shift according to real-time data of a target vehicle, a high-speed transmission can make more accurate and reasonable shift decisions according to different driving conditions and different vehicle speed gradient ranges, and driving comfort and fuel economy are improved.

In the embodiment of the invention, a first performance relation curve and a second performance relation curve are respectively subjected to curve division to obtain a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range; extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values; inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, so as to obtain optimal gear-shifting points corresponding to each vehicle speed gradient range; the method comprises the steps of constructing a mapping relation model of an optimal gear shifting point and each vehicle speed gradient range, acquiring second vehicle speed data of a target vehicle, performing intelligent gear shifting of the high-speed transmission through the mapping relation model, effectively reducing gear shifting setbacks and vibration problems through intelligent gear shifting and optimizing performance parameters, improving response speed and sensitivity of the transmission, determining the optimal gear shifting point by comprehensively considering vehicle speed, rotating speed and load condition factors, adapting to different road conditions and driving requirements, and extracting characteristic values to perform optimal gear shifting point calculation through establishing a vehicle speed and performance relation curve, so that data processing accuracy of the high-speed transmission is improved.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Setting a preset sensor group, a target vehicle and a high-speed transmission of the target vehicle, and configuring a data transmission interface of the sensor group to obtain a target data transmission interface;

(2) Test data acquisition is carried out on the target vehicle and the high-speed transmission through the sensor group, and data transmission is carried out through the target data transmission interface, so that target test data are obtained;

(3) And performing cluster analysis on the target test data based on a preset vehicle speed data tag, a preset rotating speed data tag and a preset reaction time data tag to obtain first vehicle speed data, first rotating speed data and first reaction time data.

Specifically, the server connects the preset sensor group arrangement with the target vehicle and the high speed transmission of the target vehicle. The sensor group is configured with a data transmission interface to ensure that the sensor group can effectively communicate and transmit data with the target vehicle and the high-speed transmission. Through this configuration process, the server can obtain the target data transmission interface for subsequent data transmission. And collecting test data of the target vehicle and the high-speed transmission by using the configured sensor group. The sensor group can collect the speed data of the target vehicle under different conditions and the rotating speed data of the high-speed transmission, and the data are transmitted through the target data transmission interface. Through this step, the server acquires target test data including information about the vehicle speed and the rotation speed. And carrying out cluster analysis on the target test data based on a preset vehicle speed data label, a preset rotating speed data label and a preset reaction time data label. Cluster analysis is an unsupervised learning method that can be divided into different categories or clusters based on the similarity of data. Here, the server groups the target test data by using a cluster analysis method, thereby obtaining first vehicle speed data, rotation speed data and reaction time data. For example, it is assumed that the server acquires the vehicle speed data of the target vehicle, the rotational speed data of the high speed transmission, and the reaction time data of the driver by the sensor group in an experiment for performing highway driving. The speed data labels preset by the server comprise low speed, medium speed and high speed, the rotating speed data labels comprise low rotating speed, medium speed and high rotating speed, and the reaction time data labels comprise quick reaction and slow reaction. These data are input into a cluster analysis algorithm, which will group according to the characteristics and similarity of the data. Finally, the server obtains clustering results of the first vehicle speed data, the rotating speed data and the response time data, namely the first vehicle speed data, the rotating speed data and the response time data in different speed ranges. In this embodiment, the server successfully obtains the first vehicle speed data, the rotation speed data and the reaction time data of the target vehicle, and processes and analyzes the data by using cluster analysis. This provides an important data basis for further performance assessment, optimization and decision-making.

In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:

s201, performing discretization distribution processing on first vehicle speed data to obtain a vehicle speed discrete sequence, acquiring first timestamp data of the vehicle speed discrete sequence, performing discretization distribution processing on rotating speed data to obtain a rotating speed discrete sequence, acquiring second timestamp data of the rotating speed discrete sequence, performing discretization distribution processing on reaction time data to obtain a reaction time discrete sequence, and acquiring third timestamp data of the reaction time discrete sequence;

s202, aligning data of a vehicle speed discrete sequence and a rotating speed discrete sequence according to first timestamp data and second timestamp data, and constructing a plurality of vehicle speed and rotating speed relation point pairs;

s203, according to the first timestamp data and the third timestamp data, carrying out data alignment on the vehicle speed discrete sequence and the reaction time discrete sequence, and constructing a plurality of vehicle speed and reaction time relation point pairs;

s204, calling a first relation distribution function to perform curve fitting on a plurality of relation point pairs of the vehicle speed and the rotating speed to obtain a first performance relation curve, and calling a second relation distribution function to perform curve fitting on a plurality of relation point pairs of the vehicle speed and the reaction time to obtain a second performance relation curve.

Specifically, the server performs discretization distribution processing on the first vehicle speed data, and converts continuous vehicle speed data into discrete sequences. This may be achieved by dividing the vehicle speed value by a certain interval or interval. For example, the vehicle speed data is divided into three discrete categories of "low speed", "medium speed" and "high speed". In this process, the server obtains a discrete sequence of vehicle speeds and records corresponding first timestamp data. Then, similar discretization distribution processing is performed on the rotational speed data. The continuous rotational speed data is divided into discrete sequences, such as "low rotational speed", "medium rotational speed", and "high rotational speed". The server acquires the rotating speed discrete sequence and records corresponding second timestamp data. Discretizing the reaction time data to convert continuous reaction time data into discrete sequences. For example, the reaction time data is divided into two discrete categories, namely "fast reaction" and "slow reaction". Through this process, the server obtains a discrete sequence of reaction times and records corresponding third timestamp data. And according to the first time stamp data and the second time stamp data, carrying out data alignment on the vehicle speed discrete sequence and the rotating speed discrete sequence. This means that the two sequences are matched in terms of time stamps, ensuring that they correspond to the respective values at the same point in time. The server builds a plurality of vehicle speed and speed relationship point pairs, wherein each point contains vehicle speed and speed data at the same point in time. Similarly, the discrete sequence of vehicle speeds and the discrete sequence of reaction times are data aligned based on the first time stamp data and the third time stamp data. The server builds a plurality of vehicle speed and reaction time relationship point pairs, wherein each point contains vehicle speed and reaction time data at the same point in time. And calling a first relation distribution function to perform curve fitting on a plurality of relation point pairs of the vehicle speed and the rotating speed to obtain a first performance relation curve. This curve can describe the relationship between the vehicle speed and the rotation speed and reflect the trend of the variation in performance. Similarly, a second relation distribution function is called to perform curve fitting on a plurality of relation point pairs of the vehicle speed and the reaction time, a second performance relation curve is obtained, and the relation between the vehicle speed and the reaction time is described. For example, it is assumed that the server acquires the vehicle speed data, the rotation speed data, and the reaction time data of the target vehicle through the sensor group. The server discretizes the vehicle speed data and divides the vehicle speed data into three categories of low speed, medium speed and high speed. Assume that the server obtains the following discrete sequence of vehicle speeds and corresponding first timestamp data: vehicle speed discrete sequence: [ Low speed, medium speed, high speed, medium speed, high speed ]; first timestamp data: [ t1, t2, t3, t4, t5, t6]. The server performs discretization processing on the rotation speed data and divides the rotation speed data into three categories of low rotation speed, medium rotation speed and high rotation speed. Assume that the server obtains the following discrete sequence of rotational speeds and corresponding second timestamp data: rotational speed discrete sequence: low speed, medium speed, high speed ]; second timestamp data: [ t1, t2, t3, t4, t5, t6]. The server performs data alignment according to the first timestamp data and the second timestamp data, and a vehicle speed and rotating speed relation point pair is constructed: relationship point pairs: [ (low speed, low rotational speed), (medium speed, medium rotational speed), (high speed, high rotational speed), (medium speed, medium rotational speed), (medium speed, high rotational speed), (high speed, high rotational speed) ]. Similarly, the server performs data alignment according to the first timestamp data and the third timestamp data, and builds a vehicle speed and reaction time relation point pair: relationship point pairs: [ (low speed, fast reaction), (medium speed, slow reaction), (high speed, fast reaction), (medium speed, slow reaction), (high speed, slow reaction) ]. And the server calls a first relation distribution function to perform curve fitting on the relation point pair of the vehicle speed and the rotating speed to obtain a first performance relation curve. The curve can describe the relation between the speed of the vehicle and the rotation speed, and helps the server understand the influence of the speed change on the rotation speed. Similarly, the server invokes a second relationship distribution function to perform curve fitting on the vehicle speed and reaction time relationship point pair to obtain a second performance relationship curve. The curve can describe the relation between the speed of the vehicle and the reaction time, and helps the server to know the influence of the speed change on the reaction time. Through the realization, the server obtains a relation model among the speed, the rotating speed and the reaction time, and provides a basis for subsequent high-speed transmission control and intelligent gear shifting. According to the method, the vehicle performance can be analyzed and optimized according to the actual data, and the driving experience and the overall performance of the vehicle are improved.

In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:

s301, performing vehicle speed gradient division on the first vehicle speed data according to a preset vehicle speed gradient threshold value to obtain a plurality of vehicle speed gradient ranges;

s302, extracting end points of each vehicle speed gradient range to obtain two end points corresponding to each vehicle speed gradient range;

s303, performing curve segment extraction on the first performance relation curve based on two end point values corresponding to each vehicle speed gradient range to obtain a plurality of first sub-relation curves corresponding to each vehicle speed gradient range, and performing curve segment extraction on the second performance relation curve based on two end point values corresponding to each vehicle speed gradient range to obtain a plurality of second sub-relation curves corresponding to each vehicle speed gradient range;

s304, carrying out corresponding matching on the vehicle speed gradient ranges of the first sub-relation curves and the second sub-relation curves to obtain the first sub-relation curve and the second sub-relation curve of each vehicle speed gradient range.

Specifically, the server divides the first vehicle speed data into different vehicle speed gradient ranges according to a preset vehicle speed gradient threshold value. Assume that the server has the following first vehicle speed data: first vehicle speed data: [20,30,40,55,60,70,80]. According to a preset vehicle speed gradient threshold value, the server divides the vehicle speed gradient threshold value into three vehicle speed gradient ranges: vehicle speed gradient range 1: [20,30,40]; vehicle speed gradient range 2: [55,60]; vehicle speed gradient range 3: [70,80]. The server performs endpoint extraction for each vehicle speed gradient range, i.e., extracts the minimum and maximum values for each range. Taking a vehicle speed gradient range 1 as an example, the minimum value is 20, and the maximum value is 40; the minimum value of the vehicle speed gradient range 2 is 55, and the maximum value is 60; the minimum value of the vehicle speed gradient range 3 is 70, and the maximum value is 80. Based on the two end values of each vehicle speed gradient range, the server performs curve segment extraction on the first performance relation curve. Assuming that the first performance relationship is a continuous function, the server extracts its segments as: first sub-relationship of vehicle speed gradient range 1: curve segment 1 (20 to 30), curve segment 2 (30 to 40); first sub-relationship of vehicle speed gradient range 2: curve segment 3 (55 to 60); first sub-relationship of vehicle speed gradient range 3: curve segment 4 (70 to 80). Based on the two end values of each vehicle speed gradient range, the server performs curve segment extraction on the second performance relation curve. Assuming that the second performance relationship is also a continuous function, the server extracts its segments as: a second sub-relationship of vehicle speed gradient range 1: curve segment 5 (20 to 40); a second sub-relationship for vehicle speed gradient range 2: curve segment 6 (55 to 60); a second sub-relationship for vehicle speed gradient range 3: curve segment 7 (70 to 80). Through the above operation, the server successfully extracts the first performance relationship curve and the second performance relationship curve in sections and corresponds to each vehicle speed gradient range. For each vehicle speed gradient range, the server obtains a corresponding first sub-relation curve and a corresponding second sub-relation curve, and the performance optimization and intelligent gear shifting control of the high-speed transmission can be further analyzed and applied.

In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:

s401, extracting original curve values of first sub-relation curves of each vehicle speed gradient range to obtain a plurality of first original curve values, and extracting original curve values of second sub-relation curves to obtain a plurality of second original curve values;

s402, calculating standard deviations of a plurality of first original curve values to obtain first standard deviations, and calculating standard deviations of a plurality of second original curve values to obtain second standard deviations;

s403, comparing the plurality of first original curve values with the first standard deviation respectively to obtain a first comparison result of each first original curve value, and comparing the plurality of second original curve values with the second standard deviation respectively to obtain a second comparison result of each second original curve value;

s404, determining a plurality of first curve characteristic values corresponding to each vehicle speed gradient range according to a first comparison result of each first original curve value, and determining a plurality of second curve characteristic values corresponding to each vehicle speed gradient range according to a second comparison result of each second original curve value.

Specifically, the server extracts original curve values of the first sub-relation curves of each vehicle speed gradient range, and a plurality of first original curve values are obtained. And extracting original curve values of the second sub-relation curves to obtain a plurality of second original curve values. These raw curve values represent the curve characteristics over each vehicle speed gradient. And calculating standard deviations of the plurality of first original curve values to obtain first standard deviations. And calculating standard deviations of a plurality of second original curve values to obtain second standard deviations. By comparing each first original curve value with the first standard deviation, a first comparison result of each first original curve value can be obtained. By comparing the plurality of second original curve values with the second standard deviation, a second comparison result of each second original curve value can be obtained. And determining a plurality of first curve characteristic values corresponding to each vehicle speed gradient range according to the first comparison result of each first original curve value. And determining a plurality of second curve characteristic values corresponding to each vehicle speed gradient range according to the second comparison result of each second original curve value. Through the steps, the server extracts key features from the original curve, and obtains relevant feature values of each vehicle speed gradient range according to the comparison result. For example, assume that the server has three vehicle speed gradient ranges: a low-speed gradient range (0-40 km/h), a medium-speed gradient range (40-80 km/h) and a high-speed gradient range (80-120 km/h). And the server extracts original curve values of the first sub-relation curves of each range to obtain three first original curve value sequences. And calculating the standard deviation of the first original curve value to obtain a first standard deviation. And determining a plurality of first curve characteristic values corresponding to each vehicle speed gradient range by comparing each first original curve value with the first standard deviation. And the server extracts an original curve value of the second sub-relation curve, calculates the standard deviation of the second original curve value and obtains a second standard deviation. And determining a plurality of second curve characteristic values corresponding to each vehicle speed gradient range by comparing each second original curve value with a second standard deviation. For example, in the low-speed gradient range, the server extracts the original curve value of the first sub-relationship curve and calculates the standard deviation thereof. By comparing each raw curve value to the standard deviation, the server determines a plurality of first curve characteristic values within the range, such as peak velocity and curve slope. In the low-speed gradient range, the server also extracts the original curve value of the second sub-relationship curve and calculates the standard deviation thereof. By comparing each raw curve value to the standard deviation, the server determines a plurality of second curve characteristic values within the range, such as peak rotational speed and curve volatility. Through such analysis and comparison, the server obtains the relevant curve characteristic values of each vehicle speed gradient range, so as to better understand and describe the variation condition of the vehicle performance in different speed ranges. Such analysis results may provide an important reference for further performance optimization and improvement.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Vector code conversion is carried out on a plurality of first curve characteristic values corresponding to each vehicle speed gradient range to obtain a first initial vector, and vector code conversion is carried out on a plurality of second curve characteristic values to obtain a second initial vector;

(2) Vector fusion is carried out on the first initial vector and the second initial vector to obtain a target fusion vector;

(3) Inputting the target fusion vector into a preset high-speed transmission gear shift analysis model, wherein the high-speed transmission gear shift analysis model comprises: a bidirectional long and short time memory network, an encoder and a decoder;

(4) Extracting features of the target fusion vector through a bidirectional long-short-term memory network to obtain a target feature vector;

(5) Inputting the target feature vector into an encoder for feature coding to obtain a target coding vector;

(6) And inputting the target coding vector into a decoder to calculate an optimal shift point, and obtaining the optimal shift point corresponding to each vehicle speed gradient range.

Specifically, for each vehicle speed gradient range, the server extracts a plurality of first curve characteristic values, and performs vector code conversion on the first curve characteristic values to obtain a first initial vector. Similarly, the server also extracts a plurality of second curve characteristic values and performs vector code conversion to obtain a second initial vector. These initial vectors may represent the curve features in numerical form, providing convenience for subsequent processing. And the server performs vector fusion operation on the first initial vector and the second initial vector to obtain a target fusion vector. Vector fusion the information of the two vectors can be combined into one integrated vector using various methods such as stitching, weighted averaging, etc. The server inputs the target fusion vector into a preset high-speed transmission gear shifting analysis model. The model typically includes a bi-directional long and short term memory network (BiLSTM), an encoder and a decoder. The bidirectional LSTM is used for extracting time sequence characteristics of the target fusion vector, the encoder is used for encoding the time sequence characteristics, and the decoder is used for calculating the optimal shift point. And extracting the characteristics of the target fusion vector through the bidirectional LSTM, and obtaining the target characteristic vector by the server. This vector contains timing characteristics information associated with the vehicle speed gradient range. The server inputs the target feature vector to the encoder for feature encoding. The encoder maps the target feature vector to a lower dimensional vector space to capture the importance and relevance of the feature. And inputting the coded target vector into a decoder to calculate an optimal shift point. And the decoder deduces the optimal shift point corresponding to each vehicle speed gradient range according to the coding representation of the target vector and a preset model structure. Through the process, the server performs feature extraction, fusion and calculation by using the vector representation of the curve features, so that intelligent gear shifting of the high-speed transmission is realized. According to the method, the optimal gear shifting point can be determined in a self-adaptive mode according to different vehicle speed gradient ranges, and therefore vehicle performance and driving experience are improved. For example, assume a case where the gradient of the vehicle speed is in the range of 20-40 km/h. The server extracts a first curve characteristic value (such as average acceleration, throttle response time) and a second curve characteristic value (such as maximum rotation speed, shift time) from the range. These eigenvalues are converted into a first initial vector and a second initial vector, respectively. Let the first initial vector be [0.8,0.5,0.2] and the second initial vector be [5000,250,0.4]. The server performs vector fusion on the two initial vectors, and can adopt a splicing operation. And (5) sequentially splicing the first initial vector and the second initial vector to obtain the target fusion vector [0.8,0.5,0.2,5000,250,0.4]. The server inputs the target fusion vector into a high-speed transmission shift analysis model. And (3) extracting time sequence characteristics of the target fusion vector by using a bidirectional LSTM network in the model. After the model training is assumed, the server obtains the target feature vector [0.2,0.5,0.8,0.4]. And inputting the target feature vector into an encoder for feature encoding. The encoder maps the target feature vector to a lower dimensional vector space, assuming the encoded vector is [0.6,0.3]. And inputting the coded target vector into a decoder to calculate an optimal shift point. And the decoder deduces the optimal shift point corresponding to each vehicle speed gradient range according to the coded target vector and a preset model structure. Wherein it is assumed that the optimal shift point of the decoder output is 30km/h. This means that the recommended optimal shift point is 30km/h at a vehicle speed gradient in the range of 20-40 km/h. Through feature extraction, fusion and calculation of different vehicle speed gradient ranges, the server intelligently determines the optimal gear shifting point according to actual driving conditions. The method can improve the driving smoothness, the fuel efficiency and the overall performance.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) Constructing a mapping relation model of an optimal gear shift point and each vehicle speed gradient range;

(2) Acquiring second vehicle speed data of a target vehicle, and acquiring a vehicle speed gradient range corresponding to the second vehicle speed data;

(3) Inputting a vehicle speed gradient range corresponding to the second vehicle speed data into a mapping relation model to perform shift point matching to obtain a target shift point;

(4) Based on the target shift point, intelligent shifting is performed for the high speed transmission.

Specifically, in order to establish a mapping relationship between the optimal shift point and each vehicle speed gradient range, a server adopts a machine learning method to construct a mapping relationship model. The server gathers a large amount of training data, including speed data of the target vehicle and corresponding optimal shift points. Assume that the server has collected 1000 sets of data, each set of data containing second vehicle speed data and a corresponding optimal shift point. The server divides the data into a training set and a testing set, trains the mapping relation model by the training set, and then evaluates the performance of the model by the testing set. Common mapping models include regression models and classification models. The regression model may predict a continuous optimal shift point value based on the vehicle speed gradient range, while the classification model may divide the vehicle speed gradient range into different discrete categories, each category corresponding to an optimal shift point. Let the server take the regression model as an example. The server trains the mapping relation model using algorithms such as linear regression, decision tree regression, support vector regression, and the like. The model outputs a predicted optimal shift point by inputting a vehicle speed gradient range corresponding to the second vehicle speed data. Assuming that the server is trained using a linear regression model, the following model equation is obtained: optimal shift point = 0.2 vehicle speed gradient +10. The server acquires second vehicle speed data of the target vehicle, and finds a corresponding vehicle speed gradient range according to the second vehicle speed data. The second speed of the target vehicle is assumed to be 35km/h and it is located in a gradient range of 30-40km/h. The server inputs the vehicle speed gradient range into a mapping relation model, and a target shift point is calculated: optimum shift point=0.2×35+10=17. According to the calculation result, the optimal shift point of the target vehicle in the vehicle speed gradient range is 17. Based on the target shift point, the server performs an intelligent shift. According to the vehicle speed and the target gear shifting point, the high-speed transmission can automatically select a proper gear to carry out gear shifting operation, so that smooth driving experience and optimal fuel efficiency are provided.

The data processing method for a high-speed transmission in the embodiment of the present invention is described above, and the data processing apparatus for a high-speed transmission in the embodiment of the present invention is described below, referring to fig. 5, one embodiment of the data processing apparatus for a high-speed transmission in the embodiment of the present invention includes:

an acquisition module 501, configured to acquire first vehicle speed data of a target vehicle, and acquire rotational speed data and reaction time data of a high-speed transmission in the target vehicle;

the construction module 502 is configured to perform curve fitting on the first vehicle speed data and the rotational speed data to obtain a first performance relationship curve, and perform curve construction on the first vehicle speed data and the reaction time data to obtain a second performance relationship curve;

the dividing module 503 is configured to divide the first performance relationship curve and the second performance relationship curve according to a preset plurality of vehicle speed gradient ranges, so as to obtain a first sub-relationship curve and a second sub-relationship curve of each vehicle speed gradient range;

the extracting module 504 is configured to extract curve feature points of the first sub-relationship curve and the second sub-relationship curve of each vehicle speed gradient range, so as to obtain a plurality of first curve feature values and a plurality of second curve feature values corresponding to each vehicle speed gradient range;

The calculating module 505 is configured to input a plurality of first curve feature values and a plurality of second curve feature values corresponding to each vehicle speed gradient range into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, so as to obtain an optimal gear-shifting point corresponding to each vehicle speed gradient range;

and the processing module 506 is configured to construct a mapping relation model of the optimal shift point and each vehicle speed gradient range, obtain second vehicle speed data of the target vehicle, and perform intelligent shift of the high-speed transmission through the mapping relation model.

Through the cooperative cooperation of the components, the first performance relation curve and the second performance relation curve are respectively subjected to curve division, so that a first sub-relation curve and a second sub-relation curve of each vehicle speed gradient range are obtained; extracting curve characteristic points of the first sub-relation curve and the second sub-relation curve to obtain a plurality of first curve characteristic values and a plurality of second curve characteristic values; inputting a plurality of first curve characteristic values and a plurality of second curve characteristic values into a preset high-speed transmission gear-shifting analysis model to perform optimal gear-shifting point calculation, so as to obtain optimal gear-shifting points corresponding to each vehicle speed gradient range; the method comprises the steps of constructing a mapping relation model of an optimal gear shifting point and each vehicle speed gradient range, acquiring second vehicle speed data of a target vehicle, performing intelligent gear shifting of the high-speed transmission through the mapping relation model, effectively reducing gear shifting setbacks and vibration problems through intelligent gear shifting and optimizing performance parameters, improving response speed and sensitivity of the transmission, determining the optimal gear shifting point by comprehensively considering vehicle speed, rotating speed and load condition factors, adapting to different road conditions and driving requirements, and extracting characteristic values to perform optimal gear shifting point calculation through establishing a vehicle speed and performance relation curve, so that data processing accuracy of the high-speed transmission is improved.

The data processing apparatus for a high-speed transmission in the embodiment of the present invention is described in detail above in fig. 5 from the viewpoint of a modularized functional entity, and the data processing device for a high-speed transmission in the embodiment of the present invention is described in detail below from the viewpoint of hardware processing.

Fig. 6 is a schematic structural diagram of a data processing apparatus for a high-speed transmission, where the data processing apparatus 600 for a high-speed transmission may have a relatively large difference due to configuration or performance, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632 according to an embodiment of the present invention. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the data processing apparatus 600 for a high-speed transmission. Still further, the processor 610 may be configured to communicate with a storage medium 630 to execute a series of instruction operations in the storage medium 630 on the data processing apparatus 600 for a high speed transmission.

The data processing apparatus 600 for a high speed transmission may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the data processing apparatus structure for a high speed transmission shown in fig. 6 does not constitute a limitation of the data processing apparatus for a high speed transmission, and may include more or less components than those illustrated, or may combine certain components, or may be a different arrangement of components.

The present invention also provides a data processing apparatus for a high-speed transmission, the data processing apparatus for a high-speed transmission including a memory and a processor, the memory storing computer-readable instructions that, when executed by the processor, cause the processor to perform the steps of the data processing method for a high-speed transmission in the above embodiments.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, having stored therein instructions that, when executed on a computer, cause the computer to perform the steps of the data processing method for a high speed transmission.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The data processing method for the high-speed transmission of the electric automobile is characterized by comprising the following steps of:

acquiring first vehicle speed data of a target vehicle, and acquiring rotating speed data of a motor in the target vehicle and response time data of a high-speed transmission;

2. The data processing method for a high-speed transmission of an electric vehicle according to claim 1, wherein the acquiring first vehicle speed data of a target vehicle and collecting rotational speed data of a motor in the target vehicle and reaction time data of the high-speed transmission includes:

3. The method for processing data of a high-speed transmission of an electric vehicle according to claim 1, wherein the performing curve fitting on the first vehicle speed data and the rotational speed data to obtain a first performance relationship curve, and performing curve construction on the first vehicle speed data and the reaction time data to obtain a second performance relationship curve, includes:

4. The method for processing data of an electric vehicle high-speed transmission according to claim 1, wherein the performing curve division on the first performance relationship curve and the second performance relationship curve according to a plurality of preset vehicle speed gradient ranges to obtain a first sub-relationship curve and a second sub-relationship curve of each vehicle speed gradient range includes:

5. The method for processing data of a high-speed transmission of an electric vehicle according to claim 1, wherein the extracting the curve feature points from the first sub-relationship curve and the second sub-relationship curve of each vehicle speed gradient range to obtain a plurality of first curve feature values and a plurality of second curve feature values corresponding to each vehicle speed gradient range includes:

6. The method for processing data of a high-speed transmission of an electric vehicle according to claim 1, wherein inputting the plurality of first curve characteristic values and the plurality of second curve characteristic values corresponding to each vehicle speed gradient range into a preset high-speed transmission gear shift analysis model to perform an optimal gear shift point calculation, to obtain an optimal gear shift point corresponding to each vehicle speed gradient range, comprises:

7. The data processing method for the high-speed transmission of the electric vehicle according to claim 1, wherein the constructing a mapping relation model of the optimal shift point and each vehicle speed gradient range, obtaining second vehicle speed data of the target vehicle, and performing intelligent shift of the high-speed transmission through the mapping relation model, includes:

8. A data processing apparatus for an electric vehicle high speed transmission, characterized in that the data processing apparatus for an electric vehicle high speed transmission comprises:

the system comprises an acquisition module, a speed control module and a speed control module, wherein the acquisition module is used for acquiring first vehicle speed data of a target vehicle and acquiring rotating speed data of a motor in the target vehicle and response time data of a high-speed changer;

9. A data processing apparatus for an electric vehicle high speed transmission, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invokes the instructions in the memory to cause the data processing apparatus for an electric vehicle high speed transmission to perform the data processing method for an electric vehicle high speed transmission as set forth in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, which when executed by a processor, implement the data processing method for an electric vehicle high speed transmission according to any one of claims 1 to 7.