A method and device for extracting crystallization path spectrum

Abstract

The embodiment of the present application discloses a method and device for extracting a crystallization path spectrum, which screens the actual operating data of the engine of the target vehicle model based on a preset crystallization condition screening rule to obtain crystallization condition data; divides the crystallization condition data into a plurality of pending crystallization condition data based on a preset standard condition length; and then counts the values ​​of the plurality of pending crystallization condition data and the preset index of the crystallization condition data, the preset index being used to represent the distribution characteristics of the counted data, so that the portion closer to the crystallization condition data can be screened out from the plurality of pending crystallization condition data based on the difference between the preset indexes, as a crystallization path spectrum for identifying the actual crystallization condition of the target vehicle model. The crystallization path spectrum thus obtained can represent the actual crystallization condition of the target vehicle model to a greater extent than the self-defined crystallization path spectrum, thereby improving the reliability of the engine performance bench test results of the target vehicle model.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for extracting a crystallization spectrum. Background Art

[0002] The SCR (Selective Catalytic Reduction) system is one of the treatment units widely used in engine exhaust emissions of motor vehicles. Its working principle is: the injected urea undergoes hydrolysis and pyrolysis reactions at high temperatures to generate reducing NH3, which then, under the action of the catalyst, reduces NO in the exhaust gas. X Reduced to N2 and H2O.

[0003] For motor vehicles with SCR systems, the problem of urea crystallization will have a great impact. For example, the deposits of urea crystals will increase the exhaust back pressure of the engine, thus affecting the operation of the engine. In severe cases, it will block the exhaust pipe and cause the engine to fail to operate. Urea crystallization refers to the crystallization of the injected urea on the inner wall of the exhaust pipe. For example, when the actual operating conditions of the engine are frequent parking and low-load operation, the exhaust temperature of the engine is low, which is not conducive to the hydrolysis and thermal decomposition of urea, resulting in urea crystallization.

[0004] The urea crystallization problem needs to be considered in the development and design, improved design and other stages of motor vehicles with SCR systems. Specifically, engine performance bench tests will be used in the above stages to verify whether the current design will have urea crystallization problems by simulating the actual operating conditions of motor vehicles. The tests are continuously adjusted and repeated according to the test results, and finally a design that can reduce the urea crystallization problem is obtained to facilitate subsequent production. In the related technology, R&D engineers customize the crystallization road spectrum, which identifies the actual crystallization conditions of the motor vehicle currently being tested. Specifically, the data of the customized crystallization road spectrum is used as the input parameter of the engine performance bench test to guide the test process, but the customized crystallization road spectrum often cannot represent the actual crystallization conditions well. After the design that can reduce the urea crystallization problem is put into production, there is still a high possibility that urea crystallization problems will occur in actual operation.

[0005] It can be seen that how to improve the reliability of engine performance bench test results is particularly critical to reducing the problem of urea crystallization. Summary of the invention

[0006] In order to solve the above technical problems, the present application provides a method and device for extracting a crystallization path spectrum, which can extract a crystallization path spectrum that can provide reliable input for an engine performance bench test, thereby improving the reliability of the engine performance bench test results.

[0007] The embodiments of the present application disclose the following technical solutions:

[0008] On the one hand, the present application embodiment provides a method for extracting a crystallization path spectrum, the method comprising:

[0009] Obtain the actual operating data of the engine of the target vehicle model;

[0010] Screening the actual operation data based on a preset crystallization condition screening rule to obtain crystallization condition data;

[0011] Dividing the crystallization working condition data into a plurality of to-be-determined crystallization working condition data based on a preset standard working condition length;

[0012] Counting the values ​​of preset indicators of the plurality of pending crystallization condition data to obtain statistical values ​​of the preset indicators; the preset indicators are used to represent the distribution characteristics of the statistically counted data;

[0013] Counting the values ​​of the preset indicators of the crystallization working condition data to obtain reference values ​​of the preset indicators;

[0014] The pending crystallization condition data whose difference between the statistical value of the preset indicator and the reference value of the preset indicator is less than or equal to a preset threshold value is extracted as the crystallization road spectrum of the target vehicle model; the crystallization road spectrum identifies the actual crystallization condition of the target vehicle model.

[0015] On the other hand, an embodiment of the present application provides a device for extracting a crystallization path spectrum, the device comprising an acquisition unit, a screening unit, a standardization unit, a statistical unit and an extraction unit:

[0016] The acquisition unit is used to acquire actual operating data of the engine of the target vehicle type;

[0017] The screening unit is used to screen the actual operation data based on a preset crystallization condition screening rule to obtain crystallization condition data;

[0018] The standardization unit is used to divide the crystallization working condition data into a plurality of crystallization working condition data to be determined based on a preset standard working condition length;

[0019] The statistical unit is used to count the values ​​of the preset indicators of the plurality of pending crystallization condition data to obtain the statistical value of the preset indicators; the preset indicators are used to represent the distribution characteristics of the statistical data;

[0020] The statistical unit is further used to calculate the value of the preset index of the crystallization condition data to obtain a reference value of the preset index;

[0021] The extraction unit is used to extract the pending crystallization condition data whose difference between the statistical value of the preset indicator and the reference value of the preset indicator is less than or equal to a preset threshold value as the crystallization road spectrum of the target vehicle model; the crystallization road spectrum identifies the actual crystallization condition of the target vehicle model.

[0022] In another aspect, an embodiment of the present application provides a computer device, the computer device comprising a processor and a memory:

[0023] The memory is used to store program code and transmit the program code to the processor;

[0024] The processor is used to execute the method for extracting the crystallization path spectrum described in the above aspects according to the instructions in the program code.

[0025] It can be seen from the above technical solution that the actual operating data of the engine of the target vehicle model obtained is screened based on the preset crystallization working condition screening rules to obtain crystallization working condition data; the crystallization working condition data is divided into a plurality of pending crystallization working condition data based on the preset standard working condition length; and then the values ​​of the preset index of the plurality of pending crystallization working condition data and the crystallization working condition data are counted, and the preset index is used to represent the distribution characteristics of the counted data. Therefore, based on the difference between the two in the preset index, the part closer to the crystallization working condition data can be screened out from the plurality of pending crystallization working condition data as the crystallization path spectrum for identifying the actual crystallization working condition of the target vehicle model. The crystallization path spectrum thus obtained can represent the actual crystallization working condition of the target vehicle model to a greater extent than the self-defined crystallization path spectrum, thereby improving the reliability of the engine performance bench test results of the target vehicle model and reducing the possibility of urea crystallization in actual operation after the verified design is put into production. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A method flow chart of a method for extracting a crystallization spectrum provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of the power segment data of the engine provided in the embodiment of the present application;

[0029] Figure 3 A schematic diagram of the working sub-segment data of the engine provided in the embodiment of the present application;

[0030] Figure 4 A data schematic diagram of three types of crystallization conditions of a loader provided in an embodiment of the present application;

[0031] Figure 5 This is the principle diagram of Markov chain;

[0032] Figure 6 Flowchart for Markov Chain Monte Carlo simulation;

[0033] Figure 7 A flow chart of a method for extracting a crystallization spectrum of a loader provided in an embodiment of the present application;

[0034] Figure 8 A device structure diagram of a crystallization spectrum extraction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] Figure 1 A method flow chart of a method for extracting a crystallization spectrum provided in an embodiment of the present application, the method comprising:

[0037] S101: Acquire actual operating data of the engine of the target vehicle model.

[0038] The target vehicle model refers to the vehicle model for which the user currently needs to extract the crystal road spectrum. The actual operating data of the target vehicle model's engine can be extracted from the market big data warehouse. Specifically, the data acquisition equipment is installed on the corresponding vehicle engine in the early stage to collect the actual operating data of the engine, such as the engine's speed, torque and other time series data, and transmit it to the big data platform through the network for storage. When using it, the data of the target vehicle model, market segment and time period can be extracted from the big data warehouse as needed.

[0039] S102: Screening the actual operation data based on preset crystallization condition screening rules to obtain crystallization condition data.

[0040] Based on the preset crystallization operating condition screening rules, the acquired actual operating data of the engine of the target vehicle model is screened to obtain data that meets the preset crystallization operating condition screening rules as the crystallization operating condition data.

[0041] S103: Dividing the crystallization working condition data into a plurality of crystallization working condition data to be determined based on a preset standard working condition length.

[0042] In engineering practice, the engine performance bench test has strict regulations on the length of input data. Therefore, based on the preset standard operating condition length, the obtained crystallization operating condition data is divided into a plurality of pending crystallization operating condition data that meet the standard operating condition length. In a possible implementation, the preset standard operating condition length may be 1800s or 3600s.

[0043] S104: Counting the values ​​of preset indicators of the plurality of pending crystallization condition data to obtain statistical values ​​of the preset indicators.

[0044] S105: Counting the values ​​of the preset indicators of the crystallization condition data to obtain reference values ​​of the preset indicators.

[0045] Based on the preset index, the values ​​of the preset index of the plurality of pending crystallization working condition data are counted to obtain the statistical value of the preset index corresponding to each pending crystallization working condition data; at the same time, the value of the preset index of the crystallization working condition data is counted as a reference value. The preset index is used to represent the distribution characteristics of the data being counted, such as the correlation index between the engine speed and torque, and the engine idle ratio index. Therefore, the value of the preset index obtained by statistics characterizes the distribution characteristics of each crystallization working condition data.

[0046] It is understandable that the preset index can be one or more, and can be set according to the requirements of the crystallization path spectrum that needs to be extracted at present. When the preset index is multiple, the statistical value and reference value of each index need to be counted. In addition, it is understandable that for the execution order of S102-S105, S105 can also be executed after S102, and S104 and S105 can also be executed at the same time, etc., which is not limited here.

[0047] S106: Extracting the pending crystallization condition data whose difference between the statistical value of the preset indicator and the reference value of the preset indicator is less than or equal to a preset threshold as the crystallization road spectrum of the target vehicle model.

[0048] Based on the difference between the pending crystallization condition data and the crystallization condition data between preset indicators, the part closer to the crystallization condition data is screened out from the multiple pending crystallization condition data as a crystallization road spectrum for identifying the actual crystallization condition of the target vehicle model.

[0049] It can be seen that the actual operating data of the engine of the target vehicle model obtained is screened based on the preset crystallization condition screening rules to obtain crystallization condition data; the crystallization condition data is divided into a plurality of pending crystallization condition data based on the preset standard condition length; and then the values ​​of the preset index of the plurality of pending crystallization condition data and the crystallization condition data are counted, and the preset index is used to represent the distribution characteristics of the counted data. Therefore, based on the difference between the two in the preset index, the part closer to the crystallization condition data can be screened out from the plurality of pending crystallization condition data as the crystallization path spectrum for identifying the actual crystallization condition of the target vehicle model. Compared with the self-defined crystallization path spectrum, the technical solution provided in the embodiment of the present application is extracted based on the actual operating data of the engine, and based on the difference in the preset index, the more representative part is screened out from the plurality of pending crystallization condition data, and the crystallization path spectrum obtained thereby can represent the actual crystallization condition of the target vehicle model to a greater extent, thereby improving the reliability of the engine performance bench test results of the target vehicle model, and reducing the possibility of urea crystallization in actual operation after the verified design is put into production. In addition, for engine performance bench tests or for the development and improvement of a project, the engine performance bench resources are limited and the project time is limited. Therefore, based on the differences in preset indicators, more representative crystallization paths are selected from multiple pending crystallization condition data to make the final extracted crystallization path more in line with the actual application scenario, avoiding repeated trial and error and improving efficiency.

[0050] When a vehicle is driving, the process from engine ignition to engine shutdown is called a driving cycle. In a driving cycle, the process of the engine speed starting from idle speed to work and then returning to idle speed is called a work segment. It can be seen that a driving cycle may have many work segments. The specific method is: using idle speed as the basis for division, if the speed returns to idle speed during work and the duration is less than or equal to 10s, it is considered a normal return to idle behavior. If it exceeds 10s, it is considered to have entered the next work segment, and the duration of idling before work is part of the work segment. Figure 2 The figure is a data diagram of the working segment of the engine provided in the embodiment of the present application.

[0051] In a possible implementation, the acquired actual operating data of the engine of the target vehicle type includes time series data of the rotation speed and torque of the engine, and S102 further includes:

[0052] S1021: dividing the actual operation data into N working segments based on the idle speed of the engine; wherein a working segment identifies an operation process in which the engine speed starts working from the idle speed and then returns to the idle speed;

[0053] S1022: Screening the N working segments based on the preset crystallization condition screening rule to obtain the crystallization condition data.

[0054] The engine's idle speed is used as the basis for segmentation, and the acquired actual operation data of the engine is divided into N working segments. Further, each working segment is judged based on the preset crystallization condition screening rules, and the ones that meet the conditions are screened out as crystallization condition data.

[0055] During the driving process of the vehicle, affected by the driving environment (such as road conditions, etc.), the engine speed may not actually be doing work. Therefore, in a possible implementation, S1022 includes:

[0056] Counting the working time of the N working segments;

[0057] Selecting M working segments whose working duration is greater than or equal to a preset reference working duration from the N working segments;

[0058] The M working segments are screened based on the preset crystallization working condition screening rule to obtain the crystallization working condition data.

[0059] Specifically, by counting the working time of each working segment, the working segments with working time greater than or equal to the preset reference working time are selected, and further, the crystallization condition data are selected based on the preset crystallization condition selection rule. In the operation data of a loader engine, the preset reference working time is 10s, and the working segments with working time less than 10s can also be called burrs.

[0060] With the development of non-road stage IV, the engine exhaust emissions of non-road machinery are becoming more and more stringent. During the engine performance bench test, urea crystallization problems of non-stage IV SCR route engines are frequently reported, among which urea crystallization of loaders is the most complicated. The embodiment of this application takes the loader as the starting point, and extracts the crystallization road spectrum of the loader based on the actual operation data of the engines of a large number of loaders on the market.

[0061] In a possible implementation, the target vehicle type is a loader, and the preset crystallization condition screening rules include a first rule, a second rule, and a third rule; further, based on the first rule, the second rule, and the third rule, the N working fragments are screened to obtain first crystallization condition data corresponding to the first rule, second crystallization condition data corresponding to the second rule, and third crystallization condition data corresponding to the third rule.

[0062] The first rule is that the duration of the engine idling is greater than or equal to the first threshold, and the duration of working after the idling is less than or equal to the second threshold; the second rule is that the number of working sub-segments in which the maximum speed of the engine is less than or equal to the third threshold is greater than or equal to the fourth threshold; the third rule is that the duration of the engine idling is greater than or equal to the first threshold, and the duration of working after the idling is less than or equal to the second threshold, and the number of working sub-segments in which the maximum speed of the engine within the working duration is less than or equal to the third threshold is greater than or equal to the fourth threshold. The working sub-segment identifies the operation process in which the engine speed starts working from the idling and then returns to being less than or equal to the fifth threshold, such as Figure 3 As shown, it is a data schematic diagram of the working sub-segment of the engine provided in an embodiment of the present application, wherein 1-9 each identifies a working sub-segment.

[0063] In the operation data of the engine of a loader, the first threshold is 5min, the second threshold is 3min, the third threshold is 1400rpm, the fourth threshold is 60% of the total number of working sub-segments, and the fifth threshold is 1000rpm. The first rule defines the working condition of the loader after long idle and rapid acceleration (referred to as long idle), and the first crystallization condition data selected based on the first rule is the long idle crystallization condition data set; the second rule defines the working condition of the loader while dawdling, and the second crystallization condition data selected based on the second rule is the dawdling crystallization condition data set; the third rule defines the working condition of the loader while long idle and dawdling, and the third crystallization condition data selected based on the third rule is the long idle and dawdling crystallization condition data set.

[0064] like Figure 4 As shown, it is a data schematic diagram of three types of crystallization conditions of a loader provided in an embodiment of the present application; wherein, Figure 4 (a) is a schematic diagram of long idle speed. Figure 4 (b) is a schematic diagram of slacking off. Figure 4 (c) is a schematic diagram of long idle and slacking off.

[0065] It is understandable that, in order to improve the efficiency of data processing, the acquired actual operation data may be preprocessed before screening the crystallization condition data. Specifically, S102 further includes:

[0066] S1021: performing data cleaning on the actual operation data to obtain cleaned actual operation data;

[0067] S1022: Screening the actual operation data after cleaning based on preset crystallization condition screening rules to obtain the crystallization condition data.

[0068] In a possible implementation, the performing data cleaning on the actual operation data includes:

[0069] Deleting data representing the start and stop of the engine in the actual operation data;

[0070] Abnormal data in the actual operation data is deleted, and linear interpolation processing is performed on the null value data.

[0071] In a possible implementation, the typical working condition extraction algorithm of Markov chain Monte Carlo simulation can also be used to extract the crystallization path spectrum. The typical working condition extraction algorithm framework based on Markov chain Monte Carlo simulation is a relatively popular method in the field of working condition extraction at home and abroad. This method can reproduce the transfer relationship between various working conditions in actual operation in the market through the transfer matrix. The extracted typical working conditions not only retain the actual operating characteristics of this market segment to the greatest extent based on probability, but also avoid the deviation caused by the subjective experience of engineers.

[0072] like Figure 5 The figure shows the principle diagram of Markov chain. The Markov property is briefly described as follows: if the state of the process or system at time t0 is known, then the conditional distribution of the state at time t>t0 is independent of the state of the process before time t0, that is, when a random process is given the current state and all past states, the conditional probability distribution of its future state depends only on the current state, that is, when the current state is known, the past and the future are independent of each other, then this random process has the Markov property or no aftereffect. A process with Markov property is usually called a Markov process, which can be expressed by the following formula:

[0073] The discrete time set T = {n = 0, 1, 2, ...}, its corresponding X n The state space composed of all possible values ​​is a discrete state set I = {i0, i1, i2...i n+1 ∈I}. If for a random variable {X(t), n∈T}, for any non-negative integer n∈T and any i0, i1, i2...i n+1 ∈T, we have the following formula:

[0074] P{X n+1 =i n+1 |X0=i0,X1=i1,...,X n =i n}=P{X n+1 =i n+1 |X n =i n )

[0075] The operating point of the vehicle during operation can be regarded as a random variable that changes with time and can be defined as a random process; this can be expressed as follows: the operating point at the next moment is only related to the state of the vehicle at the current moment, and has nothing to do with the vehicle state before that, that is, the vehicle operating condition has Markov properties. The time series data of the vehicle's engine operating condition can be expressed as the phase plane motion of the speed and torque state. According to the Markov property of the vehicle's operating condition, the state composed of the speed and torque conditions can be used to express the transfer relationship of the vehicle's operating condition. Furthermore, by encoding the speed and torque state, the two-dimensional spatial information is converted to one-dimensional, that is, the two-dimensional information of speed and torque is retained, and the time series relationship of the vehicle's operating condition is expressed as a one-dimensional state transfer relationship, and a state transfer matrix is ​​obtained. In this way, based on the actual operating data of the engine of the target vehicle model that is real, effective and large enough, the "operating condition transfer relationship gene spectrum" of the actual market data of the target vehicle model's market segment can be obtained. For example Figure 6 The figure shows a flow chart of Markov chain Monte Carlo simulation, which specifically includes: inputting the crystallization condition data obtained through screening into the crystallization path spectrum extraction model, performing Monte Carlo simulation, and combining the preset crystallization condition screening rules corresponding to the crystallization condition data obtained through screening, and finally obtaining the crystallization path spectrum corresponding to the crystallization condition data.

[0076] It is understandable that the input data of the model is very important, because the model will output corresponding results according to the characteristics of the input data. Therefore, in a possible implementation, the long idle crystallization condition data set, the dawdling crystallization condition data set, and the long idle and dawdling crystallization condition data set are respectively input into the corresponding models to obtain the corresponding long idle crystallization spectrum, dawdling crystallization spectrum, and long idle and dawdling crystallization spectrum. Figure 7 As shown, it is a flow chart of a method for extracting a crystallization path spectrum of a loader provided in an embodiment of the present application.

[0077] It should be noted that although the three models of long idle crystallization road spectrum extraction model, slacking crystallization road spectrum extraction model, and long idle and slacking crystallization road spectrum extraction model are all based on the theoretical framework of Markov chain Monte Carlo simulation, in order to make the extracted crystallization road spectrum conform to the characteristics of the corresponding input data set, adaptive adjustments have been made to the models respectively. The specific adjustments are as follows:

[0078] The first category: long idle crystallization road spectrum extraction model.

[0079] The input data of the long idle crystallization road spectrum extraction model is the long idle crystallization condition data set. After state encoding, the state space and state transfer matrix of the long idle crystallization condition data set are obtained. The state transfer matrix can characterize the transfer relationship between all long idle crystallization condition characteristics. Based on the state transfer matrix, Monte Carlo simulation is performed to generate state sequence data.

[0080] The state sequence data generated by the Monte Carlo simulation is decoded to obtain the first candidate road spectrum data, and according to the screening rule of the long idle crystallization condition data set, that is, according to the first rule, the first candidate road spectrum data is segmented into working segments, the working sub-segments within the working segments are judged, and the working segment duration is judged, so as to screen out the first candidate road spectrum data that contains the valid information of the long idle crystallization condition;

[0081] Based on the preset standard operating condition length, first candidate road spectrum data with the standard operating condition length and containing valid information of the long idle crystallization condition is screened and obtained as the first to-be-determined crystallization road spectrum;

[0082] The first pending crystallization spectrum is extracted for preset indicators, and compared and ranked with the statistical values ​​of various preset indicators of the market big data, and the one with the best performance is selected as the long idle crystallization spectrum; the long idle crystallization spectrum is used to identify the actual crystallization condition of the loader when working at long idle.

[0083] The second category: the slow crystallization spectrum extraction model.

[0084] The input data of the Moyanggong crystallization spectrum extraction model is the Moyanggong crystallization condition data set. After state encoding, the state space and state transfer matrix of the Moyanggong crystallization condition data set are obtained. The state transfer matrix can characterize the transfer relationship between all Moyanggong crystallization condition characteristics. Based on the state transfer matrix, Monte Carlo simulation is performed to generate state sequence data.

[0085] The state sequence data generated by the Monte Carlo simulation is decoded to obtain the second candidate path spectrum data, and according to the screening rule of the dawdling crystallization condition data set, that is, according to the second rule, the second candidate path spectrum data is segmented into working segments, the working sub-segments within the working segments are judged, and the working segment duration is judged, so as to screen out the second candidate path spectrum data that contains the valid information of the dawdling crystallization condition;

[0086] Based on the preset standard working condition length, second candidate path spectrum data with the standard working condition length and containing effective information of the slow working crystallization condition is screened and obtained as the second pending crystallization path spectrum;

[0087] The preset indicators are extracted from the second pending crystallization path spectrum, and compared and ranked with the statistical values ​​of various preset indicators of the market big data, and the one with the best performance is selected as the slacking crystallization path spectrum; the slacking crystallization path spectrum is used to identify the actual crystallization condition of the loader when it is slacking off.

[0088] The third category: long idling and slow crystallization road spectrum extraction model.

[0089] The input data of the long idle and slacking crystallization road spectrum extraction model is the long idle and slacking crystallization working condition data set. After state encoding, the state space and state transfer matrix of the long idle and slacking crystallization working condition data set are obtained. The state transfer matrix can characterize the transfer relationship between all long idle and slacking crystallization working condition characteristics; based on the state transfer matrix, Monte Carlo simulation is performed to generate state sequence data;

[0090] The state sequence data generated by the Monte Carlo simulation is decoded to obtain the third candidate road spectrum data, and according to the screening rule of the long idle and dawdling crystallization working condition data set, that is, according to the third rule, the third candidate road spectrum data is segmented into working segments, the working sub-segments within the working segments are judged, and the working segment duration is judged, so as to screen out the third candidate road spectrum data that contains the valid information of the long idle and dawdling crystallization working condition;

[0091] Based on the preset standard operating condition length, third candidate road spectrum data with the standard operating condition length and containing valid information of long idle and dawdling crystallization conditions is screened and obtained as the third pending crystallization road spectrum;

[0092] The preset indicators are extracted from the third pending crystallization spectrum, and the performance is compared and ranked with the statistical values ​​of various preset indicators of the market big data, and the best performance is selected as the long idle and slacking crystallization spectrum; the long idle and slacking crystallization spectrum is used to identify the actual crystallization condition of the loader under the condition of long idle and slacking work.

[0093] Input the crystallization condition data into the crystallization path extraction model to generate the crystallization path results and compare the results with the market big data indicators. The proportion of each condition is clear at a glance. The crystallization path is as close to the actual crystallization operating conditions as possible, which can provide actual input for forward development and avoid guessing, artificial construction, and custom crystallization path misleading R&D engineers.

[0094] Figure 8 The device structure diagram of a crystallization spectrum extraction device provided in an embodiment of the present application includes an acquisition unit 801, a screening unit 802, a standardization unit 803, a statistics unit 804 and an extraction unit 805:

[0095] The acquisition unit 801 is used to acquire actual operating data of the engine of the target vehicle type;

[0096] The screening unit 802 is used to screen the actual operation data based on a preset crystallization condition screening rule to obtain crystallization condition data;

[0097] The standardization unit 803 is used to divide the crystallization working condition data into a plurality of crystallization working condition data to be determined based on a preset standard working condition length;

[0098] The statistical unit 804 is used to count the values ​​of the preset indicators of the plurality of pending crystallization condition data to obtain the statistical value of the preset indicators; the preset indicators are used to represent the distribution characteristics of the statistically counted data;

[0099] The statistical unit 804 is further used to calculate the value of the preset index of the crystallization condition data to obtain a reference value of the preset index;

[0100] The extraction unit 805 is used to extract the pending crystallization condition data whose difference between the statistical value of the preset indicator and the reference value of the preset indicator is less than or equal to a preset threshold value as the crystallization road spectrum of the target vehicle model; the crystallization road spectrum identifies the actual crystallization condition of the target vehicle model.

[0101] In a possible implementation, the standardization unit is further used to divide the actual operation data into N working segments based on the idle speed of the engine; wherein a working segment identifies the operation process in which the speed of the engine starts working from the idle speed and then returns to the idle speed;

[0102] The screening unit is further used to screen the N working fragments based on the preset crystallization condition screening rule to obtain the crystallization condition data.

[0103] In a possible implementation, the statistical unit is further used to count the working durations of the N working segments;

[0104] The screening unit is further used to screen out M working segments whose working duration is greater than or equal to a preset reference working duration from the N working segments;

[0105] The screening unit is further used to screen the M working fragments based on the preset crystallization condition screening rule to obtain the crystallization condition data.

[0106] In a possible implementation, if the target vehicle type is a loader, the preset crystallization condition screening rule includes a first rule, a second rule and a third rule; the screening unit is further used to screen the N working segments based on the first rule, the second rule and the third rule to obtain first crystallization condition data corresponding to the first rule, second crystallization condition data corresponding to the second rule and third crystallization condition data corresponding to the third rule;

[0107] The first rule is that the idling duration of the engine is greater than or equal to a first threshold, and the working duration after idling is less than or equal to a second threshold;

[0108] The second rule is that the number of working sub-segments in which the maximum speed of the engine is less than or equal to the third threshold is greater than or equal to the fourth threshold; the working sub-segment identifies the operation process in which the speed of the engine starts working from the idle speed and then returns to being less than or equal to the fifth threshold;

[0109] The third rule is that the idling duration of the engine is greater than or equal to the first threshold, the working duration after the idling is less than or equal to the second threshold, and the number of working sub-segments in which the maximum speed of the engine within the working duration is less than or equal to the third threshold is greater than or equal to the fourth threshold.

[0110] In a possible implementation, the device also includes a preprocessing unit, which is used to perform data cleaning on the actual operation data to obtain the cleaned actual operation data; then, the screening unit is also used to screen the cleaned actual operation data based on preset crystallization condition screening rules to obtain the crystallization condition data.

[0111] In a possible implementation, the preprocessing unit is further used to delete data in the actual operation data that characterizes the start and shutdown of the engine; the preprocessing unit is further used to delete abnormal data in the actual operation data and perform linear interpolation processing on null value data.

[0112] The present application also provides a computer device, which includes a processor and a memory:

[0113] The memory is used to store program code and transmit the program code to the processor;

[0114] The processor is used to execute the method for extracting the crystallization path spectrum described in the above aspects according to the instructions in the program code.

[0115] It is understandable that the method for extracting the crystallization path spectrum provided in the embodiment of the present application can be implemented by the above-mentioned computer device, which can be a terminal device or a server, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Terminal devices include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, etc. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0116] It can be seen that the actual operating data of the engine of the target vehicle model obtained is screened based on the preset crystallization working condition screening rules to obtain crystallization working condition data; the crystallization working condition data is divided into a plurality of pending crystallization working condition data based on the preset standard working condition length; and then the values ​​of the preset index of the plurality of pending crystallization working condition data and the crystallization working condition data are counted, and the preset index is used to represent the distribution characteristics of the counted data. Therefore, based on the difference between the preset indexes of the two, the part closer to the crystallization working condition data can be screened out from the plurality of pending crystallization working condition data as the crystallization path spectrum for identifying the actual crystallization working condition of the target vehicle model. The crystallization path spectrum thus obtained can represent the actual crystallization working condition of the target vehicle model to a greater extent than the self-defined crystallization path spectrum, thereby improving the reliability of the engine performance bench test results of the target vehicle model and reducing the possibility of urea crystallization in actual operation after the verified design is put into production.

[0117] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0119] The above is a detailed introduction to a method and device for extracting a crystallization spectrum provided in the embodiment of the present application. The principle and implementation method of the present application are described in detail using specific examples herein. The description of the above embodiments is only used to help understand the method of the present application. At the same time, for those skilled in the art, according to the method of the present application, there will be changes in the specific implementation method and application scope.

[0120] In summary, the content of this specification should not be understood as limiting the present application, and any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in this application should be included in the protection scope of this application. Moreover, based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

Claims

1. A method for extracting a crystallization path spectrum, characterized in that: The method comprises: Obtain the actual operating data of the engine of the target vehicle model; Screening the actual operation data based on a preset crystallization condition screening rule to obtain crystallization condition data; Dividing the crystallization working condition data into a plurality of to-be-determined crystallization working condition data based on a preset standard working condition length; Counting the values ​​of preset indicators of the plurality of pending crystallization condition data to obtain a statistical value of the preset indicator; the preset indicator is used to represent the distribution characteristics of the statistically counted data; Counting the values ​​of the preset indicators of the crystallization working condition data to obtain reference values ​​of the preset indicators; Extracting the pending crystallization condition data for which the difference between the statistical value of the preset index and the reference value of the preset index is less than or equal to a preset threshold as the crystallization road spectrum of the target vehicle type; the crystallization road spectrum identifies the actual crystallization condition of the target vehicle type; The actual operation data includes time series data of the rotation speed and torque of the engine. Then, the actual operation data is screened based on a preset crystallization condition screening rule to obtain crystallization condition data, including: Dividing the actual operation data into N working segments based on the idle speed of the engine; wherein a working segment identifies the operation process in which the engine speed starts working from the idle speed and then returns to the idle speed; Screening the N working fragments based on the preset crystallization working condition screening rule to obtain the crystallization working condition data; If the target vehicle type is a loader, the preset crystallization working condition screening rule includes a first rule, a second rule and a third rule, and the N working segments are screened based on the preset crystallization working condition screening rule to obtain the crystallization working condition data, including: Screening the N working segments based on the first rule, the second rule, and the third rule to obtain first crystallization working condition data corresponding to the first rule, second crystallization working condition data corresponding to the second rule, and third crystallization working condition data corresponding to the third rule; The first rule is that the idling duration of the engine is greater than or equal to a first threshold, and the working duration after idling is less than or equal to a second threshold; The second rule is that the number of working sub-segments in which the maximum speed of the engine is less than or equal to the third threshold is greater than or equal to the fourth threshold; the working sub-segment identifies the operation process in which the speed of the engine starts working from the idle speed and then returns to being less than or equal to the fifth threshold; The third rule is that the idling duration of the engine is greater than or equal to the first threshold, the working duration after the idling is less than or equal to the second threshold, and the number of working sub-segments in which the maximum speed of the engine within the working duration is less than or equal to the third threshold is greater than or equal to the fourth threshold.

2. The method according to claim 1, characterized in that The step of screening the N working segments based on a preset crystallization condition screening rule to obtain crystallization condition data includes: Counting the working time of the N working segments; Filter out M working segments whose working duration is greater than or equal to a preset reference working duration from the N working segments; The M working segments are screened based on the preset crystallization working condition screening rule to obtain the crystallization working condition data.

3. The method according to claim 1, characterized in that The actual operation data is screened based on a preset crystallization condition screening rule to obtain crystallization condition data, including: Performing data cleaning on the actual operation data to obtain cleaned actual operation data; The actual operation data after cleaning is screened based on preset crystallization condition screening rules to obtain the crystallization condition data.

4. The method according to claim 3, characterized in that The performing data cleaning on the actual operation data includes: Deleting data representing the start and stop of the engine in the actual operation data; Abnormal data in the actual operation data is deleted, and linear interpolation processing is performed on the null value data.

5. A device for extracting a crystallization path spectrum, characterized in that: The device comprises an acquisition unit, a screening unit, a standardization unit, a statistics unit and an extraction unit: The acquisition unit is used to acquire actual operating data of the engine of the target vehicle type; The screening unit is used to screen the actual operation data based on a preset crystallization condition screening rule to obtain crystallization condition data; The standardization unit is used to divide the crystallization working condition data into a plurality of crystallization working condition data to be determined based on a preset standard working condition length; The statistical unit is used to count the values ​​of the preset indicators of the plurality of pending crystallization condition data to obtain the statistical value of the preset indicators; The preset indicators are used to represent the distribution characteristics of the statistical data; The statistical unit is further used to calculate the value of the preset index of the crystallization condition data to obtain a reference value of the preset index; The extraction unit is used to extract the pending crystallization condition data for which the difference between the statistical value of the preset indicator and the reference value of the preset indicator is less than or equal to a preset threshold value as the crystallization road spectrum of the target vehicle model; the crystallization road spectrum identifies the actual crystallization condition of the target vehicle model; The actual operation data includes time series data of the rotation speed and torque of the engine, then, the standardization unit is further used to divide the actual operation data into N working segments based on the idle speed of the engine; wherein a working segment identifies the operation process of the engine starting from the idle speed to work and then returning to the idle speed; The screening unit is further used to screen the N working fragments based on the preset crystallization working condition screening rule to obtain the crystallization working condition data; If the target vehicle type is a loader, the preset crystallization condition screening rule includes a first rule, a second rule and a third rule, and the screening unit is further used to screen the N working segments based on the first rule, the second rule and the third rule to obtain first crystallization condition data corresponding to the first rule, second crystallization condition data corresponding to the second rule and third crystallization condition data corresponding to the third rule; The first rule is that the idling duration of the engine is greater than or equal to a first threshold, and the working duration after idling is less than or equal to a second threshold; The second rule is that the number of working sub-segments in which the maximum speed of the engine is less than or equal to the third threshold is greater than or equal to the fourth threshold; the working sub-segment identifies the operation process in which the speed of the engine starts working from the idle speed and then returns to being less than or equal to the fifth threshold; The third rule is that the idling duration of the engine is greater than or equal to the first threshold, the working duration after the idling is less than or equal to the second threshold, and the number of working sub-segments in which the maximum speed of the engine within the working duration is less than or equal to the third threshold is greater than or equal to the fourth threshold.

6. The device according to claim 5, characterized in that The statistical unit is also used to count the working time of the N working segments; The screening unit is further used to screen out M working segments whose working duration is greater than or equal to a preset reference working duration from the N working segments; The screening unit is further used to screen the M working fragments based on the preset crystallization condition screening rule to obtain the crystallization condition data.

7. A computer device, characterized in that: The computer device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the method according to any one of claims 1 to 4 according to the instructions in the program code.

Images