Downsampling method

Abstract

To provide a downsampling method which accurately performs downsampling of traveling data.SOLUTION: A traveling data downsampling method using machine learning includes steps of: acquiring traveling data; calculating a predetermined feature quantity of the traveling data; generating cutout data by using a window from the traveling data; calculating an error between appearance frequencies of the feature quantity of the traveling data and the feature quantity of the cutout data; and setting time length and a position of the window by a randomized method in a manner to make the error a predetermined value or less.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] This disclosure relates to a downsampling method.

Background Art

[0002] When a vehicle is running, collecting and storing the running data can be used for various information processing. Since the running data accumulated over a long period of time becomes a huge amount of data, a technology for compressing the running data is required. For example, Patent Document 1 discloses an invention for compressing running data by outputting vehicle speed data when the vehicle speed becomes equal to the set vehicle speed and when the change in vehicle speed becomes an inflection point.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, the accuracy of the compressed vehicle speed data is not sufficient. To efficiently compress the running data, it is advisable to shorten the sampling time as much as possible. However, if the sampling time is too short, the accuracy may decrease.

[0005] One aspect of this disclosure aims to accurately perform downsampling of running data in view of the above technical problems.

Means for Solving the Problems

[0006] A downsampling method according to one aspect of the present disclosure includes the steps of: acquiring driving data; calculating predetermined features for the driving data; generating extracted data from the driving data using a window; calculating the error between the frequency of occurrence of features in the driving data and the frequency of occurrence of features in the extracted data; and setting the time length and position of the window by a randomization method so that the error is less than or equal to a predetermined value. [Effects of the Invention]

[0007] According to one aspect of this disclosure, it is possible to perform downsampling of driving data with high accuracy. [Brief explanation of the drawing]

[0008] [Figure 1] This flowchart shows an example of a downsampling method. [Figure 2] This figure shows an example of a feature. [Figure 3] This flowchart shows an example of a fault prediction method. [Modes for carrying out the invention]

[0009] Hereinafter, embodiments of this disclosure will be described with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant descriptions will be omitted.

[0010] [Embodiment] One embodiment of the present disclosure is a method for downsampling driving data using artificial intelligence (AI). In this embodiment, the downsampling method calculates predetermined features for the entire driving data, compares the frequency of occurrence of the features for the entire driving data with the frequency of occurrence of the features for the extracted data extracted from the driving data, and selects the extracted data such that the error in the frequency of occurrence is less than or equal to a predetermined value.

[0011] In the downsampling method, when extracting data from the driving data, a randomized window with arbitrarily set time length and position is used. In the randomized method, a window of any length may be set. Also, in the randomized method, a window may be set at any position.

[0012] Furthermore, for example, the randomized window setting may be performed by fixing the total window time. Alternatively, the randomized window setting may be performed after extending the total window time. In this case, the proportion of the extended time may be increased when the error in the frequency of occurrence is large. Moreover, for example, the randomized window setting may be performed such that the error in the sum of the features is less than or equal to a predetermined value.

[0013] Various metrics can be used to measure the error in frequency of occurrence. For example, the error in frequency of occurrence may be measured using the Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), etc.

[0014] <Driving Data> In this embodiment, the target of processing is driving data acquired from a drive system used in a hybrid vehicle. This type of drive system is disclosed, for example, in Reference 1. [Reference 1] Japanese Patent Publication No. 2008-232287

[0015] The drive device disclosed in Reference 1 is configured as follows: The drive device has a plurality of multi-plate clutches. Each multi-plate clutch has a cancellation chamber. The plurality of multi-plate clutches may share one cancellation chamber.

[0016] Among a plurality of multi-plate clutches, one multi-plate clutch is configured to include a clutch drum, a clutch piston, a clutch hub, a return spring, and a cancel plate. The clutch drum is a bottomed cylindrical member connected to integrally rotate with the first intermediate shaft, and a plurality of annular friction plates are spline-engaged with its inner peripheral surface so as to integrally rotate. The clutch piston is disposed within the clutch drum and forms a hydraulic chamber between itself and the clutch drum. The clutch hub is a cylindrical member having a cylindrical portion facing the inner peripheral surface of the cylindrical portion of the clutch drum and is connected to integrally rotate with the second intermediate shaft, and a plurality of annular friction mating plates are spline-engaged with its outer peripheral surface so as to integrally rotate.

[0017] The running data is output from a control device (ECU; Electronic Control Unit) that controls the operation of the drive device. Data such as vehicle speed, throttle opening, shift position, oil temperature of the power transmission mechanism, and mode select switch is input to the control device, for example. The control device controls the operation of the drive device based on the input data. Torque of the motor generator, electric oil pump, line pressure, engagement pressure, etc. are output from the control device, for example. A plurality of engagement pressures are output corresponding to each friction material within the drive device.

[0018] In the present embodiment, the running data is uploaded to an external storage device via a wireless communication network such as a mobile phone network. The external storage device may be, for example, a cloud storage service provided by cloud computing. Running data is uploaded to the external storage device from various vehicles, and big data is constructed.

[0019] <Downsampling Method> The downsampling method in the present embodiment will be described while referring to FIG. 1. FIG. 1(A) is a flowchart showing an example of the downsampling method.

[0020] The downsampling method in this embodiment is executed by an information processing device realized by a computer or the like. The information processing device includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a HDD (Hard Disk Drive), an input device, an output device, an external I / F (interface), a communication I / F, etc., and each is interconnected by a system bus.

[0021] In step S101, the information processing device acquires the running data acquired in each running mode. As an example, the running modes may include an urban mode, a highway mode, a mountainous area mode, etc.

[0022] In step S102, the information processing device combines the running data of each running mode acquired in step S101 to generate one piece of running data. Hereinafter, the combined running data is referred to as "overall data". When evaluating parts, it is necessary to create an evaluation mode considering all the usage methods, so it is necessary to combine the running data of each running mode. As an example, the purpose of the evaluation may be to calculate the damage rate.

[0023] In step S103, the information processing device performs machine learning on the overall data generated in step S102 and clusters it.

[0024] In step S104, the information processing device calculates a predetermined feature amount (explanatory variable) for the overall data clustered in step S103. As an example, the explanatory variable may include the number of engagements of the friction material for shifting, the engagement torque, the oil temperature, the relative rotational speed during idling, etc.

[0025] In step S105, the information processing device cuts out N pieces of data with a time series length of TL from the overall data using a window with a variable time length. Hereinafter, the cut-out running data is referred to as "cut-out data".

[0026] In step S106, the information processing device calculates the frequency of occurrence of the feature calculated in step S104 for each of the extracted data points obtained in step S105.

[0027] In step S107, the information processing device calculates the error between the frequency of occurrence of features in the overall data and the frequency of occurrence of features in the extracted data. Next, the information processing device determines whether the error is less than a predetermined value. If the error is less than the predetermined value (YES), the information processing device proceeds to step S108. On the other hand, if the error is greater than or equal to the predetermined value (NO), the information processing device returns to step S105.

[0028] After returning to step S105, the information processing device changes the window length TL and the window position using a randomization method and extracts N data again. In this way, the information processing device repeats the extraction of data while adjusting the window length TL and the window position until the error in the frequency of feature occurrences falls below a predetermined value.

[0029] In step S108, the information processing device selects the N extracted data points from step S105 as the compressed driving data.

[0030] Figure 1(B) is a flowchart showing an example of the data extraction process (step S105 in Figure 1(A)).

[0031] In step S111, the information processing device determines whether the counter Sk is greater than a predetermined value S1. If the counter Sk is greater than the predetermined value S1 (YES), the information processing device proceeds to step S115. On the other hand, if the counter Sk is less than or equal to the predetermined value S1 (NO), the information processing device proceeds to step S112.

[0032] In step S112, the information processing device fixes (maintains) the total time of the window.

[0033] In step S113, the information processing device changes the time length and position of each window using a randomization method.

[0034] In step S114, 1 is added to the counter Sk.

[0035] In step S115, the information processing device determines whether the counter Sh is greater than a predetermined value S2. If the counter Sh is greater than the predetermined value S2 (YES), the information processing device proceeds to step S119. On the other hand, if the counter Sh is less than or equal to the predetermined value S2 (NO), the information processing device proceeds to step S116.

[0036] In step S116, the information processing device extends the total window time by X%, where X is a predetermined positive number. In this embodiment, the sampling time cannot be shortened, but this is an acceptable constraint in order to reduce the error. The percentage X% by which the total time is changed may be set according to the magnitude of the error. For example, if the error is large, X should be set to a large value.

[0037] In step S117, the information processing device changes the time length and position of each window using a randomization method.

[0038] In step S118, the information processing device adds 1 to the counter Sh.

[0039] In step S119, the information processing device terminates the downsampling method.

[0040] An example of the feature quantities in this embodiment will be explained with reference to Figure 2. Figure 2(A) shows a first example of the overall data. In the overall data shown in Figure 2(A), the horizontal axis is time and the vertical axis is the engagement torque of the friction material. In this example, the extracted data is shown in windows W1 to W4 in Figure 2(A).

[0041] Figure 2(B) shows a second example of the overall data. In the overall data shown in Figure 2(B), the horizontal axis represents time, and the vertical axis represents the relative rotational speed of the friction material. In this example, the extracted data is shown in windows W5 to W8 in Figure 2(B).

[0042] Figure 2(C) shows an example of features from the overall data and the extracted data. In Figure 2(C), the frequency of occurrence of features from the overall data and the extracted data are compared for engagement torque, engagement torque × number of engagements, and relative rotational speed during idle. For each feature, the horizontal axis represents the feature value and the vertical axis represents the frequency. The smaller the error in the distribution of feature occurrences between the overall data and the extracted data, the more similar the features of the overall data and the extracted data are.

[0043] <Method for detecting signs of failure> Figure 3 is a flowchart showing an example of a fault prediction detection method in this embodiment. The fault prediction detection method is an example of information processing to which the downsampling method in this embodiment is applied.

[0044] In step S201, the information processing device acquires driving data of the vehicle to be detected from the big data.

[0045] In step S202, the information processing device extracts the driving data acquired in step S201 using the downsampling method in this embodiment (see Figure 1).

[0046] In step S203, the information processing device calculates a predetermined damage rate Ss based on the extracted data obtained in step S202. Since the extracted data is more compact due to downsampling compared to the original driving data, the calculation of the damage rate Ss can be performed in a short time.

[0047] Next, the information processing device calculates the current damage rate Sr by multiplying the damage rate Ss by a predetermined multiplier. The predetermined multiplier can be calculated by (actual driving time or distance) / (driving time or distance of extracted data).

[0048] In step S204, the information processing device displays the current damage rate Sr calculated in step S203.

[0049] In step S205, the information processing device compares the current damage rate Sr with a specified value and determines whether the current damage rate Sr is significantly large relative to the mileage or mileage. If the damage rate Sr is equal to or greater than the specified value (YES), the information processing device proceeds to step S206. On the other hand, if the damage rate Sr is less than the specified value (NO), the information processing device skips steps S206 to S207 and terminates the fault prediction detection method.

[0050] In step S206, the information processing device determines that it has detected a sign of impending failure.

[0051] In step S207, the information processing device notifies the vehicle user of a potential malfunction. Specifically, the information processing device informs the vehicle user that there is a high probability that a malfunction will occur in the near future.

[0052] <Effects> The downsampling method in this embodiment selects extracted data such that the error between the frequency of occurrence of features in the entire driving data and the frequency of occurrence of features in the extracted data is less than or equal to a predetermined value. The extracted data selected by the downsampling method has features similar to the entire driving data. Therefore, according to this embodiment, downsampling of driving data can be performed with high accuracy. In one aspect, according to this embodiment, signs of failure can be detected with high accuracy.

[0053] [supplement] Although embodiments of the present invention have been described in detail above, the present invention is not limited to these embodiments, and various modifications or changes are possible within the scope of the gist of the present invention as described in the claims.

Claims

[Claim 1] An information processing device, The process of acquiring driving data, A step of calculating predetermined feature quantities for the aforementioned driving data, A process of generating extracted data using a window from the aforementioned driving data, A step of calculating the error between the frequency of occurrence of features in the aforementioned driving data and the frequency of occurrence of features in the aforementioned extracted data, A step of setting the time length and position of the window by a random selection method so that the error is less than or equal to a predetermined value, A downsampling method that performs this operation.

Images