Information processing device

Abstract

To provide an information processing device capable of calculating an index value in a short period of time by extracting extraction data having obtained the feature of the entire original data.SOLUTION: A processing device of an information processing device executes retrieval processing which includes a first step (S120) of calculating a relative frequency distribution of original data, a second step (S125) of setting a plurality of time windows for cutting out a partial period data of the original data, a third step (S130) of cutting out data from the original data, a fourth step (S140) of calculating a relative frequency distribution of extraction data, and a fifth step (S145) for calculating an error between the relative frequency distribution of the original data and the relative frequency distribution of the extraction data, and repeatedly executes an attempt from the second step to the fifth step, changing settings of the plurality of time windows. The processing device calculates an index value of damage of a friction material of a transmission by using the extraction data whose error becomes equal to or smaller than the threshold value (S160).SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] This invention relates to an information processing apparatus.

Background Art

[0002] Patent Document 1 discloses an information processing apparatus that reduces the size of analysis data by compressing original data for analysis. The original data for analysis is data collected over a predetermined period using sensors mounted on a vehicle.

[0003] The information processing apparatus disclosed in Patent Document 1 compresses data by extracting, from the original data, the data acquired at the time when a certain vehicle speed is reached and the data acquired at the inflection point of the vehicle speed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The above - mentioned information processing apparatus extracts data focusing only on the vehicle speed. Therefore, the above - mentioned information processing apparatus cannot extract data according to the characteristics of data other than the vehicle speed. There is a need for an information processing apparatus capable of obtaining extraction data that captures the characteristics of the entire original data including a plurality of feature amounts.

Means for Solving the Problems

[0006] An information processing apparatus for solving the above problems acquires original data collected and created over a predetermined period using a plurality of sensors mounted on a vehicle, and calculates an index value indicating the magnitude of damage accumulated in a friction material of a transmission. This information processing apparatus includes a processing device that executes processing. The original data includes, as feature amounts, data on the amount of heat generated by the friction material of the transmission and data on the engagement frequency of the friction material of the transmission. In this information processing apparatus, the search processing executed by the processing device includes a first step of calculating, for each feature amount, the relative frequency distribution in the original data for a plurality of feature amounts included in the original data. The search processing includes a second step of setting a plurality of time windows for cutting out data for a partial period of the original data so that the total period of all the time window periods is shorter than the predetermined period. The search processing includes a third step of cutting out data from the original data using the plurality of time windows. The search processing includes a fourth step of calculating, for each feature amount, the relative frequency distribution in the extracted data obtained by combining the data cut out using the plurality of time windows. The search processing includes a fifth step of calculating an error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data. After executing the first step, the processing device executes the search processing of repeatedly executing the trials from the second step to the fifth step while changing the setting of the plurality of time windows, and extracts the extracted data for which the error is equal to or less than a threshold value. The processing device calculates the index value using the extracted data for which the error is equal to or less than the threshold value.

[0007] In one aspect of the information processing apparatus, the processing device executes clustering, which is machine learning for classifying data for each section obtained by dividing the original data at regular intervals into a predetermined number of clusters. In the second step, the processing device sets the plurality of time windows so that the difference between the ratio of each cluster in the extracted data and the ratio of each cluster in the entire original data is equal to or less than a threshold value.

Advantages of the Invention

[0008] This information processing apparatus can calculate an index value with the same accuracy as when using original data, by using extracted data with a smaller data volume than the original data. Therefore, this information processing apparatus can achieve both reduction of data volume and maintenance of accuracy, and can calculate the index value in a shorter time compared to the case of using original data.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0010] Hereinafter, a data center 500, which is an embodiment of an information processing apparatus, will be described with reference to FIGS. 1 to 6. <Configuration of the Information Processing System> FIG. 1 shows the configuration of an information processing system including a data center 500. As shown in FIG. 1, the data center 500 communicates with the vehicle 10 via a communication network 400. The data center 500 also communicates with the information processing terminal 600 via the communication network 400. The data center 500 communicates with a plurality of vehicles 10 and a plurality of information processing terminals 600 via the communication network 400.

[0011] <Configuration of Data Center 500> As shown in FIG. 1, the data center 500 includes a processing device 510. The data center 500 includes a storage device 520 and a communication device 530. The processing device 510 includes a CPU that executes processing according to a program and a ROM in which the program is stored. The storage device 520 stores a large amount of data. The communication device 530 is implemented as hardware such as a network adapter, various communication software, or a combination thereof. The communication device 530 realizes wired or wireless communication via the communication network 400.

[0012] The data center 500 can be configured using a plurality of computers. For example, the data center 500 can be configured by a plurality of server devices. <Configuration of Vehicle 10> Each of the plurality of vehicles 10 includes a communication device 80. These communication devices 80 are implemented as hardware such as a network adapter, various communication software, or a combination thereof. These communication devices 80 are configured to be able to realize wired or wireless communication via the communication network 400.

[0013] Each vehicle 10 is equipped with an engine 20 and an automatic transmission 30. For example, the automatic transmission 30 is a planetary gear type transmission. The automatic transmission 30 includes a friction engagement device 31 and a hydraulic control circuit 32. The friction engagement device 31 changes the combination of planetary gear trains that transmit power by engaging or disengaging a plurality of friction engagement elements. Thereby, the automatic transmission 30 forms a plurality of shift stages with different gear ratios. The friction engagement elements are, for example, clutches and brakes. These friction engagement elements each include a friction material. The hydraulic control circuit 32 controls the hydraulic pressure supplied to each friction engagement element of the friction engagement device 31.

[0014] The vehicle 10 includes an engine control device 40 and a transmission control device 50. The engine control device 40 controls the engine 20. The transmission control device 50 controls the automatic transmission 30 by controlling the hydraulic control circuit 32.

[0015] The engine control device 40 and the transmission control device 50 are equipped with various sensors that collect information on each part of the vehicle 10. In each vehicle 10, driving data is collected from these various sensors. From each vehicle 10, the driving data is transmitted to the data center 500 by the communication device 80. For example, the driving data including the driving distance, position information, and vehicle speed of each vehicle 10 is transmitted from each vehicle 10 to the data center 500. Also, the driving data includes various data indicating the state of the automatic transmission 30 acquired by the transmission control device 50 of the vehicle 10. The identification information for identifying each vehicle 10 is also transmitted from each vehicle 10 to the data center 500 together with the driving data.

[0016] The data center 500 stores the received driving data in the storage device 520 together with the identification information. In this way, the driving data of a plurality of vehicles 10 is accumulated in the storage device 520 of the data center 500.

[0017] <Configuration of the information processing terminal 600> The information processing terminal 600 includes a processing device 610, a storage device 620, and a communication device 630. The processing device 610 includes a CPU that executes processing according to a program and a ROM in which the program is stored. The storage device 620 stores data. The communication device 630 is implemented as hardware such as a network adapter, various communication softwares, or a combination thereof. The communication device 630 realizes wired or wireless communication via the communication network 400. The information processing terminal 600 is, for example, a personal computer.

[0018] <Analysis of the driving data of the vehicle 10> The information processing terminal 600 is used for the task of analyzing driving data. When analyzing the driving data, an instruction to execute the analysis is sent from the information processing terminal 600 to the data center 500. The processing device 510 of the data center 500 that has received the instruction performs the analysis using a part of the huge amount of driving data stored in the storage device 520 of the data center 500. The driving data to be used is selected from the huge amount of driving data stored in the storage device 520 according to the purpose of the analysis.

[0019] For example, the processing device 510 calculates the load on a specific component of a specific vehicle 10 based on the driving data of the specific vehicle 10. The processing device 510 estimates the damage accumulated in the component based on the calculated load. For example, the processing device 510 calculates an index value indicating the magnitude of the damage accumulated in the friction material of the automatic transmission 30 of a specific vehicle 10 based on the driving data of the specific vehicle 10. The processing device 510 of the data center 500 outputs the calculated result by sending it to the information processing terminal 600. The received result is displayed on the information processing terminal 600 that has received the result.

[0020] To perform such analysis, the processing device 510 analyzes a large amount of driving data collected over a long period of time. Since the processing device 510 needs to perform an enormous amount of calculations, the analysis takes a long time.

[0021] Therefore, it is conceivable to extract extraction data that captures the characteristics of the entire original data from a large amount of driving data that is the original data. If such extraction data can be extracted, the processing device 510 can perform analysis in a shorter time by using the extraction data. For example, when estimating the damage of the friction material when driving for 100,000 hours, the processing device 510 estimates the damage using the extraction data for 20,000 hours extracted from the original data for 100,000 hours. Then, the processing device 510 calculates the index value of the damage of the friction material when driving for 100,000 hours by multiplying the index value calculated from the extraction data for 20,000 hours by 5.

[0022] FIG. 2 shows an example of the original data. The original data shown in FIG. 2 is the driving data for 100,000 hours in one vehicle 10. The original data shown in FIG. 2 includes, as characteristic quantities, the calorific value of the friction material for which the index value of damage is to be calculated and the engagement frequency of the friction material.

[0023] FIG. 2(a) shows the transition of the calorific value of the friction material for 100,000 hours. The calorific value of the friction material can be calculated based on the relative rotational speed, which is the difference between the input-side rotational speed and the output-side rotational speed in the friction engagement element, the torque transmitted by the friction engagement element, and the shift time of the automatic transmission 30. The calorific value is calculated by the transmission control device 50. Data on the relative rotational speed, the torque transmitted by the friction engagement element, and the shift time of the automatic transmission 30 may be transmitted from the vehicle 10 to the data center 500, and the calorific value may be calculated at the data center 500.

[0024] FIG. 2(b) shows the transition of the engagement frequency of the friction material for 100,000 hours. The engagement frequency indicates the number of times the friction material is engaged per unit time. The engagement frequency is calculated by the transmission control device 50. Data recording the timing of engagement of each friction material may be transmitted from the vehicle 10 to the data center 500, and the engagement frequency may be calculated at the data center 500. The engagement frequency may be data indicating the execution interval of shifting using the same friction material.

[0025] The calorific value and the engagement frequency are correlated with the damage of the friction material of the vehicle 10. The processing device 510 of the data center 500 estimates the damage of the friction material from the running data including the engagement frequency and the engagement frequency as feature quantities.

[0026] The extracted data is created by cutting out data from the original data by a plurality of time windows. In FIG. 2, as examples of a plurality of time windows, three time windows of the first time window W_1, the second time window W_2, and the third time window W_3 are each indicated by a broken line. The start period and the end period of each time window are set so that the respective time windows do not overlap. In this example, 20,000 hours of running data is cut out as the extracted data. Therefore, the start period and the end period of each time window are set so that the total length of the periods of all the time windows is 20,000 hours.

[0027] The data center 500 searches for the setting of the start period and the end period of each time window indicating the cut-out pattern for extracting the extracted data that captures the characteristics of the entire original data. The data center 500 extracts the extracted data from the original data using the cut-out pattern found by the search. The data center 500 performs analysis using the extracted data.

[0028] <Cut-out pattern search process> FIG. 3 is a flowchart showing a series of processing flows related to the cut-out pattern search process. This series of processing is executed by the processing device 510 of the data center 500.

[0029] As shown in FIG. 3, in the process of step S100, the processing device 510 acquires original data. The original data is a part of the huge amount of driving data stored in the storage device 520 of the data center 500, which is selected according to the purpose of analysis. For example, the original data for calculating the index value indicating the magnitude of the damage accumulated on a specific friction material of the automatic transmission 30 of one vehicle 10 is the driving data of the target vehicle 10 over a predetermined period selected from the huge amount of driving data of multiple vehicles 10. For example, when estimating the damage of the friction material after driving for 100,000 hours, the original data is the driving data of the target vehicle 10 over a predetermined period.

[0030] In the process of step S110, the processing device 510 assigns labels to the original data by clustering. Specifically, the processing device 510 divides the original data at regular intervals. The length of the period for dividing the original data is, for example, several minutes. Then, the processing device 510 executes clustering, which is a machine learning that classifies the data in each section into a predetermined number of clusters. For example, the k-means method is used as the clustering algorithm. The k-means method is a clustering algorithm that classifies data into a predetermined number of clusters. The clustering algorithm is not limited to the k-means method.

[0031] The original data includes driving data collected under different environments, such as driving data when driving in the urban area, driving data when driving in the suburbs, and driving data when driving on the highway. By performing clustering, the driving data included in the original data can be classified into clusters of driving data with similar characteristics. The number of clusters to be classified is arbitrarily set according to the content of the analysis.

[0032] FIG. 4 is a graph showing an example in which original data is clustered into four clusters by the k-means method using two feature amounts included in the original data as explanatory variables. For example, the two feature amounts are the calorific value and the engagement frequency shown in FIG. 2. In FIG. 4, each data in each section obtained by dividing the original data is shown as one point. When performing clustering, the processing device 510 uses a representative value of the explanatory variable in the data of each section. For example, the processing device 510 sets the average value of the feature amounts in the data of each section as the representative value. The processing device 510 may use a moving average value of the feature amounts in a plurality of consecutive sections in time series as the representative value.

[0033] In FIG. 4, these points are shown on a two-dimensional space with the first feature amount FV_a and the second feature amount FV_b as coordinate axes. FIG. 4 is an example in which the original data is clustered into four clusters: a first cluster M_1, a second cluster M_2, a third cluster M_3, and a fourth cluster M_4. In FIG. 4, the boundaries of the four clusters are shown by solid lines. In FIG. 4, the centroids of the respective clusters are shown by open triangular marks. The centroid cgM_1 is the centroid of the first cluster M_1. The centroid cgM_2 is the centroid of the second cluster M_2. The centroid cgM_3 is the centroid of the third cluster M_3. The centroid cgM_4 is the centroid of the fourth cluster M_4.

[0034] In FIG. 4, an example in which there are two explanatory variables is shown, but the number of explanatory variables is not limited to two. For example, when the original data includes three feature amounts, the processing device 510 may perform clustering using these three feature amounts as explanatory variables. In that case, the processing device 510 clusters the original data in a three-dimensional coordinate space.

[0035] The processing device 510 assigns a label indicating the result of clustering thus obtained to the original data. Specifically, a label for identifying the cluster to which each data, which was shown as a point in the coordinate space, belongs is assigned. In this way, the processing device 510 creates the original data with labels assigned thereto.

[0036] Next, in the process of step S120, the processing device 510 calculates the relative frequency distribution of the original data. As described above, the original data includes a plurality of feature amounts. The processing device 510 calculates the relative frequency distribution in the original data for each feature amount.

[0037] The frequency distribution classifies data into a plurality of classes and represents the distribution of the number of data in each class, which is the frequency. The relative frequency indicates what percentage the frequency of that class occupies with respect to the sum of the overall frequencies.

[0038] FIG. 5 shows the relative frequency distribution of the calorific value in the original data shown in FIG. 2. In this relative frequency distribution, the classes of the calorific value in the original data are divided into m classes from 1 to m, and the relative frequency distribution is shown.

[0039] FIG. 6 shows the relative frequency distribution of the engagement frequency in the original data shown in FIG. 2. In this relative frequency distribution, the classes of the engagement frequency in the original data are divided into m classes from 1 to m, and the relative frequency distribution is shown.

[0040] In the process of step S120, the processing device 510 calculates such a relative frequency distribution for each feature amount included in the original data. The number of classes in the relative frequency distribution of each feature amount is the same.

[0041] For example, as in the example shown in FIG. 2, when the original data includes two feature amounts, namely the calorific value and the engagement frequency, as feature amounts, the processing device 510 calculates the relative frequency distribution of each of these two feature amounts.

[0042] Next, in the process of step S125, the processing device 510 sets a plurality of time windows in order to extract extraction data from the original data. In FIG. 2, as an example of a plurality of time windows, three time windows W_1 to W_3, i.e., a first time window W_1, a second time window W_2, and a third time window W_3, are shown. In the example shown in FIG. 2, the periods of all the time windows are equal. As shown in FIG. 2, the data cut out by each cut-out window is the data of each feature amount in the same period.

[0043] In the process of step S125, the processing device 510 randomly sets a plurality of time windows so that the total period of all the time windows is shorter than a predetermined period which is the period of the entire original data. As will be described later, the processing device 510 combines all the data cut out by the plurality of time windows set here to create extraction data. The total period of all the time windows is a value that determines the capacity of the extraction data. Therefore, the total period of all the time windows is set in advance.

[0044] For example, each time the processing device 510 executes the process of step S125, it randomly sets the number of time windows, the start period of each time window, and the end period of each time window. At this time, the processing device 510 sets each time window so that the time windows do not overlap. In this way, the processing device 510 randomly sets a plurality of time windows so that the total period of all the time windows becomes a preset period. In the process of step S125, the processing device 510 may set a plurality of time windows while fixing the period of each time window to be constant as shown in FIG. 2. In the process of step S125, the processing device 510 may set a plurality of time windows while fixing the number of the plurality of time windows to a certain number.

[0045] In addition to the above requirements, when setting a plurality of time windows through step S125, the processing device 510 sets a plurality of time windows so that the difference between the ratio of each cluster in the extraction data and the ratio of each cluster in the entire original data is equal to or less than a threshold value.

[0046] In this way, by setting a plurality of time windows through the process of step S125, a cut-out pattern for cutting out data from the original data is determined. When the processing device 510 determines the cut-out pattern in this way, it proceeds with the process to step S130.

[0047] In the process of step S130, the processing device 510 cuts out data from the original data according to the determined cut-out pattern. That is, in the process of step S130, the processing device 510 cuts out data from the original data according to the plurality of set time windows. Then, the processing device 510 combines all the data cut out by the plurality of time windows to create extraction data.

[0048] In the process of the next step S140, the processing device 510 calculates the relative frequency distribution of the extraction data. The processing device 510 calculates the relative frequency distribution of the extraction data in the same way as the method for calculating the relative frequency distribution in step S120. That is, in the process of step S140, the processing device 510 calculates the relative frequency distribution in the extraction data for each feature amount. At this time, the processing device 510 makes the number of classes in the relative frequency distribution of each feature amount the same as that in the relative frequency distribution in step S120.

[0049] For example, as in the example shown in FIG. 2, when the original data includes two feature amounts, namely the calorific value and the engagement frequency, as feature amounts, the processing device 510 also calculates the relative frequency distribution of each of these two feature amounts in step S140.

[0050] Next, in the process of step S145, the processing device 510 calculates the error between the relative frequency distribution in the original data and the relative frequency distribution in the extraction data. For example, the processing device 510 calculates the mean absolute error MAE (Mean Absolute Error). The mean absolute error MAE is represented by the following mathematical formula.

[0051]

Equation

[0052] In the above formula, "n" is the number of feature quantities. "m" is the number of classes in the relative frequency distribution. "Y" is the frequency in the corresponding class of the corresponding feature quantity in the original data. "y" is the frequency in the corresponding class of the corresponding feature quantity in the extracted data.

[0053] As shown in the above formula, the processing device 510 calculates, as an error, the sum of the errors of the frequencies in each class for each feature quantity between the relative frequency distribution in the entire original data and the relative frequency distribution in the extracted data.

[0054] When the error is calculated, the processing device 510 proceeds with the processing to step S150. In the processing of step S150, the processing device 510 determines whether the calculated error is less than or equal to a threshold value. The threshold value is a value for determining whether the extracted data having a relative frequency distribution close to the relative frequency distribution in the original data is extracted by the set extraction pattern. The magnitude of this threshold value is preset so that it can be determined that the extracted data having a relative frequency distribution close to the relative frequency distribution in the original data is extracted based on the error being less than or equal to the threshold value.

[0055] In the processing of step S150, if it is determined that the error is less than or equal to the threshold value (step S150: YES), the processing device 510 proceeds with the processing to step S160. In the processing of step S160, the processing device 510 calculates the target index value using the extracted data created in the processing of the most recent step S130. Here, an index value indicating the magnitude of the damage accumulated in the friction material is calculated. For example, the processing device 510 calculates the fatigue damage degree as an index value indicating the magnitude of the damage accumulated in the friction material.

[0056] The fatigue damage degree is an index value representing the ratio of the accumulated fatigue with the fatigue leading to damage being set to "1" on the assumption that the damage of the friction material follows the linear cumulative damage rule, i.e., the so-called Miner's rule. Here, the damage applied to the friction material during a certain period is calculated from the calorific value and the engagement frequency. Then, with the magnitude of the damage that causes the friction material to reach damage due to a single load input being set to "1", the ratio of the calculated damage is calculated as the index value of fatigue. By repeating this, the calculated index values of fatigue are integrated to calculate the fatigue damage degree, which is the ratio of the accumulated fatigue to the fatigue leading to damage. When the fatigue damage degree reaches "1", it means that damage has occurred, and the calculated fatigue damage degree is a value from "0" to "1".

[0057] Here, since the fatigue damage degree is calculated using the extracted data which is a part of the original data, the processing device 510 converts the calculated fatigue damage degree to the magnitude corresponding to the original data to calculate the fatigue damage degree as an index value. For example, when the original data is the driving data for 100,000 hours and the extracted data is the driving data for 20,000 hours, the calculated fatigue damage degree is multiplied by 5 to obtain the fatigue damage degree as an index value.

[0058] On the other hand, in the process of step S150, if it is determined that the error is greater than the threshold value (step S150: NO), the processing device 510 returns the process to step S125. Then, the processing device 510 executes the search process from step S125 to step S145 again.

[0059] In this way, the processing device 510 changes the setting of a plurality of time windows and repeatedly executes the search process from step S125 to step S145 to extract the extracted data with an error less than or equal to the threshold value from the original data. Then, the processing device 510 calculates the index value using the extracted data. After calculating the index value, the processing device 510 proceeds to step S170.

[0060] In the process of step S170, the processing device 510 determines whether the index value is equal to or greater than a preset value. The preset value is a value for predicting that there is a high possibility of damage based on the fact that the index value is equal to or greater than the preset value. For example, here, "0.9" can be set as the preset value for the fatigue damage degree. In this case, it is possible to predict that there is a high possibility of damage based on the fact that 90% of the fatigue leading to damage has been reached.

[0061] In the process of step S170, when it is determined that the index value is equal to or greater than the preset value (step S170: YES), the processing device 510 advances the process to step S180. In the process of step S180, the processing device 510 outputs the index value and the failure prediction. Specifically, the processing device 510 transmits the index value and the failure prediction to the information processing terminal 600 that sent the instruction requesting the analysis.

[0062] The failure prediction is, for example, a message indicating that the occurrence of a failure has been predicted. In this way, when the calculated index value is equal to or greater than the preset value, the processing device 510 issues a notification informing that the occurrence of a failure has been predicted. The failure prediction may be information on the remaining life until the failure occurs. For example, when the fatigue damage degree calculated using the extracted data extracted from 100,000 hours of original data is the index value, the processing device 510 calculates the running time until the fatigue damage degree reaches "1" and outputs it as information on the remaining life. The information on the remaining life may be converted into the running distance based on the running distance of 100,000 hours and output.

[0063] In the process of step S170, when it is determined that the index value is less than the preset value (step S170: NO), the processing device 510 advances the process to step S190. In the process of step S190, the processing device 510 outputs the index value. Specifically, the processing device 510 transmits the index value to the information processing terminal 600 that sent the instruction requesting the analysis.

[0064] When the process of step S180 or step S190 is executed, the processing device 510 ends this series of processes. <Operations of this Embodiment> The data center 500, which is an information processing device of this embodiment, acquires original data collected and created over a predetermined period using a plurality of sensors mounted on the vehicle 10, and calculates an index value indicating the magnitude of damage accumulated in the friction material of the automatic transmission 30.

[0065] The data center 500 includes a processing device 510 that executes processing. The original data includes, as feature amounts, data on the heat generation amount of the friction material of the automatic transmission 30 and data on the engagement frequency of the friction material of the automatic transmission 30. In this data center 500, the search process executed by the processing device 510 includes a first step (step S120) of calculating, for each feature amount, the relative frequency distribution in the original data for a plurality of feature amounts included in the original data. The search process includes a second step (step S125) of setting a plurality of time windows for cutting out data for a partial period of the original data so that the total period of all the time window periods is shorter than the predetermined period. The search process includes a third step (step S130) of cutting out data from the original data using the plurality of time windows. The search process includes a fourth step (step S140) of calculating, for each feature amount, the relative frequency distribution in the extracted data obtained by combining all the data cut out by the plurality of time windows. The search process includes a fifth step (step S145) of calculating the error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data. After executing the first step, the processing device 510 executes a search process of repeatedly executing the trials from the second step to the fifth step while changing the setting of the plurality of time windows. Then, the processing device 510 extracts the extracted data for which the error is equal to or less than the threshold value (step S150: YES). The processing device 510 calculates the index value using the extracted data for which the error is equal to or less than the threshold value (step S160).

[0066] According to this data center 500, extraction data that captures the features of the entire original data including a plurality of feature amounts can be obtained. Therefore, this data center 500 can calculate an index value with the same accuracy as when using the original data by using extraction data with a smaller data amount than the original data.

[0067] <Effects of this Embodiment> (1) According to the data center 500 which is the information processing apparatus of this embodiment, it is possible to achieve both reduction of the data amount and calculation accuracy of the index value.

[0068] (2) According to the data center 500 which is the information processing apparatus of this embodiment, it is possible to calculate the index value in a shorter time compared to the case of using the original data. (3) The processing device 510 executes clustering which is a machine learning for classifying the data of each section obtained by dividing the original data at regular intervals into a predetermined number of clusters (step S110). Then, in the second step (step S125) of the search process, the processing device 510 sets a plurality of time windows so that the difference between the ratio of each cluster in the extraction data and the ratio of each cluster in the entire original data is equal to or less than a threshold value.

[0069] The plurality of sections classified into the same cluster are sections having similar features. In the above search process, the setting output from the processing device 510 is a setting that can cut out extraction data in which the difference between the ratio of the entire original data and each cluster is equal to or less than the threshold value and the relative frequency distribution of each feature amount is close.

[0070] Therefore, according to the search process executed by the data center 500 described above, it is possible to find a setting that can obtain extraction data closer to the features of the entire original data. (4) When the processing device 510 can extract one piece of extraction data with an error below the threshold, it ends the search process and calculates the index value using the extraction data with an error below the threshold. Therefore, when the data center 500 can extract one piece of extraction data with an error below the threshold, it can calculate the index value and promptly output the result.

[0071] (5) When the calculated index value is equal to or greater than the preset value (step S170: YES), the processing device 510 issues a notification indicating that the occurrence of a failure has been predicted. Therefore, the data center 500 can notify the user that the occurrence of a failure has been predicted before the failure occurs.

[0072] (6) The processing device 510 calculates the fatigue damage degree as the index value. Therefore, the data center 500 can inform the user of how much time remains until the failure occurs.

[0073] <Modification Example> This embodiment can be implemented with the following modifications. This embodiment and the following modification examples can be implemented in combination with each other within a technically non - conflicting range.

[0074] · As the feature quantity, the calorific value of the friction material for which the index value of the damage is calculated and the engagement frequency of the friction material are exemplified. However, the index value may be calculated by further including the oil temperature data in the feature quantity.

[0075] · In the above - described embodiment, an example in which the information processing device is embodied as the data center 500 is shown. And an example in which the calculation of the index value is executed in the data center 500 is shown. In contrast, the above - described information processing device may be embodied as the information processing terminal 600. In this case, the calculation of the index value is executed by the processing device 610 of the information processing terminal 600. The above - described information processing device may be embodied as the control device of the vehicle 10. In this case, the calculation of the index value can also be executed by the control device of the vehicle 10. For example, the calculation of the index value can also be executed by the transmission control device 50 of the vehicle 10.

[0076] · In the above embodiment, an example was shown in which one piece of extraction data was extracted and the index value was calculated. In contrast, a plurality of pieces of extraction data may be extracted, and the final index value may be determined using a plurality of index values calculated using each piece of extraction data. For example, the minimum value, maximum value, mode value, and average value may be used as the final index value. Also, a plurality of index values may be output.

[0077] · In the above embodiment, an example was shown in which when the index value is equal to or greater than a preset value, it is notified that the occurrence of a failure has been predicted. This may be omitted. After calculating the index value, only the process of step S190 may be executed to output only the index value.

[0078] · Although the fatigue damage degree was exemplified as an example of the index value to be calculated, the index value to be calculated is not limited to the fatigue damage degree. · Index values of damage to a plurality of friction materials may be calculated. For each characteristic quantity of each friction material, its relative frequency distribution may be calculated, and a cut-out pattern may be searched so that the error of the relative frequency distribution for all characteristic quantities becomes small.

[0079] · A cut-out pattern may be searched so that the relative frequency distribution of the characteristic quantity becomes small for each friction material. And index values may be calculated for each friction material. · It is also possible to target a transmission equipped with a friction material other than the automatic transmission 30 shown in the above embodiment, such as a stepped automatic transmission, a forward and reverse switching mechanism of a continuously variable transmission, or a clutch of a manual transmission, mounted on a hybrid vehicle.

[0080] · An example was shown in which the processing device 510 sets a plurality of time windows so that the difference between the ratio of each cluster in the original data and the ratio of each cluster in the extraction data is equal to or less than a threshold value. The processing device 510 may set a plurality of time windows without such a constraint. In this case, the process of step S110 for performing clustering may be omitted.

[0081] ·The method for determining the setting of the time window in the cutout pattern does not have to be random. The setting of the time window in the cutout pattern may be changed according to a pre-set rule and the trial may be repeated.

[0082] ·The error calculated in the process of step S145 is not limited to the mean absolute error MAE. For example, the processing device 510 may calculate the mean squared error as the error. The processing device 510 may calculate the root mean square error as the error.

[0083] ·An example using the extracted data obtained by combining all the cutout data has been shown. In contrast, among the cutout data, some of the data may be combined to create the extracted data.

Explanation of Signs

[0084] 10…Vehicle, 20…Engine, 30…Automatic transmission, 31…Friction engagement device, 32…Hydraulic control circuit, 40…Engine control device, 50…Transmission control device, 80…Communication device, 400…Communication network, 500…Data center, 510…Processing device, 520…Storage device, 530…Communication device, 600…Information processing terminal, 610…Processing device, 620…Storage device, 630…Communication device

Claims

1. An information processing apparatus that acquires original data collected and created over a predetermined period using a plurality of sensors mounted on a vehicle, and calculates an index value indicating the magnitude of damage accumulated in a friction material of a transmission, comprising a processing device that executes processing, wherein the original data includes, as feature amounts, data on the calorific value of the friction material of the transmission and data on the engagement frequency of the friction material of the transmission, the processing device, a first step of calculating, for each feature amount, a relative frequency distribution in the original data for a plurality of feature amounts included in the original data; a second step of setting a plurality of time windows for cutting out data for a part of the period of the original data so that the total period of all the time windows is shorter than the predetermined period; a third step of cutting out data from the original data by the plurality of time windows; a fourth step of calculating, for each feature amount, a relative frequency distribution in the extracted data obtained by combining the data cut out by the plurality of time windows; and a fifth step of calculating an error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data, and after executing the first step, executing a search process of repeatedly executing the trials from the second step to the fifth step while changing the setting of the plurality of time windows, and extracting the extracted data in which the error is equal to or less than a threshold value, calculating the index value using the extracted data in which the error is equal to or less than the threshold value, information processing apparatus.

2. The processing device executes clustering, which is machine learning for classifying data for each section obtained by dividing the original data at regular intervals into a predetermined number of clusters, in the second step, the processing device sets the plurality of time windows so that a difference between a ratio of each cluster in the extracted data and a ratio of each cluster in the entire original data is equal to or less than a threshold value, The information processing apparatus according to claim 1.

3. When one piece of the extracted data in which the error is equal to or less than the threshold value is extracted, the processing device ends the search process and calculates the index value using the extracted data in which the error is equal to or less than the threshold value, The information processing apparatus according to claim 1.

4. When the calculated index value is equal to or greater than a predetermined value, the processing device gives a notification indicating that the occurrence of a failure has been predicted. The information processing apparatus according to claim 1.

5. The processing device calculates a fatigue damage degree as the index value. The information processing apparatus according to claim 1.

Images