Information processing device

Abstract

To provide an information processing device capable of extracting extracted data that captures the overall characteristics of original data and calculating an index value in a short time.SOLUTION: A processing unit of an information processing device executes a search process which includes a first step (S120) of calculating a relative frequency distribution of feature quantities of original data, a second step (S125) of setting a plurality of time windows for extracting data in partial periods of the original data, a third step (S130) of extracting data from the original data, a fourth step (S140) of calculating a relative frequency distribution of feature quantities in extracted data, and a fifth step (S145) of calculating an error between the relative frequency distribution in the original data and the relative frequency distribution in the extracted data, and in which the trial from the second step to the fifth step is repeatedly executed while changing the settings of the plurality of time windows. The processing unit calculates an index value by using the extracted data for which the error becomes equal to or less than a threshold (S160).SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device. [Background technology]

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

[0003] The information processing device disclosed in Patent Document 1 compresses data by extracting from the original data data acquired when a certain vehicle speed is reached and data acquired at an inflection point in the vehicle speed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-108247 Summary of the Invention [Problem to be solved by the invention]

[0005] The above-described information processing device extracts data by focusing only on vehicle speed. Therefore, the above-described information processing device cannot extract data based on data characteristics other than vehicle speed. There is a need for an information processing device that can obtain extracted data that captures the overall characteristics of original data that includes multiple feature quantities. [Means for solving the problem]

[0006] An information processing device for solving the above problem acquires original data collected over a predetermined period using multiple sensors mounted on a vehicle and calculates an index value indicating the degree of damage accumulated in the oil of an electric motor. This information processing device includes a processing device that executes processing. The processing device calculates multiple feature quantities based on the original data. The original data includes information on the temperature of the electric motor and the duration of the temperature of the electric motor. The multiple feature quantities include data calculated from the temperature of the electric motor and the duration of the temperature of the electric motor. In this information processing device, a search process executed by the processing device includes a first step of calculating a relative frequency distribution in the original data for each of the multiple feature quantities. The search process includes a second step of setting multiple time windows that extract data for a portion of the original data such that the sum of the durations of all the time windows is shorter than the predetermined period. The search process includes a third step of extracting data from the original data using the multiple time windows. The search process includes a fourth step of calculating the relative frequency distribution in extracted data obtained by combining all the data extracted using the multiple time windows for each of the feature quantities. The search process 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 process by repeatedly executing trials from the second step to the fifth step by changing the settings of the multiple time windows, and extracts the extracted data for which the error is equal to or less than a threshold. The processing device calculates the index value using the extracted data for which the error is equal to or less than the threshold.

[0007] In one aspect of the information processing device, the processing device performs clustering, which is machine learning, to classify data in each interval obtained by dividing the original data into a predetermined number of clusters. In the second step, the processing device sets the multiple time windows so that the proportion of each cluster in the extracted data is equal to the proportion of each cluster in the entire original data. [Effects of the Invention]

[0008] This information processing device can calculate index values ​​using the extracted data with the same accuracy as when using the original data, and therefore can calculate index values ​​in a shorter time than when using the original data. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram showing the relationship between a data center, which is an embodiment of an information processing device, a vehicle, and an information processing terminal. [Figure 2] FIG. 2 is a graph showing the original data, where (a) shows the transition of the motor temperature, and (b) shows the transition of the motor oil temperature. [Figure 3] FIG. 3 is a flowchart showing the flow of processing executed by the processing device in the data center. [Figure 4] FIG. 4 is a graph showing an example of clustering original data using two feature quantities. [Figure 5] Figure 5 is a graph showing an example of the relative frequency distribution for each feature of the original data, where Figure 5(a) shows the relative frequency distribution for the product of the motor temperature and the duration of the motor temperature, and Figure 5(b) shows the relative frequency distribution for the product of the oil temperature and the duration of the oil temperature. [Figure 6] FIG. 6 is a graph showing an example of a method for determining an abnormality based on a comparison between the total travel distance and the index value. DETAILED DESCRIPTION OF THE INVENTION

[0010] A data center 500, which is an embodiment of an information processing device, will be described below with reference to FIGS. <Configuration of 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 a vehicle 10 via a communication network 400. The data center 500 also communicates with an 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 also 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 of these. The communication device 530 realizes wired or wireless communication via the communication network 400.

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

[0013] Each vehicle 10 is equipped with a motor 20, which is an electric motor, a power transmission mechanism 30 that transmits the driving force of the motor 20 to the drive wheels of the vehicle 10, and a control device 40 that controls the motor 20. The motor 20 and the power transmission mechanism 30 are housed in a case 70.

[0014] Furthermore, each vehicle 10 is equipped with an oil pump 50 and an oil cooler 60. The oil pump 50 is controlled by the control device 40. The oil pump 50 sends oil in a case 70 to the oil cooler 60. The oil cooled in the oil cooler 60 is sent into the case 70. The motor 20 in the case 70 is cooled by the oil.

[0015] The control device 40 is equipped with various sensors that collect information from various parts of the vehicle 10. Each vehicle 10 collects driving data from these various sensors. The driving data is transmitted from each vehicle 10 to the data center 500 by the communication device 80. For example, driving data including the driving distance, location information, and vehicle speed of each vehicle 10 is transmitted from each vehicle 10 to the data center 500. The driving data also includes various data acquired by the control device 40 indicating the state of the motor 20 and the oil that cools the motor 20. Identification information that identifies 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 identification information and the travel data in the storage device 520. In this way, the travel data of the multiple vehicles 10 is accumulated in the storage device 520 of the data center 500.

[0017] <Configuration of 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 software, or a combination of these. 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 vehicle 10's driving data> The information processing terminal 600 is used to analyze the driving data. When analyzing the driving data, the information processing terminal 600 transmits an instruction to the data center 500 to perform the analysis. Upon receiving the instruction, the processing device 510 of the data center 500 performs the analysis using a portion of the vast 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 vast 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 object 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 object based on the calculated load. For example, the processing device 510 calculates an index value indicating the amount of damage accumulated in the oil that cools the motor 20 of the specific vehicle 10 based on the driving data of the specific vehicle 10. This index value indicates the degree of deterioration of the oil. The processing device 510 of the data center 500 outputs the calculated result by transmitting it to the information processing terminal 600. The information processing terminal 600 that receives the result displays the received result.

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

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

[0022] FIG. 2 shows an example of original data. The original data shown in FIG. 2 is driving data for 100,000 hours for one vehicle 10. The driving data includes the temperature of the oil for which the damage index value is calculated and the duration of the oil temperature. Furthermore, the driving data includes the temperature of the motor 20 cooled by the oil and the duration of the motor 20 temperature.

[0023] FIG. 2(a) shows, as an example of driving data, the temperature transition of motor 20 over 100,000 hours. The data on the temperature transition of motor 20 includes information on the temperature of motor 20 and the duration of the temperature of motor 20. FIG. 2(b) shows the oil temperature transition of motor 20 over 100,000 hours. The data on the oil temperature transition of motor 20 includes information on the oil temperature of motor 20 and the duration of the oil temperature.

[0024] Here, the temperature is, for example, Celsius temperature (°C). In this case, the temperature may be a value adjusted so that Celsius temperature (°C) is treated as a positive value. Note that the temperature data is not limited to Celsius temperature (°C). For example, the temperature data may be absolute temperature (K), or may be a value with an arbitrary reference point set to 0.

[0025] The temperature may be adjusted by multiplying it by a weight depending on the tendency of the temperature to affect oil deterioration. For example, if the temperature is equal to or higher than a predetermined value, the temperature may be adjusted by multiplying it by a weight. Furthermore, data on temperatures below the predetermined value may not be used to calculate damage.

[0026] In this processing device 510, a plurality of temperature zones are set by dividing the temperature at regular intervals, and the time during which the temperature falls within each temperature zone is regarded as the duration of the temperature. The processing device 510 calculates, as a feature quantity, the product of the temperature of the motor 20 and the duration of the temperature of the motor 20, based on data on the transition of the temperature of the motor 20. The product of the temperature of the motor 20 and the duration of the temperature of the motor 20 is an example of data calculated from the temperature of the motor and the duration of the temperature of the motor.

[0027] The processing device 510 calculates the product of the oil temperature of the motor 20 and the duration of the oil temperature, based on data on the transition of the oil temperature of the motor 20. The product of the oil temperature of the motor 20 and the duration of the oil temperature is an example of data calculated from the oil temperature of the electric motor and the duration of the oil temperature.

[0028] Here, the product of the temperature and the duration of the temperature is, for example, the product of the average temperature and the duration of each temperature zone. The original data is not limited to the duration of the temperature, but may also include the distance traveled by the vehicle 10 at that temperature. In this case, the processing device 510 may calculate the product of the temperature of the motor 20 and the distance traveled as the feature. Here, the distance traveled refers to the distance traveled by the vehicle 10 while the temperature is within that temperature range.

[0029] The product of the temperature of the motor 20 and the duration of the temperature of the motor 20, and the product of the oil temperature of the motor 20 and the duration of the oil temperature, correlate with damage to the oil that cools the motor 20 of the vehicle 10. The processing device 510 of the data center 500 estimates oil damage from the product of the temperature of the motor 20 and the duration of the temperature of the motor 20, which are feature quantities calculated based on the original data, and the product of the oil temperature of the motor 20 and the duration of the oil temperature of the motor 20.

[0030] The extracted data is created by extracting data from the original data using multiple time windows. In Figure 2, three time windows, the first time window W_1, the second time window W_2, and the third time window W_3, are shown by dashed lines as examples of multiple time windows. The start and end periods of each time window are set so that they do not overlap. In this example, 20,000 hours of driving data is extracted as the extracted data. Therefore, the start and end periods of each time window are set so that the total length of all the time windows is 20,000 hours.

[0031] The data center 500 searches for the setting of the start and end of each time window that indicates a cutout pattern for extracting extracted data that captures the characteristics of the entire original data. The data center 500 extracts extracted data from the original data using the extraction pattern found by the search, and performs analysis using the extracted data.

[0032] <Searching for extraction patterns> 3 is a flowchart showing a series of processes related to the extraction pattern search process. This series of processes is executed by the processing device 510 of the data center 500.

[0033] As shown in Fig. 3, the processing device 510 acquires original data in the process of step S100. The original data is a portion of driving data selected according to the purpose of analysis from the vast amount of driving data stored in the storage device 520 of the data center 500. For example, the original data for calculating an index value indicating the degree of damage accumulated in the oil of the motor 20 of a specific vehicle 10 is driving data of the target vehicle 10 over a predetermined period. For example, when estimating the damage to the oil of the motor 20 after 100,000 hours of driving, the original data is driving data of the target vehicle 10 over a predetermined period.

[0034] In the process of step S105, the processing device 510 calculates feature amounts based on the original data. Hereinafter, feature amounts calculated based on the original data may be referred to as feature amounts of the original data. 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 into fixed periods. The length of the periods into which the original data is divided is, for example, several minutes. Then, the processing device 510 performs clustering, which is machine learning, to classify the data in each period 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 pre-specified number of clusters. The clustering algorithm is not limited to the k-means method.

[0035] The original data includes driving data collected under different environments. 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 can be set arbitrarily depending on the content of the analysis.

[0036] FIG. 4 is a graph showing an example of clustering original data into four clusters using the k-means method, using two feature quantities calculated based on the original data as explanatory variables. For example, the two feature quantities are the product of the temperature of the motor 20 and the duration, and the product of the oil temperature of the motor 20 and the duration. In FIG. 4, data corresponding to each section into which the original data is divided is represented by a single point. When performing clustering, the processing device 510 uses a representative value of the explanatory variables in the data for each section. For example, the processing device 510 sets the average value of the feature quantities in the data for each section as the representative value. The processing device 510 may also use a moving average value of the feature quantities for multiple consecutive sections in a time series as the representative value.

[0037] In Figure 4, these points are shown in a two-dimensional coordinate space with the first feature FV_a and the second feature FV_b as the coordinate axes. Figure 4 shows an example of original data 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 Figure 4, the boundaries of the four clusters are shown with solid lines. In Figure 4, the center of gravity of each cluster is shown with a hollow triangle. The center of gravity cgM_1 is the center of gravity of the first cluster M_1. The center of gravity cgM_2 is the center of gravity of the second cluster M_2. The center of gravity cgM_3 is the center of gravity of the third cluster M_3. The center of gravity cgM_4 is the center of gravity of the fourth cluster M_4.

[0038] 4 shows an example in which there are two explanatory variables, but the number of explanatory variables is not limited to two. For example, if the original data includes three feature amounts, the processing device 510 may perform clustering using these three feature amounts as explanatory variables. In this case, the processing device 510 clusters the original data in a three-dimensional coordinate space.

[0039] The processing device 510 assigns labels indicating the clustering results to the original data. Specifically, each piece of data represented by a point in the coordinate space is assigned a label identifying the cluster into which the data is classified. In this way, the processing device 510 creates labeled original data.

[0040] Next, in the process of step S120, the processing device 510 calculates the relative frequency distribution of the feature amounts of the original data. The processing device 510 calculates the relative frequency distribution in the original data for each feature amount.

[0041] A frequency distribution classifies data into multiple classes and shows the distribution of the frequency, which is the number of data in each class. Relative frequency indicates what percentage of the frequency of that class is in relation to the total frequency.

[0042] FIG. 5(a) shows the relative frequency distribution of the product of the temperature of the motor 20 and the duration of the temperature of the motor 20 (motor temperature × duration), calculated based on the original data shown in FIG. 2. Here, the relative frequency distribution is shown by dividing the product of the temperature of the motor 20 and the duration of the temperature of the motor 20 in the original data into m classes from 1 to m. FIG. 5(b) shows the relative frequency distribution of the product of the oil temperature of the motor 20 and the duration of the oil temperature (oil temperature × duration), calculated based on the original data shown in FIG. 2. Here, the relative frequency distribution is shown by dividing the product of the oil temperature of the motor 20 and the duration of the oil temperature in the original data into m classes from 1 to m.

[0043] In the process of step S120, the processing device 510 calculates such a relative frequency distribution for each feature amount of the original data. The number of classes in the relative frequency distribution for each feature amount is the same.

[0044] For example, when calculating the product of the temperature of the motor 20 and the duration of the temperature of the motor 20, and the product of the temperature of the oil of the motor 20 and the duration of the oil temperature based on the original data, the processing device 510 calculates the relative frequency distribution of each of these two features.

[0045] Next, in the process of step S125, the processing device 510 sets a plurality of time windows to extract extracted data from the original data. 2 shows three time windows W_1 to W_3, namely, a first time window W_1, a second time window W_2, and a third time window W_3, as an example of a plurality of time windows. In the example shown in FIG. 2, the time windows are all of equal duration. As shown in FIG. 2, the data extracted by each extraction window is data of each feature amount for the same duration.

[0046] In the process of step S125, the processing device 510 randomly sets multiple time windows so that the total duration of all the time windows is shorter than a predetermined duration, which is the duration of the entire original data. As will be described later, the processing device 510 combines all the data extracted by the multiple time windows set here to create extracted data. The total duration of all the time windows is a value that determines the volume of the extracted data. Therefore, the total duration of all the time windows is set in advance.

[0047] For example, each time the processing device 510 executes the process of step S125, the processing device 510 randomly sets the number of time windows, the start time of each time window, and the end time of each time window. At this time, the processing device 510 sets each time window so that the time windows do not overlap. The processing device 510 thus randomly sets multiple time windows so that the total duration of all the time windows is a predetermined duration. In the process of step S125, the processing device 510 may set multiple time windows by fixing the duration of each time window to a constant value, as shown in FIG. 2. In the process of step S125, the processing device 510 may set multiple time windows by fixing the number of time windows to a constant value.

[0048] In addition to the above requirements, when setting multiple time windows through step S125, the processing device 510 sets the multiple time windows so that the proportion of each cluster in the extracted data is equal to the proportion of each cluster in the entire original data.

[0049] In this way, a cut-out pattern for cutting out data from the original data is determined by setting a plurality of time windows through the process of step S125. After determining the cut-out pattern in this way, processing device 510 advances the process to step S130.

[0050] In the process of step S130, the processing device 510 extracts data from the original data using the determined extraction pattern. That is, in the process of step S130, the processing device 510 extracts data from the original data using the multiple time windows that have been set. Then, the processing device 510 combines all of the data extracted using the multiple time windows to create extracted data.

[0051] In the next step S140, the processing device 510 calculates the relative frequency distribution of the feature quantities calculated from the extracted data. The processing device 510 calculates the relative frequency distribution of the feature quantities calculated from the extracted data using the same method as the method used to calculate the relative frequency distribution in step S120. That is, in the processing of step S140, the processing device 510 calculates the relative frequency distribution in the extracted data for each feature quantity. At this time, the processing device 510 sets the number of classes in the relative frequency distribution of each feature quantity to be the same as the relative frequency distribution in step S120.

[0052] For example, as described above, if two feature quantities, namely the product of the temperature of motor 20 and the duration of the temperature of motor 20, and the product of the temperature of oil of motor 20 and the duration of the oil temperature, are calculated from the original data, processing device 510 also calculates the relative frequency distribution of each of these two feature quantities in step S140.

[0053] Next, in the process of step S145, the processing device 510 calculates the error between the relative frequency distribution of the feature amount in the original data and the relative frequency distribution of the feature amount in the extracted data. For example, the processing device 510 calculates the mean absolute error (MAE). The mean absolute error (MAE) is expressed by the following formula.

[0054]

number

[0055] In the above formula, "n" is the number of features. "m" is the number of classes in the relative frequency distribution. "Y" is the frequency of the corresponding feature in the corresponding class in the original data. "y" is the frequency of the corresponding feature in the corresponding class in the extracted data.

[0056] As shown in the above formula, the processing device 510 calculates the error as the sum of the errors in the frequencies in each class for each feature between the relative frequency distribution of the feature in the entire original data and the relative frequency distribution of the feature in the extracted data.

[0057] After calculating the error, the processing device 510 proceeds to step S150. In step S150, the processing device 510 determines whether the calculated error is equal to or less than a threshold value. The threshold value is a value for determining whether extracted data having a relative frequency distribution close to the relative frequency distribution in the original data has been extracted by the set extraction pattern. The magnitude of this threshold value is set in advance so that it can be determined that extracted data having a relative frequency distribution close to the relative frequency distribution in the original data has been extracted based on the error being equal to or less than the threshold value.

[0058] If it is determined in the process of step S150 that the error is equal to or smaller than the threshold value (step S150: YES), processing device 510 proceeds to step S160. In the process of step S160, the processing device 510 calculates a target index value using the extracted data created in the most recent process of step S130. Here, the index value calculated indicates the degree of damage accumulated in the oil of the motor 20. For example, the processing device 510 calculates the degree of deterioration as the index value indicating the degree of damage accumulated in the oil of the motor 20.

[0059] The deterioration level is an index value that represents the rate of deterioration when the allowable limit of damage accumulated in the oil of the motor 20 is set to "1." Here, damage inflicted on the oil of the motor 20 over a certain period of time is calculated from the product of the temperature of the motor 20 and the duration of the temperature of the motor 20, and the product of the temperature of the oil of the motor 20 and the duration of the oil temperature. The degree of damage that is considered to result in damage to the motor 20 is then set to "1," and the calculated rate of damage is calculated as the deterioration index value. By repeating this process, the calculated deterioration index values ​​are integrated to calculate the deterioration level, which is the rate of accumulated deterioration relative to the deterioration that will result in damage to the motor 20. A deterioration level of "1" indicates a high possibility of damage to the motor 20, and the calculated deterioration level is a value between "0" and "1." The allowable limit is a value that can be arbitrarily changed, and may be a value that is considered to cause damage to the motor 20 when using oil of that deterioration level, or a value that is considered to cause damage to the motor 20 at the time that that deterioration level is reached. The acceptable limit may also be the value at which the oil must be changed before it reaches that level of degradation.

[0060] Here, since the degradation degree is calculated using the extracted data that is a part of the original data, the processing device 510 converts the calculated degradation degree into a magnitude corresponding to the original data and calculates the degradation degree as an index value. For example, if the original data is 100,000 hours of driving data and the extracted data is 20,000 hours of driving data, the calculated degradation degree is multiplied by 5 to obtain the degradation degree as an index value.

[0061] On the other hand, if it is determined in the process of step S150 that the error is greater than the threshold value (step S150: NO), processing device 510 returns the process to step S125. Then, processing device 510 executes the search process from step S125 to step S145 again.

[0062] In this way, the processing device 510 repeatedly executes the search process of steps S125 to S145 by changing the settings of multiple time windows, and extracts extracted data from the original data whose error is equal to or less than the threshold. Then, the processing device 510 calculates an index value using the extracted extracted data. After calculating the index value, the processing device 510 proceeds to step S170.

[0063] In the process of step S170, the processing device 510 determines whether the index value is equal to or greater than a predetermined value. The predetermined value is a value for predicting an increased likelihood of damage based on the index value being equal to or greater than the predetermined value. For example, here, "0.9" can be set as the predetermined value for the deterioration level. In this case, it is possible to predict an increased likelihood of damage based on the fact that 90% of the deterioration leading to damage has been reached.

[0064] In the process of step S170, if it is determined that the index value is equal to or greater than the predetermined value (step S170: YES), the processing device 510 proceeds to the process of 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 transmitted the instruction requesting the analysis.

[0065] The failure prediction is, for example, a message indicating that a failure has been predicted. In this way, when the calculated index value is equal to or greater than a predetermined value, the processing device 510 issues a notification informing the user that a failure has been predicted. The failure prediction may also be information on the lifespan until a failure occurs. For example, when the index value is a deterioration level calculated using extracted data extracted from 100,000 hours of original data, the processing device 510 calculates the driving time until the deterioration level reaches "1" and outputs this as information on the lifespan. The information on the lifespan may also be converted into a driving distance based on the driving distance for 100,000 hours and output.

[0066] In the process of step S170, if it is determined that the index value is less than the predetermined value (step S170: NO), processing device 510 proceeds to the process of step S190. In the process of step S190, processing device 510 outputs the index value. Specifically, processing device 510 transmits the index value to information processing terminal 600 that transmitted the instruction requesting analysis.

[0067] After executing the process of step S180 or step S190, the processing device 510 ends this series of processes. <Operation of this embodiment> The data center 500, which is an information processing device in this embodiment, acquires original data collected over a predetermined period of time using multiple sensors installed on the vehicle 10 and calculates an index value indicating the extent of damage accumulated in the oil of the motor 20.

[0068] The data center 500 includes a processing device 510 that executes processing. The original data includes information on the temperature of the motor 20 and the duration of the temperature of the motor 20, and based on this information, data on the product of the temperature of the motor 20 and the duration of the temperature of the motor 20 is calculated as a feature. In addition, the original data includes information on the oil temperature of the motor 20 and the duration of the oil temperature, and based on this information, data on the product of the oil temperature of the motor 20 and the duration of the oil temperature is calculated as a feature. The product of the oil temperature of the motor 20 and the duration of the oil temperature is an example of a feature calculated from the oil temperature and the duration of the oil temperature.

[0069] In this data center 500, the processing device 510 executes a search process including a first step (step S120) of calculating, for each feature, a relative frequency distribution for a plurality of feature quantities calculated based on original data. The search process includes a second step (step S125) of setting a plurality of time windows to extract data for a portion of the original data such that the sum of the periods of all the time windows is shorter than a predetermined period. The search process includes a third step (step S130) of extracting 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, a relative frequency distribution for the feature quantities calculated based on extracted data obtained by combining all the data extracted using the plurality of time windows. The search process includes a fifth step (step S145) of calculating an error between the relative frequency distribution for the feature quantities in the original data and the relative frequency distribution for the feature quantities in the extracted data. After executing the first step, the processing device 510 executes the search process by repeatedly executing trials of the second to fifth steps by changing the settings of the plurality of time windows. Then, processing device 510 extracts extracted data whose error is equal to or less than the threshold value (step S150: YES). Processing device 510 calculates an index value using the extracted data whose error is equal to or less than the threshold value (step S160).

[0070] According to this data center 500, extracted data that captures the overall characteristics of the original data for multiple feature quantities can be obtained. Therefore, this data center 500 can use the extracted data to calculate index values ​​with the same accuracy as when using the original data.

[0071] <Effects of this embodiment> (1) According to the data center 500, which is an information processing apparatus of this embodiment, the index value can be calculated in a shorter time than when original data is used.

[0072] (2) The processing device 510 performs clustering, which is machine learning, to classify data in each section obtained by dividing the original data into a fixed period into a predetermined number of clusters (step S110). Then, in the second step of the search process (step S125), the processing device 510 sets multiple time windows so that the ratio of each cluster in the extracted data is equal to the ratio of each cluster in the entire original data.

[0073] Multiple sections classified into the same cluster have similar characteristics. In the above search process, the settings output from the processing device 510 are settings that enable extraction of extracted data in which the ratio of each cluster to the entire original data is equal and the relative frequency distribution of each feature is similar.

[0074] Therefore, the search process executed by the data center 500 can find settings that can obtain extracted data that is closer to the characteristics of the entire original data for a plurality of feature amounts.

[0075] (3) The processing device 510 ends the search process when one piece of extracted data with an error equal to or less than the threshold is extracted, and calculates an index value using the extracted data with an error equal to or less than the threshold. Therefore, the data center 500 can calculate an index value when one piece of extracted data with an error equal to or less than the threshold is extracted, and quickly output the result.

[0076] (4) If the calculated index value is equal to or greater than the predetermined value (step S170: YES), the processing device 510 notifies the user that a failure has been predicted. This allows the data center 500 to notify the user that a failure has been predicted before the failure actually occurs.

[0077] <Example of change> This embodiment can be modified as follows: This embodiment and the following modifications can be combined and implemented within the scope of technical compatibility.

[0078] In the above embodiment, an example has been shown in which the information processing device is embodied as the data center 500. Then, an example has been shown in which the index value is calculated in the data center 500. In contrast, the above information processing device may be embodied as the information processing terminal 600. In this case, the index value is calculated by the processing device 610 of the information processing terminal 600. The above information processing device may be embodied as a control device of the vehicle 10. In this case, the index value can also be calculated by the control device of the vehicle 10. For example, the index value can also be calculated by the control device 40 of the vehicle 10.

[0079] In the above embodiment, an example was shown in which one extracted data item was extracted and an index value was calculated. However, a final index value may be determined using multiple index values ​​calculated using multiple extracted data items. For example, the minimum value, maximum value, mode value, and average value may be used as the final index value. Also, multiple index values ​​may be output.

[0080] In the above embodiment, an example was shown in which a notification that a failure has been predicted is given when the index value is equal to or greater than a predetermined value. This may be omitted. After the index value is calculated, only the process of step S190 may be executed and only the index value may be output.

[0081] The data center may predict the occurrence of a failure of the motor 20 based on a comparison of the index value with the total mileage or total driving time of the vehicle. In this case, even if the index value does not reach or exceed a predetermined value, the occurrence of a failure can be predicted if the index value is significantly larger than a standard index value for the total mileage or total driving time. For example, as shown in Figure 6, the data center may compare the index value Y with a standard line T that shows the trend of the index value with respect to the total mileage, and predict a failure if the index value Y is significantly larger.

[0082] In the above embodiment, the degree of deterioration is given as an example of an index value to be calculated, but the index value to be calculated is not limited to the degree of deterioration. If there are multiple targets for which damage is to be calculated, a damage index value may be calculated for each target. A relative frequency distribution may be calculated for each feature of each target, and an extraction pattern may be searched for that minimizes the error of the relative frequency distribution for all feature amounts.

[0083] A clipping pattern may be searched for so that the relative frequency distribution of the feature amount for each object becomes small. Then, an index value may be calculated for each object. In the above example, the processing device 510 sets multiple time windows so that the ratio of each cluster in the original data is equal to the ratio of each cluster in the extracted data. However, the processing device 510 may set multiple time windows without imposing such a constraint. In this case, the process of step S110 for performing clustering may be omitted.

[0084] 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 predetermined rule and repeated trials may be performed.

[0085] 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 square error as the error. The processing device 510 may calculate the root mean square error as the error.

[0086] In the above embodiment, the product of the temperature of the motor 20 and the duration of the temperature of the motor 20 is used as an example of data calculated from the temperature of the motor and the duration of the temperature of the motor 20, but this is not limiting. For example, the data on the temperature of the motor 20 and the duration of the temperature of the motor 20 may each be used as a feature quantity.

[0087] In the above embodiment, the data calculated from the oil temperature and the duration of the oil temperature change is the product of the oil temperature and the duration of the oil temperature change, but this is not limiting. For example, the oil temperature and the duration of the oil temperature change may each be used as a feature quantity. [Explanation of symbols]

[0088] 10...vehicle, 20...motor, 30...power transmission mechanism, 40...control device, 50...oil pump, 60...oil cooler, 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 device that acquires original data collected over a predetermined period of time using a plurality of sensors mounted on a vehicle and calculates an index value that indicates the degree of damage accumulated in the oil of an electric motor, a processing unit for performing processing; the processing device calculates a plurality of feature amounts based on the original data; the original data includes information on the temperature of the electric motor and the duration of the temperature of the electric motor; the plurality of feature amounts include data calculated from a temperature of the electric motor and a duration of the temperature of the electric motor; a second step of setting a plurality of time windows to extract data for a portion of the original data such that the sum of the periods of all the time windows is shorter than the predetermined period; a third step of extracting data from the original data using the plurality of time windows; a fourth step of calculating, for each of the features, the relative frequency distribution in extracted data obtained by combining the data extracted using 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, wherein after performing the first step, a search process is performed in which trials from the second step to the fifth step are repeated with settings of the plurality of time windows changed to extract the extracted data for 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 smaller than a threshold value. Information processing device.

2. the original data includes information on the oil temperature and the duration of the oil temperature; The plurality of feature amounts includes data calculated from the oil temperature and the duration of the oil temperature. The information processing device according to claim 1 .

3. In the fifth step, the information processing device calculates, as the error, a sum of differences in relative frequency for each class between the relative frequency distribution of the original data and the relative frequency distribution of the extracted data. The information processing device according to claim 1 .

4. the processing device performs clustering, which is machine learning, to classify data in each section obtained by dividing the original data 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. The information processing device according to claim 1 .

5. When the index value is equal to or greater than a predetermined value, the processing device issues a notification that a failure of the electric motor has been predicted. The information processing device according to claim 1 .

Images