Vehicle evaluation system

Abstract

To provide a vehicle evaluation system with which it is possible to discriminate and evaluate a difference in degree of vehicles from sound data.SOLUTION: A data center 100 which is one example of a vehicle evaluation system comprises a processing circuit 110 and a storage device 120. The storage device 120 stores the data of a trained model. The processing circuit 110 inputs sound data for evaluation to the trained model and outputs generated data. The processing circuit 110 executes clustering respectively on operation data at the time the sound data for evaluation was collected and the generated data, which is the machine learning for classifying, into the default number of clusters, the data of each section having been divided for a certain period that is shorter than a default time. The processing circuit 110 outputs an evaluation result indicating that the greater the deviation of the data resulting from clustering of reference data and the generated data from the data resulting from clustering of the operation data, the greater the deviation of the state of a target vehicle 10 from the state of a reference vehicle.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a vehicle evaluation system. [Background technology]

[0002] Patent Document 1 discloses an abnormality determination device that determines an abnormality in a power transmission device using a trained model trained by machine learning. This abnormality determination device inputs variables indicating the vehicle operation status by the driver into the trained model as input variables, and causes the trained model to output an estimated value of oil temperature. Then, using the estimated value output by the trained model, this abnormality determination device determines whether the cause of the oil temperature exceeding a determination value is an abnormality in the power transmission device or vehicle operation by the driver. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-017843 Summary of the Invention [Problem to be solved by the invention]

[0004] An evaluation system is being considered that evaluates vehicles by analyzing sound data recorded from the vehicle using a trained model trained by machine learning. However, in order to evaluate a vehicle, it is necessary not only to distinguish from the sound data whether the vehicle is clearly malfunctioning and making abnormal noises, but also to distinguish and evaluate the level of the vehicle from the sound data. Therefore, a vehicle evaluation system suitable for evaluating vehicles is required. [Means for solving the problem]

[0005] A vehicle evaluation system for solving the above problem is a vehicle evaluation system that evaluates a vehicle using sound data recorded from a vehicle to be evaluated. The vehicle evaluation system includes a processing circuit and a storage device. The storage device stores data of a trained model trained by supervised learning to generate operation data from the training sound data using training data including training sound data recorded while a reference vehicle in a state serving as a reference for evaluation is operated in a measurement driving pattern for a predetermined time period, and operation data consisting of multiple variables indicating the operating status of the vehicle collected simultaneously with the training sound data. The processing circuit inputs the evaluation sound data recorded while a target vehicle, which is the vehicle to be evaluated, is operated in the measurement driving pattern into the trained model and outputs generated data, which is the operation data. The processing circuit performs clustering, a machine learning method, on the operation data when the evaluation sound data was recorded and the generated data, classifying data for each section divided into fixed periods shorter than the predetermined time into a predetermined number of clusters using each of the variables as explanatory variables. The processing circuit outputs an evaluation result indicating that the greater the deviation between the reference data, which is the data resulting from clustering the operational data, and the data resulting from clustering the generated data, the greater the deviation of the state of the target vehicle from the state of the reference vehicle. [Effects of the Invention]

[0006] The difference between the clustering results of the operational data and the clustering results of the generated data reflects the difference in the condition of the target vehicle and the reference vehicle. Therefore, the vehicle evaluation system can determine the difference in the condition of the vehicle from the sound data and perform the evaluation. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a schematic diagram showing an embodiment of a vehicle evaluation system. [Figure 2]Figure 2 is a graph showing an example of operational data. (a) shows the transition of engine speed, (b) shows the transition of input shaft speed, (c) shows the transition of output shaft speed, and (d) shows the transition of gear ratio. [Figure 3] FIG. 3 is a graph showing an example of generated data and operational data, and an error in the generated data. [Figure 4] FIG. 4 is a flowchart showing the flow of a series of processes relating to the evaluation of a target vehicle. [Figure 5] FIG. 5 is a graph showing an example of clustering using two explanatory variables. [Figure 6] FIG. 6 is an explanatory diagram showing a comparative example of data resulting from clustering. DETAILED DESCRIPTION OF THE INVENTION

[0008] An embodiment of a vehicle evaluation system will be described below with reference to FIGS. <Vehicle evaluation system configuration> The vehicle evaluation system of this embodiment is configured as a data center 100. As shown in FIG. 1, the data center 100 is communicatively connected to a data acquisition device 300 via a communication network 200. As shown in FIG. 1, the data center 100 includes a storage device 120 in which a program is stored, and a processing circuit 110. The processing circuit 110 executes the program stored in the storage device 120 to perform various processes. The data center 100 also includes a communication device 130.

[0009] The data acquisition device 300 is, for example, a personal computer. The data acquisition device 300 includes a storage device 320 in which a program is stored, and a processing circuit 310. The processing circuit 310 executes the program stored in the storage device 320 to perform various processes. The data acquisition device 300 also includes a communication device 330. In this embodiment, the data acquisition device 300 is connected to the data center 100 by wireless communication via the communication network 200. The data acquisition device 300 also includes a display device 340 that displays information. The data acquisition device 300 also includes a microphone 350.

[0010] When using this vehicle evaluation system to evaluate a target vehicle 10, which is a vehicle to be evaluated, a microphone 350 is installed at a predetermined position relative to the target vehicle 10. In addition, a data acquisition device 300 is connected to the vehicle control unit 20 of the target vehicle 10. An operator then operates the target vehicle 10 to operate the target vehicle 10 in a measurement driving pattern. The measurement driving pattern is a driving pattern suitable for acquiring data for evaluation. The measurement driving pattern is a predetermined driving pattern spanning a predetermined period of time. The data acquisition device 300 records sound with the microphone 350 while the target vehicle 10 is operating in the measurement driving pattern. In addition, the data acquisition device 300 acquires operational data indicating the operating status of the target vehicle 10 simultaneously with recording the sound data.

[0011] The vehicle control unit 20 controls each part of the target vehicle 10. Various sensors that detect the state of the target vehicle 10 are connected to the vehicle control unit 20. When the data acquisition device 300 is connected to the vehicle control unit 20, the data acquisition device 300 can acquire information about the target vehicle 10 through the vehicle control unit 20.

[0012] <Outline of evaluation by the vehicle evaluation system> As described above, in this vehicle evaluation system, when evaluating the target vehicle 10, the data acquisition device 300 is connected to the vehicle control unit 20 of the target vehicle 10. Then, while the target vehicle 10 is operating, the data acquisition device 300 records sound with the microphone 350. The data acquisition device 300 transmits data including data on the recorded sound to the data center 100. Then, the data center 100 evaluates the target vehicle 10 using the received data.

[0013] The data acquisition device 300 records sound data collected by the microphone 350 while the target vehicle 10 is operating in a measurement driving pattern for a predetermined time in the storage device 320 as evaluation sound data. The data acquisition device 300 also stores operation data collected simultaneously with the sound data in the storage device 320. For example, when evaluating the transmission of the target vehicle 10, the operation data includes the engine speed, the transmission input shaft speed, the transmission output shaft speed, and the gear ratio.

[0014] FIG. 2 shows an example of operational data when evaluating the transmission of the target vehicle 10. FIG. 2 shows a portion of the operational data for a predetermined time period. FIG. 2(a) shows the transition of the engine rotation speed included in the operational data. The engine rotation speed is the number of rotations of the engine output shaft per unit time. FIG. 2(b) shows the transition of the transmission input shaft rotation speed. The input shaft rotation speed is the number of rotations of the continuously variable transmission input shaft per unit time. FIG. 2(c) shows the transition of the transmission output shaft rotation speed. The output shaft rotation speed is the number of rotations of the continuously variable transmission output shaft per unit time. FIG. 2(d) shows the transition of the gear ratio of the continuously variable transmission. As described above, such operational data is detected by sensors connected to the vehicle control unit 20 and stored in the storage device 320 of the data acquisition device 300.

[0015] The data acquisition device 300 stores the collected operational data including the evaluation sound data in the storage device 320 as one data set for a predetermined time period. The data acquisition device 300 extracts data from a data set for a predetermined time stored in the storage device 320 while changing the extraction start time for each piece of data within a window Tw, which has a time width shorter than the predetermined time, and shapes the extracted data into evaluation data. That is, the data acquisition device 300 extracts data for a period shorter than the predetermined time and shapes the extracted data into evaluation data. Note that, in the data shaping process for shaping the evaluation data, the data acquisition device 300 converts the evaluation sound data into a mel spectrogram, which is frequency-analyzed, and treats the resulting data as image data. In a mel spectrogram, the vertical axis represents frequency, and the frequency on the vertical axis is expressed in mel scale. The horizontal axis represents time. In a mel spectrogram, intensity is represented by color. Lower intensity portions are represented by darker blue colors, and higher intensity portions are represented by brighter red colors. The sound data included in one data set for the predetermined time becomes one mel spectrogram for the predetermined time. The data acquisition device 300 transmits the shaped evaluation data to the data center 100. Upon receiving the evaluation data, the data center 100 stores the evaluation data in the storage device 120. The data center 100 then uses the evaluation data to evaluate the target vehicle 10. A routine for performing this evaluation is executed by the processing circuit 110 of the data center 100.

[0016] The data center 100 performs a comparison process and an evaluation process to evaluate the target vehicle 10. The comparison process is a process in which the evaluation sound data included in the evaluation data is input into a learned model trained by supervised learning, generated data is output, and the generated data is compared with the operating data.

[0017] The trained model is a model trained by supervised learning using a large amount of training data including training sound data and operation data collected simultaneously with the training sound data so that operation data can be generated from the training sound data. The generated data is operation data generated by inputting the evaluation sound data into the trained model.

[0018] In the data center 100, for example, the evaluation sound data is converted into image data and handled, so a model that partially uses the image classification model ResNet-18 is used. ResNet-18 is a pre-trained image classification model trained on the ImageNet dataset. ResNet-18 has been trained on over one million image data and can classify input images into 1,000 categories. The trained model stored in the storage device 120 of the data center 100 is a model obtained by transfer learning of the pre-trained ResNet-18. This trained model is a model in which the classification output layer of ResNet-18 is replaced with a multilayer perceptron and this multilayer perceptron is trained using supervised learning. Training involves adjusting the weights and biases of each layer of this multilayer perceptron. The training sound data is sound data recorded while a reference vehicle in a state that serves as a reference for evaluation is operated using a measurement driving pattern. In this example, the reference vehicle is a vehicle that has completed a certain amount of break-in driving after manufacture, has undergone thorough maintenance and inspection, and has been confirmed to be free of abnormalities. In other words, the reference vehicle is in extremely good condition with almost no deterioration.

[0019] The trained model is optimized to generate generated data that reproduces operational data from sounds emitted from a reference vehicle. Therefore, if evaluation sound data emitted from a target vehicle 10 in a state different from that of the reference vehicle is input, the operating status data cannot be correctly generated. In other words, if the state of the target vehicle 10 deviates from that of the reference vehicle, a discrepancy occurs between the operational data stored in the dataset as correct data and the generated data. A larger discrepancy indicates that the state of the target vehicle 10 deviates from that of the reference vehicle. As described above, the reference vehicle is in extremely good condition with little deterioration. Therefore, in this vehicle evaluation system, the smaller the evaluation index value indicating the magnitude of this discrepancy, the closer the state of the target vehicle 10 is to the state of the reference vehicle and the higher the evaluation is. In this vehicle evaluation system, the generated data and the operational data are divided into fixed periods and each section is clustered. If the discrepancy between the generated data and the operational data is large, the discrepancy in the clustering results also becomes large. Therefore, the magnitude of the discrepancy in the clustering results reflects the difference in the state of the target vehicle 10 and the reference vehicle. Therefore, in this vehicle evaluation system, the clustering results are compared in the comparison process, and the vehicle evaluation system calculates an evaluation index value using the results of this comparison process in the evaluation process.

[0020] FIG. 3 is a graph showing operational data and generated data generated using a trained model. The graph in FIG. 3 shows only one of the multiple variables included in the operational data. In other words, it shows only one of the objective variables that are the output of the trained model. In FIG. 3, the operational data, which is the correct data, is shown with a solid line. In addition, in FIG. 3, the generated data is shown with a square symbol. The trained model outputs one value of the generated data in window Tw for each variable based on the data within that window Tw that has been formatted into a list. The error ΔPred indicates the deviation of the generated data from the operational data, which is the correct data, i.e., the magnitude of the deviation. The more the state of the target vehicle 10 deviates from the state of the reference vehicle, the larger the error ΔPred.

[0021] <Flow of a series of processes executed by the data center 100> Below, a description will be given with reference to a flowchart of a series of processes including the comparison process and evaluation process executed by the data center 100. Note that below, the step number of each process will be represented by a number preceded by "S."

[0022] As described above, upon receiving the evaluation data, the data center 100 stores the evaluation data in the storage device 120. Then, the processing circuit 110 of the data center 100 executes the routine shown in FIG.

[0023] 4, when the processing circuit 110 starts this routine, it reads the operational data and the evaluation data (S100). Then, the processing circuit 110 reads the list of the read evaluation data one by one, inputs the list into the trained model, and calculates the generated data (S110).

[0024] Next, the processing circuit 110 performs clustering on the historical data and the generated data (S120). Specifically, the processing circuit 110 divides the historical data and the generated data into fixed periods. The length of the period dividing the historical data and the generated data is shorter than a predetermined time. The length of the period dividing the historical data and the generated data may be the same as the window Tw, for example. Then, the processing circuit 110 performs clustering, which is machine learning, to classify 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 pre-specified number of clusters. The clustering algorithm is not limited to the k-means method.

[0025] Operational data includes data collected during different driving states, such as data during idling, steady driving, acceleration, deceleration, and gear changes. Clustering allows the data included in the operational data to be classified into clusters of data with similar characteristics. The number of clusters to be classified can be set arbitrarily depending on the content of the analysis.

[0026] FIG. 5 is a graph showing an example of clustering operation data into four clusters using the k-means method, using two explanatory variables included in the operation data as explanatory variables. In FIG. 5, the operation data is divided into a certain period, and each data segment is represented by a single point. When performing clustering, the processing circuit 110 uses a representative value of the explanatory variables in the data for each segment. For example, the processing circuit 110 sets the average value of the explanatory variables in the data for each segment as the representative value. The processing circuit 110 may also use a moving average value of the feature values ​​for multiple consecutive segments in a time series as the representative value.

[0027] In Figure 5, these points are shown in a two-dimensional space with the first explanatory variable EXV_a and the second explanatory variable EXV_b as coordinate axes. Figure 5 shows an example in which operational data is clustered into four clusters: a first cluster CL_1, a second cluster CL_2, a third cluster CL_3, and a fourth cluster CL_4. In Figure 5, the boundaries of the four clusters are shown with solid lines.

[0028] 5 shows an example in which there are two explanatory variables. When clustering operation data including four explanatory variables as shown in FIG. 2, the processing circuit 110 clusters the operation data in a four-dimensional coordinate space. The processing circuit 110 also performs such clustering on the generated data.

[0029] The processing circuit 110 performs such clustering on the operational data and the generated data, respectively. Then, the processing circuit 110 assigns labels indicating the clustering results to the operational data and the generated data, respectively. Specifically, the processing circuit 110 assigns a label identifying the cluster into which the data is classified to each piece of data represented by a point in the coordinate space. In this way, the processing circuit 110 creates labeled operational data and generated data. The labeled operational data is reference data.

[0030] Figure 2 shows an example of one range in the operational data labeled with the first cluster CL_1, one range in the operational data labeled with the second cluster CL_2, and one range in the operational data labeled with the third cluster CL_3, each surrounded by a dashed line.

[0031] After clustering is performed to create reference data, which is data resulting from clustering the operational data, and data resulting from clustering the generated data (S120), the processing circuit 110 compares these resulting data (S130). Specifically, as shown in FIG. 6, the processing circuit 110 compares the labels assigned to the data in each section of the generated data with the labels assigned to the data in each section of the reference data. In this comparison, labels corresponding to the same time are compared. Then, the processing circuit 110 identifies locations where the data resulting from clustering the generated data does not match the reference data.

[0032] Fig. 6 shows the labels assigned to the historical data and the labels assigned to the generated data at each time from time t1 to time t8. In Fig. 6, the parts where the labels assigned to the historical data and the generated data do not match are indicated by dashed lines. In Fig. 6, the label of the first cluster CL_1 is indicated as "1", the label of the second cluster CL_2 is indicated as "2", the label of the third cluster CL_3 is indicated as "3", and the label of the fourth cluster CL_4 is indicated as "4".

[0033] The processing circuit 110 stores and records the comparison results in the storage device 120 (S140). Then, the processing circuit 110 calculates an evaluation index value based on the comparison results recorded in the storage device 120 (S150). The processing circuit 110 calculates, as the evaluation index value, for example, the proportion of time during which data from sections whose clustering results do not match the reference data is taken up within a predetermined time period. The processing circuit 110 may also calculate, as the evaluation index value, for example, the proportion of the number of sections whose clustering results do not match the reference data to the total number of sections in the generated data.

[0034] After calculating the evaluation index value in this way, the processing circuit 110 determines the evaluation rank based on the evaluation index value and outputs the evaluation rank as the evaluation result (S160). For example, the processing circuit 110 determines the evaluation rank by selecting an evaluation rank according to the magnitude of the evaluation index value from four evaluation ranks: S rank, A rank, B rank, and C rank. S rank is the highest evaluation rank of the four evaluation ranks. And C rank is the lowest evaluation rank of the four evaluation ranks. The evaluations decrease in order from S rank to A rank, B rank, and C rank.

[0035] In the case of the evaluation index value in the above example, the larger the evaluation index value, the more the data resulting from clustering the generated data deviates from the reference data. Therefore, the processing circuit 110 selects a lower evaluation rank as the evaluation index value increases. The processing circuit 110 transmits the evaluation rank to the data acquisition device 300 and outputs the evaluation rank (S160). After outputting the evaluation rank in this manner, the processing circuit 110 ends this routine.

[0036] The data acquisition device 300 receives the evaluation rank and displays the received evaluation rank on the display device 340 as the evaluation rank of the target vehicle 10 . <Operation of this embodiment> The data center 100 inputs evaluation sound data recorded while a target vehicle 10, which is a vehicle to be evaluated, is operated according to a measurement driving pattern into a trained model and outputs generated data (S110). The data center 100 then performs clustering on the operation data obtained when the evaluation sound data was recorded and the generated data (S120). The data center 100 compares reference data, which is data resulting from clustering the operation data, with data resulting from clustering the generated data (S130). The data center 100 then outputs an evaluation result indicating that the greater the deviation between these data, the greater the deviation of the state of the target vehicle 10 from the state of the reference vehicle (S150, S160).

[0037] The processes from S100 to S140 correspond to the comparison process, and the processes from S150 to S160 correspond to the evaluation process. As described above, the reference vehicle is a vehicle in extremely good condition with almost no deterioration. Therefore, the data center 100 evaluates the target vehicle 10 higher as the evaluation index value becomes smaller, since the condition of the target vehicle 10 is closer to that of the reference vehicle.

[0038] <Effects of this embodiment> (1) The data center 100 divides the generated data and the operational data into fixed intervals and clusters each interval. If there is a large discrepancy between the generated data and the operational data, the discrepancy in the clustering results will also be large. Therefore, the magnitude of the discrepancy in the clustering results reflects the difference in the condition of the target vehicle 10 and the reference vehicle. Therefore, the data center 100 calculates an evaluation index value by comparing the clustering results. Therefore, the data center 100 can determine the difference in the degree of the target vehicle 10 from the sound data and perform an evaluation.

[0039] (2) The processing circuit 110 of the data center 100 selects an evaluation rank from a preset number of evaluation ranks according to the magnitude of the evaluation index value, and outputs the selected evaluation rank as the evaluation result.

[0040] The data center 100 outputs the evaluation results by applying them to a preset evaluation rank. Therefore, this evaluation system makes it easy to understand the relative level of the condition of the target vehicle 10 in the used car market.

[0041] <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.

[0042] The data used as evaluation data does not have to be a mel spectrogram. For example, a spectrogram obtained by wavelet transforming sound data may be used. A spectrogram obtained by short-time Fourier transforming sound data may also be used. It is not necessary to convert sound data into image data. For example, features may be extracted from the sound data itself and used as evaluation data. In this case, there is no need to use ResNet-18, which handles image data, as a trained model. Also, although a model using transfer learning of ResNet-18 has been shown as an example, the model structure is not limited to this. The trained model only needs to be able to output generated data based on the evaluation data.

[0043] The number of evaluation ranks does not have to be four. For example, the number of evaluation ranks may be increased. Conversely, the number of evaluation ranks may be decreased. Although an example in which the evaluation rank is determined based on the evaluation index value has been shown, the evaluation method is not limited to this. For example, the evaluation index value may be output as is, with a larger value indicating a lower evaluation, and displayed on the display device 340.

[0044] In the above vehicle evaluation system, an example is shown in which a vehicle in extremely good condition is used as the reference vehicle to evaluate the target vehicle 10. The reference vehicle does not necessarily have to be a vehicle in good condition. For example, a vehicle in extremely poor condition with a low rating can also be used as the reference vehicle. The above evaluation index value is a value that indicates the degree of deviation between the condition of the target vehicle 10 and that of the reference vehicle. Therefore, if an aging vehicle with an extremely low rating is used as the reference vehicle, the smaller the evaluation index value, the lower the rating. The target vehicle 10 can also be evaluated using such evaluation index values.

[0045] A vehicle evaluation system can also be configured using the data acquisition device 300 by storing trained model data in the storage device 320 of the data acquisition device 300. In this case, the processing circuit 310 of the data acquisition device 300 executes the series of processes shown in FIG.

[0046] The data acquisition device 300 itself does not have to be equipped with a microphone 350. Sound data can be acquired from an external device and subjected to data shaping processing and the series of processing shown in Fig. 4. The series of processing shown in Fig. 4 may be performed using multiple sound data recorded using multiple microphones 350.

[0047] In the above embodiment, an example was shown in which the operation data included data on the rotational speed of a rotating shaft in the powertrain as an example of evaluating the transmission of the target vehicle 10. The vehicle evaluation system may also evaluate the target vehicle 10 by evaluating other units in the target vehicle 10. For example, to evaluate an engine, data on the engine speed, ignition timing, and engine load factor may be used as operation data. For example, to evaluate a drive motor, data on the rotational speed of the motor's output shaft may be used as operation data. To evaluate a four-wheel drive vehicle, data on the rotational speed of each drive wheel may be used as operation data. The vehicle evaluation system may also evaluate the target vehicle 10 by referring to the evaluation index values ​​of various units.

[0048] In the above embodiment, the vehicle evaluation system includes a processing circuit 110 and a storage device 120 to execute software processing. However, this is merely an example. For example, the vehicle evaluation system may include a dedicated hardware circuit (e.g., an ASIC) that processes at least part of the software processing executed in the above embodiment. That is, the vehicle evaluation system may have any of the following configurations (A) to (C). (A) The vehicle evaluation system includes an execution device that executes all processing in accordance with a program and a storage device that stores the program. That is, the vehicle evaluation system includes a software execution device. (B) The vehicle evaluation system includes an execution device that executes part of the processing in accordance with the program and a storage device. Furthermore, the vehicle evaluation system includes a dedicated hardware circuit that executes the remaining processing. (C) The vehicle evaluation system includes a dedicated hardware circuit that executes all processing. Here, there may be multiple software execution devices and / or dedicated hardware circuits. That is, the above processing may be executed by a processing circuitry that includes at least one of one or more software execution devices and one or more dedicated hardware circuits. A storage device, i.e., a computer-readable medium, that stores a program includes any available medium accessible by a general-purpose or dedicated computer. [Explanation of symbols]

[0049] 10...Target vehicle, 20...Vehicle control unit, 100...Data center, 110...Processing circuit, 120...Storage device, 130...Communication device, 200...Communication network, 300...Data acquisition device, 310...Processing circuit, 320...Storage device, 330...Communication device, 340...Display device, 350...Microphone

Claims

1. A vehicle evaluation system that evaluates a vehicle to be evaluated using sound data that records sounds emitted from the vehicle, the system comprising: a processing circuit; and a storage device; The storage device stores data of a trained model that has been trained by supervised learning to generate the operation data from the training sound data using training data including training sound data recorded while a reference vehicle in a state that serves as a reference for evaluation is operated in a measurement driving pattern for a predetermined time period, and operation data consisting of a plurality of variables that indicate the operation status of the vehicle and that is collected simultaneously with the training sound data; Outputting generated data, which is the operation data generated by inputting evaluation sound data recorded while operating a target vehicle that is a vehicle to be evaluated according to the measurement driving pattern into the trained model; and performing clustering, which is machine learning, on the operational data and the generated data when the evaluation sound data was recorded, in which data of each section divided into fixed periods shorter than the predetermined time is classified into a predetermined number of clusters using each of the variables as explanatory variables; and outputting an evaluation result indicating that the state of the target vehicle deviates from the state of the reference vehicle to the extent that reference data, which is data resulting from clustering the operational data, deviates from the data resulting from clustering the generated data.

2. The processing circuit compares the data resulting from clustering the generated data with the reference data, and calculates, as an evaluation index value, a proportion of the time occupied by data in a section in which the result does not match the reference data during the predetermined time period. The vehicle evaluation system according to claim 1 .

3. The processing circuit compares the data resulting from clustering the generated data with the reference data, and calculates, as an evaluation index value, the ratio of the number of sections in which the results do not match the reference data to the total number of sections in the generated data. The vehicle evaluation system according to claim 1 .

4. The processing circuit selects an evaluation rank according to the magnitude of the evaluation index value from a predetermined number of evaluation ranks, and outputs the selected evaluation rank as the evaluation result. The vehicle evaluation system according to claim 2 or 3.

5. The operation data includes data on the rotation speed of a rotating shaft in a powertrain. The vehicle evaluation system according to claim 1 .

Images