JP2024050160A - Vehicle Evaluation System - Google Patents

Abstract

To provide a vehicle evaluation system with which it is possible to determine a difference in vehicle level from sound data and evaluate it.SOLUTION: This vehicle evaluation system comprises a processing circuit 110 and a storage device 120. Stored in the storage device 120 is the data of a trained model that has been trained so as to generate, from operational data for training, feature data that indicates the features of reference sound data. The processing circuit 110 executes a generation process of inputting, to the trained model, the operational data for training that has been collected while operating a target vehicle 10 over a prescribed duration and outputting feature data that is thereby generated. The processing circuit 110 also executes an evaluation process of comparing the generated data with the target feature data of the sound data that was recorded simultaneously with the operational data for training, and evaluating the target vehicle 10 in accordance with the magnitude of deviation between the generated data and the target feature data.SELECTED DRAWING: Figure 1

Description

This invention relates to a vehicle evaluation system that evaluates vehicles.

The abnormal sound detection device disclosed in Patent Document 1 determines the occurrence of an abnormal sound using the frequency spectrum of the measured sound data. Specifically, the abnormal sound detection device calculates the area that exceeds a threshold level in the frequency spectrum of the measured sound data. The abnormal sound detection device then compares the calculated area with a determination value to determine whether an abnormal sound has occurred.

JP 2014-222189 A

In order to evaluate a vehicle, it is necessary not only to distinguish whether it is clearly broken and making abnormal noises, but also to distinguish between different levels of vehicle condition and evaluate it accordingly. Therefore, there is a demand for a vehicle evaluation system that is suitable for evaluating vehicles.

The means for solving the above problems and their effects will be described below.
A vehicle evaluation system for solving the above problem evaluates a target vehicle using sound data recorded from a target vehicle that is a vehicle to be evaluated. The vehicle evaluation system includes a processing circuit and a storage device. The storage device stores data of a learned model trained by supervised learning using training data including reference sound data recorded while a reference vehicle in a state serving as a reference for evaluation is operated for a predetermined time, and training operation data indicating the operating status of the reference vehicle collected simultaneously with the reference sound data, to generate feature data indicating features of the reference sound data from the training operation data. The processing circuit executes a generation process of inputting the evaluation operation data collected while the target vehicle is operated for the predetermined time into the learned model and outputting generated data, which is the feature data generated, and an evaluation process of comparing the generated data with target feature data, which is the feature data of the sound data recorded simultaneously with the evaluation operation data, and evaluating the target vehicle according to the magnitude of deviation between the target feature data and the generated data.

The difference between the condition of the target vehicle and the reference vehicle is reflected in the magnitude of the deviation between the generated data and the target feature data. Therefore, the vehicle evaluation system can determine the difference in the condition of the vehicle from the sound data and perform the evaluation.

FIG. 1 is a schematic diagram showing an embodiment of a vehicle evaluation system. FIG. 2 is a schematic diagram showing the configuration of the vehicle control unit. FIG. 3 is a flowchart of the data acquisition process. FIG. 4 is a flowchart of the data formatting process. FIG. 5 is a flowchart of the training process. FIG. 6 is a flowchart relating to the generation process and the evaluation process.

Hereinafter, an embodiment of a vehicle evaluation system will be described with reference to FIGS.
<Vehicle evaluation system configuration>
As shown in Fig. 1, this vehicle evaluation system includes a data center 100 and a data acquisition device 300. The data center 100 is communicatively connected to the 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.

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.

When using this vehicle evaluation system to evaluate a target vehicle 10, 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. Then, an operator operates the target vehicle 10 to operate the target vehicle 10. While the target vehicle 10 is being operated in this manner, the data acquisition device 300 records sounds with the microphone 350. In addition, the data acquisition device 300 simultaneously records the sound data and acquires evaluation operation data that indicates the operating status of the target vehicle 10.

2, the vehicle control unit 20 includes a storage device 22 in which a program is stored, and a processing circuit 21. The processing circuit 21 executes the program stored in the storage device 22 to perform various controls. The vehicle control unit 20 controls each part of the target vehicle 10. The vehicle control unit 20 is connected to various sensors that detect the state of the target vehicle 10. For example, a crank position sensor 34 is connected to the vehicle control unit 20. The crank position sensor 34 outputs a crank angle signal corresponding to a change in the rotation phase of a crankshaft, which is the output shaft of an internal combustion engine mounted on the target vehicle 10. The vehicle control unit 20 calculates the engine rotation speed NE, which is the rotation speed of the crankshaft, based on the crank angle signal. An air flow meter 33 is connected to the vehicle control unit 20. The air flow meter 33 detects the intake air temperature THA, which is the temperature of air drawn into the cylinder through the intake passage of the internal combustion engine mounted on the target vehicle 10, and the intake air amount Ga, which is the mass of the drawn air.

The vehicle control unit 20 is also connected to a transmission control unit 30 that controls the transmission mounted on the target vehicle 10. The vehicle control unit 20 acquires information on the gear ratio, input rotation speed Nin, output rotation speed Nout, and transmission oil temperature from the transmission control unit 30. The input rotation speed Nin is the rotation speed of the input shaft of the transmission. The output rotation speed Nout is the rotation speed of the output shaft of the transmission. When the data acquisition device 300 is connected to the vehicle control unit 20 of the target vehicle 10, the data acquisition device 300 becomes able to acquire information on the target vehicle 10 through the vehicle control unit 20.

<Evaluation process using 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 sounds with the microphone 350. The data acquisition device 300 transmits data including the recorded sound data to the data center 100. Then, the data center 100 executes an evaluation process for evaluating the target vehicle 10 using the received data.

The data acquisition device 300 collects operation data while operating the target vehicle 10 for a preset time. The data acquisition device 300 then records the collected operation data in the storage device 22 as evaluation operation data. The operation data is, for example, the engine speed NE, the input rotation speed Nin, the output rotation speed Nout, and the gear ratio. The data acquisition device 300 also records sound data collected by the microphone 350 simultaneously with the operation data as evaluation sound data in the storage device 320. The data acquisition device 300 also stores the intake air temperature THA detected by the air flow meter 33 in the storage device 320 as information on the outside air temperature when the sound data is being recorded. The data acquisition device 300 then stores the collected sound data, outside air temperature data, and evaluation operation data in the storage device 320 as one data set for a preset time.

The data acquisition device 300 cuts out data for a preset time period stored in the storage device 320 for each data range of a window Tw with a time width shorter than the preset time period, and shapes the data into evaluation data. In the data shaping process for shaping the evaluation data, the data acquisition device 300 performs time-frequency analysis on the evaluation sound data and stores the data resulting from the analysis as feature data in the storage device 320. Specifically, the feature data is data on sound pressure for each frequency at each time. For example, the feature data is data on sound pressure for multiple predetermined frequencies at each time.

The data acquisition device 300 transmits the shaped evaluation data to the data center 100. The data center 100 then inputs the evaluation operation data contained in the evaluation data shaped into multiple lists into a trained model trained by supervised learning, and performs evaluation processing.

<About the trained model>
The storage device 320 of the data center 100 stores data of a trained model used to evaluate the target vehicle 10. In this vehicle evaluation system, evaluation operation data acquired while operating the target vehicle 10 for a preset time is input into the trained model, and a generation process is executed to generate feature data as generated data. Note that the data center 100 in this embodiment uses a convolutional neural network as the trained model.

Next, we will explain the training process for training the model to obtain a learned model. The model is learned by supervised learning using a large amount of measurement data collected in advance using a reference vehicle that serves as the basis for evaluation. In this example, the reference vehicle is one that has completed a certain amount of break-in driving after manufacture, has been thoroughly inspected and maintained to ensure that there are no abnormalities. In other words, the reference vehicle is one that is in extremely good condition with almost no deterioration.

<About data acquisition process>
The data acquisition process for acquiring the measurement data is executed by a computer that can be connected to the vehicle control unit 20 and acquire data, similar to the data acquisition device 300 .

Figure 3 is a flowchart showing the flow of the data acquisition process for acquiring measurement data. Note that, hereinafter, the step number of each process is represented by a number preceded by "S". This data acquisition process is executed while the reference vehicle is operating. As shown in Figure 3, when the computer starts the data acquisition process, it starts measuring data (S100). Then, while operating the reference vehicle, the computer records sound data with the microphone 350 and acquires outside air temperature data and operating data. Note that, in order to train the model, this sound data that records the sound emitted by the reference vehicle is reference sound data. In addition, in order to train the model, this operating data collected from the reference vehicle is training operating data. In this example, as described above, the operating data is the engine rotation speed NE, the input rotation speed Nin, the output rotation speed Nout, and the gear ratio.

Next, the computer determines whether or not the collection of measurement data over the predetermined time has been completed (S110). If it is determined that the collection of measurement data has not been completed (step S110: NO), the computer repeats the process of S110. On the other hand, if the collection of measurement data has been completed (S110: YES), the computer proceeds to the process of S120. Then, the computer ends the data measurement (S120). When the measurement is thus ended, the computer records the measurement data for the predetermined time as one data set in the storage device (S130). Then, the computer temporarily ends this data acquisition process. In this way, the acquisition of one data set is completed. The collection of training data used for supervised learning is performed by performing this data acquisition process many times and collecting a large amount of data sets of measurement data collected while operating the reference vehicle. The data set of measurement data collected in this way is shaped through the data shaping process shown in FIG. 4.

<About data formatting processing>
The data shaping process is a process of cutting out one data set while shifting the window Tw and shaping the data into a plurality of lists. This data shaping process is performed by a computer. The computer that performs this data shaping process may be the same as the computer that executes the data acquisition process, or may be a different computer.

When the data shaping process begins, the computer first loads one data set of measurement data (S200). Next, the computer performs time-frequency analysis of the sound data in the data set loaded in the process of S200 (S210). Specifically, the computer calculates the sound pressure for each frequency at each time. In this way, the computer calculates feature data from the sound data. Next, the computer standardizes data other than the sound data in the data set loaded in the process of S200 (S220).

Next, the computer sets the data extraction start time t to 0 (S230). Then, the computer extracts the data (S240). That is, the computer aligns the start point of window Tw with extraction start time t, and extracts the data within the range of window Tw. Specifically, the computer extracts data within the range of window Tw from the operation data and outside temperature data. The computer also extracts data within the range of window Tw from the feature data.

Next, the computer calculates a representative value of the feature data from the data extracted through the processing of S240 (S250). For example, the computer calculates sound pressure data at a plurality of predetermined frequencies at the center time from the data within the range of window Tw as a representative value. Next, the computer determines whether to shift window Tw by stride t_st (S260). Data extraction is performed by repeatedly shifting window Tw by stride t_st and extracting data from a data set acquired during the measurement pattern. When window Tw reaches the end of the data set and all data contained in the data set has been extracted, window Tw can no longer be shifted by stride t_st. When the computer determines that window Tw can no longer be shifted by stride t_st in this way, it makes a negative determination in the processing of S260.

If the computer determines that the window Tw should be shifted by the stride t_st (S260: YES), it stores the cut-out data and the set of representative values in one list (S270). When storing in the list, the computer shapes the operation data and the outside air temperature data into a matrix suitable for input to the convolution neural network. For example, if the operation data is four types of data, namely, the engine speed NE, the input speed Nin, the output speed Nout, and the gear ratio, the computer shapes the time series data for the five types of data, including the outside air temperature, into a matrix. If 20 samples of operation data and outside air temperature data are included during the window Tw, the computer shapes the operation data and outside air temperature data into a matrix with 5 rows and 20 columns. Then, the computer updates the cut-out start time t (S280). Specifically, the cut-out start time t is updated by adding the stride t_st to the cut-out start time t to obtain the new cut-out start time t. This causes the window Tw to be shifted by the stride t_st. Then, the computer shifts the window Tw by the stride t_st and executes the processes of S240 to S260 again. In other words, the computer repeats the processes of S240 to S280 until the window Tw can no longer be shifted by the stride t_st.

When the computer determines that the window Tw can no longer be shifted (S260: NO), it advances the process to S290. The process of S290 is the same as the process of S270. In the process of S290, when the data is stored in the list, the computer determines whether all the loaded data sets have been processed (S300). When it determines that the processing of all the data sets has not been completed (S300: NO), the computer returns the process to S200. Then, the computer loads one unprocessed data set and executes the process from S210 onwards. When it determines that all the data sets have been processed (S300: YES), the computer ends this series of data shaping processes. In this way, the computer repeatedly cuts out the prepared data sets to a size that fits into the window Tw, and shapes each of them into a list. In this way, a training process is performed to train a model using a large number of data sets that have been shaped into a set of multiple lists through the data shaping process.

<About training processing>
5 is a flowchart of the training process. This training process is performed by a computer. A large amount of data set shaped through a data shaping process is stored as training data in a storage device of the computer that executes the training process. When the training process is started, the computer first reads the training data stored in the storage device (S400). Next, the computer reads one data set from the read training data (S410). Next, the computer reads one list from the data set (S420).

Then, the computer inputs the operation data and outside temperature data from the list into the above-mentioned model to calculate the feature data as generated data (S430). Note that in this example, the computer calculates data equivalent to a representative value of the feature data as the generated data.

When the training process begins, the weights and biases of the convolutional neural network are set to initial values. In this training process, the weights and biases of the convolutional neural network are updated. Specifically, a list of explanatory variables consisting of operation data and outside temperature data is input to the input layer of the convolutional neural network. The value of the generated data is then output from the output layer of the convolutional neural network. After calculating the value of the generated data in this way, the computer records the value of the generated data (S440).

The computer then determines whether all lists included in the data set have been processed (S450). If it determines that processing of all lists has not been completed (S450: NO), the computer returns to S420. The computer then reads one unprocessed list (S420) and executes the processing from S430 onwards.

If it is determined that all lists have been processed (S450: YES), the computer proceeds to S460. The computer then outputs generated data for each list included in the loaded data set (S430). The computer then records the value of the output generated data (S440).

In the process of S460, the computer calculates an evaluation index value. The evaluation index value is a value indicating the magnitude of deviation between the generated data calculated through the process of S430 and the feature data included in the dataset. The feature data included in the dataset is feature data indicating the features of the reference sound data, and is a correct value. Here, the computer calculates the magnitude of deviation between the value calculated through the process of S430 and the correct value. When the evaluation index value is calculated in this way, the computer performs learning (S470). Specifically, the computer adjusts the weights and biases in the convolutional neural network by the backpropagation method so that the value of the evaluation index value becomes smaller. Next, the computer determines whether all the datasets included in the loaded training data have been processed (S480). If it is determined that the processing of all the datasets has not been completed (S480: NO), the computer returns the process to S410. Then, the computer reads one unprocessed dataset (S410) and executes the processes from S420 onwards. The computer repeats learning to train the model until the processing of all the datasets is completed in this way. In this way, the computer trains a model through supervised learning so that it can generate feature data that indicates the characteristics of the reference sound data from the operating data and outside temperature data.

If it is determined that all data sets have been processed (S480: YES), the computer records the parameters of the model that has completed learning using all data sets in the storage device (S490). The computer then ends this series of training processes. In this way, data of the trained model is obtained through the training process. The data of the trained model that has been trained through the training process is stored in the storage device 120 of the data center 100.

Next, the data acquisition process, data formatting process, and evaluation process when evaluating the target vehicle 10 using the vehicle evaluation system will be described.
<Data Acquisition Process by Data Acquisition Device 300>
When evaluating a vehicle using the vehicle evaluation system, as described above, the data acquisition device 300 is connected to the target vehicle 10, which is the vehicle to be evaluated. In addition, the microphone 350 is installed in the target vehicle 10. Then, an operator operates the target vehicle 10 to operate the target vehicle 10. While the target vehicle 10 is being operated in this manner, the data acquisition device 300 records sound with the microphone 350. In addition, the data acquisition device 300 simultaneously acquires data on the outside air temperature. In addition, the data acquisition device 300 acquires target operation data indicating the operating status of the target vehicle 10 at the same time as recording the sound data. Specifically, the data acquisition device 300 executes the data acquisition process described with reference to FIG. 3 to acquire one data set as evaluation data. The operation data included in the evaluation data is evaluation operation data.

<Data shaping process by data acquisition device 300>
The data acquisition device 300 executes a data shaping process to shape the evaluation data. Specifically, the data shaping process described with reference to FIG. 4 is executed to shape the evaluation data into a plurality of lists. Since only one evaluation data is acquired in the data acquisition process, only one data set is read and shaped in the data shaping process at this time. Through this data shaping process, the evaluation data is shaped into a plurality of lists of evaluation operating data, outside air temperature data, and target feature data. After executing the data shaping process to shape the evaluation data, the data acquisition device 300 transmits the shaped evaluation data to the data center 100.

<Evaluation Process by Data Center 100>
Upon receiving the evaluation data, the data center 100 stores the evaluation data in the storage device 120. Then, the data center 100 executes an evaluation process for evaluating the target vehicle 10 by executing a routine shown in FIG. 6. The routine shown in FIG. 6 is executed by the processing circuit 110 of the data center 100. As shown in FIG. 6, when this routine is started, the data center 100 reads the evaluation data stored in the storage device 120 (S500). Then, through the processes of S510 to S540, the data center 100 repeats the calculation of the generated data using the trained model stored in the storage device 120. Specifically, the data center 100 reads one list from the evaluation data (S510). The data center 100 inputs the data of the list into the trained model to calculate the generated data (S520), similar to the process of S430 in the training process. After calculating the generated data in this manner, the data center 100 records the value of the generated data (S530).

Next, the data center 100 determines whether all the lists included in the data set have been processed (S540). If it is determined that processing of all the lists has not been completed (S540: NO), the data center 100 returns the process to S510. Then, the data center 100 reads one unprocessed list (S510) and executes the processes from step S520 onwards. If it is determined that all the lists have been processed (S540: YES), the data center 100 advances the process to S550.

In this way, the data center 100 calculates the value of the generated data for each list included in the loaded evaluation data (S520). Then, the calculated value is recorded (S530). This series of processes from S510 to S540 is a generation process in which the evaluation operation data is input to the trained model and the generated data is output. Next, the data center 100 calculates the evaluation index value in the same manner as the process of S460 in the training process (S550). The trained model is optimized to generate generated data in which feature data is restored from operation data collected from a reference vehicle. Therefore, when evaluation operation data collected from a target vehicle 10 in a state different from that of the reference vehicle is input, the feature data cannot be restored correctly. In other words, if the state of the target vehicle 10 deviates from the state of the reference vehicle, a deviation occurs between the target feature data stored in the dataset as the correct data and the generated data. The evaluation index value indicates the magnitude of this deviation. In other words, the larger the evaluation index value, the more the state of the target vehicle 10 deviates from the state of the reference vehicle. As described above, the reference vehicle is a vehicle in an extremely good condition with almost no deterioration. Therefore, in this evaluation system, the smaller the evaluation index value, the closer the state of the target vehicle 10 is to the state of the reference vehicle, and the higher the evaluation. After calculating the evaluation index value in this manner, the data center 100 proceeds to S560.

The data center 100 determines the evaluation rank based on the evaluation index value (S560). The data center 100 determines the evaluation rank by selecting an evaluation rank according to the magnitude of the evaluation index value from among the four evaluation ranks of S rank, A rank, B rank, and C rank. The S rank is the evaluation rank indicating that the vehicle is the highest rated vehicle among the four evaluation ranks. The C rank is the evaluation rank indicating that the vehicle is the lowest rated vehicle among the four evaluation ranks. The evaluations are S rank, A rank, B rank, and C rank in descending order, with C rank being the lowest rated evaluation rank. After determining the evaluation rank of the target vehicle 10 through the processing of S560, the data center 100 proceeds to the processing of S570. The processing of S550 and the processing of S560 are evaluation processing in which the target feature data is compared with the generated data and the target vehicle 10 is evaluated according to the magnitude of the deviation between the target feature data and the generated data.

Next, the data center 100 transmits the evaluation rank to the data acquisition device 300 and outputs the evaluation rank (S570). After outputting the evaluation rank in this manner, the data center 100 ends this routine.

The data acquisition device 300 that receives the evaluation rank displays the received evaluation rank on the display device 340 as the evaluation rank of the target vehicle 10 .
<Action of this embodiment>
The data center 100 executes a generation process using the trained model to generate generated data by restoring feature data from the evaluation data. The trained model is a neural network in which the evaluation data extracted from a preset time period of data is used as an explanatory variable, and the feature data at the time point corresponding to the extracted data is used as a target variable. The data center 100 then executes an evaluation process based on the generated data. The training operation data and the target operation data are the engine rotation speed NE, the input rotation speed Nin, the output rotation speed Nout, and the gear ratio. That is, the training operation data and the evaluation operation data include data on the rotation speed of a rotating shaft in the powertrain.

In the evaluation process, the data center 100 calculates the sum of the deviations output for a preset time period for each data segment of the repeatedly extracted period while changing the extraction start time t as an evaluation index value. The data center 100 determines the evaluation rank of the target vehicle 10 based on the evaluation index value.

<Effects of this embodiment>
(1) The difference between the condition of the target vehicle 10 and the reference vehicle appears in the magnitude of the deviation between the generated data and the target characteristic data. Therefore, the vehicle evaluation system can determine the difference in the condition of the vehicle from the sound data and perform the evaluation.

(2) The above vehicle evaluation system divides data for a set period of time into multiple sections and analyzes them. The results are then integrated to calculate an evaluation index value. Therefore, with the above vehicle evaluation system, the trained model can be smaller than when analyzing data for a set period of time all at once.

(4) The vehicle evaluation system outputs the evaluation results by applying them to a preset evaluation rank. Therefore, this evaluation system makes it easier to understand the relative level of the condition of the target vehicle 10 in the used car market.

(5) Sound data can be affected by differences in the measurement environment even when the vehicle condition is the same. The vehicle evaluation system described above includes outside temperature data as data indicating the measurement conditions in the explanatory variables input to the trained model. Therefore, the vehicle evaluation system can perform evaluations that reflect the effects of differences in outside temperature. In this way, by including data indicating the measurement conditions in the explanatory variables, evaluations can be performed that reflect the effects of differences in measurement conditions.

<Example of change>
This embodiment can be modified as follows: This embodiment and the following modifications can be combined with each other to the extent that there is no technical contradiction.

The data reforming process may be performed in the data center 100 .
An example has been given in which a convolutional neural network is used as the trained model. The trained model is not limited to a convolutional neural network. For example, a recurrent neural network capable of handling time-series data may be used to output the generated data. For example, a long short-term memory network may be used to output the generated data.

The vehicle evaluation system may be composed of only the data center 100 that performs the generation process and evaluation process. In this case, the vehicle evaluation system is a system that performs the generation process and evaluation process using the received evaluation data and outputs the evaluation results. In addition, for example, the data of the trained model can be stored in the storage device 320 of the data acquisition device 300, and the vehicle evaluation system can be composed of only the data acquisition device 300. In this case, the generation process and evaluation process are executed in the data acquisition device 300.

- 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. As an example of the evaluation process, an evaluation rank is determined based on the evaluation index value, but the evaluation process is not limited to this form. For example, the evaluation index value may be output as it is, with a larger value indicating a lower evaluation, and displayed on the display device 340.

- 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. It is not necessary to use a vehicle in good condition as the reference vehicle. For example, a vehicle in extremely poor condition with a low rating can also be used as the reference vehicle. The evaluation index value in the above evaluation process is a value that indicates the degree of deviation between the condition of the target vehicle 10 and the reference vehicle. Therefore, when 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.

- 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 data shaping processing, generation processing, and evaluation processing can be performed. The generation processing and evaluation processing can be performed using multiple sound data recorded using multiple microphones 350.

- In the above embodiment, an example was shown in which the vehicle evaluation system evaluates the target vehicle 10 itself. In contrast, the vehicle evaluation system may evaluate the target vehicle 10 by evaluating a specific unit in the target vehicle 10. For example, the vehicle evaluation system may evaluate the transmission using sound data recorded from the sound emitted from the transmission mounted on the target vehicle 10. In addition, for example, in order to evaluate the engine, data on the engine rotation speed NE, ignition timing, and engine load rate can be used as the operation data. For example, in order to evaluate the drive motor, data on the rotation speed of the output shaft of the motor can be used as the operation data. In order to evaluate a four-wheel drive vehicle, data on the rotation speed of each drive wheel can be used as the operation data. In addition, the vehicle evaluation system may evaluate the target vehicle 10 by referring to the evaluation index values of various units.

10...Target vehicle, 20...Vehicle control unit, 21...Processing circuit, 22...Storage device, 30...Transmission control unit, 33...Air flow meter, 34...Crank position sensor, 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 (5)

A vehicle evaluation system for evaluating a target vehicle using sound data recorded from the target vehicle, the vehicle being an evaluation target, comprising: a processing circuit; and a storage device;
The storage device stores data of a learned model trained by supervised learning to generate feature data indicating features of the reference sound data from the training operation data, the feature data including reference sound data recorded while a reference vehicle in a state serving as a reference for evaluation is operated for a predetermined time period and training operation data indicating the operating status of the reference vehicle collected simultaneously with the reference sound data;
The processing circuit executes a generation process of inputting evaluation operation data collected while operating the target vehicle for the predetermined time into the trained model and outputting generated data, which is the feature data generated, and an evaluation process of comparing the generated data with target feature data, which is the feature data of the sound data recorded simultaneously with the evaluation operation data, and evaluating the target vehicle depending on the magnitude of deviation between the target feature data and the generated data. The trained model is a neural network that uses data for a period shorter than the predetermined time cut out from the operating status data for the predetermined time as explanatory variables, and uses sound pressure data for each frequency in the sound data at a time point corresponding to the cut out data as a target variable. The vehicle evaluation system according to claim 1. The vehicle evaluation system according to claim 2 , wherein the evaluation process calculates, as an evaluation index value, a sum of the deviations output for the predetermined time period for each of the data repeatedly extracted while changing the extraction start time. The vehicle evaluation system according to claim 2 , wherein the explanatory variables include data indicating measurement conditions when the sound data was recorded. The vehicle evaluation system according to claim 1 , wherein the training operation data and the evaluation operation data include data on a rotation speed of a rotating shaft in a powertrain.

Images