JP2021135114A - Battery monitoring system - Google Patents

Abstract

To provide a battery monitoring system enabling accuracy of diagnosis for failure of a secondary battery to be improved.SOLUTION: A battery monitoring system 1 monitors a state of a secondary battery 2, and includes a data acquisition unit 10, a calculation unit 20, an extraction unit 40, and a failure determination unit 50. The data acquisition unit 10 acquires a plurality of types of monitoring data for monitoring the secondary battery 2. The calculation unit 20 calculates a feature quantity using the monitoring data. The extraction unit 40 extracts systematic variations of the feature quantity based on change in the feature quantity calculated by the calculation unit 20 during a predetermined period. The failure determination unit 50 determines that the secondary battery 2 has failed when the systematic variations deviate from a predetermined reference range R.SELECTED DRAWING: Figure 1

Description

The present invention relates to a battery monitoring system.

Conventionally, various systems for early detection of abnormalities in various devices have been known. For example, Patent Document 1 describes a normal model in which a normal state of a device is modeled using a plurality of types of sensor data acquired from a gas engine device and mutual correlation coefficients calculated from the plurality of types of sensor data. After being created, a configuration for diagnosing a failure when the observed data deviates from the normal model by a predetermined degree is disclosed. In such a configuration, the normal state is modeled using the correlation coefficient based on the sensor data and the diagnosis is made by comparing with the observation data. We are trying to improve the diagnostic accuracy of.

JP-A-2017-10263

The inventors of the present application may fluctuate the normal state of the secondary battery depending on how the secondary battery is used, or the sensor data acquired from the secondary battery may fluctuate in a short cycle such as seasonal fluctuation. I found that. On the other hand, in the configuration disclosed in Patent Document 1, when the normal state of the device to be diagnosed is not uniquely determined, the accuracy of failure diagnosis is lowered unless the normal model is constantly updated. If the normal state is uniquely determined, the observed data tends to deviate from the normal model, and the risk of misdiagnosing the normal state as a failure increases. Therefore, when the configuration disclosed in Patent Document 1 is applied to the secondary battery, there is a further concern that the accuracy of the failure diagnosis will be lowered.

The present invention has been made in view of such a problem, and an object of the present invention is to provide a battery monitoring system in which the accuracy of failure diagnosis of a secondary battery is improved.

One aspect of the present invention is a battery monitoring system (1) that monitors the state of the secondary battery (2).
A data acquisition unit (10) that acquires a plurality of types of monitoring data for monitoring the secondary battery, and
A calculation unit (20) that calculates features using the above monitoring data, and
An extraction unit (40) that extracts systematic fluctuations of the feature amount based on the change of the feature amount in a predetermined period calculated by the calculation unit, and
The battery monitoring system includes a failure determination unit (50) for determining that the secondary battery has failed when the systematic fluctuation deviates from a predetermined reference range.

The inventors of the present application have set between the starting point of systematic variation extracted from the change of the feature amount calculated from the change in the predetermined period using a plurality of types of monitoring data acquired from the secondary battery and the initial failure point of the secondary battery. We found a new finding that there is a correlation. Then, in the battery monitoring system, based on the knowledge, systematic fluctuations are extracted based on changes in the feature amount calculated using a plurality of types of monitoring data acquired from the secondary battery in a predetermined period, and the system is concerned. When the absolute value of the target fluctuation deviates from the predetermined reference range, it is determined that the secondary battery has failed. In this way, by monitoring the state of the secondary battery based on the systematic fluctuation, the influence of the usage of the secondary battery and the fluctuation in a short cycle can be suppressed, and the accuracy of the failure judgment of the secondary battery can be suppressed. Can be improved.

As described above, according to the present invention, it is possible to provide a battery monitoring system in which the accuracy of failure diagnosis of a secondary battery is improved.

The reference numerals in parentheses described in the scope of claims and the means for solving the problem indicate the correspondence with the specific means described in the embodiments described later, and limit the technical scope of the present invention. It's not a thing.

The block diagram which shows the structure of the battery monitoring system in Embodiment 1. FIG. FIG. 6 is a conceptual diagram showing a configuration of a vehicle equipped with a battery monitoring system according to the first embodiment. The flow chart which shows the control mode of the battery monitoring system in Embodiment 1. FIG. The conceptual diagram which shows the plurality of monitoring data acquired in the battery monitoring system in Embodiment 1. FIG. The conceptual diagram which shows the feature amount calculated in the battery monitoring system in Embodiment 1. FIG. The conceptual diagram of (a) trend component, (b) seasonal variation component and (c) irregular variation component calculated in the battery monitoring system in the first embodiment. The conceptual diagram which shows the time change of the battery performance of the secondary battery in Embodiment 1. FIG. The block diagram which shows the structure of the battery monitoring system in Embodiment 2. The flow chart which shows the control mode of the battery monitoring system in Embodiment 2. The conceptual diagram which shows the monitoring data acquired in the battery monitoring system in Embodiment 2. FIG. The conceptual diagram of the trend component calculated in the battery monitoring system in Embodiment 2. The block diagram which shows the structure of the battery monitoring system in Embodiment 3. FIG. 5 is a flow chart showing a control mode of the battery monitoring system according to the third embodiment. FIG. 6 is a conceptual diagram showing a plurality of monitoring data acquired in the battery monitoring system according to the third embodiment. The conceptual diagram of the trend component calculated in the battery monitoring system in Embodiment 3. The block diagram which shows the structure of the battery monitoring system in Embodiment 4. FIG. 5 is a flow chart showing a control mode of the battery monitoring system according to the fourth embodiment. The conceptual diagram which shows the structure of the battery monitoring system in Embodiment 5. The conceptual diagram which shows the structure of the battery monitoring system in the modified form 1. The conceptual diagram which shows the structure of the battery monitoring system in the modified form 2.

(Embodiment 1)
The embodiment of the battery monitoring system will be described with reference to FIGS. 1 to 7.
The battery monitoring system 1 of the present embodiment shown in FIG. 1 monitors the state of the secondary battery 2.
As shown in FIG. 1, a data acquisition unit 10, a calculation unit 20, an extraction unit 40, and a failure determination unit 50 are provided.
The data acquisition unit 10 acquires a plurality of types of monitoring data for monitoring the secondary battery 2.
The calculation unit 20 calculates the feature amount using the monitoring data.
The extraction unit 40 extracts the systematic variation of the feature amount based on the change of the feature amount calculated by the calculation unit 20 in a predetermined period.
The failure determination unit 50 determines that the secondary battery 2 has failed when the systematic fluctuation deviates from a predetermined reference range.

Hereinafter, the battery monitoring system 1 of the present embodiment will be described in detail.
As shown in FIG. 2, the battery monitoring system 1 of the present embodiment monitors the secondary battery 2 constituting the power source mounted on the vehicle 100 such as an electric vehicle or a hybrid vehicle. In the present embodiment, as shown in FIG. 2, the secondary battery 2 is an assembled battery in which a plurality of battery cells 21, 22, and 23 are combined. The secondary battery 2 may be a single battery cell.

The data acquisition unit 10 shown in FIG. 1 acquires a plurality of types of monitoring data in the secondary battery 2. Examples of the monitoring data include closed circuit voltage, charge / discharge current, SOC (State of charge), battery capacity, battery temperature, environmental temperature around the battery, integrated charging time, integrated discharging time, integrated current, and the like. Further, as the monitoring data of the assembled battery, the total closed circuit voltage of the assembled battery, the maximum and / or minimum closed circuit voltage of the secondary battery in the assembled battery, the battery temperature, the SOC, and the like can be exemplified. The data acquisition unit 10 can be a sensor or the like capable of detecting the monitoring data to be acquired, for example, a voltage sensor, a current sensor, a temperature sensor, or the like, and the SOC is calculated based on these values. Can be obtained. In the present embodiment, as shown in FIG. 2, the data acquisition unit 10 is composed of the voltage sensor 101, the current sensor 102, and the temperature sensor 103 provided in the BMU (battery management unit) mounted on the vehicle 100. ..

The storage unit 11 shown in FIG. 1 is composed of a rewritable non-volatile memory, and stores a plurality of types of monitoring data acquired by the data acquisition unit 10. In this embodiment, the storage unit 11 is provided in the BMU.

The calculation unit 20 shown in FIG. 1 includes a processor capable of executing a predetermined program for calculating the feature amount. In the present embodiment, the calculation unit 20 is provided outside the vehicle 100. The calculation unit 20 may be configured by executing the program by a processor mounted on the BMU provided in the vehicle 100. The calculation unit 20 calculates the feature amount of the secondary battery 2 using a plurality of types of monitoring data stored in the storage unit 11. The feature quantity can be, for example, a correlation coefficient between variables of the monitoring data. In the present embodiment, the partial correlation coefficient is calculated from the components of the covariance inverse matrix of the monitoring data as the correlation coefficient. The covariance inverse matrix can be calculated by performing sparse regularization using a plurality of types of monitoring data as variables by the calculation unit 20.

As a method of calculating the feature amount by the calculation unit 20 in the present embodiment, a case where the data acquisition unit 10 acquires six types of monitoring data X1 to X6 will be described as shown in FIG. The monitoring data to be acquired may be of two or more types, and is not limited to six types. As shown in FIG. 4, each monitoring data X1 to X6 changes with the passage of time. First, the calculation unit 20 performs sparse regularization using the monitoring data X1 to X6 acquired in the first period P1 as variables, and calculates the partial correlation coefficient matrix Λ as the covariance inverse matrix. The partial correlation coefficient matrix Λ can be expressed as follows, for example.

In the above equation, the component λnm (n, m = 1 to 6) of the partial correlation coefficient matrix Λ indicates the partial correlation coefficient between the monitoring data Xn and the monitoring data Xm. That is, λ12 means a partial correlation coefficient between the monitoring data X1 and the monitoring data X2. Further, since the partial correlation coefficient matrix Λ is a symmetric matrix, a part of the partial correlation coefficient λ is omitted in the above equation. Further, since all the components on the main diagonal of the partial correlation coefficient matrix Λ are 1, the description is omitted. Then, the calculation unit 20 calculates the component λnm (n, m = 1 to 6) of the partial correlation coefficient matrix Λ as a feature amount. The partial correlation coefficient λnm, which is a feature quantity, approaches 1 or -1 when the correlation between the two types of monitoring data is high. If the correlation is low, it approaches 0. Then, as shown in FIG. 5, the partial correlation coefficient λnm, which is a feature quantity, changes with the passage of time.

In the present embodiment, the feature amount calculated by the calculation unit 20 is stored in the feature amount storage unit 30 shown in FIG. The feature quantity storage unit 30 is composed of a rewritable non-volatile memory. In the present embodiment, the feature amount storage unit 30 is provided outside the vehicle 100. The BMU provided in the vehicle 100 may include the feature amount storage unit 30.

The extraction unit 40 shown in FIG. 1 includes a processor capable of executing a predetermined program for extracting systematic fluctuations in the feature amount. In the present embodiment, the extraction unit 40 is provided outside the vehicle 100. The extraction unit 40 may be configured by executing the program by a processor mounted on the BMU provided in the vehicle 100. In the present embodiment, the extraction unit 40 extracts the trend component by the smoothing process of the factor decomposition in the time series analysis as the systematic variation of the feature amount. Factor decomposition in time series analysis can be performed by a known method. Further, as the smoothing process, a moving average for calculating the average of the latest features or a Kalman smoothing for extracting past systematic fluctuations based on the features up to the present may be adopted. The period of the feature amount used to extract the systematic variation is not particularly limited.

In the present embodiment, for example, as a feature quantity, the partial correlation coefficient λ nm, which is a specific component in the partial correlation coefficient matrix Λ, can be shown as shown in FIG. Then, the extraction unit 40 performs factor decomposition in the time series analysis on the partial correlation coefficient λ nm, so that the trend component, the seasonal variation component, and the irregular variation component shown in FIGS. The trend component is extracted as a systematic variation. The trend component shows long-period fluctuations, the seasonal variation component shows short-period fluctuations, and the irregular fluctuation component shows random fluctuations.

For example, when monitoring the cycle of each fluctuation by paying attention to the seasonal change of one year, the fluctuation component having a cycle of one year is regarded as a short cycle fluctuation, and the fluctuation component having a cycle longer than one year is regarded as a long cycle. Fluctuations with a period shorter than one year can be defined as random fluctuations. In addition, when monitoring by paying attention to changes in usage for one week, fluctuation components with a cycle of one week are defined as short-cycle fluctuations, and fluctuation components with a cycle longer than one week are defined as long-cycle fluctuations. Fluctuation components with cycles shorter than one week can be defined as random fluctuations. As described above, the period of each fluctuation can be defined based on the object of interest of the change.

Then, the abnormality of the secondary battery 2 appears as a long-period fluctuation in the partial correlation coefficient, and conditions having a low relationship with the abnormality of the secondary battery 2, such as the temperature change and usage of the secondary battery 2, are the phase deviation. It appears in the seasonal fluctuation component and the irregular fluctuation component in the number of relations. Therefore, by extracting the trend component from the partial correlation coefficient as the systematic fluctuation, the long-period fluctuation reflecting the abnormality of the secondary battery 2 can be realized.

The failure determination unit 50 shown in FIG. 1 includes a processor capable of executing a predetermined program for determining whether or not the secondary battery 2 has failed. In the present embodiment, the failure determination unit 50 is provided outside the vehicle 100. The failure determination unit 50 may be configured by executing the program by a processor mounted on the BMU provided in the vehicle 100. The failure determination unit 50 compares the systematic variation with the predetermined reference range, and when the comparison result indicates that the systematic variation deviates from the predetermined reference range R, the secondary battery 2 is used. Judge that it has failed.

Next, the control flow of the battery monitoring system 1 will be described with reference to FIG.
First, in step S1 shown in FIG. 3, the data acquisition unit 10 acquires a plurality of types of monitoring data X1 to X6 shown in FIG. 4 from the secondary battery 2. The acquired monitoring data X1 to X6 are stored in the storage unit 11 shown in FIGS. 1 and 2.

After step S1, in step S2 shown in FIG. 3, the calculation unit 20 calculates the feature amount using the monitoring data. In the present embodiment, the calculation unit 20 performs sparse regularization using a plurality of types of monitoring data as variables to calculate a covariance inverse matrix, and calculates a partial correlation coefficient as a feature amount from the components of the covariance inverse matrix. .. In the present embodiment, the feature amount over the first period P1 shown in FIG. 4 is calculated. Then, in step S3, the feature amount for the fixed period is stored in the feature amount storage unit 30 shown in FIGS. 1 and 2.

Then, after step S3, in step S4 shown in FIG. 3, the extraction unit 40 extracts the systematic variation from the feature amount stored in the feature amount storage unit 30. In the present embodiment, the extraction unit 40 performs a smoothing process by factor decomposition in the time series analysis on the partial correlation coefficient as the feature amount stored in the feature amount storage unit 30, so that FIG. 6A ) To (c), the trend component, the seasonal variation component, and the irregular variation component are separated. As a result, the extraction unit 40 extracts the trend component as the systematic variation shown in FIG. 6A from the change in the feature amount in the predetermined period.

Next, in step S5 shown in FIG. 3, the failure determination unit 50 determines whether or not the systematic variation deviates from the predetermined reference range R. In the present embodiment, as shown in FIG. 6A, the reference range R is set in advance at the time of designing the secondary battery 2 based on the fluctuation range of the systematic fluctuation in the bench evaluation. If the failure determination unit 50 determines that the systematic fluctuation deviates from the reference range R, the process proceeds to Yes in step S5, and in step S6, the failure determination unit 50 has failed the secondary battery 2. Is determined, and this control flow is terminated. For example, as shown in FIG. 6A, at time T1, the trend component, which is a systematic fluctuation, deviates from the reference range R, and it is determined that the secondary battery 2 is out of order. As shown in FIG. 7, in the secondary battery 2, the maintenance rate of the full charge capacity when the initial state is 100% gradually decreases with use as shown as an assumed value, but the secondary battery 2 In, the maintenance rate of the full charge capacity is lower than the assumed value. Then, according to the battery monitoring system 1 of the first embodiment, in the initial failure Fi of FIG. 7 corresponding to the time T1 of FIG. 6A, before the maintenance rate of the full charge capacity becomes lower than the assumed value, The failure of the secondary battery 2 can be determined. On the other hand, if the failure determination unit 50 determines in step S5 that the systematic fluctuation does not deviate from the reference range R, the process proceeds to No in step S5, and the process returns to step S1 again.

In the control flow of the battery monitoring system 1 of the first embodiment, the feature amount is calculated using a plurality of types of monitoring data acquired from the secondary battery 2, and the systematic fluctuation is calculated based on the change of the feature amount in a predetermined period. Extract. Then, when the systematic fluctuation deviates from the predetermined reference range R, it is determined that the secondary battery 2 has failed. As a result, the failure of the secondary battery 2 can be detected at an early stage.

As shown in the conceptual diagram shown in FIG. 7, when the normal state of the secondary battery 2 continues, the battery performance of the secondary battery 2 gradually decreases from the solid line L0 to the solid line L1. On the other hand, when a failure occurs in the secondary battery 2, the battery performance of the secondary battery 2 shifts from the solid line L0 to the solid line L2 as shown in FIG. 7, and rapidly decreases from the initial failure Fi, which is the initial stage of the failure. do.

In the present embodiment, as described above, the failure determination is performed by utilizing the systematic variation based on the change in the feature amount acquired from the secondary battery 2 in a predetermined period. Since the systematic fluctuation can be detected even at the stage of the initial failure Fi, the failure determination is performed at the stage of the initial failure Fi, which is before the battery performance of the secondary battery 2 is significantly deteriorated. Can be done. In other words, the initial failure Fi of the secondary battery 2 can be detected.

Next, the operation and effect of the battery monitoring system 1 of the first embodiment will be described in detail.
In the battery monitoring system 1 of the first embodiment, the starting point of the systematic variation extracted from the change of the feature amount calculated by using the plurality of types of monitoring data acquired from the secondary battery 2 in a predetermined period, and the secondary battery 2 Based on the new finding that there is a correlation with the initial failure point, the systematic fluctuation is calculated based on the change in the feature amount over a predetermined period calculated using multiple types of monitoring data acquired from the secondary battery 2. When the absolute value of the systematic fluctuation deviates from a predetermined reference range, it is determined that the secondary battery has failed. In this way, by monitoring the state of the secondary battery 2 based on the systematic fluctuation, the usage of the secondary battery 2 and the influence of the fluctuation in a short cycle are suppressed, and the secondary battery 2 fails. The accuracy of the determination can be improved.

Further, in the present embodiment, the data acquisition unit 10 acquires at least the closed circuit voltage, charge / discharge current, charging state, and battery temperature of the secondary battery 2 as a plurality of types of monitoring data X1 to X6. As a result, by acquiring these as monitoring data X1 to X6, the abnormality of the secondary battery 2 is likely to be reflected in the feature amount, so that the accuracy of failure determination can be improved.

Further, in the present embodiment, the calculation unit 20 calculates the correlation coefficient with the monitoring data X1 to X6 as variables as the feature amount. As a result, it is possible to calculate the feature amount reflecting the abnormality of the secondary battery 2 from the plurality of types of monitoring data X1 to X6, and it is possible to improve the accuracy of the failure determination of the secondary battery 2.

Further, in the present embodiment, the calculation unit 20 calculates the partial correlation coefficient from the components of the covariance inverse matrix as the correlation coefficient. As a result, the feature amount further reflects the abnormality of the secondary battery 2, so that the accuracy of failure determination of the secondary battery 2 can be further improved.

Further, in the present embodiment, the calculation unit 20 performs sparse regularization to calculate the covariance inverse matrix. As a result, the feature amount further reflects the abnormality of the secondary battery 2, so that the accuracy of the failure determination of the secondary battery 2 can be further improved.

Further, in the present embodiment, the feature amount storage unit 30 for storing the feature amount calculated by the calculation unit 20 is further provided, and the extraction unit 40 systematically smoothes the feature amount stored in the feature amount storage unit 30. Extract fluctuations. As a result, the trend component can be extracted by reflecting the long-term fluctuation as the systematic fluctuation, and the generation of noise based on the seasonal fluctuation component and the irregular fluctuation component can be effectively suppressed. The accuracy of failure determination can be further improved.

Further, in the present embodiment, as shown in FIG. 2, the secondary battery 2 and the data acquisition unit 10 are mounted on the vehicle 100, and the storage unit 11, the calculation unit 20, the feature amount storage unit 30, and the extraction unit 40 are mounted. The failure determination unit 50 is provided in the external device 8 arranged outside the vehicle 100. Then, when performing a failure diagnosis of the secondary battery 2, the external device 8 is connected to the vehicle 100, and the monitoring data X1 to X6 acquired by the data acquisition unit 10 are transmitted to the external device 8. By providing the external device 8 with a part of the configuration of the battery monitoring system 1 in this way, the number of devices mounted on the vehicle 100 can be reduced.

Further, in the present embodiment, the secondary battery 2 constitutes an assembled battery formed by combining a plurality of battery cells 21 to 23. As a result, when a plurality of battery cells are provided, it is not necessary to provide the battery monitoring system 1 for each battery cell. When the secondary battery 2 is composed of a single battery cell, the battery monitoring system 1 may be provided for each battery cell.

As described above, according to the present embodiment, it is possible to provide the battery monitoring system 1 in which the accuracy of failure diagnosis is improved.

(Embodiment 2)
As shown in FIG. 8, the battery monitoring system 1 of the second embodiment further includes a fluctuation storage unit 45 that stores systematic fluctuations and a reference range setting unit 55 that sets the reference range based on the systematic fluctuations. Be prepared. The other configurations are the same as those in the first embodiment, and the same reference numerals as those in the first embodiment are assigned and the description thereof will be omitted.

In the control flow by the battery monitoring system 1 of the second embodiment shown in FIG. 9, steps S1 to S3 are performed in the same manner as in the first embodiment shown in FIG. After that, in step S4 shown in FIG. 9, the partial correlation coefficient calculated from the components of the covariance inverse matrix of the monitoring data X1 to X6 in the period Pt shown in FIG. On the other hand, the trend component is extracted as a systematic variation by performing the smoothing process by factor decomposition in the time series analysis.

After that, as shown in FIG. 9, step S7 and step S50 are performed in parallel. First, in step S7, the fluctuation storage unit 45 stores systematic fluctuations in a predetermined period. For example, as shown in FIG. 10, all systematic fluctuations acquired in the period Pt from the start to the present are stored by the fluctuation storage unit 45. Then, in step S8, the reference range R is set based on the systematic variation stored in the variation storage unit 45 by the reference range setting unit 55. If the reference range is set earlier, it is updated and set as the latest reference range R.

On the other hand, in step S50 shown in FIG. 9, the failure determination unit 50 determines whether the systematic variation extracted in step S4 deviates from the latest reference range R. If the failure determination unit 50 determines that the latest systematic variation deviates from the latest reference range R, the process proceeds to Yes in step S50, and the failure occurs in step S6 as in the case of the first embodiment. The determination unit 50 determines that the secondary battery 2 is out of order, and ends this control flow. In the battery monitoring system 1 of the second embodiment, for example, when the trend component which is a systematic fluctuation at the time T2 shown in FIGS. 10 and 11 deviates from the reference range R, the secondary battery 2 is out of order. It is judged. On the other hand, if the failure determination unit 50 determines in step S50 that the systematic variation does not deviate from the latest reference range R, the process proceeds to No in step S50, and the process returns to step S1 again.

Next, the operation and effect of the battery monitoring system 1 of the second embodiment will be described in detail.
According to the second embodiment, by setting the reference range R for failure determination in a timely manner based on the systematic fluctuation, the failure diagnosis is performed while updating the reference range R indicating the normal state of the secondary battery 2 in a timely manner. Can be done. As a result, the accuracy of failure determination can be further improved. It should be noted that the second embodiment also has the same effect as that of the first embodiment.

(Embodiment 3)
As shown in FIG. 12, the battery monitoring system 1 of the third embodiment includes a data acquisition unit 10, a calculation unit 20, an extraction unit 40, and a failure determination unit 50, and is a feature amount storage unit according to the first embodiment shown in FIG. Not equipped with 30. Then, in the battery monitoring system 1 of the first embodiment shown in FIG. 1, the extraction unit 40 extracts the trend component as a systematic variation by smoothing the feature amount stored in the feature amount storage unit 30 for a predetermined period. .. Instead of this, in the battery monitoring system 1 of the third embodiment shown in FIG. 12, the extraction unit 40 continues to filter the feature amount calculated by the calculation unit 20 for a predetermined period, so that the trend is as a systematic fluctuation. Extract the ingredients. In the third embodiment, the filter processing by the Kalman filter is adopted as the filter processing. Instead of the filter processing by the Kalman filter, a filter processing by a low-pass filter may be adopted in which components having a frequency lower than a predetermined cutoff frequency are hardly attenuated and components having a frequency higher than the cutoff frequency are gradually reduced. In the third embodiment, the other configurations are the same as those in the first embodiment, and the same reference numerals as those in the first embodiment are assigned, and the description thereof will be omitted.

In the control flow by the battery monitoring system 1 of the third embodiment shown in FIG. 13, steps S1 and S2 are performed in the same manner as in the first embodiment shown in FIG. Then, in step S30 shown in FIG. 13, the extraction unit 40 extracts the systematic variation from the feature amount calculated by the calculation unit 20. In the third embodiment, the extraction unit 40 performs filtering processing by the Kalman filter on the partial correlation coefficient as the feature amount calculated by the calculation unit 20. As a result, the extraction unit 40 extracts the trend component as a systematic variation from the change in the feature amount in a predetermined period. In the third embodiment, as shown in FIG. 14, the extraction unit 40 filters the feature amount calculated based on the monitoring data acquired in the predetermined period Pn up to the current time Tn by the Kalman filter. , The trend component as a systematic variation at the current time Tn is extracted as shown in FIG. After that, also in the third embodiment, S5 and S6 shown in FIG. 13 are performed in the same manner as in steps S5 and S6 of the first embodiment shown in FIG.

In the third embodiment, the feature amount calculated by the calculation unit 20 is filtered to extract the systematic variation. As a result, systematic fluctuations can be extracted at a timing close to real time by performing filter processing in the extraction unit 40 each time the feature amount is calculated by the calculation unit 20, so that the real-time property of failure determination can be improved. Can be done. Also in the third embodiment, the same effects as those in the first embodiment can be obtained except for the effects of the smoothing treatment in the first embodiment.

(Embodiment 4)
As shown in FIG. 16, the battery monitoring system 1 of the fourth embodiment includes a data acquisition unit 10, a calculation unit 20, an extraction unit 40, a fluctuation storage unit 45, a failure determination unit 50, and a reference range setting unit 55. The feature amount storage unit 30 according to the second embodiment shown in 9 is not provided. Then, the extraction unit 40 in the fourth embodiment extracts the trend component as a systematic variation by continuing to filter the feature amount calculated by the calculation unit 20 for a predetermined period as in the case of the third embodiment. do. In the fourth embodiment, the other configurations are the same as those in the second embodiment, and the same reference numerals as those in the second embodiment are assigned, and the description thereof will be omitted.

In the control flow by the battery monitoring system 1 of the fourth embodiment shown in FIG. 17, steps S1, S2 and S30 are performed in the same manner as in the third embodiment shown in FIG. After that, step S7 and step S50 and subsequent steps are performed in the same manner as in the second embodiment shown in FIG. In the fourth embodiment, the same effects as those of the first and second embodiments can be obtained except for the effects of the smoothing treatment in the first and second embodiments, and the same effects as those of the third embodiment can be obtained. can get.

(Embodiment 5)
In the first embodiment, the external device 8 is directly connected to the external connection portion 105 of the vehicle, but instead, a communication means is provided in the vehicle and distributed to the outside of the vehicle 100 via a network using a cloud system. It may be connected to the external device 8 provided. For example, in the third embodiment shown in FIG. 18, the vehicle 100 includes a transmitter / receiver 110 capable of communicating with the external device 8. In the third embodiment, the secondary battery 2, the data acquisition unit 10, the calculation unit 20, the extraction unit 40, and the failure determination unit 50 are arranged in the vehicle 100, and the feature amount storage unit 30 and the storage unit 11 are external devices. It is provided in 8. The external device 8 can be configured by, for example, a server, and can be installed at a dealer of the vehicle 100 or the like. Then, the transmitter / receiver 110 is used to transmit the monitoring data X1 to X6 and the partial correlation coefficient matrix Λ as the feature amount to the feature amount storage unit 30 and the storage unit 11, or from the feature amount storage unit 30 and the storage unit 11. You can receive it.

According to the configuration of the fifth embodiment, the number of parts mounted on the vehicle 100 can be reduced, the weight of the vehicle 100 can be easily reduced, and monitoring data X1 to X6 and feature quantities can be collected in the server constituting the external device 8. It will be easy. It should be noted that even in the fifth embodiment, the same effects as those in the first to fourth embodiments can be obtained.

In the fifth embodiment, the feature amount storage unit 30 and the storage unit 11 are arranged outside the vehicle 100, but instead of this, as in the modified form 1 shown in FIG. 19, the secondary battery 2 and the data acquisition The unit 10, the storage unit 11, and the feature amount storage unit 30 may be arranged in the vehicle 100, and the calculation unit 20, the extraction unit 40, and the failure determination unit 50 may be provided in the external device 8. Further, as in the modified form 2 shown in FIG. 20, the secondary battery 2 and the data acquisition unit 10 are arranged in the vehicle 100, and the storage unit 11, the calculation unit 20, the feature amount storage unit 30, the extraction unit 40, and the failure determination unit are arranged. 50 may be provided in the external device 8. In both the modified form 1 and the modified form 2, data is transmitted and received between the external device 8 and the vehicle 100 via the transmitter / receiver 110 of the vehicle 100.

According to the configurations of the modified form 1 and the modified form 2, the failure diagnosis is performed in real time, the data stored in the feature amount storage unit 30 is managed, the program in the failure determination unit 50 is updated, and the AI technology is used. It becomes easy to execute the existing program. Further, by configuring the calculation unit 20, the extraction unit 40, and the failure determination unit 50 with a device having a high calculation speed such as a server, the failure determination can be performed in a shorter time. It should be noted that the modified form 1 and the modified form 2 also have the same effects as those in the case of the fifth embodiment.

The present invention is not limited to each of the above embodiments and modifications, and can be applied to various embodiments without departing from the gist thereof.

1 ... Battery monitoring system, 2 ... Secondary battery, 10 ... Data acquisition unit, 11 ... Storage unit, 20 ... Calculation unit, 30 ... Feature amount storage unit, 40 ... Extraction unit, 45 ... Variable storage unit, 50 ... Failure determination Department, 55 ... Reference range setting unit, 100 ... Vehicle

Claims (10)

A battery monitoring system (1) that monitors the status of the secondary battery (2).
A data acquisition unit (10) that acquires a plurality of types of monitoring data for monitoring the secondary battery, and
A calculation unit (20) that calculates features using the above monitoring data, and
An extraction unit (40) that extracts systematic changes in the features based on changes in the features over a predetermined period, and
A battery monitoring system including a failure determination unit (50) for determining that the secondary battery has failed when the systematic fluctuation deviates from a predetermined reference range (R). The battery monitoring system according to claim 1, wherein the data acquisition unit acquires at least the closed circuit voltage, charge / discharge current, charging state, and battery temperature of the secondary battery as the plurality of types of monitoring data. The battery monitoring system according to claim 1 or 2, wherein the calculation unit calculates a correlation coefficient using the monitoring data as a variable as the feature amount. The battery monitoring system according to claim 3, wherein the calculation unit calculates a partial correlation coefficient from the components of the covariance inverse matrix as the correlation coefficient. The battery monitoring system according to claim 4, wherein the calculation unit calculates the covariance inverse matrix by performing sparse regularization. The battery monitoring system according to any one of claims 1 to 5, wherein the extraction unit extracts the systematic variation by filtering the feature amount calculated by the calculation unit. A feature amount storage unit (30) for storing the feature amount calculated by the calculation unit is further provided.
The battery monitoring system according to any one of claims 1 to 5, wherein the extraction unit extracts the systematic variation by smoothing the feature amount stored in the feature amount storage unit. A fluctuation storage unit (45) that stores the systematic fluctuations extracted by the extraction unit, and a reference range setting unit (55) that sets the reference range based on the systematic fluctuations stored in the fluctuation storage unit. The battery monitoring system according to any one of claims 1 to 7, further comprising. The secondary battery and the data acquisition unit are mounted on the vehicle (100).
The battery monitoring system according to any one of claims 1 to 8, wherein at least one of the calculation unit, the extraction unit, and the failure determination unit is arranged outside the vehicle. The battery monitoring system according to any one of claims 1 to 9, wherein the secondary battery constitutes a battery cell or an assembled battery formed by combining a plurality of battery cells (21, 22, 23).

Images