KR20200061704A - A system for improving fault of a batterty of a vehicle and method thereof - Google Patents

Abstract

The present invention relates to a system for alleviating a fault of a battery of a vehicle and a method thereof which calculates a current fault state of a battery of a vehicle as a variable in real time to accurately determine an aging state of a battery in a vehicle and alleviate the degree of aging. According to the present invention, the system for alleviating a vehicle′s battery fault comprises: a battery sensor unit to sense at least one property value of a battery of a vehicle to identify a fault type of the battery; a determination unit which has a neural network model to identify the battery fault type, and applies at least one property value sensed by the battery sensor unit to the neural network model to determine the fault type for the battery; and a control unit to control the performance of an operation for fault alleviation of the battery based on the determined fault type.

Description

A system for improving a battery defect in a vehicle and a method therefor{A SYSTEM FOR IMPROVING FAULT OF A BATTERTY OF A VEHICLE AND METHOD THEREOF}

The present invention relates to a vehicle, and more particularly, to a system for improving a battery defect of a vehicle, and a method thereof.

The invention of the conventional Korean Patent Publication No. 10-2011-0103249 determines the output degradation of the generator and the battery aging using only the duty of the generator. However, this does not take into account the current state of the battery, and has a limitation in determining aging by monitoring only the voltage dropping below a certain level.

In addition, the invention of the conventional Korean Patent Registration No. 10-0906911 determines the aging degree of the battery by cumulatively calculating whether or not ISG (IDLE Stop & Go) is entered. However, this not only has a shallow depth of learning, but also uses the ISG's simple entry count as the basis for determining battery aging.

The object of the present invention for solving the above problems is to accurately determine the battery aging state in the vehicle by real-time calculation of the current vehicle's battery failure status as a variable, as well as to improve the vehicle's battery failure improvement system to improve the aging degree And to provide a method.

A system for improving a battery defect in a vehicle according to an embodiment of the present invention includes: a battery sensor unit for sensing at least one characteristic value of the battery for grasping the type of defect in the battery of the vehicle; A determination unit having a neural network model for grasping the type of the battery failure, and applying at least one characteristic value sensed by the battery sensor unit to the neural network model to determine a defect type for the battery; It comprises a; control unit for controlling to perform an operation for improving the failure of the battery based on the determined defect type.

The battery defect improvement system of the vehicle transmits first data including at least one characteristic value sensed by the battery sensor unit to the determination unit, and receives second data including the defect type from the determination unit. A wireless communication unit delivered to the control unit may be further included.

In addition, the characteristic value may include at least one of voltage, current, temperature and SOC (State of Charge) of the battery.

In addition, the determination unit may determine, based on the at least one characteristic value and the neural network model, a defective type of the battery as a first type in which the battery has been discharged more than a predetermined number of times, in which case the control unit may perform the battery If is determined as the first type, it may be controlled to perform an immediate charging operation for the battery.

In addition, the determination unit may determine, based on the at least one characteristic value and the neural network model, a defective type of the battery as a second type in which the capacity of the battery is reduced and the internal resistance is increased, in which case the control unit When the battery is determined to be the second type, it may be controlled to reduce the usage of the battery of the vehicle to a predetermined level or less.

In addition, the determining unit may determine, based on the at least one characteristic value and the neural network model, a defective type of the battery as a third type having a temperature at which the battery is higher than a preset temperature, in which case the controller controls the battery to If it is determined to be the third type, the operation of the cooling fan in the vehicle may be controlled so that the temperature of the battery is less than the predetermined temperature.

In addition, a method for improving a battery defect in a vehicle according to an embodiment of the present invention includes: sensing at least one characteristic value of the battery for grasping a defect type of a battery in the vehicle; A neural network model for determining the battery failure type, and applying at least one characteristic value sensed by the battery sensor to the neural network model to determine a failure type for the battery; And performing an operation for improving the defect of the battery based on the determined defect type.

According to an embodiment of the present invention, by classifying the type according to a defective state of the current vehicle battery, and performing an appropriate battery improvement operation, it provides an effect of increasing the battery's correct charging and battery durability.

The technical effects of the present invention will be described in more detail below with reference to the drawings.

1 is a block diagram showing a system for improving a battery defect in a vehicle according to the present invention.
2 is a view for explaining a neural network used to determine the type of battery failure according to the present invention.
3 is a table showing a charging voltage map for improving battery failure according to the present invention.
4 is a flowchart illustrating a process for improving a battery defect in a vehicle according to the present invention.

Hereinafter, exemplary embodiments disclosed herein will be described in detail with reference to the accompanying drawings, but the same or similar elements will be given the same reference numbers regardless of the reference numerals, and redundant descriptions thereof will be omitted. The suffixes "modules" and "parts" for components used in the following description are given or mixed only considering the ease of writing the specification, and do not have meanings or roles distinguished from each other in themselves. In addition, in describing the embodiments disclosed in this specification, detailed descriptions of related known technologies are omitted when it is determined that the gist of the embodiments disclosed in this specification may be obscured. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in the present specification, and the technical spirit disclosed in the specification is not limited by the accompanying drawings, and all modifications included in the spirit and technical scope of the present invention , It should be understood to include equivalents or substitutes.

Terms including ordinal numbers such as first and second may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from other components.

When an element is said to be "connected" to or "connected" to another component, it is understood that other components may be directly connected to or connected to the other component, but may exist in the middle. It should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that no other component exists in the middle.

Singular expressions include plural expressions unless the context clearly indicates otherwise.

In this application, terms such as "comprises" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described in the specification, but one or more other features. It should be understood that the presence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

1 is a configuration block diagram showing a system for improving a battery defect in a vehicle according to the present invention.

2 is a view for explaining a neural network used to determine the type of battery failure according to the present invention.

3 is a table showing a charging voltage map for improving battery failure according to the present invention.

4 is a flowchart illustrating a process for improving a battery defect in a vehicle according to the present invention.

1 to 4, the vehicle battery improvement system 100 according to the present invention includes a battery sensor unit 110, a communication unit 120, a determination unit 130, and a control unit 140 Is done.

The battery sensor unit 110 is connected to the (-) pole of the battery of the vehicle, and under the control of the control unit 140, senses at least one characteristic value of the battery in real time for grasping the type of the battery failure [S110 ]. At this time, the characteristic value may include at least one of current, voltage, SOC (State of Charge), and liquid temperature of the battery.

The communication unit 120 may communicate with the vehicle and periodically receive information related to the vehicle from various elements (sensors and AVN system) of the vehicle.

Also, the communication unit 120 communicates with the determination unit 130 corresponding to the external server, and transmits first data including at least one characteristic value sensed by the battery sensor unit 110 to the determination unit 130. Transmitting, and receiving the second data including the defective type of the battery from the determination unit 130 may be transmitted to the control unit 140.

The determination unit 130 includes a neural network model for determining the type of battery failure [S120], and receives first data including at least one characteristic value sensed by the battery sensor unit 110 through the communication unit 120 And, by applying at least one characteristic value of the received battery to the neural network model [S130], it is possible to determine the defect type for the battery [S140].

As shown in FIG. 2, the neural network model is a model that has been pre-calculated with driving data of a plurality of battery defective vehicles. The neural network model is a model that learns the characteristics of a plurality of batteries in which a durability defect is raised, and derives various defect types as a result value.

As the neural network model, a deep neural network (DNN) model may be used.

That is, since the data of the at least one characteristic value of the battery has characteristics according to time series as continuous signals, it is most appropriate to construct an architecture using DNN.

In addition, DNN is suitable because it is necessary to go through several hidden layers to derive the type of endurance defects by the correlation between each characteristic value.

A drop out layer is added to the middle layer of the hidden layer.

That is, since the SOC of the battery is a variable that is influenced by current and voltage, the intermediate result values through the hidden layer are highly correlated, which increases the error in the analysis result.

As described above, the type of durability failure for the battery is obtained through a neural network model using driving data of a plurality of battery defective vehicles as learning data.

The determining unit 130 applies at least one of the current, voltage, SOC (State of Charge), and liquid temperature of the battery corresponding to the received at least one characteristic value to the trained neural network model to determine the defective type of the battery. To judge.

Since the battery current, voltage, SOC, and liquid temperature are characteristic values having battery durability characteristics, it is possible to classify the failure type of the battery when these variables are applied to a neural network model that has been trained in advance.

That is, the driving data corresponding to a plurality of battery-defective vehicles has already been progressed due to the wrong operation of the battery, and if the neural network model is trained with these data, it is a basis for inferring the cause according to the type of the endurance failure.

At this time, the determination unit 130 may apply the at least one characteristic value of the battery to the neural network model to determine the types of the battery's endurance defects to be largely divided into the following seven types. It can be judged as a defect type.

1. The cause of the durability failure of the battery is sulfation, and the cause of the occurrence of the battery is a sustained discharge of the battery or frequent uncharged battery (factors such as dark current, black box, etc.), battery charging performance, capacity, etc. It affects the battery as a typical failure factor to reduce the, and is included in the first type of failure of the battery durability in the present invention.

2. As a temporary short circuit (Dendrites) of the battery, the cause of the occurrence is dendrite growth in the SOC of the low battery (possible during long-term decoration, exports, yards, etc.), temporarily increasing the self-discharge rate, which is abnormal self-discharge It affects the battery as a factor that causes the phenomenon, and is included in the second type of failure of the battery durability in the present invention.

3. As the active material is eliminated, the cause of occurrence is the use of high Ah, affecting the battery as a factor that causes capacity reduction and increased internal resistance, and is included in the second type of failure of the battery durability in the present invention.

4. As the electrolyte stratification, the cause of occurrence is repeatedly △SOC overuse, and although there is no direct effect, the local sulphate proceeds due to stratification, which affects the battery as a factor that degrades the performance. In the invention, it is included in the second type of defect of the battery durability defect.

5. As the substrate corrosion, the cause of the occurrence is a high temperature of the battery, a high electrolyte concentration, thereby reducing the substrate thickness and affecting the battery as a factor that increases the internal resistance. In the present invention, the third defect type of battery durability failure Is included in.

6. As the electrolyte decreases, the cause of occurrence is high temperature and overcharge of the battery, and the battery capacity is decelerated due to the lack of the electrolyte, and is included in the third defect type of battery durability failure in the present invention.

7. As the anode active material recrystallization, the cause of occurrence is high temperature and overcharge, the specific surface area decreases due to the recrystallization of the anode active material, thereby affecting the increase in endurance resistance by reducing the reactivity of the active material, and in the present invention, the third defect of battery durability defect Included in type.

As described above, when any one of the first to third types of the battery is determined to be defective, the determination unit 130 transmits second data including the determined defective type to the communication unit 120.

The control unit 140 controls the overall operation of the vehicle and the vehicle battery improvement system according to the present invention.

In addition, when the second data including the determined failure type is received from the determination unit 130 through the communication unit 120, the control unit 140 performs an operation for improving the failure of the battery based on the received failure type. Control to perform [S150].

That is, if it is determined by the determination unit 130 that the battery is the first defective type, the control unit 140 stops power generation control regardless of the SOC state of the battery to change the discharge state of the battery after the vehicle starts, The ECU of the vehicle is controlled to perform immediate charging control. The ECU is a control module that controls the overall operation of the vehicle.

In this case, the charging voltage map table of FIG. 3 is selected from the ECU of the vehicle and is controlled to prioritize charging of the battery rather than driving for improving fuel efficiency.

In addition, when it is determined that the battery is of the second defective type by the determination unit 130, the control unit 140 may control the ECU of the vehicle to reduce the usage amount of the battery to a predetermined level or less.

That is, since the second defective type is a type in which the amount of use of the battery is large and thus the capacity is reduced and the internal resistance is increased, the ECU is controlled to set the battery use width smaller than the existing one.

For example, if the SOC width of the battery currently set as the power generation control section was 20%, the power consumption control may be performed by minimizing the battery use width by reducing the battery to 10%.

In addition, when it is determined by the determination unit 130 that the battery is of the third defective type, the control unit 140 controls the operation of the cooling fan in the vehicle so that the temperature of the battery is less than the preset temperature.

That is, the third type of defect is a type in which the temperature inside the battery rises high due to an internal or external factor and the durability defect proceeds.

As the cause of the increase in the liquid temperature of the battery, it can be regarded as a high-temperature engine room, and a continuous increase in the battery charge in a state where the battery liquid temperature is high.

  Therefore, when it is determined as the third type of failure, the frequency and duty of the cooling fan are set to be high, so that the temperature of the engine room is lowered. In addition, the entire map table as shown in FIG. 3 is set and controlled to minimize battery charging at high liquid temperature.

Terminology used in the present invention is a term defined in consideration of functions in the present invention, which may vary according to the intention or custom of a person skilled in the art, so the definition is based on the contents of the present invention. Will have to be lowered.

The scope of the invention should be determined by rational interpretation of the appended claims, and all changes within the equivalent scope of the invention are included in the scope of the invention.

The present invention described above is not limited by the embodiments described above, but may bring various modifications and changes by those skilled in the art, which is included in the spirit and scope of the present invention as defined in the appended claims.

100: battery defect improvement system 110: battery sensor unit
120: communication unit 130: judgment unit
140: control unit

Claims (17)

A battery sensor unit that senses at least one characteristic value of the battery for grasping a defect type of a vehicle battery;
A determining unit having a neural network model for identifying the battery failure type, and determining at least one characteristic value sensed by the battery sensor unit to the neural network model to determine a defect type for the battery; And
And a control unit controlling to perform an operation for improving the defect of the battery based on the determined defect type. According to claim 1,
A wireless communication unit that transmits first data including at least one characteristic value sensed by the battery sensor unit to the determination unit, receives the second data including the defect type from the determination unit, and transmits the second data to the control unit; Further comprising, a vehicle battery defect improvement system. According to claim 1, The characteristic value,
A system for improving battery defects in a vehicle, comprising at least one of voltage, current, temperature and SOC (State of Charge) of the battery. The method of claim 1, wherein the determination unit,
Based on the at least one characteristic value and the neural network model, the battery failure improvement system of the vehicle is determined as the first type in which the battery is discharged more than a preset number of times. The method of claim 4, wherein the control unit,
And when the battery is determined to be the first type, controlling the battery to perform an immediate charging operation. The method of claim 1, wherein the determination unit,
Based on the at least one characteristic value and the neural network model, the battery defect improvement system of a vehicle is determined as a second type in which the capacity of the battery is reduced and the internal resistance is increased, based on the neural network model. The method of claim 6, wherein the control unit,
When it is determined that the battery is the second type, the battery defective improvement system of the vehicle is controlled to reduce the usage of the battery of the vehicle to a predetermined level or less. The method of claim 1, wherein the determination unit,
Based on the at least one characteristic value and the neural network model, the battery defect improvement system of the vehicle is determined to determine the type of the battery as a third type in which the battery is above a preset temperature. The method of claim 8, wherein the control unit,
When the battery is determined to be the third type, the battery defect improvement system of the vehicle is controlled to control the operation of the cooling fan in the vehicle so that the temperature of the battery is below the predetermined temperature. Sensing at least one characteristic value of the battery for grasping the defect type of the battery of the vehicle;
A neural network model for determining the battery failure type, and applying at least one characteristic value sensed by the battery sensor to the neural network model to determine a defect type for the battery; And
And performing an operation for improving the defect of the battery based on the determined defect type. The method of claim 10, wherein the characteristic value,
A method of improving battery failure of a vehicle, comprising at least one of voltage, current, temperature, and SOC (State of Charge) of the battery. The method of claim 10, wherein the determining step,
Based on the at least one characteristic value and the neural network model, a method for improving a battery defect in a vehicle is determined as determining a type of the battery defect as a first type in which the battery has been discharged more than a predetermined number of times. The method of claim 12, wherein the performing step,
When the battery is determined to be the first type, a method for improving battery defects in a vehicle is performed by performing an immediate charging operation on the battery. The method of claim 10, wherein the determining step,
Based on the at least one characteristic value and the neural network model, determining a defective type of the battery as a second type in which the capacity of the battery is reduced and the internal resistance is increased. The method of claim 14, wherein the performing step,
When it is determined that the battery is the second type, a method of improving battery defects in a vehicle, reducing the amount of use of the battery in the vehicle to a predetermined level or less. The method of claim 10, wherein the determining step,
Based on the at least one characteristic value and the neural network model, a method for improving a battery defect in a vehicle is determined as determining a type of the battery defect as a third type having a temperature equal to or higher than a preset temperature. The method of claim 16, wherein the performing step,
When the battery is determined to be the third type, a method of improving a battery defect in the vehicle is operated by operating a cooling fan in the vehicle such that the temperature of the battery is below the predetermined temperature.

Images