Industrial vehicle power battery automatic prediction alarm method

Abstract

The invention discloses an industrial vehicle power battery automatic prediction alarm method, and belongs to the technical field of batteries. The industrial vehicle power battery automatic prediction alarm method comprises the following steps: S01, obtaining operation data of to-be-detected industrial vehicles of the same model within a period of time; s02, judging the total current of the power battery at the current moment; s03, acquiring a temperature rise rate, a pressure drop rate and a pressure rise rate; s04, comparing the power battery parameter value with a threshold protection parameter, and performing early warning if the power battery parameter value exceeds a threshold; and S05, establishing a BP neural network prediction model to realize automatic prediction alarm. According to the automatic prediction and alarm method for the industrial vehicle power battery, the vehicle operation condition and work intensity data are collected and analyzed in advance, an accurate model is constructed, instant alarm and early warning of faults are achieved, the fault frequency is effectively reduced, the maintenance cost is reduced, the service life of the power battery is prolonged, and potential safety hazards of the battery are remarkably reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of batteries, and in particular relates to an automatic prediction and alarm method for industrial vehicle power batteries. Background Art

[0002] At present, there is a relative lack of research on automatic prediction and alarm for industrial vehicle power batteries, and the research focus of most countries is still on the fault prediction and health management of large equipment such as aircraft, trains, and ships. With the continuous advancement of big data analysis technology, how to extract and identify the degradation patterns of key components from huge equipment operation data has become an emerging technology hotspot. In this context, given the actual needs and importance of automatic prediction and alarm for industrial vehicle power batteries, the development of a key component fault diagnosis and prediction system based on big data can not only solve current challenges, but also significantly enhance the market competitiveness of enterprises, which has great practical value.

[0003] The current automatic predictive alarm for industrial vehicle power batteries does not take into account the actual impact of the industrial vehicle's speed, load, lifting height, etc. on the power battery; and the impact of the external ambient temperature on battery performance is not considered during the predictive alarm process. Summary of the invention

[0004] The embodiment of the present invention provides an automatic prediction and alarm method for power batteries of industrial vehicles, aiming to solve the problem that the existing automatic prediction and alarm method for power batteries of industrial vehicles does not consider the actual impact of the speed, load, lifting height, etc. of the industrial vehicle on the power battery; and does not consider the impact of the external ambient temperature on the battery performance during the prediction and alarm process. The present invention proposes an automatic prediction and alarm method for power batteries of industrial vehicles, which collects and analyzes the vehicle operating conditions and work intensity data in advance, builds an accurate model, realizes instant alarm and early warning of faults, effectively reduces the frequency of faults, reduces maintenance costs, prolongs the service life of power batteries, and significantly reduces battery safety hazards.

[0005] The technical solution of the present invention is achieved in this way:

[0006] An automatic prediction alarm method for industrial vehicle power battery comprises the following steps:

[0007] S01. Obtaining the operating data of the same type of industrial vehicle to be tested over a period of time; the operating data includes power battery status data, vehicle operating condition data, vehicle work intensity data, and external ambient temperature data;

[0008] S02. Analyze and process the vehicle operating condition data and the vehicle working intensity data in the discharge state in step S01, extract the vehicle operating parameters, obtain the required power of the vehicle, and extract the influence of the external ambient temperature data on the battery; determine the total current of the power battery at the current moment;

[0009] S03. Extract the power battery status data in step S01, and obtain the temperature rise rate, voltage drop rate, and voltage rise rate according to the correlation between the total current size of the power battery and the data analysis of the current power battery status;

[0010] S04. Compare the power battery parameter value obtained during the charging and discharging process with the threshold protection parameter, and issue an early warning if the threshold is exceeded;

[0011] S05. According to the influencing factors of the total current of the power battery on the other parameters, the parameter value and time of triggering the battery early warning system, they are imported into the BP neural network model for training, a BP neural network prediction model is established, and automatic prediction alarm is realized through the BP neural network prediction model.

[0012] In step S01, the power battery status data includes current, cell voltage extreme value, cell temperature extreme value, temperature difference maximum value, pressure difference maximum value, insulation resistance, SOC and SOH, etc.;

[0013] The vehicle operating condition data includes vehicle speed, road surface flatness and climbing height;

[0014] The vehicle work intensity data includes the load capacity and lifting height of the industrial vehicle;

[0015] The external environment temperature data includes the vehicle working environment temperature.

[0016] The industrial vehicle is a power-driven motor vehicle used for carrying, pushing, pulling, lifting, stacking or stacking various goods. Preferably, the industrial vehicle includes one of a crane, a forklift, a single bucket loader, etc.

[0017] The operation data within a period of time is the operation data within a period of half a month to one year. Preferably, in step S02, the extraction of the whole operation parameters includes the extraction of vehicle speed, road surface flatness, climbing height, load capacity, and lifting height, so as to obtain the required power of the whole vehicle.

[0018] In the acquisition of the required power of the whole vehicle, the required power is parameter data obtained by the on-board VCU according to the driver stepping on the accelerator or brake pedal. The most direct monitoring method reflected on the battery end is to determine the value of the product of the current voltage and current to obtain the required power.

[0019] The determination of the total current of the power battery at the current moment is specifically as follows: there will be a BMS battery management system inside the battery, which detects the charging and discharging current of the battery in real time, and will be connected to the entire vehicle through CAN data transmission, and will eventually be presented on the vehicle dashboard.

[0020] The data extraction of the influence of the external environment temperature data on the battery includes the data extraction of temperature, battery discharge rate, discharge multiple and SOH.

[0021] Preferably, in step S03, the power battery status data includes data such as the power battery current, cell voltage extreme value, cell temperature extreme value, maximum temperature difference, maximum pressure difference, insulation resistance, SOC and SOH.

[0022] The relationship between the analyses is analyzed to obtain the temperature rise rate, voltage drop rate and voltage rise rate. Specifically, the composite equal division method is used to divide the data into sections of 10S each, and the relationship between the current size and the temperature rise rate, voltage drop rate and voltage rise rate under multiple data sections is determined, so as to achieve the result of data recognition using the BP neural network. In subsequent applications, new data can automatically predict the possible rates of temperature rise, voltage drop and voltage rise, so as to achieve the function of early warning.

[0023] In step S04, the warning preferably includes three levels of warning; the three levels of warning include level one warning, level two warning and level three warning.

[0024] The power battery parameter value includes at least one of total voltage, single cell voltage, single cell pressure difference, high and low temperature of charge and discharge, charge and discharge overcurrent, SOC, and SOH.

[0025] The threshold is a protection parameter threshold set by the BMS.

[0026] In step S05, the influencing factors of the remaining parameters include at least one of the following two situations: when the total current is in the charging and discharging state, if the total current is too large, it will cause the battery cell temperature to rise sharply, triggering the protection parameter and the battery will automatically shut down; or if it continues to be charged and discharged with a large current under low temperature conditions, it will have a serious impact on the battery cell SOH.

[0027] Preferably, after the BP neural network prediction model is constructed, subsequent new data is imported into the model for prediction to obtain the training accuracy. If the accuracy is not high, it returns to the initial state and retrains, and so on to obtain an accurate BP neural network prediction model through continuous iteration; the prediction accuracy of the BP neural network prediction model reaches more than 98%.

[0028] Further preferably, the BP neural network prediction model obtains accurate prediction accuracy by iteratively training the operation data of the industrial vehicle in step S01. Then, during the operation of the vehicle, the size of the power battery charge and discharge current is judged by the size of the vehicle power demand and the influence of the ambient temperature, so as to further judge the temperature rise rate, voltage drop rate, voltage rise rate, etc., so as to predict and alarm in advance before exceeding the battery protection parameters to avoid danger.

[0029] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0030] 1. The present invention obtains the required power of the whole vehicle by extracting the operating conditions and working intensity data of the whole vehicle, thereby determining the total current of the power battery; and takes into account the influence of the external ambient temperature data on the battery.

[0031] 2. The present invention determines the correlation factors between the single cell voltage extreme value, single cell temperature extreme value, maximum temperature difference, maximum pressure difference, insulation resistance, SOC and SOH data analysis of the power battery according to the current value, and derives the temperature rise rate, voltage drop rate, voltage rise rate, etc.; the present invention considers the power battery parameters and compares the data with the threshold value according to the vehicle charging and discharging status.

[0032] 3. The present invention uses a BP neural network prediction model to process and predict data, specifically including data extraction-training learning-test set sample evaluation accuracy-accurate prediction; and verifies the prediction accuracy of the model in actual operating conditions, and predicts and warns in advance before the power battery reaches the protection parameter state. That is, it realizes real-time alarm and early warning of faults, effectively reduces the frequency of faults, reduces maintenance costs, prolongs the service life of power batteries, and significantly reduces battery safety hazards.

[0033] 4. The advantage of the present invention is that it can collect operating data from the same model of industrial vehicles for a period of time, build a model for fault analysis, and realize instant alarm and early warning of battery failure. The system continuously monitors the data of the vehicle's power battery and classifies the data into primary, secondary, and tertiary alarm processes according to preset thresholds. The model deeply analyzes the battery's voltage difference anomaly, temperature difference anomaly, and insulation status, and combines the consistency standards of voltage and temperature to use the BP neural network prediction model to predict the power battery status in real time to ensure safe alarm of battery failure. The present invention provides a high-precision automatic prediction and alarm method for industrial vehicle power batteries, which is suitable for actual working conditions, effectively realizes health monitoring of battery thermal runaway, improves battery management efficiency, and provides timely warnings and alarms to enhance the safety of battery use. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of an automatic prediction and alarm method for power batteries of industrial vehicles provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, top, bottom...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0037] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0038] At present, the existing automatic prediction and alarm methods for industrial vehicle power batteries do not consider the actual impact of the industrial vehicle speed, load, lifting height, etc. on the power battery; and the problem of the impact of the external ambient temperature on battery performance is not considered during the prediction and alarm process. In order to solve the above technical problems, the present invention proposes an automatic prediction and alarm method for industrial vehicle power batteries.

[0039] Example 1

[0040] like Figure 1 As shown, an automatic prediction alarm method for industrial vehicle power battery includes the following steps:

[0041] S01. Obtain the operating data of the same type of industrial vehicle to be tested over a period of time; the operating data includes power battery status data, vehicle operating condition data, vehicle work intensity data, external ambient temperature data, etc.;

[0042] S02. Analyze and process the vehicle operating condition data and the vehicle working intensity data in the discharge state in step S01, extract the vehicle operating parameters, obtain the required power of the vehicle, and extract the influence of the external ambient temperature data on the battery; determine the total current of the power battery at the current moment;

[0043] S03. Extract the power battery status data in step S01, and obtain the temperature rise rate, voltage drop rate, and voltage rise rate according to the correlation between the total current size of the power battery and the data analysis of the current power battery status;

[0044] S04. Compare the power battery parameter value obtained during the charging and discharging process with the threshold protection parameter, and issue an early warning if the threshold is exceeded;

[0045] S05. According to the influencing factors of the total current of the power battery on the other parameters, the parameter value and time of triggering the battery early warning system, the BP neural network model is imported for training, a BP neural network prediction model is established, and automatic prediction alarm is realized through the BP neural network prediction model.

[0046] In step S01, the power battery status data includes current, cell voltage extreme value, cell temperature extreme value, temperature difference maximum value, pressure difference maximum value, insulation resistance, SOC and SOH, etc.;

[0047] The vehicle operating condition data includes vehicle speed, road surface flatness and climbing height;

[0048] The vehicle work intensity data includes the load capacity and lifting height of the industrial vehicle;

[0049] The external environment temperature data includes the vehicle working environment temperature.

[0050] The industrial vehicle is a power-driven motor vehicle used for carrying, pushing, pulling, lifting, stacking or stacking various goods. Preferably, the industrial vehicle includes one of a crane, a forklift, a single bucket loader, etc.

[0051] In this embodiment, in step S01, the operation data within a period of time is the operation data within a period of one month.

[0052] Preferably, in step S02, the extraction of the whole operation parameters includes the extraction of vehicle speed, road surface flatness, climbing height, load capacity, and lifting height; thereby obtaining the required power of the whole vehicle.

[0053] In the acquisition of the required power of the whole vehicle, the required power is parameter data obtained by the on-board VCU according to the driver stepping on the accelerator or brake pedal. The most direct monitoring method reflected on the battery end is to determine the value of the product of the current voltage and current, which is the required power.

[0054] The determination of the total current of the power battery at the current moment is specifically as follows: there will be a BMS battery management system inside the battery, which detects the charging and discharging current of the battery in real time, and will be connected to the entire vehicle through CAN data transmission, and will eventually be presented on the vehicle dashboard.

[0055] The data extraction of the influence of the external environment temperature data on the battery includes the data extraction of temperature, battery discharge rate, discharge multiple and SOH.

[0056] In step S03, the power battery status data includes data such as the power battery current, cell voltage extreme value, cell temperature extreme value, maximum temperature difference, maximum pressure difference, insulation resistance, SOC and SOH.

[0057] The relationship between the analyses is analyzed to obtain the temperature rise rate, voltage drop rate and voltage rise rate. Specifically, the composite equal division method is used to divide the data into sections of 10S each, and the relationship between the current size and the temperature rise rate, voltage drop rate and voltage rise rate under multiple data sections is determined, so as to achieve the result of data recognition using the BP neural network. In subsequent applications, new data can automatically predict the possible rates of temperature rise, voltage drop and voltage rise, so as to achieve the function of early warning.

[0058] In step S04, the warning preferably includes three levels of warning; the three levels of warning include level one warning, level two warning and level three warning.

[0059] The power battery parameter value includes at least one of total voltage, single cell voltage, single cell pressure difference, high and low temperature of charge and discharge, charge and discharge overcurrent, SOC, and SOH.

[0060] The threshold is a protection parameter threshold set by the BMS.

[0061] In step S05, the influencing factors of the remaining parameters include at least one of the following two situations: when the total current is in the charging and discharging state, if the total current is too large, it will cause the battery cell temperature to rise sharply, triggering the protection parameter and the battery will automatically shut down; or if it continues to be charged and discharged with a large current under low temperature conditions, it will have a serious impact on the battery cell SOH.

[0062] Preferably, after the BP neural network prediction model is constructed, subsequent new data is imported into the model for prediction to obtain the training accuracy. If the accuracy is not high, it returns to the initial state and retrains, and so on to obtain an accurate BP neural network prediction model through continuous iteration; the prediction accuracy of the BP neural network prediction model reaches more than 98%.

[0063] The present invention analyzes and calculates the data obtained from the operation of an industrial vehicle for one month to obtain temperature rise, pressure drop, pressure rise rate, etc., and then compares it with the protection parameter threshold set by the BMS to determine whether the temperature difference, pressure difference, etc. at a certain moment triggers an alarm; then the subsequent new data is imported into the model for prediction, and the training accuracy can be obtained. If the accuracy is not high, it returns to the initial state and retrains, and so on to obtain an accurate model through continuous iteration; the most important thing about the model is the training accuracy. After training, the model in this embodiment has a prediction accuracy of more than 98%.

[0064] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0065] 1. The present invention obtains the required power of the whole vehicle by extracting the operating conditions and working intensity data of the whole vehicle, thereby determining the total current of the power battery; and takes into account the influence of the external ambient temperature data on the battery.

[0066] 2. The present invention determines the correlation factors between the single cell voltage extreme value, single cell temperature extreme value, maximum temperature difference, maximum pressure difference, insulation resistance, SOC and SOH data analysis of the power battery according to the current value, and derives the temperature rise rate, voltage drop rate, voltage rise rate, etc.; the present invention considers the power battery parameters and compares the data with the threshold value according to the vehicle charging and discharging status.

[0067] 3. The present invention uses a BP neural network prediction model to process and predict data, specifically including data extraction-training learning-test set sample evaluation accuracy-accurate prediction; and verifies the prediction accuracy of the model in actual operating conditions, and predicts and warns in advance before the power battery reaches the protection parameter state. That is, it realizes real-time alarm and early warning of faults, effectively reduces the frequency of faults, reduces maintenance costs, prolongs the service life of power batteries, and significantly reduces battery safety hazards.

[0068] 4. The advantage of the present invention is that it can collect operating data from the same model of industrial vehicles for a period of time, build a model for fault analysis, and realize instant alarm and early warning of battery failure. The system continuously monitors the data of the vehicle's power battery and classifies the data into primary, secondary, and tertiary alarm processes according to preset thresholds. The model deeply analyzes the battery's voltage difference anomaly, temperature difference anomaly, and insulation status, and combines the consistency standards of voltage and temperature to use the BP neural network prediction model to predict the power battery status in real time to ensure safe alarm of battery failure. The present invention provides a high-precision automatic prediction and alarm method for industrial vehicle power batteries, which is suitable for actual working conditions, effectively realizes health monitoring of battery thermal runaway, improves battery management efficiency, and provides timely warnings and alarms to enhance the safety of battery use.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic prediction and alarm method for industrial vehicle power batteries, characterized in that: The following steps are involved: S01. Obtaining the operating data of the same type of industrial vehicle to be tested over a period of time; the operating data includes power battery status data, vehicle operating condition data, vehicle work intensity data, and external ambient temperature data; S02. Analyze and process the vehicle operating condition data and the vehicle working intensity data in the discharge state in step S01, extract the vehicle operating parameters, obtain the required power of the vehicle, and extract the influence of the external ambient temperature data on the battery; determine the total current of the power battery at the current moment; S03. Extract the power battery status data in step S01, and obtain the temperature rise rate, voltage drop rate, and voltage rise rate according to the correlation between the total current size of the power battery and the data analysis of the current power battery status; S04. Compare the power battery parameter value obtained during the charging and discharging process with the threshold protection parameter, and issue an early warning if the threshold is exceeded; S05. According to the influencing factors of the total current of the power battery on the other parameters, the parameter value and time of triggering the battery early warning system, the BP neural network model is imported for training, a BP neural network prediction model is established, and automatic prediction alarm is realized through the BP neural network prediction model.

2. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S01, the power battery status data includes current, cell voltage extreme value, cell temperature extreme value, temperature difference maximum value, pressure difference maximum value, insulation resistance, SOC and SOH; The vehicle operating condition data includes vehicle speed, road surface flatness and climbing height; The vehicle working intensity data includes the load capacity and lifting height of the industrial vehicle; The external environment temperature data includes the vehicle working environment temperature.

3. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S01, the industrial vehicle is a power-driven motor vehicle used for transporting, pushing, pulling, lifting, stacking or placing various goods.

4. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S01, the operation data within a period of time is the operation data within a period of half a month to one year.

5. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S02, the extraction of the whole operation parameters includes the extraction of vehicle speed, road surface flatness, climbing height, load capacity, and lifting height; thereby obtaining the required power of the whole vehicle; In the acquisition of the required power of the whole vehicle, the required power is parameter data obtained by the on-board VCU according to the driver stepping on the accelerator or brake pedal. The most direct monitoring method reflected on the battery end is to determine the value of the product of the current voltage and current to obtain the required power.

6. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S02, the influence of the external environment temperature data on the battery is extracted, including data extraction of temperature, battery discharge rate, discharge rate and SOH.

7. The automatic prediction and alarm method for power batteries of industrial vehicles according to claim 1 is characterized in that: In step S03, the power battery status data includes the power battery current, cell voltage extreme value, cell temperature extreme value, temperature difference maximum value, pressure difference maximum value, insulation resistance, SOC and SOH data; The relationship between the analyses is analyzed to obtain the temperature rise rate, voltage drop rate and voltage rise rate. Specifically, the composite equal division method is used to divide the data into sections of 10S each, and the relationship between the current size and the temperature rise rate, voltage drop rate and voltage rise rate under multiple data sections is determined, so as to achieve the result of data recognition using the BP neural network. In subsequent applications, new data can automatically predict the possible rates of temperature rise, voltage drop and voltage rise, so as to achieve the function of early warning.

8. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S04, the warning includes three levels of warning; the three levels of warning include level one warning, level two warning and level three warning; The power battery parameter value includes at least one of the total voltage, single cell voltage, single cell pressure difference, high and low temperature of charge and discharge, charge and discharge overcurrent, SOC, and SOH; The threshold is a protection parameter threshold set by the BMS.

9. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S05, after the BP neural network prediction model is constructed, subsequent new data is imported into the model for prediction to obtain the training accuracy. If the accuracy is not high, the model returns to the initial state and is retrained. The accurate BP neural network prediction model is obtained through continuous iteration. The prediction accuracy of the BP neural network prediction model reaches more than 98%. The influencing factors of the remaining parameters include at least one of the following two situations: when the total current is in the charging and discharging state, if the total current is too large, it will cause the battery cell temperature to rise sharply, triggering the protection parameter and the battery will automatically shut down; or if it continues to be charged and discharged with a large current under low temperature conditions, it will have a serious impact on the battery cell SOH.

10. The automatic prediction and alarm method for industrial vehicle power batteries according to claim 1 is characterized in that: In step S05, the BP neural network prediction model obtains accurate prediction accuracy by iteratively training the operation data of the industrial vehicle in step S01.

Images