CN117741444A - Method and device for predicting battery shipment voltage and electronic equipment - Google Patents
Method and device for predicting battery shipment voltage and electronic equipment Download PDFInfo
- Publication number
- CN117741444A CN117741444A CN202311745117.8A CN202311745117A CN117741444A CN 117741444 A CN117741444 A CN 117741444A CN 202311745117 A CN202311745117 A CN 202311745117A CN 117741444 A CN117741444 A CN 117741444A
- Authority
- CN
- China
- Prior art keywords
- voltage
- capacity
- battery
- pressure difference
- dividing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 111
- 230000008569 process Effects 0.000 claims abstract description 56
- 230000003068 static effect Effects 0.000 claims abstract description 42
- 238000005259 measurement Methods 0.000 claims abstract description 25
- 238000004519 manufacturing process Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000000284 resting effect Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000036961 partial effect Effects 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 12
- 230000002829 reductive effect Effects 0.000 abstract description 3
- 238000004146 energy storage Methods 0.000 description 26
- 238000003860 storage Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The invention discloses a method and a device for predicting battery shipment voltage and electronic equipment. In the method for predicting the battery shipment voltage, a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference is established. And recording the measured value of the capacity-dividing voltage rebound quantity of the battery to be measured in the capacity-dividing process of the battery to be measured. And determining the predicted standing pressure difference of the battery to be tested according to the relation model and the measured value of the capacity-division voltage rebound quantity. According to the predicted standing pressure difference and the capacity-division ending voltage, the predicted shipment voltage of the battery to be detected is determined, and the prediction of the shipment voltage of the battery is realized by analyzing and processing big data. The prediction method is based on a relation model, and can complete prediction by combining measured data in the capacity division process, compared with the prediction process, the static measurement after capacity division saves a great amount of time, the prediction process does not need to carry out high-precision measurement on the voltage of the battery before and after static, the dependence on the precision of measurement equipment is avoided, and the time cost and the economic cost are greatly reduced.
Description
Technical Field
The embodiment of the invention relates to a battery manufacturing technology, in particular to a battery shipment state voltage prediction method and device and electronic equipment.
Background
As energy storage battery technology is widely applied in various fields, the factory standard of energy storage batteries is also becoming stricter.
In the existing production process, before the energy storage batteries are formed into the offline state, the shipment state voltage (also referred to as IROCV voltage) of each energy storage battery needs to be obtained so as to grade the energy storage batteries.
However, in the mass production process, after the capacity division process, the energy storage battery needs to be kept still for at least one day before the shipment voltage measurement can be performed. Such a production flow requires a long standing time and also puts high precision demands on the voltage measuring equipment.
Disclosure of Invention
The invention provides a method and a device for predicting battery shipment voltage and electronic equipment, which are used for saving production time and reducing the precision requirement on the equipment.
In a first aspect, an embodiment of the present invention provides a method for predicting a battery shipment voltage, where the method for predicting a battery shipment voltage includes:
based on a sample database, establishing a relation model between a capacity-dividing voltage rebound quantity and a standing pressure difference, wherein the capacity-dividing voltage rebound quantity is generated by standing treatment after first discharging in a capacity-dividing process, and the standing pressure difference is a voltage difference before and after the standing treatment after the capacity-dividing process;
recording a measured value of the capacity-dividing voltage rebound quantity of the battery to be measured in the capacity-dividing process of the battery to be measured;
determining the predicted standing pressure difference of the battery to be tested according to the relation model and the measured value of the capacity-division voltage rebound quantity;
and determining the predicted shipment state voltage of the battery to be detected according to the predicted standing pressure difference and the capacity-division ending voltage.
Optionally, before the establishing a relation model between the volumetric voltage rebound quantity and the standing pressure difference based on the sample database, the method further comprises:
according to battery identity information corresponding to the data, matching and grouping capacity-dividing process data in a historical database and the shipment state voltage in a one-to-one correspondence manner, wherein the capacity-dividing process data comprises the voltage rebound quantity, capacity-dividing end voltage and capacity-dividing after-standing time length;
determining the corresponding standing pressure difference according to the capacity-division ending voltage and the corresponding shipment state voltage;
and extracting the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set, and establishing the sample database.
Optionally, before the determining the corresponding standing pressure difference according to the capacity division end voltage and the corresponding shipment state voltage, the method further includes:
removing the data groups with the standing time length which is not equal to the preset time length after capacity division in the historical database;
before the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set are extracted and the sample database is built, the method further comprises the following steps:
and eliminating the data group with abnormal standing pressure difference in the historical database.
Optionally, the data set with abnormal standing pressure difference includes a data set with the standing pressure difference exceeding a preset pressure difference range and a data set with the standing pressure difference not conforming to single-tray sigma screening.
Optionally, the establishing a relation model between the volume-dividing voltage rebound quantity and the standing pressure difference based on the sample database includes:
calculating the average value of the standing pressure difference in the data groups with the same value of the volume-dividing voltage rebound quantity;
fitting the relation model between the volume-dividing voltage rebound quantity and the static pressure difference based on the value of the volume-dividing voltage rebound quantity and the corresponding average value of the static pressure difference.
Optionally, after the relation model between the volumetric voltage rebound amount and the static pressure difference is established based on the sample database, the method further comprises:
and carrying out parameter adjustment on the relation model according to the actual measurement sample.
Optionally, the number of data sets in the sample database is not less than 10 ten thousand.
Optionally, the history database comprises data of at least two production lots.
In a second aspect, the embodiment of the invention also provides a device for predicting the battery shipment voltage, which comprises a model building module, a measuring module, a static pressure difference predicting module and a shipment voltage predicting module;
the model building module is used for building a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference based on a sample database, wherein the capacity-dividing voltage rebound quantity is generated by standing treatment after first discharging in the capacity-dividing process, and the standing pressure difference is the voltage difference before and after the standing treatment after the capacity-dividing process;
the measuring module is used for recording the measured value of the capacity-division voltage rebound quantity of the battery to be measured in the capacity-division process of the battery to be measured;
the static pressure difference prediction module is used for determining the predicted static pressure difference of the battery to be detected according to the relation model and the measured value of the capacity-division voltage rebound quantity;
and the shipment voltage prediction module is used for determining the predicted shipment voltage of the battery to be detected according to the predicted standing pressure difference and the measured value of the capacity-division voltage rebound quantity.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of predicting battery shipment voltage as described in any of the first aspects.
According to the battery shipment state voltage prediction method, device and electronic equipment provided by the invention, a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference is established based on a sample database. And recording the measured value of the capacity-dividing voltage rebound quantity of the battery to be measured in the capacity-dividing process of the battery to be measured. And determining the predicted standing pressure difference of the battery to be tested according to the relation model and the measured value of the capacity-division voltage rebound quantity. According to the predicted standing pressure difference and the capacity-division ending voltage, the predicted shipment voltage of the battery to be detected is determined, and the prediction of the shipment voltage of the battery is realized by analyzing and processing big data. According to the prediction method, based on a relation model, the prediction of the battery shipment state voltage can be completed by combining measured data in the capacity division process, a great amount of time is saved in the prediction process compared with the static measurement after capacity division, the high-precision measurement of the battery voltage before and after static is not needed in the prediction process, the dependence on the precision of measurement equipment is avoided, and the time cost and the economic cost are greatly reduced.
Drawings
Fig. 1 is a flow chart of a method for predicting battery shipment voltage according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating another method for predicting battery shipment voltage according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing a linear relationship between a static pressure difference and a capacity-divided voltage rebound amount under the condition that the number of data sets in a sample database is 10 ten thousand according to the embodiment of the present invention;
FIG. 4 is a schematic diagram showing a linear relationship between a static pressure difference and a capacity-divided voltage rebound amount under the condition that the number of data sets in a sample database is 20 ten thousand according to the embodiment of the present invention;
fig. 5 is a flowchart of another method for predicting battery shipment voltage according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a device for predicting battery shipment voltage according to an embodiment of the present invention;
fig. 7 shows a schematic diagram of an electronic device that may be used to implement an embodiment of the invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
As described in the background art, in the batch manufacturing process of the energy storage battery, after the capacity division process of the energy storage battery, the measurement of the shipment voltage can be performed after at least one day of standing, and the consistency and the performance stability of the energy storage battery are improved through standing, so that the measurement result is more accurate. Such a production process requires at least one day of standing time, and at the same time places high precision demands on the voltage measuring equipment, requiring a lot of time and economic costs. In order to solve the problems, the inventor performs a great deal of data collection, analysis and research, and researches find that a certain functional relationship exists between capacity-dividing process data of the energy storage battery and the subsequently measured shipment voltage, and based on the functional relationship, the application provides a battery shipment voltage prediction method, a battery shipment voltage prediction device and electronic equipment.
Fig. 1 is a flowchart of a method for predicting battery shipment voltage according to an embodiment of the present invention, and referring to fig. 1, the method for predicting battery shipment voltage includes:
s101, based on a sample database, establishing a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference.
Specifically, in the existing production flow of the energy storage battery, the capacity-dividing process sequentially comprises a first full charge, a first discharge, a second discharge and a second full charge. After the first discharging, a standing treatment is needed, and the voltage of the energy storage battery can generate certain rebound in the standing process. The capacity-dividing voltage rebound quantity refers to the voltage rebound quantity generated by standing treatment after the first discharge in the capacity-dividing process. After the capacity-dividing process is finished (the second full charge is finished), still standing treatment is needed, and the standing treatment can enable the energy storage battery to generate certain voltage drop. The static pressure difference refers to the pressure difference before and after the static treatment after the end of the capacity separation process.
The sample database is a practical measurement large database storing the rebound quantity of the multi-component capacitance voltage and the corresponding standing pressure difference. The data in the sample database are all from history actual measurement, and each data group corresponds to an energy storage battery from a history factory. Illustratively, the number of data sets in the sample database is not less than 10 tens of thousands. The relationship model refers to a mathematical relationship model between the partial volume voltage rebound amount and the rest differential pressure, and may include a linear function model, for example. From the data sets in the sample database, a plurality of data points may be determined, wherein the number of data points may correspond one-to-one to the data sets. And fitting a relation model according to the discrete data points. In the relation model, the volume-dividing voltage rebound quantity is an independent variable, and the standing pressure difference is a dependent variable. The fitting method may employ a least squares method.
S102, recording a measured value of the capacity-division voltage rebound quantity of the battery to be measured in the capacity-division process of the battery to be measured.
Specifically, after the relation function is established, the produced battery to be measured can be directly predicted according to the volume-dividing voltage rebound quantity and the relation function in the volume-dividing process and the volume-dividing ending voltage without implementing the standing operation after the volume-dividing is finished or measuring the battery voltage after the standing operation to obtain the shipment state voltage. When the shipment voltage of the battery to be measured needs to be predicted, capacity-dividing operation can be implemented on the battery to be measured, and the measured value of the capacity-dividing voltage rebound quantity of the battery to be measured is recorded in the capacity-dividing process. And measuring the voltage of the battery to be measured at the end of capacity division, and taking the voltage as the capacity division end voltage.
S103, according to the relation model and the measured value of the capacity-division voltage rebound quantity, the predicted standing pressure difference of the battery to be measured is determined.
Specifically, the predicted resting pressure difference refers to a predicted value of the resting pressure difference of the battery to be measured. According to the relation between the volume-dividing voltage rebound quantity and the static pressure difference represented in the relation function, the static pressure difference corresponding to the measured value of the volume-dividing voltage rebound quantity can be determined, namely the predicted static pressure difference. By way of example, the measured value of the partial voltage rebound quantity is substituted into the relational model, and the resting pressure difference corresponding to the measured value of the partial voltage rebound quantity, that is, the predicted resting pressure difference of the battery to be measured, can be determined.
S104, determining the predicted shipment voltage of the battery to be tested according to the predicted standing pressure difference and the capacity-division ending voltage.
Specifically, the predicted shipment voltage is a predicted value indicating the shipment voltage. The shipment voltage is the voltage value of two ends of the battery to be measured after passing through capacity division and standing in sequence, and the shipment voltage is equal to the capacity division ending voltage minus the standing pressure difference in value, so after the predicted standing pressure difference of the battery to be measured is determined, the predicted standing pressure difference can be subtracted by the capacity division ending voltage to obtain the predicted shipment voltage of the battery to be measured, and the prediction of the shipment voltage of the battery is realized.
According to the battery shipment voltage prediction method provided by the embodiment, a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference is established based on the sample database. And recording the measured value of the capacity-dividing voltage rebound quantity of the battery to be measured in the capacity-dividing process of the battery to be measured. And determining the predicted standing pressure difference of the battery to be tested according to the relation model and the measured value of the capacity-division voltage rebound quantity. According to the predicted standing pressure difference and the capacity-division ending voltage, the predicted shipment voltage of the battery to be detected is determined, and the prediction of the shipment voltage of the battery is realized by analyzing and processing big data. According to the prediction method, based on a relation model, the prediction of the battery shipment state voltage can be completed by combining measured data in the capacity division process, a great amount of time is saved in the prediction process compared with the static measurement after capacity division, the high-precision measurement of the battery voltage before and after static is not needed in the prediction process, the dependence on the precision of measurement equipment is avoided, and the time cost and the economic cost are greatly reduced.
Fig. 2 is a schematic diagram of another method for predicting battery shipment voltage according to an embodiment of the present invention, and on the basis of the foregoing embodiment, referring to fig. 2, the method for predicting battery shipment voltage includes:
and S201, matching the capacity-dividing process data and the shipment state voltage in the historical database in a one-to-one correspondence manner according to the battery identity information corresponding to the data.
Specifically, the battery identity information refers to identification information of energy storage batteries shipped historically, and illustratively, the battery identity information may include battery identity numbers, each of which has its unique battery identity number. Any parameter information of the energy storage battery collected in the production process is stored corresponding to the battery identity information of the energy storage battery. The historical database is a storage library of process parameters collected in the production process of the energy storage battery from the factory, wherein the process parameters comprise battery identity information, capacity-dividing process data corresponding to the battery identity information and shipment state voltage. Illustratively, the historical database includes data for at least two production lots to enrich the data sources, reducing prediction errors caused by differences in environmental parameters, material lots, and other variables between different production lots.
The capacity-dividing process data refer to parameter data of the energy storage battery recorded in the process of carrying out capacity-dividing operation on the energy storage battery and in standing after the process is finished, wherein the capacity-dividing process data comprise voltage rebound quantity, capacity-dividing finishing voltage and standing time after capacity division. The capacity-division end voltage refers to the voltage at the end of capacity division, that is, the voltage of the energy storage battery when the last full charge is completed. The standing time after capacity division refers to the duration of the standing operation between the end of capacity division and the time of measuring the shipment voltage. The shipment state voltage refers to the voltage value of the two ends of the battery to be measured after the shipment state voltage is subjected to capacity passing and standing in sequence, and the shipment state voltage can be obtained through measurement of a voltage measuring device. In the step, the corresponding capacity-dividing process data with the same battery identity information and the shipment voltage are matched in a one-to-one correspondence manner.
S202, determining corresponding standing pressure difference according to the capacity-division ending voltage and the corresponding shipment state voltage.
Specifically, the static pressure difference refers to a voltage difference before and after the static treatment after the end of the capacity division process. By calculating the difference between the capacity division end voltage and the shipment state voltage of the corresponding point, the corresponding standing pressure difference of the energy storage battery can be determined and stored in the corresponding data set.
S203, extracting the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set, and establishing a sample database.
Specifically, the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set are extracted, and a sample database can be established. Similar to the historical database, each set of data in the sample database also corresponds to one energy storage cell.
S204, calculating the average value of the standing pressure difference in the data groups with the same value of the volume-dividing voltage rebound quantity in the sample database.
Specifically, since the data size in the historical database is large and generally exceeds 10 ten thousand groups, and the measurement accuracy of the volume-dividing voltage rebound amount is limited, the historical database and the sample database can include data with equal volume-dividing voltage rebound amounts, that is, the value of one volume-dividing voltage rebound amount corresponds to a plurality of static pressure differences. In the step, the average value of the standing pressure difference corresponding to the value of the capacity-division voltage rebound quantity in the sample database is calculated in sequence. For example, if the volume-divided voltage rebound amount is 90mV in 5 data groups, and the rest voltage differences in the five data groups are 13.68mV, 13.65mV, 13.66mV and 13.67mV respectively, the average value of the rest voltage differences corresponding to the volume-divided voltage 90mV is equal to (13.68+13.68+13.65+13.66+13.67)/5 mV. In addition, if the value of the partial voltage rebound quantity only appears once in the sample database, that is, is not repeated, the rest pressure difference corresponding to the partial voltage rebound quantity is the average value.
S205, fitting a relation model between the volume-dividing voltage rebound quantity and the static pressure difference based on the value of the volume-dividing voltage rebound quantity and the corresponding average value of the static pressure difference.
Specifically, the independent variable of the relation model is the volume-dividing voltage rebound quantity, and the dependent variable is the static pressure difference. The value of the volume-dividing voltage rebound quantity in each data group of the sample database and the average value of the corresponding standing pressure difference can form a data point. And fitting based on the data points, so that a functional relation model between the volume-dividing voltage rebound quantity and the standing pressure difference can be determined. Illustratively, the number of data sets in the sample database may be equal to 10 ten thousand or 20 ten thousand. Fig. 3 is a schematic diagram of a linear relationship between a static pressure difference and a capacity-division voltage rebound amount when the number of data sets in the sample database is 10 ten thousand, and fig. 4 is a schematic diagram of a linear relationship between a static pressure difference and a capacity-division voltage rebound amount when the number of data sets in the sample database is 20 ten thousand, wherein the static time is 24 hours, and when the number of data sets in the sample database is more, the distribution of data points is more uniform and concentrated, and the data points are closer to a relationship curve, in combination with fig. 3 and fig. 4.
S206, carrying out parameter adjustment on the relation model according to the actual measurement sample.
Specifically, the measured sample refers to measured data obtained by an experiment or an actual production process after a sample database is formed for the first time, and includes measured volumetric voltage rebound quantity and static pressure difference. And further correcting the relation model by utilizing a sample in a subsequent experiment or actual production, so that the relation model is more close to the actual condition of the recently produced energy storage battery. The method includes the steps that a corresponding measured data point is determined by using a measured sample, and then the measured data point participates in fitting and correcting of a relation model, so that the purpose of adjusting parameters of the relation model is achieved.
S207, recording the measured value of the capacity-division voltage rebound quantity of the battery to be measured in the capacity-division process of the battery to be measured.
S208, according to the relation model and the measured value of the capacity-division voltage rebound quantity, the predicted standing pressure difference of the battery to be measured is determined.
S209, determining the predicted shipment state voltage of the battery to be tested according to the predicted standing pressure difference and the capacity-division ending voltage.
Steps S207, S208 and S209 are the same as the foregoing steps S102, S103 and S104, respectively, and are not described herein.
According to the battery shipment state voltage prediction method provided by the embodiment, the capacity-dividing process data and the shipment state voltage in the historical database are correspondingly matched one by one according to the battery identity information corresponding to the data before the relation model is established. And then determining corresponding standing pressure difference according to the capacity-dividing ending voltage and the corresponding shipment state voltage. And extracting the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set, and establishing a sample database. When the relation model is established, the average value of the standing pressure difference in the data groups with the same value of the volume-dividing voltage rebound quantity is calculated. Based on the numerical value of the volume-dividing voltage rebound quantity and the corresponding average value of the standing pressure difference, fitting a relation model between the volume-dividing voltage rebound quantity and the standing pressure difference. After the relationship model is first formed, parameter adjustment can be carried out on the relationship model according to the actually measured sample, so that the relationship model between the capacity-division voltage rebound quantity and the standing pressure difference is determined according to big data, the data quantity, the data processing and the correction mechanism are set, the accuracy of the relationship model is improved, and the reliability of a prediction result is further improved.
Fig. 5 is a flowchart of another method for predicting battery shipment voltage according to an embodiment of the present invention, and referring to fig. 5, the method for predicting battery shipment voltage includes:
and S301, matching the capacity-dividing process data and the shipment state voltage in the historical database in a one-to-one correspondence manner according to the battery identity information corresponding to the data.
The content of step S301 is the same as the content of step S201, and will not be described here.
S302, eliminating the data group with the standing time length which is not equal to the preset time length after capacity division in the historical database.
Specifically, the standing time period after capacity division means. The preset duration refers to preset standing duration, the preset duration can be equal to any value between 24 hours and 26 hours, and the selection of the preset duration is related to the standing duration required by the measurement of the cargo state voltage of the battery to be measured in production. Illustratively, the preset duration may be equal to 24 hours. In the step, the standing time length after capacity division is compared with the preset time length, and the data group where the standing time length after capacity division is not equal to the preset time length is removed, so that the data with different standing time lengths and required time lengths in the production process are removed, and the prediction accuracy is further improved.
S302, determining corresponding standing pressure difference according to the capacity division ending voltage and the corresponding shipment state voltage.
The content of step S303 is the same as the content of step S202, and will not be described here.
S304, eliminating the data group with abnormal standing pressure difference in the history database.
Specifically, the data group having an abnormal differential pressure at rest refers to a data group having a large differential pressure at rest error among the data groups. Illustratively, the data set of the rest differential pressure abnormality includes a data set of which the rest differential pressure exceeds a preset differential pressure range and a data set of which the rest differential pressure does not conform to a single tray sigma screen, wherein a multiple of the sigma screen may be ±2 or ±3. On the one hand, the values of 99.9% of the rest pressure differences in the historical database are all in the range of 12mV-13mV (i.e. the preset pressure difference range), and when the rest pressure difference in one data set is equal to 1mV, the rest pressure difference is 1mV, and the data set where the rest pressure difference is located needs to be removed. On the other hand, the rest pressure differences of other energy storage batteries in a single tray meet sigma screening conditions, namely, the rest pressure differences of all the energy storage batteries in the single tray are near the average level and within the allowable error range, and one rest pressure difference exceeds the allowable error range, so that the rest pressure difference is abnormal data, and the data group where the rest pressure difference is located needs to be removed.
S305, extracting the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set, and establishing a sample database.
S306, based on the sample database, establishing a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference.
S307, recording the measured value of the capacity-division voltage rebound quantity of the battery to be measured in the capacity-division process of the battery to be measured.
S308, according to the relation model and the measured value of the capacity-division voltage rebound quantity, determining the predicted standing pressure difference of the battery to be measured.
S309, determining the predicted shipment voltage of the battery to be tested according to the predicted standing pressure difference and the capacity-division ending voltage.
The contents of steps S305, S306, S307, S308 and S309 are the same as those of steps S203, S101, S102, S103 and S104 described above, and will not be described again here.
In the method for predicting the battery shipment voltage provided in this embodiment, before determining the corresponding standing pressure difference according to the capacity-dividing end voltage and the corresponding shipment voltage, the data set with the standing time length different from the preset time length after capacity division in the history database is removed. Before the volume-dividing voltage rebound quantity and the corresponding static pressure difference in each data set are extracted and the sample database is established, the data set with abnormal static pressure difference in the historical database is removed, the abnormal data set and the improper data set are removed, and the prediction accuracy is further improved.
In order to verify the accuracy of the method for predicting the battery shipment voltage provided by the invention, the inventor respectively predicts a plurality of batteries to be detected twice by using the method of fig. 5, wherein the number of data sets of a sample database predicted for the first time is 10 ten thousand, the number of data sets of a sample database predicted for the second time is 20 ten thousand, and the capacity division end voltage is 3500mV in the experimental example. The experimental data are shown in the following table, and according to the data in the table, the error of the two predicted shipment voltage is less than 0.01mV, and the error is basically consistent with the measured shipment voltage, so that the actual production requirement can be met.
Table 1 shows actual measurement data in the experiment and corresponding twice prediction data and errors the embodiment of the invention also provides a prediction device for battery shipment voltage. Fig. 6 is a schematic diagram of the composition of a device for predicting battery shipment voltage according to an embodiment of the present invention, referring to fig. 6, a device 600 for predicting battery shipment voltage includes a model building module 601, a measurement module 602, a static pressure difference prediction module 603, and a shipment voltage prediction module 604, where the model building module 601 is configured to build a relationship model between a volume-dividing voltage rebound amount and a static pressure difference based on a sample database, the volume-dividing voltage rebound amount is a voltage rebound amount generated by static processing after first discharging in a volume-dividing process, and the static pressure difference is a voltage difference before and after static processing after the volume-dividing process. The measurement module 602 is configured to record a measurement value of a capacity-division voltage rebound amount of the battery to be measured during the capacity-division process of the battery to be measured. The static pressure difference prediction module 603 is configured to determine a predicted static pressure difference of the battery to be measured according to the relationship model and the measured value of the capacity-to-capacity voltage rebound quantity. The shipment voltage prediction module 604 is configured to determine a predicted shipment voltage of the battery to be measured according to the predicted measurement value of the standing voltage difference and the capacity voltage rebound amount.
Fig. 7 shows a schematic diagram of an electronic device that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 7, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a method of predicting battery shipment voltage.
In some embodiments, the method of predicting battery shipment voltage may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the battery shipment voltage prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of predicting battery shipment voltage in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for predicting battery shipment voltage, comprising:
based on a sample database, establishing a relation model between a capacity-dividing voltage rebound quantity and a standing pressure difference, wherein the capacity-dividing voltage rebound quantity is generated by standing treatment after first discharging in a capacity-dividing process, and the standing pressure difference is a voltage difference before and after the standing treatment after the capacity-dividing process;
recording a measured value of the capacity-dividing voltage rebound quantity of the battery to be measured in the capacity-dividing process of the battery to be measured;
determining the predicted standing pressure difference of the battery to be tested according to the relation model and the measured value of the capacity-division voltage rebound quantity;
and determining the predicted shipment state voltage of the battery to be detected according to the predicted standing pressure difference and the capacity-division ending voltage.
2. The method according to claim 1, further comprising, before the establishing a relation model between the volumetric voltage rebound amount and the resting differential pressure based on the sample database:
according to battery identity information corresponding to the data, matching and grouping capacity-dividing process data in a historical database and the shipment state voltage in a one-to-one correspondence manner, wherein the capacity-dividing process data comprises the voltage rebound quantity, capacity-dividing end voltage and capacity-dividing after-standing time length;
determining the corresponding standing pressure difference according to the capacity-division ending voltage and the corresponding shipment state voltage;
and extracting the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set, and establishing the sample database.
3. The method according to claim 2, characterized by further comprising, before said determining the corresponding resting differential pressure from the capacity-dividing end voltage and the corresponding shipment voltage:
removing the data groups with the standing time length which is not equal to the preset time length after capacity division in the historical database;
before the volume-dividing voltage rebound quantity and the corresponding standing pressure difference in each data set are extracted and the sample database is built, the method further comprises the following steps:
and eliminating the data group with abnormal standing pressure difference in the historical database.
4. The method according to claim 3, wherein the data set with abnormal resting pressure difference includes a data set with the resting pressure difference exceeding a preset pressure difference range and a data set with the resting pressure difference not conforming to single-tray sigma screening.
5. The method for predicting battery shipment voltage according to claim 2, wherein the establishing a relationship model between the partial capacity voltage rebound amount and the standing pressure difference based on the sample database comprises:
calculating the average value of the standing pressure difference in the data groups with the same value of the volume-dividing voltage rebound quantity;
fitting the relation model between the volume-dividing voltage rebound quantity and the static pressure difference based on the value of the volume-dividing voltage rebound quantity and the corresponding average value of the static pressure difference.
6. The method according to claim 2, further comprising, after the establishing a relation model between the partial capacity voltage rebound amount and the resting differential pressure based on the sample database:
and carrying out parameter adjustment on the relation model according to the actual measurement sample.
7. The method for predicting battery shipment voltage according to any one of claims 1-6, wherein the number of data sets in the sample database is not less than 10 ten thousand.
8. The method of claim 2-6, wherein the historical database includes data for at least two production lots.
9. A battery shipment voltage prediction apparatus, comprising:
the model building module is used for building a relation model between the capacity-dividing voltage rebound quantity and the standing pressure difference based on a sample database, wherein the capacity-dividing voltage rebound quantity is generated by standing treatment after first discharging in the capacity-dividing process, and the standing pressure difference is the voltage difference before and after the standing treatment after the capacity-dividing process;
the measuring module is used for recording the measured value of the capacity-division voltage rebound quantity of the battery to be measured in the capacity-division process of the battery to be measured;
the static pressure difference prediction module is used for determining the predicted static pressure difference of the battery to be detected according to the relation model and the measured value of the capacity-division voltage rebound quantity;
and the shipment voltage prediction module is used for determining the predicted shipment voltage of the battery to be detected according to the predicted standing pressure difference and the measured value of the capacity-division voltage rebound quantity.
10. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the battery shipment voltage prediction method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311745117.8A CN117741444A (en) | 2023-12-18 | 2023-12-18 | Method and device for predicting battery shipment voltage and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311745117.8A CN117741444A (en) | 2023-12-18 | 2023-12-18 | Method and device for predicting battery shipment voltage and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117741444A true CN117741444A (en) | 2024-03-22 |
Family
ID=90252114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311745117.8A Pending CN117741444A (en) | 2023-12-18 | 2023-12-18 | Method and device for predicting battery shipment voltage and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117741444A (en) |
-
2023
- 2023-12-18 CN CN202311745117.8A patent/CN117741444A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN115718265A (en) | Method for correcting battery DC resistance test value, electronic device and storage medium | |
| CN115598505A (en) | Chip detection method, device, equipment and storage medium | |
| CN115794916A (en) | Data processing method, device, equipment and storage medium for multi-source data fusion | |
| CN117741444A (en) | Method and device for predicting battery shipment voltage and electronic equipment | |
| CN115375039A (en) | Industrial equipment fault prediction method and device, electronic equipment and storage medium | |
| CN114879042A (en) | Method and device for predicting partial capacity and discharge capacity of battery cell and electronic equipment | |
| CN115344495A (en) | Data analysis method and device for batch task test, computer equipment and medium | |
| CN114999665A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN115408858A (en) | Pulse spectrum parameter partitioning method and device, electronic equipment and storage medium | |
| CN115328898A (en) | Data processing method and device, electronic equipment and medium | |
| CN114884813A (en) | Network architecture determination method and device, electronic equipment and storage medium | |
| CN117131353B (en) | Method and device for determining out-of-tolerance electric energy meter, electronic equipment and storage medium | |
| CN114966439A (en) | Battery capacity grading test method and device, electronic equipment and storage medium | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN115511047B (en) | Quantification method, device, equipment and medium of Softmax model | |
| CN117520605A (en) | Electric power data acquisition method, device, equipment and storage medium | |
| CN114816758B (en) | Resource allocation method and device | |
| CN116819342A (en) | Battery life curve determining method and device, electronic equipment and storage medium | |
| CN116027197A (en) | Method, device, equipment and storage medium for evaluating self-discharge consistency of battery | |
| CN118033461A (en) | Method and device for evaluating battery health state and electronic equipment | |
| CN116881857A (en) | Product recommendation method, device, equipment and medium | |
| CN116258395A (en) | Project monitoring scheme attribute weight generation method, project monitoring scheme generation method and device | |
| CN116643186A (en) | Current detection method, capacity prediction method, screening method, device and medium for self-discharge of battery | |
| CN117608896A (en) | Transaction data processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |