Lead-acid storage battery current acquisition system and method thereof

Abstract

The invention provides a lead-acid storage battery current acquisition system and a method thereof, and relates to the technical field of storage battery current acquisition. Acquisition results of different current acquirers on currents with different characteristics in different environments when the currents of a lead-acid storage battery are acquired through a detection test module; the error value of the current of each current collector is calculated, the historical and real-time current data of the lead-acid storage battery and the environmental parameters of the current collectors are obtained through the data acquisition module, the comprehensive characteristic index of the current is calculated, and then the proper current collector is selected and switched to serve as the current collector for lead current acquisition. A current acquisition error calculation model is established through an error calculation module, acquired real-time environment parameters and current acquisition device types are used as input of the model, corresponding current acquisition error values are output, and an acquisition output module performs error compensation on acquisition results of a current acquisition device according to the current acquisition error values and outputs accurate measurement results.

Description

Technical Field

[0001] The invention relates to the technical field of battery current collection, and in particular to a lead-acid battery current collection system and method. Background Art

[0002] Lead-acid batteries are a mature energy storage technology and are widely used due to their low cost, mature recycling and good technical stability. Currently, with the development of lithium batteries and intelligent battery management systems for lithium batteries, lead-acid batteries are gradually being replaced. Therefore, the intelligent management system of lead-acid batteries is very important. How to accurately collect current has become the first problem to be solved.

[0003] In the prior art, publication number CN 103943901 A discloses a lead-acid battery current acquisition system and method thereof, including a battery, a battery cover, a battery management system, a cover sheet, positive and negative terminal poles and a current acquisition component, wherein the positive and negative terminal poles are installed on the battery, the battery cover is installed on one end of the battery provided with the positive and negative terminal poles, the battery management system is installed on the battery cover and connected to the battery, the cover sheet is installed on the battery cover and placed above the battery management system, the current acquisition component is installed on the positive and negative terminal poles, the positive and negative terminal poles are provided with terminal cover sheets and placed above the current acquisition component, and the data of the current sensor is collected through the cooperation between the induction magnetic ring in the current acquisition component and the positive and negative terminal poles to perform current acquisition through the battery management system. However, in the current measurement technology of lead-acid batteries, the induction magnetic ring often faces the problem that the accuracy is affected by environmental factors, which will cause deviations in the measurement results, and is affected by the physical properties of the induction magnetic ring itself, resulting in inaccurate current measurement results when the current is small and the current fluctuation amplitude is small.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The object of the present invention is to provide a lead-acid battery current acquisition system and method thereof to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A lead-acid battery current acquisition system, comprising:

[0008] A detection test module, which is used to obtain the current collection results of different characteristics of different current collectors under different environments by using a single dependent variable method when collecting the current of lead-acid batteries, and record the environmental data, current characteristics and collection results of different collection results, print a timestamp on each set of data to form an experimental data set, and select the data under the rated environment of the current collector as the benchmark data;

[0009] A data acquisition module, which is used to calculate the comprehensive characteristic index of the current of the lead-acid battery by acquiring the historical and real-time current magnitude, current direction, and current duration data of the lead-acid battery, and to collect environmental parameters of the current collector;

[0010] A data analysis module, the data analysis module is used to calculate the current error value between each current collector and the selected benchmark data, and form a training data set with the experimental data set, and at the same time select and switch a suitable current collector as the current collector for lead-acid battery current collection according to the comprehensive characteristic index of the current and the type of the current collector;

[0011] An error calculation module, which is used to establish a current acquisition error calculation model, train the error calculation model by using a training data set, and output the error value of the current collected by the corresponding current collector by using the collected real-time environmental parameters and the current collector type as the input of the model;

[0012] The acquisition output module is used to perform error compensation on the acquisition result of the current collector according to the type of current sensor selected and the error value calculated by the current acquisition error calculation model of the corresponding type, and output accurate measurement results.

[0013] Furthermore, the current collector includes a shunt resistor and a Hall sensor, and the two current collectors are electrically connected via a series switching circuit;

[0014] The different environments include temperature and magnetic field;

[0015] The currents of different characteristics include the magnitude of the current, the direction of the current and the duration of the current;

[0016] The logic of the collection results of currents with different characteristics under different environments through the single dependent variable method is;

[0017] When the current of the lead-acid battery is collected by the current collector, only the duration of the current, the direction of the current, the magnitude of the current, the temperature of the current collector, the magnitude of the magnetic field and the type of the current collector are changed in sequence.

[0018] Furthermore, the calculation method logic of the comprehensive characteristic index of the electric quantity is as follows: the average value of the current and the average duration of the current are counted in sequence, and the volatility of the current is calculated. By weighting the average value of the current, the average duration of the current, and the volatility of the current in the comprehensive characteristic index, the specific calculation formula for calculating the comprehensive characteristic index of the current is as follows:

[0019]

[0020] Where, Ipj is the average current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected;

[0021]

[0022] Among them, Itp is the average duration of the current, CI cx is the duration of the current at the historical moment cx, cα is the collection time interval of the historical current duration, and tc is the number of collection times of the historical current duration;

[0023]

[0024] Among them, Ibd is the fluctuation of current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected;

[0025] Q=Ipj*β1+Itp*β2+Ibd*β3

[0026] Among them, Q is the comprehensive characteristic index of current, β1, β2, and β3 are the average value, average duration, and volatility weight of the current, respectively, among which, 0<β1<1, 0<β2<1, 0<β3<1, β1+β2+β3=1.

[0027] Furthermore, the method of selecting a suitable current collector according to the comprehensive characteristic index of the current and the type of the current collector is:

[0028] When Q∈(QH min ,QH max ), select and switch the Hall sensor as the current collector;

[0029] When Q∈(QD min ,QD max ), select and switch the shunt resistor as the current collector;

[0030] When Q∈[(QH min ,QH max )∩(QD min ,QDmax )], No switching is performed.

[0031] Furthermore, the calculation method of the error value of the current is:

[0032] ΔI1 γ1,γ2,γ3,γ4,γ5 =I1b-I1 γ1,γ2,γ3,γ4,γ5

[0033] ΔI1 γ1,γ2,γ3,γ4,γ5 is the current error when the duration of the current is γ1, the direction of the current is γ2, the magnitude of the current is γ3, the temperature of the current collector is γ4, and the magnitude of the magnetic field is γ5. I1b is the current value of the Hall sensor reference group, and I1 γ1,γ2,γ3,γ4,γ5 The current is a current with a duration of γ1, a direction of γ2, a magnitude of γ3, a temperature of the current collector of γ4, and a magnitude of the magnetic field of γ5.

[0034] Furthermore, the current acquisition error calculation model is based on a calculation model of a multi-layer perceptron neural network, including an input layer, a hidden layer, and an output layer;

[0035] Input layer;

[0036] X i =[Xr1,…,Xr k ,…,Xr q ]

[0037] Among them, X i is the input data set of the model, Xr k is the kth group of experimental data in the data set, and q is the total number of experimental data groups;

[0038] Hidden layers;

[0039] Z (1) =W (1) *X i +b (1)

[0040] a (1) =f(Z (1) )

[0041] Among them, Z (1) is the intermediate value of the hidden layer linear output, W (1) 、b (1) are the weight matrix and threshold of the hidden layer respectively, and f is the activation function;

[0042] Output layer;

[0043] Z (2) =W (2) *a (1) +b (2)

[0044] Y t+1 =y(Z (2) )

[0045] Among them, Z (2) is the intermediate value of the linear output of the output layer, W (2) 、b (2) are the weight matrix and threshold of the output layer, Y t+1 Risk assessment type, y is the softmax activation function, output current error value;

[0046] Among them, the activation function is the ReLU activation function, and the specific formula is:

[0047] f(Z (1) )=max(0,Z (1) )

[0048] The specific formula of the Softmax activation function is;

[0049]

[0050] Among them, i is the i-th input value of the Softmax activation function.

[0051] Furthermore, the calculation formula for performing error compensation on the collection result of the current collector and outputting the accurate measurement result is:

[0052] Ichu=Isi+ΔI

[0053] Among them, Ichu is the output current of the current acquisition system at the current moment, Isi is the current value collected at the current moment, and ΔI is the error value of the current at the current moment.

[0054] The present invention also provides a lead-acid battery current collection method, the current collection method is performed by the above-mentioned current collection system, and the current collection method steps include:

[0055] Step 1: Obtain different current collectors respectively, and collect the currents with different characteristics under different environments by using the single dependent variable method, and record the environmental data, current characteristics and collection results of different collection results, and print a timestamp on each set of data to form an experimental data set;

[0056] Step 2: Select the current data collected by different current sensors under standard working environment parameters as the benchmark data of the current sensor, calculate the error value of the current between each current collector and the benchmark data, and form a training data set with the experimental data set;

[0057] Step 3: Establish a current acquisition error calculation model, train the error calculation model through a training data set, and use the real-time environmental parameters and current collector type as inputs of the model to output the current error value of the corresponding current collector;

[0058] Step 4: By obtaining historical and real-time current magnitude, current direction, and current duration data, and calculating the comprehensive characteristic index of electric quantity, according to the comprehensive characteristic index of current and the type of current collector, select and switch a suitable current collector to collect current;

[0059] Step 5: According to the type of current sensor selected and the error value calculated by the current acquisition error calculation model of the corresponding type, the error compensation is performed on the acquisition result of the current collector to output the accurate measurement result.

[0060] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains the collection results of currents of different characteristics of different current collectors under different environments when collecting the current of lead-acid batteries through the detection test module, calculates the error value of the current of each current collector, and obtains the historical and real-time current data of the lead-acid battery and the environmental parameters of the current collector through the data acquisition module, calculates the comprehensive characteristic index of the current, and then selects and switches a suitable current collector as the current collector for lead current collection, establishes a current collection error calculation model through the error calculation module, and trains it, takes the collected real-time environmental parameters and the current collector type as the input of the model, outputs the corresponding current collection error value, and the collection output module compensates the collection result of the current collector according to the error value of the current collection, and outputs the accurate measurement result.

[0061] The present invention selects the most suitable current collector according to the comprehensive characteristic index of the current, which can ensure that the current collector used provides the best performance under specific conditions. Different types of current collectors may have their own strengths in terms of accuracy, response time, anti-interference ability, etc. Correct matching can give full play to the advantages of various current collectors. By real-time monitoring of current characteristics and dynamically switching current collectors, the system can adapt to changes in battery status or environmental conditions, ensuring that current collection is always carried out in the best state, and improving the anti-interference ability and stability of the system. A current collection error calculation model is established through a multi-layer perceptron neural network. The multi-layer perceptron can learn and simulate the nonlinear characteristics in the current collection process, and the current error can be accurately calculated to improve the prediction accuracy of the current measurement error. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of the overall system structure of the present invention;

[0063] Figure 2A circuit diagram for switching the current collector of the present invention;

[0064] Figure 3 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0065] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0066] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0067] Example:

[0068] See also Figure 1-2 , the present invention provides a technical solution:

[0069] A lead-acid battery current acquisition system, comprising:

[0070] A detection test module, which is used to obtain the current collection results of different characteristics of different current collectors under different environments by using a single dependent variable method when collecting the current of lead-acid batteries, and record the environmental data, current characteristics and collection results of different collection results, print a timestamp on each set of data to form an experimental data set, and select the data under the rated environment of the current collector as the benchmark data;

[0071] In this embodiment, the current collector includes a shunt resistor and a Hall sensor, and the two current collectors are electrically connected via a series switching circuit.

[0072] The specific circuit of the two current collectors through the series switching circuit includes four switching switches S1, S2, S3 and S4, a shunt resistor R1 and a Hall ring H1 of a Hall sensor. The switching switch S1, the shunt resistor R1, the switching switch S1 and the Hall ring H1 are connected in series between the input end IN and the output end OUT. The switching switch S2 is connected in parallel with the switching switch S1 and the shunt resistor R1. The switching switch S4 is connected in parallel with the switching switch S3 and the Hall ring H1. When in use, when the switching switch S1 and the switching switch S1 are closed at the same time, the current is collected through the shunt resistor R1. When the switching switch S2 and the switching switch S3 are closed at the same time, the current is collected through the Hall sensor. When the current collector needs to be switched, the switching switch S2 and the switching switch S2 are closed first, and then the switching switch S1 and the switching switch S4 are disconnected, so as to switch to the Hall ring for detection. The switching switch S2 and the switching switch S4 effectively solve the current interruption problem of the current collector during the switching process.

[0073] Shunt resistors are a simple and low-cost method for current measurement. The basic principle is that when a resistor is placed in a circuit, a voltage drop proportional to the current will be generated when current flows through the resistor. By measuring this voltage drop, the current value can be calculated. A Hall sensor is a device that uses the Hall effect to measure the magnetic field strength in an electromagnetic field, thereby indirectly calculating the current size.

[0074] Combining the advantages of both, the most suitable measurement method can be selected in different application scenarios, such as using Hall sensors in high current applications and using shunt resistors in low current applications that require high accuracy. Under changing working conditions, such as temperature changes or electromagnetic interference, the combined use can ensure the stability and accuracy of current acquisition.

[0075] The different environments include temperature and magnetic field;

[0076] The currents of different characteristics include the magnitude of the current, the direction of the current and the duration of the current.

[0077] The logic of the collection results of currents with different characteristics under different environments through the single dependent variable method is;

[0078] When the current of the lead-acid battery is collected by the current collector, only the duration of the current, the direction of the current, the magnitude of the current, the temperature of the current collector, the magnitude of the magnetic field and the type of the current collector are changed in sequence.

[0079] The single dependent variable method is an experimental design method. The core idea of ​​this method is to change only one independent variable at a time when conducting an experiment, while keeping all other variables unchanged. In this way, researchers can observe the specific impact of the change in the independent variable on the dependent variable.

[0080] When collecting current, obtain the duration range of charge and discharge of the lead-acid battery, the safe current range of safe charge and discharge, the current direction, the safe temperature range of the collector and the magnetic field strength range. When using a shunt resistor, first keep the current size, current direction and current duration of the battery unchanged, and gradually increase the temperature of the shunt resistor. Each increase is a set of data, and the current size, current direction, current duration and temperature of the shunt resistor of the group at this time are recorded. When using a Hall sensor, still keep the current size, current direction and current duration of the battery unchanged, and gradually increase the magnetic field where the Hall ring is located. Each increase is a set of data, and the current size, current direction, current duration and magnetic field of the Hall ring of the group at this time are recorded. Record the current size, current direction, current duration and magnetic field of the Hall ring of the group at this time, and then change the current duration, current direction and current size.

[0081] This method can more directly observe and quantify the effects of temperature, current, electromagnetic interference, etc. on current acquisition results, which helps to clarify which specific conditions will lead to increased acquisition errors. After determining the specific impact of a single environmental variable on the current measurement results, error compensation can be performed more accurately.

[0082] One of the main issues with shunt resistors is the effect of temperature changes on their resistance value. The resistance value changes with temperature, and high temperatures usually increase the resistance value, which can cause measurement errors. The heat generated when a high current passes through the resistor will increase the temperature of the resistor itself (self-heating effect), further affecting its resistance value and causing inaccurate current measurement. The method by which Hall sensors measure current is based on the magnetic field generated around the current. Therefore, the presence of an external magnetic field may interfere with the measurement of the Hall sensor, and extremely large currents may generate a magnetic field strong enough to affect the linear response of the sensor or saturate the sensor.

[0083] The data acquisition module is used to calculate the comprehensive characteristic index of the current of the lead-acid battery by acquiring the historical and real-time current size, current direction, and current duration data of the lead-acid battery, and at the same time collect the environmental parameters of the current collector.

[0084] The comprehensive characteristic index provides a comprehensive view of various parameters of the current. Selecting the current collector that best suits the current battery status, such as a shunt resistor or a Hall effect sensor, based on the comprehensive characteristic index can improve the accuracy and reliability of the measurement.

[0085] In this embodiment, the calculation method logic of the comprehensive characteristic index of the electric quantity is as follows: the average value of the current and the average duration of the current are counted in sequence, and the volatility of the current is calculated. By weighting the average value of the current, the average duration of the current, and the volatility of the current in the comprehensive characteristic index, the specific calculation formula for calculating the comprehensive characteristic index of the current is as follows:

[0086]

[0087] Where, Ipj is the average current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected;

[0088]

[0089] Among them, Itp is the average duration of the current, CI cx is the duration of the current at the historical moment cx, cα is the collection time interval of the historical current duration, and tc is the number of collection times of the historical current duration;

[0090]

[0091] Among them, Ibd is the fluctuation of current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected;

[0092] Q=Ipj*β1+Itp*β2+Ibd*β3

[0093] Among them, Q is the comprehensive characteristic index of current, β1, β2, and β3 are the average value, average duration, and volatility weight of the current, respectively, among which, 0<β1<1, 0<β2<1, 0<β3<1, β1+β2+β3=1.

[0094] A data analysis module, the data analysis module is used to calculate the current error value between each current collector and the selected benchmark data, and form a training data set with the experimental data set, and at the same time select and switch a suitable current collector as the current collector for lead-acid battery current collection according to the comprehensive characteristic index of the current and the type of the current collector;

[0095] In this embodiment, the current error value is calculated as follows:

[0096] ΔI1 γ1,γ2,γ3,γ4,γ5 =I1b-I1 γ1,γ2,γ3,γ4,γ5

[0097] ΔI1 γ1,γ2,γ3,γ4,γ5is the current error when the duration of the current is γ1, the direction of the current is γ2, the magnitude of the current is γ3, the temperature of the current collector is γ4, and the magnitude of the magnetic field is γ5. I1b is the current value of the Hall sensor reference group, and I1 γ1,γ2,γ3,γ4,γ5 The current is a current with a duration of γ1, a direction of γ2, a magnitude of γ3, a temperature of the current collector of γ4, and a magnitude of the magnetic field of γ5.

[0098] The method of selecting a suitable current collector according to the comprehensive characteristic index of the current and the type of the current collector is:

[0099] When Q∈(QH min ,QH max ), select and switch the Hall sensor as the current collector;

[0100] When Q∈(QD min ,QD max ), select and switch the shunt resistor as the current collector;

[0101] When Q∈[(QH min ,QH max )∩(QD min ,QD max )], No switching is performed.

[0102] The error calculation module is used to establish a current acquisition error calculation model, train the error calculation model by using a training data set, and use the collected real-time environmental parameters and current collector type as the input of the model to output the calculated error value of the current collected by the corresponding current collector.

[0103] Multilayer Perceptron is a feedforward artificial neural network consisting of one or more intermediate layers and an output layer. It is a type of deep learning model used to handle a series of complex pattern recognition and prediction problems. It connects nodes in each layer through nonlinear activation functions, and it can learn the complex relationship between input data and output data.

[0104] Current measurement may be affected by many factors, such as temperature changes, current changes, and magnetic field interference. These influences on current acquisition are a complex nonlinear relationship. The multilayer perceptron introduces a nonlinear activation function through the hidden layer, which can effectively capture this nonlinear relationship and provide accurate prediction of current measurement errors.

[0105] In this embodiment, the current acquisition error calculation model is based on a calculation model of a multi-layer perceptron neural network, including an input layer, a hidden layer, and an output layer;

[0106] Input layer;

[0107] X i =[Xr1,…,Xr k ,…,Xr q ]

[0108] Among them, X i is the input data set of the model, Xr k is the kth group of experimental data in the data set, and q is the total number of experimental data groups;

[0109] Hidden layers;

[0110] Z (1) =W (1) *X i +b (1)

[0111] a (1) =f(Z (1) )

[0112] Among them, Z (1) is the intermediate value of the hidden layer linear output, W (1) 、b (1) are the weight matrix and threshold of the hidden layer respectively, and f is the activation function;

[0113] Output layer;

[0114] Z (2) =W (2) *a (1) +b (2)

[0115] Y t+1 =y(Z (2) )

[0116] Among them, Z (2) is the intermediate value of the linear output of the output layer, W (2) 、b (2) are the weight matrix and threshold of the output layer, Y t+1 Risk assessment type, y is the softmax activation function, and the calculated error value of the output current;

[0117] Among them, the activation function is the ReLU activation function, and the specific formula is:

[0118] f(Z (1) )=max(0,Z (1) )

[0119] The specific formula of the Softmax activation function is;

[0120]

[0121] Among them, i is the i-th input value of the Softmax activation function.

[0122] The acquisition output module is used to perform error compensation on the acquisition result of the current collector according to the type of current sensor selected and the error value calculated by the current acquisition error calculation model of the corresponding type, and output accurate measurement results.

[0123] In this embodiment, the calculation formula for performing error compensation on the collection result of the current collector and outputting the accurate measurement result is:

[0124] Ichu=Isi+ΔI

[0125] Among them, Ichu is the output current of the current acquisition system at the current moment, Isi is the current value collected at the current moment, and ΔI is the current error value at the current moment.

[0126] See also Figure 3 The present invention also provides a lead-acid battery current collection method, the current collection method is performed by the above-mentioned current collection system, and the current collection method steps include:

[0127] Step 1: Obtain different current collectors respectively, and collect the currents with different characteristics under different environments by using the single dependent variable method, and record the environmental data, current characteristics and collection results of different collection results, and print a timestamp on each set of data to form an experimental data set;

[0128] Step 2: Select the current data collected by different current sensors under standard working environment parameters as the benchmark data of the current sensor, calculate the current error value between each current collector and the benchmark data, and form a training data set with the experimental data set;

[0129] Step 3: Establish a current acquisition error calculation model, train the error calculation model through a training data set, and use the real-time environmental parameters and current collector type as inputs to the model to output the current calculation error value of the corresponding current collector;

[0130] Step 4: By obtaining historical and real-time current magnitude, current direction, and current duration data, and calculating the comprehensive characteristic index of electric quantity, according to the comprehensive characteristic index of current and the type of current collector, select and switch a suitable current collector to collect current;

[0131] Step 5: According to the type of current sensor selected, the error value calculated by the current acquisition error calculation model of the corresponding type is used to perform error compensation on the acquisition result of the current collector to output accurate measurement results.

[0132] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0133] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A lead-acid battery current acquisition system, characterized in that: include: A detection test module, which is used to obtain the current collection results of different characteristics of different current collectors under different environments by using a single dependent variable method when collecting the current of lead-acid batteries, and record the environmental data, current characteristics and collection results of different collection results, print a timestamp on each set of data to form an experimental data set, and select the data under the rated environment of the current collector as the benchmark data; A data acquisition module, which is used to calculate the comprehensive characteristic index of the current of the lead-acid battery by acquiring the historical and real-time current magnitude, current direction, and current duration data of the lead-acid battery, and to collect environmental parameters of the current collector; A data analysis module, the data analysis module is used to calculate the current error value between each current collector and the selected benchmark data, and form a training data set with the experimental data set, and at the same time select and switch a suitable current collector as the current collector for lead-acid battery current collection according to the comprehensive characteristic index of the current and the type of the current collector; An error calculation module, which is used to establish a current acquisition error calculation model, train the error calculation model by using a training data set, and output the error value of the current collected by the corresponding current collector by using the collected real-time environmental parameters and the current collector type as the input of the model; The acquisition output module is used to perform error compensation on the acquisition result of the current collector according to the type of current sensor selected and the error value calculated by the current acquisition error calculation model of the corresponding type, and output accurate measurement results.

2. A lead-acid battery current acquisition system according to claim 1, characterized in that: The current collector includes a shunt resistor and a Hall sensor, and the two current collectors are electrically connected through a series switching circuit; The different environments include temperature and magnetic field; The currents of different characteristics include the magnitude of the current, the direction of the current and the duration of the current; The logic of the collection results of currents with different characteristics under different environments through the single dependent variable method is; When the current of the lead-acid battery is collected by the current collector, only the duration of the current, the direction of the current, the magnitude of the current, the temperature of the current collector, the magnitude of the magnetic field and the type of the current collector are changed in sequence.

3. A lead-acid battery current acquisition system according to claim 1, characterized in that: The calculation method logic of the electric quantity comprehensive characteristic index is: the average value of the current and the average duration of the current are counted in sequence, and the volatility of the current is calculated. The specific calculation formula for calculating the comprehensive characteristic index of the current is calculated by weighting the average value of the current, the average duration of the current, and the volatility of the current in the comprehensive characteristic index; Where, Ipj is the average current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected; Among them, Itp is the average duration of the current, CI cx is the duration of the current at the historical moment cx, cα is the collection time interval of the historical current duration, and tc is the number of collection times of the historical current duration; Among them, Ibd is the fluctuation of current, I Ict is the current at the historical moment Ict, tα is the time interval for historical current collection, and tn is the number of times the historical current is collected; Q=Ipj*β1+Itp*β2+Ibd*β3 Among them, Q is the comprehensive characteristic index of current, β1, β2, and β3 are the average value, average duration, and volatility weight of the current, respectively, among which, 0<β1<1, 0<β2<1, 0<β3<1, β1+β2+β3=1.

4. A lead-acid battery current acquisition system according to claim 3, characterized in that: The method of selecting a suitable current collector according to the comprehensive characteristic index of the current and the type of the current collector is: When Q∈(QH min ,QH max ), select and switch the Hall sensor as the current collector; When Q∈(QD min ,QD max ), select and switch the shunt resistor as the current collector; When Q∈[(QH min ,QH max )∩(QD min ,QD max )], No switching is performed.

5. A lead-acid battery current acquisition system according to claim 1, characterized in that: The calculation method of the error value of the current is: ΔI1 γ1,γ2,γ3,γ4,γ5 =I1b―I1 γ1,γ2,γ3,γ4,γ5 ΔI1 γ1,γ2,γ3,γ4,γ5 is the current error when the duration of the current is γ1, the direction of the current is γ2, the magnitude of the current is γ3, the temperature of the current collector is γ4, and the magnitude of the magnetic field is γ5. I1b is the current value of the Hall sensor reference group, and I1 γ1,γ2,γ3,γ4,γ5 The current is a current with a duration of γ1, a direction of γ2, a magnitude of γ3, a temperature of the current collector of γ4, and a magnitude of the magnetic field of γ5.

6. A lead-acid battery current acquisition system according to claim 1, characterized in that: The current acquisition error calculation model is based on a calculation model of a multi-layer perceptron neural network, including an input layer, a hidden layer, and an output layer; Input layer; X i =[Xr1,…,Xr k ,…,Xr q ] Among them, X i is the input data set of the model, Xr k is the kth group of experimental data in the data set, and q is the total number of experimental data groups; Hidden layers; Z (1) =W (1) *X i +b (1) a (1) =f(Z (1) ) Among them, Z (1) is the intermediate value of the hidden layer linear output, W (1) , b (1) are the weight matrix and threshold of the hidden layer respectively, and f is the activation function; Output layer; Z (2) =W (2) *a (1) +b (2) AND t+1 =y(Z (2) ) Among them, Z (2) is the intermediate value of the linear output of the output layer, W (2) , b (2) are the weight matrix and threshold of the output layer, Y t+1 Risk assessment type, y is the softmax activation function, output current error value; Among them, the activation function is the ReLU activation function, and the specific formula is: f(Z (1) )=max(0,Z (1) ) The specific formula of the Softmax activation function is; Among them, i is the i-th input value of the Softmax activation function.

7. A lead-acid battery current acquisition system according to claim 1, characterized in that: The calculation formula for performing error compensation on the collection result of the current collector and outputting accurate measurement results is: Ichu=Isi+ΔI Among them, Ichu is the output current of the current acquisition system at the current moment, Isi is the current value collected at the current moment, and ΔI is the error value of the current at the current moment.

8. A lead-acid battery current collection method, characterized in that: The current acquisition method is performed by the current acquisition system according to any one of claims 1 to 7, and the current acquisition method steps include: Step 1: Obtain different current collectors respectively, and collect the currents with different characteristics under different environments by using the single dependent variable method, and record the environmental data, current characteristics and collection results of different collection results, and print a timestamp on each set of data to form an experimental data set; Step 2: Select the current data collected by different current sensors under standard working environment parameters as the benchmark data of the current sensor, calculate the error value of the current between each current collector and the benchmark data, and form a training data set with the experimental data set; Step 3: Establish a current acquisition error calculation model, train the error calculation model through a training data set, and use the real-time environmental parameters and current collector type as inputs of the model to output the current error value of the corresponding current collector; Step 4: By obtaining historical and real-time current magnitude, current direction, and current duration data, and calculating the comprehensive characteristic index of electric quantity, according to the comprehensive characteristic index of current and the type of current collector, select and switch a suitable current collector to collect current; Step 5: According to the type of current sensor selected and the error value calculated by the current acquisition error calculation model of the corresponding type, the error compensation is performed on the acquisition result of the current collector to output the accurate measurement result.

Images