CN117130419A - LSTM-based MOS tube differential pressure intelligent regulation method and system - Google Patents
LSTM-based MOS tube differential pressure intelligent regulation method and system Download PDFInfo
- Publication number
- CN117130419A CN117130419A CN202311106357.3A CN202311106357A CN117130419A CN 117130419 A CN117130419 A CN 117130419A CN 202311106357 A CN202311106357 A CN 202311106357A CN 117130419 A CN117130419 A CN 117130419A
- Authority
- CN
- China
- Prior art keywords
- mos tube
- voltage
- mcu
- value
- differential pressure
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 210000004027 cell Anatomy 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 abstract description 8
- 229910001416 lithium ion Inorganic materials 0.000 abstract description 8
- 230000015572 biosynthetic process Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 7
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 229910052744 lithium Inorganic materials 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000013543 active substance Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 229910003002 lithium salt Inorganic materials 0.000 description 1
- 159000000002 lithium salts Chemical class 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002161 passivation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007086 side reaction Methods 0.000 description 1
- 239000007784 solid electrolyte Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/0069—Charging or discharging for charge maintenance, battery initiation or rejuvenation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05F—SYSTEMS FOR REGULATING ELECTRIC OR MAGNETIC VARIABLES
- G05F1/00—Automatic systems in which deviations of an electric quantity from one or more predetermined values are detected at the output of the system and fed back to a device within the system to restore the detected quantity to its predetermined value or values, i.e. retroactive systems
- G05F1/10—Regulating voltage or current
- G05F1/46—Regulating voltage or current wherein the variable actually regulated by the final control device is dc
- G05F1/56—Regulating voltage or current wherein the variable actually regulated by the final control device is dc using semiconductor devices in series with the load as final control devices
- G05F1/561—Voltage to current converters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/05—Accumulators with non-aqueous electrolyte
- H01M10/052—Li-accumulators
- H01M10/0525—Rocking-chair batteries, i.e. batteries with lithium insertion or intercalation in both electrodes; Lithium-ion batteries
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/05—Accumulators with non-aqueous electrolyte
- H01M10/058—Construction or manufacture
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/44—Methods for charging or discharging
- H01M10/446—Initial charging measures
Abstract
The application discloses an intelligent MOS tube pressure difference adjusting method and system based on LSTM, wherein the method comprises the following steps: providing a data acquisition technology for MOS tube differential pressure regulation, and acquiring basic data for MOS tube differential pressure regulation; constructing a MOS tube circuit signal difference model, and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data; establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, and giving a setting value of the voltage at the rear end of the MCU and a setting value of the voltage output by the front end power supply; and constructing an intelligent MOS tube pressure drop setting model, setting the MOS tube pressure drop, and finishing the adjustment of the MOS tube pressure difference. By the method and the system, the interference of uncertain factors can be avoided, the calculation accuracy of the MOS voltage setting value is improved, the differential pressure adjusting effect of the MOS tube is further improved, the running power consumption of the MOS tube is reduced, and the formation quality of the lithium ion battery is improved.
Description
Technical Field
The application relates to the technical field of batteries, in particular to an intelligent MOS tube pressure difference adjusting method and system based on LSTM.
Background
The formation of the lithium battery is the first charging process of the battery after the liquid injection of the lithium battery, and the process can activate active substances in the battery to activate the lithium battery. The formation is generally accomplished by charging the fabricated lithium ion battery with an initial low current, causing side reactions between the lithium salt and the electrolyte, and forming a passivation layer, i.e., a solid electrolyte interface film, on the negative side surface.
However, when the front-end power supply charges the lithium ion battery, the voltage of the lithium ion battery gradually increases, the front-end power supply cannot adapt to the increase of the voltage of the lithium ion battery, and after receiving a feedback signal of the increase of the voltage of the lithium ion battery, the voltage drop of the MOS of the front-end power supply is reduced, which can lead to the voltage reduction of the MOS tube, and meanwhile, the load capacity of the front-end power supply is weakened, so that the output power consumption and the generated heat are increased.
The existing method generally produces a setting value through resistor voltage division to adjust MOS voltage, but the existing method is easily affected by uncertainty such as electromagnetic interference, voltage fluctuation and the like when adjusting MOS tube voltage difference, and the accuracy of the given voltage setting value is not high, so that the setting result is not ideal.
Disclosure of Invention
Aiming at the problem that the accuracy of a voltage setting value is not high in the conventional MOS tube differential pressure regulation, the application provides an LSTM-based MOS tube differential pressure intelligent regulation method and system, which utilize an LSTM intelligent algorithm to avoid the interference of uncertainty factors, give a more accurate voltage setting value and further improve the effect of MOS tube differential pressure regulation.
In order to achieve the above object, the present application is realized by the following technical scheme:
an LSTM-based MOS tube differential pressure intelligent regulation method is characterized by comprising the following steps:
providing a data acquisition technology for MOS tube differential pressure regulation, and acquiring basic data for MOS tube differential pressure regulation, wherein the basic data for MOS tube differential pressure regulation comprises MCU operation data and front-end power supply operation data;
constructing a MOS tube circuit signal difference model, and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data;
establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, and according to the basic data for MOS tube voltage drop regulation, the circuit voltage difference signal and the circuit current difference signal, training the MOS tube voltage drop intelligent regulation correlation model by means of LSTM to give a MCU rear end voltage setting value and a front end power supply output voltage setting value;
and constructing an intelligent MOS tube voltage drop setting model, setting the MOS tube voltage drop based on the MCU rear end voltage setting value and the front end power supply output voltage setting value, and finishing the adjustment of the MOS tube voltage difference.
As a preferable scheme of the application, the MCU operation data comprises a MCU back-end voltage value, a protection voltage difference control value and a current standard value which are set by the MCU, and the front-end power supply operation data comprises a front-end power supply output voltage value and a front-end power supply output current value.
As a preferable scheme of the application, the expression of the basic data for MOS tube differential pressure regulation is as follows:
X(t)=[V h (t),V hs (t),I hs (t),I d (t),V d (t)];
wherein X (t) is basic data for MOS tube differential pressure adjustment acquired at time t; v (V) h (t) is the voltage value, V, of the rear end of the MCU acquired at the moment t hs (t) a protection differential pressure control value set for the MCU at the moment t, I hs (t) a current standard value set for the MCU at the moment t; i d (t) is the front end power supply output current value at time t, V d And (t) is the front-end power supply output voltage value at the moment t.
As a preferable scheme of the application, the MOS tube circuit signal difference model comprises a circuit voltage signal difference model and a circuit current signal difference model;
the circuit voltage signal difference model is used for calculating a circuit voltage difference signal, and the expression is as follows:
V C (t)=V de (t)-V hs (t);
V de (t)=V d (t)-V h (t);
wherein V is C (t) a circuit voltage difference signal representing time t; v (V) de (t) is the voltage difference value of the front end of the MOS tube at the moment t, V hs (t) the protection differential pressure control value, V, set for the MCU at the moment t d (t) is the front end power supply output voltage value at time t, V h (t) is the voltage value of the rear end of the MCU acquired at the moment t;
the circuit current signal difference model is used for calculating a circuit current difference signal, and the expression is as follows:
I C (t)=I d (t)-I hs (t);
wherein I is C (t) a circuit current difference signal representing time t; i d (t) is the front-end power supply output current value at time t, I hs And (t) a current standard value set by the MCU at the moment t.
As a preferable scheme of the application, the establishment of the LSTM-based MOS tube voltage drop intelligent regulation correlation model specifically comprises the following steps:
taking a circuit voltage difference signal and a circuit current difference signal which are given by a circuit voltage signal difference model and a circuit current signal difference model as input samples, wherein the expression is as follows:
Y(t)=[V C (t),I C (t)];
wherein Y (t) is an input sample at time t, V C (t) a circuit voltage difference signal representing the time t, I C (t) a circuit current difference signal representing time t;
and inputting a voltage value at the rear end of the MCU and a current value output by a front end power supply into the hidden layer, training an intelligent regulation correlation model of the voltage drop of the MOS tube by means of LSTM, wherein the training process is as follows:
wherein sigma is an activation function; f (f) t For forgetting the output of the gate, W f 、b f A corresponding forgetting gate matrix; i.e t For outputting the input gate, W i 、b i Inputting a gate weight matrix for the corresponding input; c (C) t-1 Is the information on the state of the old cells,to choose to add candidate state information, C t For updated cell information, W C 、b C Is a corresponding neuron matrix; o (o) t To output the gate output, W o 、b o For a corresponding output gate matrix; h is a t To output a result;
finally output MOS tube voltage drop intelligent regulation correlation model F based on LSTM C (t) the expression:
h t =F C (t)=f(V C (t),I C (t))=[V hδ (t),V dδ (t)];
where f () denotes when V is input C (t),I C When (t), corresponding setting values of the voltage at the rear end of the MCU and the setting values of the voltage output by the power supply at the front end are given; v (V) hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t, V dδ And (t) is the front-end power supply output voltage setting value at the moment t.
As a preferable scheme of the application, the MOS tube voltage drop intelligent setting model specifically comprises the following steps:
the first step: the MCU adjusts the voltage value of the rear end of the MCU based on the voltage setting value of the rear end of the MCU and transmits the voltage value to the MOS tube differential pressure detection circuit, and the formula is as follows:
V h-a (t)=V hδ (t);
wherein V is h-a (t) is the voltage value of the rear end of the MCU after the adjustment of the moment t, V hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t;
and a second step of: the power supply driving chip adjusts the output voltage value of the front-end power supply according to the setting value of the output voltage of the front-end power supply, and the formula is as follows:
V d-a (t)=V dδ (t);
wherein V is d-a (t) is time tThe adjusted front-end power supply outputs voltage value V dδ (t) is the front-end power supply output voltage setting value at the moment t;
through the two steps, the differential pressure of the MOS tube is adjusted.
An LSTM-based MOS tube differential pressure intelligent regulation system for realizing the LSTM-based MOS tube differential pressure intelligent regulation method, the system comprises:
the data acquisition module is used for acquiring basic data for MOS tube differential pressure adjustment, wherein the basic data for MOS tube differential pressure adjustment comprises MCU operation data and front-end power supply operation data;
the difference signal module is used for constructing a MOS tube circuit signal difference model and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data;
the LSTM training module is used for establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, training the MOS tube voltage drop intelligent regulation correlation model by means of LSTM, and giving a rear-end voltage setting value and a front-end power supply output voltage setting value of the MCU;
and the MOS tube pressure difference adjusting module is used for constructing an intelligent MOS tube pressure difference adjusting model, adjusting the MOS tube pressure difference based on the MCU rear end voltage adjusting value and the front end power supply output voltage adjusting value, and completing the adjustment of the MOS tube pressure difference.
A computer device, comprising:
one or more processors;
a storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement an LSTM-based MOS tube differential pressure intelligent regulation method as described above.
A computer readable storage medium, on which a computer program is stored, which when processed and executed implements an LSTM-based method for intelligent regulation of MOS transistor differential pressure as described above.
Compared with the prior art, the application has the beneficial effects that: aiming at MOS, the intelligent adjusting method and system for the differential pressure of the MOS tube based on LSTM are provided, interference of uncertain factors is avoided, calculation accuracy of the setting value of MOS voltage is improved, further the differential pressure adjusting effect of the MOS tube is improved, running power consumption of the MOS tube is reduced, and formation quality of a lithium ion battery is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a flow chart of the method of the present application;
FIG. 2 is a schematic diagram of training an LSTM-based MOS tube voltage drop intelligent regulation correlation model according to the present application;
FIG. 3 is a schematic diagram of the intelligent differential pressure regulation of the LSTM-based MOS tube of the present application;
fig. 4 is a modular block diagram of the system of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present application. It will be apparent that the described embodiments are some, but not all, embodiments of the application. All other embodiments, which are obtained by a person skilled in the art based on the described embodiments of the application, fall within the scope of protection of the application.
1-3, an embodiment of the present application provides an LSTM-based MOS tube differential pressure intelligent adjustment method, which specifically includes the following steps:
s1: the MOS tube differential pressure regulating data acquisition technology is provided, basic data for MOS tube differential pressure regulation are acquired, and the basic data for MOS tube differential pressure regulation mainly comprise MCU operation data and front-end power supply operation data.
In a specific embodiment, the MCU operation data may include a MCU back-end voltage value, a protection voltage difference control value set by the MCU, a current standard value, and the like, and the front-end power operation data may include a front-end power output voltage value, a front-end power output current value, and the like.
In a preferred embodiment, the expression of the basic data for differential pressure adjustment of the MOS transistor is:
X(t)=[V h (t),V hs (t),I hs (t),I d (t),V d (t)];
wherein X (t) is basic data for MOS tube differential pressure adjustment acquired at time t; v (V) h (t) is the voltage value, V, of the rear end of the MCU acquired at the moment t hs (t) a protection differential pressure control value set for the MCU at the moment t, I hs (t) a current standard value set for the MCU at the moment t; i d (t) is the front end power supply output current value at time t, V d And (t) is the front-end power supply output voltage value at the moment t.
S2: constructing a MOS tube circuit signal difference model, and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data; the MOS tube circuit signal difference model is the basis of the intelligent regulation correlation model of the MOS tube voltage drop in the next step.
In one embodiment, the MOS transistor circuit signal difference model comprises a circuit voltage signal difference model and a circuit current signal difference model;
the circuit voltage signal difference model is used for calculating a circuit voltage difference signal, and the expression is as follows:
V C (t)=V de (t)-V hs (t);
V de (t)=V d (t)-V h (t);
wherein V is C (t) a circuit voltage difference signal representing time t; v (V) de (t) is the voltage difference value of the front end of the MOS tube at the moment t, V hs (t) the protection differential pressure control value, V, set for the MCU at the moment t d (t) is the front end power supply output voltage value at time t, V h (t) is the voltage value of the rear end of the MCU acquired at the moment t;
the circuit current signal difference model is used for calculating a circuit current difference signal, and the expression is as follows:
I C (t)=I d (t)-I hs (t);
wherein I is C (t) a circuit current difference signal representing time t; i d (t) is the front-end power supply output current value at time t, I hs And (t) a current standard value set by the MCU at the moment t.
S3: and establishing an LSTM-based intelligent regulation correlation model of the MOS tube voltage drop, and according to the basic data for MOS tube voltage drop regulation, the circuit voltage difference signal and the circuit current difference signal, training the intelligent regulation correlation model of the MOS tube voltage drop by means of the LSTM to give a rear-end voltage setting value and a front-end power supply output voltage setting value of the MCU.
Aiming at the problem that the accuracy of the voltage value is not high due to the influence of uncertainty such as electromagnetic interference, voltage fluctuation and the like when the traditional resistance voltage division method is used for calculating the setting value of the voltage at the rear end of the MCU and the setting value of the output voltage of the front-end power supply, the application can avoid the interference of uncertainty factors by utilizing an LSTM intelligent algorithm and provide a more accurate setting value of the voltage.
In one embodiment, step S3 specifically includes:
taking a circuit voltage difference signal and a circuit current difference signal which are given by a circuit voltage signal difference model and a circuit current signal difference model as input samples, wherein the expression is as follows:
Y(t)=[V C (t),I C (t)];
wherein Y (t) is an input sample at time t, V C (t) a circuit voltage difference signal representing the time t, I C (t) a circuit current difference signal representing time t;
and inputting a voltage value at the rear end of the MCU and a current value output by a front end power supply into the hidden layer, training an intelligent regulation correlation model of the voltage drop of the MOS tube by means of LSTM, wherein the training process is as follows:
wherein sigma is an activation function; f (f) t For forgetting the output of the gate, W f 、b f A corresponding forgetting gate matrix; i.e t For outputting the input gate, W i 、b i Inputting a gate weight matrix for the corresponding input; c (C) t-1 Is the information on the state of the old cells,to choose to add candidate state information, C t For updated cell information, W C 、b C Is a corresponding neuron matrix; o (o) t To output the gate output, W o 、b o For a corresponding output gate matrix; h is a t To output a result;
finally output MOS tube voltage drop intelligent regulation correlation model F based on LSTM C (t) the expression:
h t =F C (t)=f(V C (t),I C (t))=[V hδ (t),V dδ (t)];
where f () denotes when V is input C (t),I C When (t), corresponding setting values of the voltage at the rear end of the MCU and the setting values of the voltage output by the power supply at the front end are given; v (V) hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t, V dδ And (t) is the front-end power supply output voltage setting value at the moment t.
S4: and constructing an intelligent MOS tube voltage drop setting model, setting the MOS tube voltage drop based on the MCU rear-end voltage setting value and the front-end power supply output voltage setting value, and completing the adjustment of the MOS tube voltage difference.
In one embodiment, step S4 specifically includes:
the first step: the MCU adjusts the voltage value of the rear end of the MCU based on the voltage setting value of the rear end of the MCU and transmits the voltage value to the MOS tube differential pressure detection circuit, and the formula is as follows:
V h-a (t)=V hδ (t);
wherein V is h-a (t) is the voltage value of the rear end of the MCU after the adjustment of the moment t, V hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t;
and a second step of: the power supply driving chip adjusts the output voltage value of the front-end power supply according to the setting value of the output voltage of the front-end power supply, and the formula is as follows:
V d-a (t)=V dδ (t);
wherein V is d-a (t) is the output voltage value of the front-end power supply after the adjustment of the moment t, V dδ (t) is the front-end power supply output voltage setting value at the moment t;
through the two steps, the differential pressure of the MOS tube is adjusted.
As shown in fig. 4, in another embodiment of the present application, an LSTM-based MOS tube differential pressure intelligent regulation system is provided, to implement an LSTM-based MOS tube differential pressure intelligent regulation method as described above, where the system includes:
the data acquisition module is used for acquiring basic data for MOS tube differential pressure adjustment, wherein the basic data for MOS tube differential pressure adjustment comprises MCU operation data and front-end power supply operation data;
the difference signal module is used for constructing a MOS tube circuit signal difference model and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data;
the LSTM training module is used for establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, training the MOS tube voltage drop intelligent regulation correlation model by means of the LSTM, and giving out an MCU rear-end voltage setting value and a front-end power supply output voltage setting value;
and the MOS tube pressure difference adjusting module is used for constructing an intelligent MOS tube pressure difference adjusting model, adjusting the MOS tube pressure difference based on the MCU rear end voltage setting value and the front end power supply output voltage setting value, and completing the adjustment of the MOS tube pressure difference.
The present application also provides a computer device comprising:
one or more processors;
a storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement an LSTM-based MOS transistor differential pressure intelligent regulation method as described above.
The application also provides a computer readable storage medium, on which a computer program is stored, which when processed and executed, realizes the intelligent regulation method of the MOS tube differential pressure based on the LSTM.
In summary, the application provides an intelligent MOS tube differential pressure regulating method and system based on LSTM, which avoid the interference of uncertain factors, improve the calculation accuracy of the MOS voltage setting value, further improve the MOS tube differential pressure regulating effect, reduce the running power consumption of the MOS tube and improve the formation quality of the lithium ion battery.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, may be embodied in whole or in part in the form of a computer program product comprising one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. Computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method description in a flowchart or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process. And the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a substantially simultaneous manner or in an opposite order from that shown or discussed, including in accordance with the functions that are involved.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the methods of the embodiments described above may be performed by a program that, when executed, comprises one or a combination of the steps of the method embodiments, instructs the associated hardware to perform the method.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules described above, if implemented in the form of software functional modules and sold or used as a stand-alone product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that various changes and substitutions are possible within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (9)
1. An LSTM-based MOS tube differential pressure intelligent regulation method is characterized by comprising the following steps:
providing a data acquisition technology for MOS tube differential pressure regulation, and acquiring basic data for MOS tube differential pressure regulation, wherein the basic data for MOS tube differential pressure regulation comprises MCU operation data and front-end power supply operation data;
constructing a MOS tube circuit signal difference model, and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data;
establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, and according to the basic data for MOS tube voltage drop regulation, the circuit voltage difference signal and the circuit current difference signal, training the MOS tube voltage drop intelligent regulation correlation model by means of LSTM to give a MCU rear end voltage setting value and a front end power supply output voltage setting value;
and constructing an intelligent MOS tube voltage drop setting model, setting the MOS tube voltage drop based on the MCU rear end voltage setting value and the front end power supply output voltage setting value, and finishing the adjustment of the MOS tube voltage difference.
2. The intelligent regulation method of the MOS tube differential pressure based on the LSTM according to claim 1, wherein the MCU operation data comprises a MCU back-end voltage value, a protection differential pressure control value set by the MCU and a current standard value, and the front-end power supply operation data comprises a front-end power supply output voltage value and a front-end power supply output current value.
3. The intelligent regulation method of the differential pressure of the MOS tube based on the LSTM according to claim 1, wherein the expression of the basic data for regulating the differential pressure of the MOS tube is as follows:
X(t)=[V h (t),V hs (t),I hs (t),I d (t),V d (t)];
wherein X (t) is basic data for MOS tube differential pressure adjustment acquired at time t; v (V) h (t) is the voltage value, V, of the rear end of the MCU acquired at the moment t hs (t) a protection differential pressure control value set for the MCU at the moment t, I hs (t) a current standard value set for the MCU at the moment t; i d (t) is the front end power supply output current value at time t, V d And (t) is the front-end power supply output voltage value at the moment t.
4. The intelligent regulation method of the MOS tube differential pressure based on the LSTM according to claim 1, wherein the MOS tube circuit signal differential value model comprises a circuit voltage signal differential value model and a circuit current signal differential value model;
the circuit voltage signal difference model is used for calculating a circuit voltage difference signal, and the expression is as follows:
V C (t)=V de (t)-V hs (t);
V de (t)=V d (t)-V h (t);
wherein V is C (t) a circuit voltage difference signal representing time t; v (V) de (t) is the voltage difference value of the front end of the MOS tube at the moment t, V hs (t) the protection differential pressure control value, V, set for the MCU at the moment t d (t) is the front end power supply output voltage value at time t, V h (t) is the voltage value of the rear end of the MCU acquired at the moment t;
the circuit current signal difference model is used for calculating a circuit current difference signal, and the expression is as follows:
I C (t)=I d (t)-I hs (t);
wherein I is C (t) a circuit current difference signal representing time t; i d (t) is the front-end power supply output current value at time t, I hs And (t) a current standard value set by the MCU at the moment t.
5. The method for intelligently adjusting the pressure drop of the MOS tube based on the LSTM according to claim 2, wherein the establishing of the intelligent adjusting and correlating model of the pressure drop of the MOS tube based on the LSTM specifically comprises the following steps:
taking a circuit voltage difference signal and a circuit current difference signal which are given by a circuit voltage signal difference model and a circuit current signal difference model as input samples, wherein the expression is as follows:
Y(t)=[V C (t),I C (t)];
wherein Y (t) is an input sample at time t, V C (t) a circuit voltage difference signal representing the time t, I C (t) a circuit current difference signal representing time t;
and inputting a voltage value at the rear end of the MCU and a current value output by a front end power supply into the hidden layer, training an intelligent regulation correlation model of the voltage drop of the MOS tube by means of LSTM, wherein the training process is as follows:
wherein sigma is an activation function; f (f) t For forgetting the output of the gate, W f 、b f A corresponding forgetting gate matrix; i.e t For outputting the input gate, W i 、b i Inputting a gate weight matrix for the corresponding input; c (C) t-1 Is the information on the state of the old cells,to choose to add candidate state information, C t For updated cell information, W C 、b C Is a corresponding neuron matrix; o (o) t To output the gate output, W o 、b o For a corresponding output gate matrix; h is a t To output a result;
MOS tube voltage drop intelligent regulation correlation model based on LSTM (least squares) is finally outputF C (t) the expression:
h t =F C (t)=f(V C (t),I C (t))=[V hδ (t),V dδ (t)];
where f () denotes when V is input C (t),I C When (t), corresponding setting values of the voltage at the rear end of the MCU and the setting values of the voltage output by the power supply at the front end are given; v (V) hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t, V dδ And (t) is the front-end power supply output voltage setting value at the moment t.
6. The intelligent regulation method of the pressure difference of the MOS tube based on the LSTM according to claim 5, wherein the intelligent regulation model of the pressure drop of the MOS tube specifically comprises:
the first step: the MCU adjusts the voltage value of the rear end of the MCU based on the voltage setting value of the rear end of the MCU and transmits the voltage value to the MOS tube differential pressure detection circuit, and the formula is as follows:
V h-a (t)=V hδ (t);
wherein V is h-a (t) is the voltage value of the rear end of the MCU after the adjustment of the moment t, V hδ (t) is the setting value of the voltage at the rear end of the MCU at the moment t;
and a second step of: the power supply driving chip adjusts the output voltage value of the front-end power supply according to the setting value of the output voltage of the front-end power supply, and the formula is as follows:
V d-a (t)=V dδ (t);
wherein V is d-a (t) is the output voltage value of the front-end power supply after the adjustment of the moment t, V dδ (t) is the front-end power supply output voltage setting value at the moment t;
through the two steps, the differential pressure of the MOS tube is adjusted.
7. The system for adjusting the differential pressure intelligent adjusting method of the MOS transistor based on the LSTM according to any one of claims 1 to 6, wherein the system comprises:
the data acquisition module is used for acquiring basic data for MOS tube differential pressure adjustment, wherein the basic data for MOS tube differential pressure adjustment comprises MCU operation data and front-end power supply operation data;
the difference signal module is used for constructing a MOS tube circuit signal difference model and calculating circuit voltage difference signals and circuit current difference signals under different MOS tube differential pressure adjustment basic data;
the LSTM training module is used for establishing an LSTM-based MOS tube voltage drop intelligent regulation correlation model, training the MOS tube voltage drop intelligent regulation correlation model by means of LSTM, and giving a rear-end voltage setting value and a front-end power supply output voltage setting value of the MCU;
and the MOS tube pressure difference adjusting module is used for constructing an intelligent MOS tube pressure difference adjusting model, adjusting the MOS tube pressure difference based on the MCU rear end voltage adjusting value and the front end power supply output voltage adjusting value, and completing the adjustment of the MOS tube pressure difference.
8. A computer device, comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement an LSTM based MOS transistor differential pressure intelligent regulation method as recited in any one of claims 1-6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being processed and executed, implements an LSTM based MOS tube differential pressure intelligent regulation method as claimed in any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311106357.3A CN117130419B (en) | 2023-08-30 | 2023-08-30 | LSTM-based MOS tube differential pressure intelligent regulation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311106357.3A CN117130419B (en) | 2023-08-30 | 2023-08-30 | LSTM-based MOS tube differential pressure intelligent regulation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117130419A true CN117130419A (en) | 2023-11-28 |
CN117130419B CN117130419B (en) | 2024-03-12 |
Family
ID=88850496
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311106357.3A Active CN117130419B (en) | 2023-08-30 | 2023-08-30 | LSTM-based MOS tube differential pressure intelligent regulation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117130419B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107839500A (en) * | 2017-07-11 | 2018-03-27 | 苏州大学 | A kind of dynamic corrections SOC lithium battery group balance control method and system |
CN110661403A (en) * | 2019-09-27 | 2020-01-07 | 福建星云电子股份有限公司 | Circuit for controlling parallel MOS (metal oxide semiconductor) tubes to be balanced |
WO2020087373A1 (en) * | 2018-10-31 | 2020-05-07 | 华为技术有限公司 | Compensation method and apparatus for battery voltage, and terminal device |
WO2020204584A1 (en) * | 2019-04-05 | 2020-10-08 | 주식회사 엘지화학 | Battery management device and method |
CN113014235A (en) * | 2021-02-22 | 2021-06-22 | 福建星云电子股份有限公司 | Automatic MOS tube pressure difference adjusting device and method |
CN214591356U (en) * | 2021-02-22 | 2021-11-02 | 福建星云电子股份有限公司 | MOS pipe pressure difference automatic regulating apparatus |
CN114189024A (en) * | 2021-12-20 | 2022-03-15 | 浙江特康电子科技有限公司 | Method and device for realizing constant current mode, switching power supply and medium |
CN114400898A (en) * | 2022-03-08 | 2022-04-26 | 广州菲利斯太阳能科技有限公司 | Inverter circuit power regulation method and system based on BUCK-BOOST |
CN116245373A (en) * | 2022-12-06 | 2023-06-09 | 云南电网有限责任公司信息中心 | Power data quality rule self-adaption method based on deep learning |
CN116365843A (en) * | 2023-04-26 | 2023-06-30 | 普敏半导体(苏州)有限公司 | Automatic regulating circuit for lifting voltage |
CN116526617A (en) * | 2023-04-26 | 2023-08-01 | 广芯微电子(广州)股份有限公司 | Lithium battery charging control method and device based on reinforcement learning |
-
2023
- 2023-08-30 CN CN202311106357.3A patent/CN117130419B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107839500A (en) * | 2017-07-11 | 2018-03-27 | 苏州大学 | A kind of dynamic corrections SOC lithium battery group balance control method and system |
WO2020087373A1 (en) * | 2018-10-31 | 2020-05-07 | 华为技术有限公司 | Compensation method and apparatus for battery voltage, and terminal device |
WO2020204584A1 (en) * | 2019-04-05 | 2020-10-08 | 주식회사 엘지화학 | Battery management device and method |
CN110661403A (en) * | 2019-09-27 | 2020-01-07 | 福建星云电子股份有限公司 | Circuit for controlling parallel MOS (metal oxide semiconductor) tubes to be balanced |
CN113014235A (en) * | 2021-02-22 | 2021-06-22 | 福建星云电子股份有限公司 | Automatic MOS tube pressure difference adjusting device and method |
CN214591356U (en) * | 2021-02-22 | 2021-11-02 | 福建星云电子股份有限公司 | MOS pipe pressure difference automatic regulating apparatus |
CN114189024A (en) * | 2021-12-20 | 2022-03-15 | 浙江特康电子科技有限公司 | Method and device for realizing constant current mode, switching power supply and medium |
CN114400898A (en) * | 2022-03-08 | 2022-04-26 | 广州菲利斯太阳能科技有限公司 | Inverter circuit power regulation method and system based on BUCK-BOOST |
CN116245373A (en) * | 2022-12-06 | 2023-06-09 | 云南电网有限责任公司信息中心 | Power data quality rule self-adaption method based on deep learning |
CN116365843A (en) * | 2023-04-26 | 2023-06-30 | 普敏半导体(苏州)有限公司 | Automatic regulating circuit for lifting voltage |
CN116526617A (en) * | 2023-04-26 | 2023-08-01 | 广芯微电子(广州)股份有限公司 | Lithium battery charging control method and device based on reinforcement learning |
Non-Patent Citations (1)
Title |
---|
明彤彤;王凯;田冬冬;徐松;田浩含;: "基于LSTM神经网络的锂离子电池荷电状态估算", 广东电力, no. 03 * |
Also Published As
Publication number | Publication date |
---|---|
CN117130419B (en) | 2024-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Song et al. | Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries | |
Chen et al. | SOC estimation for lithium-ion battery using the LSTM-RNN with extended input and constrained output | |
Chen et al. | Synthetic state of charge estimation for lithium-ion batteries based on long short-term memory network modeling and adaptive H-Infinity filter | |
CN111007399B (en) | Lithium battery state of charge prediction method based on improved generation countermeasure network | |
Xu et al. | Improving the state of charge estimation of reused lithium-ion batteries by abating hysteresis using machine learning technique | |
JP4075925B2 (en) | Internal state detection system for lead-acid batteries for vehicles | |
CN113511082B (en) | Hybrid electric vehicle energy management method based on rule and double-depth Q network | |
CN110398697B (en) | Lithium ion health state estimation method based on charging process | |
US8207706B2 (en) | Method of estimating battery state of charge | |
CN113022374B (en) | Passive equalization control method and system for battery management system of electric vehicle | |
CN112035777B (en) | Battery charging remaining time calculation method and device and vehicle | |
Chen et al. | State of charge estimation for lithium-ion batteries using gated recurrent unit recurrent neural network and adaptive Kalman filter | |
JP2008232758A (en) | Detection device for internal state of secondary cell and neural network type estimation device for quantity of state | |
CN112163372B (en) | SOC estimation method of power battery | |
US11796597B2 (en) | Method for estimating state of charge (SOC) of lithium-ion battery system based on artificial intelligence (AI) | |
CN115308616A (en) | OCV-SOC calibration and estimation method, device, medium and vehicle | |
CN112858929A (en) | Battery SOC estimation method based on fuzzy logic and extended Kalman filtering | |
US11675017B2 (en) | Method and apparatus for device-specific determination of an internal-resistance based state of health of a battery | |
CN110376535A (en) | A kind of determination method and device of dump energy | |
CN115639481A (en) | Battery data preprocessing system and method based on big data prediction SOC | |
Li et al. | State of Health and Charge Estimation Based on Adaptive Boosting integrated with particle swarm optimization/support vector machine (AdaBoost-PSO-SVM) Model for Lithium-ion Batteries | |
Hu et al. | State-of-charge estimation for lithium-ion batteries of electric vehicle based on sensor random error compensation | |
CN117130419B (en) | LSTM-based MOS tube differential pressure intelligent regulation method and system | |
CN113552490B (en) | Reconfigurable battery pack SOC estimation method based on rest recovery effect | |
WO2024060539A1 (en) | Annual carbon emission amount estimation method and device for power battery |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |