Detailed Description
So that the manner in which the features and techniques of the disclosed embodiments can be understood in more detail, a more particular description of the embodiments of the disclosure, briefly summarized below, may be had by reference to the appended drawings, which are not intended to be limiting of the embodiments of the disclosure. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawing.
The terms first, second and the like in the description and in the claims of the embodiments of the disclosure and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are, for example, capable of operation in connection with other embodiments. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
In the embodiments of the present disclosure, the terms "upper", "lower", "inner", "middle", "outer", "front", "rear", and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are used primarily to better describe embodiments of the present disclosure and embodiments thereof and are not intended to limit the indicated device, element, or component to a particular orientation or to be constructed and operated in a particular orientation. Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the embodiments of the present disclosure will be understood by those of ordinary skill in the art in view of the specific circumstances.
In addition, the terms "disposed," "connected," "secured" and "affixed" are to be construed broadly. For example, "connected" may be in a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the embodiments of the present disclosure may be understood by those of ordinary skill in the art according to specific circumstances.
The term "plurality" means two or more, unless otherwise indicated.
It should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other.
In some embodiments, as shown in connection with FIG. 1, there is provided a method for training a driving data model, comprising:
s101, an offline battery database and an online battery database are established;
s102, establishing an initial data driving model;
and S103, training the initial data driving model according to the offline battery database and the online battery database to obtain a target driving data model.
The present disclosure provides a method for training a driving data model, comprising: establishing an offline battery database and an online battery database; establishing an initial data driving model; and training the initial data driving model according to the offline battery database and the online battery database to obtain a target driving data model.
According to the method and the device, the offline battery database and the online battery database are built, the offline battery database and the online battery database are utilized respectively, the initial data driving model is trained, and then the target driving data model for estimating the service life of the battery is obtained, so that the accurate trend prediction of the residual service life of the battery is improved, and the reliability and the stability of the system are improved.
In some embodiments, as shown in connection with FIG. 2, there is provided a method for training a driving data model, comprising:
s201, an offline battery database and an online battery database are established.
S202, an initial data driving model is established.
S203, utilizing an offline battery database to drive the model to the initial data, and obtaining a trained data driving model;
s204, verifying the trained data driving model by using the online battery database to obtain a target driving data model.
In this embodiment, the initial data-driven model is first obtained using the offline battery database, and the trained data-driven model is then validated by the online battery database to obtain the target-driven data model. The current remaining life and the future remaining life of the battery can be estimated simultaneously by combining the offline battery database and the online battery database. The method improves the accurate trend prediction of the residual life of the battery and improves the reliability and stability of the system.
Optionally, the offline battery database includes an offline health factor, and the step of obtaining the trained data-driven model from the initial data-driven model using the offline battery database includes: and acquiring the offline health factor in the offline battery database. The offline health factor is input into the initial data driven model for training. And adjusting parameter setting of the initial data driving model through training to obtain a first trained data driving model.
In this embodiment, the initial data driven model is a conventional known model, such as a transducer model. An initial data driven model can be readily established by those skilled in the art based on well known knowledge. And injecting the offline health factors stored in the offline battery database into the initial data driving model for training to obtain a first data driving model with higher accuracy.
Optionally, the offline battery database includes an offline capacity fade curve, and the step of obtaining the trained data-driven model from the initial data-driven model using the offline battery database includes:
acquiring an offline capacity fading curve in an offline battery database;
inputting the offline capacity fading curve into an initial data driving model for training;
And (3) adjusting parameter setting of the initial data driving model through training to obtain a trained second data driving model.
In this embodiment, the initial data driven model as described above is a conventional known model, such as a transducer model. And (3) inputting a large number of offline capacity fading curves stored in an offline battery database into an initial data driving model for training, and learning and predicting the capacity fading trend and the battery health state, so that the model can predict the future capacity fading trend.
Optionally, the step of establishing the offline battery database comprises: acquiring battery parameters of a battery used by an energy storage power station; according to the battery parameters, performing an accelerated aging experiment and a parameter calibration experiment; acquiring a capacity fading curve and an off-line health factor obtained by an experiment; and establishing an offline battery database according to the capacity fading curve and the offline health factor.
The off-line health factors comprise off-line polarized internal resistance, off-line polarized capacitance, off-line diffused internal resistance and off-line diffused capacitance.
In this embodiment, obtaining an offline capacity decay curve and an offline health factor for the battery to build an offline battery database includes obtaining a model of the battery of the energy storage power station; performing an accelerated aging test and a parameter calibration test on the battery of the model to obtain an offline capacity fading curve and an offline health factor of the battery; the offline capacity fade curve and the offline health factor are stored in a battery database to build an offline battery database, wherein the offline health factor includes an offline polarized internal resistance, an offline polarized capacitance, an offline diffused internal resistance, and an offline diffused capacitance.
Specifically, the energy storage power stations all have batteries of respective corresponding models. And after the corresponding battery model is obtained, performing an accelerated aging test and a parameter calibration test on the battery of the same model. Both tests are known from which the offline capacity fade curve and offline health factor for that model of battery can be obtained. The off-line health factor preferably includes off-line polarized internal resistance, off-line polarized capacitance, off-line diffused internal resistance, and off-line diffused capacitance.
Optionally, the step of establishing an online battery database includes: acquiring a current value and a voltage value of a battery; obtaining the state of charge of the battery after denoising according to the current value and the voltage value; inputting the current value, the voltage value and the denoised battery state of charge into an equivalent circuit model to obtain an online health factor and an online health state; and establishing an online battery database according to the online health factor and the online health state.
The on-line health factors comprise on-line polarized internal resistance, on-line polarized capacitance, on-line diffused internal resistance and on-line diffused capacitance.
In this embodiment, the real-time on-line current and on-line voltage of the battery are obtained to solve the on-line state of charge SOC of the battery and remove noise; inputting real-time online current, online voltage and online state of charge (SOC) with noise removed of the battery into an equivalent circuit model to obtain an online capacity fading curve, an online health factor and an online health State (SOH); storing the online capacity fade curve, the online health factor, and the online health status SOH into a battery database to establish an online battery database; the on-line health factors comprise on-line polarized internal resistance, on-line polarized capacitance, on-line diffused internal resistance and on-line diffused capacitance. The equivalent circuit model is a particle swarm algorithm.
Specifically, the batteries of the energy storage power station are all operated on line, after the on-line parameters of the batteries are obtained, the on-line state of charge (SOC) of the batteries is solved by using an industry general method, noise is filtered, and an equivalent circuit model is input to solve an on-line capacity fading curve, an on-line health factor and an on-line health State (SOH). Wherein the on-line parameters include on-line voltage and on-line current. The equivalent circuit model is, for example, a particle swarm algorithm.
Optionally, the step of obtaining the denoised battery state of charge according to the current value and the voltage value includes: and obtaining the state of charge of the denoised battery by utilizing a self-adaptive H-infinity filtering method according to the current value and the voltage value.
Optionally, the equivalent circuit model is a particle swarm algorithm model.
In the embodiment, the identification process of the transducer model is greatly influenced by noise of input parameters, the stability of model prediction is seriously interfered, and in order to reduce the noise caused by the input parameters and radically solve the prediction error caused by health factors, therefore, a self-adaptive H-infinity filtering method with strong robustness is used for solving the SOC of the battery, a particle swarm algorithm is used for solving health factors such as the ohmic internal resistance of the battery, the battery capacity and the like of the key parameters of the battery, and an equivalent circuit model and a data driving model are used for fusion, so that the accurate trend prediction of the residual service life of the battery is realized, and the reliability and the stability of the system are improved.
Specifically, the on-line parameters of the battery can be substituted into the adaptive H-infinity filtering method to find the on-line state of charge SOC, and the noise removal work is already performed in the process. The solution process of the method of adaptive H-infinity filtering is referred to in FIG. 3. The method comprises the steps of setting noise, error covariance initial value, error covariance matrix estimation, symmetric positive definite matrix updating, gain matrix updating, adaptive noise covariance matching, error covariance matrix updating, setting state initial value, priori estimation-prediction, information updating, posterior estimation correction, system output SOC estimated value and the like. The input values may be voltage U, current I, period T and SOH.
Optionally, the step of verifying the trained data driven model with the online battery database to obtain the target driven data model includes: acquiring an online health factor in an online battery database; inputting the online health factors into a first data driving model for training, and outputting a first health state; acquiring an online health state in an online battery database; and verifying the first data driving model according to the first health state and the online health state to obtain a first target driving data model.
In this embodiment, the online health factor is substituted into the first data driving model to output the first health state SOH and compared with the previous online health state SOH, and the first target driving data model is determined according to the comparison structure.
Optionally, the step of verifying the first data driving model according to the first health state and the online health state to obtain the first target driving data model includes: calculating a difference between the first health state and the online health state; and under the condition that the difference value is smaller than a preset value, completing verification of the first data driving model to obtain a first target driving data model.
In this embodiment, there are two possibilities for the comparison process of the first state of health SOH with the online state of health SOH. When the difference between the first health state SOH and the online health state SOH is smaller than the preset value K, the data driving model, for example, a transducer model is considered to be trained and output, the battery SOH is not estimated by using the particle swarm algorithm any more, and the transducer is used for estimation instead. When the difference between the first health state SOH and the online health state SOH is greater than or equal to the preset value K, the data driving model, such as the transducer model, is considered to be still required to be trained, training is required to be continued at this time, and the relationship between the first health state SOH and the online health state SOH is judged, and the process is repeated until the difference between the first health state SOH and the online health state SOH is smaller than the preset value K.
Optionally, the step of calculating the difference between the first health status and the online health status comprises: and periodically acquiring and calculating the difference value between the first health state and the online health state within a preset duration.
The value range of the preset duration is as follows: more than or equal to 12 hours and less than or equal to 24 hours; the range of the preset value is as follows: greater than or equal to 1% and less than or equal to 3%.
In this embodiment, when the difference between the first health state SOH and the online health state SOH within the preset time period is smaller than the preset value K, the parameter setting of the first data driving model is adjusted to obtain the first target data driving model.
Specifically, if the difference between the first health state SOH and the online health state SOH can be kept smaller than the preset value K within the preset time period, the best effect of the first target data driving model is indicated. The value of t is the conclusion from a number of experiments.
Optionally, the step of verifying the trained data driven model with the online battery database to obtain the target driven data model includes: acquiring an online capacity fading curve of an online battery database; and inputting the online capacity fading curve into a second data driving model to obtain a second target driving data model.
In this embodiment, a number of offline capacity fade curves are injected into the initial data driven model for training and self-learning to form a second data driven model. And substituting the line capacity fading curve into the second data driving model to train to obtain a second target data driving model, and testing the future capacity fading trend to further obtain the future residual service life of the battery.
Optionally, the step of establishing the initial data driven model comprises: establishing a transducer model; wherein, the transform model includes coding component and decoding component, and the coding component includes: the decoding component includes a multi-headed attention mechanism layer.
In this embodiment, a transducer model is used to predict the capacity fade trend, through the encoding component and decoding component, using two sublayers in the encoding component: a Self-Attention layer (Self-Attention layer) and a feed-forward network layer (Position-wise Feed Forward Network). And a Decoder multi-head attention mechanism layer in the decoding component, wherein in the prediction of the residual service life influenced by more battery health factors, the prediction of the battery capacity fading trend can be preferably realized by integrating the health factors. Compared with the cyclic neural network such as LSTM and RNN, the method has the advantages of higher processing speed and higher advantage in the energy storage power station of mass battery monomers because the cyclic neural network can execute instructions in parallel.
In some embodiments, as shown in connection with fig. 4, there is provided a method for estimating remaining life of a battery, the method being applied to an energy storage power station, the method comprising:
s401, acquiring a capacity fading curve and a health factor of a battery of an energy storage power station;
s402, inputting the health factors into a trained first target data driving model to obtain the battery health state of the battery energy storage power station;
s403, inputting the capacity fading curve into a trained second target data driving model to obtain the residual life of the battery of the energy storage power station;
wherein the first target data-driven model and the second target data-driven model are obtained by the method for training the driven data model as described in the above embodiments, respectively.
According to the method for estimating the remaining life of the battery, the capacity fading curve and the health factor of the battery of the energy storage power station are obtained, the health factor is input into the trained first target data driving model, and the battery health state of the energy storage power station is output. The capacity fading curve is input into the trained second target data driving model, the residual service life of the battery of the energy storage power station is output, the accurate trend prediction of the residual service life of the battery is improved, and the reliability and stability of the system are improved.
In some embodiments, as shown in connection with fig. 5, there is provided a method for estimating remaining life of a battery, the method being applied to an energy storage power station, the method comprising:
s501, an offline battery database and an online battery database are established;
s502, an initial data driving model is established;
s503, utilizing an offline battery database to drive the model to the initial data, and obtaining a first data driving model after training;
and S504, verifying the trained data driving model by using an online battery database to obtain a first target driving data model.
S505, acquiring a capacity fading curve and a health factor of a battery of the energy storage power station;
s506, inputting the health factors into the trained first target data driving model to obtain the battery health state of the battery energy storage power station;
and S507, inputting the capacity fading curve into a trained second target data driving model to obtain the residual life of the battery of the energy storage power station.
In this embodiment, the initial data-driven model is first obtained using the offline battery database, and the trained data-driven model is then validated by the online battery database to obtain the target-driven data model. The current remaining life and the future remaining life of the battery can be estimated simultaneously by combining the offline battery database and the online battery database. The method improves the accurate trend prediction of the residual life of the battery and improves the reliability and stability of the system.
Optionally, the step of obtaining the trained first data-driven model from the initial data-driven model using the offline battery database includes: acquiring an offline health factor in an offline battery database; inputting the offline health factors into an initial data driving model for training; and adjusting parameter setting of the initial data driving model through training to obtain a first trained data driving model.
In this embodiment, the initial data driven model is a conventional known model, such as a transducer model. An initial data driven model can be readily established by those skilled in the art based on well known knowledge. And injecting the offline health factors stored in the offline battery database into the initial data driving model for training to obtain a first data driving model with higher accuracy.
Optionally, the step of verifying the trained data-driven model using the online battery database to obtain the first target-driven data model includes: acquiring an online health factor in an online battery database; inputting the online health factors into a first data driving model for training, and outputting a first health state; acquiring an online health state in an online battery database; and verifying the first data driving model according to the first health state and the online health state to obtain a first target driving data model.
In this embodiment, the online health factor is substituted into the first data driving model to output the first health state SOH and compared with the previous online health state SOH, and the first target driving data model is determined according to the comparison structure.
Optionally, the step of verifying the first data driving model according to the first health state and the online health state to obtain the first target driving data model includes: calculating a difference between the first health state and the online health state; and under the condition that the difference value is smaller than a preset value, completing verification of the first data driving model to obtain a first target driving data model.
In this embodiment, there are two possibilities for the comparison process of the first state of health SOH with the online state of health SOH. When the difference between the first health state SOH and the online health state SOH is smaller than the preset value K, the data driving model, for example, a transducer model is considered to be trained and output, the battery SOH is not estimated by using the particle swarm algorithm any more, and the transducer is used for estimation instead. When the difference between the first health state SOH and the online health state SOH is greater than or equal to the preset value K, the data driving model, such as the transducer model, is considered to be still required to be trained, training is required to be continued at this time, and the relationship between the first health state SOH and the online health state SOH is judged, and the process is repeated until the difference between the first health state SOH and the online health state SOH is smaller than the preset value K.
Optionally, the step of calculating the difference between the first health status and the online health status comprises: and periodically acquiring and calculating the difference value between the first health state and the online health state within a preset duration.
In this embodiment, when the difference between the first health state SOH and the online health state SOH within the preset time period is smaller than the preset value K, the parameter setting of the first data driving model is adjusted to obtain the first target data driving model.
Specifically, if the difference between the first health state SOH and the online health state SOH can be kept smaller than the preset value K within the preset time period, the best effect of the first target data driving model is indicated. The value of t is the conclusion from a number of experiments.
In some embodiments, as shown in connection with fig. 6, there is provided a method for estimating remaining life of a battery, the method being applied to an energy storage power station, the method comprising:
s601, an offline battery database and an online battery database are established;
s602, an initial data driving model is established;
s603, utilizing an offline battery database to drive the model to the initial data, and obtaining a first data driving model after training;
and S604, verifying the trained data driving model by using the online battery database to obtain a first target driving data model.
S605, obtaining a trained second data driving model by using an offline battery database to the initial data driving model;
and S606, verifying the trained data driving model by using the online battery database to obtain a second target driving data model.
S607, acquiring a capacity fading curve and a health factor of a battery of the energy storage power station;
s608, inputting the health factors into the trained first target data driving model to obtain the battery health state of the battery energy storage power station;
s609, inputting the capacity fade curve into the trained second target data driving model to obtain the residual life of the battery of the energy storage power station.
In this embodiment, the battery of the energy storage power station obtains a large amount of offline experimental data through a large amount of experiments, and the offline experimental data are stored to form an offline battery database. Such offline experimental data includes, but is not limited to, offline capacity fade curves and offline health factors. The offline capacity fade curve may also be given other offline health factors by various methods. A plurality of offline capacity fade curves are injected into the initial data-driven model for training and self-learning to form a second data-driven model. And injecting the offline health factors into the initial data driving model to perform training and self-learning to form a first data driving model. And then calculating out real-time online detection data to form an online battery database. The online detection data includes, but is not limited to, online capacity fade curves, online health factors, and online health status SOH. Substituting the online health factors into the first data driving model to output a first health state SOH, comparing the first health state SOH with the previous online health state SOH to obtain a difference value, and when the difference value is smaller than a preset value K, considering that the first data driving model is trained, and outputting a first target data driving model. The first target data driving model may be used to estimate the current remaining life of the battery at this time. Since the on-line detection data of the battery is acquired in real time, the latter process is dynamically performed until the requirements are satisfied. When the online training data driving model is obtained, the simultaneous online capacity fading curve is substituted into the second data driving model to be trained to obtain a second target data driving model, and future capacity fading trend can be tested, so that future residual service life of the battery is obtained. The method and the device are combined to realize a data driving model with high robustness, so that the accurate trend prediction of the residual life of the battery is improved, and the reliability and stability of the system are improved.
Optionally, the step of obtaining the trained second data-driven model from the initial data-driven model using the offline battery database comprises: acquiring an offline capacity fading curve in an offline battery database; inputting the offline capacity fading curve into an initial data driving model for training; and (3) adjusting parameter setting of the initial data driving model through training to obtain a trained second data driving model.
The initial data driven model as described above is a conventional known model, such as a transducer model. And (3) inputting a large number of offline capacity fading curves stored in an offline battery database into an initial data driving model for training, and learning and predicting the capacity fading trend and the battery health state, so that the model can predict the future capacity fading trend.
Optionally, the step of verifying the trained second data-driven model with the online battery database to obtain the second target-driven data model includes: acquiring an online capacity fading curve of an online battery database; and inputting the online capacity fading curve into a second data driving model to obtain a second target driving data model.
In this embodiment, a number of offline capacity fade curves are injected into the initial data driven model for training and self-learning to form a second data driven model. And substituting the line capacity fading curve into the second data driving model to train to obtain a second target data driving model, and testing the future capacity fading trend to further obtain the future residual service life of the battery.
Optionally, the step of establishing the offline battery database comprises: acquiring battery parameters of a battery used by an energy storage power station; according to the battery parameters, performing an accelerated aging experiment and a parameter calibration experiment; acquiring a capacity fading curve and an off-line health factor obtained by an experiment; establishing an offline battery database according to the capacity fading curve and the offline health factor; the off-line health factors comprise off-line polarized internal resistance, off-line polarized capacitance, off-line diffused internal resistance and off-line diffused capacitance.
In this embodiment, a transducer model is used to predict the capacity fade trend, through the encoding component and decoding component, using two sublayers in the encoding component: a Self-Attention layer (Self-Attention layer) and a feed-forward network layer (Position-wise Feed Forward Network). And a Decoder multi-head attention mechanism layer in the decoding component, wherein in the prediction of the residual service life influenced by more battery health factors, the prediction of the battery capacity fading trend can be preferably realized by integrating the health factors. Compared with the cyclic neural network such as LSTM and RNN, the method has the advantages of higher processing speed and higher advantage in the energy storage power station of mass battery monomers because the cyclic neural network can execute instructions in parallel.
Optionally, the step of establishing an online battery database includes: acquiring a current value and a voltage value of a battery; obtaining the state of charge of the battery after denoising according to the current value and the voltage value; inputting the current value, the voltage value and the denoised battery state of charge into an equivalent circuit model to obtain an online health factor and an online health state; establishing an online battery database according to the online health factors and the online health states; the on-line health factors comprise on-line polarized internal resistance, on-line polarized capacitance, on-line diffused internal resistance and on-line diffused capacitance.
Acquiring real-time on-line current and on-line voltage of the battery to solve on-line state of charge (SOC) of the battery and remove noise; inputting real-time online current, online voltage and online state of charge (SOC) with noise removed of the battery into an equivalent circuit model to obtain an online capacity fading curve, an online health factor and an online health State (SOH); storing the online capacity fade curve, the online health factor, and the online health status SOH into a battery database to establish an online battery database; the on-line health factors comprise on-line polarized internal resistance, on-line polarized capacitance, on-line diffused internal resistance and on-line diffused capacitance. The equivalent circuit model is a particle swarm algorithm.
Specifically, the batteries of the energy storage power station are all operated on line, after the on-line parameters of the batteries are obtained, the on-line state of charge (SOC) of the batteries is solved by using an industry general method, noise is filtered, and an equivalent circuit model is input to solve an on-line capacity fading curve, an on-line health factor and an on-line health State (SOH). Wherein the on-line parameters include on-line voltage and on-line current. The equivalent circuit model is, for example, a particle swarm algorithm.
Optionally, the step of establishing the initial data driven model comprises: establishing a transducer model; wherein, the transform model includes coding component and decoding component, and the coding component includes: the decoding component includes a multi-headed attention mechanism layer.
In this embodiment, a transducer model is used to predict the capacity fade trend, through the encoding component and decoding component, using two sublayers in the encoding component: a Self-Attention layer (Self-Attention layer) and a feed-forward network layer (Position-wise Feed Forward Network). And a Decoder multi-head attention mechanism layer in the decoding component, wherein in the prediction of the residual service life influenced by more battery health factors, the prediction of the battery capacity fading trend can be preferably realized by integrating the health factors. Compared with the cyclic neural network such as LSTM and RNN, the method has the advantages of higher processing speed and higher advantage in the energy storage power station of mass battery monomers because the cyclic neural network can execute instructions in parallel.
In some embodiments, an apparatus for training a driving data model is provided, comprising a processor and a memory storing program instructions, the processor being configured to, when executing the program instructions, perform a method for training a driving data model as described in any of the embodiments above.
In some embodiments, an apparatus for estimating remaining battery life, comprising a processor and a memory storing program instructions, wherein the processor is configured, when executing the program instructions, to perform a method for estimating remaining battery life as described in any of the embodiments above.
According to the device for estimating the residual life of the battery, offline experimental data of the battery are acquired through a large number of experiments, an offline battery database is built, an initial data driving model is built, the offline health factor is utilized to train the offline data driving model to change the parameter setting of the offline data driving model, a first data driving model is obtained for standby, and the capacity attenuation curve is utilized to train the offline data driving model to change the parameter setting of the offline data driving model, so that a second data driving model is obtained for standby. And acquiring the on-line state of charge (SOC) with noise removed and the on-line health factor, training the first data driving model again to obtain a first target data driving model, comparing the output first health State (SOH) with the on-line health State (SOH) output by the equivalent circuit model to obtain a data driving model with high robustness, and training the second data driving model by using the on-line capacity fading curve of the first target data driving model after meeting the requirements to obtain a second target data driving model. The combination of the two can simultaneously estimate the health state of the battery and the residual life of the battery. The method improves the accurate trend prediction of the residual life of the battery and improves the reliability and stability of the system.
In some embodiments, there is provided an energy storage power station comprising: a power station body; and the device for estimating remaining life of a battery according to any of the above embodiments is provided in a power station body.
As shown in fig. 7, an embodiment of the present disclosure provides an energy storage power station comprising an apparatus for estimating remaining battery life as described in any of the embodiments above. The means for estimating the remaining life of the battery includes a processor 700 and a memory 701. Optionally, the battery management system may also include a communication interface (Communication Interface) 702 and a bus 703. The processor 700, the communication interface 702, and the memory 701 may communicate with each other through the bus 703. The communication interface 702 may be used for information transfer. The processor 700 may invoke logic instructions in the memory 701 to perform the estimation method for remaining battery life of the above-described embodiments.
Further, the logic instructions in the memory 701 may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product.
The memory 701 is used as a computer readable storage medium for storing a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor 700 executes the functional applications and data processing by executing the program instructions/modules stored in the memory 701, i.e., implements the estimation method for remaining battery life in the above-described embodiments.
Memory 701 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include a high-speed random access memory, and may also include a nonvolatile memory.
Embodiments of the present disclosure may be embodied in a software product stored on a storage medium, including one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of a method according to embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium including: a plurality of media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or a transitory storage medium.
The above description and the drawings illustrate embodiments of the disclosure sufficiently to enable those skilled in the art to practice them. Other embodiments may involve structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in, or substituted for, those of others. Moreover, the terminology used in the present application is for the purpose of describing embodiments only and is not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a," "an," and "the" (the) are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this application is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, when used in this application, the terms "comprises," "comprising," and/or "includes," and variations thereof, mean that the stated features, integers, steps, operations, elements, and/or components are present, but that the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof is not precluded. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements. In this context, each embodiment may be described with emphasis on the differences from the other embodiments, and the same similar parts between the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method sections disclosed in the embodiments, the description of the method sections may be referred to for relevance.
Those of skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. The skilled artisan may use different methods for each particular application to achieve the described functionality, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the embodiments disclosed herein, the disclosed methods, articles of manufacture (including but not limited to devices, apparatuses, etc.) may be practiced in other ways. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the units may be merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form. The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to implement the present embodiment. In addition, each functional unit in the embodiments of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than that disclosed in the description, and sometimes no specific order exists between different operations or steps. For example, two consecutive operations or steps may actually be performed substantially in parallel, they may sometimes be performed in reverse order, which may be dependent on the functions involved. Each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.