CN118050650B

CN118050650B - Distribution network power supply online nuclear capacity control method and device, distribution network power supply and storage medium

Info

Publication number: CN118050650B
Application number: CN202410451855.XA
Authority: CN
Inventors: 具浩; 何胤; 李嘉添; 苏俊妮; 骆树权
Original assignee: Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2024-04-16
Filing date: 2024-04-16
Publication date: 2024-07-02
Anticipated expiration: 2044-04-16
Also published as: CN118050650A

Abstract

The invention discloses a distribution network power supply online nuclear capacity control method, a distribution network power supply online nuclear capacity control device, a distribution network power supply and a storage medium, wherein the distribution network power supply online nuclear capacity control method comprises the following steps: when the temperature in the battery compartment is detected to be out of the preset temperature range, the temperature regulating device is controlled to output a cooling medium or a heating medium to the battery compartment, the voltage and the current of the battery are collected, the collected voltage, current and temperature are input into the capacity prediction model when the preset capacity condition is met, the predicted capacity of the battery is obtained, and the confidence coefficient of the predicted capacity is calculated according to the collected temperature, voltage and current, so that the predicted capacity is determined to be the capacity of the battery when the confidence coefficient is larger than a threshold value. The temperature regulating device is used as a nuclear capacity load, the energy of the distribution network power supply is fully utilized, the energy rate is improved, the temperature, the voltage and the current are adopted for capacity prediction, the confidence coefficient is calculated, the accuracy of the nuclear capacity is improved, the accurate life cycle monitoring is realized, the battery is enabled to work in a preset temperature range, and the life cycle level of the distribution network power supply is improved.

Description

Distribution network power supply online nuclear capacity control method and device, distribution network power supply and storage medium

Technical Field

The present invention relates to the field of distribution network power technologies, and in particular, to a distribution network power online core capacity control method and apparatus, a distribution network power, and a storage medium.

Background

In the power distribution network, the power supply object of the power distribution network power supply can be secondary equipment or primary equipment, the core component of the power distribution network power supply is a battery, and the life cycle and the working environment of the battery are important guarantees for guaranteeing the power supply reliability of the power distribution network power supply.

The distribution network power supply is usually outdoor, in order to monitor the life cycle level of the distribution network power supply, the capacity of the battery in the distribution network power supply needs to be periodically checked, and at present, resistive loads, such as a capacity resistance, are mainly added in the distribution network power supply, and when the capacity is needed, the battery is controlled to perform constant-current discharge on the capacity resistance so as to perform capacity.

On the one hand, the influence of the environmental temperature of the battery in the distribution network power supply on the battery core capacity is not considered by adding the resistive load on the online core capacity of the distribution network power supply, the core capacity accuracy is low, and the battery energy waste is caused during the core capacity, on the other hand, the core capacity can only monitor the life cycle of the distribution network power supply, and the life cycle level of the distribution network power supply cannot be improved.

Disclosure of Invention

The invention provides a distribution network power supply online nuclear capacity control method and device, a distribution network power supply and a storage medium, and aims to solve the problems that the distribution network power supply online nuclear capacity is low in accuracy due to temperature influence, energy is wasted and the life cycle level of the distribution network power supply cannot be improved.

In a first aspect, the present invention provides an online nuclear capacity control method for a distribution network power supply, where the distribution network power supply includes a battery compartment for accommodating a battery, a processor for taking electricity from the battery, a temperature adjusting device, a temperature sensor, and an electrical parameter sampling module, where a cooling and heating medium output channel of the temperature adjusting device is communicated with the battery compartment, and the method includes:

collecting the temperature in the battery compartment through a temperature sensor;

when the temperature is outside the preset temperature range, controlling the temperature regulating device to work and outputting a cooling medium or a heating medium to the battery compartment;

collecting the voltage and the current of the battery through an electric parameter sampling module;

loading a capacity prediction model when a preset nuclear capacity condition is met, and inputting voltage, current and temperature acquired during the working period of the temperature regulating device into the capacity prediction model to obtain the predicted capacity of the battery;

Calculating the confidence coefficient of the predicted capacity according to the temperature, the voltage and the current acquired during the working period of the temperature regulating device;

And when the confidence coefficient is larger than a preset confidence coefficient threshold value, determining the predicted capacity as the nuclear capacity of the battery.

In a second aspect, the present invention provides an online nuclear capacity control device for a distribution network power supply, where the distribution network power supply includes a battery compartment for accommodating a battery, a processor for taking electricity from the battery, a temperature adjusting device, a temperature sensor, and an electrical parameter sampling module, where a cold and hot medium output channel of the temperature adjusting device is communicated with the battery compartment, and the online nuclear capacity control device includes:

the temperature acquisition module is used for acquiring the temperature in the battery compartment through a temperature sensor;

the temperature adjusting module is used for controlling the temperature adjusting device to work and outputting a cooling medium or a heating medium to the battery compartment when the temperature is out of a preset temperature range;

the voltage and current acquisition module is used for acquiring the voltage and current of the battery through the electric parameter sampling module;

The capacity prediction module is used for loading a capacity prediction model when a preset nuclear capacity condition is met, and inputting the voltage, the current and the temperature acquired during the working period of the temperature regulating device into the capacity prediction model to obtain the predicted capacity of the battery;

the confidence coefficient calculating module is used for calculating the confidence coefficient of the predicted capacity according to the temperature, the voltage and the current acquired during the working period of the temperature regulating device;

And the core capacity determining module is used for determining the predicted capacity as the core capacity of the battery when the confidence coefficient is larger than a preset confidence coefficient threshold value.

In a third aspect, the present invention provides a distribution network power supply, including:

the battery compartment is used for accommodating batteries;

The temperature sensor is used for collecting the temperature in the battery compartment;

the temperature regulating device is used for outputting a cooling medium or a heating medium to the battery compartment;

the electric parameter sampling module is used for collecting the voltage and the current of the battery;

at least one processor connected to the temperature regulating device, the temperature sensor and the electrical parameter sampling module; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the distribution network power supply online core capacity control method of the first aspect.

In a fourth aspect, the present invention provides a computer readable storage medium, where the computer readable storage medium stores computer instructions, where the computer instructions are configured to cause a processor to implement the on-line core capacity control method for a distribution network power supply according to the first aspect of the present invention when executed.

The power supply of the distribution network is provided with the temperature regulating device with the cold and hot medium output channel communicated with the battery compartment, when the temperature sensor detects that the temperature in the battery compartment is outside a preset temperature range, the temperature regulating device is controlled to output cold medium or hot medium to the battery compartment, and collect the voltage and current of the battery, when the nuclear capacity condition is met, a capacity prediction model is loaded, the voltage, current and temperature collected during the working process of the temperature regulating device are input into the capacity prediction model to obtain the predicted capacity of the battery, and the confidence coefficient of the predicted capacity is calculated through the collected voltage, current and temperature, when the confidence coefficient is larger than a threshold value, the predicted capacity is determined to be the nuclear capacity of the battery, on one hand, the temperature regulating device is used as the nuclear capacity load of the battery when the temperature regulating device is used, the special resistive load is not required to be increased, the cost is reduced, the energy utilization rate of the distribution network power supply can be fully utilized, the capacity prediction is carried out by utilizing the voltage and current of the battery compartment, the influence of the temperature on the battery and the battery during the working process is considered, the accuracy of the calculated by the temperature on the battery, the calculated and the calculated capacity of the battery is further, the accuracy of the distribution network can be improved, the life cycle can be guaranteed, and the life cycle of the distribution network can be prolonged.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a method for controlling on-line core capacity of a distribution network power supply according to a first embodiment of the present invention;

FIG. 2 is a schematic diagram of a distribution network power supply according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a plurality of batteries powered in parallel;

Fig. 4 is a flowchart of a method for controlling on-line core capacity of a distribution network power supply according to a second embodiment of the present invention;

fig. 5 is a schematic structural diagram of an on-line core capacity control device for a distribution network power supply according to a third embodiment of the present invention;

fig. 6 is a block diagram of a distribution network power supply according to a fourth embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

Example 1

Fig. 1 is a flowchart of a method for controlling online capacity of a distribution network power supply according to a first embodiment of the present invention, where the method may be performed by an online capacity control device of a distribution network power supply, and the online capacity control device of the distribution network power supply may be implemented in a hardware and/or software form and may be configured in the distribution network power supply. As shown in fig. 1, the method for controlling the online nuclear capacity of the distribution network power supply includes:

s101, acquiring the temperature in the battery compartment through a temperature sensor.

The distribution network power supply of the embodiment may be a power supply applied to power supply of secondary equipment or primary equipment in a distribution network, and the distribution network power supply generally outputs direct current, and the distribution network power supply is mainly powered by a rechargeable battery, for example, a battery such as a rechargeable lead-acid battery, a lithium battery or the like.

Fig. 2 is a schematic diagram of a distribution network power supply applied to an online nuclear capacity control method of the distribution network power supply, where the distribution network power supply may include a battery compartment for accommodating a battery, a processor for taking power from the battery, a temperature adjusting device, a temperature sensor, and an electrical parameter sampling module, where the temperature adjusting device, the temperature sensor, and the electrical parameter sampling module are all connected with the processor.

The processor may be various microprocessors with data processing and various instructions output, the temperature sensor may be various devices or circuits capable of detecting the temperature in the battery compartment, for example, may be a circuit including a thermistor, the electrical parameter sampling module may be a circuit for collecting voltage and current data, in this embodiment, the battery may be accommodated in the battery compartment, the temperature adjusting device may be a device for outputting cold medium or hot medium, for example, may be a device for outputting cold air and hot air, the output channels of the cold medium and the hot medium of the temperature adjusting device are communicated with the battery compartment, for example, the temperature adjusting device is respectively provided with a cold medium output channel and a hot medium output channel which are communicated with the battery compartment, the temperature of the battery in the battery compartment may be reduced when the temperature adjusting device outputs the cold medium to the battery compartment, and the battery in the battery compartment may be heated when the temperature adjusting device outputs the hot medium to the battery compartment.

As shown in fig. 3, the number of the batteries in the battery compartment may be one or more than two, and when the number of the batteries is more than two, a plurality of batteries may be connected to the bus in parallel through a voltage conversion circuit to realize external power supply, where the voltage conversion circuit may be a dc boost or buck circuit, or may be a dc-to-ac circuit or an ac-to-dc circuit.

Of course, the distribution network power supply of this embodiment may further include a humidity sensor, configured to detect humidity in the battery compartment, and may further include a communication unit, where the communication unit is connected to the processor, where the communication unit may be a wired communication unit or a wireless communication unit, and the processor may send collected data such as temperature, humidity, voltage, current, capacity of the battery compartment, and the like, to a remote centralized control master station through the communication unit, so that the centralized control master station may monitor and manage a life cycle of each distribution network power supply through the centralized control master station, and may also send an instruction to the processor of each distribution network power supply through the communication unit, so as to implement remote operation and maintenance management.

And S102, when the temperature is out of the preset temperature range, controlling the temperature regulating device to work and outputting the cooling medium or the heating medium to the battery compartment.

In one embodiment, the ideal operating temperature range of the battery in the battery compartment, that is, the preset temperature range, may be preset, and in one example, the preset temperature range may be 20-25 ℃, and of course, the preset temperature ranges of the distribution network power supplies of different geographic locations and different types may be different. When the acquired temperature starts to be outside the preset temperature range, a timer can be started to count to obtain a timing duration, whether the acquired temperature in the timing duration is outside the preset temperature range is judged, if not, the step of acquiring the temperature in the battery compartment through the temperature sensor is returned to continuously detect the temperature of the battery compartment, if so, a cooling instruction is generated and sent to the temperature regulating device when the acquired temperature is larger than or equal to the upper limit temperature of the preset temperature range, the temperature regulating device works and outputs the cooling medium to the battery compartment when receiving the cooling instruction, and when the acquired temperature is smaller than or equal to the lower limit temperature of the preset temperature range, a heating instruction is generated and sent to the temperature regulating device, and the temperature regulating device works and outputs the heating medium to the battery compartment when receiving the heating instruction.

The processor may send a cooling instruction to the temperature adjustment device to enable the temperature adjustment device to output Leng Jie media to cool the battery compartment until the acquired temperature is within the preset temperature range of 20-25 ℃, and similarly, if the acquired temperature in the time duration is less than the lower limit temperature of 20-25 ℃ in the preset temperature range of 20-25 ℃, the processor may send a heating instruction to the temperature adjustment device to enable the temperature adjustment device to output the heating media to heat the battery compartment until the acquired temperature is within the preset temperature range of 20-25 ℃, and similarly, the processor may send the heating instruction to the temperature adjustment device to enable the temperature adjustment device to output the heating media to the battery compartment until the acquired temperature is within the preset temperature range of 20-25 ℃, so that whether the battery compartment is within the preset temperature range or not can be accurately determined by comparing the acquired temperatures in the time duration with the preset temperature range, and the situation that the temperature of the temperature is not within the preset temperature range is further avoided, and the frequency of the frequency is further increased, and the frequency of the frequency is avoided.

S103, collecting the voltage and the current of the battery through an electric parameter sampling module.

In one embodiment, the electrical parameter sampling module may include a voltage sensor and a current sensor, where the voltage of the battery may be the voltage between the positive electrode and the negative electrode of the battery, and the current of the battery may be the output current of the battery, that is, the discharge current, and it should be noted that the current of the battery includes the current of the temperature regulator, and further includes the current of the temperature sensor, the electrical parameter sampling module, and the processor.

And S104, loading a capacity prediction model when a preset nuclear capacity condition is met, and inputting the voltage, the current and the temperature acquired during the working period of the temperature regulating device into the capacity prediction model to obtain the predicted capacity of the battery.

In this embodiment, the core capacity condition may include whether the current time is a time within a specified time period, whether the current time is a single-battery power supply, whether a voltage of the single-battery power supply is greater than a voltage threshold, whether a time interval from a last core capacity is greater than a preset duration, and the like, and the core capacity condition may be one or more, and when the current time is one, the core capacity condition is satisfied, that is, the core capacity condition is satisfied, and when the core capacity condition is plural, it is necessary to satisfy plural conditions at the same time to determine that the core capacity condition is satisfied.

When the nuclear capacity condition is satisfied, a capacity prediction model which is trained in advance can be loaded, the capacity prediction model can predict the capacity of the battery through the ambient temperature, the voltage and the current when the battery discharges, and in this embodiment, the temperature regulating device can be used as a load for discharging when the battery nuclear capacity, and the voltage, the current and the temperature collected during the working period of the temperature regulating device are input into the capacity prediction model to obtain the predicted capacity of the battery.

S105, calculating the confidence coefficient of the predicted capacity according to the temperature, the voltage and the current acquired during the working period of the temperature regulating device.

The confidence coefficient means the confidence coefficient of the temperature, voltage and current acquired during the operation of the temperature adjusting device to the nuclear capacity of the battery, and the confidence coefficient of the predicted capacity outputted by the capacity prediction model can be calculated through the temperature, voltage and current acquired during the operation of the temperature adjusting device, in one example, the confidence coefficient corresponding to the temperature, voltage and current can be searched in a pre-established confidence coefficient reference table, in another example, the average temperature, maximum temperature, minimum temperature, temperature fluctuation rate, minimum voltage, voltage fluctuation rate, current fluctuation rate and other parameters can be calculated, and the confidence coefficient of the predicted capacity can be calculated through the average temperature, maximum temperature, minimum temperature, temperature fluctuation rate, minimum voltage, voltage fluctuation rate and current fluctuation rate.

And S106, when the confidence coefficient is larger than a preset confidence coefficient threshold value, determining the predicted capacity as the nuclear capacity of the battery.

If the confidence coefficient of the predicted capacity is greater than the confidence coefficient threshold, the confidence coefficient of the predicted capacity is high, the temperature regulating device is used as a discharging load to perform nuclear capacity on the battery at the current temperature, the obtained predicted capacity is close to the real capacity of the battery, the predicted capacity output by the capacity prediction model can be used as the nuclear capacity of the battery, the nuclear capacity is sent to a remote centralized control master station through a communication unit, the life cycle level of the battery is monitored at the centralized control master station, and the ratio of the nuclear capacity to the standard capacity can be calculated to serve as a health index of the battery to evaluate the life cycle level of the battery through the health index.

If the confidence coefficient is less than or equal to the confidence coefficient threshold value, which indicates that the reliability of the battery is low by using the temperature regulating device as the discharging load at the current temperature, the predicted capacity output by the capacity prediction model can be discarded, and the process returns to S101.

The power supply of the distribution network is provided with the temperature regulating device with the cold and hot medium output channel communicated with the battery compartment, when the temperature sensor detects that the temperature in the battery compartment is outside a preset temperature range, the temperature regulating device is controlled to output cold medium or hot medium to the battery compartment, the voltage and the current of the battery are collected, a capacity prediction model is loaded when the nuclear capacity condition is met, the collected voltage, current and temperature during the working process of the temperature regulating device are input into the capacity prediction model to obtain the predicted capacity of the battery, the confidence coefficient of the predicted capacity is calculated through the collected voltage, current and temperature, the predicted capacity is determined to be the nuclear capacity of the battery when the confidence coefficient is larger than a threshold value, on one hand, the temperature regulating device is used as the nuclear capacity load of the battery when the temperature regulating device is used, the special resistive load is not required to be increased, the cost is reduced, the energy utilization rate of the distribution network power supply can be fully utilized, the capacity prediction is carried out by utilizing the voltage and the current of the battery compartment, the influence of the temperature on the battery is considered, the confidence coefficient of the predicted capacity is calculated, the accuracy of the predicted capacity of the battery is improved, the accuracy of the distribution network can be ensured by the temperature distribution network is improved, the life cycle of the temperature is prolonged, the life cycle of the distribution network can be prolonged, and the life cycle of the device is ensured.

Example two

Fig. 4 is a flowchart of a method for controlling on-line core capacity of a distribution network power supply according to a second embodiment of the present invention, where the optimization is performed based on the first embodiment of the present invention, as shown in fig. 4, and the method for controlling on-line core capacity of a distribution network power supply includes:

S401, acquiring the temperature in the battery compartment through a temperature sensor.

And S402, when the temperature is out of the preset temperature range, controlling the temperature regulating device to work and outputting the cooling medium or the heating medium to the battery compartment.

S403, collecting the voltage and the current of the battery through an electric parameter sampling module.

In this embodiment, S401 to S403 are substantially similar to S101 to S103, and reference may be made to S101 to S103 in the first embodiment, which is not described herein.

S404, judging whether a preset nuclear capacity condition is met.

In this embodiment, the kernel-volume condition may be that the following conditions are simultaneously satisfied:

the single battery is powered, so that the nuclear capacity of the single battery can be ensured;

The battery voltage is larger than the preset voltage, so that the nuclear capacity of the battery in a state close to full charge can be ensured;

The interval time length of two adjacent nuclear capacity is larger than a first time length threshold value, so that frequent nuclear capacity can be avoided;

the working time length of the temperature regulating device is larger than the second time length threshold value, so that the battery discharge time during capacity checking can be prevented from being too short.

In order to judge whether the core capacity condition is met, whether a single battery supplies power to the temperature adjusting device or not can be judged, if yes, the current voltage of the battery supplying power is obtained, the working time length of the temperature adjusting device is calculated, the working time length is the time length from the time of the last core capacity to the current time when the temperature adjusting device adjusts the temperature of the battery compartment to be within a preset temperature range, when the time length of the last core capacity is longer than a first time length threshold, the working time length is longer than a second time length threshold and the current voltage is greater than a preset voltage threshold, the preset core capacity condition is met, S405 is executed, if the preset core capacity condition is not met, the core capacity operation is not executed, and S401 is returned. The working time of the temperature regulating device can be estimated through the current collected temperature, the upper limit temperature or the lower limit temperature of a preset temperature range, the volume of a battery compartment and the power of the temperature regulating device.

According to the embodiment, whether the core capacity is carried out during the working of the temperature regulating device is determined through the preset core capacity condition, the core capacity of the battery can be carried out under ideal conditions, invalid core capacity operation is avoided, the accuracy of the core capacity of the battery can be improved, and frequent core capacity can be avoided.

S405, obtaining the model of the distribution network power supply, and loading model parameters matched with the model of the distribution network power supply to complete the loading of the capacity prediction model.

In this embodiment, the model of the distribution network power supply indicates the model of the battery and the model of the temperature adjusting device in the distribution network power supply, and at least one of the battery and the temperature adjusting device of the distribution network power supply with different models is different, so that different capacity prediction models need to be trained in advance for the distribution network power supplies with different models, and the different capacity prediction models can be the same model structure and different model parameters.

When the capacity prediction model is trained, training data sets of various types of distribution network power supplies can be obtained, training samples in the training data sets are voltage curves, current curves and temperature curves of a battery compartment of each distribution network power supply in different capacities and different temperatures during the working period of a temperature adjusting device, each training sample marks a first capacity, the capacity prediction model is initialized, the training samples of the distribution network power supplies of the first type are input into the initialized capacity prediction model to obtain a second capacity, the first capacity and the second capacity are adopted to calculate loss rate, whether training conditions are met or not is judged, if not, model parameters of the capacity prediction model are adjusted by adopting the loss rate, the step of inputting the training samples of the distribution network power supplies of the first type into the capacity prediction model is returned, if yes, the capacity prediction model of the distribution network power supplies of the first type is determined, the model parameters of the capacity prediction model are stored in association with the first type, the training samples of the distribution network power supplies of the first type are deleted from the training data set, the training samples of the distribution network power supplies of the first type are determined to be the initialized capacity prediction model, if no, and if the capacity prediction model of the distribution network power supplies of the second type is calculated, and the first type of the distribution network power supply of the first type is judged, and if not, the capacity prediction model of the distribution network power supply of the first type is completely is judged, and the capacity prediction model is judged, and the capacity of the distribution network power supply is calculated.

For example, assuming that a capacity prediction model of a distribution network power supply of model A, B, C needs to be trained, a voltage curve, a current curve and a temperature curve of a battery compartment of a distribution network power supply of model a during operation of a temperature adjustment device at different capacities and different temperatures can be obtained, for example, when the distribution network power supply is capable of obtaining capacities of 95%, 90%, 85% and 80% of standard capacities, the temperature adjustment device is controlled to operate at different temperatures for each capacity, the voltage, the current and the battery compartment temperature of a battery are collected during operation of the temperature adjustment device, the voltage curve, the current curve and the temperature curve are generated as training samples, and a first capacity is marked as a label, one training sample can be expressed as (a, T1, U, I, T2 and C), wherein a represents the model of the distribution network power supply, T1 is the temperature of the battery compartment when the temperature adjustment device starts to operate, U represents the voltage curve of the battery, I represents the circuit curve of the battery, T2 represents the temperature curve of the battery compartment during operation of the temperature adjustment device, C represents the marked first capacity, that is the actual capacity of the battery, and the first capacity is marked as a training sample of the distribution network power supply of model of the other examples.

When training a capacity prediction model of a distribution network power supply of a first model (such as model A), randomly extracting a training sample of the distribution network power supply of the model A from a training data set, inputting the training sample into the initialized capacity prediction model to obtain a second capacity, calculating a loss rate by adopting the first capacity and the second capacity of the training sample, judging whether a training condition is met (such as whether the loss rate is smaller than a threshold value or whether the training frequency reaches the prediction frequency or whether the change rate of the loss rate calculated by two adjacent times is smaller than the threshold value) or not, if so, determining that the capacity prediction model of the distribution network power supply of the first model completes training, and storing the first model and model parameters in an associated mode to realize that corresponding model parameters can be searched through the first model; if not, after calculating the gradient by using the loss rate, performing random gradient descent, batch random gradient descent and the like on the models of the capacity prediction model so as to adjust model parameters and continue training, if the capacity prediction model of the distribution network power supply of the first model is trained, for example, the capacity prediction model of the model a is trained, the capacity prediction model of the model a after the training is used as the initialized capacity prediction model, training samples of the distribution network power supply of all models a are deleted from the training data set, then a second model (for example, model B) is used as the first model, training samples of the first model (at this time, model B) are extracted from the training data set, and are input into the initialized capacity prediction model for continuous training, so as to obtain the capacity prediction model of the model B, until the capacity prediction models of all models are trained, wherein the loss rate can be calculated by a mean square error, cross entropy and other loss functions, and the calculation mode of the loss rate is not limited in the embodiment.

In addition, the capacity prediction model is trained through a temperature curve, a voltage curve and a current curve, so that the capacity prediction model can learn the capacity of a battery predicted through temperature, voltage and current, and the capacity of the battery is predicted by combining the influence of temperature on the nuclear capacity of the battery, so that the capacity prediction model can predict the capacity of the battery under various temperature working conditions, and the accuracy of the capacity prediction model is improved.

After model parameters of capacity prediction models of various distribution network power supplies are trained and stored, model parameters matched with the model can be searched through the model of the distribution network power supply which needs core capacity at present so as to finish loading of the capacity prediction model, and an exemplary structure of the capacity prediction model can be preloaded in a processor of the distribution network power supply, and after the model parameters are loaded, the model parameters in the capacity prediction model are set so as to finish loading.

S406, temperature, voltage and current acquired during the working period of the temperature regulating device are adopted to respectively generate a temperature curve, a voltage curve and a current curve.

The temperature, voltage and current collected during the operation of the temperature regulating device are a temperature sequence, a voltage sequence and a current sequence which are time-lapse, and a temperature curve, a voltage curve and a current curve can be generated by adopting the temperature sequence, the voltage sequence and the current sequence, wherein the time is taken as an abscissa, and the temperature, the voltage and the current are taken as an ordinate.

S407, inputting the temperature curve, the voltage curve and the current curve into a capacity prediction model to obtain the predicted capacity of the battery.

After the nuclear capacity condition is met and a temperature curve of a battery compartment, a voltage curve of a battery and a current curve of the battery are generated during the operation of the temperature regulating device, the temperature curve, the voltage curve and the current curve can be input into a capacity prediction model, temperature characteristics, voltage characteristics and current characteristics are extracted from the capacity prediction model, the temperature characteristics, the voltage characteristics and the current characteristics are fused, the capacity of the battery is predicted through the fused characteristics, and the predicted capacity of the battery is output.

S408, calculating the confidence coefficient of the predicted capacity according to the temperature, the voltage and the current acquired during the working period of the temperature regulating device.

In one embodiment, for the collected temperature, the working duration of the temperature adjustment device may be determined, the average temperature, the maximum temperature, the minimum temperature and the temperature fluctuation rate are calculated by using the temperature collected during the working period of the temperature adjustment device, and the temperature influence fraction Con_t of the temperature on the confidence coefficient is calculated by a preset first formula, wherein the first formula is as follows:

（1）；

Wherein t ₀ is the standard ambient temperature required by nuclear capacity, As can be seen from the formula (1), the highest temperature t _max, the lowest temperature t _min and the average temperature of the battery compartment in the nuclear capacity are obtained from the average temperature t _max, the highest temperature t _min and the lowest temperature t _rate, and the temperature fluctuation rate t _rate=2(t_max-t_min)/(t_max+t_min The closer the standard ambient temperature t ₀ needed when the nuclear capacity is, the smaller the temperature fluctuation rate t _rate is, the closer the temperature of the battery compartment is to the standard ambient temperature t ₀ during the nuclear capacity, the more stable the temperature change is, the smaller the temperature influence on the nuclear capacity is, the larger the temperature influence fraction Con_t of the temperature on the confidence coefficient is, the higher the reliability of the predicted capacity is, otherwise, the larger the difference between the temperature of the battery compartment and the standard ambient temperature t ₀ during the nuclear capacity is, the larger the temperature change fluctuation is, the larger the temperature influence on the nuclear capacity is, the smaller the temperature influence fraction Con_t of the temperature on the confidence coefficient is, and the lower the reliability of the predicted capacity is.

For the collected voltage, the maximum voltage, the minimum voltage and the voltage fluctuation rate can be determined from the collected voltage during the operation of the temperature regulating device, and the voltage influence fraction Con_u of the voltage to the confidence coefficient is calculated through a preset second formula, wherein the second formula is as follows:

（2）；

u ₀ is a standard voltage at the time of full charge of the battery, u ₁ is a standard cut-off voltage at the time of discharge of the battery core capacity, u _max is a maximum voltage, u _min is a minimum voltage, u _rate is a voltage fluctuation ratio, u _rate=2(u_max-u_min)/(u_max+u_min), from the above formula (2), the closer the maximum voltage u _max is to the standard voltage u ₀ at the time of full charge, the closer the minimum voltage u _min is to the standard cut-off voltage at the time of discharge of the battery core capacity, the smaller the voltage fluctuation ratio u _rate is, the closer the battery core capacity is to the full charge state, and the full discharge is performed, and the voltage drop during the discharge is relatively smooth, the larger the voltage influence fraction con_u of the voltage to the confidence is, the higher the reliability of the predicted capacity is, and conversely, the reliability of the predicted capacity is lower the predicted that the battery is not to perform the full discharge of the core capacity in the full charge state.

For the collected current, the current fluctuation rate can be calculated by using the maximum current and the minimum current in the collected current in the working period of the temperature regulating device, and the pearson correlation coefficient of the collected temperature and the collected voltage can be calculated, and the confidence coefficient of the predicted capacity is further calculated by using the working time length, the temperature influence fraction, the voltage influence fraction, the current fluctuation rate, the pearson correlation coefficient and a preset third formula, wherein the third formula is as follows:

（3）；

Wherein T is the working time, I _rate is the current fluctuation rate, I _rate=2(I_max-I_min)/(I_max+I_min),I_max is the maximum current, I _min is the minimum current, and r _u,t is the Pearson correlation coefficient of the acquired temperature and the acquired voltage.

In this embodiment, the pearson correlation coefficient r _u,t of the temperature and the collected voltage can be calculated by the following formula:

（4）；

Where u _i is the i-th voltage collected, t _i is the i-th temperature collected, As an average value of the acquired voltages,As can be seen from the formula (4), if the pearson correlation coefficient r _u,t of the temperature and the voltage is larger, the correlation between the voltage change and the temperature is strong when the battery core capacity is discharged, the collected voltage and temperature change follow the change rule of the voltage and the temperature when the battery core capacity is discharged, and the collected voltage, current and temperature of the core capacity are objective change data in the battery core capacity, so that the accuracy is high.

From the above formula (3), it can be seen that, when the operating time period T of the temperature adjustment device is longer (the battery discharging time period is longer when the core capacity is described), the current fluctuation rate I _rate is smaller, the confidence factor Con of the predicted capacity is larger, that is, the longer the discharging time period is when the battery core capacity is discharged, the smaller the current fluctuation rate is closer to constant current discharging in the discharging process, and the more reliable the predicted capacity is obtained.

According to the embodiment, the confidence coefficient of the predicted capacity is calculated through the temperature, the voltage and the current of the battery core capacity, the influence of the temperature on the voltage and the current in the core capacity process is fully considered, and the accuracy of the core capacity is improved.

And S409, when the confidence coefficient is larger than a preset confidence coefficient threshold value, determining the predicted capacity as the nuclear capacity of the battery.

After calculating the confidence coefficient of the predicted capacity, it may be determined whether the confidence coefficient is greater than a confidence coefficient threshold (for example, 0.9), if so, it indicates that the confidence coefficient of the battery is high by using the temperature adjustment device as a discharge load at the current temperature, the predicted capacity output by the capacity prediction model is determined as the core capacity of the battery, and S410 is executed, if not, it indicates that the confidence coefficient of the battery is low by using the temperature adjustment device as a discharge load at the current temperature, the predicted capacity output by the capacity prediction model may be discarded, and S401 is returned.

S410, judging whether the nuclear capacity is smaller than a preset capacity threshold.

The capacity threshold may be set in this embodiment, where the capacity threshold may be a threshold that cannot support the operation of the distribution network power supply on the primary device or the secondary device in the distribution network when the battery capacity is too low, and exemplary capacity thresholds may be 50% and 60% of the standard capacity, and those skilled in the art may set different capacity thresholds according to the scenario used by the distribution network power supply. S411 is performed when the core capacity obtained for the battery core capacity is less than or equal to the capacity threshold, and S412 is performed when the core capacity obtained for the battery core capacity is greater than the capacity threshold.

S411, generating alarm information of the excessively low battery capacity.

When the core capacity obtained from the core capacity of the battery is smaller than the capacity threshold, the capacity of the battery is determined to be too low, alarm information can be generated, the alarm information is sent to a remote centralized control master station through a communication unit, after the centralized control master station receives the alarm information, the address of a distribution network power supply with the too low capacity is determined, related information is generated and sent to operation and maintenance personnel, and the operation and maintenance personnel replace the battery at the distribution network power supply after receiving the information.

S412, calculating a capacity difference value between the preset standard capacity and the core capacity, and calculating a ratio of the capacity difference value to the standard capacity.

In this embodiment, the standard capacity may be a nominal capacity of the battery when the battery leaves the factory, and in general, after the battery is used for a period of time, the core capacity is smaller than the standard capacity, and a capacity difference between the standard capacity and the core capacity may be calculated, and a ratio of the capacity difference to the standard capacity may be calculated.

S413, calculating the product of the ratio and the interval length of the preset standard temperature range to obtain the temperature regulation amplitude.

The standard temperature range may be a preset temperature range set for the first time, typically, the range of the standard temperature range is the largest, and exemplary, the standard temperature range set when the battery leaves the factory is 15-35 ℃, the life cycle extending effect of the battery when the battery works in the temperature range is relatively good, the interval length of the standard temperature range of 15-35 ℃ can be calculated to be 20 ℃, the standard capacity is assumed to be 1000KWh, the nuclear capacity is assumed to be 800KWh, the ratio is (1000-800)/1000=0.2, and the temperature adjustment range is 0.2x20=4 ℃.

S414, reducing the preset temperature range by adopting the temperature regulation amplitude to obtain an updated preset temperature range.

Specifically, the preset temperature range can be subjected to bilateral reduction processing by adopting the temperature adjustment range, for example, the standard capacity of the battery is 1000Kwh, the ideal working environment temperature of the battery is 25 ℃, the preset temperature range is 15-35 ℃ when the battery leaves the factory and is not used, the temperature adjustment range is 4 ℃ through the nuclear capacity 800Kwh after six months of use, the preset temperature range is 15-35 ℃ and is subjected to bilateral reduction processing, the updated preset temperature range is 17-33 ℃, if the temperature adjustment range is 6 ℃ through the nuclear capacity 700Kwh after twelve months of use, the preset temperature range is subjected to bilateral reduction processing, namely, the preset temperature range is subjected to bilateral reduction 6 ℃ on the basis of the preset temperature range of 15-35 ℃ when the battery leaves the factory, the updated preset temperature range is 18-32 ℃, and the like, namely, the smaller nuclear capacity is the updated preset temperature range is smaller, namely, the battery capacity is increased along with the increase of the use, the preset temperature range triggering the working of the temperature adjustment device is smaller and smaller as the battery capacity is more easy to be more convenient to reduce the working cycle life cycle of the battery is more easily and the service cycle is more prolonged.

Of course, the preset temperature range is not updated after being updated to the set range, and the preset temperature range is not reduced when the preset temperature range is between 23 and 26 ℃ so as to avoid frequent work of the temperature regulating device caused by too narrow preset temperature range.

When the temperature of the battery compartment is out of the preset temperature range, the temperature regulating device is controlled to work, cold medium or heat medium is output to the battery compartment, the voltage and the current of the battery are collected, after the capacity prediction model is loaded under the nuclear capacity condition, the generated temperature curve, voltage curve and current curve are input into the capacity prediction model to obtain the predicted capacity of the battery, the confidence coefficient of the predicted capacity is calculated through the collected temperature, voltage and current, the predicted capacity is determined to be the nuclear capacity of the battery when the confidence coefficient is larger than the threshold value, on one hand, the nuclear capacity of the battery is set when the temperature regulating device is used as the nuclear capacity load, the special resistive load is not required to be added, the cost is reduced, the energy source of the distribution network power source can be fully utilized, the energy source utilization rate is improved, the influence of the temperature of the battery compartment, the voltage curve and the current curve of the battery is utilized, the influence of the battery on the battery is considered, the accuracy of the predicted capacity is improved, the life cycle of the distribution network power source can be accurately monitored, on the other hand, the life cycle of the battery can be ensured to be ensured within the preset temperature range, the service cycle of the distribution network can be prolonged, and the life cycle of the power source can be prolonged.

Further, when the core capacity is smaller than the capacity threshold, alarm information of the capacity which is too low is generated so as to monitor and alarm the life cycle of the battery, and therefore operation and maintenance personnel are prompted to replace the distribution network power supply with the too low capacity in time.

Furthermore, the preset temperature range can be reduced by the core capacity and the standard capacity, so that the battery can work in a more ideal temperature environment more easily after the capacity of the battery is reduced along with the increase of the working time, the capacity of the battery is reduced, and the life cycle level of the battery is improved.

Example III

Fig. 5 is a schematic structural diagram of an online nuclear capacity control device of a distribution network power supply according to a third embodiment of the present invention, where the distribution network power supply includes a battery compartment for accommodating a battery, a processor for taking electricity from the battery, a temperature adjusting device, a temperature sensor, and an electrical parameter sampling module, and a cooling and heating medium output channel of the temperature adjusting device is communicated with the battery compartment, as shown in fig. 5, where the online nuclear capacity control device of the distribution network power supply includes:

the temperature acquisition module 501 is used for acquiring the temperature in the battery compartment through a temperature sensor;

The temperature adjusting module 502 is configured to control the temperature adjusting device to work and output a cooling medium or a heating medium to the battery compartment when the temperature is outside a preset temperature range;

a voltage and current acquisition module 503, configured to acquire the voltage and current of the battery through an electrical parameter sampling module;

the capacity prediction module 504 is configured to load a capacity prediction model when a preset core capacity condition is satisfied, and input a voltage, a current and a temperature acquired during the operation of the temperature adjustment device into the capacity prediction model to obtain a predicted capacity of the battery;

a confidence calculating module 505, configured to calculate a confidence of the predicted capacity according to the temperature, the voltage, and the current acquired during the operation of the temperature adjustment device;

And a core capacity determining module 506, configured to determine the predicted capacity as the core capacity of the battery when the confidence coefficient is greater than a preset confidence coefficient threshold.

Optionally, the temperature adjustment module 502 includes:

the timing unit is used for starting a timer to count when the acquired temperature starts to be outside a preset temperature range so as to obtain timing duration;

the temperature judging unit is configured to judge whether the temperatures acquired in the timing duration are outside the preset temperature range, if yes, execute the cooling control unit or the heating control unit, and if not, return to the temperature acquisition module 501;

The cooling control unit is used for generating a cooling instruction and sending the cooling instruction to the temperature regulating device when the acquired temperatures are all greater than or equal to the upper limit temperature of the preset temperature range, and the temperature regulating device works and outputs a cooling medium to the battery compartment when receiving the cooling instruction;

And the heating control unit is used for generating a heating instruction and sending the heating instruction to the temperature regulating device when the acquired temperatures are smaller than or equal to the lower limit temperature of the preset temperature range, and the temperature regulating device works and outputs a heating medium to the battery compartment when receiving the heating instruction.

Optionally, the capacity prediction module 504 includes:

the kernel capacity condition judging unit is used for judging whether a preset kernel capacity condition is met or not, and if yes, the model loading unit is executed;

the model loading unit is used for acquiring the model of the distribution network power supply and loading model parameters matched with the model of the distribution network power supply so as to complete capacity prediction model loading;

The curve generating unit is used for generating a temperature curve, a voltage curve and a current curve respectively by adopting the temperature, the voltage and the current acquired during the working period of the temperature regulating device;

And the capacity prediction unit is used for inputting the temperature curve, the voltage curve and the current curve into a capacity prediction model to obtain the predicted capacity of the battery.

Optionally, the battery compartment includes more than two batteries connected in parallel, and the nuclear capacity condition judging unit is used for:

Judging whether a single cell supplies power to the temperature regulating device;

if so, acquiring the current voltage of the battery for power supply, and calculating the working time of the temperature regulating device, wherein the working time is the time for the temperature regulating device to regulate the temperature of the battery compartment to be within the preset temperature range;

calculating the interval duration from the last time of the core capacity to the current time;

and when the interval time length is larger than a first time length threshold value, the working time length is larger than a second time length threshold value and the current voltage is larger than a preset voltage threshold value, determining that a preset nuclear capacity condition is met.

Optionally, the capacity prediction model is trained by:

the training data acquisition module is used for acquiring training data sets of distribution network power supplies of various types, training samples in the training data sets are voltage curves, current curves and temperature curves of a battery compartment during the working period of the temperature regulating device when each distribution network power supply has different capacities and different temperatures, and each training sample marks a first capacity;

the model initialization module is used for initializing a capacity prediction model;

the training sample input module is used for inputting the training samples of the first-model distribution network power supply into the initialized capacity prediction model to obtain a second capacity;

a loss rate calculation module for calculating a loss rate using the first capacity and the second capacity;

The training condition judging module is used for judging whether the training condition is met, if yes, executing the training completion determining module, and if not, executing the model parameter adjusting module;

The model parameter adjustment module is used for adjusting model parameters of the capacity prediction model by adopting the loss rate and returning to the training sample input module;

The training completion determining module is used for determining that a capacity prediction model of the distribution network power supply of the first model is completed to train, storing model parameters of the capacity prediction model in association with the first model, deleting training samples of the distribution network power supply of the first model from the training dataset, and determining the trained capacity prediction model as an initialized capacity prediction model;

the model judging module is used for judging whether a training sample of the distribution network power supply of the second model exists in the training data set, if so, executing the first model updating module, and if not, executing the training ending module;

the first model updating module is used for determining the second model as the first model and returning to the training sample input module;

and the training ending module is used for determining capacity prediction models of all types of distribution network power supplies to finish training.

Optionally, the confidence calculating module 505 includes:

The working time length determining unit is used for determining the working time length of the temperature regulating device;

the temperature data calculation unit is used for calculating average temperature, highest temperature, lowest temperature and temperature fluctuation rate by adopting the temperature acquired during the working period of the temperature regulating device;

a temperature influence score calculating unit, configured to calculate a temperature influence score con_t of the temperature to the confidence coefficient according to a preset first formula, where the first formula is as follows:

；

Wherein t ₀ is the standard ambient temperature required by nuclear capacity, For average temperature, t _max is the highest temperature, t _min is the lowest temperature, t _rate is the temperature fluctuation rate, t _rate=2(t_max-t_min)/(t_max+t_min);

the voltage data calculation unit is used for determining the maximum voltage, the minimum voltage and the voltage fluctuation rate from the voltages acquired during the working period of the temperature regulating device;

a voltage influence score calculating unit, configured to calculate a voltage influence score con_u of the voltage to the confidence coefficient according to a preset second formula, where the second formula is as follows:

；

u ₀ is the standard voltage at full battery, u ₁ is the standard cut-off voltage at discharge at battery core capacity, u _max is the maximum voltage, u _min is the minimum voltage, u _rate is the voltage ripple rate, u _rate=2(u_max-u_min)/(u_max+u_min);

The current parameter calculation unit is used for calculating the current fluctuation rate by adopting the maximum current and the minimum current in the current acquired in the working period of the temperature regulating device;

A correlation coefficient calculation unit for calculating a pearson correlation coefficient of the acquired temperature and the acquired voltage;

the confidence calculating unit is configured to calculate the confidence of the predicted capacity by using the working time, the temperature influence score, the voltage influence score, the current fluctuation rate, the pearson correlation coefficient and a preset third formula, where the third formula is as follows:

；

Optionally, the method further comprises:

The core capacity judging module is used for judging whether the core capacity is smaller than a preset capacity threshold, if yes, executing the alarm information generating module, and if not, executing the ratio calculating module;

The alarm information generation module is used for generating alarm information with excessively low battery capacity;

The ratio calculating module is used for calculating a capacity difference value between a preset standard capacity and the nuclear capacity and calculating a ratio of the capacity difference value to the standard capacity;

The adjusting amplitude calculating module is used for calculating the product of the ratio and the interval length of a preset standard temperature range to obtain a temperature adjusting amplitude, wherein the preset standard temperature range is a temperature range set for the first time;

And the temperature range updating module is used for reducing the preset temperature range by adopting the temperature regulation amplitude to obtain an updated preset temperature range.

The on-line nuclear capacity control device for the distribution network power supply provided by the embodiment of the invention can execute the on-line nuclear capacity control method for the distribution network power supply provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 6 shows a schematic diagram of a distribution network power supply 60 that may be used to implement an embodiment of the present invention. The power supply of the distribution network comprises a battery compartment, a temperature sensor, a temperature regulating device, an electrical parameter sampling module and at least one processor 61, and a memory, such as a Read Only Memory (ROM) 62, a Random Access Memory (RAM) 63, etc., which is communicatively connected to the at least one processor 61, wherein the memory stores a computer program executable by the at least one processor, and the processor 61 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 62 or the computer program loaded from the storage unit 68 into the Random Access Memory (RAM) 63. In RAM 63, various programs and data required for operation of the distribution network power supply 60 may also be stored. The processor 61, the ROM 62 and the RAM 63 are connected to each other via a bus 64. An input/output (I/O) interface 65 is also connected to bus 64.

Various components in the distribution network power supply 60 are connected to the I/O interface 65, including: an input unit 66 such as a temperature sensor, an electrical parameter adoption module, etc.; an output unit 67 such as various types of displays, speakers, and the like; a storage unit 68 such as a memory card or the like; and a communication unit 69 such as a network card, modem, wireless communication transceiver, etc. The communication unit 69 allows the distribution network power supply 60 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Processor 61 can be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 61 performs the various methods and processes described above, such as the distribution network power on-line core capacity control method.

In some embodiments, the distribution network power on-line core volume control method may be implemented as a computer program tangibly embodied on a computer readable storage medium, such as storage unit 68. In some embodiments, part or all of the computer program may be loaded and/or installed onto the distribution network power supply 60 via the ROM 62 and/or the communication unit 69. When the computer program is loaded into RAM 63 and executed by processor 61, one or more steps of the distribution network power on-line core capacity control method described above may be performed. Alternatively, in other embodiments, processor 61 may be configured to perform the distribution network power on-line core capacity control method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a distribution network power supply having: display devices (e.g., LCD (liquid crystal display)) for displaying information to a user, other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a centralized master), or that includes a middleware component (e.g., a server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The utility model provides a join in marriage net power supply and hold control method on line nuclear, its characterized in that joins in marriage net power supply includes the battery compartment that holds the battery, follow the treater that the battery got the electricity, temperature regulating device, temperature sensor and electric parameter sampling module, temperature regulating device's cold and hot medium output channel with the battery compartment intercommunication includes:

When the confidence coefficient is larger than a preset confidence coefficient threshold value, determining the predicted capacity as the nuclear capacity of the battery;

Loading a capacity prediction model when a preset nuclear capacity condition is met, and inputting the voltage, the current and the temperature acquired during the working period of the temperature regulating device into the capacity prediction model to obtain the predicted capacity of the battery, wherein the method comprises the following steps:

judging whether a preset nuclear capacity condition is met;

if yes, the model of the distribution network power supply is obtained, and model parameters matched with the model of the distribution network power supply are loaded to finish capacity prediction model loading;

The temperature, the voltage and the current acquired during the working period of the temperature regulating device are adopted to respectively generate a temperature curve, a voltage curve and a current curve;

inputting the temperature curve, the voltage curve and the current curve into a capacity prediction model to obtain the predicted capacity of the battery;

The battery compartment comprises more than two batteries connected in parallel, and the judgment of whether the preset nuclear capacity condition is met comprises the following steps:

Determining that a preset nuclear capacity condition is met when the interval time is greater than a first time threshold, the working time is greater than a second time threshold and the current voltage is greater than a preset voltage threshold;

calculating the confidence of the predicted capacity according to the temperature, the voltage and the current acquired during the working of the temperature regulating device, comprising:

determining the working time length of the temperature regulating device;

calculating average temperature, highest temperature, lowest temperature and temperature fluctuation rate by adopting the temperatures acquired during the working period of the temperature regulating device;

calculating a temperature influence fraction Con_t of the temperature on the confidence coefficient through a preset first formula, wherein the first formula is as follows:

；

Determining maximum voltage, minimum voltage and voltage fluctuation rate from the voltages acquired during the operation of the temperature regulating device;

Calculating a voltage influence fraction Con_u of the voltage to the confidence coefficient through a preset second formula, wherein the second formula is as follows:

；

calculating a current fluctuation rate by adopting the maximum current and the minimum current in the current acquired during the working period of the temperature regulating device;

Calculating a pearson correlation coefficient of the acquired temperature and the acquired voltage;

Calculating the confidence coefficient of the predicted capacity by adopting the working time length, the temperature influence fraction, the voltage influence fraction, the current fluctuation rate, the pearson correlation coefficient and a preset third formula, wherein the third formula is as follows:

；

2. The on-line nuclear capacity control method of a distribution network power supply according to claim 1, wherein when the temperature is out of a preset temperature range, controlling a temperature adjusting device to work and outputting a cooling medium or a heating medium to the battery compartment comprises:

when the acquired temperature starts to be outside a preset temperature range, starting a timer to count to obtain a count duration;

judging whether the temperatures acquired in the timing time are all outside the preset temperature range;

if not, returning to the step of collecting the temperature in the battery compartment through the temperature sensor;

if so, when the acquired temperatures are all greater than or equal to the upper limit temperature of the preset temperature range, generating a cooling instruction, and sending the cooling instruction to the temperature regulating device, wherein the temperature regulating device works and outputs a cooling medium to the battery compartment when receiving the cooling instruction;

when the acquired temperatures are smaller than or equal to the lower limit temperature of the preset temperature range, a heating instruction is generated and sent to the temperature regulating device, and the temperature regulating device works and outputs a heating medium to the battery compartment when receiving the heating instruction.

3. The online capacity control method of a distribution network power supply according to claim 1 or 2, wherein the capacity prediction model is trained by the following steps:

acquiring training data sets of distribution network power supplies of various types, wherein training samples in the training data sets are voltage curves, current curves and temperature curves of a battery compartment during the working period of a temperature regulating device of each distribution network power supply at different capacities and different temperatures, and each training sample marks a first capacity;

Initializing a capacity prediction model;

Inputting a training sample of the first type of distribution network power supply into the initialized capacity prediction model to obtain a second capacity;

calculating a loss rate using the first capacity and the second capacity;

Judging whether the training condition is met;

if not, the model parameters of the capacity prediction model are adjusted by adopting the loss rate, and a step of inputting training samples of the first model of distribution network power supply into the capacity prediction model is returned;

If yes, determining that the capacity prediction model of the first-model distribution network power supply is trained, storing model parameters of the capacity prediction model in association with the first model, deleting training samples of the first-model distribution network power supply from the training data set, and determining the trained capacity prediction model as an initialized capacity prediction model;

Judging whether a training sample of a second type of distribution network power supply exists in the training data set;

if yes, determining the second model as a first model, and returning to the step of inputting a training sample of the distribution network power supply of the first model into the initial capacity prediction model to obtain a second capacity;

if not, determining capacity prediction models of all types of distribution network power supplies to complete training.

4. The on-line core capacity control method of a distribution network power supply according to claim 1 or 2, wherein after determining the predicted capacity as the core capacity of the battery, further comprising:

judging whether the nuclear capacity is smaller than a preset capacity threshold value or not;

If yes, generating alarm information of the excessively low battery capacity;

If not, calculating a capacity difference value between a preset standard capacity and the nuclear capacity, and calculating a ratio of the capacity difference value to the standard capacity;

calculating the product of the ratio and the interval length of a preset standard temperature range to obtain a temperature regulation amplitude, wherein the preset standard temperature range is a temperature range set for the first time;

And adopting the temperature regulation amplitude to reduce the preset temperature range to obtain an updated preset temperature range.

5. The utility model provides a join in marriage online nuclear appearance controlling means of net power, its characterized in that joins in marriage net power include hold battery compartment, follow the battery gets electric treater, temperature regulating device, temperature sensor and electric parameter sampling module, temperature regulating device's cold and hot medium output channel with battery compartment intercommunication includes:

The core capacity determining module is used for determining the predicted capacity as the core capacity of the battery when the confidence coefficient is larger than a preset confidence coefficient threshold value;

The capacity prediction module includes:

the capacity prediction unit is used for inputting the temperature curve, the voltage curve and the current curve into a capacity prediction model to obtain the predicted capacity of the battery;

the battery compartment comprises more than two batteries connected in parallel, and the nuclear capacity condition judging unit is used for:

The confidence calculation module comprises:

；

6. A distribution network power supply, comprising:

the battery compartment is used for accommodating batteries;

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the distribution network power on-line core capacity control method of any one of claims 1-4.

7. A computer readable storage medium storing computer instructions for causing a processor to implement the distribution network power supply online core capacity control method of any one of claims 1-4 when executed.