Battery endurance time determination method, device, equipment, medium and product

Abstract

The embodiment of the application provides a kind of battery endurance time determination method, device, equipment, medium and product, comprising: obtaining the initial endurance time of battery, initial endurance time includes the first endurance time determined based on battery parameter and the second endurance time determined based on base station power failure data;First endurance time and second endurance time are respectively corrected by based on endurance time correction model to obtain the first target endurance time and the second target endurance time after correction, and endurance time correction model is the neural network model obtained by multiple iteration training based on reference endurance time and the label endurance time corresponding to reference endurance time;Based on first target endurance time and second target endurance time, determine the target endurance time of battery.The embodiment of the application improves the accuracy of the endurance time of battery.

Description

Technical Field

[0001] This application belongs to the field of base station energy management technology, and in particular relates to a method, device, equipment, medium and product for determining the battery life. Background Technology

[0002] With the widespread use of storage batteries in daily life, they play a crucial role as an emergency backup for power supply systems. Therefore, accurately determining the battery's runtime to avoid service interruptions due to insufficient battery capacity is a pressing issue. However, the accuracy of determining battery runtime in existing technologies is relatively low. Summary of the Invention

[0003] This application provides a method, apparatus, device, medium, and product for determining the battery's runtime, which improves the accuracy of the calculated battery runtime.

[0004] In a first aspect, embodiments of this application provide a method for determining the battery's operating time, the method comprising:

[0005] The initial driving range of the battery is obtained, which includes a first driving range determined based on battery parameters and a second driving range determined based on power outage data.

[0006] The first and second battery life are corrected based on the battery life correction model to obtain the corrected first target battery life and second target battery life. The battery life correction model is a neural network model obtained by multiple iterations of training based on the reference battery life and the tag battery life corresponding to the reference battery life.

[0007] The target range of the battery is determined based on the first target range and the second target range.

[0008] In an optional implementation of the first aspect, determining the target driving range of the battery based on a first target driving range and a second target driving range includes:

[0009] The target battery range is obtained by weighting and summing the first target range and the second target range based on preset weights.

[0010] In one alternative implementation of the first aspect, obtaining the first battery life includes:

[0011] Obtain battery parameters, including battery capacity, number of battery banks, battery life, and base station load current;

[0012] Based on the battery's service life, target service life coefficients corresponding to the battery's service life are selected from a preset mapping relationship;

[0013] The product of the battery capacity, the number of battery packs, and the target life coefficient is determined as the first value, and the product of the base station load current and the preset performance coefficient is determined as the second value.

[0014] The ratio of the first value to the second value is determined as the first battery life.

[0015] In one alternative implementation of the first aspect,

[0016] The second battery life includes wireless battery life and transmission battery life; obtaining the second battery life includes:

[0017] Acquire power outage data, which includes N service outage times, Q transmission alarm times, and M power outage times;

[0018] The wireless battery life is determined based on the N outage times and the M power outage times;

[0019] The transmission duration is determined based on the Q transmission alarm times and the M power outage times.

[0020] In one alternative implementation of the first aspect,

[0021] Based on the N outage times and the M power outage times, the wireless battery life is determined, including:

[0022] From the M power outage times, select the first power outage time that is closest to the target service termination time. The first power outage time is earlier than the target service termination time. The target service termination time is any one of the M power outage times.

[0023] The difference between the target service outage time and the first power outage time is determined as the first time difference, and N first time differences are obtained;

[0024] The first time difference among the N first time differences that satisfies the first preset condition is determined as the wireless battery life.

[0025] In one alternative implementation of the first aspect,

[0026] The determination of transmission endurance based on the Q transmission alarm times and the M power outage times includes:

[0027] From the M power outage times, select the second power outage time that is closest to the target transmission alarm time. The second power outage time is earlier than the target transmission alarm time. The target transmission alarm time is any one of the Q transmission alarm times.

[0028] The difference between the target transmission alarm time and the second power outage time is determined as the second time difference, and Q second time differences are obtained;

[0029] The time difference among the Q second time differences that satisfies the second preset condition is determined as the transmission duration.

[0030] Secondly, embodiments of this application provide a battery range determination device, which includes: an acquisition module for acquiring an initial battery range, the initial battery range including a first battery range determined based on battery parameters and a second battery range determined based on power outage data; a correction module for correcting the first battery range and the second battery range based on a battery range correction model to obtain a corrected first target battery range and a second target battery range, the battery range correction model being a neural network model obtained through multiple iterations of training based on a reference battery range and a tag battery range corresponding to the reference battery range; and a determination module for determining a target battery range based on the first target battery range and the second target battery range.

[0031] Thirdly, an electronic device is provided, comprising: a memory for storing computer program instructions; and a processor for reading and running the computer program instructions stored in the memory to execute a battery duration determination method provided in any optional embodiment of the first aspect.

[0032] Fourthly, a computer storage medium is provided, on which computer program instructions are stored, wherein when the computer program instructions are executed by a processor, the battery life determination method provided by any optional embodiment of the first aspect is implemented.

[0033] Fifthly, a computer program product is provided, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to execute a battery life determination method provided by any optional embodiment of the first aspect.

[0034] In this embodiment, an initial driving range can be obtained, including a first driving range determined based on battery parameters and a second driving range determined based on power outage data. Then, the first driving range and the second driving range are corrected based on a driving range correction model to obtain a corrected first target driving range and a corrected second target driving range. Since the driving range correction model is a neural network model obtained through multiple iterations based on a reference driving range and the tag driving range corresponding to the reference driving range, the corrected first target driving range and the second target driving range are more accurate than the first driving range and the second target driving range. Thus, the target driving range of the battery can be accurately determined based on the first target driving range and the second target driving range, thereby improving the accuracy of the target driving range of the battery. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating a method for determining the battery life according to an embodiment of this application.

[0037] Figure 2 This is a schematic diagram of a discriminator network structure provided in an embodiment of this application;

[0038] Figure 3 This is a schematic diagram of a discriminator training process provided in an embodiment of this application;

[0039] Figure 4 This is a schematic diagram of a generator network structure provided in an embodiment of this application;

[0040] Figure 5 This is a schematic diagram of a generator training process provided in an embodiment of this application;

[0041] Figure 6 This is a schematic diagram of a battery range determination device provided in an embodiment of this application;

[0042] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0043] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0044] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0045] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0046] In real life, with the widespread use of storage batteries, they play an extremely important role as an emergency backup for power supply systems. Therefore, how to accurately determine the battery's operating time to avoid business interruptions due to insufficient battery capacity is an urgent problem to be solved.

[0047] To address the aforementioned issues, existing technologies employ one method: calculating battery range using a specific formula, such as: Range = Battery Voltage × Battery Capacity × Battery Discharge Coefficient × Inverter Conversion Efficiency ÷ Base Station Power. However, this formula uses a customized base station power and assumes the battery is in an ideal state. Furthermore, in practical applications, battery voltage, capacity, discharge coefficient, and inverter efficiency are related to battery aging, and the inverter's conversion efficiency is related to the age of the inverter. Consequently, the accuracy of battery range calculations in existing technologies is relatively low.

[0048] The second existing method assesses battery range by calculating the difference between the power outage alarm time and the service failure alarm time. However, this method relies on a single criterion, resulting in low accuracy in calculating battery range.

[0049] In summary, to address the issue of low accuracy in determining battery range in existing technologies, this application provides a method, apparatus, device, medium, and product for determining battery range. This method acquires an initial range including a first range determined based on battery parameters and a second range determined based on power outage data. Then, it corrects the first and second ranges using a range correction model to obtain corrected first and second target ranges. Since the range correction model is a neural network model obtained through multiple iterations of a reference range and the corresponding tag range, the corrected first and second target ranges are more accurate than the original first and second target ranges. Therefore, the target range of the battery can be accurately determined based on the first and second target ranges, thereby improving the accuracy of the target battery range.

[0050] The battery range determination method provided in this application can be executed by a battery range determination device or a control module within the battery range determination device for executing the battery range determination method. This application uses the execution of the battery range determination method by a battery range determination device as an example to illustrate the battery range determination method provided in this application.

[0051] The method for determining the battery's runtime provided in this application embodiment will be described in detail with reference to the following figure.

[0052] Figure 1 This is a flowchart illustrating a method for determining the battery life provided in an embodiment of this application.

[0053] like Figure 1 As shown, the execution subject of this method for determining the battery's driving range can be a battery driving range determination device, and the method may specifically include the following steps:

[0054] S110, obtain the initial battery life.

[0055] In some embodiments, the initial battery life may include a first battery life determined based on battery parameters and a second battery life determined based on power outage data. The battery parameters may be parameters of the battery itself, such as current and voltage, and are not specifically limited here. The power outage data may be relevant data generated by the base station when a power outage occurs due to insufficient battery capacity in the event of a mains power outage alarm.

[0056] Specifically, the battery runtime determination device can, after calculating the battery runtime, obtain a first runtime based on battery parameters and a second runtime based on power outage data. This takes into account both the battery's own influence on runtime and the possibility of base station power outages, allowing for accurate subsequent calculations of the battery runtime.

[0057] S120, based on the battery life correction model, corrects the first battery life and the second battery life respectively to obtain the corrected first target battery life and the second target battery life.

[0058] In some embodiments, the battery life correction model is a neural network model obtained through multiple iterations of training based on a reference battery life and the corresponding tag battery life. The accuracy of the tag battery life is greater than that of the reference battery life.

[0059] Specifically, after obtaining the initial driving range of the battery, the battery driving range determination device can input the first driving range and the second driving range included in the initial driving range into the driving range correction model, and then perform correction processing on the first driving range and the second driving range through the driving range correction model to obtain the corrected first target driving range and the second target driving range.

[0060] Since the initial battery life obtained is determined based on the battery parameters acquired at the current moment and power outage data within a preset time period, there may be inaccuracies in the calculation. However, the battery life correction model is a neural network model obtained through multiple iterations of training based on the reference battery life and the tag battery life corresponding to the reference battery life. Therefore, this model can correct the first and second battery life obtained to avoid the impact of other factors such as poor operating environment, faults, and abnormal business volume on the battery's battery life.

[0061] S130 determines the target range of the battery based on the first target range and the second target range.

[0062] After obtaining the first target driving range and the second target driving range, the battery driving range determination device can determine the target driving range of the battery based on the more accurate first target driving range and the second target driving range obtained after correction by the driving range correction model.

[0063] In this embodiment, an initial driving range can be obtained, including a first driving range determined based on battery parameters and a second driving range determined based on power outage data. Then, the first driving range and the second driving range are corrected based on a driving range correction model to obtain a corrected first target driving range and a corrected second target driving range. Since the driving range correction model is a neural network model obtained through multiple iterations based on a reference driving range and the tag driving range corresponding to the reference driving range, the corrected first target driving range and the second target driving range are more accurate than the first driving range and the second target driving range. Thus, the target driving range of the battery can be accurately determined based on the first target driving range and the second target driving range, thereby improving the accuracy of the target driving range of the battery.

[0064] In order to accurately and comprehensively describe the battery range determination method provided in the embodiments of this application, in one embodiment, the above-mentioned S130 may include the following steps:

[0065] The target battery range is obtained by weighting and summing the first target range and the second target range based on preset weights.

[0066] The preset weights can be weights pre-set based on actual conditions or experience values, and no specific restrictions are imposed here.

[0067] Specifically, the battery range determination device can, after obtaining the first target range and the second target range, perform a weighted sum of the first target range and the second target range based on a preset weight to obtain the target range of the battery.

[0068] In one example, assume the first target range is T1 and the second target range is T2, with a preset weight of h1 for the first target range and h2 for the second target range. Based on this, the target range of the battery = h1T1 + h2T2.

[0069] It should be noted that the preset weights mentioned above can also be updated and adjusted based on the first target battery life and the second target battery life output by the battery life correction model over a historical period.

[0070] In this embodiment, the battery life determination device can perform a weighted sum of the first target battery life and the second target battery life based on preset weights to obtain the target battery life. This not only considers the impact of the battery itself on the battery life but also takes into account the situation of base station power outages, thereby accurately calculating the battery life and improving the accuracy of the battery life calculation.

[0071] Since the initial driving range may include a first driving range, in order to accurately obtain the first driving range so that the target driving range of the battery can be accurately calculated subsequently, in one embodiment, the steps involved in obtaining the first driving range may specifically include the following steps:

[0072] Obtain battery parameters, including battery capacity, number of battery banks, battery life, and base station load current;

[0073] Based on the battery's service life, the service life coefficient corresponding to the battery's service life is selected from the preset mapping relationship;

[0074] The product of the battery capacity, the number of battery packs, and the age coefficient is determined as the first value, and the product of the base station load current and the preset performance coefficient is determined as the second value.

[0075] The ratio of the first value to the second value is determined as the first battery life.

[0076] Specifically, the battery endurance determination device can obtain battery parameters and, based on the battery service life included in the battery parameters, filter out the target service life coefficient corresponding to the battery service life from a preset mapping relationship. Then, it can determine the product of the battery capacity, the number of battery packs, and the aforementioned target service life coefficient as a first value, and determine the product of the base station load current and the preset performance coefficient as a second value. Then, it can determine the ratio of the first value to the second value as the first endurance time.

[0077] The battery's service life can be the difference between the current time and the battery's grid connection time. The preset performance parameters can be based on the battery's performance parameters, such as the ratio of the battery's safety factor to its discharge coefficient. In this embodiment, the preset performance parameters can be empirical values; for example, the preset performance parameter could be 1.6, without further specific limitations.

[0078] In some embodiments, the preset mapping relationship mentioned above may be a preset correspondence between the battery's service life and a service life coefficient. This preset mapping relationship may be a coefficient preset based on actual experience or circumstances, or it may be obtained by continuously updating and adjusting the preset mapping relationship based on actual experience based on the first target service life output by the service life correction model over a historical period.

[0079] Based on this, in one example, the aforementioned preset mapping relationship could be: battery life greater than 6 years, life coefficient 0.2; battery life equal to 6 years, life coefficient 0.4; battery life less than 6 years but greater than or equal to 5 years, life coefficient 0.45; battery life less than 5 years but greater than or equal to 4 years, life coefficient 0.5; battery life less than 4 years but greater than or equal to 3 years, life coefficient 0.6; battery life less than 3 years but greater than or equal to 2 years, life coefficient 0.7; battery life less than 2 years but greater than or equal to 1 year, life coefficient 0.8; battery life less than 1 year but greater than or equal to 0.5 years, life coefficient 0.9; battery life less than 0.5 years but greater than or equal to 0, life coefficient 1.

[0080] It should be noted that since a base station may include multiple switching power supplies, the battery life determination device can query and obtain the load current of each switching power supply included in the base station, and determine the sum of the maximum load currents of the multiple switching power supplies as the base station load current.

[0081] In this embodiment, the battery range determination device can introduce an age coefficient and a preset performance coefficient during the calculation of the first range based on battery parameters. Considering battery aging, it can also replace the base station power in the prior art with the base station load current. In this way, the first battery range can be accurately calculated, which facilitates the subsequent accurate calculation of the target battery range.

[0082] In addition, since the initial battery life mentioned above may include a second battery life, and this second battery life may include wireless battery life and transmission battery life, in order to accurately obtain the second battery life, in one embodiment, the step of obtaining the second battery life may specifically include the following steps:

[0083] Acquire power outage data, which includes N service outage times, Q transmission alarm times, and M power outage times;

[0084] The wireless battery life is determined based on the N outage times and the M power outage times;

[0085] The transmission duration is determined based on the Q transmission alarm times and the M power outage times.

[0086] The outage time can be the time when a base station or other wireless device goes out of service. The transmission alarm time can be the time when a transmission device is unable to transmit due to a power outage. The power outage time can refer to the duration of a mains power outage.

[0087] Specifically, the battery life determination device can determine the wireless battery life based on N outage times and M outage times included in the power outage data, and determine the transmission battery life based on Q transmission alarm times and M outage times included in the power outage data.

[0088] It should be noted that since the second battery life can include wireless battery life and transmission battery life, the battery life determination device can also input the first battery life and the wireless battery life and transmission battery life included in the second battery life into the battery life correction model for correction, and perform weighted summation based on the correction results and preset weights to obtain the target battery life.

[0089] In this embodiment, the battery life determination device can treat the base station's wireless communication and transmission as a whole. If any part loses power, the base station is considered to be no longer working. Therefore, the device can determine the working time of the battery and other equipment such as the base station based on the service outage time, transmission alarm time, and power outage time, and thus determine the second battery life.

[0090] Therefore, in one embodiment, the step of determining the wireless battery life based on the N outage times and the M power outage times mentioned above may specifically include the following steps:

[0091] From the M power outage times, select the first power outage time that is closest to the target service termination time. The first power outage time is earlier than the target service termination time. The target service termination time is any one of the M power outage times.

[0092] The difference between the target service outage time and the first power outage time is determined as the first time difference, and N first time differences are obtained;

[0093] The first time difference among the N first time differences that satisfies the first preset condition is determined as the wireless battery life.

[0094] The first preset condition can be a condition set in advance based on actual experience or circumstances. For example, the first preset condition can be the smallest first time difference selected from N first time differences, or it can be the largest first time difference. No specific limitation is made here.

[0095] Specifically, the battery life determination device can filter out the first power outage time closest to the target shutdown time from M power outage times, and the first power outage time is earlier than the target shutdown time. The target shutdown time is any one of the M power outage times. Then, the difference between the target shutdown time and the first power outage time can be determined as the first time difference value. N first time differences are obtained, and then the first time difference value that meets the first preset condition among the N time differences can be determined as the wireless battery life.

[0096] In one example, the battery life determination device can obtain N wireless outage alarm data from the network optimization system. Each wireless outage alarm data may include the base station, equipment room, and outage time. Based on this, the battery life determination device can query the nearest mains power outage time based on the outage time, calculate the time difference between the two, and thus obtain N time differences. The device can then select the smallest time difference as the wireless outage endurance.

[0097] In addition, the battery life determination device can query the nearest mains power outage time based on the outage time. It can filter out the nearest mains power outage time from a first preset time to ensure that the outage of the reference or other wireless devices is caused by insufficient battery life. The first preset time can be preset based on actual experience or circumstances, and is the normal duration for which the battery can maintain power supply.

[0098] In this embodiment, the wireless battery life can be accurately obtained by calculating the first time difference between each of the N outage times and the nearest power outage time, and selecting the first time difference that meets the first preset condition as the wireless battery life.

[0099] In another embodiment, the step of determining the transmission duration based on the Q transmission alarm times and the M power outage times mentioned above may specifically include the following steps:

[0100] From the M power outage times, select the second power outage time that is closest to the target transmission alarm time. The second power outage time is earlier than the target transmission alarm time. The target transmission alarm time is any one of the Q transmission alarm times.

[0101] The difference between the target transmission alarm time and the second power outage time is determined as the second time difference, and Q second time differences are obtained;

[0102] The time difference among the Q second time differences that satisfies the second preset condition is determined as the transmission duration.

[0103] The second preset condition can be a condition preset based on actual experience or circumstances, similar to the first preset condition, and is not specifically limited here.

[0104] Specifically, the battery life determination device can filter out the second power outage time closest to the target transmission alarm time from M power outage times, and the second power outage time is earlier than the target transmission alarm time. The target transmission alarm time can be any one of the Q transmission alarm times. Then, the difference between the target transmission alarm time and the second power outage time can be determined as the second time difference, resulting in Q second time differences. The device can then determine the second time difference among the Q second time differences that meets the second preset condition as the transmission life.

[0105] In one example, the battery life determination device can obtain Q transmission LOS alarm data from the faulty system. Since each transmission LOS alarm data includes the base station, the equipment room, and the transmission alarm time, it can query the nearest historical power outage time based on the transmission alarm time. Then, it can calculate the time difference between the transmission alarm time and the historical power outage time to obtain multiple time differences between the transmission alarm time and the historical power outage time, and select the smallest time difference as the transmission life.

[0106] In addition, the battery life determination device can query the power outage time closest to the transmission alarm time based on the transmission alarm time. It can filter out the power outage time closest to the transmission alarm time from a first preset time to ensure that the base station transmission is caused by insufficient battery life. The first preset time can be preset based on actual experience or circumstances, and is the normal duration for which the battery can maintain power supply.

[0107] In this embodiment, the transmission duration can be accurately obtained by calculating the second time difference between each of the Q transmission alarm times and the nearest power outage time, and selecting the second time difference that meets the second preset condition as the transmission duration.

[0108] Based on the battery range determination method provided in the embodiments of this application, it should also be noted that the range correction model provided in the embodiments of this application can be a model trained based on a deep generative adversarial network, and its overall idea is: to use the adversarial mode of conditional GAN ​​to continuously approximate the initial value of the range to the true value of the range, so that the network has the ability to accurately predict the battery range.

[0109] Therefore, it should also be noted that the deep generative adversarial network provided in this application embodiment may include a discriminator network and a generator network. Accordingly, it is necessary to first obtain training samples to train a battery life correction model, so that the input data can be corrected based on the trained battery life correction model to output the corrected battery life. Specifically, the deep generative adversarial network training method may include the following steps:

[0110] First, train the discriminator network, combining Figure 2 and Figure 3 This step may include the following steps:

[0111] (1) Cross-sample and randomly sample the first and second battery life included in the initial battery life, as well as the wireless and transmission battery life included in the second battery life, to obtain (x1, x2, x3...x n Given a vector of m-dimensional data that follows a Gaussian distribution, random sampling is performed to obtain (z1, z2, z3... z...). n );

[0112] (2) (z1, z2, z3...z) n Inputting the generator G of a deep generative adversarial network yields (x′1, x′2, x′3, ..., x′). n ).

[0113] (3) and (x1, x2, x3...x n The label positioning is 1, (x′1, x′2, x′3……x′) n The label is located at 0, and the discriminator D of the deep generative adversarial network is input.

[0114] (4) Gradient descent updates the parameters θ of the discriminator D. D The loss function to be minimized is L1, as shown in formula (1):

[0115]

[0116] Secondly, train the generator network, combining Figure 4 and Figure 5 This step may include the following steps:

[0117] (1) Resample the m-dimensional data that follows a Gaussian distribution to obtain (z1, z2, z3...z... n );

[0118] (2), will (z1, z2, z3...z n Inputting the generator G of the deep generative adversarial network yields (x′1, x′2, x′3, ..., x′). nVector data.

[0119] (3) Set (x′1, x′2, x′3, ..., x′...) n The label is set to 1, and the discriminator D of the deep generative adversarial network is input.

[0120] (4) Gradient descent updates the parameters θ of the generator G. G Minimize the loss function L2

[0121]

[0122] Furthermore, the training process of the discriminator network and the generator network is repeated until the loss function L1 of the discriminator D and the loss function L2 of the generator G converge.

[0123] After the network is trained, random sampling is performed on k-dimensional data that follows a Gaussian distribution to obtain (z1, z2, z3... z... n Input the trained generator G, forward propagation to obtain the generated battery life prediction samples, and update the prediction value to the latest battery life of the base station.

[0124] Finally, by collecting data from 13 stations, the battery life determined by methods one and two in the prior art was compared with the battery life obtained by the method provided in this application embodiment, as shown in Table 1. It can be seen that the battery life determined by the battery life determination method provided in this application embodiment is more accurate.

[0125] Table 1

[0126]

[0127] It should be noted that this algorithm assumes that different groups of batteries at the same site have the same capacity and age, and does not consider cases where they are different; the preset performance coefficient requirement in the algorithm formula is configurable, with a default of 1.6; the daily calculation of various battery life measurements at the site needs to save historical records; the current algorithm does not consider cases where wireless or transmission is powered off in stages.

[0128] Based on the same inventive concept, embodiments of this application also provide a device for determining the battery's runtime. Specifically, in conjunction with... Figure 6 The battery life determination device provided in the embodiments of this application will be described in detail.

[0129] Figure 6 This is a schematic diagram of a battery range determination device provided in an embodiment of this application.

[0130] like Figure 6 As shown, the battery range determination device 600 may include: an acquisition module 610, a calibration module 620, and a determination module 630.

[0131] The acquisition module 610 is used to acquire the initial driving range of the battery. The initial driving range includes a first driving range determined based on battery parameters and a second driving range determined based on power outage data.

[0132] The correction module 620 is used to correct the first battery life and the second battery life based on the battery life correction model to obtain the corrected first target battery life and the second target battery life. The battery life correction model is a neural network model obtained by multiple iterations of training based on the reference battery life and the tag battery life corresponding to the reference battery life.

[0133] The determination module 630 is used to determine the target range of the battery based on the first target range and the second target range.

[0134] In one embodiment, the aforementioned battery-related battery life determination device may further include a weighted summation module.

[0135] The weighted summation module is used to perform a weighted summation of the first target range and the second target range based on preset weights to obtain the target range of the battery.

[0136] In one embodiment, the aforementioned battery range determination device may further include a screening module.

[0137] The acquisition module is also used to acquire battery parameters, including battery capacity, number of battery packs, battery life, and base station load current.

[0138] The filtering module is used to filter out target age coefficients corresponding to the battery's age from a preset mapping relationship based on the battery's service life.

[0139] The determination module is also used to determine the product of the battery capacity, the number of battery packs, and the target life coefficient as the first value, and to determine the product of the base station load current and the preset performance coefficient as the second value.

[0140] The determination module is also used to determine the ratio of the first value to the second value as the first battery life.

[0141] In one embodiment, the second battery life includes wireless battery life and transmission battery life.

[0142] The aforementioned acquisition module is also used to acquire power outage data, which includes N service outage times, Q transmission alarm times, and M power outage times.

[0143] The determining module is also used to determine the wireless battery life based on the N outage times and the M power outage times.

[0144] The determination module is also used to determine the transmission duration based on the Q transmission alarm times and the M power outage times.

[0145] In one embodiment, the filtering module is used to filter out the first power outage time that is closest to the target service termination time from the M power outage times, wherein the first power outage time is earlier than the target service termination time, and the target service termination time is any one of the M power outage times;

[0146] The determination module is used to determine the difference between the target service outage time and the first power outage time, which is the first time difference, and to obtain N first time differences;

[0147] The determining module is further configured to determine the wireless battery life as the first time difference among the N first time differences that satisfies a first preset condition. In one embodiment, the filtering module is configured to filter out the second power outage time closest to the target transmission alarm time from the M power outage times, wherein the second power outage time is earlier than the target transmission alarm time, and the target transmission alarm time is any one of the Q transmission alarm times;

[0148] The determining module is further configured to determine the difference between the target transmission alarm time and the second power outage time as a second time difference, and obtain Q second time differences;

[0149] The determining module is also used to determine the transmission duration as the time difference among the Q second time differences that satisfies the second preset condition.

[0150] In this embodiment, an initial driving range can be obtained, including a first driving range determined based on battery parameters and a second driving range determined based on power outage data. Then, the first driving range and the second driving range are corrected based on a driving range correction model to obtain a corrected first target driving range and a corrected second target driving range. Since the driving range correction model is a neural network model obtained through multiple iterations based on a reference driving range and the tag driving range corresponding to the reference driving range, the corrected first target driving range and the second target driving range are more accurate than the first driving range and the second target driving range. Thus, the target driving range of the battery can be accurately determined based on the first target driving range and the second target driving range, thereby improving the accuracy of the target driving range of the battery.

[0151] The various modules in the battery life determination device provided in this application embodiment can achieve... Figure 1The method steps of the illustrated embodiment, and the corresponding technical effects they achieve, will not be described in detail here for the sake of brevity.

[0152] Figure 7 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0153] An electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0154] Specifically, the processor 701 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0155] Memory 702 may include mass storage for data or instructions. For example, and not limitingly, memory 702 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 702 may include removable or non-removable (or fixed) media. Where appropriate, memory 702 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 702 is non-volatile solid-state memory.

[0156] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0157] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement any of the battery life determination methods in the above embodiments.

[0158] In one example, the electronic device may also include a communication interface 703 and a bus 710. For example, Figure 7 As shown, the processor 701, memory 702, and communication interface 703 are connected through bus 710 and complete communication with each other.

[0159] The communication interface 703 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0160] Bus 710 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 710 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0161] In addition, in conjunction with the battery life determination method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the battery life determination method provided in this application embodiment.

[0162] This application also provides a computer program product, in which instructions are executed by the processor of an electronic device, causing the electronic device to perform the scientific and technological innovation achievement evaluation method provided in this application.

[0163] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0164] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0165] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0166] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable battery endurance determining device to produce a machine such that these instructions, executed via the processor of the computer or other programmable battery endurance determining device, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0167] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining the driving range of a storage battery, characterized in that, The method includes: The initial driving range of the battery is obtained, which includes a first driving range determined based on battery parameters and a second driving range determined based on power outage data. The first and second battery life are corrected based on the battery life correction model to obtain the corrected first target battery life and second target battery life. The battery life correction model is a neural network model obtained through multiple iterations of training based on a reference battery life and a tag battery life corresponding to the reference battery life. The accuracy of the tag battery life is greater than that of the reference battery life. The reference battery life is used to represent the initial value of the battery life, and the tag battery life is used to represent the true value of the battery life. The target battery life is determined based on the first target battery life and the second target battery life.

2. The method according to claim 1, characterized in that, Determining the target driving range of the battery based on the first target driving range and the second target driving range includes: The first target battery life and the second target battery life are weighted and summed based on preset weights to obtain the target battery life.

3. The method according to claim 1, characterized in that, Obtaining the first battery life includes: Obtain battery parameters, including battery capacity, number of battery banks, battery service life, and base station load current; Based on the battery's service life, a target service life coefficient corresponding to the battery's service life is selected from a preset mapping relationship; The product of the battery capacity, the number of battery packs, and the target life coefficient is determined as a first value, and the product of the base station load current and the preset performance coefficient is determined as a second value; the preset performance coefficient is a coefficient set based on the battery performance parameters. The ratio of the first value to the second value is determined as the first battery life.

4. The method according to claim 1, characterized in that, The second battery life includes wireless battery life and transmission battery life; To obtain the second battery life, the following is included: Acquire power outage data, which includes N service outage times, Q transmission alarm times, and M power outage times; The wireless battery life is determined based on the N outage times and the M power outage times; The transmission duration is determined based on the Q transmission alarm times and the M power outage times.

5. The method according to claim 4, characterized in that, The determination of wireless battery life based on the N outage times and the M power outage times includes: From the M power outage times, select the first power outage time that is closest to the target service termination time. The first power outage time is earlier than the target service termination time. The target service termination time is any one of the M power outage times. The difference between the target service outage time and the first power outage time is determined as the first time difference, and N first time differences are obtained; The first time difference among the N first time differences that satisfies the first preset condition is determined as the wireless battery life.

6. The method according to claim 4, characterized in that, The determination of transmission endurance based on the Q transmission alarm times and the M power outage times includes: From the M power outage times, select the second power outage time that is closest to the target transmission alarm time. The second power outage time is earlier than the target transmission alarm time. The target transmission alarm time is any one of the Q transmission alarm times. The difference between the target transmission alarm time and the second power outage time is determined as the second time difference, and Q second time differences are obtained; The time difference among the Q second time differences that satisfies the second preset condition is determined as the transmission duration.

7. A device for determining the driving time of a storage battery, characterized in that, The device includes: The acquisition module is used to acquire the initial driving range of the battery, which includes a first driving range determined based on battery parameters and a second driving range determined based on power outage data. A correction module is used to correct the first battery life and the second battery life based on a battery life correction model to obtain a corrected first target battery life and a second target battery life. The battery life correction model is a neural network model obtained through multiple iterations of training based on a reference battery life and a labeled battery life corresponding to the reference battery life. The accuracy of the labeled battery life is greater than that of the reference battery life, and the reference battery life is used to represent the initial value of the battery life, while the labeled battery life is used to represent the true value of the battery life. The determination module is used to determine the target battery life based on the first target battery life and the second target battery life.

8. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the battery life determination method as described in any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the battery life determination method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the battery life determination method as described in any one of claims 1-6.

Images