Wireless battery management system and method

Abstract

The present disclosure relates to a battery data management system and method. The technical problem to be solved is to present a mechanism capable of dramatically improving the performance, safety, and efficiency of an xEV. To this end, the present disclosure provides a configuration for collecting data related to a network environment of a wireless battery, storing the data in a memory, and optimizing a dynamic network topology of the wireless battery through analysis of data based on artificial intelligence (AI).

Description

Wireless battery management system and method

[0001] The present disclosure relates to a wireless battery management system and method.

[0002] xEVs, encompassing electric vehicles (EVs), hybrid electric vehicles (HEVs), and plug-in hybrid electric vehicles (PHEVs), represent a rapidly growing sector in the Hyundai automotive industry and are attracting attention as a key solution for addressing environmental issues and improving energy efficiency. Battery systems, a core component of these vehicles, are a critical factor in determining performance, driving range, and safety.

[0003] The Battery Management System (BMS) is responsible for the efficient operation and monitoring of the battery system, measuring and controlling the voltage, current, and temperature of individual cells in real time. While traditional BMSs have utilized wired communication methods, Wireless BMSs are gaining attention due to recent advancements in wireless technology. Wireless BMSs offer advantages such as reduced weight by minimizing complex wiring within the battery pack, easier maintenance, and increased design flexibility.

[0004] The information described above disclosed in the background technology of this invention is intended only to enhance understanding of the background of the present invention and may therefore include information that does not constitute prior art.

[0005] However, challenges remain, such as ensuring reliability in wireless communication environments, addressing electromagnetic interference (EMI), and real-time data processing. Furthermore, dynamic response capabilities to various driving conditions and changes in battery status are required for xEVs, playing a crucial role in optimizing battery life and performance.

[0006] Therefore, there is an increasing need for advanced optimization and adaptive management systems utilizing AI technology, which is recognized as a key factor in improving the overall performance of xEVs and strengthening their market competitiveness.

[0007] The purpose of the present invention is to provide a wireless battery management system and method that can dramatically improve the performance, safety, and efficiency of an xEV.

[0008] However, the technical problems that the present invention aims to solve are not limited to those described above, and other unmentioned problems can be clearly understood by those skilled in the art from the description of the invention below.

[0009] A wireless battery management system according to an embodiment of the present invention for solving the above technical problem is characterized by comprising: a memory; and a master controller that collects data related to the network environment of a wireless battery, stores it in the memory, and optimizes the dynamic network topology of the wireless battery through analysis of the data based on AI (Artificial Intelligence).

[0010] The above data may include at least one of RSSI (Received Signal Strength Indicator), PDR (Pedestrian Dead Reckoning), network delay, and EMI (Electromagnetic Interference) level.

[0011] The above master controller can optimize the dynamic network topology of the wireless battery by dynamically reconfiguring the network structure by further considering external factor data including at least one of vehicle vibration, temperature change, and ambient electromagnetic environment.

[0012] The master controller can collect data from each node within the network topology of the wireless battery at regular intervals, and remove noise by normalizing the collected data and applying a moving average filter.

[0013] The master controller can evaluate the network status of the wireless battery based on the data, and predict the optimal network configuration based on the evaluation result of the network status to determine a change in the network topology of the wireless battery.

[0014] The master controller can determine a Q-table based on the network status of the wireless battery and determine an active path and a standby path based on the Q-table using an epsilon-greedy algorithm.

[0015] The above master controller can reduce communication errors caused by EMI by learning and predicting EMI patterns based on AI to select the optimal frequency and modulation method, and by monitoring EMI intensity and adjusting communication parameters.

[0016] The above master controller can determine a Q table based on the network status of the wireless battery and determine a frequency changing channel based on the Q table using an epsilon-greedy algorithm.

[0017] The master controller can reduce the power consumption of the Battery Management System (BMS) by dynamically adjusting the optimal power level for the RF antenna output through the analysis of at least one of the data among the battery status, communication requirements, and surrounding environment of each node within the topology based on the AI.

[0018] A wireless battery management method according to one embodiment of the present invention is characterized by comprising: a step in which a master controller collects data related to the network environment of a wireless battery and stores it in memory; and a step in which the master controller optimizes the dynamic network topology of the wireless battery through analysis of the data based on AI.

[0019] According to the present invention, communication efficiency is significantly improved, stable performance can be maintained even under various driving conditions, and communication stability can be guaranteed by dynamically reconfiguring the network structure by considering various external factors such as vehicle vibration, temperature changes, and the surrounding electromagnetic environment.

[0020] In addition, according to the present invention, the communication error rate caused by EMI can be significantly reduced, and stable communication can be maintained even in a high-voltage environment by monitoring the EMI intensity in real time and immediately adjusting communication parameters accordingly.

[0021] In addition, according to the present invention, data processing delay can be significantly reduced and real-time control accuracy improved, important information can be rapidly transmitted through a priority-based data processing algorithm, and overall system responsiveness can be improved through a function that predicts and avoids network congestion.

[0022] In addition, according to the present invention, power consumption of the BMS can be reduced and unnecessary power consumption can be prevented in advance through the prediction of usage patterns, and the applicability to various xEV models can be significantly improved.

[0023] In addition, according to the present invention, network configurations can be flexibly changed by utilizing software-defined networking (SDN) technology, and continuous performance improvement can be enabled through cloud-based updates.

[0024] However, the effects obtainable through the present invention are not limited to those described above, and other unmentioned technical effects will be clearly understood by those skilled in the art from the description of the invention below.

[0025] The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention provided below; therefore, the present invention should not be interpreted as being limited only to the matters described in such drawings.

[0026] FIG. 1 illustrates a block diagram of a wireless battery management system according to one embodiment of the present invention.

[0027] Figures 2 and 3 illustrate example diagrams for explaining the xEX wireless BMS network structure and dynamic topology changes.

[0028] FIGS. 4 and FIGS. 5 illustrate a flowchart of a wireless battery management method according to an embodiment of the present invention.

[0029] Preferred embodiments of the present invention will be described in detail below with reference to the attached drawings. Prior to this, terms and words used in this specification and claims should not be interpreted as being limited to their ordinary or dictionary meanings. Instead, based on the principle that the inventor may appropriately define the concepts of terms to best describe his invention, they should be interpreted in a meaning and concept consistent with the technical spirit of the present invention. Therefore, it should be understood that the embodiments described in this specification and the configurations illustrated in the drawings are merely some of the most preferred embodiments of the present invention and do not represent all of the technical spirit of the present invention; thus, various equivalents and modifications that can replace them may exist at the time of filing this application. Furthermore, as used in this specification, "comprise" or "include" and / or "comprising" or "including" specify the presence of the mentioned features, numbers, steps, actions, parts, elements, and / or groups thereof, and do not exclude the presence or addition of one or more other features, numbers, actions, parts, elements, and / or groups. In addition, when describing embodiments of the present invention, "may" and "may be" may include "one or more embodiments of the present invention."

[0030] Additionally, to aid in understanding the invention, the attached drawings are not drawn to actual scale, and the dimensions of some components may be exaggerated. Furthermore, the same reference numerals may be assigned to identical components in different embodiments.

[0031] The statement that two subjects of comparison are 'identical' means that they are 'substantially identical.' Therefore, substantial identity may include deviations considered low in the industry, for example, deviations within 5%. Additionally, the statement that a parameter is uniform in a given area may mean that it is uniform from an average perspective.

[0032] Although terms such as "first," "second," etc., are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless specifically stated otherwise, the first component may also be the second component.

[0033] Throughout the specification, unless specifically stated otherwise, each component may be singular or plural.

[0034] The fact that any configuration is placed on the "upper (or lower)" of a component or on the "upper (or lower)" of a component may mean not only that any configuration is placed in contact with the upper (or lower) surface of said component, but also that another configuration may be interposed between said component and any configuration placed on (or below) said component.

[0035] Furthermore, where it is stated that one component is "connected," "coupled," or "connected" to another component, it should be understood that while said components may be directly connected or connected to each other, another component may be "interposed" between each component, or that each component may be "connected," "coupled," or "connected" through another component. Additionally, when it is stated that a part is electrically coupled with another part, this includes not only cases where they are directly connected but also cases where they are connected with another component in between.

[0036] Throughout the specification, "A and / or B" means A, B, or A and B unless specifically stated otherwise. That is, "and / or" includes any combination or any combination of the enumerated items. "C to D" means C or more and D or less, unless specifically stated otherwise.

[0037]

[0038] Before describing the embodiments thereof, the direction of improvement and the ultimate goal of the present invention are described.

[0039] Research and development have been conducted in various directions to improve existing Wireless BMS technology. First, the introduction of multipath routing and mesh network topologies has been proposed to enhance communication reliability; this can contribute to reducing the risk of failure in a single communication path and increasing the stability of the overall system.

[0040] Second, the adoption of low-power wireless protocols and adaptive power management techniques are being researched to optimize power consumption, which can play an important role in extending battery life.

[0041] Third, the development of frequency hopping technology and advanced signal processing algorithms is underway to address electromagnetic interference (EMI), which can improve communication stability in high-voltage and high-current environments.

[0042] Fourth, the introduction of advanced encryption technology and authentication mechanisms has been proposed to enhance data security, which can be important for protecting the system from external hacking threats.

[0043] Fifth, the introduction of machine learning-based predictive models is being researched for real-time performance optimization, and this can be utilized for predicting battery status and extending battery life.

[0044] Sixth, improvements in sensor technology are enabling the collection of more accurate and reliable battery data, which can contribute to enhancing the accuracy and efficiency of the entire system.

[0045] Finally, through standardization efforts, technological advancements are moving toward increasing compatibility among various manufacturers and models, which can promote the widespread application of technology and the development of the industry as a whole.

[0046] Meanwhile, the present invention aims to simultaneously solve several key technical challenges of the xEV Wireless BMS.

[0047] First, we aim to solve the problem of optimizing a highly adaptive network topology capable of responding in real-time to various driving environments and changes in battery status. This is intended to overcome the performance degradation and inefficiency caused by static network configurations.

[0048] Second, we aim to significantly improve the stability and reliability of wireless communication by resolving serious electromagnetic interference (EMI) issues that occur in high-voltage and high-current environments.

[0049] Third, we aim to improve the accuracy of real-time data processing and control by minimizing communication delays and packet loss issues occurring in the complex wireless network within the battery pack.

[0050] Fourth, we aim to optimize the overall energy consumption of xEVs by addressing the issue of improving the energy efficiency of the battery management system.

[0051] Fifth, we aim to solve the problem of scalable system design that can be flexibly applied to various battery configurations and vehicle models.

[0052] Sixth, we aim to improve the accuracy of battery status prediction by addressing the issue of efficient data collection and analysis in large-scale battery packs.

[0053] Seventh, we aim to safely protect the system from external hacking threats by addressing the issue of strengthening data security in wireless communication environments.

[0054] Finally, the present invention aims to solve the problem of integratively solving these complex technical challenges while minimizing system complexity and implementation costs. By solving these technical challenges, the present invention aims to dramatically improve the performance, safety, and efficiency of xEVs.

[0055]

[0056] FIG. 1 is a block diagram of a wireless battery management system according to one embodiment of the present invention.

[0057] Referring to FIG. 1, the wireless battery management system (100) of the present embodiment may include a memory (110) and a master controller (120), and each component (110, 120) may form a battery pack together with a battery managed by the BMS in the present embodiment.

[0058] At least one command executed by the master controller (120) described below may be stored in the memory (110). The memory (110) may be implemented as a volatile storage medium and / or a non-volatile storage medium, for example, as a read-only memory (ROM) and / or random access memory (RAM).

[0059] In addition, the memory (110) may store data related to the network environment of the wireless battery, such as RSSI (Received Signal Strength Indicator), PDR (Pedestrian Dead Reckoning), network delay, and EMI (Electromagnetic Interference) level.

[0060] Additionally, the memory (110) may store external factor data including at least one of vehicle vibration, temperature change, and ambient electromagnetic environment. This data may be used to optimize the dynamic network topology of the wireless battery by the master controller (120) described later.

[0061] The master controller (120) is the entity managing the wireless battery and can be implemented as a Central Processing Unit (CPU) or a System on Chip (SoC). It can control multiple hardware or software components connected to the master controller (120) by running an operating system or application, and can perform various data processing and calculations. The master controller (120) can be configured to execute at least one command stored in memory (110) and store the execution result data in memory (110).

[0062] Meanwhile, the master controller (120) may be implemented as a Battery Management System (BMS) provided in the battery pack or a Micro Controller Unit (MCU) inside the BMS, and may be configured to detect external factor data including at least one of vehicle vibration, temperature change, and surrounding electromagnetic environment as previously mentioned.

[0063] Below, the operation of the master controller (120) managing the wireless battery is described in detail.

[0064] The master controller (120) can collect data and store it in memory (110), and optimize the dynamic network topology of the wireless battery through AI-based data analysis. At this time, the master controller (120) can perform data analysis using a network topology optimization engine that uses a Deep Reinforcement Learning algorithm as a technical means.

[0065] At this time, the master controller (120) can manage the wireless battery by analyzing at least one of the data of RSSI, PDR, network delay, and EMI level based on AI and optimizing the dynamic network topology of the wireless battery.

[0066] Additionally, the master controller (120) can optimize the dynamic network topology of the wireless battery by analyzing external factor data including at least one of vehicle vibration, temperature change, and surrounding electromagnetic environment based on AI, and dynamically reconstructing the network structure by integrating the analysis results (including the previous analysis results).

[0067] To this end, the master controller (120) can collect data from each node within the topology of the wireless battery at regular intervals and perform data preprocessing on the collected data. That is, the master controller (120) can complete data preprocessing on the collected data by normalizing the collected data and then applying a moving average filter to the normalized data to remove noise.

[0068] For example, the master controller (120) can collect data such as RSSI, PDR, and EMI at 1-second intervals from each node and normalize the collected data as follows: '(RSSI + 100) / 100' for RSSI, 'PDR / 100' for PDR, and 'EMI / 10' for EMI. Then, the master controller (120) can complete the data preprocessing process by applying a moving average filter (window size: 5 seconds) to the normalized data to remove noise.

[0069] The master controller (120) can evaluate the network status of the wireless battery based on the preprocessed data and predict the optimal network configuration based on the evaluation result of the network status to determine the topology change of the wireless battery.

[0070] To this end, the master controller (120) can determine a Q-table based on the network state of the wireless battery and determine an active path and a standby path based on the Q-table using an epsilon-greed algorithm. For example, the master controller (120) can calculate Q(S_t, A) with the current network state S_5 as input and select an action according to an epsilon-greed policy (epsilon = 0.1). That is, the master controller (120) can select an action with the maximum Q value with a 90% probability and a random action with a 10% probability.

[0071] The master controller (120) can execute a selected action A_t (e.g., changing the path, adjusting the transmission power, etc.) and calculate an immediate reward R_t upon observing a new state S_t+1 (R_t = w1*△PDR + w2*△RSSI + w3*△EMI + w4*△Delay, w1=0.4, w2=0.3, w3=0.2, w4=0.1). The master controller (120) can store the experience (S_t, A_t, R_t, S_t+1) in a replay memory, randomly extract a batch (size: 32) from the replay memory, and perform training (learning rate: 0.001, discount rate: 0.99) and updating of a Deep Q-Network (DQN) model with the extracted batch.

[0072] According to one embodiment, the master controller (120) can reconfigure the topology around nodes that are less affected when the EMI level increases during driving. Additionally, the master controller (120) can distribute the load by adjusting the data transmission path of the battery module when the temperature of the battery module rises.

[0073] Meanwhile, the master controller (120) can reduce communication errors caused by EMI by learning and predicting EMI patterns based on AI to select the optimal frequency and modulation method, and by monitoring EMI intensity and adjusting communication parameters. To this end, the master controller (120) can determine a Q-table based on the network status of the wireless battery and determine a frequency change channel based on the Q-table using an epsilon-greedy algorithm.

[0074] At this time, the master controller (120) can monitor the EMI level of the frequency band in real time using AI-based spectrum sensing and dynamic frequency allocation algorithms as technical means, predict the EMI pattern through EMI pattern learning to select the optimal frequency band, and dynamically switch the modulation method according to the communication environment.

[0075] According to an embodiment, the master controller (120) can generate a frequency hopping sequence that avoids periodic EMI patterns that occur during high-speed driving after learning them. Additionally, the master controller (120) can automatically switch to a more robust modulation method (e.g., QPSK) by taking into account signal attenuation when entering a tunnel.

[0076] The master controller (120) can use an edge computing-based distributed AI processing system and a machine learning-based routing algorithm as technical means to deploy a lightweight AI model to each battery module and perform data preprocessing and initial analysis locally, and can optimize the entire network in cooperation with a central AI system.

[0077] According to the embodiment, the master controller (120) can immediately notify the central system when abnormal signs are detected, based on the results of the self-status analysis of each module. In addition, the master controller (120) can predict network congestion and dynamically set the priority transmission path for important data.

[0078] Meanwhile, the master controller (120) can reduce the power consumption of the BMS by dynamically adjusting the optimal power level for the RF antenna output through the analysis of at least one of the data of the battery status, communication requirements, and surrounding environment of each node in the AI-based topology.

[0079] At this time, the master controller (120) can use a deep learning-based power consumption prediction model and a dynamic power allocation algorithm as technical means to analyze the battery status, communication requirements, and surrounding environment of each node in real time, predict future power consumption patterns and determine the optimal power level, and dynamically adjust the transmission power of each node.

[0080] According to one embodiment, the master controller (120) can reduce the transmission power of a module with a low battery level and enable surrounding modules to strengthen the relay role, minimize unnecessary communication when the vehicle is stopped, and reduce standby power consumption.

[0081] Meanwhile, the master controller (120) can implement each function (topology optimization, EMI response, power management, etc.) as an independent AI module by utilizing a modularized AI system and online learning algorithm based on a microservices architecture as technical means, and can perform continuous model updates and performance improvements based on new data. In addition, the master controller (120) can learn the characteristics of each vehicle model and automatically adjust the optimization strategy.

[0082] According to one embodiment, when a new battery module is added, the master controller (120) can automatically learn the characteristics of the new battery module and integrate the newly added battery module into the existing system based on the learned characteristics. In addition, the master controller (120) can learn changes in battery performance according to changes in driving patterns and automatically adjust the BMS strategy.

[0083] The master controller (120) can use a time series prediction model based on an LSTM (Long Short-Term Memory) network as a technical means to analyze voltage, current, and temperature data at the individual cell and module level in a time series, and predict battery performance considering various operating conditions and environmental factors to detect signs of battery abnormalities early and predict battery life.

[0084] According to the embodiment, the master controller (120) can generate a preemptive warning when detecting a sudden temperature change or an excessive charge / discharge pattern. In addition, the master controller (120) can analyze the performance deviation of individual cells within the battery pack to establish an optimal balancing strategy.

[0085] The master controller (120) can learn normal communication patterns and detect abnormal behavior in real time by using a Generative Adversarial Network (GAN)-based anomaly detection model and a quantum-resistant encryption algorithm as technical means, and can dynamically adjust the encryption strength and method according to the detected threat. In addition, the master controller (120) can learn continuous security threats and update response strategies.

[0086] According to one embodiment, the master controller (120) may isolate the node and require additional authentication when an abnormal data request pattern is detected. Additionally, the master controller (120) may immediately deploy a defense strategy to the entire network when a new type of cyber attack is detected.

[0087] In addition, based on the combination of a lightweight AI model at the edge device and a cloud-based high-performance AI engine, real-time data processing and initial decision-making can be performed at the edge device level. Furthermore, the master controller (120) can process complex analysis and long-term learning in the cloud AI engine and perform overall system optimization through periodic model synchronization.

[0088] According to one embodiment, the master controller (120) may have edge AI handle real-time battery management during driving, and cloud AI handle detailed analysis and optimization after driving. Additionally, the master controller (120) may distribute a new optimization strategy learned in the cloud to edge devices via an OTA (Over-The-Air) update.

[0089]

[0090] Figures 2 and 3 are example diagrams illustrated to explain the xEX wireless BMS network structure and dynamic topology changes.

[0091] First, as shown in FIG. 2, the network structure of the xEV wireless BMS is based on a hierarchical mesh topology and consists of a master controller (MC) (120), relay nodes (RN) (210, 211, 212) and battery module nodes (BMN) (220, 221, 222, 223, 224) as its main components.

[0092] Here, the master controller (120) serves as the central control unit of the entire network, is equipped with an AI-based dynamic topology optimization engine, and is directly connected to the vehicle's main ECU to manage the entire battery system. The relay nodes (210, 211, 212) can act as communication relays between the master controller (120) and the battery module nodes (220, 221, 222, 223, 224). The relay nodes (210, 211, 212) can perform local network optimization and data aggregation functions, and can also perform dynamic routing and load balancing functions. The battery module nodes (220, 221, 222, 223, 224) are communication nodes directly connected to individual battery modules, and can collect and transmit real-time data such as voltage, current, and temperature, and perform local data processing by being equipped with a lightweight edge AI model.

[0093] Next, referring to FIG. 3, an example of a dynamic topology change is described as follows. When a high temperature is detected at battery module node 2 (BMN2) (221), the master controller (120) can change the direct communication path from relay node 1 (RN1) (210) to battery module node 2 (BMN2) (221) as in FIG. 2, as the connection weakens due to a deterioration in link quality between relay node 1 (RN1) (220) and battery module node 2 (BMN2) (221), to a path from relay node 1 (RN1) (210) to battery module node 3 (BMN3) via battery module node 1 (BMN1) (220) and battery module node 2 (BMN2) (221) as in FIG. 3.

[0094] When high temperature is detected at the battery module node (BMN5) (224), the master controller (120) can change the direct communication path from relay node 3 (RN3) (212) to the battery module node 5 (BMN5) (224) as shown in FIG. 2, as the connection weakens due to a deterioration in link quality between relay node 3 (RN3) (222) and the battery module node 5 (BMN5) (224), to a path from the battery module node 5 (BMN5) (224) to the battery module node 6 (BMN6) (225) as shown in FIG. 3. Additionally, the master controller (120) can set a priority path through the battery module node 5 (BMN5) (224) due to the occurrence of critical data at the battery module node 6 (BMN6) (225).

[0095] As described above, in this embodiment, the network structure can be adjusted in real time through AI-based dynamic topology optimization, EMI response capabilities can be improved by introducing AI-based frequency hopping technology and adaptive modulation schemes, and real-time data processing and latency can be minimized by implementing distributed AI processing and multi-hop routing optimization. In addition, in this embodiment, energy efficiency can be improved by introducing an AI-based adaptive power control system, and scalability and flexibility can be improved by significantly enhancing applicability to various xEV models through the provision of a system equipped with a modular AI architecture and self-learning capabilities.

[0096] According to the present invention, communication efficiency is significantly improved, and stable performance can be maintained even under various driving conditions. This is because the AI ​​continuously maintains an optimal network structure by analyzing RSSI, PDR, EMI levels, etc., in real time. Furthermore, according to the present invention, communication stability can be guaranteed by dynamically reconfiguring the network structure by considering various external factors such as vehicle vibration, temperature changes, and the surrounding electromagnetic environment.

[0097] Furthermore, according to the present invention, the communication error rate caused by EMI can be significantly reduced. This is because the AI ​​learns and predicts EMI patterns to select the optimal frequency and modulation method. In addition, according to the present invention, stable communication can be maintained even in high-voltage environments by monitoring EMI intensity in real time and immediately adjusting communication parameters accordingly.

[0098] Furthermore, according to the present invention, data processing delays can be significantly reduced and real-time control accuracy can be improved. This is because partial data processing is performed at each node, and the AI ​​continuously calculates the optimal routing path. Additionally, according to the present invention, critical information is rapidly transmitted through a priority-based data processing algorithm, and overall system responsiveness can be improved through the function of predicting and avoiding network congestion.

[0099] Furthermore, according to the present invention, the power consumption of the BMS can be significantly reduced. This is because the AI ​​dynamically adjusts the optimal power level for the RF antenna output by considering the battery status, communication requirements, and surrounding environment of each node. Additionally, according to the present invention, unnecessary power consumption can be prevented in advance through the prediction of usage patterns. Moreover, according to the present invention, the applicability to various xEV models can be greatly enhanced. This is because the system can automatically learn and optimize new battery configurations and vehicle characteristics. Furthermore, according to the present invention, network configurations can be flexibly changed by utilizing Software Defined Networking (SDN) technology, and continuous performance improvement can be enabled through cloud-based updates.

[0100]

[0101] FIGS. 4 and 5 are flowcharts of a wireless battery management method according to an embodiment of the present invention. With reference to FIGS. 4 and 5, a process for optimizing a dynamic network topology as a wireless battery management method according to an embodiment of the present invention is described. Specific descriptions of configurations that overlap with the aforementioned content are omitted, and the description focuses on the chronological configuration.

[0102] First, referring to FIGS. 1 and FIGS. 4, in step (410), the master controller (120) can collect data related to the network environment of the wireless battery and store it in memory (110).

[0103] Next, in step (420), the master controller (120) can optimize the dynamic network topology of the wireless battery through the analysis of AI-based data. This is specifically explained with reference to FIG. 5 as follows.

[0104] That is, in step (510), the master controller (120) can normalize the collected data.

[0105] Afterwards, in step (520), the master controller (120) can remove noise from the normalized data by applying a moving average filter.

[0106] Afterwards, in step (530), the master controller (120) can evaluate the network status of the wireless battery based on the preprocessed data.

[0107] Afterwards, in step (540), the master controller (120) can predict the optimal network configuration based on the evaluation results of the network status.

[0108] Afterwards, in step (550), the master controller (120) can optimize the dynamic network topology of the wireless battery based on the optimal network configuration prediction result.

[0109]

[0110] The implementations described herein may be implemented, for example, as methods or processes, devices, software programs, data streams, or signals. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., devices or programs). Devices may be implemented in appropriate hardware, software, and firmware, etc. Methods may be implemented in devices such as processors, which generally refer to processing devices including, for example, computers, microprocessors, integrated circuits, or programmable logic devices. Processors also include communication devices such as computers, cell phones, portable / personal digital assistants ("PDAs"), and other devices that facilitate the communication of information between end-users.

[0111] Although the present invention has been described above by limited embodiments and drawings, the present invention is not limited thereto, and it is obvious that various modifications and variations are possible within the scope of the technical spirit of the present invention and the equivalent scope of the claims described below by those skilled in the art to which the present invention belongs.

Claims

1. Memory; and A master controller that collects data related to the network environment of a wireless battery, stores it in the memory, and optimizes the dynamic network topology of the wireless battery through analysis of the data based on AI (Artificial Intelligence). A wireless battery management system characterized by including 2. In Paragraph 1, The above data A wireless battery management system characterized by including at least one of RSSI (Received Signal Strength Indicator), PDR (Pedestrian Dead Reckoning), network delay, and EMI (Electromagnetic Interference) level.

3. In Paragraph 1, The above master controller is A wireless battery management system characterized by optimizing the dynamic network topology of the wireless battery by dynamically reconstructing the network structure by further considering external factor data including at least one of vehicle vibration, temperature change, and surrounding electromagnetic environment.

4. In Paragraph 1, The above master controller is A wireless battery management system characterized by collecting data from each node within the network topology of the wireless battery at regular intervals, normalizing the collected data, and then applying a moving average filter to remove noise.

5. In Paragraph 1, The above master controller is A wireless battery management system characterized by evaluating the network status of the wireless battery based on the above data, predicting an optimal network configuration based on the evaluation result of the network status, and determining a change in the network topology of the wireless battery.

6. In Paragraph 5, The above master controller is A wireless battery management system characterized by determining a Q-table based on the network status of the wireless battery and determining an active path and a standby path based on the Q-table using an Epsilon-Greedy algorithm.

7. In Paragraph 1, The above master controller is A wireless battery management system characterized by reducing communication errors caused by EMI by learning and predicting EMI patterns based on AI to select the optimal frequency and modulation method, and by monitoring EMI intensity and adjusting communication parameters.

8. In Paragraph 7, The above master controller is A wireless battery management system characterized by determining a Q-table based on the network status of the wireless battery and determining a frequency changing channel based on the Q-table using an epsilon-greedy algorithm.

9. In Paragraph 1, The above master controller is A wireless battery management system characterized by reducing power consumption of a Battery Management System (BMS) by dynamically adjusting the optimal power level for an RF antenna output through the analysis of at least one of the battery status, communication requirements, and surrounding environment of each node within the topology based on the AI.

10. A step in which the master controller collects data related to the network environment of the wireless battery and stores it in memory; and The step in which the master controller optimizes the dynamic network topology of the wireless battery through AI-based analysis of the data A wireless battery management method characterized by including 11. In Paragraph 10, The above data A wireless battery management method characterized by including at least one of RSSI, PDR, network delay, and EMI level.

12. In Paragraph 10, The step of optimizing the above dynamic network topology is A step of optimizing the dynamic network topology of the wireless battery by dynamically reconstructing the network structure by further considering external factor data including at least one of vehicle vibration, temperature change, and ambient electromagnetic environment. A wireless battery management method characterized by including 13. In Paragraph 10, The step of collecting the above data and storing it in memory is A step of collecting the data from each node within the network topology of the wireless battery at regular intervals; and Step of removing noise by applying a moving average filter after normalizing the collected data above. A wireless battery management method characterized by including 14. In Paragraph 10, The step of optimizing the above dynamic network topology is A step of evaluating the network status of the wireless battery based on the above data; and A step of determining a change in the network topology of the wireless battery by predicting an optimal network configuration based on the evaluation results of the above network status. A wireless battery management method characterized by including 15. In Paragraph 14, The step of determining the above topology change is A step of determining a Q-table based on the network status of the wireless battery; and A step of determining the active path and standby path based on the above Q-table using the Epsilon-Greedy algorithm A wireless battery management method characterized by including 16. In Paragraph 10, The above master controller is A wireless battery management method characterized by learning and predicting EMI patterns based on AI to select the optimal frequency and modulation method, and reducing communication errors caused by EMI by monitoring EMI intensity and adjusting communication parameters.

17. In Paragraph 16, The above master controller is A wireless battery management method characterized by determining a Q-table based on the network status of the wireless battery and determining a frequency changing channel based on the Q-table using an epsilon-greedy algorithm.

18. In Paragraph 10, The above master controller is A wireless battery management method characterized by reducing power consumption of a BMS by dynamically adjusting the optimal power level for an RF antenna output through the analysis of at least one data among the battery status, communication requirements, and surrounding environment of each node within the topology based on the AI.

Images