Cloud computing end protection mode dynamic starting method

Abstract

The invention relates to a dynamic starting method for a cloud computing terminal protection mode. The method comprises the steps that an AI cell temperature prediction model corresponding to a configuration battery of a current electric vehicle is adopted at a cloud computing terminal to intelligently predict the average cell temperature of the configuration battery of the current electric vehicle in a current time segment; and whether an overheating trigger protection mode is started for the configuration battery in the current time segment is determined at the cloud computing end according to the intelligent prediction result and the trigger protection starting temperature of the configuration battery of the current electric vehicle. According to the invention, reliable intelligent prediction can be carried out on the battery cell temperature of the configuration battery of the electric vehicle in a future time segment by adopting an artificial intelligence model with a customized structure design at a cloud computing end based on various basic data screened in a targeted manner; and the safety management of the configuration battery of the electric vehicle in the future time segments is configured in advance based on the intelligent prediction result, so that the safety and the reliability of the electric vehicle are further improved.

Description

Technical Field

[0001] This invention relates to the field of cloud computing, and in particular to a method for dynamically starting a cloud computing endpoint protection mode. Background Technology

[0002] Currently, due to the limited computing and storage resources of electric vehicles, much of the intelligent control and management of electric vehicles is moved to the cloud computing platform. The results of intelligent control and management are then wirelessly returned to the local electric vehicle for execution. This not only makes full use of the computing and storage resources of the cloud computing platform, but also ensures the reliable operation of the intelligent control and management of electric vehicles.

[0003] For electric vehicles, the safety of their battery configuration is a key focus of intelligent control and management. Electric vehicle drivers want to know the cell temperature of the battery configuration in future time segments and make advance safety management configurations to more effectively prevent future accidents such as battery fires. However, there is no mature and reliable technical solution for intelligent prediction of the cell temperature of the electric vehicle's battery configuration in future time segments, which prevents further improvement in the safety of the electric vehicle's battery configuration. Summary of the Invention

[0004] To address the technical problems in existing technologies, this invention provides a dynamic activation method for cloud-based protection mode. By employing a customized artificial intelligence model on the cloud, based on various targeted screening data, the method performs reliable intelligent prediction of the cell temperature of the electric vehicle's battery configuration in future time segments. Based on the intelligent prediction results, the method pre-configures the safety management of the electric vehicle's battery configuration in future time segments, thereby further improving the safety and reliability of the electric vehicle.

[0005] According to the present invention, a method for dynamically starting a cloud computing endpoint protection mode is provided, the method comprising: The system retrieves the weight, volume, capacity, cell weight ratio, charging time, discharging time, operating voltage, and cycle life of the battery configuration of the current electric vehicle from the cloud and outputs these as multiple relevant information for the battery configuration of the current electric vehicle. On the cloud computing side, obtain the average cell temperature of the current electric vehicle's battery configuration for each past time segment before the current moment. The duration of each time segment is the same, and the number of each past time segment before the current moment is monotonically positively correlated with the charge capacity of the current electric vehicle's battery configuration. On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration in previous time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment starts from the current time. On the cloud computing side, based on the average cell temperature of the battery configuration of the electric vehicle in the current time segment and the trigger protection start temperature of the battery configuration of the electric vehicle, it is determined whether to start the overheat trigger protection mode for the battery configuration in the current time segment. Specifically, on the cloud computing side, determining whether to activate the overheating trigger protection mode for the current electric vehicle's battery configuration in the current time segment based on the average cell temperature of the battery configuration in the current time segment and the trigger protection activation temperature of the battery configuration in the current electric vehicle includes: if the average cell temperature of the battery configuration in the current time segment is greater than or equal to the trigger protection activation temperature of the battery configuration in the current electric vehicle, then activating the overheating trigger protection mode for the battery configuration in the current time segment; otherwise, activating the overheating trigger protection mode for the battery configuration in the current time segment.

[0006] Therefore, it can be seen that the present invention has at least the following three important inventive points: The first invention point: On the cloud computing side, an AI cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment starts from the current moment, thereby providing reference data for predicting and responding to the cell temperature of the electric vehicle in future time segments. The second invention point: On the cloud computing end, based on the average cell temperature of the current electric vehicle's battery configuration in the current time segment and the trigger protection activation temperature of the current electric vehicle's battery configuration, it is determined whether to activate the overheat trigger protection mode for the battery configuration in the current time segment. Specifically, if the average cell temperature of the current electric vehicle's battery configuration in the current time segment is greater than or equal to the trigger protection activation temperature of the current electric vehicle's battery configuration, it is determined that the overheat trigger protection mode will be activated for the battery configuration in the current time segment; otherwise, it is determined that the overheat trigger protection mode will not be activated for the battery configuration in the current time segment. This completes the configuration for preventing overheating of the electric vehicle's battery cells and improves the safety of the electric vehicle. The third invention point: In order to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment, a targeted AI cell temperature prediction model corresponding to the current electric vehicle's battery configuration is introduced. The AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is a Hoffert neural network that has been learned multiple times, and the number of learning times is positively correlated with the weight of the current electric vehicle's battery configuration. Detailed Implementation

[0007] The embodiments of the dynamic startup method for cloud computing protection mode of the present invention will be described in detail below.

[0008] Embodiment 1 of the present invention The dynamic startup method for cloud computing protection mode according to Embodiment 1 of the present invention specifically includes the following steps: The system retrieves the weight, volume, capacity, cell weight ratio, charging time, discharging time, operating voltage, and cycle life of the battery configuration of the current electric vehicle from the cloud and outputs these as multiple relevant information for the battery configuration of the current electric vehicle. For example, obtaining the weight, volume, capacity, cell weight percentage, charging time, discharging time, operating voltage, and cycle life of the current electric vehicle's battery configuration on the cloud computing end and outputting it as multiple relevant information of the current electric vehicle's battery configuration includes: using multiple different information detection units to detect and obtain the weight, volume, capacity, cell weight percentage, charging time, discharging time, operating voltage, and cycle life of the current electric vehicle's battery configuration separately; On the cloud computing side, obtain the average cell temperature of the current electric vehicle's battery configuration for each past time segment before the current moment. The duration of each time segment is the same, and the number of each past time segment before the current moment is monotonically positively correlated with the charge capacity of the current electric vehicle's battery configuration. Specifically, the number of past time segments before the current moment is monotonically positively correlated with the battery capacity of the current electric vehicle, including: the higher the battery capacity of the current electric vehicle, the more past time segments before the current moment there are. On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration in previous time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment starts from the current time. On the cloud computing side, based on the average cell temperature of the battery configuration of the electric vehicle in the current time segment and the trigger protection start temperature of the battery configuration of the electric vehicle, it is determined whether to start the overheat trigger protection mode for the battery configuration in the current time segment. Specifically, on the cloud computing side, determining whether to activate the overheating trigger protection mode for the battery configuration in the current time segment based on the average cell temperature of the battery configuration of the current electric vehicle in the current time segment and the trigger protection activation temperature of the battery configuration of the current electric vehicle includes: if the average cell temperature of the battery configuration of the current electric vehicle in the current time segment is greater than or equal to the trigger protection activation temperature of the battery configuration of the current electric vehicle, it is determined that the overheating trigger protection mode is activated for the battery configuration in the current time segment; otherwise, it is determined that the overheating trigger protection mode is not activated for the battery configuration in the current time segment. Specifically, on the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment includes the current moment as the starting moment. The AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is a Hoffert neural network that has been learned multiple times, and the number of learning times is positively correlated with the weight of the current electric vehicle's battery configuration. In addition, on the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the various past time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current time as the starting time, also includes: the current time segment and the various past time segments before the current time form a complete time interval on the time axis.

[0009] Embodiment 2 of the present invention Compared to Embodiment 1 of the present invention, the dynamic startup method for cloud computing protection mode shown in Embodiment 2 of the present invention further includes the following steps: The local terminal of the electric vehicle receives the average cell temperature of the configured battery of the electric vehicle in the current time segment and the overheat trigger flag indicating whether the configured battery has started the overheat trigger protection mode in the current time segment. The average cell temperature of the battery configuration of the current electric vehicle in the current time segment and the overheating trigger flag indicating whether the battery configuration has started the overheating trigger protection mode in the current time segment are displayed synchronously. For example, the center console of an electric vehicle can be selected to synchronously display the average cell temperature of the current electric vehicle's configured battery in the current time segment, as well as the overheat trigger flag indicating whether the configured battery has activated the overheat trigger protection mode in the current time segment.

[0010] Embodiment 3 of the present invention Compared to Embodiment 1 of the present invention, the dynamic startup method for cloud computing protection mode shown in Embodiment 3 of the present invention further includes the following steps: The Hofit neural network is trained multiple times to obtain a Hofit neural network after multiple training sessions. The number of training sessions is positively correlated with the weight of the battery configuration of the current electric vehicle. The Hofit neural network after multiple training sessions is then used as the output of the AI ​​cell temperature prediction model corresponding to the battery configuration of the current electric vehicle.

[0011] Next, the specific steps of the dynamic startup method for cloud computing protection mode of the present invention will be further explained.

[0012] In the cloud computing protection mode dynamic startup method according to any embodiment of the present invention: On the cloud computing side, based on the average cell temperature of the current electric vehicle's battery configuration in the current time segment and the trigger protection start temperature of the current electric vehicle's battery configuration, it is determined whether to activate the overheat trigger protection mode for the battery configuration in the current time segment, including: the trigger protection start temperature of the current electric vehicle's battery configuration is between 60 degrees Celsius and 70 degrees Celsius. Specifically, on the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current time as the starting time, also includes: synchronously inputting the battery configuration's past time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment into the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration. Specifically, a CPLD device can be selected to perform synchronous input of various past time segments of the battery configuration before the current moment, multiple relevant information of the battery configuration of the current electric vehicle, and the duration of each time segment; Specifically, on the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current moment as the starting moment, also includes: running the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration to obtain the average cell temperature of the current electric vehicle's battery configuration in the current time segment output by the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration.

[0013] And in the cloud computing protection mode dynamic startup method according to any embodiment of the present invention: The AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is a Hoffert neural network that has undergone multiple learning iterations, and the number of learning iterations is positively correlated with the weight of the current electric vehicle's battery configuration. This includes: using a number extraction formula to represent the numerical conversion relationship between the number of learning iterations and the weight of the current electric vehicle's battery configuration. The numerical conversion relationship between the number of learning iterations and the weight of the battery configuration of the current electric vehicle, expressed by the iteration extraction formula, includes: in the iteration extraction formula, the weight of the battery configuration of the current electric vehicle is the input value, and the number of learning iterations positively correlated with the weight of the battery configuration of the current electric vehicle is the output value.

[0014] In addition, in the cloud computing protection mode dynamic start method, obtaining the average cell temperature of the current electric vehicle's battery configuration at each past time segment before the current moment on the cloud computing end, where the duration of each time segment is the same and the number of past time segments before the current moment is monotonically positively correlated with the charge capacity of the current electric vehicle's battery configuration, further includes: for each time segment, taking the average value of each cell temperature corresponding to each time segment at even intervals within the time segment as the average cell temperature corresponding to the time segment.

[0015] The cloud-based protection mode dynamic startup method of the present invention addresses the technical problem that the safety of electric vehicle battery configuration cannot be further improved in the prior art. By using a customized artificial intelligence model on the cloud, based on various targeted screening basic data, it performs reliable intelligent prediction of the cell temperature of electric vehicle battery configuration in future time segments, and pre-configures the safety management of electric vehicle battery configuration in future time segments based on the intelligent prediction results, thereby solving the above-mentioned technical problem.

[0016] The foregoing description of exemplary embodiments of the invention is provided for illustrative and descriptive purposes. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations will obviously be apparent to those skilled in the art. Exemplary embodiments were chosen and described in order to best illustrate the principles of the invention and its practical application, thereby enabling others skilled in the art to understand the various embodiments and variations of the invention suitable for the contemplated particular purpose. The scope of the invention is intended to be defined by the appended claims and their equivalents.

Claims

1. A method for dynamically starting a cloud computing endpoint protection mode, characterized in that, The method includes: The system retrieves the weight, volume, capacity, cell weight ratio, charging time, discharging time, operating voltage, and cycle life of the battery configuration of the current electric vehicle from the cloud and outputs these as multiple relevant information for the battery configuration of the current electric vehicle. On the cloud computing side, obtain the average cell temperature of the current electric vehicle's battery configuration for each past time segment before the current moment. The duration of each time segment is the same, and the number of each past time segment before the current moment is monotonically positively correlated with the charge capacity of the current electric vehicle's battery configuration. On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration in previous time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment starts from the current time. On the cloud computing side, based on the average cell temperature of the battery configuration of the electric vehicle in the current time segment and the trigger protection start temperature of the battery configuration of the electric vehicle, it is determined whether to start the overheat trigger protection mode for the battery configuration in the current time segment. Specifically, on the cloud computing side, determining whether to activate the overheating trigger protection mode for the current electric vehicle's battery configuration in the current time segment based on the average cell temperature of the battery configuration in the current time segment and the trigger protection activation temperature of the battery configuration in the current electric vehicle includes: if the average cell temperature of the battery configuration in the current time segment is greater than or equal to the trigger protection activation temperature of the battery configuration in the current electric vehicle, then activating the overheating trigger protection mode for the battery configuration in the current time segment; otherwise, activating the overheating trigger protection mode for the battery configuration in the current time segment.

2. The dynamic startup method for cloud computing protection mode as described in claim 1, characterized in that: On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration in each past time segment before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment includes the current moment as the starting moment. The AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is a Hoffert neural network that has been learned multiple times, and the number of learning times is positively correlated with the weight of the current electric vehicle's battery configuration. Specifically, on the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the various past time segments before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current moment as the starting moment, also includes: the current time segment and the various past time segments before the current moment forming a complete time interval on the time axis.

3. The dynamic startup method for cloud computing protection mode as described in claim 2, characterized in that, The method further includes: The local terminal of the electric vehicle receives the average cell temperature of the configured battery of the electric vehicle in the current time segment and the overheat trigger flag indicating whether the configured battery has started the overheat trigger protection mode in the current time segment. The average cell temperature of the current electric vehicle's battery configuration in the current time segment and the overheating trigger flag indicating whether the battery configuration has activated the overheating trigger protection mode in the current time segment are displayed synchronously.

4. The dynamic startup method for cloud computing protection mode as described in claim 2, characterized in that, The method further includes: The Hofit neural network is trained multiple times to obtain a Hofit neural network after multiple training sessions. The number of training sessions is positively correlated with the weight of the battery configuration of the current electric vehicle. The Hofit neural network after multiple training sessions is then used as the output of the AI ​​cell temperature prediction model corresponding to the battery configuration of the current electric vehicle.

5. The dynamic startup method for cloud computing protection mode as described in any one of claims 2-4, characterized in that: On the cloud computing side, based on the average cell temperature of the current electric vehicle's battery configuration in the current time segment and the trigger protection activation temperature of the current electric vehicle's battery configuration, it is determined whether to activate the overheat trigger protection mode for the battery configuration in the current time segment. This includes situations where the trigger protection activation temperature of the current electric vehicle's battery configuration is between 60 degrees Celsius and 70 degrees Celsius.

6. The dynamic startup method for cloud computing protection mode as described in claim 5, characterized in that: On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current time as the starting time, also includes: synchronously inputting the battery configuration's past time segments before the current time, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment into the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration.

7. The dynamic startup method for cloud computing protection mode as described in claim 6, characterized in that: On the cloud computing side, the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration is used to intelligently predict the average cell temperature of the current electric vehicle's battery configuration in the current time segment based on the battery configuration's past time segments before the current moment, multiple relevant information of the current electric vehicle's battery configuration, and the duration of each time segment. The current time segment, with the current moment as the starting moment, also includes: running the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration to obtain the average cell temperature of the current electric vehicle's battery configuration in the current time segment output by the AI ​​cell temperature prediction model corresponding to the current electric vehicle's battery configuration.

8. The dynamic startup method for cloud computing protection mode as described in any one of claims 2-4, characterized in that: The AI ​​cell temperature prediction model for the current electric vehicle's battery configuration is a Hoffert neural network that has undergone multiple learning iterations, and the number of learning iterations is positively correlated with the weight of the current electric vehicle's battery configuration. This includes: using a formula to extract the number of learning iterations to represent the numerical conversion relationship between the number of learning iterations and the weight of the current electric vehicle's battery configuration.

9. The dynamic startup method for cloud computing protection mode as described in claim 8, characterized in that: The numerical conversion relationship between the number of learning iterations and the weight of the battery configuration of the current electric vehicle is expressed by the number of iterations extraction formula. In the number of iterations extraction formula, the weight of the battery configuration of the current electric vehicle is the input value, and the number of learning iterations that are positively correlated with the weight of the battery configuration of the current electric vehicle is the output value.