Inspection robot battery intelligent charging management system

Abstract

This invention relates to the field of charging management technology, specifically to an intelligent charging management system for inspection robot batteries. It includes an operational feature acquisition module, a state offset construction module, a charging stage adjustment module, a charging collaborative execution module, and a charging strategy adaptation module. Based on the inspection robot, it analyzes the load changes recorded by the main control unit when the robot enters the charging base. This invention constructs a continuous mapping relationship between operational features and charging states, ensuring clear state boundaries at the start of charging. During the charging process, it introduces cross-cycle state alignment and offset characterization, enabling voltage and temperature changes to form correlated feature expressions. Combined with the linkage correction of stage switching conditions and control parameters, it ensures that charging execution maintains a consistent rhythm with state changes. Furthermore, it forms strategy inputs based on multi-round charging results, enabling subsequent charging initiation to have conditional awareness capabilities, thereby establishing a continuous and traceable charging management logic.

Description

Technical Field

[0001] This invention relates to the field of charging management technology, and in particular to an intelligent charging management system for inspection robot batteries. Background Technology

[0002] Charging management involves a technical system for monitoring, controlling, and optimizing the charging process of battery devices. It encompasses multiple aspects such as charging strategy design, battery status assessment, power prediction, current and voltage regulation, and temperature monitoring, and is widely used in portable electronic devices, electric vehicles, robotic systems, and renewable energy storage systems. Among these, the traditional intelligent charging management system for inspection robots refers to a system used to control battery charging, identify status, and execute charging tasks for inspection robots during their operating cycle. Its main purpose is to manage the automatic charging process of inspection robots without human intervention.

[0003] Traditional inspection robot charging management relies on a single state dimension to drive the control process. There is a lack of unified correlation between the operating load, discharge trajectory and environmental conditions. The charging process focuses on stage division and rule triggering. State judgment is based on discrete parameters. It is difficult to form a continuous understanding of the state differences between cycles. Historical charging information remains at the recording level and does not participate in subsequent decision constraints. The charging parameter adjustment lacks consistency of state source. When facing changes in operating conditions, there is a disconnect between charging behavior and the actual change rhythm of the battery. Summary of the Invention

[0004] To address the technical problems existing in the prior art, embodiments of the present invention provide an intelligent charging management system for the battery of an inspection robot. The technical solution is as follows: On the one hand, it provides an intelligent charging management system for the inspection robot's battery, including: The operation feature acquisition module is based on the inspection robot, analyzes the load changes recorded by the main control unit, integrates the discharge process current curve of the current sensing unit, and combines the temperature change of the temperature sensing unit. The parameters are grouped in chronological order to obtain the charging initialization feature group. The state offset construction module compares the current cycle voltage curve with the end segment curve of the previous cycle based on the charging initialization feature group, compares the parameters point by point, extracts the voltage and temperature change features during the two weeks, and obtains the state residual weight features. Based on the state residual weight characteristics, the charging stage adjustment module determines the voltage adjustment requirement of the termination stage, optimizes the start sequence of the trickle stage, and synchronously corrects the stage switching conditions according to the offset trend to obtain the charging correction control parameters. The charging coordination execution module adjusts the voltage and current at the output terminal of the charging base, issues real-time control commands based on the charging correction control parameters, periodically analyzes the output signal, monitors the temperature change of the main control terminal, and obtains the feedback response offset ratio. The charging strategy adaptation module, based on the feedback response offset ratio, filters data from previous charging processes that are consistent with the ambient temperature of the current cycle, performs difference judgment in combination with the parameter range, inputs the result to the next round of configuration, and obtains the intelligent threshold control start signal.

[0005] On the other hand, the charging initialization feature group includes a charging start status code, a historical status reference identifier, and a feature parameter mapping relationship; the state residual weight feature includes an offset classification label, a response trend parameter, and a dynamic weight index; the charging correction control parameters include a stage trigger signal set, a parameter configuration template, and an adjustment response record; the feedback response offset ratio includes a real-time feedback factor, output deviation information, and adjustment adaptation parameters; and the intelligent threshold control start signal includes a threshold control switching identifier, a strategy update flag, and a next-round activation factor.

[0006] On the other hand, the operational feature acquisition module includes: The data stream receiving submodule is based on the inspection robot. It analyzes the load change records of the main control unit, calculates the discharge process curve synchronously output by the current sensing unit, judges the temperature change continuously detected by the temperature sensing unit, identifies data segments with synchronization, corrects data integrity, and obtains a set of synchronous data sequences. The load fluctuation analysis submodule compares the current fluctuation and temperature change trends at each stage based on the synchronous data sequence set, calculates the differences between current and temperature changes, identifies characteristic parameters during the load state duration, and obtains a load state associated feature set. The parameter mapping construction submodule determines the load, current and temperature parameters involved based on the load state associated feature set, optimizes the numbering allocation according to time sequence, sorts out the source and type identifier of each group of numbers, analyzes the belonging relationship in the index set, performs parameter grouping, and obtains the charging initialization feature group.

[0007] On the other hand, the state offset construction module includes: The curve comparison submodule analyzes the difference between the voltage acquisition curve of the current cycle and the voltage curve at the end of the previous cycle based on the charging initialization feature group. By matching and comparing the voltage change trends of the two at time points, it calculates the voltage difference at the corresponding time points and determines the voltage offset characteristics between the two cycles based on the direction and amplitude of the voltage change, thus obtaining the voltage change difference sequence. Based on the voltage change difference sequence, the trend fusion submodule obtains the current cycle temperature sampling data and the historical cycle temperature curve data, compares the temperature fluctuation trend in the current cycle and the historical cycle, analyzes the difference direction at each time node, identifies the time period of temperature change, and obtains the temperature trend change mapping result. Based on the temperature trend change mapping results, the deviation deconstruction submodule analyzes the direction and magnitude of voltage and temperature changes within the same time period, determines the offset relationship between the two, identifies the changed data segments, and obtains the state residual weight features.

[0008] On the other hand, the charging stage adjustment module includes: The voltage adjustment judgment submodule analyzes the current voltage output data based on the state residual weight characteristics, compares the voltage change trend with the voltage curve of the historical stage, determines the direction of voltage fluctuation, and determines whether the voltage output needs to be adjusted based on the offset trend, so as to obtain the voltage regulation requirements. The trickle start optimization submodule analyzes the trend of current cycle temperature change and historical temperature fluctuation based on the voltage regulation requirements, compares the relationship between voltage and temperature changes, determines whether the start sequence of the trickle stage needs to be adjusted, optimizes the start conditions based on the current state, and obtains the trickle start optimization configuration. The parameter correction and archiving submodule adjusts the voltage output and temperature monitoring conditions for each charging stage based on the trickle start optimization configuration, modifies the stage switching condition settings, records the control behavior of each adjustment, organizes and archives the corrected parameters, and obtains the charging correction control parameters.

[0009] On the other hand, the charging coordination execution module includes: The voltage and current adjustment submodule analyzes the voltage and current output requirements of the current charging stage based on the charging correction control parameters, monitors the current and voltage change data, compares the voltage and current situation of similar stages in historical data, judges the difference between the current state and the target output, calculates the required adjustment range, and obtains the voltage and current adjustment command. The control command issuing submodule transmits real-time control commands to the charging base based on the voltage and current adjustment commands, monitors the voltage and current response during command execution, verifies the degree of matching with the set target, adjusts the output state, and obtains real-time control feedback results. Based on the real-time control feedback results, the feedback response monitoring submodule monitors the temperature change trend and power unit output signal returned by the main control terminal, analyzes the changes in voltage and temperature in each charging cycle, compares the relationship between the real-time response and historical data, calculates the degree of deviation of each parameter, and obtains the feedback response deviation ratio.

[0010] On the other hand, the charging strategy adaptation module includes: The data filtering submodule obtains data from each charging process based on the feedback response offset ratio, identifies historical data that matches the current cycle ambient temperature, filters the data based on temperature matching degree and data quality, removes off-target data points, and obtains an ambient temperature matching dataset. The difference comparison submodule, based on the ambient temperature matching dataset, compares the deviation performance of various parameters in the current cycle with those in historical cycles, analyzes the changing trends of voltage and current parameters in each charging cycle, calculates the direction of voltage and temperature difference, determines the deviation magnitude and trend, and obtains the cycle deviation comparison analysis results. The parameter configuration generation submodule, based on the cycle offset comparison analysis results, makes a difference judgment according to the preset parameter range, analyzes the matching of parameter offset with the ambient temperature of the next cycle, adjusts the parameter configuration according to the judgment results, and obtains the intelligent threshold control start signal.

[0011] On the other hand, the main control unit refers to the computing and scheduling control board or embedded processor of the inspection robot, which is responsible for recording and synchronizing various status data during the operation of the robot, and the current sensing unit refers to the current detection sensor installed on the robot's battery system or power circuit.

[0012] On the other hand, the temperature sensing unit refers to a temperature sensor installed on the surface of the battery pack or inside the inspection robot, and the final curve refers to the voltage change or temperature change curve collected near the end of the previous charging cycle.

[0013] On the other hand, the termination stage refers to the last part of the battery charging process, corresponding to the transition period before constant voltage, trickle charging or stopping charging. The trickle charging stage refers to the small current supplementary charging stage after the high current main charging stage ends, in order to prevent overcharging, by using a low current to maintain charging.

[0014] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: By constructing a continuous mapping relationship between operational characteristics and charging states, charging starts with clear state boundaries. During the charging process, cross-cycle state alignment and offset characterization are introduced, enabling voltage and temperature changes to form correlated feature expressions. Combined with the linkage correction of stage switching conditions and control parameters, charging execution and state changes maintain a consistent rhythm. Based on the results of multiple rounds of charging, strategy inputs are formed, enabling subsequent charging starts to have conditional awareness capabilities, thereby establishing a continuous and traceable charging management logic. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the system of the present invention; Figure 2 This is a schematic diagram of the system framework of the present invention; Figure 3 This is a flowchart of the feature acquisition module of the present invention; Figure 4 This is a flowchart of the state offset construction module of the present invention; Figure 5 This is a flowchart of the charging stage adjustment module of the present invention; Figure 6 This is a flowchart of the charging collaborative execution module of the present invention; Figure 7 This is a flowchart of the charging strategy adaptation module of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0018] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0019] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0020] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0021] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0022] This invention provides an intelligent charging management system for the battery of an inspection robot, such as... Figure 1 As shown, the system includes: The operation feature acquisition module is based on the inspection robot. It analyzes the load changes recorded by the main control unit when the robot enters the charging base, integrates the discharge process current curve collected by the current sensing unit, continuously monitors the temperature changes by the temperature sensing unit, and groups and arranges the parameters in chronological order, associating them with numbers and types one by one to obtain the charging initialization feature group. The state offset construction module is based on the charging initialization feature group. It compares the current cycle voltage acquisition curve with the end curve of the previous cycle, and combines the temperature change trend of the current cycle with the historical curve. It compares each set of parameters point by point over time, sorts out the differences in the direction and magnitude of voltage and temperature changes during the two weeks, and obtains the state residual weight features. Based on the state residual weight characteristics, the charging stage adjustment module determines whether the voltage output needs to be adjusted in the current charging termination stage, optimizes the start sequence of the trickle stage, synchronously corrects the switching conditions of each charging stage according to the offset trend, and organizes and archives each parameter adjustment action to obtain the charging correction control parameters. The charging coordination execution module adjusts the voltage and current at the output of the charging base, issues real-time control commands based on the charging correction control parameters, periodically analyzes the output signal of the inspection robot's power unit, monitors the temperature change trend returned by the main control terminal, and compares the performance of each parameter adjustment in chronological order to obtain the feedback response offset ratio. The charging strategy adaptation module uses the feedback response offset ratio to filter data that are consistent with the ambient temperature of the current cycle during previous charging processes. It compares the current offset performance with that of previous weeks, makes a difference judgment based on the preset parameter range, and inputs the judgment result into the parameter configuration for the next round to obtain the intelligent threshold control start signal.

[0023] The charging initialization feature group includes the charging start status code, historical status reference identifier, and feature parameter mapping relationship. The state residual weight feature includes offset classification label, response trend parameter, and dynamic weight index. The charging correction control parameters include stage trigger signal set, parameter configuration template, and adjustment response record. The feedback response offset ratio includes real-time feedback factor, output deviation information, and adjustment adaptation parameter. The intelligent threshold control start signal includes threshold control switching identifier, strategy update flag, and next round activation factor.

[0024] In the feature acquisition module, the main control unit refers to the core computing and scheduling control board or embedded processor in the inspection robot body, responsible for recording and synchronizing various status data during robot operation; load change refers to the energy change required by the drive system during robot movement and operation, which can be indirectly reflected by parameters such as actual power consumption and motor current; the current sensing unit refers to the current detection module installed on the robot's battery system or power circuit, which collects current signals in real time during charging and discharging; the discharge process current curve refers to the curve data of the current flowing out of the battery pack over time when the robot performs a task, used to reflect energy consumption and load intensity; the temperature sensing unit refers to the temperature sensor components arranged on the surface of the battery pack or inside the robot body, which monitors temperature fluctuations in real time during operation; grouping and arrangement refers to organizing the collected parameters into data according to time series, dividing them into their respective categories for easy subsequent analysis and retrieval; numbering and type refer to assigning a unique number to each group of data and distinguishing parameter types according to data content or source, such as load, current, temperature, etc.

[0025] In the state offset construction module, the final curve refers to the voltage or temperature change curve collected near the end of the previous charging cycle, serving as a standard sample for comparison in the current cycle; the temperature change trend refers to the trend of temperature parameters rising, stabilizing, or falling over time throughout the charging process; the historical curve refers to the voltage, temperature, and other curve data collected in previous charging cycles, typically used for evaluation, comparison, or benchmarking; point-by-point comparison by time refers to comparing the values ​​of two sets of similar curves at the same time point to identify differences; the difference in change direction and magnitude refers to comparing the rising or falling trend (direction) and the magnitude (amplitude) of the changes in the two sets of data, used to describe the difference between the actual operating state and the ideal reference.

[0026] In the charging stage adjustment module, the charging termination stage refers to the last segment of the battery charging process, usually corresponding to the transition period before constant voltage, trickle charging, or stopping charging; the trickle charging stage refers to the small current supplementary charging stage after the high current main charging stage ends, which uses low current to maintain charging to prevent overcharging; the offset trend refers to the trend of state offset characteristics changing with the charging process, used to guide the direction of parameter adjustment; the switching conditions of each charging stage refer to the judgment basis and triggering conditions for judging and executing the transition between different charging stages (such as constant current, constant voltage, trickle charging, etc.); the parameter adjustment action refers to the operation behavior of actively adjusting the charging process control parameters (such as current limit, termination voltage, etc.) in response to the detected state offset.

[0027] In the charging collaborative execution module, real-time control commands refer to the parameter change, charging start / stop, and other command signals that are sent from the control system to the charging base or robot body in real time; output signals refer to the voltage, current, temperature, and other working status signals that are fed back in real time by devices such as the charging base power unit and battery management system; parameter adjustment performance refers to monitoring the actual response of various parameters after real-time adjustment of charging parameters and comparing it with the state before adjustment.

[0028] In the charging strategy adaptation module, "each charging process" refers to all charging cycles that have occurred since the system started operating, along with the relevant operational data collected and stored. "Offset performance" refers to the actual deviations and response characteristics of various parameters during the charging process in the past or current cycle. "Preset parameter range" refers to the reasonable range of parameter fluctuations initially set or accumulated based on historical data, used to determine whether the current charging status is abnormal. "Difference judgment" refers to the conclusion drawn from comparing the currently collected data with historical references or set standards to determine whether the parameters have deviated. "Parameter configuration" refers to the initial set of parameters set by the charging management system for the next round of charging tasks in response to strategy adjustments. "Intelligent threshold control start signal" refers to the parameter configuration or trigger signal used to guide the start of the next charging cycle.

[0029] like Figure 2 and Figure 3 As shown, the feature acquisition module includes: The data stream receiving submodule is based on the inspection robot. It analyzes the load change records of the main control unit, calculates the discharge process curve synchronously output by the current sensing unit, judges the temperature change continuously detected by the temperature sensing unit, identifies data segments with synchronization, corrects data integrity, and obtains a set of synchronous data sequences. Based on the main control unit of the inspection robot, the operational load data during the inspection process is used as an initial reference. By recording the power output value of the control board during the robot's movement, turning, and parking actions second by second, time periods with significant power fluctuations are extracted as candidate regions. Simultaneously, the output value of the current sensing unit installed in the battery circuit is recorded synchronously once per second. This is matched one by one with the sampling time points of the main control unit on the time axis to form a current change curve. Then, the current data segment that changes synchronously with the load power fluctuation amplitude is selected as the target segment. For example, when the robot enters the charging base, the power value jumps from 18 watts to 28 watts within 3 seconds, and the current value increases from 1.8 amps in the same period. Up to 2.7 amps, it can be preliminarily determined to be a highly correlated data segment. Then, the temperature data recorded by the temperature sensing unit is continuously output at a frequency of once every two seconds. The temperature curve is read to read the temperature trend within the same period as the load and current changes. If the temperature value shows a continuous upward trend, starting at 25 degrees and rising to 28 degrees after 3 minutes, it is considered that the temperature data in this period has a follow-up change characteristic. Then, by analyzing whether there are any missing points in this period, if it is found that the temperature data is missing data records of two time points, the missing items will be filled by the average of the time points before and after, thereby completing the time alignment and integrity repair of the three types of data: load, current and temperature, and constructing a multi-dimensional synchronous data sequence set represented by a unified time axis.

[0030] The load fluctuation analysis submodule compares the current fluctuation and temperature change trends at each stage based on the synchronous data sequence set, calculates the differences between current and temperature changes, identifies the characteristic parameters during the load state duration, and obtains the load state associated feature set. The fluctuations of power, current, and temperature data within each recording period are extracted. The current change values ​​between adjacent recording points are calculated sequentially, and each change value is compared with its corresponding temperature change at that time point. By calculating the difference in the amplitude of these changes, a sequence of current-temperature difference trajectories is formed. This difference value is then compared with a set fixed standard. For example, if the average current change value is above 0.5 amps for 10 consecutive seconds, while the temperature change is less than 1 degree Celsius during this period, it is considered that the difference between current and temperature is significant, and this time period is marked as a non-coordinated fluctuation segment. Subsequently... The start and end times of the non-cooperative segment in each cycle are statistically determined. Within this time range, the maximum, minimum, and average current values, as well as the temperature change trend, are extracted. For example, if the temperature slowly rises from 27 degrees to 28.2 degrees within 10 seconds, this is recorded as a slow upward trend. At the same time, the power fluctuation amplitude of this segment is statistically analyzed, from the original 20 watts to 29 watts. This segment is then identified as a period of severe load fluctuation. All extracted maximum current, average current, current fluctuation amplitude, temperature growth rate, and power change values ​​are combined to form a load state correlation feature set, which serves as the data basis for subsequent mapping.

[0031] The parameter mapping construction submodule determines the load, current and temperature parameters involved based on the load state associated feature set, optimizes the numbering allocation according to the time sequence, sorts out the source and type identifier of each group of numbers, analyzes the belonging relationship in the index set, performs parameter grouping, and obtains the charging initialization feature group. After identifying a set of load status-related characteristic data, the data is immediately processed item by item. First, current, temperature, and load data are assigned unique numbers, and their sequential positions on the original timeline are recorded. For example, a current data point is marked as number 1, with a time of 10:12:30 AM, corresponding to the current type; another temperature data point is 10:12:31 AM, labeled as temperature; and a third power data point is 10:12:32 AM, labeled as load. These three data points are recorded in a mapping table. By comparing their time differences (not exceeding 2 seconds) and their positions within the same inspection cycle number, it is considered that the three parameters belong to the same operating state, and the data is automatically... The parameters are grouped into a set and a cycle identifier is added according to the cycle number. Further, information such as the source module, the original sampling sequence number, and the parameter type identifier are recorded in the parameters of each group. For example, the above three items are named record numbers 001 to 003, the source is marked as cycle number 5, and the type is current, temperature, and load, which constitute a charging initialization feature group. This feature group serves as the initial reference data for the parameter adjustment, status identification, and other modules in the entire charging control process. If a parameter is found to be mismatched in terms of time point or cycle number during the construction of the feature group, the group will be automatically discarded to ensure that the feature group meets the matching criteria in three dimensions: consistent source, tight time, and complete type.

[0032] like Figure 2 and Figure 4 As shown, the state offset building block includes: The curve comparison submodule analyzes the difference between the voltage acquisition curve of the current cycle and the voltage curve at the end of the previous cycle based on the charging initialization feature group. By matching and comparing the voltage change trends of the two at time points, it calculates the voltage difference at the corresponding time points and determines the voltage offset characteristics between the two cycles based on the direction and amplitude of the voltage change, thus obtaining the voltage change difference sequence. The voltage curves of the current cycle are arranged in chronological order to form a standard sequence. Simultaneously, the voltage change data of the previous cycle before the end of charging is read and divided into a final reference sequence with one sampling point per minute. Then, each time point in the two curves is compared one-to-one, using the two nearest neighbor sampling points on the same time axis as the basis for comparison. For example, if the voltage at the 12th minute of the current cycle is 25.2 volts, the corresponding data at the 12th minute of the previous cycle is 24.7 volts, with a difference of 0.5 volts. Similarity calculations are performed point by point, and all differences are combined to form a voltage difference sequence. In this sequence, the voltage offset value and direction at each time point are recorded sequentially. A positive offset direction is marked as an upward trend, and a negative offset direction as a downward trend. The offset is then statistically analyzed. Whether the shift amplitude remains above 0.3 volts continuously within a certain period is determined. If a positive shift trend is maintained for more than 3 consecutive time periods and the amplitude is above 0.4 volts, it is determined that there is a significant upward shift in that time period. Further, the overall voltage shift performance of the current period is judged based on the standard set by the average of the total difference. For example, if the average voltage of the current period is 25.6 volts and the average value of the last segment of the previous period is 24.8 volts, then the average difference is 0.8 volts. This value falls into the high voltage shift range. This range is preset to be greater than 0.6 volts as the high shift range, 0.3 volts to 0.6 volts as the medium shift range, and less than 0.3 volts as the low shift range. Thus, it is determined that the current period has a high shift characteristic compared with the previous period. The direction of each difference and the corresponding amplitude are recorded to form a voltage change difference sequence.

[0033] The trend fusion submodule acquires the current cycle temperature sampling data and the historical cycle temperature curve data based on the voltage change difference sequence, compares the temperature fluctuation trend in the current cycle and the historical cycle, analyzes the difference direction at each time node, identifies the time period of temperature change, and obtains the temperature trend change mapping result. Temperature sampling data is extracted from the start to the end of the current cycle, with a sampling frequency of one sampling point every two seconds. Simultaneously, historical cycles with similar task type, runtime, and ambient temperature are retrieved for comparison. Records with the same starting temperature conditions and a total cycle length difference of no more than 10% are selected from the historical database for matching. The selected historical cycle temperature curves are then aligned with the current cycle node by time, and the growth or decline trend of temperature data within the two time periods is compared. A comparison window of 10 seconds is used, and within each window, the direction of the current cycle's temperature rise rate is identified to ensure consistency with the historical cycle's temperature change trend. For example, if the temperature rises from 27.3 degrees Celsius to 28.6 degrees Celsius in the current 3rd to 4th minute, while in the historical cycle it only rises to 28.0 degrees Celsius during the same time period... The process records that the current cycle is showing a faster upward trend within a given time period. It then determines whether the slope of the current cycle's temperature curve is greater than the historical curve for three consecutive windows. If so, the interval is marked as an accelerating temperature upward trend segment. Conversely, if the current cycle's slope is lower than the historical cycle and persists for two windows, it is marked as a slowing segment. All window comparison results are merged in chronological order to form a complete temperature trend change mapping result. This mapping records the comparison direction and magnitude of the current cycle's temperature change trend with the historical reference curve within each time interval. For example, from the 5th minute to the 7th minute, the current cycle continues to heat up, with a temperature increase of 2.1 degrees Celsius, while the historical reference cycle only increases by 1.4 degrees Celsius during the same period. The direction is the same, but the magnitude is greater than 0.5 degrees Celsius. Based on this, the segment is marked as a positive difference segment, constituting the trend change mapping result.

[0034] The deviation deconstruction submodule analyzes the direction and magnitude of voltage and temperature changes within the same time period based on the temperature trend change mapping results, determines the offset relationship between the two, identifies the changed data segments, and obtains the state residual weight characteristics. After obtaining the temperature trend change mapping results, they are jointly analyzed with the aforementioned voltage change difference sequence. The direction of change of voltage and temperature is compared for each time period to see if they are consistent. For example, in the interval from the 8th to the 9th minute, if the voltage is decreasing with an amplitude of 0.6 volts and the temperature is increasing with an amplitude of 1.3 degrees, this segment is marked as a reverse offset segment. Same-direction and opposite-direction changes are identified segment by segment, and the corresponding amplitude difference is calculated. When changes are in the same direction but the amplitude difference exceeds a set threshold, for example, if the temperature changes by 2 degrees but the voltage only changes by 0.1 volts, it is considered an amplitude mismatch segment. The threshold is determined based on the average amplitude and standard fluctuation range of the two corresponding values ​​within a historical statistical period. For example, voltage and temperature within a normal week... The average corresponding change during the period is 1 volt corresponding to 3 degrees. Based on this, the offset identification benchmark value is set to ±0.3 volts and ±0.5 degrees as the normal fluctuation range. If it exceeds the range, it is marked as a deviation segment. Then, the offset amplitude and frequency of occurrence of each deviation segment are statistically analyzed. They are combined according to time, direction, amplitude and interval label to form the state residual weight feature. This feature records the time position, offset direction, consistency label and corresponding voltage and temperature fluctuation difference value of each offset segment. For example, if there are two consecutive segments from the 10th minute to the 11th minute where the voltage drops and the temperature rises, with the voltage dropping by 0.7 volts and the temperature rising by 2.5 degrees, this segment is marked as high reverse deviation and included in the weight feature sequence for the control basis of subsequent charging parameter adjustment strategy.

[0035] like Figure 2 and Figure 5 As shown, the charging stage adjustment module includes: The voltage adjustment judgment submodule analyzes the current voltage output data based on the state residual weight characteristics, compares the voltage change trend with the voltage curve of the historical stage, determines the direction of voltage fluctuation, and determines whether the voltage output needs to be adjusted based on the offset trend, thus obtaining the voltage regulation requirements. The system retrieves real-time voltage output data for the current cycle and organizes it into a complete voltage change curve in chronological order. Then, it reads voltage curves from historical periods under similar load conditions and selects those with an ambient temperature difference of no more than 1.5 degrees Celsius and a consistent load change trend as comparison samples. The system compares the direction of change of the current voltage curve at key points with the direction of change at the same time points in the selected historical curves. For example, if the voltage drops from 25.8 volts to 25.5 volts in the 10th minute of the current cycle, the corresponding historical voltage drop is from 25.6 volts to 25.3 volts. After determining that the directions are consistent, the two voltage change amounts are compared. The change amount in the current cycle is 0.3 volts, while the historical change amount is... The voltage is 0.3 volts, and the difference between the two is 0 volts. This data is recorded as an offset record with consistent amplitude. Then, the proportion of directional consistency and the average amplitude difference of all similar comparison time periods in the entire cycle are calculated and compared with the historical reference threshold. It is set that when the proportion of directional inconsistency exceeds 30% or the average fluctuation difference is greater than 0.4 volts, it is marked as a significant voltage offset. Based on this rule, it is determined whether there is a need for adjustment in the current cycle. In the example, there are 60 sampling time points in the current cycle. There are 18 times when the voltage direction is opposite to the reference historical data, and the proportion of directional inconsistency reaches 30%. At the same time, the average voltage fluctuation difference is 0.52 volts, which is higher than the reference value range of 0.4 volts. Therefore, it is recorded as a state where there is a need for voltage adjustment.

[0036] The trickle start optimization submodule analyzes the trend of current cycle temperature change and historical temperature fluctuation based on voltage regulation requirements, compares the relationship between voltage and temperature changes, determines whether the start sequence of the trickle stage needs to be adjusted, optimizes the start conditions based on the current state, and obtains the trickle start optimization configuration. Assuming voltage adjustment is required in the current cycle, the temperature change sequence from the start to the end of charging in the current cycle is extracted and matched with the temperature sequences of historical charging cycles in the same season with similar ambient temperatures and voltage deviation characteristics. The temperature fluctuation trends of the current cycle and historical cycles are compared segment by segment, and the temperature change rate of each stage is divided into intervals. When the temperature fluctuation of the current cycle in the pre-trickle stage exceeds the normal temperature rise range set by the historical curve, for example, the current temperature rises from 34 degrees to 37 degrees between 45 and 50 minutes, while the maximum temperature rise in the historical cycle does not exceed 2 degrees, the temperature fluctuation during this period is recorded as abnormal. Subsequently, it is checked whether this fluctuation segment is adjacent to the trickle charging interval. If, during the voltage adjustment phase before trickle start, the time interval is less than 5 minutes and the temperature fluctuation exceeds 3 degrees Celsius, it is determined that there is a coupling relationship between voltage and temperature fluctuations. Based on this result, it is determined whether the current trickle start sequence needs to be advanced or delayed. The trickle start conditions are then reset according to the intersection of the voltage fluctuation segment corresponding to the temperature peak. For example, if the original trickle start threshold was set to a voltage of 26.5 volts and a temperature stable below 35 degrees Celsius, and the peak fluctuation occurs within 1 minute before start when the temperature is above 36.5 degrees Celsius, the voltage start threshold is corrected to 26.7 volts, the temperature threshold is corrected to 34 degrees Celsius, and the time condition is delayed by 2 minutes. This method optimizes the trickle start configuration conditions for the current cycle, resulting in the optimized trickle start configuration.

[0037] The parameter correction and archiving submodule optimizes the configuration based on trickle start, adjusts the voltage output and temperature monitoring conditions for each charging stage, modifies the condition settings for stage switching, records the control behavior of each adjustment, organizes and archives the corrected parameters, and obtains the charging correction control parameters. Given that both the starting voltage and temperature conditions need adjustment, the process for revising the switching conditions for each charging stage begins. First, the time boundaries and parameter settings for the constant current, constant voltage, and trickle charging stages in the current cycle are extracted. The deviations of the actual voltage and temperature values ​​at the switching nodes in the current cycle are compared with the original settings. If the voltage is more than 0.3 volts higher than the original setting or the temperature is more than 2 degrees higher than the set value at the end of the constant voltage cycle, the correction process begins. This involves resetting the switching threshold conditions from constant voltage to trickle charging and updating the previously stored parameter template. In this example, the original setting for the constant voltage to trickle charging switching point is... With a voltage of 26.5 volts and a temperature of 34 degrees Celsius, the current cycle's measured switching point is 26.9 volts and a temperature of 36 degrees Celsius. Based on this data, the template value is revised to 26.8 volts and 35 degrees Celsius, and this adjustment operation is recorded in the parameter change log. The record includes the time, operator ID, original setting value, adjusted setting value, reason for adjustment, and corresponding status feature number. After all records are completed, they are compiled into a set of correction parameter archive files with adjustment trajectory records, and automatically linked to the parameter initialization module of the next cycle. This serves as the basis for configuring the initial charging value for subsequent tasks and outputs charging correction control parameters.

[0038] like Figure 2 and Figure 6 As shown, the charging coordination execution module includes: The voltage and current adjustment submodule analyzes the voltage and current output requirements of the current charging stage based on the charging correction control parameters, monitors the current and voltage change data, compares the voltage and current situation of similar stages in historical data, judges the difference between the current state and the target output, calculates the required adjustment range, and obtains the voltage and current adjustment command. Extract the target range value corresponding to the current charging stage. For example, in the constant current stage, the target voltage is 25.5V to 26.0V, and the target current is 4.5A to 5.0A. Receive real-time voltage and current output records, summarize and statistically analyze the output data sampled for 10 consecutive seconds within the current time period, and calculate the average voltage and average current values. If the statistical results show that the current voltage is 25.2V and the current is 4.1A, it is determined that both are below the target lower limit, and the state is recorded as a negative offset. Subsequently, read the voltage and current data from historical tasks under similar stages and temperature conditions as comparison samples. The comparison samples record the average voltage for this stage as 25.7V and the average current as 4.6A. The offset amplitudes are 0.5 volts and 0.5 amps, respectively, with a set reference offset tolerance of 0.3 volts and 0.3 amps. If the offset amplitude exceeds the tolerance, it is considered to be in an adjustment state. The difference between the current output and the target value is directly calculated to obtain the correction amplitude that needs to be increased by 0.5 volts and 0.4 amps. Then, the adjustment action direction is determined to be upward and an adjustment amplitude identifier is generated, forming a control instruction structure package with a stage identifier, voltage adjustment direction and amplitude, and current adjustment direction and amplitude. In this example, the output control package content is: stage "constant current", voltage increased by 0.5 volts, current increased by 0.4 amps. This structured result serves as the adjustment basis, and the output voltage and current adjustment instructions are generated.

[0039] The control command issuing submodule transmits real-time control commands to the charging base based on voltage and current adjustment commands, monitors the voltage and current response during command execution, verifies the degree of matching with the set target, adjusts the output state, and obtains real-time control feedback results. The control interface is invoked to adjust the voltage to a set value within the upper limit offset range, for example, adjusting the current voltage from 25.2 volts to 25.7 volts, and simultaneously adjusting the current from 4.1 amps to 4.5 amps. The control module synchronously transmits this adjustment command to the charging base's execution port. Upon receiving the command, the charging base's power output unit performs internal output signal correction and transmits back the current voltage and current changes per second in real time. The feedback acquisition window is set to within 10 seconds after the command is issued. During this period, the actual voltage and current values ​​per second are recorded. By comparing the actual response with the target set value, the execution offset is determined. For example, if the voltage rises to 25.5 volts but does not reach 25 volts in the 5th second after the command is issued... If the voltage is 0.7 volts and the current rises to 4.3 amps but remains below 4.5 amps, it is recorded that the target has not been fully achieved in this round of execution. At the same time, a second adjustment process is initiated. Based on the current offset, an incremental fine-tuning control command is issued to increase the voltage by 0.2 volts and the current by 0.2 amps until the voltage and current are stable within the target tolerance range for three consecutive seconds within a 10-second window. The allowable deviation for voltage is set to ±0.1 volts and the allowable deviation for current is set to ±0.1 amps. If these are achieved consecutively, it is marked as the control round has been achieved. The control feedback execution log is recorded, including the control issuance time, response time, maximum offset, final stable value, cumulative number of adjustments, and adjustment actions. The corresponding real-time control feedback results are generated.

[0040] The feedback response monitoring submodule monitors the temperature change trend and power unit output signal returned by the main control terminal based on the real-time control feedback results, analyzes the changes in voltage and temperature in each charging cycle, compares the relationship between the real-time response and historical data, calculates the degree of deviation of each parameter, and obtains the feedback response deviation ratio. The system reads the temperature change record sequence uploaded by the main control unit and the real-time power output signal fed back by the power unit. It extracts the time-series change data of voltage, temperature, and power in each charging cycle, and statistically analyzes and categorizes the voltage rise rate, temperature change trend, and power output stability for each time period. For example, it statistically shows that the temperature rise rate is 1.2 degrees Celsius per minute within 15 minutes after voltage adjustment, and the power output value slowly decreases from 110 watts to 102 watts. The temperature change rate is divided into three categories based on time period: below 1 degree Celsius / minute, 1 to 2 degrees Celsius / minute, and above 2 degrees Celsius / minute. Correspondingly, power output stability is categorized as fluctuation less than 5 watts (stable), 5 to 10 watts (mild fluctuation), and above 10 watts (severe fluctuation). If the temperature... The current response offset is marked as medium level, given that the power is in the medium-speed increase range and fluctuates slightly. Then, the offset levels of each item in this cycle are compared with the response data under similar conditions in historical cycles. The average offset degree and frequency of occurrence in each cycle are extracted. The offset degree of the current cycle is calculated to be 60% medium offset, 40% slight offset, and no severe offset. Combined with parameters such as the total number of adjustments and execution time, the feedback indicator structure is constructed. The offset ratio level is set as low offset ratio less than 20%, medium offset ratio between 20% and 50%, and high offset ratio more than 50%. In the example, the current cycle offset ratio is 60%, which is judged as a high offset ratio. The feedback response offset ratio is then output.

[0041] like Figure 2 and Figure 7 As shown, the charging strategy adaptation module includes: The data filtering submodule acquires data from each charging process based on the feedback response offset ratio, identifies historical data that matches the ambient temperature of the current cycle, filters the data based on temperature matching degree and data quality, removes off-target data points, and obtains an ambient temperature matching dataset. All archived historical charging cycle data records were retrieved, with filtering dimensions including ambient temperature, voltage response fluctuation, current adjustment frequency, and temperature peak. Ambient temperature was the primary filtering criterion. The average ambient temperature of the current cycle was extracted. For example, if the ambient temperature of the current charging cycle was 26.3 degrees Celsius, a matching threshold of ±1 degree Celsius was set. Cycle data with ambient temperatures between 25.3 and 27.3 degrees Celsius were selected as the initial candidate set, yielding a total of 108 historical data records. Subsequently, the completeness of the temperature record, the stability of the voltage and current data sampling interval, the presence of abrupt changes, and abnormal termination markers were checked for each candidate data record. Each record was then analyzed based on data... Completeness is scored, and data quality is defined as follows: above 90% is high quality, 70% to 90% is medium quality, and below 70% is low quality. Data entries with scores below 70% are removed. From the remaining data, data segments with a "high offset" level in the past are excluded based on the feedback response offset ratio to avoid misusing historical periods with excessive bias as references for current parameters. After completing temperature matching screening and data quality comparison, an environmental temperature matching dataset is formed. For example, it is confirmed that 72 data entries are retained, all of which meet the requirements of temperature difference not exceeding 1 degree, data completeness exceeding 90%, and offset level not higher than medium offset. This dataset serves as the data basis for subsequent trend comparison analysis.

[0042] The difference comparison submodule is based on the ambient temperature matching dataset. It compares the deviation performance of various parameters in the current cycle with those in the historical cycle, analyzes the changing trends of voltage and current parameters in each charging cycle, calculates the direction of voltage and temperature difference, judges the deviation magnitude and trend, and obtains the cycle deviation comparison analysis results. The system reads the voltage, current, and temperature change sequences for each cycle and normalizes them according to fixed time points. For example, it uses sampling values ​​per minute as the comparison unit. From charging start to completion, the process is divided into three stages: constant current, constant voltage, and trickle charging. During the constant voltage stage, the system reads the voltage and temperature data from the 30th to the 45th minute of the current cycle and compares them with the average voltage and temperature values ​​for the same stage in the historical dataset. If the voltage change in the current cycle is from 26.0 volts to 25.5 volts, and the historical average change range is from 26.1 volts to 25.7 volts, the system calculates that the voltage change direction is consistently downward, and the change amplitude is... The difference in voltage is 0.1 volts, and the temperature change is 0.8 degrees higher than the historical average in the current cycle. This segment is marked as having a small positive voltage offset and a medium temperature offset. At the same time, the trajectory of the current parameter change is calculated to determine whether there is an early or delayed drop relative to the historical cycle. For example, if the current has dropped to 2.0 amps in the 40th minute in the history, but it drops to the same value in the 43rd minute in the current cycle, this difference is recorded as the current response delay, and the offset time length is recorded as 3 minutes. After summarizing all the comparison data, a table of the difference direction, offset magnitude and trend consistency of each parameter is generated according to the stage, and the cycle offset comparison analysis results are obtained.

[0043] The parameter configuration generation submodule judges the difference based on the cycle offset comparison analysis results and the preset parameter range, analyzes the matching of parameter offset with the ambient temperature of the next cycle, adjusts the parameter configuration according to the judgment results, and obtains the intelligent threshold control start signal. First, a reference range of preset parameters is used to determine the differences. The voltage offset tolerance is set to ±0.3 volts, the current response offset tolerance to ±2 minutes, and the temperature offset tolerance to ±1.0 degree. The offset values ​​of each stage in the current cycle are compared with the above reference ranges item by item. When multiple parameters in a certain stage exceed the tolerance threshold at the same time, the parameter adjustment action judgment mechanism is triggered. Then, a joint judgment is made based on the matching of the estimated ambient temperature of the next cycle with the temperature change trend of the current cycle. For example, if the estimated ambient temperature of the next cycle is 27.0 degrees and the maximum temperature of the current cycle is 34.5 degrees, and the system has triggered the trickle stage to start early under the same temperature conditions in historical data, this matching relationship is recorded as a high correlation match. Then, based on the offset result, it is determined that the upper limit of the charging voltage in the next cycle needs to be adjusted from 26.0 volts to 25.8 volts, the trickle start is delayed by 2 minutes, and the temperature trigger point is lowered by 1 degree. This set of new settings is used as the initial configuration for the next cycle. A parameter configuration set is formed in a structured way and assigned a threshold control identifier, strategy number, and effective cycle index identifier. The output is an intelligent threshold control start signal.

[0044] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent charging management system for the battery of an inspection robot, characterized in that, The system includes: The operation feature acquisition module is based on the inspection robot, analyzes the load changes recorded by the main control unit, integrates the discharge process current curve of the current sensing unit, and combines the temperature change of the temperature sensing unit. The parameters are grouped in chronological order to obtain the charging initialization feature group. The state offset construction module compares the current cycle voltage curve with the end segment curve of the previous cycle based on the charging initialization feature group, compares the parameters point by point, extracts the voltage and temperature change features during the two weeks, and obtains the state residual weight features. Based on the state residual weight characteristics, the charging stage adjustment module determines the voltage adjustment requirement of the termination stage, optimizes the start sequence of the trickle stage, and synchronously corrects the stage switching conditions according to the offset trend to obtain the charging correction control parameters. The charging coordination execution module adjusts the voltage and current at the output terminal of the charging base, issues real-time control commands based on the charging correction control parameters, periodically analyzes the output signal, monitors the temperature change of the main control terminal, and obtains the feedback response offset ratio. The charging strategy adaptation module, based on the feedback response offset ratio, filters data from previous charging processes that are consistent with the ambient temperature of the current cycle, performs difference judgment in combination with the parameter range, inputs the result to the next round of configuration, and obtains the intelligent threshold control start signal.

2. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The charging initialization feature group includes a charging start status code, a historical status reference identifier, and a feature parameter mapping relationship. The state residual weight feature includes an offset classification label, a response trend parameter, and a dynamic weight index. The charging correction control parameters include a stage trigger signal set, a parameter configuration template, and an adjustment response record. The feedback response offset ratio includes a real-time feedback factor, output deviation information, and adjustment adaptation parameters. The intelligent threshold control start signal includes a threshold control switching identifier, a strategy update flag, and a next-round activation factor.

3. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The operational feature acquisition module includes: The data stream receiving submodule is based on the inspection robot. It analyzes the load change records of the main control unit, calculates the discharge process curve synchronously output by the current sensing unit, judges the temperature change continuously detected by the temperature sensing unit, identifies data segments with synchronization, corrects data integrity, and obtains a set of synchronous data sequences. The load fluctuation analysis submodule compares the current fluctuation and temperature change trends at each stage based on the synchronous data sequence set, calculates the differences between current and temperature changes, identifies characteristic parameters during the load state duration, and obtains a load state associated feature set. The parameter mapping construction submodule determines the load, current and temperature parameters involved based on the load state associated feature set, optimizes the numbering allocation according to time sequence, sorts out the source and type identifier of each group of numbers, analyzes the belonging relationship in the index set, performs parameter grouping, and obtains the charging initialization feature group.

4. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The state offset construction module includes: The curve comparison submodule analyzes the difference between the voltage acquisition curve of the current cycle and the voltage curve at the end of the previous cycle based on the charging initialization feature group. By matching and comparing the voltage change trends of the two at time points, it calculates the voltage difference at the corresponding time points and determines the voltage offset characteristics between the two cycles based on the direction and amplitude of the voltage change, thus obtaining the voltage change difference sequence. Based on the voltage change difference sequence, the trend fusion submodule obtains the current cycle temperature sampling data and the historical cycle temperature curve data, compares the temperature fluctuation trend in the current cycle and the historical cycle, analyzes the difference direction at each time node, identifies the time period of temperature change, and obtains the temperature trend change mapping result. Based on the temperature trend change mapping results, the deviation deconstruction submodule analyzes the direction and magnitude of voltage and temperature changes within the same time period, determines the offset relationship between the two, identifies the changed data segments, and obtains the state residual weight features.

5. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The charging phase adjustment module includes: The voltage adjustment judgment submodule analyzes the current voltage output data based on the state residual weight characteristics, compares the voltage change trend with the voltage curve of the historical stage, determines the direction of voltage fluctuation, and determines whether the voltage output needs to be adjusted based on the offset trend, so as to obtain the voltage regulation requirements. The trickle start optimization submodule analyzes the trend of current cycle temperature change and historical temperature fluctuation based on the voltage regulation requirements, compares the relationship between voltage and temperature changes, determines whether the start sequence of the trickle stage needs to be adjusted, optimizes the start conditions based on the current state, and obtains the trickle start optimization configuration. The parameter correction and archiving submodule adjusts the voltage output and temperature monitoring conditions for each charging stage based on the trickle start optimization configuration, modifies the stage switching condition settings, records the control behavior of each adjustment, organizes and archives the corrected parameters, and obtains the charging correction control parameters.

6. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The charging coordination execution module includes: The voltage and current adjustment submodule analyzes the voltage and current output requirements of the current charging stage based on the charging correction control parameters, monitors the current and voltage change data, compares the voltage and current situation of similar stages in historical data, judges the difference between the current state and the target output, calculates the required adjustment range, and obtains the voltage and current adjustment command. The control command issuing submodule transmits real-time control commands to the charging base based on the voltage and current adjustment commands, monitors the voltage and current response during command execution, verifies the degree of matching with the set target, adjusts the output state, and obtains real-time control feedback results. Based on the real-time control feedback results, the feedback response monitoring submodule monitors the temperature change trend and power unit output signal returned by the main control terminal, analyzes the changes in voltage and temperature in each charging cycle, compares the relationship between the real-time response and historical data, calculates the degree of deviation of each parameter, and obtains the feedback response deviation ratio.

7. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The charging strategy adaptation module includes: The data filtering submodule obtains data from each charging process based on the feedback response offset ratio, identifies historical data that matches the current cycle ambient temperature, filters the data based on temperature matching degree and data quality, removes off-target data points, and obtains an ambient temperature matching dataset. The difference comparison submodule, based on the ambient temperature matching dataset, compares the deviation performance of various parameters in the current cycle with those in historical cycles, analyzes the changing trends of voltage and current parameters in each charging cycle, calculates the direction of voltage and temperature difference, determines the deviation magnitude and trend, and obtains the cycle deviation comparison analysis results. The parameter configuration generation submodule, based on the cycle offset comparison analysis results, makes a difference judgment according to the preset parameter range, analyzes the matching of parameter offset with the ambient temperature of the next cycle, adjusts the parameter configuration according to the judgment results, and obtains the intelligent threshold control start signal.

8. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The main control unit refers to the computing and scheduling control board or embedded processor of the inspection robot, which is responsible for recording and synchronizing various status data during the operation of the robot. The current sensing unit refers to the current detection sensor installed on the robot's battery system or power circuit.

9. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The temperature sensing unit refers to a temperature sensor installed on the surface of the battery pack or inside the inspection robot, and the final curve refers to the voltage or temperature change curve collected near the end of the previous charging cycle.

10. The intelligent charging management system for the inspection robot battery according to claim 1, characterized in that, The termination stage refers to the last part of the battery charging process, corresponding to the transition period before constant voltage, trickle charging, or stopping charging. The trickle charging stage refers to the small current supplementary charging stage after the high current main charging stage ends, in order to prevent overcharging, by using a low current to maintain charging.

Images