Charging robot fault diagnosis method and system based on deep learning

Abstract

The invention discloses a charging robot fault diagnosis method and system based on deep learning, and particularly relates to the technical field of robot fault diagnosis, and the method comprises the following steps: collecting multi-type sensing channel data in an operation process, and constructing a structured input sequence; calculating a local disturbance amplitude and trend difference to generate a weak anomaly confidence value, and judging whether subsequent analysis is triggered or not; if so, extracting a modal drift residual index and a micro-abnormal evolution trend index, and splicing to form a fusion feature vector; outputting a numerical coefficient of each channel through the trained deep learning model; adjusting the sampling frequency according to the numerical coefficient and the characteristic; according to the invention, through unifying a multi-channel data processing flow, constructing a trend-driven anomaly identification mechanism, and combining with deep learning model output, dynamic closed-loop regulation and control of sampling frequency are realized, data consistency, identification sensitivity and resource utilization efficiency of the charging robot fault diagnosis system are improved, and fault diagnosis accuracy is improved. And refined and adaptive monitoring of multi-channel states is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot fault diagnosis, and more particularly, relates to a charging robot fault diagnosis method and system based on deep learning. BACKGROUND

[0002] With the continuous expansion of the application of charging robots in the fields of intelligent transportation, power inspection, warehouse logistics, etc., the continuity, safety and intelligence of their operation have increasingly become the focus of the industry. As a core link in service robot systems, during the long-term autonomous operation of charging robots, internal actuators, perception systems, power systems and other key components are easily affected by environmental disturbances, fatigue wear or control errors, resulting in potential faults or performance degradation, which in turn affects the overall task execution efficiency and system operation safety.

[0003] Currently, for the judgment of the health status of charging robots during operation, the mainstream methods include rule judgment based on threshold, frequency domain signal analysis, expert knowledge base reasoning and shallow learning modeling, etc. These methods mostly rely on manual setting of feature extraction processes and make judgments based on single-channel monitoring results, lacking modeling capabilities for the coupling relationship between channels, trend evolution patterns and complex background noise. Especially in current application scenarios, charging robots often deploy multiple types of sensor channels simultaneously to achieve high-dimensional perception, such as voltage channels and current channels for reflecting energy status, displacement channels and acceleration channels for reflecting structural motion information, torque channels for recording changes in force on the execution unit, and environmental temperature channels for reflecting external operating environment changes, etc.

[0004] Although multi-source data provides a rich information base for fault identification, due to differences in sampling frequency, data distribution and physical meaning, traditional unified rules cannot take into account the characteristics and risk performance of various channels. In addition, in actual systems, potential faults often present as low-intensity, low-frequency, slowly accumulating early weak abnormal signals, which manifest as an increase in local disturbance amplitude or unstable changes in trend direction. Traditional diagnosis methods often trigger responses only when the abnormality evolves into a significant deviation, missing the window period for proactive maintenance and early intervention. Therefore, a charging robot fault diagnosis method and system based on deep learning is proposed to address the above problems. SUMMARY

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions: A charging robot fault diagnosis method based on deep learning, comprising the following steps: Collecting multiple types of sensor channel data of the charging robot during operation, performing time alignment, normalization and abnormality rejection processing on the collected data, and constructing a structured data input sequence as a unified input basis for the subsequent diagnosis process; Based on the structured data input sequence, the local disturbance amplitude of each channel and the trend difference between channels are calculated in a continuous time period to form a weak anomaly confidence value for identifying potential anomalies, which is used to determine whether to trigger a further analysis step; When the analysis step is triggered, two types of feature quantities are extracted, one is a modal drift residual index constructed based on the joint change trend of multiple channel data, and the other is a micro anomaly evolution trend index constructed based on the historical change direction of a single channel. The two types of feature quantities are spliced to form a fusion feature vector. The fusion feature vector is finally output by multiple calls to a deep learning model trained on historical labeled data. Each numerical coefficient corresponds to a channel, representing the severity of potential faults in the current state of the channel. Based on the numerical coefficient of each channel, the micro anomaly evolution trend index, the initial sampling frequency of the channel, and the current modal drift residual index, the sampling frequency of each channel is adjusted, and the frequency after adjustment is used to update the data input sequence in the next period.

[0006] In a preferred embodiment, before time alignment, normalization and anomaly rejection processing of the collected data, channel identification mapping is performed on the channel data to establish a channel identification matching relationship between different channel data in the same time interval.

[0007] In a preferred embodiment, when time aligning the collected data, based on a unified timestamp index rule, linear interpolation is used to fill in missing time points in each data channel. When normalizing the collected data, the minimum-maximum normalization method is used to convert the numerical values of each channel data in a specified time window into standardized data within a fixed interval range according to the proportional relationship between the minimum value and the maximum value.

[0008] In a preferred embodiment, in the process of calculating the local disturbance amplitude of each channel and the trend difference between channels based on the structured data input sequence, the calculation of the local disturbance amplitude uses a window sliding mechanism. The first-order difference of each channel's continuous data segment is processed in a pre-set length time window. The absolute difference between adjacent data points is measured and averaged to obtain the local disturbance amplitude of the channel in the corresponding time window. The calculation of the trend difference between channels includes performing linear fitting on each channel in a continuous time period, extracting the fitting slope value, and calculating the slope difference value set between all channels. The maximum value of the slope difference value set is taken as the quantitative indicator of the trend difference.

[0009] In a preferred embodiment, when forming a weak anomaly confidence value for identifying a latent anomaly, the local disturbance amplitude of each channel in the structured data input sequence within a continuous time period is first standardized to a unified dimension interval respectively corresponding to its inter-channel trend difference, and then the standardized local disturbance amplitude and trend difference are respectively assigned a pre-set static weight factor, the anomaly sensitivity value of each channel is calculated by merging, and the maximum value among all channel anomaly sensitivity values is extracted as the final weak anomaly confidence value, which is used to depict the most significant latent anomaly performance in the overall multi-channel signal within the current continuous time period; after obtaining the weak anomaly confidence value, it is compared with the set multi-level judgment threshold value, if it is in the critical interval, further analysis steps are triggered, if it is in the safe interval, the subsequent analysis process is terminated.

[0010] In a preferred embodiment, when constructing the modal drift residual index based on the joint change trend of multiple channels, first, a first-order difference sequence is extracted for each channel in the structured data input sequence under the same time window, and each value in the difference sequence is converted into a symbol sequence, with positive values as positive symbols, negative values as negative symbols, and zero values as static symbols, to obtain a symbol trend sequence for each channel; The symbol trend sequences of any two channels are position-aligned, and the symbol pairs are compared in sequence from the first position, with a match recorded as a matching number; then the average matching density between the two sequences is calculated, defined as the matching number divided by the length of the symbol sequence, and further subtracted by the average symbol jump position difference between the two sequences, which is the average offset distance between the two channels at all symbol change points, and the result obtained is defined as the consistency coefficient of the channel pair; A trend cross matrix is constructed, in which each element represents the consistency coefficient of the trend direction of two channels in each coding segment, the difference between the maximum and minimum values of all consistency coefficients is extracted from the matrix as a range span value, then the standard deviation and skewness of the matrix are combined for weighted summation to constitute the modal drift residual index, which is used to reflect the overall amplitude of the joint trend difference of multiple channels within the current time window.

[0011] In a preferred embodiment, when constructing the micro-anomaly evolution trend index based on single-channel historical change direction, for each channel in the structured data input sequence, equal-interval segments are extracted under the same time window, a linear trend function is fitted for each segment, and the slope direction, slope amplitude, and residual sum of squares of each trend function are recorded. After obtaining the entire trend function sequence within the time window, the trend direction transformation frequency, average residual fluctuation amplitude, and slope amplitude standard deviation are calculated. The three types of statistics are normalized to form a three-dimensional feature vector. The distance between the three-dimensional feature vector and the normal baseline trend vector is calculated using the normalized Euclidean distance function. The resulting distance value is the micro-anomaly evolution trend index, reflecting the combined characteristics of change direction fluctuation, trend stability, and residual disturbance within the time window for the current channel.

[0012] In a preferred embodiment, the deep learning model is a convolutional neural network model, and each time a channel corresponding feature combination input is selected. The convolutional neural network model is called multiple times, and each time a numerical coefficient is output. Finally, multiple numerical coefficients are obtained.

[0013] In a preferred embodiment, during the process of adjusting the sampling frequency of each channel, for each channel, the numerical coefficient corresponding to the channel and the micro-anomaly evolution trend index are weighted and averaged, where the weights are the pre-set parameters of the channel. The resulting weighted value is multiplied by the current modal drift residual index to obtain the risk enhancement factor of the channel. Then, the risk enhancement factor is multiplied by the initial sampling frequency of the channel to obtain the recommended sampling frequency. The recommended sampling frequency is then adjusted with upper and lower boundary limits, where the lower limit is fifty percent of the initial sampling frequency and the upper limit is twice the initial sampling frequency. Values exceeding the boundary are truncated to the boundary value. Finally, the updated sampling frequency of each channel uses the recommended sampling frequency as the collection interval control parameter to schedule the data collection rate of the channel in the next period. This adjustment mechanism is executed once in each data processing period to achieve differentiated dynamic updating of the sampling frequencies of all channels.

[0014] In a preferred embodiment, a deep learning-based charging robot fault diagnosis system specifically includes: A data acquisition module for acquiring multiple types of sensor channel data of a charging robot during operation, performing time alignment, normalization, and abnormality rejection processing on the acquired data, and constructing a structured data input sequence as a unified input basis for subsequent diagnosis process; An anomaly discrimination module based on the structured data input sequence, which calculates the local disturbance amplitude of each channel and the trend difference between channels within a continuous time period to form a weak anomaly confidence value for identifying latent anomalies. This confidence value is used to determine whether to trigger further analysis steps. The feature extraction module is used to extract two types of feature quantities when the analysis step is triggered, one is a modal drift residual index constructed based on the joint change trend of multiple channel data, and the other is a micro-abnormal evolution trend index constructed based on the historical change direction of a single channel, and the two types of feature quantities are spliced to form a fusion feature vector; The fault identification module is used to input the fusion feature vector into the deep learning model trained by the historical labeled data for multiple times, and each numerical coefficient in the final output corresponds to a channel, indicating the severity of the potential fault under the current state of the channel. The frequency regulation module adjusts the sampling frequency of each channel based on the numerical coefficient of each channel, the micro-abnormal evolution trend index, the initial sampling frequency of the channel and the current modal drift residual index.

[0015] The technical effects and advantages of the present application are as follows: The present application collects multiple types of sensing channel data of the charging robot during operation, and sequentially performs time alignment, normalization and abnormality rejection processing on the collected data to construct a structured data input sequence as a unified input basis for the subsequent diagnosis process. Through this processing mechanism, the differences in sampling time, data distribution and noise characteristics between different channels are effectively eliminated, so that the data of all channels can participate in the calculation under a unified time window, and have a unified numerical scale and effectiveness guarantee, avoiding interference with the subsequent diagnosis due to sampling delay, amplitude anomaly or drift error of a certain channel. This mechanism ensures the consistency of multi-channel fusion calculation, effectively improves the robustness of subsequent feature extraction and model reasoning, and ensures that the diagnosis system can be applied to various combinations of channel types, with better versatility and engineering deployment flexibility.

[0016] Based on the structured data input sequence, the local disturbance amplitude of each channel and the trend difference between channels are calculated in a continuous time period, and a weak abnormal confidence value for identifying latent abnormalities is constructed therefrom, which is further used to determine whether to trigger the subsequent analysis step, and an abnormality recognition mechanism based on trend fluctuation is constructed. Compared with the traditional single-layer diagnosis strategy based on threshold judgment, this mechanism has higher state recognition sensitivity and process adaptability. When the system runs stably, the weak abnormal confidence value is in the safe interval, and resource redundancy is automatically avoided; once local disturbance or cross-channel trend appears, the confidence value quickly reflects the potential abnormality, and automatically activates the deeper feature extraction and depth analysis process, realizing dynamic scheduling and intelligent focusing of system resources. This trend-driven mechanism not only ensures the early detection capability of latent abnormalities, but also improves the computational resource efficiency of the diagnosis process, so that the entire fault identification system has the characteristics of high efficiency and adaptability.

[0017] After the analysis step is triggered, the present invention extracts the modal drift residual index and the micro-anomaly evolution trend index to construct a fused feature vector. This is then repeatedly invoked based on a deep learning model trained with historically annotated data. The model outputs a corresponding numerical coefficient for each channel, representing the severity of the potential fault in that channel's current state. The numerical coefficient output by this model is not used as a static judgment but is further incorporated into the subsequent sampling frequency control process. The system combines each channel's numerical coefficient, the corresponding micro-anomaly evolution trend index, the channel's initial sampling frequency, and the current modal drift residual index in the sampling frequency calculation, thereby implementing a dynamic sampling frequency update mechanism based on a multi-factor risk fusion indicator. This mechanism effectively addresses the resource waste and missed fault detection issues caused by fixed sampling frequencies. It enables each channel to flexibly adjust its sampling density based on its changing state. High-risk channels are sampled more densely to ensure timeliness, while low-risk channels are sampled less frequently to conserve computing power. This entire process is data-driven, featuring closed-loop regulation and periodic execution, significantly enhancing the system's adaptability to dynamic environmental changes and its ability to optimize resource scheduling for long-term operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings; Figure 1 This is a schematic diagram of a charging robot fault diagnosis method based on deep learning in the present invention.

[0019] Figure 2 This is a schematic diagram of a charging robot fault diagnosis system based on deep learning in the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Reference Figure 1 - Figure 2 The following examples were obtained: Example 1: A charging robot fault diagnosis method based on deep learning, comprising the following steps: The multiple types of sensing channel data of the charging robot in the running process are collected, the collected data is time-aligned, normalized and abnormality-eliminated, a structured data input sequence is constructed, and the structured data input sequence is used as a unified input basis for a subsequent diagnosis process; the consistency of different types of original sensing data is processed, so that the data from different channels has comparability and cooperativeness in the same time scale. The time alignment operation ensures that the sampling points of different channels are uniformly analyzed at the same reference time, the normalization process is used to eliminate the numerical scale deviation of each channel due to the dimensional difference of physical quantities, and the abnormality-elimination processing eliminates the interference points such as sudden jumps or sampling errors, so as to form a data sequence format with stable input structure and unified expression capability, and provide reliable, clean and continuous basic data support for subsequent algorithm analysis.

[0022] Based on the structured data input sequence, the local disturbance amplitude of each channel and the trend difference between channels are calculated in a continuous time period to form a weak abnormality confidence value for identifying latent abnormalities, and the weak abnormality confidence value is used to determine whether to trigger a further analysis step; the continuity and cross-channel cooperativeness of the structured data are used to analyze the short-term fluctuation characteristics of each channel and the trend deviation behavior between multiple channels in multiple time windows. The local disturbance amplitude reflects whether each channel itself has a micro abnormal change in a relatively stable state, and the trend difference between channels reveals whether there is a feature of synchronization decline or inconsistent motion direction between multiple channels. By fusing the two types of analysis quantities to form a weak abnormality confidence value, weak abnormal signs that have not evolved into strong faults can be discovered in advance without relying on obvious fault features, so as to establish a preliminary discrimination mechanism for early warning, and the weak abnormality confidence value is compared with a set threshold to trigger subsequent in-depth analysis.

[0023] When the analysis step is triggered, two types of feature quantities are extracted, one is a modal drift residual index constructed based on the joint change trend of multiple channels, and the other is a micro abnormal evolution trend index constructed based on the historical change direction of a single channel, the two types of feature quantities are spliced to form a fusion feature vector; the potential spatial cooperative change mode in time series data and the local historical abnormal evolution trend are extracted and fused at the same time to enrich the feature semantics representing the current state. The modal drift residual index emphasizes whether the joint trend behavior between channels appears cooperative imbalance or mode shift, and the micro abnormal evolution trend index is more concerned about the stability of the trend direction and fluctuation of a single channel in its own historical evolution process. By extracting and splicing the two types of complementary feature quantities in time and space dimensions, a fusion feature vector is constructed, which helps to improve the recognition ability of the subsequent model to potential complex fault states, and has stronger perception ability for ambiguous fault feature performance caused by cross-coupling between multiple source heterogeneous data.

[0024] The fusion feature vector is output by multiple calls to the deep learning model trained on the historical labeled data. Each numerical coefficient corresponds to a channel, representing the severity of potential failure in the current state of the channel. In this step, the deep learning model has the ability to learn complex abnormal patterns through a large number of labeled historical samples. Through multiple inputs of fusion feature vectors of different channels, an independent inference process is performed for each channel. Each model call performs nonlinear mapping of the specific channel feature vector, outputting a numerical coefficient that reflects the health of the channel state. This coefficient can be used to intuitively depict the potential failure risk level of the channel at the current time, facilitating subsequent system risk weighting, strategy response, or information fusion for further operations. At the same time, it also avoids the limitations of traditional fixed rule-based fault judgment logic, enabling the system to have stronger adaptive diagnostic capabilities and learning capabilities.

[0025] Based on the numerical coefficient of each channel, the micro-abnormal evolution trend index, the initial sampling frequency of the channel, and the current modal drift residual index, the sampling frequency of each channel is adjusted. The frequency adjustment is used to update the data input sequence for the next period. This step establishes a feedback adjustment mechanism based on the fault risk assessment results. The current risk expression results and trend evolution indicators of each channel are used to dynamically adjust the current sampling strategy. The numerical coefficient represents the severity of the fault of the channel, the micro-abnormal evolution trend index represents the persistence of short-term fluctuations, and the modal drift residual index reflects the difference of the channel in the global trend. These factors are combined as weighted factors input into the sampling adjustment strategy, which can adaptively increase the sampling frequency of high-risk channels to obtain more intensive diagnostic data, while reducing the sampling frequency of low-risk channels to save resources. This mechanism realizes the closed-loop feedback between data collection and analysis decision-making, significantly improving the overall response agility and data utilization efficiency of the system.

[0026] Before time alignment, normalization, and abnormality rejection processing of the collected data, the channel identification mapping of the channel data is performed to establish the channel identification matching relationship of different channel data within the same time interval. The "collected data" refers to the original sensor measurement data continuously collected based on a predetermined time period during the actual operation of the charging robot, including multiple source channels. The "multi-type sensing channel data" refers to the time series measurement output from different types of sensors, including but not limited to: voltage channel data and current channel data reflecting the state of electrical energy, acceleration channel data and displacement channel data reflecting the motion structure characteristics, torque channel data reflecting the joint execution state, environmental temperature channel data reflecting the external environment, and image channel data for visual identification assistance. Each type of channel mentioned above may differ in physical structure, signal dimension, sampling frequency, unit dimension, etc., so a unified mapping logic needs to be performed before analysis.

[0027] "channel identification" refers to a unique distinguishable label set for each sampling data source channel, including channel category, channel number, physical location index, etc. Field information, used to accurately identify the data source and corresponding relationship in the data preprocessing and feature fusion process. "Channel identification mapping of each channel data" refers to after the original data collection, according to the preset channel configuration table or device sampling strategy, the identification information of the corresponding channel is added to each data point, forming a "channel-data-time" ternary relationship structure, which is used for subsequent time alignment and channel corresponding logical construction.

[0028] "channel identification matching relationship" refers to that in the same time interval, based on the time stamp record of each channel sampling data, the data channels with different sampling start and end time and sampling interval are mapped to each other through time index rules (such as linear interpolation, index interpolation), so that multiple channels have a unified reference frame in the structured input sequence. For example, if the voltage channel is sampled at 0.1 second interval and the image channel is sampled at 0.5 second interval, the image channel needs to be established with the corresponding sampling identification of the voltage channel at each 0.1 second node through the interpolation mechanism to realize channel matching mapping. The establishment of the above channel identification mapping ensures that different types of channel data are processed in a unified time dimension in the subsequent time alignment, normalization and abnormal elimination processing steps, avoids processing errors or feature distortion caused by different data distribution and channel source confusion, is one of the prerequisite steps for constructing structured data input sequence, and is an important basis for subsequent calculation of local disturbance amplitude, channel trend difference and fusion feature vector processing links.

[0029] When the collected data is time aligned, based on the unified time stamp index rule, linear interpolation is used to fill in the missing time points in each data channel; when the collected data is normalized, the minimum-maximum normalization method is used to convert the values of each channel data in the specified time window to standardized data in the fixed interval range according to the proportional relationship between the minimum value and the maximum value.

[0030] In the present application, "time alignment" refers to the time synchronization operation of the original data obtained by collecting multiple data channels, so that all channels form a consistent data representation under a unified time reference. Due to different sampling frequencies or response delays, each channel often has missing, asynchronous, and skip sampling problems. Therefore, a "unified timestamp indexing rule" is set, that is, a reference timestamp sequence is constructed according to the global sampling reference period (such as 100 ms) as the target index set for aligning all channel data. For time points with missing samples, data is filled by performing linear interpolation in each data channel. Linear interpolation is the most commonly used interpolation method in existing technology, which is suitable for the continuity of multi-channel sensor data of the charging robot, and can effectively avoid the interference of data structure misalignment or inconsistent sampling step of different channels on subsequent diagnostic analysis. For example, in the scenario where the image channel is sampled every 500 ms and the voltage channel is sampled every 100 ms, linear interpolation can interpolate the image data to the same time step as the voltage channel, ensuring that each time slice in the structured data input sequence has a complete channel correspondence.

[0031] Normalization processing refers to the standardization adjustment of the numerical incommensurability problem between different channels due to unit, dimension, and measurement scale differences. The present application adopts the min-max normalization method, which is a classical normalization form in existing data preprocessing technology. The principle is: the data in a channel is linearly mapped according to its minimum and maximum value in the specified time window, so that it is normalized to the interval [0, 1] or any specified interval [a, b]. This method ensures that the normalized data of different channels has comparability in the same scale interval, and is suitable for subsequent anomaly detection, feature extraction, and deep model input. For example, the original measurement value of the acceleration channel may range from -2g to +2g, while the temperature channel ranges from 20℃ to 80℃. Without normalization processing, direct input to the model may cause gradient imbalance or learning bias. Through the min-max normalization method, both can be mapped to the same interval, so that the deep learning model obtains stable training performance.

[0032] Anomaly removal involves identifying and removing significant outliers or invalid samples from the input data after time alignment and normalization of the collected data. This prevents noise or erroneous values ​​from interfering with subsequent calculations. In this application, outliers primarily include sudden changes, hysteresis, and sensor packet loss. Common identification strategies include: a sliding window z-score method: Calculating the z-score of each point using the mean and standard deviation of the data within a sliding window. Any point greater than a set threshold (e.g., 3) is marked as an anomaly; continuous constant value detection: If the value of a number of consecutive sampling points remains unchanged (exceeding a set hysteresis threshold), it is considered a hysteresis-type anomaly; and a boundary value strategy: Setting reasonable physical upper and lower limits (e.g., voltage should not exceed 300V) will result in invalid values. For example, in the current channel, if a sample value suddenly jumps to more than five times the normal range within a certain period and differs significantly from surrounding values, it is considered a spike anomaly and is removed or replaced with interpolated points. The data after outlier removal serves as the final, cleaned input sequence for the feature construction and model diagnosis process. This processing step is a commonly used technology for existing industrial data preprocessing and has universal applicability and engineering feasibility.

[0033] In the process of calculating the local disturbance amplitude of each channel and the trend difference between channels based on the structured data input sequence, the calculation of the local disturbance amplitude adopts a window sliding mechanism, and the continuous data segments of each channel are processed by first-order difference within a time window of preset length. The absolute difference between adjacent data points is measured and the average value is taken as the local disturbance amplitude of the channel within the corresponding time window; the calculation of the trend difference between channels includes performing linear fitting on each channel within a continuous time period, extracting the fitting slope value, and calculating the slope difference set between all channels. The maximum value of the slope difference set is taken to form a quantitative indicator of the trend difference.

[0034] The structured data input sequence refers to the aforementioned multi-channel data matrix that has undergone time alignment, normalization, and outlier removal. Its structural characteristics are a two-dimensional time series array with unified sampling timing and channel identification. Each column corresponds to a sensor channel, and each row corresponds to the sampled values ​​of all channels at the same moment. "Local disturbance amplitude" is a quantitative measure of the degree of fluctuation of a single channel over a continuous time period, used to reflect whether the channel exhibits short-term non-stationary changes. To accurately assess the degree of fluctuation within a channel within a short period, the present invention employs a "window sliding mechanism," which gradually slides a fixed time window of length L (e.g., 5 seconds) across the channel time series, processing the data segments within each window.

[0035] In each time window, the data segment of the channel Perform "first-order difference processing", that is, calculate the absolute value of the difference between every two adjacent points in the sequence: , where i=1, 2, 3, ..., L-1; Then for all the differences Perform arithmetic averaging to obtain the local disturbance amplitude D of the channel within the time window: This indicator can sensitively capture weak signal anomalies such as sudden changes and small oscillations within a short period of time. For example, in a voltage channel, if a device experiences a short flash, the disturbance amplitude will be significantly higher than in other windows, thus becoming the basis for subsequent anomaly confidence calculations.

[0036] Inter-channel trend differences measure whether there are significant differences in direction or growth rate between the evolution trends of different channels within a unified time period. This is useful for capturing potential synchronization misalignments or coordination anomalies within the system. The specific calculation process involves performing a "linear fit" using a linear regression method for each channel within a "continuous time period" (equivalent to the time window mentioned above). This involves fitting a function to the data sequence of each channel: ; where k represents the fitting slope (channel change trend), b represents the intercept, and the fitting can be completed using existing statistical methods such as the least squares method. After obtaining the fitting slope values ​​of all channels, construct a "slope difference set" : ; i and j are both numbered indexes. All slope differences in the above set are counted, and the maximum value is taken, which is defined as the "trend difference quantitative index" within this time window: ; Quantitative indicators of the trend difference It can effectively reveal whether a single channel in a system's channels is deviating from group consistency. For example, if the slope of one channel among acceleration, displacement, and torque channels is significantly higher than that of the others, this indicates that the channel is experiencing abnormal behavior that deviates from the global motion trend, potentially indicating potential localized wear, lag, or signal drift. The trend difference quantification metric, combined with the aforementioned local disturbance amplitude, provides a comprehensive cross-channel and intra-channel metric foundation for forming the subsequent "weak anomaly confidence value."

[0037] The weak anomaly confidence value is a numerical indicator used to represent the degree of the most significant latent abnormal feature in the current time period. This indicator is not a local performance of a specific channel, but extracts the most risk-sensitive point from the overall multi-channel to serve as a basis for further diagnosis of whether it should be triggered. In the specific implementation process, first, the "local disturbance amplitude" of each channel in the current continuous time period and the "inter-channel trend difference" indicator value of the channel are extracted from the structured data input sequence. In order to use two indicators with different sources and scales for unified calculation, the two indicators need to be "standardized". Standardization is a preprocessing method that maps the indicator value to a fixed dimension range. It is usually based on the minimum and maximum values of the indicator in the historical statistical range for linear interval mapping, so that it is converted into a relative value between zero and one.

[0038] After standardization, in order to further reflect the relative importance of the two indicators in different scenarios, the application assigns a "preset static weight factor" to each indicator. This factor is a fixed coefficient, which is set based on experience or training set statistics, representing the influence weight of local disturbance or trend difference on the overall judgment in weak anomaly judgment. For example, for inertial measurement channels, local disturbance amplitude is more sensitive; for voltage and current channels, trend difference is more diagnostic. Then, the standardized local disturbance amplitude is multiplied by its corresponding weight factor, and the trend difference indicator is also multiplied by the corresponding factor, and the sum of the two is obtained. The "anomaly sensitivity value" of each channel in the current time period. This anomaly sensitivity value can be understood as a risk comprehensive score that combines the channel's own abnormal fluctuation characteristics and cross-channel trend difference characteristics.

[0039] After obtaining the anomaly sensitivity values of all channels, the system selects the largest value in the current time period as the final "weak anomaly confidence value". This weak anomaly confidence value is used to represent the most attention-worthy latent abnormal channel performance of the entire charging robot system in the time period, which is a mechanism for extracting the strongest signal from the global. Then, the weak anomaly confidence value is compared with the preset "multi-level judgment threshold". The multi-level judgment threshold is a plurality of judgment limits formulated based on a large number of historical normal and abnormal samples, which usually includes a safe interval, a critical interval, and a dangerous interval. If the current weak anomaly confidence value is in the "critical interval", the system judges that there is a strong latent abnormal risk, triggers further analysis steps, and enters the subsequent feature extraction and deep reasoning process; if it is in the "safe interval", it is considered that the current system state is stable, and there is no need to start in-depth analysis, terminate the subsequent process, and maintain the normal operation of sampling and monitoring.

[0040] For example, in a typical case, only the displacement channel among the current, temperature, and displacement channels has a sudden high-frequency jitter, causing the local disturbance amplitude of this channel to increase significantly. After standardization and weight fusion, the abnormal sensitivity value of this channel is higher than that of other channels, and its value is selected as the weak anomaly confidence value of the current period. The system detects that the value is in the critical interval of the set threshold, and then starts the further analysis process of the modal drift residual index and the micro anomaly evolution trend index. Through this mechanism, the system does not need to enter the model reasoning stage every time, but only when the latent anomaly sensitivity reaches the preset risk level, the system needs to be processed in detail, improving the diagnosis efficiency and saving computing resources.

[0041] When constructing the modal drift residual index based on the joint change trend of multiple channel data, first, extract the first-order difference sequence of each channel in the structured data input sequence under the same time window, and convert each value in the difference sequence into a symbol sequence, with positive values as positive symbols, negative values as negative symbols, and zero values as static symbols, to obtain the symbol trend sequence of each channel. Align the position of the symbol trend sequences of any two channels, and compare the symbol pairs from the first position one by one. If they are the same, it is a match, and the number of matches is recorded. Then calculate the average matching density between the two sequences, defined as the number of matches divided by the length of the symbol sequence, and further subtract the average symbol jump position difference between the two sequences. The jump position difference is the average offset distance between the two channels at all symbol change points. The result obtained is defined as the consistency coefficient of the channel pair. Construct a trend cross matrix, where each element in the matrix represents the consistency coefficient of the trend direction of two channels in each encoding segment. Extract the difference between the maximum and minimum values of all consistency coefficients from the matrix as the range span value, and then perform a weighted sum with the standard deviation and skewness of the matrix to form the modal drift residual index, which reflects the overall amplitude of the joint trend difference of multiple channels in the current time window.

[0042] The above process measures the consistency of the change trend of multiple sensor channel output sequences of the charging robot under the current continuous time window, thereby forming the modal drift residual index reflecting the systematic shift phenomenon. Among them, the index is an important criterion for whether the system has a joint trend anomaly, and reflects whether multiple channels show signs of synchronous destruction or increased drift under factors such as function, load, and environmental disturbance.

[0043] In a specific implementation, first, the structured data input sequence is limited to a uniform length time window. The structured sequence has completed time alignment and normalization processing, and the data of each channel forms a one-dimensional continuous numerical sequence in the window. For each channel, a "first-order difference processing" is performed, that is, the subtraction operation is performed on two adjacent data points in the current data sequence to obtain a difference sequence describing the change amplitude. Then, each value in the difference sequence is converted to "symbol encoding", that is: if the value is positive, it indicates an upward trend and is converted to a "positive symbol"; if the value is negative, it indicates a downward trend and is converted to a "negative symbol"; if the value is zero, it indicates stable and no change and is converted to a "still symbol". The sequence generated by this process is the "symbol trend sequence", which reflects the change direction of the channel in the time window. Then, for any two channels, "position alignment of symbol trend sequence" is performed, that is, the symbol sequences of the two channels are compared from the first time point to see if the symbols are the same. If the symbols are the same, it is considered that the "trend direction matches", and the position is recorded as a match. Count the number of all matching positions and divide by the total length of the sequence to get the "average matching density" of the channel pair. The higher the value, the more consistent the trend direction of the two channels. Further, in order to consider the time offset problem of trend jump, the average position difference between all symbol change points in the two symbol trend sequences is counted, that is, the "symbol jump position difference". This difference value is used to represent whether the change of the two channels is time delayed or out of sync although the overall trend is consistent. Subtract the jump position difference from the average matching density to get a "modified trend consistency score", which is defined as the "consistency coefficient" of the channel pair.

[0044] After all the pairwise consistency coefficients between channels are calculated, a "trend cross matrix" is constructed, each element of which represents the trend consistency degree between any two channels at the current time window. Next, statistical analysis is performed on the trend cross matrix. First, the maximum consistency coefficient and the minimum consistency coefficient are extracted from the matrix, and the difference between the two is calculated, defined as the "range span value", which represents the dispersion degree of the maximum and minimum trend consistency between channels. Second, the standard deviation and skewness of all consistency coefficients in the matrix are calculated. The standard deviation reflects the fluctuation degree of the consistency distribution, and the skewness reflects the symmetry of the distribution. Finally, the range span value r1, the standard deviation r2, and the skewness r3 are weighted and summed according to the weights set by experience, such as the weights f1, f2, and f3 obtained by expert assignment method, in the form of MTI = f1*r1 + f2*r2 + f3*r3, to form the "modal drift residual index" in the current time window. The modal drift residual index MTI, as a global statistical indicator of multi-channel trend consistency, is used to comprehensively evaluate whether the current system has a trend inconsistency enhancement behavior due to the imbalance of some functional components, mechanical wear or external disturbance. For example, in an actual case, the displacement, acceleration and torque channels originally have a high consistency trend; when a slight mechanism falls off at the end of the charging arm, the torque channel trend suddenly reverses, causing the signs of other channels to be inconsistent, and the corresponding consistency coefficient decreases significantly, eventually increasing the modal drift residual index.

[0045] The present application constructs a microscopic trend change discrimination mechanism for each channel, i.e. through its historical change direction, trend consistency and volatility, etc. multiple dimensions of dynamic behavior, to form a numerical indicator reflecting whether the channel has weak disturbance abnormal evolution characteristics, i.e. "micro abnormal evolution trend index". First, the processing object is each channel in the "structured data input sequence". The structured data input sequence refers to a unified format data table after preprocessing such as time alignment, normalization and abnormality removal, each table representing a channel, and each row corresponding to the multi-channel sampling results at a uniform time point. The sequence of each channel constitutes a one-dimensional time-varying history record. In the "same time window", a continuous fixed-length time interval, such as ten seconds, is selected as the analysis period, and fine-grained trend behavior segmentation is performed on the channel within the period. The so-called "extracting equal-interval segments" refers to uniformly dividing the time sequence of the channel into several segments within the window, such as dividing it into five segments, each containing an equal number of sampling points.

[0046] For each segment, a "linear trend function" is fitted, i.e. a straight line is used to represent the overall trend direction and slope strength of the data in the time segment. The straight line is obtained based on the least square fitting principle, representing the dominant change direction of the segment in the time period. During the fitting process, three quantities are extracted: one is the "slope direction", indicating whether the trend is rising, falling or stable; the second is the "slope amplitude", indicating the rate of trend rise or fall; the third is the "residual sum of squares", indicating the error degree between the fitted curve and the actual data, used to reflect the fluctuation stability.

[0047] After the trend function fitting of all segments is completed in the entire time window, the following three statistical quantities are calculated: trend direction transformation frequency: the trend direction between adjacent segments is counted to see if it changes, such as from rising to falling or vice versa. The higher the frequency, the more unstable the trend direction, indicating that the system has multiple reverse fluctuation phenomena. Average residual fluctuation amplitude: the residual sum of squares of each segment is averaged to measure the fitting degree of the data to the linear trend in the entire window. The larger the value, the worse the trend fitting effect and the greater the disturbance. Slope amplitude standard deviation: the dispersion of the slope amplitude of all trend functions is calculated. The larger the standard deviation, the more obvious the difference between the trend strengths of different segments in the channel, indicating that there is fluctuation anomaly. The above three statistical quantities represent three different dimensions of the trend direction consistency, trend stability and trend amplitude distribution of the channel in the time period. To facilitate comprehensive processing, the three values are uniformly "normalized", i.e. the values are mapped to the standardized range of zero to one, forming a three-dimensional feature vector with consistent dimensions. Then, the three-dimensional feature vector is compared with a pre-set "normal baseline trend vector", and the "normalized Euclidean distance function" is used to calculate the distance. The distance represents the difference between the current channel change trend characteristics and the normal state trend pattern. The larger the distance, the more the current channel change characteristics deviate from the normal behavior, indicating the possibility of abnormal evolution. The final distance value is the "micro abnormal evolution trend index", which is a fusion index based on the trend direction, fitting residual and trend amplitude statistics of the channel in the current time window, used to represent the micro abnormal fluctuation level of the channel.

[0048] For example, during the operation of the charging robot, if the temperature channel repeatedly switches the trend direction in multiple time segments, and the fitting error of each segment is large and the trend strength fluctuates sharply, the calculated trend direction transformation frequency is high, the average residual is large, and the slope standard deviation is high. The distance value from the normal trend vector is much larger than the set safety interval, indicating that there is a potential risk of heat dissipation anomaly, which is significantly reflected by the index.

[0049] In the foregoing process, two types of feature extraction for each channel within the target time window have been completed, namely the modal drift residual index and the micro abnormal evolution trend index, and the two are spliced to form a "fusion feature vector". The fusion feature vector can be understood as a joint representation of the temporal trend discreteness feature and the micro volatility evolution feature embodied by a single channel in the current period. The fusion feature vector is not a set of original data points, but a set of quantitative feature values extracted through structural modeling, with significant data compression and representation capabilities for input processing in deep learning models.

[0050] In the present application, the deep learning model adopts a convolutional neural network model, which is a typical structure widely used in pattern recognition, feature abstraction, and image classification tasks in the prior art. It has multiple layers of convolutional layers and nonlinear activation layers combined to automatically extract deep spatial correlation structures from input features. The convolutional neural network model is not a general model, but is trained with historical labeled data, that is, a large number of charging robots collect multi-channel sample data under known healthy and fault states, label the health state level of the corresponding channel, and perform supervised training on the model. In the specific implementation process, each time the convolutional neural network model is called, a fusion feature combination corresponding to a channel is selected as input, which is the modal drift residual index and the micro abnormal evolution trend index related to the current channel. After inputting into the convolutional neural network, the model undergoes multiple layers of feature convolution, activation transformation, pooling processing, and full connection mapping, and finally obtains a numerical coefficient in the output layer. The numerical coefficient has the following meaning: quantitatively represents the severity of potential failure under the current channel state, and the higher the value, the greater the risk. Since each model call only inputs a feature combination corresponding to a channel, the model needs to be called one by one for each channel in the structured data input sequence. The model is called multiple times in the entire processing flow, and a numerical coefficient is output each time. The multiple numerical coefficients obtained finally correspond to the current state of all channels in the structured data input sequence. Further, a numerical range-risk level table corresponding to the numerical coefficient can be set, and the specific risk level can be obtained by querying the numerical range of the numerical coefficient, for example, the risk level has ten levels, and the higher the level, the higher the risk. Intervention can be performed when the risk level reaches three, and timely risk warning can be issued in the early stage of hidden danger in the subsequent process, which is beneficial to timely intervention by maintenance personnel and has the explicitness of the fault channel.

[0051] For example, in one practical application scenario, the charging robot system accesses six different types of sensing channels, including current, voltage, temperature, displacement, acceleration, and image channels. After extracting the fusion feature vectors of the six channels, they are input into the trained convolutional neural network model in turn for judgment. The model outputs six numerical coefficients, and the numerical coefficient of the displacement channel is significantly higher than that of the other channels, indicating that there is a potential fault trend in the displacement signal in the current system, suggesting that there may be problems such as trajectory deviation and limit blockage, thereby providing decision-making basis for subsequent frequency regulation and response strategy. Compared with the parallel unified determination mode of all channels, this mechanism has stronger channel-level risk identification capability and the advantage of modeling each channel. It not only retains the ability of deep learning model to automatically extract high-order features, but also adapts to scenarios with large differences between multiple heterogeneous sensing channels.

[0052] For each channel, the numerical coefficient and the micro-abnormal evolution trend index corresponding to the channel are weighted and averaged, where the weights are channel pre-set parameters. The resulting weighted value is multiplied by the current modal drift residual index to obtain the risk enhancement factor of the channel. Then, the risk enhancement factor is multiplied by the initial sampling frequency of the channel to obtain the recommended sampling frequency. The recommended sampling frequency is then adjusted within the upper and lower boundaries, where the lower boundary is 50% of the initial sampling frequency and the upper boundary is twice the initial sampling frequency. Values exceeding the boundaries are truncated to the boundary values. Finally, the updated sampling frequency of each channel is used as the collection interval control parameter to schedule the data collection rate of the channel in the next cycle. This adjustment mechanism is executed once in each data processing cycle to achieve differentiated dynamic updating of the sampling frequencies of all channels.

[0053] The purpose is to achieve reasonable allocation of system resources and dynamic scheduling of sensing tasks while ensuring fault diagnosis sensitivity. First, each channel is independently judged, with the following input indicators: the numerical coefficient output by the deep learning model under the current state of the channel, indicating the severity of the potential fault in the channel; the micro-abnormal evolution trend index extracted in the current period of the channel, reflecting the trend direction volatility and trend stability of the channel. Both have been calculated through fusion feature construction and trend modeling in the previous steps, with timeliness and correspondence under the same time window. The above two indicators are combined into a weighted average structure, where the weights are channel pre-set parameters. These parameters can be developed based on the following factors: Sensitivity level of the channel to system safety: if the voltage channel and displacement channel are crucial to the safety of the structure, a higher weight is given; historical statistical anomaly frequency: if the frequency of abnormal detection in the historical sample is higher, the reliability of the micro- abnormal evolution trend index can be improved, and a higher weight is allocated; signal stability characteristics: for channels with poor signal stability and large sampling fluctuations, the weight of the model output value is appropriately adjusted to suppress false positives; empirical engineering weight matrix: a set of channel level parameters is developed based on expert experience, and a constant array is statically configured before actual deployment. Specific examples are as follows: assuming that the importance of the current channel is higher than that of the image channel, a higher weight (for example, seven tenths) can be given to the model output value in the weighted average, while the model output of the image channel accounts for only five tenths, and the rest is supplemented by the trend index. The weighted average result reflects the local abnormal intensity performance of the channel under the comprehensive state, and then the modal drift residual index calculated by the trend joint between channels at the current time window is multiplied to obtain the risk enhancement factor of the channel. The multiplication structure logically reflects whether the possibility of risk in the channel is amplified in the background of global trend anomalies. Continue processing, multiply the risk enhancement factor by the initial sampling frequency of the channel to obtain the recommended sampling frequency of the channel. On this basis, set the boundary conditions: The lower limit is fifty percent of the initial sampling frequency, which is used to prevent over-slow sampling due to false positives; the upper limit is twice the initial sampling frequency, which avoids excessive system load or over-sampling redundancy. If the calculation result exceeds the boundary, value truncation processing is performed to ensure that the recommended sampling frequency is always within a reasonable and controllable range. Finally, each channel is configured with a data acquisition interval control parameter according to the updated recommended sampling frequency, which is used to perform sampling scheduling in the next cycle. The sampling frequency adjustment mechanism is executed once in each data processing cycle, which has a periodic triggering attribute, so that the system can maintain diagnostic accuracy while having adaptive sampling resource allocation capability, forming a state-driven differentiated sampling mechanism between multiple channels.

[0054] For example, in a specific implementation scenario, the current model value coefficient of the torque channel is zero point eight, the micro- abnormal evolution trend index is zero point six, the weights are zero point seven and zero point three respectively, and the weighted value is zero point seven four. Multiply the modal drift residual index zero point nine to get a risk enhancement factor of about zero point six seven, and then multiply the original sampling frequency of forty hertz to get a recommended sampling frequency of twenty seven hertz, which does not exceed the boundary, so it is set as the sampling frequency in the next cycle; while another stable state channel calculates the recommended frequency below its lower limit of twenty hertz, which is truncated to twenty hertz to ensure safe sampling.

[0055] Embodiment 2: A deep learning-based charging robot fault diagnosis system, specifically comprising: The data acquisition module is configured to acquire multiple types of sensing channel data of the charging robot during operation, perform time alignment, normalization and abnormality elimination on the acquired data, construct a structured data input sequence, and use the structured data input sequence as a unified input basis for a subsequent diagnosis process. The anomaly discrimination module is configured to calculate local disturbance amplitudes and inter-channel trend differences in a continuous time period based on the structured data input sequence, and form a weak anomaly confidence value for identifying a latent anomaly. The confidence value is used to determine whether to trigger a further analysis step. The feature extraction module is configured to extract two types of feature quantities when the analysis step is triggered. One is a modal drift residual index constructed based on joint change trends of multiple channels, and the other is a micro-anomaly evolution trend index constructed based on a historical change direction of a single channel. The two types of feature quantities are spliced to form a fusion feature vector. The fault recognition module is configured to input the fusion feature vector into a deep learning model trained based on historical labeled data, and output a numerical coefficient corresponding to each channel. The numerical coefficient represents the severity of a potential fault in the current state of the channel. The frequency regulation module is configured to adjust the sampling frequency of each channel based on the numerical coefficient of each channel, the micro-anomaly evolution trend index, the initial sampling frequency of the channel, and the current modal drift residual index. The adjusted sampling frequency is used to update the data input sequence for the next period.

[0056] The above formulas are dimensionless numerical calculations. The formulas are obtained by software simulation of a large amount of data to obtain a formula for the most recent real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0057] It should be understood that the size of the sequence number of the above processes does not mean the order of execution in various embodiments of the present application. The execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0058] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0060] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A deep learning-based charging robot fault diagnosis method, characterized in that, The method comprises the following steps: Collecting multiple types of sensor channel data of the charging robot during operation, performing time alignment, normalization and abnormality elimination on the collected data, constructing a structured data input sequence, and using the structured data input sequence as a unified input basis for subsequent diagnosis process; Based on the structured data input sequence, the local disturbance amplitude of each channel and the trend difference between channels are calculated within a continuous time period to form a weak abnormality confidence value for identifying latent abnormalities, which is used to determine whether to trigger further analysis steps; When the analysis step is triggered, two types of feature quantities are extracted, one is a modal drift residual index based on the joint change trend of multiple channel data, and the other is a micro-abnormal evolution trend index based on the historical change direction of a single channel. The two types of feature quantities are spliced to form a fusion feature vector; The fusion feature vector is input into a deep learning model trained by historical labeled data, and each numerical coefficient in the output corresponds to a channel, representing the severity of potential faults in the current state of the channel; Based on the numerical coefficient of each channel, the micro-abnormal evolution trend index, the initial sampling frequency of the channel, and the current modal drift residual index, the sampling frequency of each channel is adjusted, and the frequency after adjustment is used to update the data input sequence of the next period.

2. The deep learning-based charging robot fault diagnosis method according to claim 1, characterized in that, Before performing time alignment, normalization and abnormality elimination on the collected data, the channel identification mapping of each channel data is performed to establish the channel identification matching relationship of different channel data within the same time interval.

3. The deep learning-based charging robot fault diagnosis method according to claim 2, characterized in that, When performing time alignment on the collected data, linear interpolation is used to fill in missing time points in each data channel based on a unified timestamp index rule; When performing normalization on the collected data, the minimum-maximum normalization method is used to convert the numerical values of each channel data within a specified time window into standardized data within a fixed interval range according to the proportional relationship between the minimum value and the maximum value.

4. The deep learning-based charging robot fault diagnosis method according to claim 3, characterized in that, In the process of calculating the local disturbance amplitude and the trend difference between channels based on the structured data input sequence, the local disturbance amplitude is calculated using a window sliding mechanism. The first-order difference of each channel is calculated within a preset length of time window, and the average of the absolute difference between adjacent data points is taken as the local disturbance amplitude of the channel within the corresponding time window. The calculation of the trend difference between channels includes performing linear fitting on each channel within a continuous time period, extracting the fitting slope value, and calculating the slope difference value set between all channels. The maximum value of the slope difference value set is taken as the quantitative indicator of the trend difference.

5. The deep learning-based charging robot fault diagnosis method according to claim 4, characterized in that, In the formation of weak anomaly confidence value for identifying latent anomaly, the local disturbance amplitude of each channel in the structured data input sequence within a continuous time period is standardized to a unified dimension interval respectively according to its corresponding inter-channel trend difference, and then the standardized local disturbance amplitude and trend difference are respectively given a preset static weight factor, and the abnormal sensitivity value of each channel is obtained by merging calculation, and the maximum value in all channel abnormal sensitivity values is extracted as the final weak anomaly confidence value; after obtaining the weak anomaly confidence value, it is compared with the set multi-level judgment threshold value, if it is in the critical interval, the further analysis step is triggered, if it is in the safe interval, the subsequent analysis process is terminated.

6. The deep learning-based charging robot fault diagnosis method according to claim 5, characterized in that, In the construction of modal drift residual index based on the joint change trend of multiple channels, first, the first-order difference sequence of each channel in the structured data input sequence is extracted under the same time window, and each value in the difference sequence is converted into a symbol sequence, with positive values as positive symbols, negative values as negative symbols, and zero values as static symbols, to obtain the symbol trend sequence of each channel; The symbol trend sequences of any two channels are position-aligned, and the symbol pairs are compared in turn from the first position, and the same symbol pair is matched, and the matching times are recorded; then the average matching density between the two sequences is calculated, which is defined as the matching times divided by the length of the symbol sequence, and further subtracted by the average symbol jump position difference between the two sequences, which is the average offset distance between the two channels at all symbol change points, and the result is defined as the consistency coefficient of the channel pair; A trend cross matrix is constructed, and each element in the matrix represents the consistency coefficient of the trend direction of the two channels in each coding segment; the difference between the maximum value and the minimum value of all consistency coefficients is extracted from the matrix as the range span value, and then the standard deviation and skewness of the matrix are added together to form the modal drift residual index.

7. The deep learning-based charging robot fault diagnosis method according to claim 6, characterized in that, In the construction of micro anomaly evolution trend index based on single channel historical change direction, for each channel in the structured data input sequence, equal-interval segments are extracted under the same time window, and a linear trend function is fitted for each segment, and the slope direction, slope amplitude and residual sum of squares of each trend function are recorded; after obtaining all the trend function sequences within the time window, the trend direction transformation frequency, the average residual fluctuation amplitude and the slope amplitude standard deviation are calculated, and the three types of statistics are normalized to form a three-dimensional feature vector, and the distance between the three-dimensional feature vector and the normal reference trend vector is calculated using the normalized Euclidean distance function, and the obtained distance value is the micro anomaly evolution trend index.

8. The deep learning-based charging robot fault diagnosis method according to claim 7, characterized in that, The deep learning model is a convolutional neural network model, which inputs a feature combination corresponding to one channel each time, and the convolutional neural network model is called multiple times, outputting a numerical coefficient each time, and finally obtaining multiple numerical coefficients.

9. The deep learning-based charging robot fault diagnosis method according to claim 8, characterized in that, In the process of adjusting the sampling frequency of each channel, for each channel, the numerical coefficient corresponding to the channel and the micro anomaly evolution trend index are weighted and averaged, where the weights are the pre-set parameters of the channel, and the obtained weighted value is multiplied by the current modal drift residual index to obtain the risk enhancement factor of the channel. The risk enhancement factor is then multiplied by the initial sampling frequency of the channel to obtain a recommended sampling frequency, which is then adjusted by upper and lower boundary limits, with the lower limit being 50% of the initial sampling frequency and the upper limit being twice the initial sampling frequency, and values exceeding the boundary being truncated to the boundary value; finally, the updated sampling frequency of each channel uses the recommended sampling frequency as the acquisition interval control parameter to schedule the data acquisition rate of the channel in the next cycle.

10. A deep learning-based charging robot fault diagnosis system based on the deep learning-based charging robot fault diagnosis method of any one of claims 1-9, characterized in that, Specifically, it comprises: A data acquisition module for acquiring multiple types of sensor channel data of the charging robot during operation, performing time alignment, normalization and abnormality rejection processing on the acquired data, and constructing a structured data input sequence as a unified input basis for subsequent diagnosis processes; An abnormality discrimination module that calculates the local disturbance amplitude of each channel and the trend difference between channels within a continuous time period based on the structured data input sequence to form a weak abnormality confidence value for identifying latent abnormalities, which is used to determine whether to trigger further analysis steps; A feature extraction module for extracting two types of feature quantities when the analysis step is triggered, one being a modal drift residual index constructed based on the joint change trend of multiple channel data, and the other being a micro-abnormal evolution trend index constructed based on the historical change direction of a single channel, and concatenating the two types of feature quantities to form a fusion feature vector; A fault recognition module for passing the fusion feature vector through a deep learning model trained on historical labeled data multiple times, and finally outputting a numerical coefficient for each channel, representing the severity of potential faults in the current state of the channel; A frequency regulation module that adjusts the sampling frequency of each channel based on the numerical coefficient of each channel, the micro-abnormal evolution trend index, the initial sampling frequency of the channel, and the current modal drift residual index, and the frequency after adjustment is used to update the data input sequence in the next cycle.

Images