Carbon brush intelligent monitoring device

Abstract

The invention relates to the technical field of state early warning, in particular to a carbon brush intelligent monitoring device, which comprises a time sequence synchronous acquisition module, a contact performance judgment module, an asynchronous feature recognition module, a feature event alignment module and an operation risk early warning module, and judges the response time of a carbon brush current and a temperature sensor based on a time sequence pulse sent by a main control board. According to the method, when multiple types of parameters of the carbon brush are collected, synchronous matching characteristics of current and temperature are actively constructed, contact performance fluctuation factors under periodic disturbance are integrated, and a structure anomaly risk grading model is established by synchronously judging sudden wear change and vibration events and dynamically outputting synchronous grouping and dislocation proportions of wear and vibration events; a multi-level, sequential and associated carbon brush health assessment system is formed, trend monitoring, early warning and risk grading of key hidden dangers are supported, intelligent diagnosis and data traceability under complex working conditions are enhanced, and fault recognition and safety management and control levels in the carbon brush operation process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of status warning, and in particular to an intelligent carbon brush monitoring device. Background Art

[0002] The status warning field involves real-time monitoring of the status of key components during equipment or system operation and issuing timely abnormality alerts. This includes collecting equipment operating data, identifying potential failures in key components, and communicating early warning information to operations and maintenance personnel. It encompasses systematic technical content such as equipment safety monitoring, status identification, and automated early warning. Traditional carbon brush intelligent monitoring devices, in particular, are systems that monitor and diagnose the operating status of carbon brushes in generators or motors in the context of thermal power plants and hydropower plants. These systems target long-term carbon brush failures such as wear, breakage, and poor contact, and combine real-time data analysis to determine whether the carbon brushes are in an abnormal state.

[0003] Existing technologies mostly rely on the static collection of single signals and single-parameter alarm modes. There are often deviations in the collection and response timing. Independent parameters are difficult to reveal periodic changes and collaborative trends between parameters. Multi-dimensional characteristics such as sudden changes in carbon brush wear, vibration synchronization and contact performance are difficult to comprehensively reflect, resulting in the monitoring results being unable to truly reflect the dynamic operating status. Risk warnings of equipment under high load fluctuations or abnormal working conditions are prone to omissions, periodic hidden dangers and structural anomalies are difficult to manage in a hierarchical manner, and operation and maintenance work faces problems such as data isolation, status distortion and delayed judgment. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent carbon brush monitoring device.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a carbon brush intelligent monitoring device, the device comprising: The timing synchronization acquisition module determines the carbon brush current and temperature sensor response time based on the timing pulses sent by the main control board, organizes the current and temperature sequences under the same pulse, compares the time tags of the collected data, calculates the synchronization characteristics, and obtains the current-temperature rise matching characteristics; The contact performance identification module compares the changes in the carbon brush contact resistance in each cycle based on the current-temperature rise matching characteristics, analyzes the resistance fluctuation curves before and after the disturbance, calculates the change amplitude and rate, determines the corresponding relationship with the stability benchmark, determines the difference between cycles, and obtains the contact performance fluctuation factor; The asynchronous feature recognition module screens the carbon brush wear data of the corresponding period based on the contact performance fluctuation factor, determines the frequency and distribution of wear mutation phenomena, analyzes the time of abnormal vibration signal events, compares the wear mutation and vibration abnormality time series within the period, identifies the synchronization situation, and obtains the wear-vibration synchronization event; Based on the wear-vibration synchronization events, the feature event alignment module analyzes the time distribution of wear and vibration mutation events, identifies the time differences within the same period, screens event combinations that exceed the interval, determines the proportion, summarizes the abnormal dislocation phenomena, and obtains the mutation dislocation proportion index.

[0006] The improvements of the present invention are that the current-temperature rise matching characteristics include current-temperature correlation parameters, synchronization statistical indicators, and timing consistency factors; the contact performance fluctuation factors include contact state fluctuation characteristics, periodic response discreteness, and stability evaluation results; the wear and vibration synchronization events include wear event identifiers, vibration event identifiers, and synchronization association groups; the mutation dislocation ratio indicators include periodic dislocation event ratios, timing offset intervals, and distribution ratio statistics.

[0007] The present invention is improved in that the timing synchronization acquisition module includes: The acquisition response judgment submodule determines the synchronization of the carbon brush current sensor and the temperature sensor in starting the acquisition action based on the timing pulses sent by the main control board. It compares the startup order of the sensors under the same signal trigger, determines whether there is a startup delay in each channel, and generates a response delay amplitude index. The synchronization characteristic calculation submodule compares the time stamps of the carbon brush current and temperature sensor data acquisition based on the response delay amplitude index, calculates the difference in data acquisition time intervals between channels under multiple cycles, summarizes the trend of time difference changes, and obtains the time synchronization stability level; The current-temperature-rise matching submodule selects data with consistent time sequence according to the time synchronization stability level, compares the distribution of carbon brush current and temperature data, analyzes the correlation between current data and temperature data, establishes a matching relationship, and obtains current-temperature-rise matching characteristics.

[0008] The present invention is improved in that the contact performance determination module includes: The response difference extraction submodule compares the change process of the carbon brush contact resistance before and after the disturbance cycle based on the current-temperature rise matching feature, integrates the data sequence at the difference time, optimizes the data consistency of each monitoring point in the same cycle, determines the trend of the resistance change trajectory, screens the typical interval, and obtains the disturbance response difference sequence; The resistance fluctuation calculation submodule compares the variation range of the contact resistance in the key period within the disturbance cycle based on the disturbance response difference sequence, analyzes the fluctuation of the resistance curve under the action of the disturbance, calculates the rise and fall amplitude of the resistance curve in the difference interval, determines the rate correlation between the continuous fluctuation data, and obtains the resistance fluctuation characteristic data; The key characteristic discrimination submodule determines whether the fluctuation characteristics of the resistance fluctuation characteristic data exceed the operating stability reference range, obtains the resistance offset strength index, analyzes its relationship with the reference range, identifies the continuous deviation phenomenon, and obtains the contact performance fluctuation factor.

[0009] The present invention is improved in that the asynchronous feature recognition module includes: The wear mutation extraction submodule analyzes the carbon brush wear data within the associated period based on the contact performance fluctuation factor, determines the rate variation characteristics of thickness change within a continuous period, compares the data sequences of adjacent time periods, calculates the fluctuation of the wear change rate, and obtains the wear mutation frequency sequence; The vibration anomaly identification submodule analyzes the vibration signal amplitude data within the corresponding period based on the wear mutation frequency sequence, optimizes the signal fluctuation analysis method, determines the abnormal fluctuation of the vibration amplitude in different time periods, compares the vibration amplitude changes in continuous intervals, and obtains the vibration amplitude anomaly sequence; The event synchronization identification submodule compares the time distribution of events according to the vibration amplitude abnormal sequence, analyzes the time intervals between event combinations, calculates the time synchronization index, and obtains the wear vibration synchronization event.

[0010] The present invention is improved in that the feature event alignment module includes: The time difference analysis submodule analyzes the occurrence time of the wear mutation and vibration mutation events within the same monitoring period based on the wear-vibration synchronization events, compares the time tags of the corresponding events, calculates the time interval between each group of events, determines the time distribution characteristics of the events, and obtains the event time offset sequence; The misaligned event screening submodule screens event combinations whose time intervals are greater than the synchronization determination interval based on the event time offset sequence, analyzes the synchronization status of the difference events, summarizes the unsynchronized events, and obtains a misaligned event combination set; The proportion index calculation submodule compares the maximum time interval and the average time interval in the dislocation events based on the dislocation event combination set, determines the proportion of dislocation events in the period and the offset fluctuation characteristics, and obtains the sudden change dislocation proportion index.

[0011] The present invention is improved in that the device further comprises: The operation risk warning module determines whether the misalignment ratio and the contact performance fluctuation factor simultaneously exceed the abnormality judgment criteria based on the sudden misalignment ratio indicator, analyzes the abnormal period and risk change trend, and determines that the carbon brush currently has a hidden danger of abnormal operation if the conditions are met, and obtains a structural abnormality risk classification; The structural abnormality risk classification includes a risk classification mark, a risk category mark, and an operational abnormality status indication.

[0012] The present invention is improved in that the operation risk warning module includes: The dislocation discrimination submodule analyzes the distribution of events reflected in the cycle based on the sudden dislocation ratio indicator, compares the state change amplitude of the contact performance fluctuation factor corresponding to the cycle, determines whether a consistent trend is shown in the same cycle, and obtains the dislocation and fluctuation overlap segments; The risk trend calculation submodule calculates the continuation and change in multiple consecutive cycles based on the overlapped segments of the dislocation and fluctuation, selects the synchronous change segments between cycles, analyzes the trend increase or decrease, and obtains the periodic risk trajectory; The structural risk grading submodule determines the grading boundary characteristics in the structural anomaly risk standard based on the periodic risk trajectory, compares the distribution range of the current cycle under each level classification, analyzes the risk category identification and the frequency of occurrence of abnormal operating conditions, and obtains the structural anomaly risk classification.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, when collecting multiple types of parameters of the carbon brush, the synchronous matching characteristics of current and temperature are actively constructed, the contact performance fluctuation factors under periodic disturbances are integrated, and through the synchronous judgment of wear mutations and vibration events, the synchronous grouping and dislocation ratio of wear vibration events are dynamically output, and a structural abnormality risk grading model is established to form a multi-level, time-series, and correlated carbon brush health assessment system, which supports trend monitoring, early warning and risk grading of key hidden dangers, enhances the intelligent diagnosis and data traceability capabilities under complex working conditions, and improves the fault identification and safety management level during the operation of the carbon brush. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of the device of the present invention; Figure 2 This is a flow chart of the timing synchronization acquisition module in the present invention; Figure 3 This is a flow chart of the contact performance discrimination module in the present invention; Figure 4 This is a flow chart of the asynchronous feature recognition module in the present invention; Figure 5 This is a flow chart of the feature event alignment module in the present invention; Figure 6 This is a flow chart of the risk warning module in the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, they should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined. Examples:

[0017] See also Figure 1 The present invention provides a technical solution: a carbon brush intelligent monitoring device includes: The timing synchronization acquisition module determines the acquisition response time of the carbon brush current sensor and temperature sensor based on the timing pulses sent by the main control board. It organizes the acquisition sequence of the carbon brush current and temperature under the same pulse signal, compares the time tags of the collected data at each moment, calculates the synchronization characteristics of the two sets of data on the time axis, and organizes the corresponding relationship between the carbon brush operating current and temperature to obtain the current-temperature rise matching characteristics. The contact performance identification module compares the change process of carbon brush contact resistance during different disturbance cycles based on the current-temperature rise matching characteristics, analyzes the fluctuation curve of carbon brush contact resistance before and after the disturbance, calculates the change amplitude and change rate of the resistance curve, determines the degree of correspondence between the change amplitude and the operating stability benchmark, and determines whether there are key differences in the resistance characteristics between cycles to obtain the contact performance fluctuation factor; The asynchronous feature recognition module screens the carbon brush wear data within the corresponding cycle based on the contact performance fluctuation factor, determines the frequency and time distribution of mutations in the wear information, analyzes the time when abnormal vibration signal amplitude events occur, and identifies synchronization by comparing the time series of wear mutations and vibration anomalies within the cycle, thereby obtaining wear-vibration synchronization events. The feature event alignment module analyzes the time distribution of wear mutation events and vibration mutation events based on wear and vibration synchronization events, identifies the time difference between wear and vibration mutation events within the same cycle, selects event combinations with time differences exceeding a specified range, determines the proportion of such combinations in all events, summarizes abnormal dislocation phenomena within the cycle, and obtains a mutation dislocation ratio indicator; The operation risk warning module is based on the sudden dislocation ratio indicator to determine whether the dislocation ratio and the contact performance fluctuation factor exceed the abnormal judgment criteria at the same time, and analyzes the cycle period and risk change trend of the abnormality. If the conditions are met, it is determined that the carbon brush currently has the risk of abnormal operation and obtains the structural abnormality risk classification.

[0018] The current-temperature rise matching characteristics include current-temperature correlation parameters, synchronization statistical indicators, and timing consistency factors. The contact performance fluctuation factors include contact state fluctuation characteristics, periodic response discreteness, and stability evaluation results. The wear and vibration synchronization events include wear event identification, vibration event identification, and synchronization correlation grouping. The mutation dislocation ratio indicator includes the periodic dislocation event ratio, timing offset interval, and distribution ratio statistics. The structural abnormality risk classification includes risk classification mark, risk category identification, and operation abnormality status indication.

[0019] In module 1, the timing pulse refers to the periodic electrical signal emitted by the main control board, which is used to trigger downstream sensors to start collecting various monitoring parameters under the same time reference, ensuring the time consistency of various types of data; the collection response time refers to the specific moment when the carbon brush current sensor and temperature sensor actually start collecting data after receiving the timing pulse signal. This time is used to determine whether the sensor response is synchronized; the collection sequence refers to a group of continuous data collected by the sensor in the order of the timing pulse. Each collection corresponds to a pulse trigger, forming an ordered data set; the time label refers to the time mark attached to each set of collected data, which is used to accurately mark the specific moment when the data is generated and is the basis for subsequent multi-source data alignment and comparison; the synchronization characteristic refers to the degree of temporal alignment of the data collected by multiple sensors under the same timing pulse. It is used to evaluate whether the signals of each channel are strictly synchronized and provide support for data fusion; the correspondence relationship refers to the pairing of current and temperature collection data one by one according to time to form a complete parameter pair of current and temperature rise of the carbon brush at a certain moment to reflect the working status of the carbon brush.

[0020] In Module 2, the differential disturbance cycle refers to the periodic time period in which the system is artificially subjected to different pulse load disturbances, which facilitates the comparison of the changing patterns of the carbon brush contact resistance under different working conditions before and after the disturbance; the contact resistance change process refers to the entire dynamic process in which the contact resistance between the carbon brush and the collector ring changes from the initial state to the disturbance, and then to recovery, during the disturbance cycle, reflecting the contact quality; the fluctuation curve refers to the value of the contact resistance changing with time plotted into a curve, which intuitively shows its fluctuation with the disturbance; the amplitude of change refers to the difference between the maximum and minimum values ​​of the contact resistance during the disturbance cycle; the rate of change refers to the speed of the resistance change, which can be measured by the resistance change within the time interval; the operating stability benchmark refers to the range or state of contact resistance that should be expected during normal operation of the equipment or system based on industry experience, experimental results, etc., which is used to identify abnormalities; the key difference refers to the contact resistance characteristics discovered through periodic comparison that are significantly different from the benchmark or the state of the previous cycle, which usually indicates abnormal carbon brush contact performance.

[0021] In Module 3, wear data refers to the record of carbon brush consumption changes over time measured by wear sensors such as displacement and thickness, which is the basis for determining the life and failure risk of carbon brushes; mutation phenomenon refers to the situation where wear data shows a significant sharp rise or drop in a short period of time, which often means abnormal physical wear of the carbon brush or external impact; vibration signal amplitude abnormality event refers to the event of sudden increase or decrease in the amplitude of the collected vibration signal. This fluctuation reflects problems such as loose mechanical structure and abnormal vibration of carbon brushes; time series refers to the data time axis sequence formed by arranging the specific time of occurrence of wear mutation events and vibration abnormality events; synchronization refers to the relationship between wear mutation events and vibration abnormality events in time, such as proximity, overlap, and sequence within the same period, which is used to reveal potential causal relationships.

[0022] In Module 4, the time distribution refers to the arrangement of the time points at which all wear mutations and vibration mutations occur within a monitoring period, which can be used to analyze the concentration or dispersion trend of events; the time difference refers to the length of the interval between wear mutations and vibration mutations on the time axis within the same period, which is a key parameter for measuring synchronization or misalignment; the limited interval refers to the time interval range (not a specific value) used to determine whether an event is "synchronous" or "misaligned", that is, if it is greater than this range, it is judged to be misaligned, and if it is less than this range, it is judged to be synchronized; the abnormal misalignment phenomenon refers to the situation where, within the monitoring period, the time differences of wear and vibration mutation events exceed the limited interval, which usually reflects abnormal operating conditions such as structural looseness or system interference.

[0023] In Module 5, the abnormality judgment standard refers to the judgment benchmark for identifying abnormal carbon brush status, such as the proportion of wear and vibration mutation dislocation, and the boundary line of contact performance fluctuation, which are all system preset standards; the abnormal cycle segment refers to the periodic interval in which abnormal indicators appear in the continuous monitoring cycle, and the cycle corresponds to the stage when the equipment working state is unstable and there are hidden fault risks; the risk change trend refers to the analysis of continuous cycle monitoring data to show the changing direction and rate of risk level, which can help judge the development trend of faults.

[0024] See also Figure 2 , the timing synchronization acquisition module includes: The acquisition response judgment submodule determines the synchronization of the carbon brush current sensor and the temperature sensor in starting the acquisition action based on the timing pulses sent by the main control board. It compares the startup order of the sensors under the same signal trigger, determines whether there is a startup delay in each channel, and generates a response delay amplitude index. The pulse is set as a periodic electrical signal, for example, with a period of 100 milliseconds and a fixed voltage amplitude of 5 volts. This pulse triggers the carbon brush current sensor and temperature sensor to collect data. After receiving the pulse, each sensor starts data collection through an internal trigger mechanism. The actual start time of each sensor is then recorded and stored as an acquisition timestamp. Each timestamp is generated by the main control board's built-in clock. All acquisition start times are compared with the time of the pulse signal to obtain the acquisition start delay value for each channel. In actual operation, if the current sensor records the acquisition start time as 21.5 milliseconds after the pulse trigger and the temperature sensor records it as 20.1 milliseconds, then the current sensor has a 1.4 millisecond delay relative to the temperature sensor. This delay value is stored in the response delay data group and then the preset time synchronization judgment threshold is called for judgment. If the delay value is less than the set 2 millisecond threshold, it is marked as "synchronous start". If it exceeds 2 milliseconds, it is marked as "asynchronous start". The judgment result is continuously counted based on the start delay record after each sensor acquisition, generating a series of response delay amplitude indicators over multiple acquisition cycles as the basis for time synchronization assessment.

[0025] The synchronization characteristic calculation submodule compares the time stamps of the carbon brush current and temperature sensor data acquisition based on the response delay amplitude index, calculates the difference in data acquisition time intervals between channels under multiple cycles, summarizes the trend of time difference changes, and obtains the level of time synchronization stability; Extract the acquisition time tags of the current sensor and temperature sensor after each timing pulse is triggered, and compare the actual acquisition time difference of each channel in the same cycle. In actual operation, 5 cycles can be monitored continuously, and the recorded time differences are 1.2 milliseconds, 1.6 milliseconds, 1.4 milliseconds, 2.3 milliseconds, and 3.1 milliseconds, respectively. All time differences are uniformly distributed to the preset delay intervals, for example, 0 to 2 milliseconds is the synchronous interval, and 2 to 5 milliseconds is the asynchronous interval. Then, by counting the number of cycles of data acquisition in each interval and calculating the proportion of different delay levels, the distribution trend of the acquisition time difference between channels in continuous cycles is obtained. A sliding calculation method is used to evaluate the fluctuation range of the time difference value set, extracting the degree of fluctuation and changing trend of the set. In an actual example, if the average acquisition delay difference in the first 50 cycles is 1.92 milliseconds and the fluctuation amplitude is 0.78 milliseconds, the average value and fluctuation amplitude are compared with the preset stability threshold based on the set stability judgment standard. If the average difference is less than 2 milliseconds and the fluctuation value is less than 1 millisecond, the state is evaluated as "medium stability". Otherwise, it is judged as "low stability" or "high stability". Finally, the time synchronization stability level label of the channel combination is output, and the synchronization performance of each cycle is categorized and marked for use as a basis for matching data screening.

[0026] The current-temperature matching submodule selects data with consistent time sequence based on the time synchronization stability level, compares the distribution of carbon brush current and temperature data, analyzes the correlation between current data and temperature data, establishes a matching relationship, and obtains the current-temperature matching characteristics; During data screening, only the acquisition period data with synchronization stability of "high stability" or "medium stability" level is retained. All the acquisition data in the period determined to be "low stability" will be eliminated. Then the retained current and temperature acquisition data will be re-sorted in the order of acquisition time, and two one-to-one corresponding parameter sequences are constructed. Each current value is paired with the temperature value collected at the same time point to form a parameter pair. After completing the parameter pairing, the difference of the pairing is extracted and recorded group by group to form a set of difference sequence representing the correspondence between current and temperature changes. In practical applications, the average value and maximum value in the difference sequence are counted as the consistency parameter of the paired data. Based on the examination, if the difference is small, it means that the pairing relationship is stable and consistent. If the difference is large, it means that there is an inconsistent response to temperature and current changes in the pairing. For example, the average difference calculated in a set of data is 0.8, and the maximum difference is 2.3. According to the set matching classification standard, a strong pairing must meet the average difference of less than 0.5 and the maximum difference of less than 1. Otherwise, it is marked as a weak pairing or an abnormal pairing. Finally, the pairing strength level ratio information in multiple acquisition cycles is output, for example, strong pairing cycles account for 60%, weak pairing cycles account for 30%, and abnormal pairing accounts for 10%, and the pairing level sequence is output as the current-temperature rise matching feature.

[0027] See also Figure 3 , the contact performance judgment module includes: The response difference extraction submodule compares the change process of carbon brush contact resistance before and after the disturbance cycle based on the current-temperature rise matching characteristics, integrates the data sequence at the difference time, optimizes the data consistency of each monitoring point in the same cycle, determines the trend of the resistance change trajectory, screens typical intervals, and obtains the disturbance response difference sequence; The monitoring data before and after the disturbance period is called, and the continuously collected data of the carbon brush contact resistance 10 seconds before and after the disturbance period is extracted. The data is divided into 200 groups of contact resistance values ​​at a sampling frequency of 10 times per second. The disturbance starting point is set to t=0. The resistance sequence from t=−10 seconds to t=0 seconds and the resistance sequence from t=0 seconds to t=10 seconds are named as the pre-disturbance sequence and the post-disturbance sequence respectively. During the comparison process, the difference between the average resistance of each second in the two time periods is calculated and the difference sequence is recorded. In this example, if the resistance of the pre-disturbance sequence is 0.032 ohms at t=−3 seconds and the resistance of the post-disturbance sequence is 0.041 ohms at t=3 seconds, the difference is 0.009 ohms. In this way, a list of difference time points is constructed, and points with significant differences are extracted. The judgment criterion is that when the difference is greater than 0.005 ohms, it is marked as a "significant difference point". This threshold is derived from the statistical data when the equipment is running stably. The upper limit of the resistance standard fluctuation range is obtained, and the current, temperature, and vibration data corresponding to all the difference points are integrated to form a data sequence at the difference moment. Then, according to the acquisition time of the monitoring points in the same period in the data sequence, a time alignment operation is performed. Even if there are slight differences in the sampling intervals of data from different channels, linear interpolation is performed to fill in the gaps or the misaligned points are directly discarded by comparing the acquisition time labels. In this way, the time consistency between data in the same period is optimized. Then, the trend of the resistance change trajectory is judged, and the peak and trough positions are extracted on each resistance time series. The increase and decrease amplitude and duration between the peaks and troughs are calculated to determine whether the trend is continuously rising, continuously falling, or fluctuating. In this example, if the curve is flat before the disturbance and rapidly rising after the disturbance, the periodic change trajectory is judged to be "rising type". Then, the intervals with continuous changes of more than 3 seconds are selected as typical intervals to obtain the disturbance response difference sequence.

[0028] The resistance fluctuation calculation submodule compares the variation range of contact resistance in key periods within the disturbance cycle based on the disturbance response difference sequence, analyzes the fluctuation of the resistance curve under the action of the disturbance, calculates the rise and fall amplitude of the resistance curve in the difference interval, determines the rate correlation between continuous fluctuation data, and obtains the resistance fluctuation characteristic data; Select the resistance time period marked as the typical interval in each disturbance cycle, take the resistance values ​​at the starting and ending points of the interval respectively, perform the difference calculation to obtain the variation range. If the starting resistance is 0.035 ohms and the ending resistance is 0.046 ohms, the variation range is 0.011 ohms. Then record the resistance value change data of each second in the entire typical interval as a fluctuation curve sequence. In this example, if the typical interval length is 5 seconds, extract the resistance value sequence within 5 seconds, and then calculate the resistance difference between any two adjacent seconds in the sequence as the resistance change rate per unit time. The maximum, minimum and average values ​​of the rate set are extracted, and the fluctuation amplitude and fluctuation trend are statistically analyzed. The judgment standard is that if the maximum change rate is greater than 0.004 ohms / second and the minimum rate is less than 0.001 ohms / second, it is marked as rate-discrete fluctuation; if the overall change rate is between 0.002 and 0.003 ohms / second, it is marked as rate-balanced fluctuation. Then, by comparing the difference between the change rates of any two consecutive data segments, if the difference between the rates of three consecutive segments is less than 0.001 ohms / second, it is considered to have rate correlation, otherwise it is an uncorrelated rate. The above operation is performed on each resistance curve of the disturbance response difference sequence one by one, and finally the resistance fluctuation characteristic data containing the resistance change range, fluctuation type, and rate correlation labels are obtained.

[0029] The key characteristic identification submodule determines whether the resistance fluctuation characteristic data exceeds the operating stability benchmark range using the formula: ; Get resistance offset strength indicator , analyze its relationship with the benchmark interval, identify the continuous deviation phenomenon, and obtain the contact performance fluctuation factor, among which, Indicates the maximum number of contact resistance samples within the disturbance period, that is, the maximum contact resistance data point monitored within the period. Indicates the minimum sampling number of contact resistance during the disturbance period, that is, the minimum data point of contact resistance monitored during the period. It represents the average number of contact resistance samples during the disturbance period, that is, the average number of contact resistance data of all monitoring points. It represents the standard deviation of the time intervals between sampling moments within the disturbance period, and is used to measure the degree of discreteness of the time intervals of each sampling point, reflecting the uniformity of the time series distribution of the acquisition process. Indicates the first The time corresponding to the collection moment, Indicates the total number of sampling moments within the disturbance period.

[0030] The resistance offset strength index refers to a comprehensive statistical data used to reflect the overall fluctuation amplitude and rate of change of the carbon brush contact resistance during the time series change of the disturbance period during the intelligent monitoring process of the carbon brush. It can intuitively reflect whether the fluctuation range of the carbon brush contact resistance is abnormally expanded and whether the change trend becomes unstable under the abnormal disturbance period, thereby assisting in judging whether there is any obvious abnormality in the contact performance of the carbon brush during this period.

[0031] To determine whether its fluctuation characteristics exceed the operating stability benchmark range, it is necessary to conduct a joint analysis based on the resistance fluctuation amplitude, time coverage, and balance of the resistance change process within the disturbance period. In the specific implementation process, the key values ​​extracted from the resistance fluctuation curve are first confirmed. Taking this acquisition as an example, the maximum number of contact resistance samples within the disturbance period is set to , the minimum number of samples is , each time point in the cycle is 、 、 、 、 , the sum of which is , the average number of resistance samples is The standard deviation of the five sampling intervals is calculated using the standard formula: In order to ensure the adaptability of different physical quantity units in a unified expression, each participating item is converted to dimensionless according to the normalization standard. The normalized parameters are: 、 、 、 、 ; Substituting the above values ​​into the formula: ; This value is the resistance offset strength index of the contact resistance in this cycle. The numerical result can be compared and analyzed with the set stability reference range. For example, the reference interval is 0.00–0.25. If the value of this index exceeds the upper limit, it is determined that there is a continuous deviation feature in the periodic contact state. Based on the above results, it can be identified that the carbon brush contact resistance state has abnormal fluctuation behavior in this disturbance cycle, and it is necessary to enter the subsequent fluctuation behavior classification and structural stability judgment process to obtain the contact performance fluctuation factor. The formula constructs a multi-factor fusion judgment mechanism by simultaneously coupling the dynamic change range of the contact resistance, the total span of the sampling time and the discrete level of the fluctuation time series, which can comprehensively determine the true impact of the periodic disturbance on the contact performance.

[0032] See also Figure 4 , the asynchronous feature recognition module includes: The wear mutation extraction submodule analyzes the carbon brush wear data within the associated cycle based on the contact performance fluctuation factor, determines the rate variation characteristics of thickness change within a continuous period, compares the data series of adjacent time periods, calculates the fluctuation of the wear change rate, and obtains the wear mutation frequency series; Extract the corresponding monitoring cycle number, call the carbon brush wear thickness data sequence within the cycle, and obtain continuous thickness data points at a sampling rate of 1 per second. For example, when the cycle is 30 seconds, a total of 30 thickness sampling values ​​are obtained. Then, divide it into multiple equal-length periods according to the acquisition order, each containing 5 seconds of data. Calculate the total thickness change in each period and divide it by the duration of the period to obtain the wear rate sequence. In the actual sample, in the first 5-second period, the thickness decreases from 15.20 mm to 15.17 mm, and the wear rate is 0.003 mm / s. In the second 5-second period, the thickness decreases from 15.17 mm to 15.12 mm, and the corresponding rate is 0.01 mm / s, and so on. The wear rate of multiple time periods is obtained, and then the difference between two adjacent rate values ​​is calculated to form a rate change sequence. For example, the rate difference from 0.003 to 0.01 is 0.007 mm / s. Then the next difference is extracted and the entire set of change amplitude sequences is constructed. The reference threshold for judging mutations is set to 0.006 mm / s. This threshold is derived from the maximum rate fluctuation amplitude within the 95% confidence range in the first 500 cycle data. When the rate change amplitude is greater than the threshold, it is recorded as a mutation point. Each time a mutation point is detected, a count is added to the wear mutation frequency record table to form a wear mutation frequency sequence corresponding to each monitoring cycle. This sequence is used for subsequent alignment and comparison with vibration information.

[0033] The vibration anomaly identification submodule analyzes the vibration signal amplitude data within the corresponding period based on the wear mutation frequency sequence, optimizes the signal fluctuation analysis method, determines the abnormal fluctuation of the vibration amplitude in different time periods, compares the vibration amplitude changes in continuous intervals, and obtains the vibration amplitude anomaly sequence; The periods with non-zero mutation frequency are selected as analysis periods, and the vibration signal amplitude data within the corresponding period is extracted. The original vibration signal is processed. First, the time period is divided by a fixed sliding window. For example, every 3 seconds is an analysis window. The difference between the maximum and minimum values ​​of the vibration signal within the window is calculated as the amplitude fluctuation value of the current window. In the example, the maximum value of the vibration signal in a certain 3-second window is 2.5, and the minimum value is 0.8, then the fluctuation amplitude is 1.7. If the difference in the fluctuation amplitude in three consecutive analysis windows exceeds 1.2, and the minimum window amplitude is less than 0.8, and the maximum window amplitude is greater than 2.0, then the current period vibration is marked as abnormal. Fluctuation: Arrange the fluctuation amplitudes of all analysis windows in the current cycle to form a vibration fluctuation sequence, and determine the time window with the most significant difference, mark it as the difference time period, and then extract the vibration amplitude value of each second in the difference time period and compare it with the average value of the adjacent windows. If the difference between the amplitude value at a certain point in time and the adjacent average value is greater than 1.0, it is identified as an abnormal point in time and recorded in the abnormal sequence. The number of abnormal points in each cycle is the vibration abnormality frequency. Further organize the points with abnormal amplitude values ​​exceeding 2.0 in each cycle to form the final vibration amplitude abnormal sequence, which is used for subsequent synchronous analysis and alignment with wear mutation events.

[0034] The event synchronization identification submodule compares the time distribution of events based on the abnormal sequence of vibration amplitudes and analyzes the time intervals between event combinations using the formula: ; Calculating time synchronization indicators , we get the wear vibration synchronization event, where Indicates the total number of synchronization events, Indicates the The time point of each wear mutation event, Indicates the The time point of the abnormal vibration event corresponding to the wear event, Indicates the The time point fluctuation compensation factor for each event pair, Indicates the The time distribution dispersion coefficient of event pairs.

[0035] The temporal synchronization index is a parameter used to measure the consistency and degree of synchronization of the temporal distribution of sudden carbon brush wear events and abnormal vibration events within the same cycle. It is used to determine whether the two abnormal wear and vibration events are temporally correlated, serving as an important basis for subsequent fault diagnosis, risk identification, and structural anomaly analysis. For example, if wear and vibration anomalies frequently occur simultaneously, it indicates a special risk in the mechanical structure or operating state.

[0036] According to the vibration amplitude abnormal sequence, the wear mutation time point of each event and its corresponding vibration abnormal time point are extracted, and the event time pairs are formed in sequence. The time difference under the same event number is compared, and the time interval between all event time pairs is calculated and substituted into the corresponding fluctuation compensation factor. and the distribution dispersion coefficient To analyze the time synchronization between the two types of events, the time points of event numbers 1 to 4 are: the wear event time points are 1023ms, 1874ms, 2560ms, and 3120ms, and the corresponding vibration event time points are 1050ms, 1902ms, 2610ms, and 3185ms. After calculation, the time differences are 27ms, 28ms, 50ms, and 65ms, respectively. The corresponding normalized time differences are 0.27, 0.28, 0.50, and 0.65, respectively. Each time difference is corrected and weighted in combination with the fluctuation compensation factor. The parameter Set them to 0.12, 0.15, 0.08, and 0.10 respectively, and calculate the product of each term as follows: Group 1: ; Group 2: ; Group 3: ; Group 4: ; Adding the above results together gives the numerator: ; The denominator uses the normalized distribution coefficient , which are set to 0.05, 0.07, 0.04, and 0.06, and the corresponding correction terms are 1.05, 1.07, 1.04, and 1.06, respectively. The sum is: ; Calculating time synchronization indicators for: ; This numerical result indicates that abnormal wear and vibration events exhibit a certain degree of temporal synchronization within this monitoring period. Comparing these events with the set synchronization standard interval [0.40, 0.60] indicates that these events are classified as medium-level synchronization, demonstrating a certain degree of synergy and enabling joint analysis and processing of subsequent risk events. The formula uses the root of square difference to measure the absolute distance of the time difference, a fluctuation compensation factor to adjust the intensity of the event response, and a distribution dispersion coefficient to suppress statistical deviations from overly concentrated event pairs. The overall calculation incorporates both inter-event variability and periodic stability, reflecting the temporal consistency of structural anomalies.

[0037] See also Figure 5 , the feature event alignment module includes: The time difference analysis submodule is based on wear-vibration synchronization events. It analyzes the occurrence time of wear mutation and vibration mutation events within the same monitoring period, compares the time tags of the corresponding events, calculates the time interval between each group of events, determines the time distribution characteristics of the events, and obtains the event time offset sequence. Call the event data marked as wear mutation and vibration mutation in the current monitoring cycle, extract the time tags of their respective recorded occurrence times, for example, in a certain monitoring cycle, the wear mutation event occurs at 12.3 seconds, 17.8 seconds, and 25.5 seconds, and the vibration mutation event occurs at 12.1 seconds, 18.5 seconds, and 25.9 seconds. Pair the wear mutation time tags with the vibration mutation time tags in the order of the time axis. The pairing principle is to find the event pair with the shortest time distance. Calculate the time interval between the paired events group by group. The interval is the vibration mutation occurrence time minus the corresponding wear mutation occurrence time. If the interval of the first group is -0.2 seconds, the second group is 0.7 seconds, and the third group is 0.4 seconds, the interval values ​​are summarized to form a time offset value list and marked according to the positive and negative signs of the time. The order of events is calculated. A positive value indicates that vibration lags behind wear, while a negative value indicates that vibration precedes wear. The time offset list is then divided into intervals and statistics are calculated. The interval division is set as the synchronization interval of ±0.3 seconds, the mild offset interval of ±0.3 to ±0.8 seconds, and the severe offset interval of greater than ±0.8 seconds. The division standard is based on the 80% concentrated distribution segment obtained in the previous actual test process as the synchronization interval threshold. Each time offset value is allocated to the above three intervals, and the proportion of events in each interval is counted. For example, if there are 5 pairs of events, 3 pairs are in the synchronization interval, 1 pair is in the mild offset interval, and 1 pair is in the severe offset interval, then the synchronization ratio is 60%. Finally, the event time offset sequence is output periodically. The sequence indicates the time interval value, offset direction, and classification label of each pair of events.

[0038] The misaligned event screening submodule screens event combinations whose time intervals are greater than the synchronization determination interval based on the event time offset sequence, analyzes the synchronization of the difference events, and summarizes the unsynchronized events to obtain the misaligned event combination set; First, select all event groups whose time interval values ​​are greater than the preset synchronization judgment interval. The preset synchronization judgment interval is set to a time difference of 0.3 seconds or less in absolute value. Any event exceeding this interval is considered to be an unsynchronized event combination. For example, if the time difference of an event pair is 0.65 seconds, the combination is judged to be a misaligned event. All event pairs exceeding ±0.3 seconds are screened again and marked as difference events. The time difference value and event identification number are recorded. The frequency of occurrence of the misaligned event in the cycle segment is then counted. If there are more than three misaligned event combinations in a cycle, the cycle is marked as an abnormally high-frequency misaligned cycle. , judge the synchronization status of each misalignment event combination, and record whether there are asymmetric patterns such as long lag, advance, and repeated changes by comparing the order of occurrence of vibration and wear events. In the example, if the vibration mutation always occurs 3 seconds after the wear event, it is marked as "long lag type misalignment". If the wear precedes the vibration by less than 1 second but frequently intersects, it is marked as "alternating type misalignment". Then, summarize all event pairs that do not meet the synchronization interval judgment criteria, summarize their time difference, misalignment type, cycle number, event sequence and other information, and organize the information into a misalignment event combination set for further analysis of the proportion and distribution trend of the combination in the cycle operation.

[0039] The proportion index calculation submodule compares the maximum time interval and average time interval in the dislocation events based on the dislocation event combination set, using the formula: ; Determine the proportion of dislocation events and the characteristics of offset fluctuations within the cycle to obtain the sudden dislocation proportion index ,in, represents the number of misalignment event combinations, Indicates the maximum time interval between the wear mutation event and the vibration mutation event in all combinations of misalignment events. It represents the average time interval of all event pairs, that is, the average time interval of all wear mutation and vibration mutation events. represents the number of all event pairs, Indicates the In the combination of group dislocation events, the product of the wear mutation amplitude and the vibration mutation amplitude measures the combined intensity of abnormal fluctuations in the combination. It represents the average of the product of the wear mutation amplitude and the vibration mutation amplitude in all combinations of misalignment events.

[0040] The mutation misalignment ratio indicator is a comprehensive statistical parameter used to measure the proportion and distribution characteristics of the carbon brush wear mutation events and vibration mutation events that are not synchronized in time (i.e., "misalignment") within a monitoring period. It can directly reflect the severity of abnormal wear and vibration event misalignment of components such as carbon brushes and slip rings during actual operation, help to discover risks such as loose equipment structure and abnormal system interference in advance, and provide a quantitative basis for intelligent monitoring and risk warning.

[0041] First determine the number of misalignment events , the total number of event combinations is , where the 8th and 10th groups are dislocation event combinations. The wear mutation times of the 8th and 10th groups have been identified as 830 seconds and 1040 seconds, respectively. The corresponding vibration mutation times are 825 seconds and 1035 seconds, respectively. The time intervals are calculated to be 5 seconds. The maximum time interval is set to The average total time interval is , and then extract the wear mutation amplitude and vibration mutation amplitude from the monitoring data, normalize the original data, and set the wear mutation amplitude of the 8th group to be 2.5mm and the vibration mutation amplitude to be 2.6g. The corresponding product after normalization is , the wear mutation amplitude of group 10 is 2.7mm, the vibration mutation amplitude is 3.0g, and the normalized product is , calculate the average product , and then substitute the above parameters into the formula: ; ; The results show that during the monitoring period, the proportion of misalignment events reached about 96.15% after adjustment for the joint fluctuation term, reflecting that although the number of events was small, the offset distribution had a dominant trend due to the significant concentration of time intervals and fluctuation intensity. The final generated parameter was defined as the mutation misalignment ratio index, which can be used to comprehensively evaluate the relative offset degree of event combinations under asynchronous characteristics, and assist in identifying potential abnormal periodic segments of carbon brush wear. The formula combines the time interval and the dual-parameter amplitude offset, and constructs the denominator by the square root plus absolute deviation method, so that the indicator has a more sensitive response capability when facing small samples with high volatility.

[0042] See also Figure 6 , the operation risk warning module includes: The dislocation discrimination submodule analyzes the distribution of events reflected in the cycle based on the mutation dislocation ratio indicator, compares the state change amplitude of the contact performance fluctuation factor corresponding to the cycle, determines whether it shows a consistent trend within the same cycle, and obtains the overlap segments of dislocation and fluctuation; Extract the event time difference statistics table within the current monitoring cycle, calculate the misalignment ratio value of the cycle based on the number of event pairs recorded therein and the number of event combinations falling into the asynchronous interval, divide the number of misaligned event pairs in each cycle by the total number of event pairs, and obtain the mutation misalignment ratio index of the cycle. For example, in the 35th cycle, there are 10 wear-vibration event pairs, of which 4 groups have time differences exceeding the synchronization judgment threshold of 0.3 seconds, then the misalignment ratio is 0.4. Then analyze whether the time position of each misalignment event in the cycle coincides with the contact resistance fluctuation degree in the corresponding cycle of the contact performance fluctuation factor data. The resistance fluctuation degree is expressed as contact The resistance change amplitude is used as a benchmark. The difference between the maximum and minimum values ​​of the resistance curve in the same cycle is extracted as the fluctuation amplitude. For example, if the fluctuation amplitude is 0.012 ohms, the resistance fluctuation amplitude is set to be higher than 0.01 ohms, which is considered to be significant. If the current cycle satisfies both the misalignment ratio higher than 0.3 and the resistance fluctuation amplitude higher than 0.01 ohms, the cycle is marked as a cycle in which the misalignment and fluctuation appear in the same direction. It is determined whether both types of characteristic values ​​exceed the set threshold in the same cycle. If so, the cycle number is included in the misalignment and fluctuation overlap segment, and finally a joint result of the cycle number, its corresponding misalignment ratio value, and the resistance fluctuation amplitude value is generated.

[0043] The risk trend calculation submodule calculates the continuation and changes in multiple consecutive cycles based on the overlap of dislocation and fluctuation, screens the synchronous change segments between cycles, analyzes the trend increase or decrease, and obtains the cyclical risk trajectory; Extract the period numbers recorded as overlapping segments in multiple consecutive periods, arrange them in chronological order, and then calculate whether there is continuity between the numbers. For example, if the segment period numbers are 35, 36, 37, 40, and 41, identify two consecutive segments as 35 to 37 and 40 to 41. Then judge the changes in the overlapping characteristics in each continuous segment, extract the misalignment ratio and resistance fluctuation amplitude value in each period, construct two series in increasing order of period, perform adjacent item difference calculation on the two series respectively and record the positive and negative differences. If all differences are positive, it is judged as an increasing trend. If they are negative, it is judged as a decreasing trend. If there is a sign alternation It is judged to be a fluctuating type. In the example, if the dislocation ratio of the 35th cycle is 0.34, the 36th cycle is 0.41, and the 37th cycle is 0.49, the dislocation feature is increasing. If the resistance fluctuation amplitude is 0.011, 0.013, and 0.018 ohms respectively, the fluctuation trend is also increasing. This section is judged to be a synchronous increasing risk section. This section is marked as a risk-aggravated section. The same analysis process is performed on the next section, and the trend type and start and end cycle numbers of each interval are recorded. Finally, the set of intervals with trend changes in all monitoring periods is output to form a periodic risk trajectory. The trajectory structure is arranged in order and accompanied by trend labels and characteristic parameters.

[0044] The structural risk classification submodule determines the classification boundary characteristics of the structural abnormality risk standard based on the periodic risk trajectory, compares the distribution range of the current cycle under each level classification, analyzes the risk category identification and the frequency of occurrence of abnormal operation status, and obtains the structural abnormality risk classification; The set structural anomaly risk level boundary value table is called. This table defines three risk level classification criteria: Level 1 risk requires a misalignment ratio greater than 0.5 and a resistance fluctuation greater than 0.02 ohms; Level 2 risk requires a misalignment ratio greater than 0.35 and less than or equal to 0.5, and a resistance fluctuation between 0.015 and 0.02 ohms; Level 3 risk requires a misalignment ratio between 0.25 and 0.35, and a resistance fluctuation greater than 0.01 ohms and less than or equal to 0.015 ohms. The parameters of each cycle in the periodic risk trajectory are compared with the upper and lower limits of each level. If the misalignment ratio in a cycle is 0.52 and the resistance fluctuation is 0, then the risk level is determined to be 0. If the value is 0.023 ohms, it meets the first-level risk condition. If it is 0.38 and 0.016 ohms, it is classified as second-level. Then the frequency of occurrence of each level of risk is counted by cycle. Within 50 cycles, the first-level risk occurs 5 times, the second-level risk occurs 12 times, and the third-level risk occurs 18 times. The rest are normal or undefined levels. The frequency of occurrence is counted, and the first-level risk is 10%, the second-level risk is 24%, and the third-level risk is 36%. The risk category identifier and the cycle number are stored in the structural abnormality classification record table, and an abnormal operation status mark field is added to record whether there is a sharp increase in vibration or a sudden increase in current in the corresponding cycle. Finally, the structural abnormality risk classification result sequence is output.

[0045] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. Carbon brush intelligent monitoring device, characterized in that: The device comprises: The timing synchronization acquisition module determines the carbon brush current and temperature sensor response time based on the timing pulses sent by the main control board, organizes the current and temperature sequences under the same pulse, compares the time tags of the collected data, calculates the synchronization characteristics, and obtains the current-temperature rise matching characteristics; The contact performance identification module compares the changes in the carbon brush contact resistance in each cycle based on the current-temperature rise matching characteristics, analyzes the resistance fluctuation curves before and after the disturbance, calculates the change amplitude and rate, determines the corresponding relationship with the stability benchmark, determines the difference between cycles, and obtains the contact performance fluctuation factor; The asynchronous feature recognition module screens the carbon brush wear data of the corresponding period based on the contact performance fluctuation factor, determines the frequency and distribution of wear mutation phenomena, analyzes the time of abnormal vibration signal events, compares the wear mutation and vibration abnormality time series within the period, identifies the synchronization situation, and obtains the wear-vibration synchronization event; Based on the wear-vibration synchronization events, the feature event alignment module analyzes the time distribution of wear and vibration mutation events, identifies the time differences within the same period, screens event combinations that exceed the interval, determines the proportion, summarizes the abnormal dislocation phenomena, and obtains the mutation dislocation proportion index.

2. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The current-temperature rise matching characteristics include current-temperature correlation parameters, synchronization statistical indicators, and timing consistency factors; the contact performance fluctuation factors include contact state fluctuation characteristics, periodic response discreteness, and stability evaluation results; the wear-vibration synchronization events include wear event identifiers, vibration event identifiers, and synchronization association groups; the mutation dislocation ratio indicators include periodic dislocation event ratios, timing offset intervals, and distribution ratio statistics.

3. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The timing synchronization acquisition module includes: The acquisition response judgment submodule determines the synchronization of the carbon brush current sensor and the temperature sensor in starting the acquisition action based on the timing pulses sent by the main control board. It compares the startup order of the sensors under the same signal trigger, determines whether there is a startup delay in each channel, and generates a response delay amplitude index. The synchronization characteristic calculation submodule compares the time stamps of the carbon brush current and temperature sensor data acquisition based on the response delay amplitude index, calculates the difference in data acquisition time intervals between channels under multiple cycles, summarizes the trend of time difference changes, and obtains the time synchronization stability level; The current-temperature-rise matching submodule selects data with consistent time sequence according to the time synchronization stability level, compares the distribution of carbon brush current and temperature data, analyzes the correlation between current data and temperature data, establishes a matching relationship, and obtains current-temperature-rise matching characteristics.

4. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The contact performance determination module includes: The response difference extraction submodule compares the change process of the carbon brush contact resistance before and after the disturbance cycle based on the current-temperature rise matching feature, integrates the data sequence at the difference time, optimizes the data consistency of each monitoring point in the same cycle, determines the trend of the resistance change trajectory, screens the typical interval, and obtains the disturbance response difference sequence; The resistance fluctuation calculation submodule compares the variation range of the contact resistance in the key period within the disturbance cycle based on the disturbance response difference sequence, analyzes the fluctuation of the resistance curve under the action of the disturbance, calculates the rise and fall amplitude of the resistance curve in the difference interval, determines the rate correlation between the continuous fluctuation data, and obtains the resistance fluctuation characteristic data; The key characteristic discrimination submodule determines whether the fluctuation characteristics of the resistance fluctuation characteristic data exceed the operating stability reference range, obtains the resistance offset strength index, analyzes its relationship with the reference range, identifies the continuous deviation phenomenon, and obtains the contact performance fluctuation factor.

5. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The asynchronous feature recognition module includes: The wear mutation extraction submodule analyzes the carbon brush wear data within the associated period based on the contact performance fluctuation factor, determines the rate variation characteristics of thickness change within a continuous period, compares the data sequences of adjacent time periods, calculates the fluctuation of the wear change rate, and obtains the wear mutation frequency sequence; The vibration anomaly identification submodule analyzes the vibration signal amplitude data within the corresponding period based on the wear mutation frequency sequence, optimizes the signal fluctuation analysis method, determines the abnormal fluctuation of the vibration amplitude in different time periods, compares the vibration amplitude changes in continuous intervals, and obtains the vibration amplitude anomaly sequence; The event synchronization identification submodule compares the time distribution of events according to the vibration amplitude abnormal sequence, analyzes the time intervals between event combinations, calculates the time synchronization index, and obtains the wear vibration synchronization event.

6. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The feature event alignment module includes: The time difference analysis submodule analyzes the occurrence time of the wear mutation and vibration mutation events within the same monitoring period based on the wear-vibration synchronization events, compares the time tags of the corresponding events, calculates the time interval between each group of events, determines the time distribution characteristics of the events, and obtains the event time offset sequence; The misaligned event screening submodule screens event combinations whose time intervals are greater than the synchronization determination interval based on the event time offset sequence, analyzes the synchronization status of the difference events, summarizes the unsynchronized events, and obtains a misaligned event combination set; The proportion index calculation submodule compares the maximum time interval and the average time interval in the dislocation events based on the dislocation event combination set, determines the proportion of dislocation events in the period and the offset fluctuation characteristics, and obtains the sudden change dislocation proportion index.

7. The carbon brush intelligent monitoring device according to claim 1, characterized in that: The device further comprises: The operation risk warning module determines whether the misalignment ratio and the contact performance fluctuation factor simultaneously exceed the abnormality judgment criteria based on the sudden misalignment ratio indicator, analyzes the abnormal period and risk change trend, and determines that the carbon brush currently has a hidden danger of abnormal operation if the conditions are met, and obtains a structural abnormality risk classification; The structural abnormality risk classification includes a risk classification mark, a risk category mark, and an operational abnormality status indication.

8. The carbon brush intelligent monitoring device according to claim 7, characterized in that: The operation risk warning module includes: The dislocation discrimination submodule analyzes the distribution of events reflected in the cycle based on the sudden dislocation ratio indicator, compares the state change amplitude of the contact performance fluctuation factor corresponding to the cycle, determines whether a consistent trend is shown in the same cycle, and obtains the dislocation and fluctuation overlap segments; The risk trend calculation submodule calculates the continuation and change in multiple consecutive cycles based on the overlapped segments of dislocation and fluctuation, selects the synchronous change segments between cycles, analyzes the trend increase or decrease, and obtains the periodic risk trajectory; The structural risk grading submodule determines the grading boundary characteristics in the structural anomaly risk standard based on the periodic risk trajectory, compares the distribution range of the current cycle under each level classification, analyzes the risk category identification and the frequency of occurrence of abnormal operating conditions, and obtains the structural anomaly risk classification.

Images