Motor performance monitoring data processing system

Abstract

The invention relates to the technical field of data processing, in particular to a motor performance monitoring data processing system which comprises a signal registration module, a rhythm judgment module, a trend lag module, an effect recognition module and a label scheduling module. According to the method, the waveband gravity center is established by identifying extreme points, trend comparison is performed, a gravity center alignment structure between different channels is constructed, the time period rhythm stability is judged based on the sampling interval change trend, abnormal paragraphs are marked, and the response lag time period is positioned in combination with the rotation speed slope change and the current fluctuation behavior. And detecting the sequence and direction relationship of a plurality of parameter fluctuation frames, identifying the dense segments which alternately act to construct a label labeling index, and adjusting the state output sequence according to the occurrence frequency of different labels in a continuous time period, thereby realizing the identification and dynamic sorting scheduling of the response structure relationship among different time sequence behaviors. And the time sequence consistency identification capability and the parameter linkage structure expression capability of the monitoring data in the continuous abnormal state are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a motor performance monitoring data processing system. Background Art

[0002] The field of data processing technology includes the entire process of collecting, analyzing, identifying and structurally representing the original information obtained from industrial equipment, sensors or operating environments. It aims to standardize, convert, extract features and reconstruct sequences of discrete or continuous data sources to achieve the feasibility of subsequent data analysis and application. It includes data acquisition interface design, signal normalization, time series splicing, data anomaly identification, feature dimension compression, redundant information elimination, and basic processing of classification and regression. It uses numerical mapping, window sliding sampling, outlier detection, threshold discrimination or mathematical transformation to achieve effective aggregation and processing of multi-source data streams. It is the basic link supporting various monitoring, diagnosis and evaluation systems. Among them, motor performance monitoring data The processing system is used to acquire and process various performance parameter data during the operation of the motor. It is carried out in multiple aspects such as electrical signal acquisition, electrical parameter calculation and operation status classification. It involves the acquisition of signal data with voltage and current as the core, converting analog quantities into processable structural data in a digital conversion manner, performing numerical judgments based on logical rules and generating status labels accordingly, and uniformly packaging the result information through coding and sorting. Specifically, it first relies on electrical signal acquisition means to obtain the original values, then performs numerical normalization and category screening processing, and then uses preset conditions to execute classification and judgment logic. Finally, the processed performance information is output in a unified structural format. Through the coordinated cooperation of timing control and logical processing, a stable data processing link is formed.

[0003] Existing motor performance monitoring data processing technology relies on a unified time base to perform sampling sequence merging when facing the synchronous processing of multi-channel electrical signals. It lacks a means to consistently judge the center of gravity migration trend. In the case of uneven sampling intervals or inconsistent channel frequencies, it is easy to cause sampling frame alignment confusion. The label generation path based on normalization and conditional discrimination fails to reflect the structural hierarchy between the parameter response sequence and the fluctuation combination. In the case of concurrent linkage phenomena such as speed mutation, current hysteresis, and temperature resonance, it is impossible to establish a clear correspondence between the influence order of parameters, resulting in a messy label output order and weak matching with the state priority, causing the abnormal state information recognition chain to be interrupted and the output logic to lag. Summary of the Invention

[0004] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides a motor performance monitoring data processing system. The technical solution is as follows: In one aspect, a motor performance monitoring data processing system is provided, the system comprising: The signal registration module obtains the operating data monitoring sequence, calculates the band center of gravity using the extreme point position, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences of continuous time periods, adjusts the arrangement order of the sampling frames on the time axis, and generates the center of gravity matching registration axis; The rhythm judgment module uses the center of gravity matching and alignment axis to calculate the interval changes of continuous current sampling points, determine the peak-valley offset sequence in the segment interval sequence, screen the time period of unidirectional offset structure, mark it as the rhythm offset segment, analyze the consistency of the change direction, detect the rhythm abnormal data segment, and output the data processing record; The trend hysteresis module calls the data processing record, identifies the mutation moment in the speed sequence, locates the starting position of the continuous trend by analyzing the change direction of adjacent sampling points of the current sequence after the mutation moment, identifies the hysteresis response time, and outputs the hysteresis response time information; The action identification module calls the data processing records and hysteresis response time information, obtains the continuous fluctuation frame positions of voltage, temperature and vibration, analyzes the interleaving of the fluctuation directions and sequences of adjacent parameters, calculates the parameter interleaving density, constructs the parameter combination relationship and generates a state label, and outputs the alternating trigger sequence information.

[0005] As a further solution of the present invention, the center of gravity matching alignment axis is specifically the center of gravity position of the voltage sequence, the center of gravity position of the current sequence, and the band center of gravity time index. The data processing record includes the sampling interval variation range, the interval gradient peak and valley offset sequence, and the rhythm abnormality segment identification. The hysteresis response time information specifically refers to the speed mutation moment, the current trend starting time, and the speed-current time interval. The alternating trigger sequence information includes the fluctuation direction consistency distribution, the parameter fluctuation interleaving density, and the parameter combination trigger sequence.

[0006] As a further solution of the present invention, the signal registration module includes: The extreme value anchoring submodule obtains the operation data monitoring sequence, including the voltage monitoring sequence and the current monitoring sequence, filters the extreme value points in each time period in the sequence, analyzes the position distribution of the extreme value points in each time period, and establishes the extreme value distribution index; The center of gravity trajectory analysis submodule calculates the center of gravity of the value distribution of the voltage and current sampling sequence in each time period based on the extreme value distribution index, compares the relative position changes of the voltage center of gravity and the current center of gravity in consecutive time periods, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences, and obtains the center of gravity trajectory trend; The sampling arrangement adjustment submodule adjusts the arrangement order of the sampling frames on the time axis according to the center of gravity trajectory trend, determines the change trend of the center of gravity position of the sampling frames and the synchronization between the two sequences, and generates the center of gravity matching alignment axis.

[0007] As a further solution of the present invention, the specific formula for comparing the relative position changes of the voltage center of gravity and the current center of gravity in consecutive time periods is: ; Calculate the center of gravity trend deviation; in, Indicates the Normalized numerical center of gravity of the segment voltage sampling sequence, Indicates the Normalized numerical center of gravity of the segment current sampling sequence, Indicates the The normalized value of the amplitude range of the segment voltage sequence, Indicates the The normalized value of the amplitude range of the segment current sequence, Indicates the The trend direction symbol of the center of gravity of the voltage sequence of the segment relative to the previous segment, Indicates the trend direction symbol of the center of gravity of the current sequence of the first segment relative to the previous segment, Indicates the total number of continuous sequence segments involved in the calculation, Indicates the deviation of the voltage and current center of gravity trend, Indicates the sequence number of consecutive sampling time periods.

[0008] As a further solution of the present invention, the rhythm determination module includes: The interval calculation submodule obtains the time intervals of consecutive current sampling points according to the center of gravity matching and alignment axis, analyzes the changes in adjacent time intervals of each sampling segment, classifies the time interval distribution order of all sampling segments, and generates a segment interval distribution sequence; The offset identification submodule determines the interval change order in each segment based on the segment interval distribution sequence, selects segments with continuous change order, marks them as offset aggregation segments, establishes a unidirectional offset structure, and obtains unidirectional offset segments; The anomaly detection submodule calls the unidirectional offset segment, analyzes the interval change direction of continuous sampling points in the corresponding segment, detects the segment with continuous same-direction offset by comparing the consistency and duration of the interval direction, records it as a rhythm abnormality segment, and obtains data processing records.

[0009] As a further solution of the present invention, the trend hysteresis module includes: The abnormal segment screening submodule calls the data processing record, removes the data segments with abnormal rhythm, and obtains the mutation moment in the speed sequence on the remaining alignment axis by analyzing the speed slope of the speed data sequence to obtain the mutation moment sequence; The trend start positioning submodule locates the starting position of the current continuous change trend based on the mutation time sequence by analyzing the change direction of adjacent sampling points in the current sequence after the mutation moment, and generates the trend start time point; The hysteresis duration identification submodule identifies the hysteresis response duration by calculating the relative distance between the mutation point time and the starting position time according to the trend starting time point, and obtains the hysteresis response time information.

[0010] As a further solution of the present invention, the role identification module includes: The fluctuation frame positioning submodule obtains the data processing record and hysteresis response time information, identifies the continuous fluctuation frames of voltage, temperature, and vibration, determines the change direction of each parameter in adjacent frames, analyzes the consistency of the change direction, and obtains the parameter fluctuation direction distribution information; The interleaving density discrimination submodule analyzes the order of fluctuations between parameters based on the parameter fluctuation direction distribution information, identifies the number of fluctuation interleavings for each pair of parameters, analyzes the number of order alternations for each pair of parameters, and calculates the fluctuation interleaving density for each pair of parameters to obtain a fluctuation interleaving density matrix; The sequence information generation submodule identifies the combination relationship between multiple parameters according to the fluctuation interleaving density matrix, constructs state labels between the parameters, sorts the triggering order of multiple groups of state labels, establishes alternating triggering sequence information, and obtains alternating triggering sequence information.

[0011] As a further solution of the present invention, the specific formula for calculating the fluctuation interleaving density of each pair of parameters is: ; Calculate the value of the wave interlaced density; in, For parameters With parameters The fluctuating staggered density value in the observation sequence, For parameters At the time point and time point The normalized value of the direction difference, For parameters At the time point and time point The normalized value of the direction difference, is the sampling time point index, is the number of sampling points corresponding to the total duration of the sampling period, is the first parameter number involved in the analysis, The number of the second parameter involved in the analysis.

[0012] As a further embodiment of the present invention, the system further comprises: The tag scheduling module calls the alternating trigger sequence information, extracts the parameter pair with the highest interleaving density and uses it as the dominant parameter combination, calls the distribution sequence of the corresponding state tags on the time axis, analyzes the cumulative number of occurrences of the tags in the continuous time period, compares the cumulative number of multiple tags, adjusts the output order of the state tags according to the number, and outputs the state tag sorting result; The state tag sorting results are specifically the dominant parameter tag combination, the cumulative number of state tag occurrences, and the tag time series distribution.

[0013] As a further solution of the present invention, the label scheduling module includes: The dominant parameter screening submodule calls the alternating trigger sequence information, screens the parameter pair with the highest interleaving density, and uses it as the dominant parameter combination, locates the identifier of the target parameter combination in the state label sequence, and obtains the dominant parameter label index; The tag statistics submodule collects the distribution sequence of the corresponding state tag on the time axis based on the dominant parameter tag index, counts the cumulative number of times the tag appears in a continuous time period, and obtains the cumulative number of tag appearances; The output sorting submodule adjusts the output order of multiple status tags according to the cumulative number of occurrences of the tags, arranges the tag output priorities, and obtains the status tag sorting results.

[0014] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: By identifying extreme points, the center of gravity of the band is established and trends are compared. The center of gravity alignment structure between different channels is constructed. The rhythm stability of the time period is determined based on the trend of sampling interval changes and abnormal sections are marked. The response lag period is located by combining the speed slope change and the current fluctuation behavior. The sequence and direction relationship of multiple parameter fluctuation frames are detected, and the dense segments of alternating effects are identified to construct a label annotation index. The state output order is adjusted according to the frequency of occurrence of different labels in continuous time periods. The response structure relationship between different time series behaviors is recognized and dynamically sorted and scheduled, which improves the monitoring data's ability to recognize time series consistency and express parameter linkage structures under continuous abnormal conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 is a system flow chart of the present invention; Figure 2 Schematic diagram of the system framework of the present invention; Figure 3 This is a flow chart of the signal registration module of the present invention; Figure 4 is a flow chart of the rhythm determination module of the present invention; Figure 5 This is a flow chart of the trend hysteresis module of the present invention; Figure 6 This is a flow chart of the action identification module of the present invention; Figure 7 This is a flow chart of the label scheduling module of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0018] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0019] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0020] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0021] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0022] The present invention provides a motor performance monitoring data processing system, please refer to Figures 1 to 2 The present invention provides a technical solution, a motor performance monitoring data processing system includes: The signal registration module obtains the operating data monitoring sequence, calculates the band center of gravity using the extreme point position, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences of continuous time periods, adjusts the arrangement order of the sampling frames on the time axis, and generates the center of gravity matching registration axis; The rhythm judgment module uses center of gravity matching to align the axis, calculates the interval changes of continuous current sampling points, determines the peak-valley offset sequence in the segment interval sequence, selects the time period of unidirectional offset structure, marks it as the rhythm offset segment, analyzes the consistency of the change direction, detects rhythm abnormal data segments, and outputs data processing records; The trend hysteresis module calls data processing records to identify the mutation moment in the speed sequence. By analyzing the change direction of adjacent sampling points in the current sequence after the mutation moment, it locates the starting position of the continuous trend, identifies the hysteresis response duration, and outputs the hysteresis response time information; The action identification module uses data processing records and hysteresis response time information to obtain the continuous fluctuation frame positions of voltage, temperature, and vibration, analyze the interleaving of the fluctuation directions and sequences of adjacent parameters, calculate the parameter interleaving density, construct parameter combination relationships, generate state labels, and output alternating trigger sequence information; The tag scheduling module calls the alternating trigger sequence information, extracts the parameter pair with the highest interleaving density and uses it as the dominant parameter combination, calls the distribution sequence of the corresponding state tags on the time axis, analyzes the cumulative number of occurrences of the tags in a continuous time period, compares the cumulative number of multiple tags, adjusts the output order of the state tags according to the number, and outputs the state tag sorting result.

[0023] The center of gravity matching and alignment axes are specifically the center of gravity position of the voltage sequence, the center of gravity position of the current sequence, and the band center of gravity time index. The data processing records include the sampling interval variation range, the interval gradient peak and valley offset sequence, and the rhythm abnormality segment identification. The hysteresis response time information specifically refers to the speed mutation moment, the current trend start time, and the speed and current time interval. The alternating trigger sequence information includes the fluctuation direction consistency distribution, the parameter fluctuation interleaving density, and the parameter combination trigger sequence. The state label sorting results are specifically the dominant parameter label combination, the cumulative number of state label occurrences, and the label time series distribution.

[0024] See also Figure 2 and Figure 3 , the signal registration module includes: The extreme value anchoring submodule obtains the operation data monitoring sequence, including the voltage monitoring sequence and the current monitoring sequence, filters the extreme value points in each time period in the sequence, analyzes the position distribution of the extreme value points in each time period, and establishes the extreme value distribution index; When acquiring the operational data monitoring sequence, the voltage and current monitoring sequences collected every second are divided into 10 time periods. Within each period, the maximum and minimum voltage points, as well as the maximum and minimum current points, are screened. The frame number of each extreme point within the sequence is recorded. For example, in the first period, the maximum voltage occurs in the fourth frame, and the minimum current occurs in the second frame. These extreme point indices are distributed according to their sequence numbers to form a set of extreme point indices. For each period, the frame number of the extreme point within the period is used as the interval reference. The above process is repeated for all 10 periods to obtain the location distribution of the extreme points within each period. Assuming that in the first period, the voltage extremes occur in the second and ninth frames, and the current extremes occur in the fourth and seventh frames, respectively, the following table summarizes the results.

[0025] Table 1: Example of extreme point distribution: As shown in Table 1, the extreme value point frame numbers are accurately marked in each time period. Based on this distribution, an extreme value distribution index is established.

[0026] The center of gravity trajectory analysis submodule calculates the center of gravity of the voltage and current sampling sequences in each time period based on the extreme value distribution index, compares the relative position changes of the voltage center of gravity and the current center of gravity in consecutive time periods, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences, and obtains the center of gravity trajectory trend; The specific formula for comparing the relative position changes of the voltage center of gravity and the current center of gravity in consecutive time periods is: ; Calculate the center of gravity trend deviation; in, Indicates the Normalized numerical center of gravity of the segment voltage sampling sequence, Indicates the Normalized numerical center of gravity of the segment current sampling sequence, Indicates the The normalized value of the amplitude range of the segment voltage sequence, Indicates the The normalized value of the amplitude range of the segment current sequence, Indicates the The trend direction symbol of the center of gravity of the voltage sequence of the segment relative to the previous segment, Indicates the The trend direction symbol of the center of gravity of the current sequence of the segment relative to the previous segment, Indicates the total number of continuous sequence segments involved in the calculation, Indicates the deviation of the voltage and current center of gravity trend, Indicates the serial number of the continuous sampling time period; formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: The formula is used to calculate the consistency of the center of gravity trajectory change trend of voltage and current in multiple consecutive sampling segments. The result is used to confirm the trend direction and provide a reference for sampling frame arrangement in the subsequent center of gravity alignment process. Parameter meaning and setting value: , represents the total number of current motor signal sampling segments. The sampling period is set to 10 milliseconds, the monitoring time period is 50 milliseconds, and the number of sampling segments is 5, divided into 10 milliseconds each segment. , represents the normalized numerical center of gravity of the second voltage sampling sequence. The original voltage values ​​collected are 214V, 212V, 209V, 202V, and 199V. The time points are weighted and averaged and then normalized to the range of 0 to 1. , represents the normalized numerical center of gravity of the second segment current sampling sequence. The original current values ​​collected are 5.2A, 5.3A, 5.1A, 5.0A, and 4.8A, and the corresponding normalized value after weighted processing is 0.60; , represents the normalized value of the voltage range difference in the second section, the difference between 214V and 199V is 15V, normalized to 0.08; , represents the normalized value of the second segment current range difference, the difference between 5.3A and 4.8A is 0.5A, which is 0.10 after normalization; , indicating the rising trend direction of the voltage center of gravity of the second segment relative to the first segment. The trend direction is determined by the sign of the difference between the center of gravity of the current segment and the center of gravity of the previous segment. , indicating that the center of gravity of the second current segment is consistent with that of the first current segment, and the direction symbol is 0; Substitute the parameters into the formula for calculation: Calculate the difference between the voltage and current center of gravity: ; Calculate the denominator: ; Calculate trend direction divergence: ; Calculate the trend consistency index for the second segment: ; Set the calculation results of segments 3 to 5 to 0.0521, 0.0367, and 0.0574 respectively; ; The result of 0.0476 shows the degree of consistency of the centroid trajectory trend of the voltage and current sequences in the current sampling section. The closer the value is to 0, the higher the degree of trend consistency. The result is directly input into the subsequent processing link as a reference indicator for centroid alignment. The formula is to calculate the consistency of the numerical centroid and change trend of the two sampling sequences of voltage and current in a continuous time period. The formula first calculates the difference between the normalized centroids of voltage and current in the same section, divides the difference by the square root of the sum of the extreme differences in their amplitudes and adds 1 (to avoid the denominator being zero and to standardize the scale of the difference), and then multiplies the result by the difference between the trend direction sign of the voltage centroid and the current trend direction sign in the section (that is, whether the trends are consistent), takes the absolute value and accumulates it for all sections, and finally averages the number of sections to obtain the overall trend deviation degree. By comprehensively considering the numerical difference, amplitude range and trend consistency, the matching quality of multiple centroid trajectories is quantitatively measured; among them, all parameters involved in the formula are dimensionless values ​​obtained through normalization, including the centroid, The range and trend direction sign, and the final deviation exist as relative consistency indicators, which are not affected by the specific physical units of the original data (such as volts, amperes), ensuring the universality and comparability across parameters, channels, and devices. By adding 1 to the denominator, zero division errors are avoided and abnormal amplification is suppressed. It is suitable for objective evaluation of the stability and alignment effect of continuous sequences; the center of gravity trend deviation is used to indicate the degree of deviation of the voltage and current series in value and trend during the entire sampling time period. The closer the value is to 0, the more consistent the center of gravity trajectories of the two are and the better the synchronization is, which is more conducive to subsequent signal registration and alignment. The larger the value, the more significant the amplitude difference or trend inconsistency, suggesting that the sampling frame needs to be further adjusted, marked, or abnormal data segments are eliminated.

[0027] The sampling arrangement adjustment submodule adjusts the arrangement order of the sampling frames on the time axis according to the trend of the center of gravity trajectory, determines the change trend of the center of gravity position of the sampling frames and the synchronization between the two sequences, and generates the center of gravity matching alignment axis; Based on the center of gravity trajectory trend, the center of gravity changes for 10 time periods are arranged. The relative rise and fall of the voltage and current centers of gravity are determined segment by segment. If the trends are consistent, the sampling frames for that segment are rearranged in their original order. If the voltage center of gravity rises and the current center of gravity falls in a certain segment, the sampling frame order within that segment is adjusted to align the center of gravity position with the previous segment trend. For example, if the voltage center of gravity rises and the current center of gravity falls in the third segment, the sampling frames for that segment are reordered. For example, if the original frame sequence is [21, 22, 23, 24, 25, 26, 27, 28, 29, 30], the reordered sequence becomes [23, 24, 25, 26, 27, 28, 29, 30, 21, 22], aligning the center of gravity with the previous segment trend. The frame order adjustment is completed step by step for all segments, ultimately generating the center of gravity matching alignment axis.

[0028] See also Figure 2 and Figure 4 , the rhythm judgment module includes: The interval calculation submodule aligns the axes according to the center of gravity, obtains the time intervals of consecutive current sampling points, analyzes the changes in the adjacent time intervals of each sampling segment, classifies the time interval distribution order of all sampling segments, and generates a segment interval distribution sequence; Using the center of gravity alignment axis, the timestamps of consecutive current sampling points are read sequentially. The time difference between each two adjacent sampling points is calculated, and the resulting time intervals are stored in an array. For example, within a sampling segment, the times of the 10 sampling points are [1.000, 1.005, 1.010, 1.016, 1.022, 1.028, 1.034, 1.040, 1.047, 1.053] seconds, corresponding to the time intervals of [0.005, 0.005, 0.006, 0.006, 0.006, 0.006, 0.006, 0.007, 0.006] seconds. This calculation is repeated for each sampling segment to obtain an array of time intervals for multiple segments. Adjacent time intervals within each segment are compared, and the interval distribution within the segment is sorted from smallest to largest, summarizing the order of interval changes within each segment. If the time intervals in one segment show a gradual increase, such as [0.005, 0.006, 0.006, 0.007], while another segment shows no obvious increase or decrease, the former can be classified as an increasing distribution, and the latter as a disordered distribution. This classification can be used to organize all sampling segments and organize the segment interval distribution sequence.

[0029] The offset identification submodule determines the interval change order in each segment based on the segment interval distribution sequence, selects segments with continuous change order, marks them as offset aggregation segments, establishes a unidirectional offset structure, and obtains unidirectional offset segments; Based on the segment interval distribution sequence, the interval change sequence of each segment is analyzed, and the intervals are determined segment by segment to determine whether they are increasing, decreasing, or disordered. All segments with continuously changing intervals are selected. If the intervals within a segment are [0.005, 0.006, 0.007, 0.008], it is marked as an increasing segment; if they are [0.008, 0.007, 0.006, 0.005], it is marked as a decreasing segment. The number of segments with continuously changing sequences is further counted. If a segment and its adjacent segments are all increasing (or decreasing) in sequence, they are merged into an offset aggregation segment. For example, if segments 2-4 are all increasing, they are merged into a single offset aggregation segment. The offset aggregation segments are numbered and archived, and a unidirectional offset structure is established to generate a unidirectional offset segment sequence. The unidirectional offset structure reflects the behavior of the current signal sampling interval changing continuously in a time segment.

[0030] The anomaly detection submodule calls the unidirectional offset segment and analyzes the change direction of the intervals of consecutive sampling points in the corresponding segment. By comparing the consistency and duration of the interval direction, it detects the segment with continuous same-direction offset, records it as a rhythm abnormality segment, and obtains data processing records; Call the unidirectional offset segment and analyze the direction of change in the time intervals of all consecutive sampling points within each offset segment. For each segment, determine whether the time interval is continuously increasing or decreasing, and count the number of sampling points that are continuously changing. For example, if the sampling point intervals within a certain offset segment are [0.005, 0.006, 0.007, 0.008, 0.009], the direction of change is continuously increasing, and the duration is 4 intervals. All segments that continuously change in the same direction and last for more than 3 intervals are recorded as rhythm abnormal segments. For example, if the time interval of the fifth segment is detected to be continuously increasing for 4 intervals, which meets the conditions, then the fifth segment is recorded as a rhythm abnormal segment. All rhythm abnormal segments and their corresponding segment numbers are counted and organized into data processing records to facilitate subsequent abnormal segment removal and trend monitoring and analysis.

[0031] See also Figure 2 and Figure 5 , the trend lag module includes: The abnormal segment screening submodule calls the data processing record to eliminate the data segments with abnormal rhythm. By analyzing the speed slope of the speed data sequence, it obtains the sudden change moment in the speed sequence on the remaining registration axis and obtains the sudden change moment sequence. The data processing log is called up, and all current sampling point data is traversed one by one. Data segments marked as rhythm anomalies are removed. During this removal process, the frame number and corresponding time interval of each abnormal segment are carefully annotated. Only the remaining unmarked current sampling frames are retained to ensure the continuity and validity of the remaining data. For the current sampling segments remaining after the abnormal segments are removed, the speed sampling point sequences corresponding to the alignment axis on the same time axis are selected and aligned to form a speed data sequence. For this speed data sequence, the speed increments of adjacent sampling points are calculated segment by segment. For example, if the time points in a segment are [0.00, 0.02, 0.04, 0.06, 0.08] seconds and the corresponding speeds are [1450, 1460, 1490, 1495, 1480] rpm, the speed increments of the adjacent points are 10, 30, 5, and -15, respectively. We further divide the time interval between each pair of sampling points to obtain the speed slope. For frames 1-2, the slope is (1460-1450) / 0.02=500; for frames 2-3, it is (1490-1460) / 0.02=1500; for frames 3-4, it is (1495-1490) / 0.02=250; and for frames 4-5, it is (1480-1495) / 0.02=-750. A baseline value of 1000 is selected as a reference for determining a sudden change. All time points corresponding to slopes greater than 1000 or less than -1000 are selected and recorded as sudden change moments. For example, if the slope of frames 2-3 is 1500 in the above sample data, indicating a sudden change, the corresponding time is 0.04 seconds. This point is recorded as the sudden change moment, resulting in a sudden change moment sequence such as [0.04] seconds.

[0032] The trend start location submodule is based on the mutation time sequence. By analyzing the change direction of adjacent sampling points in the current sequence after the mutation moment, it locates the starting position of the current continuous change trend and generates the trend start time point. Based on the mutation time sequence obtained in the previous section, analyze the current sampling data after each mutation time to determine whether the current sequence shows a continuous trend of change after the mutation. For example, take the mutation time of 0.04 seconds. Continuous current sampling data is collected from 0.04 seconds onwards. Assuming the current data is [7.8, 8.0, 8.3, 8.7, 8.8] amperes, subtract each pair of adjacent points to obtain a difference sequence of [0.2, 0.3, 0.4, 0.1] amperes. These are all positive values, indicating a continuous increase. If the difference sequence is [0.2, -0.2, 0.1, -0.1] amperes, the change direction is discontinuous. Based on the direction of continuous increase or decrease, locate the first sampling point that shows continuous change as the trend starting point. For example, in the above example, the first point after 0.04 seconds is the trend starting point. Repeat this process for each mutation time, compiling the entire trend starting time sequence and laying the foundation for the subsequent response duration calculation.

[0033] The hysteresis time identification submodule calculates the relative distance between the mutation point time and the starting position time according to the trend starting time point, identifies the hysteresis response time, and obtains the hysteresis response time information; Based on the trend starting time, the time interval between each set of mutation moments and the trend starting point is precisely calculated, using absolute value arithmetic to ensure the non-negativity of the calculated results. For example, if the mutation moment is 0.04 seconds and the trend starting point is 0.06 seconds, the lag duration is 0.02 seconds. Using statistical induction, all lag duration data is divided into intervals, and a judgment threshold of 0.005 seconds is set to distinguish significant lag from general response. If a group of intervals is greater than 0.005 seconds, such as 0.012 seconds, it is determined to be a significant lag response and recorded as a key monitoring object. All time intervals between mutation points and trend starting points are archived separately, and a lag response time information table is generated, which contains core parameters such as mutation moment, trend starting time, and time interval. This type of lag identification and data collection is performed on multiple groups of mutation points and trend starting points in subsequent monitoring cycles, providing basic data support for further linkage identification and early warning decision-making in the system.

[0034] See also Figure 2 and Figure 6 , the role identification module includes: The fluctuation frame positioning submodule obtains data processing records and hysteresis response time information. By identifying the continuous fluctuation frames of voltage, temperature, and vibration, it determines the change direction of each parameter in adjacent frames, analyzes the consistency of the change direction, and obtains the parameter fluctuation direction distribution information; Data processing records and hysteresis response time information are obtained. Sampled data corresponding to voltage, temperature, and vibration parameters are associated with the registration timeline. Successive sample frames for each parameter are iterated through, and the difference between each frame is calculated. For example, if five consecutive frames of voltage sample data are [220, 221, 223, 224, 222] volts, the changes in adjacent frames are +1, +2, +1, and -2 volts, respectively, and are labeled as rising, rising, rising, and falling. For temperature frames, such as [65.0, 65.5, 66.0, 65.8, 65.7] degrees Celsius, the changes are +0.5, +0.5, -0.2, and -0.1 degrees Celsius, and are labeled as rising, rising, falling, and falling. For vibration frame data such as [0.25, 0.27, 0.26, 0.28, 0.30] mm / s, the variations are +0.02, -0.01, +0.02, and +0.02, labeled as rising, falling, rising, and rising. Align these results along the time axis to form a parameter fluctuation direction sequence. Count the combinations of change directions of the three parameters at each time point. For example, if one frame shows rising, rising, and rising for voltage, temperature, and vibration, respectively, and another shows rising, falling, and rising, then all combinations of these sampling frames are combined to obtain the parameter fluctuation direction distribution information. This data is recorded in a parameter direction distribution table for subsequent interleaved analysis.

[0035] The interleaving density discrimination submodule analyzes the order of fluctuations between parameters based on the parameter fluctuation direction distribution information, identifies the number of fluctuation interleavings for each pair of parameters, analyzes the number of order alternations for each pair of parameters, and calculates the fluctuation interleaving density for each pair of parameters to obtain the fluctuation interleaving density matrix; The specific formula for calculating the fluctuation interleaving density of each pair of parameters is: ; Calculate the value of the wave interlaced density; in, For parameters With parameters The fluctuating staggered density value in the observation sequence, For parameters At the time point and time point The normalized value of the direction difference, For parameters At the time point and time point The normalized value of the direction difference, is the sampling time point index, is the number of sampling points corresponding to the total duration of the sampling period, is the first parameter number involved in the analysis, The number of the second parameter involved in the analysis.

[0036] formula: ; Detailed explanation of the formula and the process of formula calculation and derivation: The formula is used to calculate the fluctuation interleaving density value of parameter i and parameter j within the sampling period. The obtained results are used to determine the trend correlation relationship between parameters and the degree of coupling of fluctuation influence. Parameter meaning and setting value: , is the number of continuous valid sampling points within the sampling period. According to the actual motor monitoring system with a sampling period of 0.01 seconds, the number of sampling points obtained by continuous observation for 0.06 seconds is 7; The normalized result of the direction difference of parameter i between time t and t+1 is obtained. The continuous fluctuation direction data of parameter i (such as current) is collected. The original collected values ​​are 0.10, 0.13, 0.14, 0.18, 0.15, 0.16, and 0.17. The direction differences are 0.03, 0.01, 0.04, -0.03, 0.01, and 0.01, respectively. The normalized interval takes the actual maximum and minimum difference range. The normalized results are 0.43, 0.14, 0.57, -0.43, 0.14, and 0.14, respectively. The normalized result of the direction difference of parameter j between time t and t+1 is obtained. The continuous fluctuation direction data of parameter j (such as temperature) is collected. The original collected values ​​are 36.1, 36.2, 36.3, 36.2, 36.4, 36.6, and 36.5. The direction differences are 0.1, 0.1, -0.1, 0.2, 0.2, and -0.1, respectively. The normalized results are 0.50, 0.50, -0.50, 1.00, 1.00, and -0.50, respectively. It means that T-1 direction differences are accumulated item by item, and the product term is the absolute value of the product of the normalized direction differences at each moment.

[0037] Substitute the parameters into the formula for calculation: ; ; ; The result 0.421 indicates that the fluctuation interleaving density of current and temperature during the sampling period is 0.421, reflecting that the trend fluctuations of the two parameters have a moderate degree of synchronization or interleaving trend. This value can be used to judge the parameter linkage relationship or assign weights to the interaction mechanism, providing a data basis for the subsequent extraction of behavioral combination features. For each pair of parameters in the observation period, the formula first calculates the difference in their fluctuation directions at consecutive time points (after normalization), then takes the absolute value of the product of each pair of time differences and accumulates them, representing the intensity of the same-direction or alternating effects of the two parameter fluctuations. Next, the denominator uses the square root of the sum of the squares of the two parameter direction differences as a scale factor, and adds 1 to avoid division by zero. By quantifying the degree of fluctuation intersection of the parameter pair on the time axis as a relative density value, the larger the value, the more common fluctuations or interlaced characteristics the fluctuations of the two parameters have in time. In this formula, all input items are dimensionless values ​​after normalization, and the resulting fluctuation interlaced density value is also a dimensionless relative density index. The design of adding 1 to the denominator not only prevents the denominator from being zero and causing calculation overflow, but also avoids the abnormal amplification of the fraction when the fluctuation amplitude is extremely small, ensuring the accuracy. The numerical stability and practical interpretability of the results are verified, which conforms to the normalization principle in the physical and mathematical sense, making the calculation applicable to parameter pairs of different dimensions and different measurement ranges, facilitating horizontal comparison between multiple parameters. The fluctuation interleaving density value represents the fluctuation interleaving density of parameters and parameters within a given time window, that is, the degree to which their fluctuation trends appear synchronously or alternately within the period. The closer the value is to 0, the more independent or weakly correlated the fluctuations of the two parameters in time. The closer the value is to 1, the more highly coupled or densely alternating the order of their fluctuations is, and there is obvious linkage or mutual influence. In subsequent analysis, the fluctuation interleaving density matrix is ​​used to screen out parameter pairs with the strongest coupling relationship, which is used to construct state labels, determine behavioral combination characteristics and optimize label output order. It is an important quantitative basis for multi-parameter dynamic monitoring and diagnostic decision-making.

[0038] The sequence information generation submodule identifies the combination relationship between multiple parameters based on the fluctuation interleaving density matrix, constructs the state labels between the parameters, sorts the triggering order of multiple groups of state labels, establishes the alternating triggering sequence information, and obtains the alternating triggering sequence information; According to the fluctuation interleaving density matrix, the interleaving density values ​​of all parameter pairs are sorted, and the parameter pair corresponding to the maximum interleaving density is selected as the dominant parameter combination for the state label. For example, the voltage-temperature pair with the largest interleaving density is set as the dominant parameter pair. A state label for this parameter pair is constructed, and the triggering order of this label throughout all sampling cycles is recorded. The state labels of other parameter pairs are further arranged in sequence, and each state label is sorted by the magnitude of the fluctuation interleaving density to obtain the triggering order of the labels. The sorting information is then matched one-to-one with the specific triggering order of each cycle, and finally the alternating triggering order information is established. This sorting information can be used to support data decisions for subsequent state diagnosis or risk warning output.

[0039] See also Figure 2 and Figure 7 , the label scheduling module includes: The dominant parameter screening submodule calls the alternating trigger sequence information, screens the parameter pair with the highest interleaving density, and uses it as the dominant parameter combination, locates the identifier of the target parameter combination in the state label sequence, and obtains the dominant parameter label index; After invoking the alternating trigger sequence information, the dominant parameter screening submodule extracts all parameter pairs involved in the combination and their corresponding interleaving density values. These are sorted from highest to lowest interleaving density, and the parameter pair with the highest interleaving density is selected as the dominant parameter combination. Assuming the interleaving density of the voltage-temperature combination is 0.82, the temperature-vibration combination is 0.76, and the voltage-vibration combination is 0.65, then voltage-temperature is selected as the dominant parameter combination. Subsequently, the tag identifier associated with the voltage-temperature combination is retrieved from the state tag sequence, and its corresponding index position in the time series is extracted to form the dominant parameter tag index. If the state tag sequence is [VT1, VV1, VT1, TV2, VV1], where "VT1" represents the voltage-temperature state tag, the corresponding time series index is [0, 2]. This index information is used for subsequent time series statistical processing of the state tags and provides a precise mapping between tags and dominant parameter pairs on the time axis, assisting in identifying the tag's temporal characteristics and intensity distribution.

[0040] The tag statistics submodule collects the distribution sequence of the corresponding state tag on the time axis based on the dominant parameter tag index, counts the cumulative number of times the tag appears in a continuous time period, and obtains the cumulative number of tag appearances; Based on the dominant parameter label index, the label statistics submodule collects the occurrence times of all state labels corresponding to this index from the timeline and categorizes the labels into continuous time periods. Using 1 second as the criterion for continuous time periods, assuming the label "VT1" appears at time points 0.2 seconds, 0.7 seconds, 1.8 seconds, 2.0 seconds, and 2.3 seconds, these time points can be classified as appearing twice in the [0-1 second] segment, once in the [1-2 second] segment, and twice in the [2-3 second] segment. By summing the number of label occurrences within each time period, a cumulative sequence of label occurrences is obtained. For example, the cumulative number of occurrences of the label "VT1" is [2, 1, 2], which is recorded as the label density for the corresponding time period. This data item not only reflects the temporal strength of the dominant label but also serves as a basis for adjusting label priorities in the subsequent output sorting stage. The specific data can be displayed as follows: Table 2 Cumulative occurrence of status tags As shown in Table 2, the cumulative occurrence distribution of the “VT1” status label in consecutive time periods is listed.

[0041] The output sorting submodule adjusts the output order of multiple status tags according to the cumulative number of tag occurrences, arranges the tag output priority, and obtains the status tag sorting result; The output sorting submodule sorts all state tags according to the cumulative number of tag appearances to form a priority order for tag output. First, the cumulative number data of all dominant parameter tags are collected and uniformly arranged, and their total frequency of appearance in continuous time periods is compared. Assuming "VT1" is the dominant tag, it appears a total of 5 times, "TV2" appears 3 times, and "VV1" appears 4 times. Then, according to the frequency, it is arranged from high to low as "VT1" > "VV1" > "TV2". The sorting results are sequentially configured in the output module to form a priority queue for the state tag output, and finally the state tag sorting results are obtained for subsequent output control or trigger scheduling of system instructions. This sorting not only reflects the importance of each tag in the current monitoring cycle, but also facilitates the system to accurately identify and call key tags in multi-state responses, realizing a sequential scheduling mechanism in the multi-tag state decision process.

[0042] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0043] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0044] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0045] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0046] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians 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 invention.

[0047] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0048] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0049] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0050] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0051] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0052] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The motor performance monitoring data processing system is characterized by: The system comprises: The signal registration module obtains the operating data monitoring sequence, calculates the band center of gravity using the extreme point position, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences of continuous time periods, adjusts the arrangement order of the sampling frames on the time axis, and generates the center of gravity matching registration axis; The rhythm judgment module uses the center of gravity matching and alignment axis to calculate the interval changes of continuous current sampling points, determine the peak-valley offset sequence in the segment interval sequence, screen the time period of unidirectional offset structure, mark it as the rhythm offset segment, analyze the consistency of the change direction, detect the rhythm abnormal data segment, and output the data processing record; The trend hysteresis module calls the data processing record, identifies the mutation moment in the speed sequence, locates the starting position of the continuous trend by analyzing the change direction of adjacent sampling points of the current sequence after the mutation moment, identifies the hysteresis response time, and outputs the hysteresis response time information; The action identification module calls the data processing records and hysteresis response time information, obtains the continuous fluctuation frame positions of voltage, temperature and vibration, analyzes the interleaving of the fluctuation directions and sequences of adjacent parameters, calculates the parameter interleaving density, constructs the parameter combination relationship and generates a state label, and outputs the alternating trigger sequence information.

2. The motor performance monitoring data processing system according to claim 1, characterized in that: The center of gravity matching alignment axis is specifically the center of gravity position of the voltage sequence, the center of gravity position of the current sequence, and the band center of gravity time index. The data processing record includes the sampling interval variation range, the interval gradient peak and valley offset sequence, and the rhythm abnormality segment identifier. The hysteresis response time information specifically refers to the speed mutation moment, the current trend starting time, and the speed-current time interval. The alternating trigger sequence information includes the fluctuation direction consistency distribution, the parameter fluctuation interleaving density, and the parameter combination trigger sequence.

3. The motor performance monitoring data processing system according to claim 1, characterized in that: The signal registration module includes: The extreme value anchoring submodule obtains the operation data monitoring sequence, including the voltage monitoring sequence and the current monitoring sequence, filters the extreme value points in each time period in the sequence, analyzes the position distribution of the extreme value points in each time period, and establishes the extreme value distribution index; The center of gravity trajectory analysis submodule calculates the center of gravity of the value distribution of the voltage and current sampling sequence in each time period based on the extreme value distribution index, compares the relative position changes of the voltage center of gravity and the current center of gravity in consecutive time periods, analyzes the consistency of the center of gravity movement trend in the voltage and current sequences, and obtains the center of gravity trajectory trend; The sampling arrangement adjustment submodule adjusts the arrangement order of the sampling frames on the time axis according to the center of gravity trajectory trend, determines the change trend of the center of gravity position of the sampling frames and the synchronization between the two sequences, and generates the center of gravity matching alignment axis.

4. The motor performance monitoring data processing system according to claim 3, characterized in that: The specific formula for comparing the relative position changes of the voltage center of gravity and the current center of gravity in continuous time periods is: ； Calculate the center of gravity trend deviation; in, Indicates the Normalized numerical center of gravity of the segment voltage sampling sequence, Indicates the Normalized numerical center of gravity of the segment current sampling sequence, Indicates the The normalized value of the amplitude range of the segment voltage sequence, Indicates the The normalized value of the amplitude range of the segment current sequence, Indicates the The trend direction symbol of the center of gravity of the voltage sequence of the segment relative to the previous segment, Indicates the The trend direction symbol of the center of gravity of the current sequence of the segment relative to the previous segment, Indicates the total number of continuous sequence segments involved in the calculation, Indicates the deviation of the voltage and current center of gravity trend, Indicates the sequence number of consecutive sampling time periods.

5. The motor performance monitoring data processing system according to claim 3, characterized in that: The rhythm decision module includes: The interval calculation submodule obtains the time intervals of consecutive current sampling points according to the center of gravity matching and alignment axis, analyzes the changes in adjacent time intervals of each sampling segment, classifies the time interval distribution order of all sampling segments, and generates a segment interval distribution sequence; The offset identification submodule determines the interval change order in each segment based on the segment interval distribution sequence, selects segments with continuous change order, marks them as offset aggregation segments, establishes a unidirectional offset structure, and obtains unidirectional offset segments; The anomaly detection submodule calls the unidirectional offset segment, analyzes the interval change direction of continuous sampling points in the corresponding segment, detects the segment with continuous same-direction offset by comparing the consistency and duration of the interval direction, records it as a rhythm abnormality segment, and obtains data processing records.

6. The motor performance monitoring data processing system according to claim 5, characterized in that: The trend hysteresis module includes: The abnormal segment screening submodule calls the data processing record, removes the data segments with abnormal rhythm, and obtains the mutation moment in the speed sequence on the remaining alignment axis by analyzing the speed slope of the speed data sequence to obtain the mutation moment sequence; The trend start positioning submodule locates the starting position of the current continuous change trend based on the mutation time sequence by analyzing the change direction of adjacent sampling points in the current sequence after the mutation moment, and generates the trend start time point; The hysteresis duration identification submodule calculates the relative distance between the mutation point time and the starting position time according to the trend starting time point, identifies the hysteresis response duration, and obtains the hysteresis response time information.

7. The motor performance monitoring data processing system according to claim 6, characterized in that: The role identification module includes: The fluctuation frame positioning submodule obtains the data processing record and hysteresis response time information, identifies the continuous fluctuation frames of voltage, temperature, and vibration, determines the change direction of each parameter in adjacent frames, analyzes the consistency of the change direction, and obtains the parameter fluctuation direction distribution information; The interleaving density discrimination submodule analyzes the order of fluctuations between parameters based on the parameter fluctuation direction distribution information, identifies the number of fluctuation interleavings for each pair of parameters, analyzes the number of order alternations for each pair of parameters, and calculates the fluctuation interleaving density for each pair of parameters to obtain a fluctuation interleaving density matrix; The sequence information generation submodule identifies the combination relationship between multiple parameters according to the fluctuation interleaving density matrix, constructs state labels between the parameters, sorts the triggering order of multiple groups of state labels, establishes alternating triggering sequence information, and obtains alternating triggering sequence information.

8. The motor performance monitoring data processing system according to claim 7, characterized in that: The specific formula for calculating the fluctuation interleaving density of each pair of parameters is: ； Calculate the value of the wave interlaced density; in, For parameters With parameters The fluctuating staggered density value in the observation sequence, For parameters At the time point and time point The normalized value of the direction difference, For parameters At the time point and time point The normalized value of the direction difference, is the sampling time point index, is the number of sampling points corresponding to the total duration of the sampling period, is the first parameter number involved in the analysis, The number of the second parameter involved in the analysis.

9. The motor performance monitoring data processing system according to claim 1, characterized in that: The system further comprises: The tag scheduling module calls the alternating trigger sequence information, extracts the parameter pair with the highest interleaving density and uses it as the dominant parameter combination, calls the distribution sequence of the corresponding state tags on the time axis, analyzes the cumulative number of occurrences of the tags in the continuous time period, compares the cumulative number of multiple tags, adjusts the output order of the state tags according to the number, and outputs the state tag sorting result; The state tag sorting results are specifically the dominant parameter tag combination, the cumulative number of state tag occurrences, and the tag time series distribution.

10. The motor performance monitoring data processing system according to claim 9, characterized in that: The label scheduling module includes: The dominant parameter screening submodule calls the alternating trigger sequence information, screens the parameter pair with the highest interleaving density, and uses it as the dominant parameter combination, locates the identifier of the target parameter combination in the state label sequence, and obtains the dominant parameter label index; The tag statistics submodule collects the distribution sequence of the corresponding state tag on the time axis based on the dominant parameter tag index, counts the cumulative number of times the tag appears in a continuous time period, and obtains the cumulative number of tag appearances; The output sorting submodule adjusts the output order of multiple status tags according to the cumulative number of occurrences of the tags, arranges the tag output priorities, and obtains the status tag sorting results.

Images