A predictive maintenance method for transmission equipment

Abstract

The present invention discloses a method for predictive maintenance of transmission equipment, which relates to the technical field of transmission equipment maintenance and is applied to a roller conveying system for flexible materials. The method is characterized in that it includes the following steps: S1, placing position triggers at each key transition node of the roller conveyor to collect the timestamps of the materials passing through the detection points in real time, and generating a unique number and a corresponding time series relationship for each material; S2, calculating the standard material passing time based on the theoretical beat cycle, and subtracting the actual time from the standard cycle to construct a beat offset set to reflect the conveying beat deviation of the materials between adjacent detection points. The present invention realizes early warning and intelligent regulation of flexible material conveying rhythm disorders through beat offset modeling, abnormal cluster identification and root cause diagnosis, and dynamically adjusts the compression bandwidth and drive delay when the risk of disorder occurs, effectively alleviating the risk of accumulation, and improving system stability, automation level and operating efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of transmission equipment maintenance, and in particular to a method for predictive maintenance of transmission equipment. Background Art

[0002] Predictive maintenance for conveyor equipment involves continuous data monitoring and intelligent analysis of automated material conveying equipment, such as tilters and roller conveyors, to proactively identify potential failures or performance degradation trends, enabling proactive intervention and planned maintenance before failures occur. This approach typically relies on real-time data collection of equipment operating parameters (such as motor current, vibration spectrum, temperature rise curve, and speed fluctuation). By building health assessment models or incorporating machine learning algorithms, the wear level or failure probability of key components (such as bearings, chains, and rollers) is determined. This approach optimizes maintenance timing, avoids unplanned downtime, improves transmission efficiency and production line stability, and reduces production interruptions and repair costs caused by failures.

[0003] The existing technology has the following deficiencies:

[0004] When handling flexible materials such as soft packaging or bagged materials, existing automated material conveying systems have technical problems such as localized stacking imbalances caused by insufficient conveying rhythm control accuracy. Especially at the corners, junctions, or end buffers of roller conveyor lines, if the roller drive rhythm is locally misaligned, it can easily cause the material aggregation density to rise rapidly in a short period of time, forming a "critical stacking density" state. Since flexible materials themselves lack structural support capabilities, once the density critical point is exceeded, local collapse or mutual squeezing of materials will occur, resulting in leakage of contents and damage to outer packaging, further inducing pushing imbalances and conveying blockages. This type of problem not only destroys the integrity of the material, but in severe cases can also cause chain stacking blockages, requiring manual intervention for disassembly and cleaning. This not only increases the risk of line stoppages, but also significantly affects the stability and operating efficiency of the entire production line.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a predictive maintenance method for transmission equipment, which collects material timestamps in real time at key transportation nodes, constructs a beat offset model, combines density clustering and extreme value analysis to identify imbalance cluster segments, and uses distance change and speed data to diagnose the source of imbalance; calculates the beat imbalance index through the beat offset intensity, frequency and duration, and dynamically adjusts the compression bandwidth of the flexible material when the beat imbalance index exceeds the risk threshold, realizes buffering adjustment by controlling the drive delay, effectively absorbs beat disturbances, prevents material collapse and blockage, effectively improves the visual management and adaptability of the conveying system, reduces the risk of manual intervention and line stoppage, and solves the problems in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for predictive maintenance of transmission equipment, applied to a roller conveying system for flexible materials, comprising the following steps:

[0008] S1. Position triggers are placed at each key transition node of the roller conveyor to collect the timestamps of materials passing through the detection points in real time and generate a unique number and corresponding time series relationship for each material;

[0009] S2. Calculate the standard material passing time based on the theoretical beat cycle, and subtract the actual time from the standard cycle to construct a beat offset set to reflect the material conveying beat deviation between adjacent detection points;

[0010] S3. Perform local extreme value analysis and density clustering operations on the beat offset set within the sliding time window to extract the imbalance cluster segment and mark its range and evolution trend on the time axis;

[0011] S4. Based on the distance change curve of the front and rear materials, combined with the set speed and feedback speed data of each drive section, analyze whether the beat imbalance is caused by drive mismatch, material slippage or foreign object interference;

[0012] S5. Normalize the amplitude, frequency, and duration of the beat deviation and calculate the beat deviation index based on the spatial position distribution weight of the deviation segment to quantify the synchronization stability level of the conveying system in the current cycle;

[0013] S6. When the beat imbalance index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and flexible stacking buffering and beat compensation are achieved by controlling the drive delay within the controllable stacking range.

[0014] Preferably, the step of arranging position triggers at each key transition node of the roller conveyor includes the following specific operations:

[0015] A position trigger is constructed at the key transition nodes of the roller conveyor by combining a laser beam sensor with a high-frequency encoder. This position trigger is used to accurately capture the moment when the leading edge of the flexible material passes with a high time resolution of less than 5 milliseconds, thereby accurately identifying high-speed passing materials. After the position trigger collects the timestamp signal of the material passing event, it is combined with the current operating status parameters of the roller conveyor section (including operating speed, drive number, etc.) to assign a set of unique identifiers to each unit of material. This identifier includes the material serial number, the section number and the timestamp information, ensuring the uniqueness and traceability of the material throughout the entire conveying process. The correspondence between the unique identifier and the timestamp is written into the central time series cache table for subsequent beat offset analysis and time series modeling. This cache table has a first-in-first-out structure and supports real-time data updates to ensure the timing consistency and high-frequency dynamic data processing capabilities of the entire conveyor line.

[0016] Preferably, the step of calculating the standard material passing time based on the theoretical takt cycle, subtracting the actual time from the standard cycle, and constructing a takt offset set includes the following specific operations:

[0017] Based on the structural parameters and rated drive speed of each conveying section in the roller conveyor system, a theoretical beat cycle model is pre-established. The model dynamically calculates the standard transmission time period that a unit material should experience from the previous detection point to the current detection point under ideal conditions according to the length of each type of material, the length of the conveying section and the set linear speed. It also supports adaptive adjustment of model parameters for different flexible material characteristics (such as compressibility and slip tendency). The two timestamp values ​​of the same numbered material at adjacent detection points are retrieved from the central time series cache table, and the difference between the two is used as the actual passing time of the material in the conveying section, and is compared with the time series. The theoretical beat period of the segment is compared and calculated to obtain the beat offset value of the material, which is then recorded in the beat offset set in the order of material arrival. To improve the sensitivity of identifying continuous beat disturbances, the system performs a sliding segment superposition algorithm on the beat offset set, applies weight markings to the parts of the material flow with continuous offset trends, and eliminates isolated abnormal offset values ​​caused by single-point measurement errors or slight jitters of the conveying system, thereby constructing a beat offset set with trend stability and analytical robustness, providing a reliable data basis for subsequent cluster analysis, local synchronization imbalance identification, and beat disturbance modeling.

[0018] Preferably, the step of performing local extreme value analysis and density clustering operations on the beat offset set within the sliding time window includes the following operations: setting a fixed-length or dynamically adjustable sliding time window, and the system extracting a continuous data sequence from the beat offset set in a periodic scheduling manner as local sample data within the current analysis window, which is used to capture the tempo fluctuation behavior of the beat within a short period; performing a local extreme value analysis operation on the extracted local offset samples, using the first-order difference method combined with the sliding variance algorithm to identify the sudden rise, sudden fall and critical oscillation points of the offset value, and extracting the turning signal of the beat disturbance and the turning point of the change trend to reveal the potential starting point of synchronization imbalance; based on Based on the density distribution characteristics of the offset values ​​of the local sample, a density-based spatial clustering algorithm (such as DBSCAN) is used to cluster and identify the beat offset points, and automatically distinguish the clustered segments of dense and continuous offsets from the outlier segments of dispersed fluctuations, thereby constructing the precise boundaries and morphological characteristics of the beat imbalance segments; the identified imbalance clustered segments are mapped to the global time axis coordinate system, and their evolution trends are marked according to their duration, local density intensity and offset trend slope in the sliding time window, and they are divided into "growth type", "decay type" or "fluctuation type" imbalance modes, providing classification judgment basis and dynamic input parameters for the system's synchronous speed regulation strategy selection and risk warning mechanism.

[0019] Preferably, the identified disorder cluster segments are mapped to the global time axis coordinate system, and the evolution trend is marked according to the duration, local density intensity and offset trend slope of the disorder cluster segments in the sliding time window, and they are divided into "growth type", "decay type" or "fluctuation type" disorder modes. The specific steps are as follows: all the offset data points in the disorder cluster segments identified by density clustering are mapped back to the global time axis coordinate system according to their original timestamps, and the time range and start and end boundaries of the cluster segments in the global dimension are constructed to uniformly manage the disorder events in each local analysis window and realize the time positioning and historical comparison of the beat disturbance of the whole line; for the mapped disorder cluster segments, their duration in the sliding time window is calculated. The duration (the time span of the clustered segment), local density intensity (the density or mean amplitude of offset points per unit time), and offset trend slope (the slope of the offset value change curve based on the least squares fitting method) comprehensively reflect the strength, stability, and development direction of the imbalanced segment. According to the preset multidimensional classification judgment rules, the trend is classified in combination with the above three quantitative indicators: if the slope is positive and the density increases, it is marked as "growth type"; if the slope is negative and the duration is prolonged, it is marked as "decay type"; if the slope fluctuates significantly but the overall amplitude is limited, it is classified as "fluctuation type". The evolution trend label is attached to the data metadata of the imbalanced segment, providing strategic judgment and decision-making clues for subsequent segmented speed regulation strategies, priority control, and abnormal warning.

[0020] Preferably, the step of analyzing the source of beat imbalance based on the distance change curve of the front and rear materials and in combination with the set speed and feedback speed data of each driving section includes the following specific operations: based on the timestamp information of the trigger points of the continuous materials at adjacent positions, combined with the spatial structure parameters of the roller conveying section, dynamically calculating the material spacing change curve, and constructing a "time-distance" relationship model by sliding fitting to detect whether there is a nonlinear compression or expansion trend and reveal the dynamic evolution of the material flow density; synchronously collecting the set speed parameters and actual feedback speed signals of each driving section from the conveying control system, and comparing them within the corresponding time window, Identify whether there is a systematic deviation between setting and feedback, and further combine the material spacing trend to construct a correlation matrix between drive response and logistics behavior; based on the data model constructed above, call the embedded multi-factor imbalance judgment logic, and judge one by one according to the three characteristic pattern matching rules of drive mismatch, material slippage and foreign object interference: if the feedback speed of the drive section abnormally lags behind the set value, it is inferred to be drive mismatch; if the material spacing change is not supported by the drive abnormality, it is inferred to be material slippage; if a sudden spacing disturbance occurs accompanied by a signal interruption, it is identified as foreign object interference, and the final diagnosis result is written into the imbalance event tag for subsequent processing module to call.

[0021] Preferably, the step of calculating the beat imbalance index includes the following operations: for each imbalance segment identified in the sliding time window, the beat offset amplitude (i.e., the maximum offset value), offset frequency (the number of offsets occurring per unit time) and duration (the span of the imbalance segment on the time axis) corresponding to each segment are extracted in turn, and the above three dimensional features are normalized in combination with the upper and lower limits of the system preset standards to form an imbalance characteristic factor matrix under a unified scale, thereby improving the horizontal comparability and modeling consistency of the imbalance states among multiple segments; in combination with the physical spatial position of each imbalance segment in the conveyor line, the normalized imbalance characteristic factor is subjected to spatial weighting processing, wherein for key control nodes such as corners, confluence sections, and end sections, the spatial weighting is used to calculate the normalized imbalance characteristic factor. The end buffer area is given a higher sensitivity coefficient to reflect its importance in the overall stability structure of the system, and finally a comprehensive imbalance score that integrates the beat disturbance intensity and the structural position weight is formed; the above weighted score is used as the input feature and imported into the beat imbalance index evaluation model, and a weighted average mechanism or segment aggregation rule is adopted to output a unified quantitative indicator representing the beat synchronization stability in the current conveying system cycle, namely the beat imbalance index. This beat imbalance index can be used as the core display parameter in the conveying status visualization panel, and can also be used as the judgment input for subsequent modules such as dynamic speed control, flexible buffer start-stop adjustment and fault warning mechanism, so as to realize the accurate quantification and intelligent drive of the health status of the entire conveying line.

[0022] Preferably, when the beat disorder index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and the driving delay within the controllable stacking range is controlled. The specific steps are as follows:

[0023] During each monitoring cycle, the beat imbalance index of the conveyor line is continuously evaluated and compared with the preset risk threshold. When the beat imbalance index is greater than the risk threshold, it means that the system beat disturbance in the current cycle has reached a perceptible risk level and the flexible response mechanism needs to be activated to mitigate the spread of the imbalance. At this time, the system will dynamically calculate the compression band tolerance coefficient of the flexible material based on the current imbalance intensity and distribution. The calculation formula is: ,in: It is the current beat imbalance index, which quantifies the degree of synchronization deviation of the roller conveyor system; is the set risk threshold, representing the lower limit of the allowed synchronization stability; The maximum historical misalignment index of the roller conveyor system, used to normalize the adjustment scale; Spatial sensitivity weights for misaligned segments (e.g., higher weights for corner segments); and is the empirical adjustment coefficient, which is used to balance the impact of global imbalance intensity and structural risk; is the compression band tolerance coefficient, indicating the controllable bulk density range;

[0024] After calculating the compression band tolerance coefficient, the response delay time of the partition driver unit is adjusted according to the compression band tolerance coefficient within the imbalance aggregation section. The adjustment expression is: ,in: is the dynamic delay response time of the drive unit; The average length of the current flexible material, used to estimate the stacking space size; Set the conveying speed for the current section; is the response adjustment factor, which is used to control the response speed and stacking buffer sensitivity.

[0025] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0026] The present invention collects material movement timestamps in real time at key nodes of the conveying path, and constructs a beat offset model based on the theoretical beat, so that the system can identify rhythm disorder trends at an early stage; further, with the help of density clustering and extreme value analysis, the disorder cluster segments are extracted, and source classification diagnosis is performed through distance curves and speed data to locate the root cause of the beat disturbance; finally, a unified and quantitative "beat disorder index" is constructed based on the beat offset intensity, frequency and duration, and the controllable compression bandwidth of the flexible material is dynamically adjusted when the risk threshold is exceeded. Local buffering is achieved by driving the delay strategy, thereby effectively alleviating the propagation of disorder, absorbing the impact of beat fluctuations, and avoiding the collapse, squeezing, breakage or chain blockage of flexible materials in key sections. This not only improves the visual management and self-regulation capabilities of the conveying process, but also reduces dependence on manual intervention and reduces the risk of system shutdown. It has significant practical engineering application value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0028] Figure 1 This is a flow chart of a method for predictive maintenance of transmission equipment according to the present invention. DETAILED DESCRIPTION

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0030] The present invention provides Figure 1 A predictive maintenance method for transmission equipment is shown, which is applied to a roller conveying system for flexible materials and includes the following steps:

[0031] S1. Position triggers are placed at each key transition node of the roller conveyor to collect the timestamps of materials passing through the detection points in real time and generate a unique number and corresponding time series relationship for each material;

[0032] The steps for deploying position triggers at key transition nodes of the roller conveyor include the following specific operations:

[0033] A position trigger is constructed at the key transition nodes of the roller conveyor by combining a laser beam sensor with a high-frequency encoder. This position trigger is used to accurately capture the moment when the leading edge of the flexible material passes with a high time resolution of less than 5 milliseconds, thereby accurately identifying high-speed passing materials. After the position trigger collects the timestamp signal of the material passing event, it is combined with the current operating status parameters of the roller conveyor section (including operating speed, drive number, etc.) to assign a set of unique identifiers to each unit of material. This identifier includes the material serial number, the section number and the timestamp information, ensuring the uniqueness and traceability of the material throughout the entire conveying process. The correspondence between the unique identifier and the timestamp is written into the central time series cache table for subsequent beat offset analysis and time series modeling. This cache table has a first-in-first-out structure and supports real-time data updates to ensure the timing consistency and high-frequency dynamic data processing capabilities of the entire conveyor line.

[0034] Position triggers are deployed at key transition points on the roller conveyor to collect real-time timestamps of material passing through detection points. A unique number is generated for each material, corresponding to a time series. This serves as a core data foundation for the predictive maintenance algorithm, providing a highly accurate and time-consistent data model for accurately modeling and tracking the dynamic behavior of flexible materials during automated conveying. Due to the inherent structural stability of flexible packaging or bagged materials, their motion is susceptible to factors such as rhythm perturbations, uneven friction, and accumulation resistance. Small deviations in operating rhythm can accumulate at certain points and lead to serious failures such as accumulation, collapse, or jostling imbalance. Therefore, fine-grained spatiotemporal labeling of each material unit is essential to ensure the system understands its actual transit time at each key point, thereby assessing rhythm consistency and transmission delays during the conveying process. By assigning a unique number to each material and establishing a corresponding time series, not only does this enable accurate identification and tracking of materials throughout the conveyor path, but it also provides a reliable data foundation for subsequent calculations of rhythm offsets, identification of synchronization errors, and analysis of drive misalignment.

[0035] S2. Calculate the standard material passing time based on the theoretical beat cycle, and subtract the actual time from the standard cycle to construct a beat offset set to reflect the material conveying beat deviation between adjacent detection points;

[0036] The steps for calculating the standard material passing time based on the theoretical takt cycle, subtracting the actual time from the standard cycle, and constructing a takt offset set include the following specific operations:

[0037] Based on the structural parameters and rated drive speed of each conveying section in the roller conveyor system, a theoretical beat cycle model is pre-established. The model dynamically calculates the standard transmission time period that a unit material should experience from the previous detection point to the current detection point under ideal conditions according to the length of each type of material, the length of the conveying section and the set linear speed. It also supports adaptive adjustment of model parameters for different flexible material characteristics (such as compressibility and slip tendency). The two timestamp values ​​of the same numbered material at adjacent detection points are retrieved from the central time series cache table, and the difference between the two is used as the actual passing time of the material in the conveying section, and is compared with the time series. The theoretical beat period of the segment is compared and calculated to obtain the beat offset value of the material, which is then recorded in the beat offset set in the order of material arrival. To improve the sensitivity of identifying continuous beat disturbances, the system performs a sliding segment superposition algorithm on the beat offset set, applies weight markings to the parts of the material flow with continuous offset trends, and eliminates isolated abnormal offset values ​​caused by single-point measurement errors or slight jitters of the conveying system, thereby constructing a beat offset set with trend stability and analytical robustness, providing a reliable data basis for subsequent cluster analysis, local synchronization imbalance identification, and beat disturbance modeling.

[0038] This step primarily aims to quantify the tempo discrepancies between the actual material conveying process and the theoretical ideal, revealing subtle synchronization errors or potential misalignment trends within the automated conveying system. This provides critical data support for predictive maintenance and adaptive control. In roller conveyor systems, particularly those used for flexible materials, small disturbances in the conveyor path can quickly accumulate into tempo disruption, localized accumulation, or even complete blockages due to their unstable physical form, susceptibility to slippage, and extrusion. Therefore, relying solely on traditional "arrival or not" logic is crucial; precise calculation of the material transport time between each key detection node is essential. By establishing a standard tempo cycle model, the system determines how long each material should ideally take to pass through adjacent detection points. Subtracting this theoretical value from the actual measured time difference creates a "tempo offset set" that comprehensively reflects the tempo consistency and fluctuation characteristics across different conveyor segments. This difference not only reveals local drive unit mismatches but can also indicate early signs of operational anomalies such as material accumulation, foreign object interference, and slippage delays. The beat offset set serves as an important input for subsequent cluster analysis, beat disturbance trend identification, and speed control strategies. It can help the system achieve "continuous perception" and "dynamic correction" of the conveying status, thereby ensuring the timing coordination and flexible response capability of the entire line operation, and significantly reducing the occurrence rate of failures and maintenance costs.

[0039] S3. Perform local extreme value analysis and density clustering operations on the beat offset set within the sliding time window to extract the imbalance cluster segment and mark its range and evolution trend on the time axis;

[0040] The steps of performing local extreme value analysis and density clustering operations on the beat offset set within a sliding time window include the following operations: setting a fixed-length or dynamically adjustable sliding time window, and the system extracting a continuous data sequence from the beat offset set in a periodic scheduling manner as the local sample data within the current analysis window, which is used to capture the tempo fluctuation behavior of the beat within a short period; performing local extreme value analysis operations on the extracted local offset samples, using the first-order difference method combined with the sliding variance algorithm to identify the sudden rise, sudden fall and critical oscillation points of the offset value, and extracting the turning signal of the beat disturbance and the turning point of the change trend to reveal the potential starting point of synchronization imbalance; based on this The offset value density distribution characteristics of local samples are used to cluster and identify beat offset points using a density-based spatial clustering algorithm (such as DBSCAN), automatically distinguishing the clustered segments of dense and continuous offsets from the outlier segments of dispersed fluctuations, thereby constructing the precise boundaries and morphological characteristics of the beat imbalance segments; the identified imbalance clustered segments are mapped to the global time axis coordinate system, and their evolutionary trends are marked according to their duration, local density intensity and offset trend slope within the sliding time window, and they are divided into "growth type", "decay type" or "fluctuation type" imbalance modes, providing classification judgment basis and dynamic input parameters for the system's synchronous speed regulation strategy selection and risk warning mechanism.

[0041] The identified imbalance cluster segments are mapped to the global time axis coordinate system, and the evolution trend is marked according to the duration, local density intensity and offset trend slope of the imbalance cluster segments in the sliding time window, and they are divided into "growth type", "decay type" or "fluctuation type" imbalance modes. The specific steps are as follows: all the offset data points in the imbalance cluster segments identified by density clustering are mapped back to the global time axis coordinate system according to their original timestamps, and the time range and start and end boundaries of the cluster segments in the global dimension are constructed to uniformly manage the imbalance events in each local analysis window and realize the time positioning and historical comparison of the beat disturbance of the whole line; for the mapped imbalance cluster segments, their duration in the sliding time window is calculated. The time span of the clustered segment, local density intensity (density or mean amplitude of offset points per unit time), and offset trend slope (slope of the offset value change curve based on least squares fitting) comprehensively reflect the strength, stability, and development direction of the imbalanced segment. According to the preset multidimensional classification judgment rules, the trend is classified in combination with the above three quantitative indicators: if the slope is positive and the density increases, it is marked as "growth type"; if the slope is negative and the duration is prolonged, it is marked as "decay type"; if the slope fluctuates significantly but the overall amplitude is limited, it is classified as "fluctuation type". The evolution trend label is attached to the data metadata of the imbalanced segment, providing strategic judgment and decision-making clues for subsequent segmented speed regulation strategies, priority control, and abnormal warning.

[0042] Local extreme value analysis and density clustering are performed on the set of beat offsets within a sliding time window. Dissynchronization clusters are extracted, their timescales, and their evolutionary trends are marked. This step is crucial for dynamically identifying and trending local beat synchronization misalignments in flexible material conveying processes, thereby providing an accurate basis for subsequent speed regulation strategies, risk warnings, and maintenance decisions. In actual operation, beat offsets are often not linear or continuous anomalies, but rather manifest as "clustered fluctuations," "local jitter," or "sudden drift," exhibiting significant temporal localization and nonlinear characteristics. Relying solely on global statistics or fixed thresholds often fails to promptly detect these potentially risky perturbations. Therefore, a sliding time window allows for dynamic sampling analysis of beat offsets. Combined with local extreme value analysis, these sudden changes in beat disturbances can be detected. Density clustering methods (such as DBSCAN) can effectively identify the boundaries and structure of abnormal clusters, eliminating noise and discrete point interference. Ultimately, by mapping the identified misaligned segments onto the global timeline and categorizing and annotating their evolutionary trends (such as growth, decay, and fluctuation), the system can visualize the timing of the conveyor chain's beat synchronization and identify trends, laying the data and model foundation for flexible control and predictive maintenance. This step serves as a bridging link in the entire predictive maintenance algorithm, serving as a critical step in the transition from basic data collection to intelligent identification and serving as the "sensing hub" for ensuring stable flexible material transportation.

[0043] S4. Based on the distance change curve of the front and rear materials, combined with the set speed and feedback speed data of each drive section, analyze whether the beat imbalance is caused by drive mismatch, material slippage or foreign object interference;

[0044] The steps of analyzing the source of beat imbalance based on the distance change curve of the front and rear materials and combining the set speed and feedback speed data of each drive section include the following specific operations: based on the timestamp information of the trigger points of the continuous materials at adjacent positions, combined with the spatial structure parameters of the roller conveying section, dynamically calculate the material spacing change curve, and construct a "time-distance" relationship model through sliding fitting to detect whether there is a nonlinear compression or expansion trend and reveal the dynamic evolution of the material flow density; synchronously collect the set speed parameters and actual feedback speed signals of each drive section from the conveying control system, and compare them within the corresponding time window to identify Whether there is a systematic deviation between setting and feedback, further combined with the material spacing trend, a correlation matrix between drive response and logistics behavior is constructed; based on the data model constructed above, the embedded multi-factor imbalance judgment logic is called, and judgments are made one by one according to the three characteristic pattern matching rules of drive mismatch, material slippage and foreign object interference: if the feedback speed of the drive section abnormally lags behind the set value, it is inferred that it is a drive mismatch; if the material spacing change is not supported by the drive abnormality, it is inferred that it is material slippage; if a sudden spacing disturbance occurs accompanied by a signal interruption, it is identified as foreign object interference, and the final diagnosis result is written into the imbalance event tag for subsequent processing module to call.

[0045] Based on the distance curve between the front and rear materials, combined with the set and feedback speed data for each drive section, analyzing whether the beat deviation stems from drive mismatch, material slippage, or foreign object interference is a key step in diagnosing and classifying beat anomalies. Its purpose is to accurately identify the cause of the beat deviation, moving from "symptom identification" to "root cause identification," thereby providing a targeted and precise intervention path for subsequent control strategies. In actual operation, flexible materials, due to their inherent instability, are highly susceptible to subtle anomalies in the conveyor system, such as drive motor response delays, belt slippage, sensor interference, or foreign objects. These factors often cause the conveyor beat to deviate, leading to cascading failures such as accumulation and collapse. Beat deviation alone cannot determine the underlying cause. Therefore, continuous modeling of the dynamic variation in material spacing is necessary, combining the set values ​​of each drive section during this period with the actual feedback signals for comparison and analysis. By calculating the changing trends in the distance between the front and rear materials, it is possible to identify compression, stagnation, or abnormal sparseness in the logistics chain. Correlating this with the set-feedback deviations in the drive speed can further determine whether there are pattern characteristics of "drive mismatch" (such as hysteresis or failure of the drive section), "material slip" (such as material displacement but normal drive), or "foreign object interference" (such as sudden jumps or sensor interruptions). This step enables the system to automatically classify and label different types of rhythm disturbance behaviors, not only improving the dimensionality and accuracy of the system's perception capabilities but also providing a decision-making basis for hierarchical response strategies (such as speed regulation, obstacle removal, and alarms), forming a key support link for algorithm intelligence.

[0046] S5. Normalize the amplitude, frequency, and duration of the beat deviation and calculate the beat deviation index based on the spatial position distribution weight of the deviation segment to quantify the synchronization stability level of the conveying system in the current cycle;

[0047] The steps for calculating the beat imbalance index include the following operations: for each imbalance segment identified in the sliding time window, extract the beat offset amplitude (i.e., maximum offset value), offset frequency (the number of offsets occurring per unit time) and duration (the span of the imbalance segment on the time axis) corresponding to each segment in turn, and normalize the above three dimensional features in combination with the upper and lower limits of the system preset standards to form an imbalance characteristic factor matrix under a unified scale, thereby improving the horizontal comparability and modeling consistency of the imbalance status among multiple segments; and perform spatial weighting on the normalized imbalance characteristic factors in combination with the physical spatial position of each imbalance segment in the conveyor line, wherein for key control nodes such as corners, confluence sections, and end buffers, the spatial weighting is used to calculate the normalized imbalance characteristic factors. The storage area is given a higher sensitivity coefficient to reflect its importance in the overall stability structure of the system, and finally a comprehensive imbalance score that integrates the beat disturbance intensity and the structural position weight is formed; the above weighted score is used as the input feature and imported into the beat imbalance index evaluation model, and a weighted average mechanism or segment aggregation rule is adopted to output a unified quantitative indicator representing the beat synchronization stability in the current conveying system cycle, namely the beat imbalance index. The beat imbalance index can be used as the core display parameter in the conveying status visualization panel, and can also be used as the judgment input for subsequent modules such as dynamic speed control, flexible buffer start-stop adjustment and fault warning mechanism, so as to realize the accurate quantification and intelligent drive of the health status of the entire conveying line.

[0048] Normalizing the amplitude, frequency, and duration of beat deviations and calculating the beat misalignment index based on the spatial distribution weights of the misaligned segments is a key step in achieving quantitative assessment of the beat synchronization stability of the entire conveyor system within its current cycle and supporting intelligent decision-making. This step transcends the traditional, crude method of determining the status of conveyor systems based solely on blockages or timeouts, introducing a multi-dimensional, continuous, and structure-aware index system to deeply model and trend-evaluate beat disturbances, thereby enabling real-time health monitoring, predictive control, and adaptive optimization of adjustment strategies for flexible material conveying systems.

[0049] In the transport of flexible packaging or bagged materials, slight deviations in the beat are often early signals of systemic failures (such as stack collapse, foreign object blockage, and drive mismatch). A single indicator (such as a specific offset time or a single lag) cannot fully reflect the overall state of the system. Therefore, this step first extracts three core characteristics of the misaligned segment: offset amplitude (fluctuation intensity), offset frequency (disturbance intensity), and duration (abnormal continuation trend). These characteristics are then normalized to allow for comparison and modeling of offset behaviors across different time windows and material types using the same dimensions. This step not only standardizes the data but also improves the stability and generalization capabilities of subsequent analysis and modeling.

[0050] Furthermore, to overcome the misconception that all disruptions are weighted equally, this step introduces a spatial distribution weighting mechanism to account for the impact of different transport segments on system stability. For example, disruptions occurring at system bottlenecks such as corners, junctions, and buffer zones can lead to more severe chain reactions, so the disturbance factors corresponding to these critical nodes should be given higher weights. This spatially sensitive mechanism ensures that the disruption indicator reflects not only the severity of the disruption but also its significance to the entire line, enhancing the algorithm's structural awareness.

[0051] Ultimately, by weightedly integrating the normalization factors and spatial weights of each misalignment segment, a unified "beat misalignment index" is output as the core indicator reflecting the synchronous stability of the conveying cycle. This beat misalignment index can be used to drive the speed regulation logic, flexible accumulation control strategy, and early warning system criteria of the production management system, enabling visual quantification and intelligent feedback on the conveying system's operating status. This provides a clear basis for stability ratings for on-site engineers and can also serve as an input parameter for predictive maintenance systems to predict the evolution of potential risks, ultimately improving the operational safety, flexible response capabilities, and intelligent control capabilities of the entire conveyor line.

[0052] S6. When the beat imbalance index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and flexible stacking buffering and beat compensation are achieved by controlling the drive delay within the controllable stacking range;

[0053] When the beat mismatch index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and the drive delay within the controllable accumulation range is controlled. The specific steps are as follows:

[0054] During each monitoring cycle, the beat imbalance index of the conveyor line is continuously evaluated and compared with the preset risk threshold. When the beat imbalance index is greater than the risk threshold, it means that the system beat disturbance in the current cycle has reached a perceptible risk level and the flexible response mechanism needs to be activated to mitigate the spread of the imbalance. At this time, the system will dynamically calculate the compression band tolerance coefficient of the flexible material based on the current imbalance intensity and distribution. The calculation formula is: ,in: It is the current beat imbalance index, which quantifies the degree of synchronization deviation of the roller conveyor system; is the set risk threshold, representing the lower limit of the allowed synchronization stability; The maximum historical misalignment index of the roller conveyor system, used to normalize the adjustment scale; Spatial sensitivity weights for misaligned segments (e.g., higher weights for corner segments); and is the empirical adjustment coefficient, which is used to balance the impact of global imbalance intensity and structural risk; is the compression band tolerance coefficient, indicating the controllable bulk density range;

[0055] The purpose of this step is to quantify the intensity of beat disorder and link the sensitivity of spatial structure to obtain a regulation factor for the controllable flexible stacking compression range, which serves as the input basis for the subsequent driving regulation strategy.

[0056] After calculating the compression band tolerance coefficient, the response delay time of the partition driver unit is adjusted according to the compression band tolerance coefficient within the imbalance aggregation section. The adjustment expression is: ,in: is the dynamic delay response time of the drive unit; The average length of the current flexible material, used to estimate the stacking space size; Set the conveying speed for the current section; is the response adjustment factor, which is used to control the response speed and stacking buffer sensitivity;

[0057] This delay is distributed to multiple drive controllers, causing some drive sections to experience instantaneous beat "delays," artificially creating controllable material accumulation. The flexibility and compressibility of the material mitigate beat offset fluctuations, implementing a "dynamic hysteresis-buffer absorption" mechanism. This step converts the calculated flexible response strategy into specific drive instructions, enabling real-time dynamic compensation of beat synchronization while avoiding uncontrollable congestion or material damage, ensuring the stability and flexible robustness of the entire line.

[0058] Adjusting the compression bandwidth of flexible materials essentially involves controlling the controlled accumulation of materials in local areas of the conveyor line to buffer material flow fluctuations caused by rhythm imbalance. This goal can be achieved in a variety of ways: first, the speed of the drive roller or the start-stop delay can be dynamically adjusted to make the material stay slightly longer in a certain section, thereby achieving flexible accumulation without causing actual blockage; second, the inter-segment control logic can be adjusted according to the real-time rhythm status, such as delaying the start of the downstream section and pausing the upstream section in advance, creating a spatial compression zone from the rhythm; third, the buffer zone or transition zone designed in the conveyor path can be used to stack the materials in this area in an orderly manner, ensuring that its stacking density is controlled within the structural limit that the packaging material can withstand; in addition, by synchronously controlling the sensor trigger frequency and the material number tracking algorithm, the material flow status can be intelligently identified and the compression bandwidth calculated at the software level.

[0059] By combining these methods, it is possible to achieve a "safe, predictable, and controllable" dynamic stacking bandwidth adjustment mechanism for flexible materials in the conveying system through joint control of software and hardware without the need for physical modification of the system, thereby effectively absorbing rhythm disturbances and improving system stability and intelligent response capabilities.

[0060] When the beat mismatch index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and flexible stacking buffering and beat compensation are achieved by controlling the drive delay within the controllable stacking range. Its core function is to provide the conveying system with an adaptive buffering adjustment mechanism to offset material flow fluctuations caused by beat synchronization mismatch, thereby avoiding serious consequences such as stacking collapse, jamming, and chain blockage, and ensuring the continuity and stability of the entire conveyor line. The logic behind this step is based on a deep understanding of the physical characteristics and system behavior laws during the flexible material conveying process: flexible materials such as bagged and soft-packed products are structurally unstable and prone to over-dense stacking or even damage due to local rhythm abnormalities. Traditional conveying systems often lack fine-grained buffering adjustment capabilities. Once beat mismatch occurs, it can easily evolve into a large-scale failure.

[0061] By calculating the beat misalignment index and determining whether it exceeds the risk threshold, the system can trigger a response mechanism at the earliest sign of a misalignment trend. The so-called "compression bandwidth" allows a certain degree of "controlled accumulation" of flexible materials within a limited space within the conveyor path for a short period of time. This accumulation, unlike congestion, acts as a "soft buffer layer" controlled by system perception and algorithmic control. The size of the compression bandwidth is dynamically calculated using the compression band tolerance coefficient, reflecting the system's tolerance for the current beat risk. This parameter affects the response logic of downstream drive segments. If the current beat misalignment index is high and the compression band tolerance coefficient increases, the system will delay the start of the drive, creating a "delay band" in a certain section, prompting the flexible material to automatically accumulate in this section, thereby absorbing the impact of upstream beat fluctuations.

[0062] The drive delay setting not only considers the current material length, conveying speed, and density distribution, but also the location and evolution of the imbalance, giving the adjustment spatial awareness and dynamic response capabilities. This allows the system to proactively adjust the drive rhythm when it detects an abnormal rhythm in a specific area, rather than passively relying on sensor alarms or line stoppages. This "buffer absorption + synchronous compensation" mechanism can locally mitigate the impact of the imbalance while maintaining the continuity and smoothness of material flow along the entire line.

[0063] In summary, the purpose of this step is to build an intelligent and adaptive stacking buffer strategy in a flexible material conveying environment, replacing the static transmission logic with a dynamic control strategy, so that the system can "respond flexibly, transition smoothly, and repair automatically" when facing rhythm disturbances, greatly improving the fault tolerance, robustness and operating efficiency of the flexible conveying system, and providing a core control means for realizing intelligent predictive maintenance.

[0064] By implementing the aforementioned predictive maintenance algorithm for conveying equipment, precise perception, dynamic identification, and adaptive control of the beat synchronization state during flexible material conveying can be achieved, significantly improving the operational stability and fault prevention capabilities of the entire roller conveyor system. This solution collects material movement timestamps in real time at key nodes along the conveyor path and constructs a beat deviation model based on theoretical beat data, enabling the system to identify rhythmic misalignment trends at an early stage. Density clustering and extreme value analysis are then used to extract misalignment clusters, and source classification and diagnosis are performed using distance curves and speed data to pinpoint the root cause of the beat disturbance. Finally, a unified, quantitative "beat misalignment index" is constructed by combining beat deviation intensity, frequency, and duration. When the risk threshold is exceeded, the controllable compression bandwidth of the flexible material is dynamically adjusted. Local buffering is achieved through a driven delay strategy, effectively mitigating misalignment propagation and absorbing the impact of beat fluctuations, preventing collapse, jostling, breakage, or chain jams in critical sections. In summary, this algorithm not only improves the visual management and self-regulation capabilities of the conveying process, but also reduces reliance on manual intervention and the risk of system downtime, demonstrating significant practical engineering application value and widespread adoption.

[0065] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0066] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0067] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A predictive maintenance method for transmission equipment, applied to a roller conveying system for flexible materials, characterized in that: The steps include: S1. Position triggers are placed at each key transition node of the roller conveyor to collect the timestamps of materials passing through the detection points in real time and generate a unique number and corresponding time series relationship for each material; S2. Calculate the standard material passing time based on the theoretical beat cycle, and subtract the actual time from the standard cycle to construct a beat offset set to reflect the material conveying beat deviation between adjacent detection points; S3. Perform local extreme value analysis and density clustering operations on the beat offset set within the sliding time window to extract the imbalance cluster segment and mark its range and evolution trend on the time axis; S4. Based on the distance change curve of the front and rear materials, combined with the set speed and feedback speed data of each drive section, analyze whether the beat imbalance is caused by drive mismatch, material slippage or foreign object interference; S5. Normalize the amplitude, frequency, and duration of the beat deviation and calculate the beat deviation index based on the spatial position distribution weight of the deviation segment to quantify the synchronization stability level of the conveying system in the current cycle; S6. When the beat imbalance index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and flexible stacking buffering and beat compensation are achieved by controlling the drive delay within the controllable stacking range.

2. A transmission equipment predictive maintenance method according to claim 1, characterized in that: The steps for deploying position triggers at key transition nodes of the roller conveyor include the following specific operations: A laser beam sensor and a high-frequency encoder are combined to create a position trigger at the key transition nodes of the roller conveyor. The position trigger is used to capture the moment when the front edge of the flexible material passes through with a high time resolution of less than 5 milliseconds. When the position trigger collects the timestamp signal of the material passing event, it combines the current operating status parameters of the roller conveyor section to assign a unique identifier to each unit of material. The identifier includes the material serial number, the section number and the timestamp information. The correspondence between the unique identifier and the timestamp is written into the central time series cache table for subsequent beat offset analysis and time series modeling.

3. A transmission equipment predictive maintenance method according to claim 2, characterized in that: The steps to calculate the standard material passing time based on the theoretical beat cycle and subtract the actual time from the standard cycle to construct the beat offset set are as follows: Based on the structural parameters and rated drive speed of each conveying section in the roller conveyor system, a theoretical beat cycle model is pre-established. Based on the length of each type of material, the length of the conveying section, and the set linear speed, the standard transmission time period that a unit of material should experience from the previous detection point to the current detection point under ideal conditions is dynamically calculated. Retrieve two timestamp values ​​for materials with the same number at adjacent detection points from the central time series cache table. Use the difference between the two as the actual time the material passes through the conveyor section. Compare this with the theoretical beat period of the section to calculate the beat offset value for the material and record it in the beat offset set in the order in which the materials arrive. A sliding segment superposition algorithm is performed on the beat offset set, and weight marks are applied to the parts of the material flow with continuous offset trends. At the same time, isolated abnormal offset values ​​caused by single-point measurement errors or slight jitters of the conveying system are eliminated.

4. A transmission equipment predictive maintenance method according to claim 1, characterized in that: The steps for performing local extreme value analysis and density clustering on a set of beat offsets within a sliding time window are as follows: Set a fixed-length or dynamically adjustable sliding time window, and extract a continuous data sequence from the beat offset set in a periodic scheduling manner as the local sample data within the current analysis window to capture the timing fluctuation behavior of the beat in a short period; For the extracted local offset samples, a local extreme value analysis operation is performed. The first-order difference method is combined with the sliding variance algorithm to identify the sudden rise, sudden drop and critical oscillation points of the offset value, from which the turning signal of the beat disturbance and the turning point of the change trend are extracted; Based on the density distribution characteristics of the offset values ​​of the local offset samples, a density-based spatial clustering algorithm is used to cluster and identify the beat offset points. The clustered segments of dense and continuous offsets are automatically distinguished from the outlier segments of dispersed fluctuations, and the boundaries and morphological characteristics of the beat disorder segments are constructed. The identified disorder cluster segments are mapped to the global time axis coordinate system, and their evolutionary trends are marked according to their duration, local density intensity, and offset trend slope within the sliding time window, and are divided into "growth type", "decay type" or "fluctuation type" disorder patterns.

5. A transmission equipment predictive maintenance method according to claim 4, characterized in that: The identified imbalance cluster segments are mapped to the global time axis coordinate system. The evolution trend of the imbalance cluster segments is marked according to their duration, local density intensity, and offset trend slope within the sliding time window, and they are classified as "growth type", "decay type", or "fluctuation type" imbalance patterns. The specific steps are as follows: Map all offset data points in the imbalanced cluster segments identified by density clustering back to the global time axis coordinate system according to their original timestamps, and construct the time range and start and end boundaries of the cluster segment in the global dimension; For the mapped disordered cluster segments, calculate their duration, local density intensity, and offset trend slope within the sliding time window; According to the preset multidimensional classification judgment rules, combined with quantitative indicators, trend classification is performed: if the slope is positive and the density increases, it is marked as "growth type"; if the slope is negative and the duration is prolonged, it is marked as "decay type"; if the slope fluctuates significantly but the overall amplitude is limited, it is classified as "fluctuation type", and the evolution trend label is attached to the data metadata of the imbalance segment.

6. A transmission equipment predictive maintenance method according to claim 1, characterized in that: The steps for analyzing the source of beat imbalance based on the distance change curve of the front and rear materials and combining the set speed and feedback speed data of each drive section are as follows: Based on the time stamp information of the trigger points of adjacent positions of continuous materials and the spatial structural parameters of the roller conveyor section, the material spacing change curve is dynamically calculated, and a "time-distance" relationship model is constructed through sliding fitting. The set speed parameters and actual feedback speed signals of each drive section are synchronously collected from the conveying control system and compared within the corresponding time window to identify whether there are systematic deviations between the set speed and the feedback speed. Furthermore, the correlation matrix between the drive response and the logistics behavior is constructed by combining the material spacing trend. Based on the constructed data model, the embedded multi-factor imbalance judgment logic is called to judge one by one according to the three characteristic pattern matching rules of drive mismatch, material slippage and foreign object interference: if the feedback speed of the drive section abnormally lags behind the set value, it is inferred as drive mismatch; if the material spacing change is not supported by drive abnormality, it is inferred as material slippage; if a sudden spacing disturbance occurs accompanied by signal interruption, it is identified as foreign object interference.

7. A transmission equipment predictive maintenance method according to claim 1, characterized in that: The steps to calculate the beat disorder index are as follows: For each misalignment segment identified within the sliding time window, the beat offset amplitude, offset frequency, and duration corresponding to each segment are extracted in turn. Combined with the preset upper and lower limits of the roller conveyor system standard, the three-dimensional features are normalized to form a misalignment feature factor matrix at a unified scale. Combined with the physical spatial location of each imbalanced section in the conveyor line, the normalized imbalance characteristic factors are spatially weighted, with higher sensitivity coefficients assigned to key control nodes to form a comprehensive imbalance score that integrates the beat disturbance intensity and structural position weights. The above weighted scores are used as input features and imported into the beat disorder index evaluation model. A weighted average mechanism is used to output a unified quantitative index representing the beat synchronization stability within the current conveying system cycle, namely the beat disorder index.

8. The method for predictive maintenance of transmission equipment according to claim 1, characterized in that: When the beat mismatch index exceeds the set risk threshold, the compression bandwidth of the flexible material is dynamically adjusted, and the drive delay within the controllable accumulation range is controlled. The specific steps are as follows: The beat imbalance index of the conveyor line is continuously evaluated in each monitoring cycle and compared with the preset risk threshold. When the beat imbalance index is greater than the risk threshold, the flexible response mechanism is activated to alleviate the spread of the imbalance. The compression band tolerance coefficient of the flexible material is dynamically calculated based on the current imbalance intensity and distribution. The calculation formula is: ,in: It is the current beat imbalance index, which quantifies the degree of synchronization deviation of the roller conveyor system; is the set risk threshold, representing the lower limit of the allowed synchronization stability; The maximum historical misalignment index of the roller conveyor system, used to normalize the adjustment scale; is the spatial sensitivity weight of the imbalanced segment; and is the empirical adjustment coefficient, which is used to balance the impact of global imbalance intensity and structural risk; is the compression band tolerance coefficient, indicating the controllable bulk density range; After calculating the compression band tolerance coefficient, the response delay time of the partition driver unit is adjusted according to the compression band tolerance coefficient within the imbalance aggregation section. The adjustment expression is: ,in: is the dynamic delay response time of the drive unit; The average length of the current flexible material, used to estimate the stacking space size; Set the conveying speed for the current section; is the response adjustment factor, which is used to control the response speed and stacking buffer sensitivity.

Images