A method and system for dynamically adjusting a preventive maintenance cycle based on working condition self-learning

Abstract

The application relates to the technical field of equipment maintenance, and discloses a preventive maintenance period dynamic adjustment method and system based on working condition self-learning, which comprises the following steps: collecting electrical parameters and physical parameters of equipment; analyzing the fluctuation of main shaft current and the change of power factor, judging the electrical health state of the equipment according to the fluctuation and the change, and obtaining an electrical health value; obtaining a physical health initial value according to a vibration signal and the load weight of the equipment, correcting the physical health initial value according to the wear degree of the equipment, and obtaining a physical health final value; obtaining an equipment comprehensive health state value according to the electrical health value and the physical health final value, dynamically adjusting the current maintenance period of the equipment according to the equipment comprehensive health state value, and obtaining an adjusted maintenance period. The application can break the rigid mode of the traditional fixed maintenance period, and make the maintenance arrangement of the equipment more in line with the real running state and health condition of the equipment.

Description

Technical Field

[0001] This invention relates to the field of equipment maintenance technology, and more specifically, to a method and system for dynamically adjusting preventive maintenance cycles based on operating condition self-learning. Background Technology

[0002] With the rapid development of advanced manufacturing and automation technologies, machining equipment undertakes continuous operation tasks with long durations, high precision, and high loads during the production process. To ensure the stability of the equipment and the quality of processing, companies typically perform maintenance on the equipment according to fixed maintenance cycles.

[0003] However, experience-based or time-interval-based maintenance models have significant limitations: on the one hand, premature maintenance when equipment is in good operating condition can lead to unnecessary downtime, wasted labor, and spare parts; on the other hand, when equipment health has clearly declined but the maintenance cycle has not yet arrived, the optimal maintenance opportunity may be missed, leading to further escalation of the fault, equipment downtime, and even production interruptions and economic losses. In recent years, although some machine tool manufacturers have introduced sensor-based condition monitoring methods, such as vibration analysis and temperature monitoring, most still rely on single parameters or static threshold judgments, lacking integrated analysis of multiple electrical and mechanical parameters, and thus failing to accurately reflect the overall health status of the equipment. Furthermore, existing technologies rarely possess self-learning capabilities and cannot dynamically optimize maintenance strategies based on actual usage characteristics, resulting in insufficient accuracy and adaptability of maintenance plans.

[0004] Therefore, it is necessary to provide a method and system for dynamic adjustment of preventive maintenance cycles based on working condition self-learning to solve the limitations of experience-based or fixed time interval maintenance modes, such as premature maintenance when equipment is in good condition, which leads to waste, and missed opportunities when the health status declines before the cycle is reached, which can lead to the expansion of faults. Although some existing technologies have introduced sensor-based condition monitoring methods, they mostly rely on single parameter or static threshold judgment, lack multi-dimensional parameter fusion analysis and have insufficient self-learning ability, resulting in poor accuracy and adaptability of maintenance plans. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for dynamic adjustment of preventive maintenance cycle based on working condition self-learning. It aims to solve the limitations of maintenance mode based on experience or fixed time intervals, such as premature maintenance when equipment is running well, which leads to waste, and missed opportunities when the health status declines before the cycle is reached, which can lead to the expansion of faults. Although some existing technologies have introduced sensor-based condition monitoring methods, they mostly rely on single parameter or static threshold judgment, lack multi-dimensional parameter fusion analysis and have insufficient self-learning ability, resulting in poor accuracy and adaptability of maintenance plans.

[0006] On the one hand, this invention proposes a method for dynamically adjusting preventive maintenance cycles based on operating condition self-learning, including:

[0007] The electrical and physical parameters of the acquisition equipment are collected; wherein the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, equipment load weight, and equipment wear degree.

[0008] Analyze the fluctuations in spindle current and the changes in power factor, determine the electrical health status of the equipment based on the fluctuations and changes, and obtain the electrical health value;

[0009] An initial physical health value is obtained based on the vibration signal and the equipment load weight. It is then determined whether the initial physical health value needs to be corrected based on the degree of equipment wear. If it is determined that correction is needed, the initial physical health value is corrected based on the degree of equipment wear to obtain a final physical health value.

[0010] The overall health status value of the equipment is obtained based on the electrical health value and the final physical health value. The current maintenance cycle of the equipment is then dynamically adjusted based on the overall health status value of the equipment to obtain the adjusted maintenance cycle.

[0011] Furthermore, the analysis of spindle current fluctuations and power factor changes, and the determination of the equipment's electrical health status based on these fluctuations and changes, includes:

[0012] A data acquisition period is preset, and several data acquisition points are set within the data acquisition period. The main shaft current of each data acquisition point is acquired, and the current fluctuation value of the main shaft current of adjacent data acquisition points is calculated to form a set of fluctuation conditions.

[0013] The power factor of each sampling point is collected to construct a power factor set; and the factor fluctuation value of the power factor of adjacent sampling points is calculated to form a set of changes.

[0014] The electrical health status of the equipment is determined based on the set of fluctuations in the spindle current, the set of power factors, and the set of changes.

[0015] Furthermore, when determining the electrical health status of the equipment based on the set of fluctuation conditions, the set of power factors, and the set of changes, the following steps are included:

[0016] Calculate the average values ​​of the fluctuation set, the power factor set, and the change set respectively to obtain the average value of current fluctuation, the average value of power factor, and the average value of power factor change;

[0017] Pre-set the maximum current fluctuation and the minimum power factor;

[0018] If the average current fluctuation is less than the maximum current fluctuation and the average power factor is greater than the minimum power factor, the electrical health of the equipment is preliminarily judged to be good; if the average current fluctuation is greater than or equal to the maximum current fluctuation and the average power factor is greater than the minimum power factor, the electrical health of the equipment is preliminarily judged to be medium; if the average current fluctuation is less than the maximum current fluctuation and the average power factor is less than or equal to the minimum power factor, the electrical health of the equipment is preliminarily judged to be medium; if the average current fluctuation is greater than or equal to the maximum current fluctuation and the average power factor is less than or equal to the minimum power factor, the electrical health of the equipment is preliminarily judged to be poor; wherein, the electrical health of the equipment, from high to low, is good, medium, and poor.

[0019] Based on the average value of the power factor change, determine whether adjustments are needed to the initially assessed electrical health status of the equipment.

[0020] Furthermore, when determining whether adjustments to the initially assessed electrical health status of the equipment are needed based on the average power factor change, the following steps are included:

[0021] If the average power factor change is zero, it is determined that no adjustments will be made to the preliminary assessment of the equipment's electrical health status.

[0022] If the average value of the power factor change is not zero, it is determined that the electrical health status of the equipment needs to be adjusted based on the preliminary assessment.

[0023] If the average value of the power factor change is greater than zero, the electrical health status of the equipment will be upgraded by one level; if the electrical health status of the equipment is good, it will remain unchanged.

[0024] If the average power factor change is less than zero, the preliminary assessment of the equipment's electrical health status will be downgraded by one level; if the preliminary assessment of the equipment's electrical health status is poor, it will remain unchanged.

[0025] Furthermore, obtaining the electrical health value includes:

[0026] When the adjusted electrical health status of the equipment is poor, the electrical health value is the first health value;

[0027] When the adjusted electrical health status of the equipment is medium, the electrical health value is the second health value;

[0028] When the adjusted electrical health status of the equipment is good, the electrical health value is the third health value;

[0029] Among them, the first health value < the second health value < the third health value.

[0030] Furthermore, when obtaining the initial physical health value based on the vibration signal and the equipment load weight, the process includes:

[0031] Acquire equipment vibration signals and equipment load weight within a preset time period, and calculate the average equipment vibration and average load.

[0032] Collect the allowable vibration value and rated load of the equipment, calculate the vibration ratio of the average vibration value to the allowable vibration value, and the load ratio of the average load to the rated load, and obtain the initial physical health value based on the vibration ratio and load ratio.

[0033] Specifically, if both the vibration ratio and the load ratio are greater than 1, the initial physical health value is the first initial value; if either the vibration ratio or the load ratio is greater than 1, the initial physical health value is the second initial value; and if both the vibration ratio and the load ratio are less than 1, the initial physical health value is the third initial value.

[0034] In the initial values ​​of physical health, the first initial value < the second initial value < the third initial value.

[0035] Furthermore, when determining whether to correct the initial physical health value based on the degree of equipment wear, the following steps are included:

[0036] Obtain the wear area of ​​the equipment, calculate the ratio of the wear area to the equipment surface area, and record it as the degree of equipment wear;

[0037] If the wear level is greater than a preset wear threshold, it is determined that the initial physical health value should be corrected; otherwise, it is determined that the initial physical health value should not be corrected.

[0038] Furthermore, when correcting the initial physical health value based on the degree of equipment wear to obtain the final physical health value, the process includes:

[0039] The final physical health value is the product of the initial physical health value and the correction coefficient.

[0040] The degree of equipment wear is inversely proportional to the correction coefficient, which ranges from 0 to 1.

[0041] Furthermore, the step of obtaining a comprehensive equipment health status value based on the electrical health value and the final physical health value, and then dynamically adjusting the current maintenance cycle of the equipment based on the comprehensive equipment health status value to obtain the adjusted maintenance cycle includes:

[0042] The overall health status value of the equipment is the weighted sum of the electrical health value and the final physical health value.

[0043] Set a sum range; if the overall health status value of the device is greater than the maximum value of the sum range, then adjust the current maintenance cycle of the device using a first adjustment coefficient.

[0044] If the overall health status value of the equipment is within the sum range, the current maintenance cycle of the equipment is adjusted by the second adjustment coefficient;

[0045] If the overall health status value of the equipment is less than the minimum value of the sum range, the current maintenance cycle of the equipment will be adjusted by a third adjustment coefficient.

[0046] The adjustment coefficient ranges from 1 to 3, and the adjusted maintenance cycle is the product of the current maintenance cycle of the equipment and the adjustment coefficient.

[0047] Compared with existing technologies, the advantages of this invention are as follows: This invention breaks the rigid pattern of traditional fixed maintenance cycles, allowing equipment maintenance arrangements to better align with its actual operating and health conditions. By simultaneously collecting electrical and physical parameters, this invention constructs a multi-dimensional sensing system for equipment operating status. Spindle current and power factor reflect the load characteristics and operating efficiency of the motor and drive system, while vibration signals, load weight, and wear degree reveal the actual health level of the mechanical structure and processing. Through the fusion calculation of electrical and physical health values, a quantitative comprehensive health status value can be obtained, which can be used to dynamically adjust maintenance cycles, enabling flexible strategies for early warning or delayed maintenance. This dynamism not only extends the equipment's trouble-free operating time and reduces maintenance costs but also improves the stability of production plans by avoiding sudden failures. Furthermore, as the self-learning model continuously accumulates historical data, the accuracy of the algorithm's judgments will continuously improve, forming an adaptive and evolvable intelligent maintenance system. This greatly improves the scientific and advanced nature of equipment management, ultimately achieving the comprehensive goals of cost reduction, efficiency improvement, increased production capacity, and equipment utilization.

[0048] On the other hand, this application also provides a preventive maintenance cycle dynamic adjustment system based on operating condition self-learning, including:

[0049] The acquisition module is configured to acquire electrical and physical parameters of the device; wherein the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, device load weight, and device wear degree;

[0050] The analysis module is configured to analyze the fluctuations in spindle current and the changes in power factor, determine the electrical health status of the equipment based on the fluctuations and changes, and obtain an electrical health value.

[0051] The analysis module is also configured to obtain an initial physical health value based on the vibration signal and the equipment load weight, and to determine whether to correct the initial physical health value based on the degree of equipment wear. If it is determined that correction is needed, the initial physical health value is corrected based on the degree of equipment wear to obtain a final physical health value.

[0052] The cycle adjustment module is configured to obtain a comprehensive health status value of the equipment based on the electrical health value and the final physical health value, and to dynamically adjust the current maintenance cycle of the equipment based on the comprehensive health status value of the equipment to obtain the adjusted maintenance cycle.

[0053] It is understood that the preventive maintenance cycle dynamic adjustment method and system based on working condition self-learning provided in this application have the same beneficial effects, and will not be elaborated here. Attached Figure Description

[0054] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0055] Figure 1 A flowchart illustrating the method for dynamically adjusting preventive maintenance cycles based on working condition self-learning provided in an embodiment of the present invention;

[0056] Figure 2 This is a functional block diagram of a preventive maintenance cycle dynamic adjustment system based on working condition self-learning provided in an embodiment of the present invention. Detailed Implementation

[0057] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0058] In some embodiments of this application, see Figure 1 As shown, this embodiment provides a method for dynamically adjusting preventive maintenance cycles based on operating condition self-learning, including the following steps:

[0059] S100, electrical and physical parameters of the acquisition device; wherein, the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, equipment load weight and equipment wear degree;

[0060] S200. Analyze the fluctuation of the spindle current and the change of the power factor, determine the electrical health status of the equipment based on the fluctuation and change, and obtain the electrical health value.

[0061] S300. Obtain an initial physical health value based on the vibration signal and the equipment load weight, and determine whether to correct the initial physical health value based on the degree of equipment wear. If it is determined that correction is needed, correct the initial physical health value based on the degree of equipment wear to obtain a final physical health value.

[0062] S400. Obtain the comprehensive health status value of the equipment based on the electrical health value and the final physical health value. Dynamically adjust the current maintenance cycle of the equipment based on the comprehensive health status value of the equipment to obtain the adjusted maintenance cycle.

[0063] Understandably, this invention breaks away from the rigid pattern of traditional fixed maintenance cycles, allowing equipment maintenance schedules to better align with their actual operating and health conditions. By simultaneously collecting electrical and physical parameters, this invention constructs a multi-dimensional sensing system for equipment operating status. Spindle current and power factor reflect the load characteristics and operating efficiency of the motor and drive system, while vibration signals, load weight, and wear levels reveal the actual health level of the mechanical structure and processing. Through the fusion calculation of electrical and physical health values, a quantitative comprehensive health status value can be obtained, which can be used to dynamically adjust maintenance cycles, enabling flexible strategies for early warning or delayed maintenance. This dynamism not only extends the equipment's trouble-free operating time and reduces maintenance costs but also improves the stability of production plans by avoiding sudden failures. Furthermore, as the self-learning model continuously accumulates historical data, the accuracy of the algorithm's judgments will continuously improve, forming an adaptive and evolvable intelligent maintenance system. This greatly enhances the scientific and advanced nature of equipment management, ultimately achieving the comprehensive goals of cost reduction, efficiency improvement, increased production capacity, and equipment utilization.

[0064] In some embodiments of this application, the analysis of spindle current fluctuations and power factor changes, and the determination of the electrical health status of the equipment based on the fluctuations and changes, includes:

[0065] A data acquisition period is preset, and several data acquisition points are set within the data acquisition period. The main shaft current of each data acquisition point is acquired, and the current fluctuation value of the main shaft current of adjacent data acquisition points is calculated to form a set of fluctuation conditions.

[0066] The power factor of each sampling point is collected to construct a power factor set; and the factor fluctuation value of the power factor of adjacent sampling points is calculated to form a set of changes.

[0067] The electrical health status of the equipment is determined based on the set of fluctuations in the spindle current, the set of power factors, and the set of changes.

[0068] In some embodiments of this application, determining the electrical health status of the equipment based on the set of fluctuation conditions, the set of power factors, and the set of changes includes:

[0069] Calculate the average values ​​of the fluctuation set, the power factor set, and the change set respectively to obtain the average value of current fluctuation, the average value of power factor, and the average value of power factor change;

[0070] Pre-set the maximum current fluctuation and the minimum power factor;

[0071] If the average current fluctuation is less than the maximum current fluctuation and the average power factor is greater than the minimum power factor, the electrical health of the equipment is preliminarily judged to be good; if the average current fluctuation is greater than or equal to the maximum current fluctuation and the average power factor is greater than the minimum power factor, the electrical health of the equipment is preliminarily judged to be medium; if the average current fluctuation is less than the maximum current fluctuation and the average power factor is less than or equal to the minimum power factor, the electrical health of the equipment is preliminarily judged to be medium; if the average current fluctuation is greater than or equal to the maximum current fluctuation and the average power factor is less than or equal to the minimum power factor, the electrical health of the equipment is preliminarily judged to be poor; wherein, the electrical health of the equipment, from high to low, is good, medium, and poor.

[0072] Based on the average value of the power factor change, determine whether adjustments are needed to the initially assessed electrical health status of the equipment.

[0073] In some embodiments of this application, the step of determining whether to adjust the initially assessed electrical health status of the equipment based on the average power factor change includes:

[0074] If the average power factor change is zero, it is determined that no adjustments will be made to the preliminary assessment of the equipment's electrical health status.

[0075] If the average value of the power factor change is not zero, it is determined that the electrical health status of the equipment needs to be adjusted based on the preliminary assessment.

[0076] If the average value of the power factor change is greater than zero, the electrical health status of the equipment will be upgraded by one level; if the electrical health status of the equipment is good, it will remain unchanged.

[0077] If the average power factor change is less than zero, the preliminary assessment of the equipment's electrical health status will be downgraded by one level; if the preliminary assessment of the equipment's electrical health status is poor, it will remain unchanged.

[0078] In some embodiments of this application, obtaining the electrical health value includes:

[0079] When the adjusted electrical health status of the equipment is poor, the electrical health value is the first health value;

[0080] When the adjusted electrical health status of the equipment is medium, the electrical health value is the second health value;

[0081] When the adjusted electrical health status of the equipment is good, the electrical health value is the third health value;

[0082] Among them, the first health value < the second health value < the third health value.

[0083] Understandably, this invention achieves a refined assessment of the electrical health status of equipment by introducing a dual-indicator method combining spindle current fluctuation analysis and power factor change analysis. Specifically, within a preset acquisition period, this invention uses multiple acquisition points to obtain spindle current and power factor data, forming sets of current fluctuation and power factor change data respectively, and calculates their average values ​​to determine the equipment's operational stability and energy efficiency. Spindle current fluctuation reflects load changes and the stability of the motor drive system; the smaller the fluctuation, the more stable the mechanical load and control state. The power factor measures energy utilization efficiency; a high power factor means the equipment is operating within a superior electrical performance range. By setting the maximum current fluctuation value and the minimum power factor value as thresholds, the equipment status can be divided into three levels: good, medium, and poor, achieving rapid quantification of operating conditions.

[0084] Furthermore, by introducing the average power factor change as a dynamic adjustment factor, the initial judgment results can be adjusted upwards or downwards, avoiding misjudgments caused by short-term fluctuations or special operating conditions, thereby enhancing the accuracy and flexibility of health assessment. Finally, different levels of electrical health status are mapped to quantitative electrical health values, which can directly participate in the calculation of the overall equipment health status, providing a reliable basis for subsequent dynamic adjustments to maintenance cycles. This invention can reflect the operational health of the equipment's electrical system in real time, objectively, and quantitatively, identify potential anomalies in advance, avoid sudden downtime caused by electrical faults, and extend maintenance cycles when equipment is in good condition, reducing unnecessary repairs and downtime, and improving production efficiency and equipment utilization.

[0085] In some embodiments of this application, obtaining the initial physical health value based on the vibration signal and the equipment load weight includes:

[0086] Acquire equipment vibration signals and equipment load weight within a preset time period, and calculate the average equipment vibration and average load.

[0087] Collect the allowable vibration value and rated load of the equipment, calculate the vibration ratio of the average vibration value to the allowable vibration value, and the load ratio of the average load to the rated load, and obtain the initial physical health value based on the vibration ratio and load ratio.

[0088] Specifically, if both the vibration ratio and the load ratio are greater than 1, the initial physical health value is the first initial value; if either the vibration ratio or the load ratio is greater than 1, the initial physical health value is the second initial value; and if both the vibration ratio and the load ratio are less than 1, the initial physical health value is the third initial value.

[0089] In the initial values ​​of physical health, the first initial value < the second initial value < the third initial value.

[0090] In some embodiments of this application, determining whether to correct the initial physical health value based on the degree of device wear includes:

[0091] Obtain the wear area of ​​the equipment, calculate the ratio of the wear area to the equipment surface area, and record it as the degree of equipment wear;

[0092] If the wear level is greater than a preset wear threshold, it is determined that the initial physical health value should be corrected; otherwise, it is determined that the initial physical health value should not be corrected.

[0093] In some embodiments of this application, when correcting the initial physical health value based on the degree of equipment wear to obtain the final physical health value, the following steps are included:

[0094] The final physical health value is the product of the initial physical health value and the correction coefficient.

[0095] The degree of equipment wear is inversely proportional to the correction coefficient, which ranges from 0 to 1.

[0096] Understandably, this invention, by combining equipment vibration signals, load weight, and wear degree, can more comprehensively and realistically reflect the mechanical condition of the equipment. Specifically, it first collects the equipment's vibration signals and load weight within a preset time period and calculates their average values ​​to avoid interference from instantaneous fluctuations in the judgment results. Subsequently, the vibration average value is compared with the allowable vibration value, and the load average value is compared with the rated load weight, respectively, to obtain the vibration ratio and load ratio. These two ratios correspond to the relative health level of the equipment's structural stability and load-bearing condition, respectively. By comparing whether the ratio is greater than 1, it is possible to quickly determine whether the equipment is operating beyond its limits, and the results are divided into three initial physical health values, achieving preliminary quantification from excellent to poor.

[0097] Furthermore, introducing wear degree as a correction factor can compensate for the shortcomings of simple vibration and load analysis, because equipment may still have potential wear hazards due to long-term use even under normal vibration and load conditions. The wear degree is calculated by the proportion of wear area and is inversely proportional to the correction coefficient. When the wear degree exceeds the threshold, the initial value will be adjusted down proportionally to obtain a final physical health value that is closer to reality. Therefore, this method can not only reflect the immediate operating load and structural stability, but also correct the results by combining long-term deterioration trends, improving the accuracy and predictive ability of health assessment. This invention can effectively identify potential fatigue and aging risks of mechanical components, avoiding sudden downtime caused by decreased mechanical performance; when the equipment is in good condition, it can extend the maintenance cycle, reduce unnecessary downtime and maintenance, thereby reducing maintenance costs, improving production continuity and equipment utilization.

[0098] In some embodiments of this application, the step of obtaining a comprehensive equipment health status value based on the electrical health value and the final physical health value, and then dynamically adjusting the current maintenance cycle of the equipment based on the comprehensive equipment health status value to obtain the adjusted maintenance cycle includes:

[0099] The overall health status value of the equipment is the weighted sum of the electrical health value and the final physical health value.

[0100] Set a sum range; if the overall health status value of the device is greater than the maximum value of the sum range, then adjust the current maintenance cycle of the device using a first adjustment coefficient.

[0101] If the overall health status value of the equipment is within the sum range, the current maintenance cycle of the equipment is adjusted by the second adjustment coefficient;

[0102] If the overall health status value of the equipment is less than the minimum value of the sum range, the current maintenance cycle of the equipment will be adjusted by a third adjustment coefficient.

[0103] The adjustment coefficient ranges from 1 to 3, and the adjusted maintenance cycle is the product of the current maintenance cycle of the equipment and the adjustment coefficient.

[0104] Understandably, this invention achieves a unified quantification of health assessment results across both electrical and mechanical dimensions by weighted summation of electrical and physical health values ​​to form a comprehensive health status value for the equipment. This provides a scientific basis for dynamic adjustment of maintenance cycles. The weighted summation method can flexibly set weights based on the relative importance of electrical and physical factors during actual operation, ensuring that the comprehensive result more closely reflects the actual operating state of the equipment. Subsequently, by setting a range for the sum of the comprehensive health status value, the equipment status is divided into three typical scenarios: high health status (greater than the maximum value in the range), normal health status (within the range), and low health status (less than the minimum value in the range). This invention introduces different maintenance cycle adjustment coefficients for different health states, and the coefficient values ​​follow the principle of first adjustment coefficient > 1 > second adjustment coefficient > third adjustment coefficient. That is, when the health state is higher than normal, the maintenance cycle can be appropriately extended (multiplied by a coefficient greater than 1) to reduce unnecessary maintenance; when the health state is normal, the cycle remains relatively stable (coefficient close to 1); when the health state is lower than normal, the maintenance cycle is significantly shortened (coefficient less than 1) to reduce the risk of failure. This allows for a dynamic balance between equipment availability and maintenance costs, enabling a flexible strategy of proactive preventative maintenance and delayed non-essential maintenance. This invention not only improves the scientific and real-time nature of maintenance decisions but also significantly reduces production interruptions caused by improper maintenance. In long-term operation, the weights and interval thresholds can be continuously optimized based on historical data, allowing the adjustment model to continuously adapt, ultimately maximizing equipment lifespan, minimizing downtime losses, and achieving optimal allocation of maintenance resources.

[0105] On the other hand, see Figure 2 As shown, this application also provides a preventive maintenance cycle dynamic adjustment system based on operating condition self-learning, used to apply the above-mentioned preventive maintenance cycle dynamic adjustment method based on operating condition self-learning, including:

[0106] The acquisition module is configured to acquire electrical and physical parameters of the device; wherein the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, device load weight, and device wear degree;

[0107] The analysis module is configured to analyze the fluctuations in spindle current and the changes in power factor, determine the electrical health status of the equipment based on the fluctuations and changes, and obtain an electrical health value.

[0108] The analysis module is also configured to obtain an initial physical health value based on the vibration signal and the equipment load weight, and to determine whether to correct the initial physical health value based on the degree of equipment wear. If it is determined that correction is needed, the initial physical health value is corrected based on the degree of equipment wear to obtain a final physical health value.

[0109] The cycle adjustment module is configured to obtain a comprehensive health status value of the equipment based on the electrical health value and the final physical health value, and to dynamically adjust the current maintenance cycle of the equipment based on the comprehensive health status value of the equipment to obtain the adjusted maintenance cycle.

[0110] Understandably, this invention achieves comprehensive perception and intelligent decision-making regarding the operational health status of equipment through the organic collaboration of a data acquisition module, an analysis module, and a periodic adjustment module. The data acquisition module can acquire electrical parameters (spindle current, power factor) and physical parameters (vibration signal, equipment load weight, equipment wear level) in real time, constructing a multi-dimensional data foundation covering electrical drive performance and mechanical structure condition, ensuring sufficient data support for subsequent analysis. The analysis module processes the electrical and physical parameters separately: the electrical part assesses the stability and efficiency of the drive system through spindle current fluctuations and power factor changes, outputting electrical health values; the physical part calculates initial physical health values ​​based on vibration and load, and corrects for wear level, making the final physical health value more closely reflect the actual condition of the equipment. The periodic adjustment module integrates the electrical health value and the final physical health value to form a comprehensive health status value, and dynamically extends, maintains, or shortens the maintenance cycle based on set interval thresholds and adjustment coefficients. Therefore, the system can intelligently adjust the maintenance plan according to the equipment's health status, avoiding resource waste caused by "over-maintenance," and can also detect potential fault risks in advance, reducing the probability of sudden downtime. In summary, this invention achieves precise and dynamic equipment maintenance strategies; significantly improves equipment utilization and production capacity stability; reduces maintenance costs and spare parts consumption; and as the system continuously learns historical operating data, the accuracy of analysis and adjustment will continuously improve, forming a self-optimizing intelligent operation and maintenance closed loop, comprehensively supporting the efficient and safe operation of advanced manufacturing and automated production.

[0111] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0113] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for dynamically adjusting preventive maintenance cycles based on operating condition self-learning, characterized in that, include: The electrical and physical parameters of the acquisition equipment are collected; wherein the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, equipment load weight, and equipment wear degree. Analyze the fluctuations in spindle current and the changes in power factor, determine the electrical health status of the equipment based on the fluctuations and changes, and obtain the electrical health value; An initial physical health value is obtained based on the vibration signal and the equipment load weight. It is then determined whether the initial physical health value needs to be corrected based on the degree of equipment wear. If it is determined that correction is needed, the initial physical health value is corrected based on the degree of equipment wear to obtain a final physical health value. Based on the electrical health value and the final physical health value, the overall health status value of the equipment is obtained. Based on the overall health status value of the equipment, the current maintenance cycle of the equipment is dynamically adjusted to obtain the adjusted maintenance cycle. The analysis of spindle current fluctuations and power factor changes, and the determination of the electrical health status of the equipment based on these fluctuations and changes, includes: pre-setting a sampling period; setting several sampling points within the sampling period; sampling the spindle current at each sampling point; calculating the current fluctuation values ​​of the spindle current at adjacent sampling points to form a set of fluctuation conditions; sampling the power factor at each sampling point to construct a set of power factors; and calculating the power factor fluctuation values ​​at adjacent sampling points to form a set of changes. The electrical health status of the equipment is determined based on the set of fluctuations, power factors, and changes in the spindle current: The average values ​​of these sets are calculated to obtain the average current fluctuation, average power factor, and average power factor change. A maximum current fluctuation value and a minimum power factor value are preset. If the average current fluctuation value is less than the maximum current fluctuation value, and the average power factor value is greater than the minimum power factor value, the equipment's electrical health status is preliminarily judged as good. If the average current fluctuation value is greater than or equal to the maximum current fluctuation value, and the average power factor value is greater than the minimum power factor value, the equipment's electrical health status is preliminarily judged as medium. If the average current fluctuation value is less than the maximum current fluctuation value, and the average power factor value is less than or equal to the minimum power factor value, the equipment's electrical health status is preliminarily judged as medium. If the average current fluctuation value is greater than or equal to the maximum current fluctuation value, and the average power factor value is less than or equal to the minimum power factor value, the equipment's electrical health status is preliminarily judged as poor. The equipment's electrical health status is ranked from highest to lowest as good, medium, and poor. The determination of whether to adjust the preliminary assessment of the equipment's electrical health status is based on the average power factor change: if the average power factor change is zero, it is determined that no adjustment is needed; if the average power factor change is not zero, it is determined that adjustment is needed; specifically, if the average power factor change is greater than zero, it is determined that the preliminary assessment of the equipment's electrical health status will be upgraded by one level; if the preliminary assessment of the equipment's electrical health status is good, it will remain unchanged; if the average power factor change is less than zero, it is determined that the preliminary assessment of the equipment's electrical health status will be downgraded by one level; if the preliminary assessment of the equipment's electrical health status is poor, it will remain unchanged.

2. The method for dynamic adjustment of preventive maintenance cycles based on operating condition self-learning according to claim 1, characterized in that, When obtaining the electrical health value, the following are included: When the adjusted electrical health status of the equipment is poor, the electrical health value is the first health value; When the adjusted electrical health status of the equipment is medium, the electrical health value is the second health value; When the adjusted electrical health status of the equipment is good, the electrical health value is the third health value; Among them, the first health value < the second health value < the third health value.

3. The method for dynamic adjustment of preventive maintenance cycles based on operating condition self-learning according to claim 1, characterized in that, When obtaining the initial physical health value based on the vibration signal and the equipment load weight, the process includes: Acquire equipment vibration signals and equipment load weight within a preset time period, and calculate the average equipment vibration and average load. Collect the allowable vibration value and rated load of the equipment, calculate the vibration ratio of the average vibration value to the allowable vibration value, and the load ratio of the average load to the rated load, and obtain the initial physical health value based on the vibration ratio and load ratio. Specifically, if both the vibration ratio and the load ratio are greater than 1, the initial physical health value is the first initial value; if either the vibration ratio or the load ratio is greater than 1, the initial physical health value is the second initial value; and if both the vibration ratio and the load ratio are less than 1, the initial physical health value is the third initial value. In the initial values ​​of physical health, the first initial value < the second initial value < the third initial value.

4. The method for dynamic adjustment of preventive maintenance cycles based on operating condition self-learning according to claim 3, characterized in that, When determining whether to correct the initial physical health value based on the degree of equipment wear, the following steps are included: Obtain the wear area of ​​the equipment, calculate the ratio of the wear area to the equipment surface area, and record it as the degree of equipment wear; If the wear level is greater than a preset wear threshold, it is determined that the initial physical health value should be corrected; otherwise, it is determined that the initial physical health value should not be corrected.

5. The method for dynamic adjustment of preventive maintenance cycles based on operating condition self-learning according to claim 4, characterized in that, When correcting the initial physical health value based on the degree of equipment wear to obtain the final physical health value, the following steps are included: The final physical health value is the product of the initial physical health value and the correction coefficient. The degree of equipment wear is inversely proportional to the correction coefficient, which ranges from 0 to 1.

6. The method for dynamic adjustment of preventive maintenance cycles based on operating condition self-learning according to claim 1, characterized in that, The process of obtaining a comprehensive equipment health status value based on the electrical health value and the final physical health value, and then dynamically adjusting the current maintenance cycle of the equipment based on the comprehensive equipment health status value to obtain the adjusted maintenance cycle includes: The overall health status value of the equipment is the weighted sum of the electrical health value and the final physical health value. Set a sum range; if the overall health status value of the device is greater than the maximum value of the sum range, then adjust the current maintenance cycle of the device using a first adjustment coefficient. If the overall health status value of the equipment is within the sum range, the current maintenance cycle of the equipment is adjusted by the second adjustment coefficient; If the overall health status value of the equipment is less than the minimum value of the sum range, the current maintenance cycle of the equipment will be adjusted by a third adjustment coefficient. The adjustment coefficient ranges from 1 to 3, and the adjusted maintenance cycle is the product of the current maintenance cycle of the equipment and the adjustment coefficient.

7. A preventive maintenance cycle dynamic adjustment system based on operating condition self-learning, used to apply the preventive maintenance cycle dynamic adjustment method based on operating condition self-learning as described in any one of claims 1-6, characterized in that, include: The acquisition module is configured to acquire electrical and physical parameters of the device; wherein the electrical parameters include spindle current and power factor, and the physical parameters include vibration signal, device load weight, and device wear degree; The analysis module is configured to analyze the fluctuations in spindle current and the changes in power factor, determine the electrical health status of the equipment based on the fluctuations and changes, and obtain an electrical health value. The analysis module is also configured to obtain an initial physical health value based on the vibration signal and the equipment load weight, and to determine whether to correct the initial physical health value based on the degree of equipment wear. If it is determined that correction is needed, the initial physical health value is corrected based on the degree of equipment wear to obtain a final physical health value. The cycle adjustment module is configured to obtain a comprehensive health status value of the equipment based on the electrical health value and the final physical health value, and to dynamically adjust the current maintenance cycle of the equipment based on the comprehensive health status value of the equipment to obtain the adjusted maintenance cycle.

Images