A method for optimizing equipment maintenance personnel allocation based on multi-factor dynamic coupling

Abstract

This invention relates to the field of computer technology and discloses a method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling. The method includes acquiring status characteristic information such as equipment age, technical complexity, and average daily utilization time; determining corresponding influence coefficients; calculating the maintenance requirements for a single unit based on baseline maintenance workload; and summarizing the total maintenance requirements for the equipment group. Further, correction factors such as personnel capability equivalent coefficient, cross-site collaboration coefficient, on-duty availability coefficient, and resource balance coefficient are determined. The total maintenance requirements are then corrected item by item in the order of capability conversion, collaboration adjustment, on-duty correction, and resource balance compensation, outputting the required number of maintenance engineers. This invention enables refined and optimized equipment maintenance personnel configuration, improves the accuracy and adaptability of personnel allocation, and reduces operation and maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a method for optimizing the configuration of equipment maintenance personnel based on multi-factor dynamic coupling. Background Technology

[0002] Currently, in terms of staffing for the maintenance of large and complex equipment, the industry generally adopts the fixed man-machine ratio method, historical working hours statistics method, or fixed post and staffing method to determine the number of maintenance engineers required.

[0003] The fixed man-machine ratio method sets a fixed number of personnel for each piece of equipment based on experience, ignoring individual differences in equipment usage years, technical complexity, average daily utilization time, etc.

[0004] Historical working hours statistics are based on the total maintenance working hours of previous years to estimate personnel demand, but they cannot reflect dynamic factors such as equipment aging, the introduction of new equipment, and changes in operational intensity.

[0005] The fixed-position and fixed-staffing method determines the number of positions based on organizational structure and management experience, but lacks quantitative basis for actual maintenance needs.

[0006] Existing technologies cannot distinguish the differences in maintenance needs between equipment with different service lives, technical complexity, and utilization rates; they treat maintenance engineers as homogeneous labor, failing to consider the differences in work efficiency among personnel with different technical levels; when equipment is distributed across multiple geographically different bases, it is impossible to quantitatively calculate the manpower savings brought about by cross-base technical support and resource sharing; the interrelationships between multiple factors such as equipment aging, utilization rate, and personnel capabilities are not incorporated into a unified calculation framework, resulting in significant deviations between configuration schemes and actual conditions.

[0007] Therefore, this application provides a method for optimizing the configuration of equipment maintenance personnel based on multi-factor dynamic coupling to solve the above-mentioned technical problems. Summary of the Invention

[0008] The purpose of this invention is to provide a method for optimizing the allocation of equipment maintenance personnel based on dynamic coupling of multiple factors, in order to solve the technical problems in the prior art where the allocation of equipment maintenance personnel depends on a fixed ratio, ignores individual differences in equipment, fails to quantify differences in personnel capabilities, lacks quantitative calculation of multi-site synergistic effects, and results in inaccurate allocation schemes and a lack of dynamic adaptability due to the separation between various influencing factors.

[0009] To address the aforementioned technical problems, this invention provides a method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling, comprising:

[0010] Obtain the status characteristic information of each device, wherein the dimensions of the status characteristic information include the degree of age, technical complexity, and average daily utilization time;

[0011] Based on the aforementioned status characteristic information, an impact coefficient for age, an impact coefficient for technical complexity, and an impact coefficient for utilization rate are determined for each device. The utilization rate impact coefficient is determined according to the average daily utilization time and a preset mapping relationship between the average daily utilization time interval and the impact coefficient. When the average daily utilization time exceeds a benchmark value, the utilization rate impact coefficient exhibits a non-linear relationship with the average daily utilization time.

[0012] Based on the baseline maintenance workload of each piece of equipment and the corresponding impact coefficients of age, technical complexity, and utilization rate, the maintenance requirements of each piece of equipment are determined, and the total maintenance requirements of the equipment group are obtained by combining the maintenance requirements of all equipment.

[0013] A plurality of correction factors are determined for sequentially adjusting the total maintenance requirements, wherein the correction factors include personnel capability equivalent coefficient, cross-site coordination coefficient, on-duty availability coefficient, and resource balance coefficient;

[0014] The total maintenance requirements are adjusted item by item based on the correction factor, and the required number of maintenance engineers is output.

[0015] In some specific embodiments, determining the impact coefficient of aging degree further includes:

[0016] Obtain the service life information for each device;

[0017] Based on the service life information, and according to the preset mapping relationship between service life range and score, the age rating of each device is determined;

[0018] According to the preset piecewise linear mapping function between the score and the influence coefficient, the oldness score is converted into the oldness influence coefficient. The piecewise linear mapping function defines the maximum influence coefficient corresponding to the lowest score, the benchmark influence coefficient corresponding to the benchmark score, and the minimum influence coefficient corresponding to the highest score.

[0019] The average of the influence coefficients of the aging degree of all equipment is statistically analyzed to obtain the weighted average of the influence coefficients of the aging degree.

[0020] In some specific embodiments, determining the technical complexity impact coefficient further includes:

[0021] Obtain the technical architecture type information for each device;

[0022] Based on the technical architecture type information, and according to the preset mapping relationship between technical architecture type and maintenance difficulty benchmark score, the technical complexity score of each device is determined;

[0023] Based on the preset mapping relationship between technical complexity score and influence coefficient, the technical complexity score is converted into the technical complexity influence coefficient;

[0024] The average of the technical complexity influence coefficients of all devices is statistically analyzed to obtain a weighted average of the technical complexity influence coefficients.

[0025] In some specific embodiments, determining the utilization impact coefficient further includes:

[0026] Obtain the average daily usage time information for each device;

[0027] Based on the average daily utilization time information, and according to the preset mapping relationship between the average daily utilization time interval and the influence coefficient, the utilization rate influence coefficient of each device is determined. When the average daily utilization time exceeds the benchmark value, the utilization rate influence coefficient and the average daily utilization time have a non-linear relationship.

[0028] The average utilization rate impact coefficient of all equipment is statistically analyzed to obtain a weighted average value of the utilization rate impact coefficient.

[0029] In some specific embodiments, determining the personnel capability equivalent coefficient further includes:

[0030] Obtain the technical skill level information of each engineer in the maintenance team;

[0031] Based on the preset mapping relationship between levels and ability weights, a corresponding ability weight value is assigned to each engineer;

[0032] Calculate the weighted average of the ability weights of all engineers in the team to obtain the team's weighted average ability value;

[0033] The personnel capability equivalent coefficient is determined based on the correspondence between the team's weighted average capability value and the capability weight value of the benchmark engineer.

[0034] In some specific embodiments, determining the cross-site synergy coefficient further includes:

[0035] Obtain information on the number of bases where the equipment is distributed;

[0036] Based on the synergy effect model including the maximum saving ratio parameter and the saturation base number parameter, the basic synergy coefficient is calculated, wherein when the number of bases is one, the basic synergy coefficient is one, and when the number of bases increases, the basic synergy coefficient gradually decreases until it reaches the lower limit value determined by the maximum saving ratio parameter.

[0037] Obtain geographical distance information between bases and information on the homogeneity of equipment models at each base, and generate distance penalty factor and homogeneity factor respectively;

[0038] The cross-site coordination coefficient is obtained by combining the basic coordination coefficient, the distance penalty factor, and the homogenization factor.

[0039] In some specific embodiments, the total maintenance requirement is adjusted item by item based on the correction factor to output the required number of maintenance engineers, further including:

[0040] Obtain the total number of calendar days in the year, the total number of statutory paid holidays in the year, the average number of training days in the year, the average number of sick days in the year, and the number of other unavailable days in the year. Determine the number of available days in the year based on the difference between the total number of calendar days in the year and each of the other numbers of days. Obtain the on-the-job availability coefficient based on the ratio between the number of available days in the year and the total number of calendar days in the year.

[0041] The resource balance coefficient is determined based on at least one of the following factors: shift work pattern, skill level matching, operating time difference, and management redundancy.

[0042] Following the order of capacity conversion, coordination adjustment, on-the-job correction, and resource balancing compensation, the total maintenance requirements are sequentially correlated with the personnel capacity equivalent coefficient, the cross-base coordination coefficient, the on-the-job availability coefficient, and the resource balancing coefficient.

[0043] The result of the correlation operation is quantized and rounded to obtain the required number of maintenance engineers.

[0044] In some specific embodiments, a dynamic update step is also included:

[0045] Monitor changes in the state characteristic information;

[0046] Monitor changes in the underlying data used to determine the plurality of correction factors;

[0047] When the status feature information or the basic data changes, the operations of acquiring status feature information, determining each influence coefficient, determining total maintenance requirements, determining multiple correction factors, and correcting each item and outputting the required number of maintenance engineers are re-executed.

[0048] The required number of maintenance engineers will be updated based on the results of the re-execution.

[0049] In some specific embodiments, a parameter calibration step is also included:

[0050] Obtain actual maintenance man-hour data within the historical period;

[0051] Obtain the state characteristic information within the historical period and the basic data used to determine the multiple correction factors, and determine the theoretical maintenance requirements within the historical period;

[0052] The actual maintenance hours are compared with the theoretical maintenance requirements;

[0053] Adjust the baseline maintenance workload based on the comparison results, and adjust the parameters in the mapping relationship on which each influence coefficient depends.

[0054] Repeat the adjustment until the deviation between the theoretical maintenance requirements and the actual maintenance hours meets the preset conditions.

[0055] In some specific embodiments, a configuration scheme generation step is also included:

[0056] The number of work teams will be determined based on the required number of maintenance engineers.

[0057] Based on the existing technical skill level distribution of the maintenance team, determine the ratio of engineers of each technical skill level within each shift.

[0058] Determine the number of people in each work group and the independent allocation of special positions;

[0059] The output includes a configuration scheme with suggestions on job positions, work group assignments, and hierarchical structure.

[0060] Compared with existing technologies, its advantages are as follows:

[0061] This invention discloses a method for optimizing the allocation of equipment maintenance personnel based on multi-factor dynamic coupling. It establishes an equivalent workload model with multi-dimensional product coupling, and incorporates three influencing factors—equipment age, technical complexity, and daily utilization rate—into a unified calculation framework in a product manner. This accurately reflects the mutual reinforcement effect between the factors and realizes the differentiated quantification of maintenance needs for a single piece of equipment.

[0062] Construct a personnel capability equivalent assessment system, and through the mapping of technical level to capability weight and the calculation of team capability coefficient, quantitatively incorporate personnel capability differences into configuration optimization, so as to accurately match personnel configuration with the actual capabilities of the team.

[0063] A cross-site synergy coefficient model with saturation characteristics is proposed, and a distance penalty factor and a technology homogenization factor are introduced for correction, so as to realize the quantitative calculation of the multi-site human resource sharing effect.

[0064] It enables dynamic and interconnected calculation of all elements, automatically triggering reconfiguration when any parameter such as equipment status, personnel changes, or operation plan changes, eliminating the subjective bias of fragmented evaluation of various factors in traditional methods.

[0065] It has the ability to predict trends based on equipment aging curves and operational plans, and can provide early warnings of personnel demand in future cycles, supporting forward-looking recruitment and training plans.

[0066] A parameter self-calibration mechanism based on historical data is set up to optimize model parameters by comparing actual maintenance hours with theoretical requirements, ensuring that the model remains accurate and has adaptive capabilities. Attached Figure Description

[0067] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0068] Figure 1 This is a flowchart illustrating some specific embodiments of the equipment maintenance personnel configuration optimization method based on multi-factor dynamic coupling of the present invention. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0070] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0071] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0072] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0073] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0074] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0075] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0076] Reference Figure 1 A method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling includes:

[0077] S101, Obtain the status characteristic information of each device, wherein the dimensions of the status characteristic information include the degree of obsolescence, technical complexity, and average daily utilization time;

[0078] S102, based on the status feature information, determine the aging degree influence coefficient, technical complexity influence coefficient and utilization rate influence coefficient for each device respectively. The utilization rate influence coefficient is determined according to the average daily utilization time and the preset mapping relationship between the average daily utilization time interval and the influence coefficient. When the average daily utilization time exceeds the benchmark value, the utilization rate influence coefficient and the average daily utilization time have a non-linear relationship.

[0079] S103. Based on the baseline maintenance workload of each piece of equipment and the corresponding impact coefficients of aging degree, technical complexity and utilization rate, determine the maintenance requirements of each piece of equipment, and combine the maintenance requirements of all equipment to obtain the total maintenance requirements of the equipment group.

[0080] S104, determine a plurality of correction factors for sequentially correcting the total maintenance requirements, wherein the correction factors include personnel capability equivalent coefficient, cross-site coordination coefficient, on-duty availability coefficient and resource balance coefficient;

[0081] S105, Based on the correction factor, the total maintenance requirements are corrected item by item, and the required number of maintenance engineers is output.

[0082] Specifically, in this embodiment of the invention, for each device in the device group, its status characteristic information is acquired in three dimensions: age, technical complexity, and average daily utilization time. The age dimension is determined based on the device's years of use, the technical complexity dimension is determined based on the device's technical architecture type and maintenance difficulty level, and the average daily utilization time dimension is determined based on the device's average daily operating time. Then, based on the years of use of each device, an age score is determined according to a preset age score scoring rule. This score is then converted into a corresponding age influence coefficient using a preset piecewise linear mapping function between the score and the influence coefficient. In this piecewise linear mapping function, the lowest score corresponds to the largest influence coefficient, the benchmark score corresponds to the benchmark influence coefficient, and the highest score corresponds to the smallest influence coefficient. Similarly, based on the technical architecture type of each device, a technical complexity score is determined according to a preset technical complexity scoring rule, and then converted into a technical complexity influence coefficient using the mapping relationship between the score and the influence coefficient. For the average daily utilization time dimension, the utilization rate influence coefficient is determined based on the average daily utilization time of each device, according to the preset mapping relationship between the utilization time interval and the influence coefficient. When the average daily utilization time exceeds the benchmark value, the relationship between the utilization rate influence coefficient and the utilization time becomes non-linear; that is, as the utilization time increases further, the increase in the utilization rate influence coefficient gradually increases, reflecting the accelerated amplification effect of high utilization on maintenance demand. After obtaining the three influence coefficients for each device, the preset benchmark maintenance workload is coupled with the three influence coefficients of that device through a product operation to obtain the equivalent maintenance workload of that device. The equivalent maintenance workloads of all devices are then summed to obtain the total equivalent maintenance workload of the device group. The aforementioned benchmark maintenance workload is defined as the standard equivalent number of full-time engineers required for a single standard device under standard conditions (medium equipment age, medium complexity, standard utilization time). Several correction factors are determined for sequentially correcting the total equivalent maintenance workload, including the personnel capability equivalent coefficient, cross-site collaboration coefficient, on-the-job availability coefficient, and resource balance coefficient. The personnel capability equivalent coefficient is generated as follows: the technical level of each engineer in the maintenance team is obtained, a capability weight value is assigned to each engineer according to the preset mapping relationship between level and capability weight, the weighted average of the capability weight values ​​of all engineers is calculated to obtain the team's weighted average capability value, and then the personnel capability equivalent coefficient is determined according to the correspondence between the weighted average value and the baseline engineer capability weight value. This coefficient is used to convert the team's actual capability into standard capability.The cross-base synergy coefficient is generated as follows: The number of bases where the equipment is distributed is obtained. A basic synergy coefficient is calculated based on a synergy effect model that includes a maximum saving ratio parameter and a saturation base number parameter. When the number of bases is one, the basic synergy coefficient is one. As the number of bases increases, the basic synergy coefficient gradually decreases until it reaches the lower limit determined by the maximum saving ratio parameter. Then, geographical distance information between bases and the homogeneity information of equipment models at each base are obtained, generating distance penalty factors and homogeneity factors respectively. Finally, the basic synergy coefficient, distance penalty factor, and homogeneity factor are combined to obtain the cross-base synergy coefficient. This coefficient is used to quantify the manpower saving effect brought about by resource sharing among multiple bases. The on-the-job availability coefficient is generated as follows: The total number of calendar days in the year, as well as the annual statutory paid holidays, average training, average sick leave, and other unavailable days, are obtained. The annual available days are determined based on the difference between the total number of calendar days in the year and the above-mentioned days. The on-the-job availability coefficient is then obtained based on the ratio of the annual available days to the total number of calendar days in the year. This coefficient reflects the actual available working hours ratio at the individual level. The resource balance coefficient is determined based on at least one of the following factors: shift work patterns, skill level matching, operational time differences, and management redundancy. It is used to compensate for additional personnel needs arising from actual operational constraints such as scheduling, emergency response, and skill matching. Following a pre-defined sequence of first capacity calculation, then collaborative adjustment, then on-the-job correction, and finally resource balance compensation, the total equivalent maintenance workload is sequentially correlated with the personnel capacity equivalent coefficient, cross-site collaboration coefficient, on-the-job availability coefficient, and resource balance coefficient. The results of these correlation calculations are then quantified and rounded to output the required number of maintenance engineers.

[0083] In some applications, determining the aging degree impact coefficient includes obtaining the usage years information of each device; determining the aging degree score of each device based on the usage years information and according to a preset mapping relationship between usage years intervals and scores; converting the aging degree score into the aging degree impact coefficient according to a preset piecewise linear mapping function between scores and impact coefficients, wherein the piecewise linear mapping function defines the maximum impact coefficient corresponding to the lowest score, the benchmark impact coefficient corresponding to the benchmark score, and the minimum impact coefficient corresponding to the highest score; and calculating the average of the aging degree impact coefficients of all devices to obtain a weighted average of the aging degree impact coefficients.

[0084] Understandably, for each piece of equipment in the equipment group, the service life information since its commissioning is obtained. Service life refers to the cumulative number of years the equipment has been in operation from its initial commissioning to the current time. This information can be obtained from the equipment asset management system or maintenance logs. Then, according to a pre-defined mapping relationship between service life intervals and scores, the service life of each piece of equipment is converted into a corresponding age rating. In this mapping relationship, different service life intervals correspond to different score values. For example, newer equipment with shorter service life receives a higher score, while older equipment with longer service life receives a lower score. Scores are usually represented in integer form. After obtaining the age rating for each piece of equipment, the score is further converted into an age impact coefficient through a pre-defined piecewise linear mapping function between the score and the impact coefficient. This piecewise linear mapping function defines three key points: the maximum impact coefficient corresponding to the lowest score, the benchmark impact coefficient corresponding to the benchmark score, and the minimum impact coefficient corresponding to the highest score. For scores between these key points, the corresponding impact coefficient is determined through linear interpolation. Through the above transformation, each piece of equipment obtains a coefficient value representing the amplification effect of its aging degree on maintenance workload. The influence coefficient of new equipment is less than the benchmark value, while the influence coefficient of old equipment is greater than the benchmark value. In order to obtain a coefficient reflecting the overall level of aging of the entire equipment group, the influence coefficients of aging degree of all equipment are statistically averaged, that is, the weighted average of the influence coefficients of aging degree of all equipment is calculated. This weighted average value can be directly used as the influence coefficient of aging degree of the equipment group in subsequent calculations, or as the basis for normalizing the coefficient of individual equipment.

[0085] In some applications, determining the technical complexity impact coefficient includes obtaining technical architecture type information for each device; determining a technical complexity score for each device based on the technical architecture type information and a preset mapping relationship between technical architecture type and maintenance difficulty benchmark score; converting the technical complexity score into the technical complexity impact coefficient based on a preset mapping relationship between technical complexity score and impact coefficient; and calculating the average of the technical complexity impact coefficients for all devices to obtain a weighted average of the technical complexity impact coefficients.

[0086] Understandably, for each device in the equipment group, its technical architecture type information is obtained. This information includes at least the device manufacturer, model, technology generation, system integration complexity, and the level of manufacturer technical support. This information can be obtained from the device's technical documentation or manufacturer's manual. Based on a pre-established mapping relationship between technical architecture type and maintenance difficulty benchmark scores, a technical complexity score is assigned to each device. In this mapping relationship, different technical architecture types correspond to different benchmark scores. For example, devices using mature and stable technologies with comprehensive manufacturer support receive higher scores, indicating relatively low maintenance difficulty; while devices using new technologies, with high system integration, or difficult troubleshooting receive lower scores, indicating relatively high maintenance difficulty. Scores are typically represented using integers or a finite number of levels. After obtaining the technical complexity score for each device, it is converted into a technical complexity influence coefficient through a pre-defined mapping relationship between the score and an influence coefficient. In this mapping relationship, different score ranges correspond to different influence coefficient values; higher scores (lower maintenance difficulty) correspond to smaller technical complexity influence coefficients, and lower scores (higher maintenance difficulty) correspond to larger technical complexity influence coefficients. Through the above transformation, each piece of equipment obtains a coefficient value characterizing the amplification effect of its technical complexity on maintenance workload. To obtain a coefficient reflecting the overall level of technical complexity of the entire equipment group, the technical complexity impact coefficients of all equipment are statistically averaged, i.e., a weighted average of the technical complexity impact coefficients of all equipment is calculated. This weighted average can be used to characterize the overall technical complexity level of the equipment group in subsequent calculations, or it can serve as the basis for normalizing or grouping the coefficients of individual equipment.

[0087] In some applications, determining the utilization rate impact coefficient includes obtaining the average daily utilization time information of each device; based on the average daily utilization time information, and according to a preset mapping relationship between the average daily utilization time interval and the impact coefficient, determining the utilization rate impact coefficient of each device, wherein when the average daily utilization time exceeds a benchmark value, the utilization rate impact coefficient and the average daily utilization time have a non-linear relationship; and statistically analyzing the average utilization rate impact coefficient of all devices to obtain a weighted average value of the utilization rate impact coefficient.

[0088] Understandably, for each piece of equipment in the equipment group, the average daily utilization time information of that equipment is obtained. Average daily utilization time refers to the average daily running time of the equipment within its normal operating cycle. This information can be obtained from equipment operation logs, usage records, or operating plans. Based on a pre-defined mapping relationship between average daily utilization time intervals and influence coefficients, the utilization rate influence coefficient for each piece of equipment is determined. This mapping relationship sets a baseline utilization time value. When the average daily utilization time of the equipment is lower than this baseline value, the maintenance window is relatively ample, and the utilization rate influence coefficient is less than the baseline value. When the average daily utilization time of the equipment is close to the baseline value, the utilization rate influence coefficient takes the baseline value. When the average daily utilization time of the equipment exceeds the baseline value, the utilization rate influence coefficient is greater than the baseline value, and as the average daily utilization time further increases, the increase in the utilization rate influence coefficient gradually increases, meaning that the utilization rate influence coefficient and average daily utilization time exhibit a non-linear relationship. The design basis for this non-linear relationship is that as utilization time increases, the time window available for preventative maintenance and fault repair is compressed more rapidly. Simultaneously, continuous equipment operation leads to the accumulation of fault-inducing factors such as component fatigue and heat buildup, resulting in a super-linear increase in maintenance demands. Specifically, within different intervals exceeding the benchmark value, the utilization rate impact coefficient is set segmented according to an increasing slope, or calculated using a nonlinear function. After obtaining the utilization rate impact coefficient for each piece of equipment, in order to obtain a coefficient reflecting the overall utilization level of the entire equipment group, the utilization rate impact coefficients of all equipment are statistically averaged, i.e., a weighted average of the utilization rate impact coefficients of all equipment is calculated. This weighted average can be used to characterize the overall utilization level of the equipment group in subsequent calculations, or it can serve as the basis for normalizing the coefficients of individual equipment.

[0089] In some applications, determining the personnel capability equivalent coefficient includes obtaining the technical level information of each engineer in the maintenance team; assigning a corresponding capability weight value to each engineer according to the preset mapping relationship between level and capability weight; calculating the weighted average of the capability weight values ​​of all engineers in the team to obtain the team weighted average capability value; and determining the personnel capability equivalent coefficient according to the correspondence between the team weighted average capability value and the capability weight value of the benchmark engineer.

[0090] Understandably, this involves obtaining the technical level information of each engineer in the maintenance team. Technical levels are tiered based on factors such as professional skills, work experience, troubleshooting capabilities, and certifications; for example, they can range from junior engineers to senior engineers. Based on a pre-established mapping relationship between levels and capability weights, a corresponding capability weight value is assigned to each engineer. In this mapping relationship, different technical levels correspond to different capability weights. Capability weights represent the efficiency multiple of an engineer at that level relative to a baseline engineer. For example, higher-level engineers have higher capability weights, indicating they can handle more or more complex maintenance tasks per unit of time, while lower-level engineers have relatively lower capability weights. After obtaining the capability weights of each engineer, a weighted average of the capability weights of all engineers in the team is calculated. This involves summing the capability weights of each engineer and then dividing by the total number of team members to obtain the team's weighted average capability value. This weighted average reflects the overall capability level of the entire maintenance team. Based on the correspondence between the team's weighted average capability value and the capability weight value of the baseline engineer, a personnel capability equivalent coefficient is determined. The baseline engineer is typically selected as a standard level (e.g., senior engineer) as a reference, and their capability weight value is set as the baseline value. The personnel capability equivalent coefficient is the ratio of the team's weighted average capability value to the benchmark value. This coefficient is used to convert the team's actual capability into standard capability: when the coefficient is greater than the benchmark value, it means that the team's overall level is higher than the standard, and each person can undertake more workload; when the coefficient is less than the benchmark value, it means that the team's overall level is lower than the standard, and more people are needed to complete the same workload.

[0091] In some applications, determining the cross-base synergy coefficient includes obtaining information on the number of bases where the equipment is distributed; calculating a basic synergy coefficient based on a synergy effect model that includes a maximum saving ratio parameter and a saturation base number parameter, wherein the basic synergy coefficient is one when the number of bases is one, and gradually decreases as the number of bases increases until it reaches a lower limit determined by the maximum saving ratio parameter; obtaining geographical distance information between bases and information on the homogeneity of equipment models at each base, and generating a distance penalty factor and a homogeneity factor respectively; and combining the basic synergy coefficient, the distance penalty factor, and the homogeneity factor to obtain the cross-base synergy coefficient.

[0092] Understandably, this involves obtaining information on the number of bases where the equipment is distributed. A base refers to the physical location or operating site where the equipment is located. Different bases may have technical support channels that share maintenance resources. A basic synergy coefficient is calculated based on a synergy effect model that includes a maximum saving ratio parameter and a saturation base number parameter. The basic characteristic of this model is that when the equipment is distributed only in one base, there is no cross-base synergy effect, and the basic synergy coefficient is one. As the number of bases increases, the basic synergy coefficient gradually decreases because different bases can achieve manpower savings through remote technical support, expert sharing, and unified spare parts allocation. In other words, the synergy effect reduces the theoretically required number of personnel. However, the synergy effect does not grow indefinitely with the number of bases. When the number of bases reaches the threshold specified by the saturation base number parameter, further additions to the bases no longer bring additional savings. At this point, the basic synergy coefficient reaches the lower limit determined by the maximum saving ratio parameter. The mathematical expression of this model is: the basic synergy coefficient equals one minus the maximum saving ratio parameter multiplied by the ratio of the number of new bases exceeding a single base to the saturation base number. The number of new bases is taken as the smaller value between the actual number of bases minus one and the saturation base number to ensure that the basic synergy coefficient is not lower than the lower limit. After obtaining the basic coordination coefficient, further consideration is given to corrective factors affecting coordination efficiency. The first corrective factor is the geographical distance between bases: when the geographical distance between bases is large, the response latency of remote support increases, and coordination efficiency decreases. Therefore, a distance penalty factor needs to be introduced. This factor is determined based on the average or maximum distance between bases, with a baseline value of one, representing no distance penalty for bases in the same region. The greater the distance, the larger the value of this factor. The second corrective factor is the homogeneity of equipment models at each base: when the equipment models at each base are highly consistent, the reusability of technical experience is strong, and coordination efficiency is high. When the equipment models at each base differ significantly, the difficulty of cross-base migration of technical experience increases, and coordination efficiency decreases. Therefore, a homogeneity factor needs to be introduced, with a baseline value of one, representing completely consistent equipment models. The greater the difference, the larger the value of this factor. Multiplying the basic coordination coefficient by the distance penalty factor and the homogeneity factor yields the corrected cross-base coordination coefficient. The combined cross-base synergy coefficient is used to adjust the personnel requirements of the main base or each base in subsequent calculations. A coefficient less than one indicates that manpower is saved due to synergy, while a coefficient greater than one indicates that synergy is weakened or even costs are increased due to distance or heterogeneity.

[0093] In some applications, the total maintenance requirement is adjusted item by item based on the correction factor to output the required number of maintenance engineers. This includes obtaining the total number of calendar days in the year, the total number of statutory paid holidays in the year, the average number of training days in the year, the average number of sick days in the year, and the number of other unavailable days in the year. The number of available days in the year is determined based on the difference between the total number of calendar days in the year and each of the other numbers. The on-duty availability coefficient is obtained based on the ratio between the number of available days in the year and the total number of calendar days in the year. The resource balance coefficient is determined based on at least one of the following factors: shift work mode, technical level matching, operating time difference, and management redundancy. The total maintenance requirement is sequentially correlated with the personnel capability equivalent coefficient, the cross-base coordination coefficient, the on-duty availability coefficient, and the resource balance coefficient in the order of capability conversion, coordination adjustment, on-duty correction, and resource balance compensation. The result of the correlation operation is quantified and rounded to obtain the required number of maintenance engineers.

[0094] Understandably, the on-the-job availability factor is calculated. This involves obtaining the total number of calendar days in the year, along with various deductions affecting engineers' actual on-the-job time, including the total number of statutory paid holidays, the average number of training days, the average number of sick days, and other unavailable days (such as personal leave and special leave). Subtracting the sum of these deductions from the total number of calendar days in the year yields the annual available days. Then, dividing the annual available days by the total number of calendar days gives the on-the-job availability factor. This factor reflects the percentage of actual available working hours at the individual engineer level due to statutory holidays, training, sick leave, etc., and is used to adjust the theoretical number of employees needed to the actual number of employees needed after considering individual absences. Next, the resource balance factor is determined. The resource balance coefficient comprehensively considers multiple practical operational constraints, including shift work factors (such as the minimum number of shifts required for day / night / rest shift systems), technical skill matching factors (each shift must be equipped with a certain number of senior engineers to ensure fault handling capabilities), operational time difference factors (uneven workload distribution between day and night shifts, with day shifts needing to undertake additional work such as scheduled maintenance and modifications), and management redundancy factors (to cope with emergencies such as multiple equipment failures and support for major events). Based on at least one of the above factors, the resource balance coefficient is determined through preset rules or experience-based value ranges. This coefficient is used to comprehensively adjust the theoretically calculated number of personnel to compensate for the additional personnel needs brought about by actual operational constraints such as scheduling, emergency response, and technical skill matching. The total maintenance requirements are adjusted item by item according to a preset order. This order is: first, capacity conversion; second, coordination adjustment; third, on-the-job adjustment; and finally, resource balance compensation. Specifically, the total maintenance requirements are correlated with the personnel capability equivalent coefficient (capacity conversion) to obtain an intermediate result adjusted for team capabilities. This intermediate result is then correlated with the cross-site collaboration coefficient (collaboration adjustment) to obtain an intermediate result considering manpower savings across multiple sites. This intermediate result is further correlated with the on-the-job availability coefficient (on-the-job correction) to obtain an intermediate result after removing individual unavailable working hours. Finally, this intermediate result is correlated with the resource balance coefficient (resource balance compensation) to obtain the final theoretical number of personnel required. The above correlation calculations employ corresponding arithmetic operations based on the physical meaning of each correction factor: capability conversion uses division (because stronger capabilities require fewer personnel), collaboration adjustment uses multiplication (because collaboration savings reduce the number of personnel), on-the-job correction uses division (because a lower percentage of available working hours requires more personnel), and resource balance compensation uses multiplication (because the compensation coefficient increases the number of personnel). Finally, the final result of the correlation calculations is quantified and rounded to obtain the required number of maintenance engineers. Rounding typically uses rounding up or rounding to the nearest whole number to ensure that personnel allocation meets actual operational needs.

[0095] In some applications, a dynamic update step is also included: monitoring changes in the status feature information; monitoring changes in the base data used to determine the plurality of correction factors; when the status feature information or the base data changes, re-executing the operations of acquiring status feature information, determining each influence coefficient, determining total maintenance requirements, determining the plurality of correction factors, and correcting and outputting the required number of maintenance engineers item by item; and updating the required number of maintenance engineers based on the results of the re-executing.

[0096] Understandably, this also includes a dynamic update step to enable real-time adaptive adjustments to personnel configuration plans. The dynamic update step continuously monitors changes in two types of parameters: The first type is the status characteristics of each piece of equipment, including its service life in terms of age, its technical architecture type in terms of technical complexity, and its runtime in terms of average daily utilization. This information may change due to equipment aging (e.g., exceeding a preset threshold), technology upgrades, or adjustments to operational plans (e.g., changes in utilization). The second type is the basic data used to determine multiple correction factors, including the technical level information of each engineer in the maintenance team (which may change due to personnel joining, leaving, promotion, or training certification), the number and distribution of equipment at various bases (which may change due to the establishment of new bases or the closure of existing bases), the geographical distance between bases and the homogeneity of equipment models (which may change due to equipment relocation or the introduction of new equipment), and statistical data such as annual leave, training, and sick leave used to calculate the on-duty availability coefficient (which may change due to company policy adjustments or updates to actual statistical values). Monitoring can be achieved through periodic polling, event triggering, or an interface with an external database. When any of the above-mentioned status characteristics or basic data changes, the entire personnel configuration calculation process is automatically re-executed. This calculation process includes: re-acquiring the status characteristic information of each piece of equipment; re-determining the impact coefficients of each piece of equipment's age, technical complexity, and utilization rate; re-determining the maintenance requirements of each piece of equipment and synthesizing them into a total maintenance requirement; re-determining the personnel capability equivalent coefficient, cross-site collaboration coefficient, on-duty availability coefficient, and resource balance coefficient; and correcting the total maintenance requirement item by item in the order of capability conversion, collaboration adjustment, on-duty correction, and resource balance compensation, and outputting the required number of maintenance engineers. After the re-execution is completed, the original required number of maintenance engineers is updated based on the results of the re-execution, and the updated configuration plan is output to the administrator. The dynamic update step can be set to a real-time trigger mode, i.e., recalculating immediately after a change occurs; or it can be set to a delayed trigger mode, i.e., waiting for a preset stabilization time window after a change occurs before recalculating, to avoid frequent updates caused by short-term parameter fluctuations.

[0097] In some applications, a parameter calibration step is also included: acquiring actual maintenance man-hour data within a historical period; acquiring the state characteristic information and basic data for determining the multiple correction factors within the historical period, and determining the theoretical maintenance requirements within the historical period; comparing the actual maintenance man-hour data with the theoretical maintenance requirements; adjusting the baseline maintenance workload based on the comparison results, and adjusting the parameters in the mapping relationship on which each influence coefficient depends; repeating the adjustment until the deviation between the theoretical maintenance requirements and the actual maintenance man-hour data meets a preset condition.

[0098] Understandably, this also includes a parameter calibration step, used to back-optimize model parameters using historical data to ensure the model's continued accuracy. Acquire actual maintenance man-hour data for a historical period. This data can be extracted from the maintenance management system, including preventative maintenance man-hours, corrective maintenance man-hours, and related support man-hours for all equipment within that period, statistically analyzed in man-hours or man-days. Acquire status characteristic information and basic data for determining multiple correction factors within the same historical period. Status characteristic information includes the service life, technical architecture type, and average daily utilization time of each piece of equipment at each point in time within that period; basic data includes the technical skill level distribution of maintenance team members, the number and geographical distance of equipment locations, the homogeneity of equipment models, and statistics on holidays, training, and sick leave within that period. Using this historical data, following the complete process for determining total maintenance requirements, calculate the theoretical maintenance requirements for that historical period, i.e., the required maintenance workload calculated solely based on equipment status and the correction factor model, without considering actual personnel allocation. Compare the actual maintenance man-hour data with the theoretical maintenance requirements. The comparison can be a total comparison, which compares the cumulative actual total working hours over a historical period with the cumulative theoretical total demand; or a time series comparison, which compares monthly or quarterly. Based on the comparison results, the direction and magnitude of the deviation between the model output and reality are determined. Adjustable parameters in the model are then adjusted based on this deviation. Adjustable parameters include at least the baseline maintenance workload, which directly affects the basic maintenance needs of all equipment; and parameters in the mapping relationship upon which each influence coefficient depends, such as the endpoint values ​​in the piecewise linear mapping function between the age rating and the influence coefficient (the maximum coefficient corresponding to the lowest rating, the baseline coefficient corresponding to the baseline rating, and the minimum coefficient corresponding to the highest rating), and the interval division points and corresponding coefficient values ​​in the nonlinear mapping relationship between the utilization rate influence coefficient and the average daily utilization time. The adjustment principle is: if the theoretical maintenance demand is greater than the actual working hours, the baseline maintenance workload should be appropriately reduced or each influence coefficient should be lowered; if the theoretical maintenance demand is less than the actual working hours, the baseline maintenance workload should be appropriately increased or each influence coefficient should be raised. Finally, the above adjustment steps are repeated. After each adjustment, the theoretical maintenance requirements for the historical period are recalculated and compared with the actual maintenance man-hour data again, until the deviation between the two meets the preset conditions, such as the absolute value of the deviation being less than a preset threshold, or the deviation no longer decreasing significantly after multiple consecutive adjustments. The calibrated parameters are stored and used for subsequent real-time calculations, and the model has completed adaptive updates.

[0099] In some applications, a configuration scheme generation step is also included: determining the number of work groups based on the required number of maintenance engineers; determining the ratio of engineers of each technical level within each work group based on the existing technical level distribution of the maintenance team; determining the number of people in each work group and the independent configuration number of special positions; and outputting a configuration scheme that includes job settings, work group allocation, and hierarchical structure suggestions.

[0100] Understandably, this also includes a configuration scheme generation step, used to transform the calculated number of required maintenance engineers into an executable organizational structure scheme. The number of work teams is determined based on the total number of required maintenance engineers. The division of work teams is determined according to the operating model. For example, for equipment groups requiring continuous 24 / 7 operation, a shift system is typically used, requiring a separate team of personnel for each shift cycle; therefore, the number of work teams equals the number of shift rotation teams. For equipment groups with non-continuous operation, the number of work teams can be divided according to function or equipment area. Based on the existing technical level distribution of the maintenance team, the ratio of engineers of different technical levels within each work team is determined. This ratio should ensure that each work team has the necessary fault handling capabilities when operating independently. For example, each work team should include at least a certain number of senior engineers to handle complex faults, while simultaneously allocating intermediate and junior engineers proportionally to balance cost and talent development needs. The ratio can be determined using optimization algorithms to ensure a balanced distribution of skill levels among work teams while meeting technical capability constraints. The specific number of personnel in each work team and the independent allocation of special positions are then determined. The number of personnel in each shift is calculated by dividing the total number of required maintenance engineers by the number of shifts, rounded down, and then fine-tuned according to the technical staffing ratio to ensure that the number of personnel in each shift meets the requirements for shift work or functional roles. Special positions refer to personnel who do not participate in regular shift work but undertake functions such as technical management, quality supervision, spare parts management, and training guidance. These positions need to be allocated independently, and their numbers are deducted from the total number of required maintenance engineers, with the remaining portion then allocated to each shift. Output a complete configuration plan, which should at least include job descriptions (such as the names and responsibilities of positions like shift leader, technical supervisor, and maintenance engineer), shift allocation (each shift's number, number of personnel, and shift schedule), and a suggested hierarchical structure (the specific number of personnel for each technical level in each shift).

[0101] The following describes another embodiment of the equipment maintenance personnel configuration optimization method based on multi-factor dynamic coupling of the present invention:

[0102] This implementation includes:

[0103] Definitions of abbreviations and key terms:

[0104] Equivalent Maintenance Workload: The maintenance requirements of different equipment under different conditions are converted into a unified standard unit of measurement for workload through multi-dimensional influence coefficients.

[0105] Capability Equivalence Factor: A conversion factor that transforms the actual work capabilities of engineers at different technical levels into the equivalent of a "standard engineer".

[0106] Operational Envelope: The dynamic boundary of the operational status, maintenance needs, and personnel load of a group of equipment over time.

[0107] Cross-base Synergy Coefficient: A coefficient that quantifies the human resource savings resulting from resource sharing among multiple bases.

[0108] Resource Balancing Factor: A correction factor for the theoretical number of employees, taking into account factors such as shift work, differences in skill levels, and staggered operation.

[0109] Availability Factor: The percentage of actual working hours available to engineers after considering factors such as statutory holidays, training, and sick leave.

[0110] Basic Maintenance Workload: Under standard conditions (medium equipment age, medium complexity, standard utilization time), the standard equivalent number of full-time engineers required for a single standard piece of equipment is the baseline value for calculating the equivalent maintenance workload.

[0111] This embodiment of the system includes:

[0112] Equipment Status Acquisition and Evaluation Module: Collects basic parameter information for each piece of equipment, including service life, equipment manufacturer and model, technical architecture type, average daily utilization time, historical failure rate, etc., and generates quantitative scores for each piece of equipment in multiple dimensions according to preset evaluation rules.

[0113] Multidimensional Influence Coefficient Generation Module: Based on the output of the equipment status assessment module, it generates influence coefficients for each device in at least three dimensions, including the aging coefficient, the technical complexity coefficient, and the utilization rate coefficient. The value of each coefficient is determined according to the score of that dimension and the preset mapping function.

[0114] Equivalent maintenance workload calculation module: The baseline maintenance workload of each piece of equipment is multiplied and coupled with the multidimensional influence coefficient of the equipment to obtain the equivalent maintenance workload of the equipment, and the equivalent maintenance workload of all equipment is summed to obtain the total workload;

[0115] Personnel Capability Equivalent Assessment Module: Collects technical level information of each engineer in the maintenance team, assigns capability weight values ​​to each engineer according to the preset level-capability mapping relationship, and calculates the team's weighted average capability coefficient as the capability equivalent coefficient.

[0116] Cross-site synergy coefficient calculation module: Calculates the cross-site synergy coefficient based on the number of sites where the equipment is distributed and the preset synergy effect model. This model includes the maximum saving ratio parameter and the saturation site number parameter.

[0117] On-the-job constraints and resource balance module: Calculates the on-the-job availability coefficient based on information such as shift system, number of statutory holidays, average annual training time, and historical sick leave rate, and calculates the resource balance coefficient based on shift mode, technical level distribution, and differences in operating hours;

[0118] The comprehensive optimization decision module integrates the total equivalent maintenance workload, capacity equivalence coefficient, cross-base collaboration coefficient, on-the-job availability coefficient, and resource balance coefficient into a unified calculation formula, outputs the required number of maintenance engineers, and generates a complete configuration plan that includes job configuration, team allocation, and hierarchical structure suggestions.

[0119] Dynamic update and prediction module: When any input parameter (change in equipment quantity, equipment aging, personnel changes, operation plan adjustments, etc.) changes, it automatically triggers recalculation and can predict personnel demand for a certain period of time in the future based on equipment aging trends and operation plans.

[0120] This embodiment includes:

[0121] Quantitative assessment of multidimensional influence coefficients:

[0122] Determination of the equipment aging factor:

[0123] Each piece of equipment is scored based on its age and service life. The scoring rules are defined as follows: equipment used for less than 5 years receives 5 points; equipment used for 5 to 10 years receives 4 points; equipment used for 10 to 15 years receives 3 points; equipment used for 15 to 20 years receives 2 points; equipment used for 20 to 25 years receives 1 point; and equipment used for more than 25 years receives 0 points.

[0124] After obtaining a rating for the age of each device, the rating needs to be converted into an impact coefficient. (No. The age coefficient corresponding to each piece of equipment. A piecewise linear mapping function is used: a score of 5 (newest equipment) corresponds to... A value of 0.8 indicates that the maintenance requirements for new equipment are lower than the baseline; a score of 3 (medium-level equipment) corresponds to... A value of 1.0 is used as a benchmark; a score of 0 (oldest equipment) corresponds to... A value of 1.5 or higher indicates that the maintenance needs of older equipment are significantly higher than the baseline. Intermediate scores are obtained through linear interpolation.

[0125] For a group of devices, a weighted average age coefficient can be calculated:

[0126] ;

[0127] in,

[0128] The device serial number, with a value ranging from 1 to... ;

[0129] This represents the total number of devices.

[0130] Determining the technical complexity coefficient:

[0131] Each device is scored for technical complexity based on its technical architecture, manufacturer, and system integration complexity. Different technical architecture types correspond to different baseline scores for maintenance difficulty: devices using mature and stable technologies with comprehensive manufacturer support receive the highest score (e.g., 5 points), corresponding to a lower maintenance difficulty coefficient. (No. The technical complexity coefficient for each piece of equipment is 0.9; equipment using new technologies or with high integration and difficult troubleshooting receives a lower score (e.g., 1 point), corresponding to a higher maintenance difficulty coefficient. =1.3; the score for medium-complexity equipment is in the middle. We take 1.0 as the baseline.

[0132] For flight simulator scenarios, they can be categorized by manufacturer and technology level: Category 1 (highest maintenance difficulty) scores 1 point. =1.3; Category II score: 2 points. =1.15; Category III score: 3 points. =1.0; Category IV score: 4 points. =0.95; Category 5 (lowest maintenance difficulty) score: 5 points. =0.9.

[0133] Determination of daily utilization rate coefficient:

[0134] The average daily utilization time of equipment directly affects the length of the maintenance window and the probability of failure. Based on a baseline of 15 hours of daily utilization (…), (No. The daily utilization rate coefficient for each unit of equipment is defined as 1.0, and the calculation rules for the utilization rate coefficient are as follows:

[0135] When the daily usage time is less than 12 hours, there are sufficient maintenance windows. Take 0.85; when the daily usage time is 12 to 15 hours, Linear interpolation between 0.85 and 1.0; when the daily utilization time is 15 to 16 hours. Linear interpolation between 1.0 and 1.2; when the daily utilization time is 16 to 18 hours. Linear interpolation is used between 1.2 and 1.5; when daily utilization exceeds 18 hours, the maintenance window becomes extremely tight, and the risk of accumulated faults increases significantly. Use 1.5 or higher.

[0136] The rationale for using a non-linear growth design for the utilization rate coefficient is that as daily utilization time increases, the available maintenance time is compressed at a faster rate. At the same time, continuous operation of equipment leads to a super-linear increase in the probability of failure. Therefore, the amplification effect of high utilization rate on maintenance demand is non-linear.

[0137] Combinatorial verification of influence coefficients:

[0138] After obtaining the three-dimensional influence coefficients for each piece of equipment, the equivalent maintenance workload of a single piece of equipment is calculated using a product-coupled rather than nonlinear superposition method. The physical meaning of product-coupled is that the amplification effect of each factor on maintenance requirements is mutually reinforcing. For example, the maintenance requirements of an old, technically complex, and highly utilized piece of equipment are far greater than the simple sum of the individual effects of each factor.

[0139] For the The equivalent maintenance workload (EMW) for a single device is denoted as EMW. )for:

[0140] ;

[0141] in, Baseline maintenance workload represents the standard equivalent number of full-time engineers required per device under standard conditions (medium equipment age, medium complexity, standard utilization time).

[0142] System settings validity verification rules: When any single device Exceeding the preset limit (e.g.) When the device's capacity is 3 times that of the standard equipment, an error message is triggered, reminding the administrator that the device may require a special maintenance plan instead of the standard configuration.

[0143] Personnel capability equivalent assessment and team capability coefficient calculation:

[0144] Mapping between technical level and capability weight:

[0145] Maintenance engineers are categorized into multiple technical levels, each with a different competency weighting value. This competency weighting value reflects the efficiency multiple of an engineer at that level relative to a standard senior engineer.

[0146] The capability weight mapping is defined as follows: The capability weight of the chief / supervisor level engineer (the highest level) is 5, indicating that they can independently handle complex and difficult faults, guide multi-person collaborative work, and undertake high-value work such as technical decision-making, with an overall efficiency of approximately 1.67 times that of the benchmark; the capability weight of the senior engineer is 4, and they can independently handle most complex faults; the capability weight of the senior engineer is 3, which serves as a capability benchmark reference; the capability weight of the intermediate engineer is 2; and the capability weight of the junior engineer and below is 1.5 or lower.

[0147] Calculation of team weighted average ability:

[0148] Assume the team has a total of Maintenance engineer ( (Total number of maintenance engineers in the team), the ability weight of the j-th engineer is (No. The corresponding competency weight values ​​for each engineer. The engineer's serial number, ranging from 1 to... Then the team's weighted average ability value is:

[0149] ;

[0150] Using a capability weight of 3 (senior engineer level) as the capability benchmark for a "standard engineer", the team capability equivalent coefficient is... The calculation method is as follows:

[0151] ;

[0152] when A score >1 indicates that the team's overall performance is above the benchmark, and each individual can handle a greater workload; when A score less than 1 indicates that the team's overall performance is below the baseline, requiring more personnel to complete the same workload.

[0153] Dynamic updating mechanism for competency assessment:

[0154] Team capability coefficients are not static. The following dynamic update trigger conditions are set: automatic recalculation when there are personnel changes within the team (onboarding, departure, job transfer); updating capability weights when engineers complete technical level promotions or training certifications; and periodic verification at preset intervals (e.g., quarterly), with fine-tuning of capability weights based on actual work performance data.

[0155] Example of parameter values:

[0156] A maintenance team consists of 65 people, including 3 supervisors (weight 5), 3 seniors (weight 5, including acting supervisors), 3 level 8 (weight 4), 11 level 7 (weight 4), 19 level 6 (weight 3), and 29 level 5 and below (weight 2).

[0157] =(3×5+3×5+3×4+11×4+19×3+29×2) / 65≈2.9;

[0158] =2.9 / 3≈0.97;

[0159] The team's capability coefficient is slightly lower than the baseline of 1.0, mainly because the proportion of junior engineers is relatively high (approximately 44.6%), requiring slightly more personnel than the standard calculated value.

[0160] Cross-site synergy coefficient modeling and calculation:

[0161] The physical significance of the synergistic effect:

[0162] When equipment is distributed across multiple bases, these bases can achieve a certain degree of human resource savings through remote technical support, expert resource sharing, unified spare parts allocation, and centralized training. However, the synergy effect does not increase indefinitely with the number of bases. Once the number of bases reaches a certain level, the increased management complexity will offset the savings brought by synergy.

[0163] Mathematical model of the synergy coefficient:

[0164] Equipment distributed in One base ( (Total number of bases where equipment is distributed) Define cross-base coordination coefficient. (Equipment distributed in) The formula for calculating the cross-base synergy coefficient (for each base) is as follows:

[0165] ;

[0166] in, The maximum saving percentage parameter represents the maximum percentage of manpower savings that can be achieved when the synergistic effect is fully saturated, and its value typically ranges from 0.1 to 0.25.

[0167] To conserve the number of bases that reach the effect saturation point (i.e., after exceeding this number of bases, adding new bases will no longer bring additional savings), the value is usually between 3 and 6;

[0168] The number of new bases exceeding the number of single bases represents the base increment that can generate synergistic effects.

[0169] when When =1, =1 indicates that a single base has no synergistic effect; when When gradually increasing, Gradually decrease (savings increase); when ≥ +1 (when the number of bases exceeds the saturation threshold), Reaching the minimum value .

[0170] It should be noted that the synergy coefficient Used to adjust personnel requirements at the main base. <1 indicates that the main base can reduce some personnel due to collaboration, but each branch base still needs to independently configure basic personnel according to local minimum operating requirements.

[0171] Correction factors for the synergy coefficient:

[0172] Based on the basic model, the following modification factors are introduced:

[0173] Inter-base distance correction: When the geographical distance between bases exceeds a preset threshold (e.g., across provinces or regions), the response latency of remote support increases, and the coordination efficiency decreases, requiring adjustments to... Adjustments were made (i.e., the savings effect was reduced), and a distance penalty factor was introduced. (A baseline value of 1 indicates no distance penalty for bases in the same area; a value greater than 1 indicates a loss in coordination efficiency due to distance, with a larger value indicating a more severe loss.)

[0174] Correction of Technology Homogenization: When the equipment models of each base are highly consistent, the reusability of technical experience is strong, and the collaboration efficiency is high; when the equipment models of each base differ greatly, the collaboration efficiency decreases, introducing a homogenization factor. (A baseline value of 1 indicates that the equipment models at each base are completely identical, with no loss in collaborative efficiency; a value greater than 1 indicates a loss in collaborative efficiency due to differences in equipment models, with a larger value indicating a more severe loss.)

[0175] The corrected synergy coefficient is:

[0176] ;

[0177] in ≥1, ≥1, when both factors are 1, revert to the base model.

[0178] Example of parameter values:

[0179] The equipment is distributed across three bases. =0.2, =5, then:

[0180] (3) = 1 - 0.2 × min(2,5) / 5 = 1 - 0.08 = 0.92;

[0181] Considering the long distances between bases (across regions). =1.03; the equipment models are basically the same. =1.0;

[0182] =0.92×1.03×1.0≈0.95;

[0183] Comprehensive optimization formula and complete calculation process:

[0184] Core calculation formula:

[0185] Number of maintenance engineers required The formula for calculating (the total number of theoretically configured engineers to meet all maintenance needs) is:

[0186] ;

[0187] in:

[0188] This refers to the total number of devices;

[0189] The baseline maintenance workload (standard person / unit) corresponds to the baseline maintenance workload defined by the abbreviation.

[0190] , , The first The equipment's age coefficient, technical complexity coefficient, and utilization rate coefficient;

[0191] The team capability equivalent coefficient;

[0192] This represents the availability coefficient for employees currently on the job.

[0193] This refers to the cross-base collaboration coefficient.

[0194] The resource balance coefficient represents the comprehensive correction multiple for the theoretically calculated number of personnel. When the coefficient is greater than 1, the personnel configuration needs to be increased based on the theoretical value to meet actual operational constraints such as shift work, emergency response, and technical coordination.

[0195] Calculation of on-the-job availability factor:

[0196] On-the-job availability factor The calculation is based on the following parameters:

[0197] Total number of days in the annual calendar (Total number of calendar days in a year, typically 365 days); Total number of statutory paid holidays per year (Including national statutory holidays and paid annual leave); average number of training days per year Average number of sick days per year Other unavailable days per year .

[0198] ;

[0199] For example, =365 days (Including statutory holidays and paid annual leave) = 15 days =10 days =3 days =2 days, then =(365-15-10-3-2) / 365≈0.92.

[0200] Considering the actual on-duty rate under the shift work model (four shifts: day, night, rest, and double rotation), the actual on-duty rate is approximately 50%, but this has already been reflected in the resource balance coefficient. Availability is calculated only at the individual level.

[0201] Determination of the resource balance coefficient:

[0202] Resource balance coefficient This is an actual correction factor for the theoretically calculated number of people, taking into account the following factors:

[0203] Shift work factors: Under the day-night-rest system, at least 4 teams are needed to maintain 24-hour operation, and even if the workload is not full, the minimum number of teams is required.

[0204] Technical level matching factor: Each team must be equipped with at least one senior engineer to ensure fault handling capabilities, rather than simply distributing the workload equally;

[0205] Factors affecting operating hours: The workload distribution between day shifts and night shifts is uneven. Night shifts are mainly focused on operational support, while day shifts need to undertake additional work such as scheduled inspections and modifications.

[0206] Management redundancy factors: It is necessary to consider the emergency response capabilities for unforeseen circumstances (such as simultaneous failure of multiple devices, support for major events, etc.).

[0207] For example, The value range is from 1.05 to 1.20, with a default value of 1.10.

[0208] Complete calculation process:

[0209] Data Acquisition. The Equipment Status Acquisition and Evaluation module obtains basic data such as the service life, technology type, and average daily utilization time of each piece of equipment; the Personnel Capability Equivalence Assessment module obtains the technical level and capability certification information of each engineer; and the Cross-Base Collaboration Coefficient Calculation module obtains information on the number and distribution of bases.

[0210] Calculation of multidimensional influence coefficients. Calculations are performed separately for each piece of equipment. , , Influence coefficients in three dimensions.

[0211] Equivalent workload calculation. Calculation for each piece of equipment. And find the sum. (The total equivalent maintenance workload of the equipment group is the sum of the equivalent maintenance workloads of all individual equipment) = .

[0212] Team capability coefficient calculation. Calculate the team's weighted average capability and convert it into a capability equivalent coefficient. .

[0213] Calculation of cross-base synergy coefficient. Calculated based on the number and distribution characteristics of bases. .

[0214] Calculation of on-the-job constraint parameters. and .

[0215] Comprehensive calculation. Substituting all parameters into the core formula yields... The integer value of the ceiling is taken as the final number of recommended users.

[0216] Solution generation. Based on... Based on the constraints of team hierarchy structure, specific team configuration plans are generated, including the number of people in each team, the ratio of engineers of different levels in each team, and independent configuration suggestions for special positions (such as technical management, quality supervision, warehouse management, etc.).

[0217] Sensitivity analysis. Sensitivity analysis is conducted on key parameters (equipment additions / reductions, utilization rate changes, staff turnover, etc.) to quantify the impact of fluctuations in a single parameter on staffing outcomes. The analysis outputs a trend chart of personnel demand changes as parameters change, providing a reference for management decisions.

[0218] Numerical calculation example:

[0219] Main base calculation:

[0220] Equipment parameters: =33 units (including 27 full-motion simulators converted to equivalent units, 2 fixed base equipment, 15 program training equipment and 2 other equipment; the latter three categories are converted to equivalent full-motion units of approximately 4 to 6 units).

[0221] =2.5 people / unit;

[0222] Equipment average coefficient: =1.03, =1.02, =1.05;

[0223] Team capability coefficient =0.95;Number of bases =3, =0.95; =0.98;

[0224] Equivalent workload per unit: =2.5×1.03×1.02×1.05≈2.76;

[0225] (here) The value already takes into account the conversion of full-motion simulators; in practice, non-full-motion equipment... Take the lower value. In this example, the calculation is based on an equivalent total number of 31 units for the mixed equipment group.

[0226] Total workload: =31 × 2.76 ≈ 85.6 people;

[0227] Without considering collaboration, the following requirements apply: =85.6 / 0.95≈90.1 people;

[0228] After considering collaboration: 90.1 × 0.95 ≈ 85.6 people;

[0229] After considering the on-duty rate: 85.6 / 0.98 ≈ 87.3 people;

[0230] After rounding, it is recommended that the main base be staffed with approximately 78 to 88 people (depending on...). The specific calibration value may vary.

[0231] Sub-base calculation:

[0232] Equipment parameters: =4 full-motion simulators; =2.5 people / unit;

[0233] Equipment average coefficient: =0.95, =0.95, =1.0;

[0234] Team capability coefficient =0.80 (High proportion of beginners); =0.95; =0.95;

[0235] Equivalent workload per unit: =2.5×0.95×0.95×1.0≈2.26;

[0236] Total workload: =4 × 2.26 ≈ 9.03 people;

[0237] Without considering collaboration, the required number of people is approximately 9.03 / 0.80 ≈ 11.3.

[0238] After considering collaboration: 11.3 × 0.95 ≈ 10.7 people;

[0239] After considering the on-duty rate: 10.7 / 0.95≈11.3 people;

[0240] Considering resource balance coefficient =1.10: 11.3 × 1.10 ≈ 12.4 people;

[0241] After rounding, it is recommended that each branch base be staffed with 12 to 13 people.

[0242] Dynamic updates and trend forecasting:

[0243] Parameter change monitoring and automatic triggering:

[0244] The system settings parameter change monitoring engine continuously monitors the following events:

[0245] New equipment coming online or old equipment being decommissioned (number of devices) Changes); Equipment utilization time plan adjustment ( Changes); personnel joining, leaving, or changes in rank ( Changes); the establishment of a new base or the closure of an existing base ( and Changes); equipment crossing the lifespan threshold (e.g., a piece of equipment moving from 14 years to 15 years of use, (From the 3-minute interval to the 2-minute interval).

[0246] When any of the above events occur, the system automatically triggers a recalculation, compares the old and new results, and outputs the amount of change and an analysis of the reasons for the change.

[0247] Trend prediction based on equipment aging curve:

[0248] Regarding the equipment age coefficient, the system automatically calculates the service life based on the equipment's commissioning date and the current date, and can extrapolate the equipment's age over the next 1 to 5 years. As multiple pieces of equipment age year by year, the overall... The demand will show an upward trend, and the system can predict the changing trends of personnel demand in future years.

[0249] Similarly, if future equipment introduction and decommissioning plans are known, the system can incorporate future equipment changes into the prediction model and output early warnings of personnel shortages for each future year.

[0250] Parameter calibration based on historical data:

[0251] The system is equipped with a parameter calibration function that uses historical maintenance man-hour data to perform reverse calibration of model parameters. The specific method involves collecting data on total actual maintenance man-hours, actual number of personnel, and actual overtime situations from the past several years. Using the actual data as the target value and the model-calculated value as the predicted value, adjustments are made using least squares regression or other optimization algorithms. The mapping function parameters for each influence coefficient are used to minimize the sum of squared residuals between the model's calculated values ​​and historical actual values, thereby minimizing the deviation between the model's output and historical actual values.

[0252] The calibrated parameters are stored in the parameter database, with the calibration date and the data range on which they are based noted, to ensure the continued accuracy of the model.

[0253] For the purpose of simplicity, the method steps disclosed in the above embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0254] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the allocation of equipment maintenance personnel based on multi-factor dynamic coupling, characterized in that, include: Obtain the status characteristic information of each device, wherein the dimensions of the status characteristic information include the degree of age, technical complexity, and average daily utilization time; Based on the aforementioned status characteristic information, an impact coefficient for age, an impact coefficient for technical complexity, and an impact coefficient for utilization rate are determined for each device. The utilization rate impact coefficient is determined according to the average daily utilization time and a preset mapping relationship between the average daily utilization time interval and the impact coefficient. When the average daily utilization time exceeds a benchmark value, the utilization rate impact coefficient exhibits a non-linear relationship with the average daily utilization time. Based on the baseline maintenance workload of each piece of equipment and the corresponding impact coefficients of age, technical complexity, and utilization rate, the maintenance requirements of each piece of equipment are determined, and the total maintenance requirements of the equipment group are obtained by combining the maintenance requirements of all equipment. A plurality of correction factors are determined for sequentially adjusting the total maintenance requirements, wherein the correction factors include personnel capability equivalent coefficient, cross-site coordination coefficient, on-duty availability coefficient, and resource balance coefficient; The total maintenance requirements are adjusted item by item based on the correction factor, and the required number of maintenance engineers is output.

2. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, The impact coefficient of aging degree is determined, and further includes: Obtain the service life information for each device; Based on the service life information, and according to the preset mapping relationship between service life range and score, the age rating of each device is determined; According to the preset piecewise linear mapping function between the score and the influence coefficient, the oldness score is converted into the oldness influence coefficient. The piecewise linear mapping function defines the maximum influence coefficient corresponding to the lowest score, the benchmark influence coefficient corresponding to the benchmark score, and the minimum influence coefficient corresponding to the highest score. The average of the influence coefficients of the aging degree of all equipment is statistically analyzed to obtain the weighted average of the influence coefficients of the aging degree.

3. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, Determine the impact coefficient of technical complexity, which further includes: Obtain the technical architecture type information for each device; Based on the technical architecture type information, and according to the preset mapping relationship between technical architecture type and maintenance difficulty benchmark score, the technical complexity score of each device is determined; Based on the preset mapping relationship between technical complexity score and influence coefficient, the technical complexity score is converted into the technical complexity influence coefficient; The average of the technical complexity influence coefficients of all devices is statistically analyzed to obtain a weighted average of the technical complexity influence coefficients.

4. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, Determining the utilization rate impact coefficient further includes: Obtain the average daily usage time information for each device; Based on the average daily utilization time information, and according to the preset mapping relationship between the average daily utilization time interval and the influence coefficient, the utilization rate influence coefficient of each device is determined. When the average daily utilization time exceeds the benchmark value, the utilization rate influence coefficient and the average daily utilization time have a non-linear relationship. The average utilization rate impact coefficient of all equipment is statistically analyzed to obtain a weighted average value of the utilization rate impact coefficient.

5. The method for optimizing equipment maintenance personnel allocation based on multi-factor dynamic coupling according to claim 1, characterized in that, Determining the personnel capability equivalent coefficient further includes: Obtain the technical skill level information of each engineer in the maintenance team; Based on the preset mapping relationship between levels and ability weights, a corresponding ability weight value is assigned to each engineer; Calculate the weighted average of the ability weights of all engineers in the team to obtain the team's weighted average ability value; The personnel capability equivalent coefficient is determined based on the correspondence between the team's weighted average capability value and the capability weight value of the benchmark engineer.

6. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, Determining the cross-base synergy coefficient further includes: Obtain information on the number of bases where the equipment is distributed; Based on the synergy effect model including the maximum saving ratio parameter and the saturation base number parameter, the basic synergy coefficient is calculated, wherein when the number of bases is one, the basic synergy coefficient is one, and when the number of bases increases, the basic synergy coefficient gradually decreases until it reaches the lower limit value determined by the maximum saving ratio parameter. Obtain geographical distance information between bases and information on the homogeneity of equipment models at each base, and generate distance penalty factor and homogeneity factor respectively; The cross-site coordination coefficient is obtained by combining the basic coordination coefficient, the distance penalty factor, and the homogenization factor.

7. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, Based on the correction factor, the total maintenance requirements are corrected item by item, and the required number of maintenance engineers is output, further including: Obtain the total number of calendar days in the year, the total number of statutory paid holidays in the year, the average number of training days in the year, the average number of sick days in the year, and the number of other unavailable days in the year. Determine the number of available days in the year based on the difference between the total number of calendar days in the year and each of the other numbers of days. Obtain the on-the-job availability coefficient based on the ratio between the number of available days in the year and the total number of calendar days in the year. The resource balance coefficient is determined based on at least one of the following factors: shift work pattern, skill level matching, operating time difference, and management redundancy. Following the order of capacity conversion, coordination adjustment, on-the-job correction, and resource balancing compensation, the total maintenance requirements are sequentially correlated with the personnel capacity equivalent coefficient, the cross-base coordination coefficient, the on-the-job availability coefficient, and the resource balancing coefficient. The result of the correlation operation is quantized and rounded to obtain the required number of maintenance engineers.

8. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, It also includes a dynamic update step: Monitor changes in the state characteristic information; Monitor changes in the underlying data used to determine the plurality of correction factors; When the status feature information or the basic data changes, the operations of acquiring status feature information, determining each influence coefficient, determining total maintenance requirements, determining multiple correction factors, and correcting each item and outputting the required number of maintenance engineers are re-executed. The required number of maintenance engineers will be updated based on the results of the re-execution.

9. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, It also includes a parameter calibration step: Obtain actual maintenance man-hour data within the historical period; Obtain the state characteristic information within the historical period and the basic data used to determine the multiple correction factors, and determine the theoretical maintenance requirements within the historical period; The actual maintenance hours are compared with the theoretical maintenance requirements; Adjust the baseline maintenance workload based on the comparison results, and adjust the parameters in the mapping relationship on which each influence coefficient depends. Repeat the adjustment until the deviation between the theoretical maintenance requirements and the actual maintenance hours meets the preset conditions.

10. The method for optimizing equipment maintenance personnel configuration based on multi-factor dynamic coupling according to claim 1, characterized in that, It also includes the configuration scheme generation step: The number of work teams will be determined based on the required number of maintenance engineers. Based on the existing technical skill level distribution of the maintenance team, determine the ratio of engineers of each technical skill level within each shift. Determine the number of people in each work group and the independent allocation of special positions; The output includes a configuration scheme with suggestions on job positions, work group assignments, and hierarchical structure.

Images