Integrated platform and method based on production materials, MRO and temporary purchasing

Abstract

The invention belongs to the technical field of data processing, and discloses an integrated platform and method based on production materials, MRO and temporary purchasing, and the platform comprises a data obtaining module which is used for obtaining production supply chain data; the data processing module is used for processing the production supply chain data to obtain a supply chain comprehensive feature data set; the demand prediction module is used for taking the supply chain comprehensive feature data as the input of a material demand prediction model, and predicting the material demand in n periods of time in the future; the inventory optimization module is used for acquiring real-time inventory data by using an RFID technology, acquiring an inventory gap in combination with the predicted material demand quantity in the n periods of time in the future, and judging whether inventory adjustment needs to be carried out or not based on the inventory gap; if inventory adjustment needs to be carried out, an optimal inventory adjustment plan is obtained through a spectrum particle optimization algorithm in combination with spectrum disturbance and a momentum factor limiting mechanism; the stock turnover rate is improved; and meanwhile, the production line can run stably.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to an integrated platform and method based on production materials, MRO and temporary procurement. Background Art

[0002] The patent publication number CN104281902A discloses a method for formulating material demand suggestions. The method includes: obtaining the demand source, which is one or more of the latest master production plan, the latest sales order, or a temporary plan; obtaining all the demand items involved in the demand source and the demand quantity of each demand item; obtaining the static available quantity of each item, the static available quantity includes: the inventory quantity of each item, the available quantity of each item involved in each planning element before obtaining the demand source; the planning elements include: production suggestions, procurement suggestions, outsourcing suggestions, production plans, procurement plans, production orders, procurement orders, outsourcing orders, one or more; using the static available quantity of each item to offset the demand quantity of the demand item with the same name as the item, and the result is displayed as a material demand suggestion. The present invention can quickly and accurately adjust the demand quantity of each demand item when the demand changes.

[0003] The existing integrated platform and methods for production materials, MRO and temporary procurement have the following main problems: Failure to effectively manage and optimize the key cost components of inventory (ordering cost, holding cost, out-of-stock cost), resulting in unreasonable cost control and inability to effectively balance these costs in actual operations, affecting profit maximization; lack of accurate identification and control of costs, resulting in unnecessary waste of resources and inventory backlogs; failure to consider the dynamic adaptability of multi-variety inventory management, which may result in the system being only applicable to the management of a single material and unable to flexibly respond to demand fluctuations for multiple material categories; inability to dynamically adjust inventory based on the actual demand for different materials, thereby increasing the complexity and uncertainty of inventory management; lack of an effective inventory adjustment plan, which may result in a lack of a clear optimization path in the process of solving inventory optimization problems and making it difficult to conduct effective inventory optimization; Due to the lack of flexible and efficient optimization strategies, the search space of traditional inventory optimization methods may be too narrow, resulting in the optimization process being unable to fully explore the solution space and easily falling into local optimal solutions in the early stages, reducing the efficiency and accuracy of the algorithm. For large-scale, multi-variety inventory optimization problems, the lack of adaptive and flexible adjustment mechanisms makes the algorithm unable to adapt to changing demands and complex material management strategies.

[0004] In view of this, the present invention proposes an integrated platform and method based on production materials, MRO and temporary procurement to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an integrated platform based on production materials, MRO and temporary procurement, comprising: Data acquisition module, used to acquire production supply chain data; The data processing module is used to process the production supply chain data to obtain a comprehensive supply chain feature data set; The demand forecasting module is used to use the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; The inventory optimization module uses RFID technology to obtain real-time inventory data, combines the predicted material demand in the next n periods of time to obtain the inventory gap, and determines whether inventory adjustment is needed based on the inventory gap; if inventory adjustment is needed, the spectral particle optimization algorithm is combined with spectrum disturbance and momentum factor restriction mechanism to obtain the optimal inventory adjustment plan; The decision feedback module is used to transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level; each module is connected by wired and / or wireless means.

[0006] Furthermore, the production supply chain data includes production material data, MRO parameter data and temporary procurement data; the production material data includes material name, material specification, inventory quantity, usage cycle, supplier information and procurement cost; the MRO parameter data includes production equipment code, production equipment model, maintenance cycle, failure rate, maintenance record and MRO material inventory; the temporary procurement data includes temporary procurement quantity, application department, temporary procurement material requirements, temporary procurement supplier information and temporary procurement cost.

[0007] Furthermore, the method for processing production supply chain data includes: The Z-score algorithm is used to detect outliers in the production supply chain data, and the identified outliers are eliminated; the missing values ​​in the production supply chain data after outliers are eliminated are filled by linear interpolation to obtain the production supply chain parameter data; the production supply chain parameter data is normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby obtaining the normalized production supply chain parameter data.

[0008] Furthermore, the method for acquiring the supply chain comprehensive feature data set includes: The principal component analysis is used to reduce the dimension of the normalized production supply chain parameter data to obtain the production supply chain feature data set. The Apriori algorithm is used to mine the association rules of the normalized production supply chain parameter data to obtain the association feature data set. The association feature data set and the production supply chain feature data set are fused through a weighted model to obtain the supply chain comprehensive feature data set. The association feature data set is recorded as , the production supply chain feature dataset is recorded as ; The weighted model is: ;in, is the weight coefficient of the associated feature data set; Weight coefficients for the production supply chain characteristics dataset.

[0009] Furthermore, the method for acquiring the associated feature data set includes: S51, discretize the normalized production supply chain parameter data and convert it into transaction data form; preset the minimum support threshold as , the minimum confidence threshold is ; Initialize the frequent itemsets to empty sets; S52: For each parameter combination, calculate the support in the normalized production supply chain parameter data, and retain the support greater than or equal to the preset minimum support threshold. The parameter combination generates Frequent item sets are generated, and the iteration is repeated until no new frequent item sets are generated; the frequent item sets generated in each iteration are collected to obtain the comprehensive frequent item sets; S53, for each frequent item set in the comprehensive frequent item set, generating a corresponding association rule; for each association rule, calculating its confidence and retaining the association rules whose confidence is greater than or equal to the minimum confidence threshold; S54. Collect all association rules whose confidences are greater than or equal to a minimum confidence threshold, and then obtain an association feature data set.

[0010] Furthermore, the training method of the material demand prediction model includes: The data set is divided into training set, validation set and test set to train the model and evaluate the model performance; the sample set is a subset of the data set, each sample set includes the historical supply chain comprehensive feature data set and the corresponding material demand in the next n period of time; A material demand prediction model is constructed using the deep learning library TensorFlow; the material demand prediction model includes an input layer, an LSTM layer, and an output layer; the input layer of the model is used to input a historical supply chain comprehensive feature data set; the output layer of the model is used to output the material demand in the next n periods of time; the material demand prediction model is an LSTM model; Define the loss function of the model and use the L2 regularized mean square error loss function to measure the difference between the model's predicted value and the true value; use the training set to train the material demand forecasting model and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the material demand forecasting model by calculating the accuracy index; The Adam optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The performance of the model in the prediction task is evaluated using the test set, and the trained material demand prediction model is used to predict the current supply chain comprehensive feature data set to obtain the material demand in the next n period of time.

[0011] Furthermore, the method for determining whether inventory adjustment is required based on inventory gap includes: Use RFID technology to obtain real-time inventory data, including current inventory quantity, storage location and material status; Subtract the current inventory from the predicted material demand in the next n periods of time to obtain the inventory gap; preset an inventory gap threshold, and compare the inventory gap with the preset inventory gap threshold; If the inventory gap is less than the preset inventory gap threshold, it is determined that no inventory adjustment is required; if the inventory gap is greater than or equal to the preset inventory gap threshold, it is determined that inventory adjustment is required.

[0012] Furthermore, the method for obtaining the optimal inventory adjustment plan includes: S81. The goal of the preset inventory adjustment plan is to minimize inventory costs, and the objective function is defined as: ;in, is the objective function; is the unit ordering cost; For the Adjustment amount of this type of material; is the unit inventory holding cost; is the unit out-of-stock cost; For the Demand for materials of this type; The index of the material category; is the total number of material categories; S82. Define the position of each spectral particle to represent an inventory adjustment plan. ;in, For the Adjustment amount of this type of material; The total amount of adjustment for the material; S83, Initialization The position of the spectral particles and the corresponding spectral frequency , initialize the spectral particles: ;in, For the The initial position of each spectral particle; It is the lower bound of the material inventory adjustment amount; It is the upper limit of the material inventory adjustment amount; is the random number of the initial spectral particle position; Initialize the spectral frequencies: ;in, For the The initial frequency of the spectral particles; is the minimum value of the spectral frequency; is the maximum value of the spectral frequency; is the random number of the initial spectrum particle frequency; S84. Based on the energy propagation law of the spectrum, the position and velocity of the spectrum particles are updated through the position update formula and the velocity update formula; the position update formula is: ;in, For the spectral particle The position of the iteration; For the spectral particle The position of the iteration; For the spectral particle The speed of iterations; The speed update formula is: ;in, For the spectral particle The speed of iterations; For the spectral particle The speed of iterations; represents the momentum factor; is the learning factor; is the gradient of the objective function; is the spectrum disturbance factor; is the spectrum oscillation term; For the spectral particle The temperature of the iteration; S85. The temperature of the spectrum particles during iteration is limited by the temperature attenuation formula. The temperature attenuation formula is: ;in, is the initial temperature of the spectral particle; is the temperature control factor; is the current iteration number; The spectrum perturbation factor is adjusted by the spectrum perturbation adjustment formula Perform dynamic adjustment, and the spectrum disturbance adjustment formula is: ;in, is the initial maximum spectrum disturbance factor; To control the disturbance factor with the number of iterations Adjustment parameters of decay speed; is the total number of spectral particles; the momentum factor is restricted by the momentum factor restriction formula; S86. Update the spectrum frequency using a spectrum update formula according to the fitness of the spectrum particle; the spectrum update formula is: ;in, is the current global optimal fitness; is the spectrum adjustment factor; For the The spectral particle is The spectral frequency at the iteration; For the The spectral particle is The spectral frequency at the iteration; S87. In each iteration, calculate the fitness of each spectral particle and update the global optimal solution , preset the global optimal solution threshold, when the spectrum optimization algorithm reaches the maximum number of iterations or the global optimal solution Stop when it is less than the preset global optimal solution threshold; the global optimal solution at this time This is the optimal inventory adjustment plan.

[0013] Furthermore, the method of limiting the momentum factor by using the momentum factor limiting formula includes: The momentum factor constraint formula is: ;in, is the maximum value of the momentum factor; is the maximum number of iterations; is the absolute value of the objective function gradient; It is a parameter for adjusting the balance between the effect of gradient and particle number on momentum factor.

[0014] An integrated approach based on production materials, MRO and ad hoc procurement, including: S1. Obtain production supply chain data; S2. Process the production supply chain data to obtain a comprehensive supply chain feature data set; S3, using the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; S4. Use RFID technology to obtain real-time inventory data, combine it with the predicted material demand in the next n periods of time to obtain the inventory gap, and determine whether inventory adjustment is needed based on the inventory gap; if inventory adjustment is needed, use the spectral particle optimization algorithm combined with spectrum perturbation and momentum factor restriction mechanism to obtain the optimal inventory adjustment plan; S5. Transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level.

[0015] The technical effects and advantages of the integrated platform and method based on production materials, MRO and temporary procurement of the present invention are as follows: The present invention clearly decomposes inventory costs into three parts through the objective function: ordering cost, holding cost and out-of-stock cost, which are the core cost sources of inventory management; by considering the adjustment amount and demand of each type of material, it ensures that the objective function can dynamically adapt to multi-variety inventory management; the position of each spectral particle represents an inventory adjustment plan, and this mapping method is intuitive and easy to implement the optimization algorithm; the upper and lower bounds and random numbers are used to generate the initial solution to ensure the diversity of the search space and avoid falling into the local optimal solution; the position update formula combines the current position, speed and gradient of the particle with the objective function, so that the particle has guidance when searching the solution space; The speed update formula introduces momentum factor, learning factor and spectrum disturbance factor to control inertia, learning ability and dynamic disturbance respectively, thus enhancing the exploration and development ability of the algorithm. The temperature controls the randomness of particles, and through exponential decay, ensures that the algorithm searches the solution space extensively in the early stage and gradually concentrates on the global optimal solution in the later stage. By dynamically adjusting the spectrum disturbance factor, it can adapt to particle swarms of different sizes, while retaining the dynamic adjustment characteristics of the algorithm in the iterative process. It avoids the influence of too large or too small momentum factor on the search trajectory and ensures the stability of particle motion. Through dynamic adjustment of the global optimal fitness and spectrum adjustment factor, the spectral particles can approach the optimal solution faster. It enhances the search ability of the algorithm and the convergence performance of the global optimal solution, which has high practical value for solving complex inventory optimization problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the structure of an integrated platform based on production materials, MRO and temporary procurement of the present invention; Figure 2 The figure is a flow chart of an integrated method based on production materials, MRO and temporary procurement according to the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 See also Figure 1 As shown, this embodiment is an integrated platform based on production materials, MRO and temporary procurement, including: Data acquisition module, used to acquire production supply chain data; The data processing module is used to process the production supply chain data to obtain a comprehensive supply chain feature data set; The demand forecasting module is used to use the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; The inventory optimization module uses RFID technology to obtain real-time inventory data, combines the predicted material demand in the next n periods of time to obtain the inventory gap, and determines whether inventory adjustment is needed based on the inventory gap; if inventory adjustment is needed, the spectral particle optimization algorithm is combined with spectrum disturbance and momentum factor restriction mechanism to obtain the optimal inventory adjustment plan; The decision feedback module is used to transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level; each module is connected by wired and / or wireless means.

[0019] Production supply chain data includes production material data, MRO parameter data and temporary procurement data; production material data includes material name, material specification, inventory quantity, usage cycle, supplier information and procurement cost; MRO parameter data includes production equipment code, production equipment model, maintenance cycle, failure rate, maintenance record and MRO material inventory; temporary procurement data includes temporary procurement quantity, application department, temporary procurement material requirements, temporary procurement supplier information and temporary procurement cost.

[0020] Methods for processing production supply chain data include: The Z-score algorithm is used to detect outliers in the production supply chain data, and the identified outliers are eliminated; the missing values ​​in the production supply chain data after outliers are eliminated are filled by linear interpolation to obtain the production supply chain parameter data; the production supply chain parameter data is normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby obtaining the normalized production supply chain parameter data.

[0021] The methods for obtaining the comprehensive characteristic dataset of the supply chain include: The principal component analysis is used to reduce the dimension of the normalized production supply chain parameter data to obtain the production supply chain feature data set. The Apriori algorithm is used to mine the association rules of the normalized production supply chain parameter data to obtain the association feature data set. The association feature data set and the production supply chain feature data set are fused through a weighted model to obtain the supply chain comprehensive feature data set. The association feature data set is recorded as , the production supply chain feature dataset is recorded as ; The weighted model is: ;in, is the weight coefficient of the associated feature data set; Weight coefficients for the production supply chain characteristics dataset.

[0022] The method for obtaining the associated feature data set includes: S51, discretize the normalized production supply chain parameter data and convert it into transaction data form; preset the minimum support threshold as , the minimum confidence threshold is ; Initialize the frequent itemsets to empty sets; Transaction data consists of transactions, items, and Boolean values. Each transaction represents an independent record or an event. Each "item" in a transaction represents a feature, parameter, or item. In association rule mining, each item is usually extracted from an attribute (such as temperature, humidity, product, behavior, etc.) or an event (such as purchased goods, purchase frequency, etc.) in the data set. In the form of transaction data, each item is usually represented by a Boolean value (True or False) to indicate whether it appears in the transaction or satisfies a certain condition. True means that the item appears in the transaction or satisfies a certain condition (for example, the value is greater than a certain threshold), and False means that the item does not appear in the transaction or does not meet the condition. The minimum support threshold is a very critical parameter in the Apriori algorithm, which is used to determine which item sets are "frequent". In the process of association rule mining, support measures the frequency of occurrence of an item set in the transaction data set, and the minimum support threshold is used to filter out those item sets with too low frequency. The minimum confidence threshold is used to filter out association rules with too low confidence. Only when the confidence of an association rule is greater than or equal to the set minimum confidence threshold, the association rule is considered valid and can be used for subsequent analysis and application. S52: For each parameter combination, calculate the support in the normalized production supply chain parameter data, and retain the support greater than or equal to the preset minimum support threshold. The parameter combination generates Frequent item sets are generated, and the iteration is repeated until no new frequent item sets are generated; the frequent item sets generated in each iteration are collected to obtain the comprehensive frequent item sets; In the context of association rule mining, "each parameter combination" refers to the set of different parameters that may appear in the normalized production supply chain parameter data; specifically, these parameter combinations include single parameter combinations and multi-parameter combinations; single parameter combinations are basic items, specifically referring to a single parameter in the normalized production supply chain parameter data, such as a specific material name, material specification, production equipment model, etc.; multi-parameter combinations are item sets, which are sets composed of two or more basic items. For example, a parameter combination may include "material name, material specification, production equipment model, etc." ","Material Specifications ” and “Suppliers ”; In data mining and association rule learning, Frequent itemsets are those that contain Itemsets of items, taking 1-item frequent itemsets as an example: "1-item frequent itemsets" are also called single-element frequent itemsets or frequent single-item sets, specifically referring to a single element in a data set whose frequency exceeds the minimum support threshold preset by the user; 1-item refers to a single element in a data set. If the data set is a transaction record, then each individually sold product is an "item" here; S53. For each frequent item set in the comprehensive frequent item set, generate corresponding association rules; for each association rule, calculate its confidence and retain the association rules whose confidence is greater than or equal to the minimum confidence threshold; association rules are mainly used for data mining the association relationship between items, such as "if If occurs, When applied to the normalized production supply chain parameter data, it is possible to mine the potential relationships in the data, such as "If the purchased material , then you may choose a supplier ”; S54. Collect all association rules whose confidences are greater than or equal to a minimum confidence threshold, and then obtain an association feature data set.

[0023] The training methods of the material demand forecasting model include: The data set is divided into training set, validation set and test set to train the model and evaluate the model performance; the sample set is a subset of the data set, each sample set includes the historical supply chain comprehensive feature data set and the corresponding material demand in the next n period of time; Use the deep learning library TensorFlow to build a material demand prediction model; the material demand prediction model includes an input layer, an LSTM layer, and an output layer; the input layer of the model is used to input the historical supply chain comprehensive feature data set; the output layer of the model is used to output the material demand in the next n period of time; the material demand prediction model is an LSTM model; Define the loss function of the model and use the L2 regularized mean square error loss function to measure the difference between the model's predicted value and the true value; use the training set to train the material demand forecasting model and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the material demand forecasting model by calculating the accuracy index; The Adam optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The performance of the model in the prediction task is evaluated using the test set, and the trained material demand prediction model is used to predict the current supply chain comprehensive feature data set to obtain the material demand in the next n period of time.

[0024] Methods for determining whether inventory adjustments are needed based on inventory gaps include: Use RFID technology to obtain real-time inventory data, including current inventory quantity, storage location and material status; Subtract the current inventory from the predicted material demand in the next n periods of time to obtain the inventory gap; preset an inventory gap threshold, and compare the inventory gap with the preset inventory gap threshold; If the inventory gap is less than the preset inventory gap threshold, it is determined that no inventory adjustment is required; if the inventory gap is greater than or equal to the preset inventory gap threshold, it is determined that inventory adjustment is required.

[0025] Methods for obtaining the optimal inventory adjustment plan include: S81. The goal of the preset inventory adjustment plan is to minimize inventory costs (including ordering costs, holding costs, and out-of-stock costs). The objective function is defined as: ;in, is the objective function; is the unit ordering cost; For the Adjustment amount of this type of material; is the unit inventory holding cost; is the unit out-of-stock cost; For the Demand for materials of this type; The index of the material category; is the total number of material categories; S82. Define the position of each spectral particle to represent an inventory adjustment plan. ;in, For the Adjustment amount of this type of material; The total amount of adjustment for the material; S83, Initialization The position of the spectral particles and the corresponding spectral frequency , initialize the spectral particles: ;in, For the The initial position of the spectral particle, the initial position Corresponds to inventory adjustment decisions; is the lower bound of the material inventory adjustment, indicating the minimum possible value of the adjustment (for example, the minimum reduction in inventory); The upper bound of the material inventory adjustment, indicating the maximum possible value of the adjustment (for example, the maximum increase in inventory); is the random number of the initial spectral particle position, ranging from , used to randomly initialize the positions of spectral particles between upper and lower bounds; Initialize the spectral frequencies: ;in, For the The initial frequency of the spectral particles; is the minimum value of the spectrum frequency, which is used to limit the initial frequency range of the spectrum particles; is the maximum value of the spectrum frequency, which is used to limit the initial frequency range of the spectrum particles; is the random number of the initial spectrum particle frequency, ranging from , used to randomly initialize the frequencies of spectral particles between upper and lower bounds; S84. Based on the energy propagation law of the spectrum, the position and velocity of the spectrum particles are updated through the position update formula and the velocity update formula; the position update formula is: ;in, For the spectral particle The position of the iteration (inventory adjustment amount); For the spectral particle The position of the iteration; For the spectral particle The speed of iterations; The speed update formula is: ;in, For the spectral particle The speed of iterations; For the spectral particle The speed of iterations; It represents the momentum factor, controls the contribution of the inertia of the spectral particles to the velocity, and smoothes the moving trajectory of the spectral particles; It is a learning factor that controls the speed at which the spectral particles move in the gradient direction (the descending direction of the objective function); is the gradient of the objective function, indicating the current solution The changing trend in the solution space guides the spectral particles to move toward a better solution; is the spectrum disturbance factor, which controls the influence of spectrum oscillation on speed; It is a spectrum oscillation term, which simulates the spectrum propagation law, introduces dynamic disturbance, and enhances the diversity of spectrum particles; For the spectral particle The temperature of the iteration; S85. The temperature of the spectrum particles during iteration is limited by the temperature attenuation formula. The temperature attenuation formula is: ;in, is the initial temperature of the spectral particle; is the temperature control factor, which represents the control parameter of the temperature decay rate. The value causes the temperature to drop rapidly, while a smaller The value delays the temperature drop; is the current iteration number; Through exponential decay, the temperature can naturally decrease gradually as the number of iterations increases, thus achieving a smooth transition from "randomness" to "stability" in search behavior. For example, the initial temperature of the spectral particle =100; Temperature control factor is 0.1, the current number of iterations is 5, then ; The spectrum perturbation factor is adjusted by the spectrum perturbation adjustment formula Perform dynamic adjustment, and the spectrum disturbance adjustment formula is: ;in, is the initial maximum spectrum disturbance factor; To control the disturbance factor with the number of iterations Adjustment parameters of decay speed; is the total number of spectral particles; The combination of the number of spectral particles and time allows the spectrum disturbance adjustment formula to adapt to spectral particle groups of different sizes while retaining the iterative dynamic adjustment characteristics; For example, the initial maximum spectrum perturbation factor 1; control disturbance factor changes with the number of iterations Adjustment parameters of decay speed is 0.1; the total number of spectral particles is 25; the current number of iterations is 10, then the dynamically adjusted spectrum disturbance factor .

[0026] The momentum factor is restricted by the momentum factor restriction formula; S86, according to the fitness of the spectral particles, that is, the objective function , update the spectrum frequency through the spectrum update formula; the spectrum update formula is: ;in, is the current global optimal fitness; is the spectrum adjustment factor, which controls the sensitivity of the spectrum particles to fitness; For the The spectral particle is The spectral frequency at the iteration; For the The spectral particle is The spectral frequency at the iteration; S87. In each iteration, calculate the fitness of each spectral particle and update the global optimal solution , preset the global optimal solution threshold, when the spectrum optimization algorithm reaches the maximum number of iterations or the global optimal solution Stop when it is less than the preset global optimal solution threshold; the global optimal solution at this time This is the optimal inventory adjustment plan.

[0027] Methods for limiting the momentum factor through the momentum factor restriction formula include: The momentum factor constraint formula is: ;in, is the maximum value of the momentum factor; is the maximum number of iterations; is the absolute value of the objective function gradient; A parameter that adjusts the momentum factor to balance the effect of gradient and particle number; The gradient guides the optimization direction, and the number of particles adjusts the search intensity. The combination of the two improves the overall optimization efficiency. When the gradient is high, reduce the momentum to avoid oscillation. When the gradient is low, increase the momentum moderately to increase the search ability, for example, the maximum value of the momentum factor is 0.9; the maximum number of iterations is 200; the current number of iterations is 50, the absolute value of the objective function gradient is 0.02; the adjustment parameter for the influence of the balance gradient and the number of particles on the momentum factor is 0.1; the total number of spectral particles is 30; then the momentum factor after the constraint is .

[0028] The preset inventory gap threshold is set by the staff. Different inventory gaps are collected through the intelligent monitoring terminal, and the average value of multiple inventory gaps is taken as the preset inventory gap threshold.

[0029] In this embodiment, the objective function explicitly decomposes the inventory cost into three parts: ordering cost, holding cost and out-of-stock cost, which are the core cost sources of inventory management; by considering the adjustment amount and demand amount of each type of material, it is ensured that the objective function can dynamically adapt to multi-variety inventory management; the position of each spectral particle represents an inventory adjustment plan, and this mapping method is intuitive and easy to implement the optimization algorithm; the upper and lower bounds and random numbers are used to generate the initial solution to ensure the diversity of the search space and avoid falling into the local optimal solution; the position update formula combines the current position and speed of the particle and the gradient of the objective function, so that the particle has guidance when searching the solution space; The speed update formula introduces momentum factor, learning factor and spectrum disturbance factor to control inertia, learning ability and dynamic disturbance respectively, thus enhancing the exploration and development ability of the algorithm. The temperature controls the randomness of particles, and through exponential decay, ensures that the algorithm searches the solution space extensively in the early stage and gradually concentrates on the global optimal solution in the later stage. By dynamically adjusting the spectrum disturbance factor, it can adapt to particle swarms of different sizes, while retaining the dynamic adjustment characteristics of the algorithm in the iterative process. It avoids the influence of too large or too small momentum factor on the search trajectory and ensures the stability of particle motion. Through dynamic adjustment of the global optimal fitness and spectrum adjustment factor, the spectral particles can approach the optimal solution faster. It enhances the search ability of the algorithm and the convergence performance of the global optimal solution, which has high practical value for solving complex inventory optimization problems.

[0030] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides an integrated method based on production materials, MRO and temporary procurement, including: S1. Obtain production supply chain data; S2. Process the production supply chain data to obtain a comprehensive supply chain feature data set; S3, using the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; S4. Use RFID technology to obtain real-time inventory data, combine it with the predicted material demand in the next n periods of time to obtain the inventory gap, and determine whether inventory adjustment is needed based on the inventory gap; if inventory adjustment is needed, use the spectral particle optimization algorithm combined with spectrum perturbation and momentum factor restriction mechanism to obtain the optimal inventory adjustment plan; S5. Transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level.

[0031] Since the electronic device introduced in this embodiment is an electronic device used to implement the embodiment of this application based on an integrated platform and method based on production materials, MRO and temporary procurement, based on the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements an electronic device based on an integrated platform and method for production materials, MRO and temporary procurement in the embodiment of this application, it belongs to the scope of protection of this application.

[0032] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0033] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An integrated platform based on production materials, MRO and temporary procurement, characterized by: include: Data acquisition module, used to acquire production supply chain data; The data processing module is used to process the production supply chain data to obtain a comprehensive supply chain feature data set; The demand forecasting module is used to use the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; The inventory optimization module uses RFID technology to obtain real-time inventory data, combines the predicted material demand in the next n periods of time to obtain inventory gaps, and determines whether inventory adjustments are needed based on the inventory gaps; If inventory adjustment is required, the optimal inventory adjustment plan is obtained through the spectral particle optimization algorithm combined with spectrum perturbation and momentum factor restriction mechanism; The decision feedback module is used to transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level; each module is connected by wired and / or wireless means.

2. The integrated platform based on production materials, MRO and temporary procurement according to claim 1 is characterized in that: The production supply chain data includes production material data, MRO parameter data and temporary procurement data; production material data includes material name, material specification, inventory quantity, usage cycle, supplier information and procurement cost; MRO parameter data includes production equipment code, production equipment model, maintenance cycle, failure rate, maintenance record and MRO material inventory; temporary procurement data includes temporary procurement quantity, application department, temporary procurement material requirements, temporary procurement supplier information and temporary procurement cost.

3. The integrated platform based on production materials, MRO and temporary procurement according to claim 2 is characterized in that: The method for processing production supply chain data includes: The Z-score algorithm is used to detect outliers in the production supply chain data, and the identified outliers are eliminated; the missing values ​​in the production supply chain data after outliers are eliminated are filled by linear interpolation to obtain the production supply chain parameter data; the production supply chain parameter data is normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, thereby obtaining the normalized production supply chain parameter data.

4. The integrated platform based on production materials, MRO and temporary procurement according to claim 3 is characterized in that: The method for obtaining the supply chain comprehensive feature data set includes: The normalized production supply chain parameter data is reduced in dimension through principal component analysis to obtain the production supply chain characteristic data set; The Apriori algorithm is used to mine association rules on the normalized production supply chain parameter data to obtain an associated feature data set. The associated feature data set and the production supply chain feature data set are fused through a weighted model to obtain a supply chain comprehensive feature data set. The associated feature data set is recorded as , the production supply chain feature dataset is recorded as ; The weighted model is: ;in, is the weight coefficient of the associated feature data set; Weight coefficients for the production supply chain characteristics dataset.

5. The integrated platform based on production materials, MRO and temporary procurement according to claim 4 is characterized in that: The method for acquiring the associated feature data set includes: S51, discretize the normalized production supply chain parameter data and convert it into transaction data form; preset the minimum support threshold as , the minimum confidence threshold is ; Initialize the frequent itemsets to empty sets; S52: For each parameter combination, calculate the support in the normalized production supply chain parameter data, and retain the support greater than or equal to the preset minimum support threshold. The parameter combination generates Frequent item sets are generated, and the iteration is repeated until no new frequent item sets are generated; the frequent item sets generated in each iteration are collected to obtain the comprehensive frequent item sets; S53, for each frequent item set in the comprehensive frequent item set, generating a corresponding association rule; for each association rule, calculating its confidence and retaining the association rules whose confidence is greater than or equal to the minimum confidence threshold; S54. Collect all association rules whose confidences are greater than or equal to a minimum confidence threshold, and then obtain an association feature data set.

6. The integrated platform based on production materials, MRO and temporary procurement according to claim 5 is characterized in that: The training method of the material demand prediction model includes: The data set is divided into training set, validation set and test set to train the model and evaluate the model performance; the sample set is a subset of the data set, each sample set includes the historical supply chain comprehensive feature data set and the corresponding material demand in the next n period of time; A material demand prediction model is constructed using the deep learning library TensorFlow; the material demand prediction model includes an input layer, an LSTM layer, and an output layer; the input layer of the model is used to input a historical supply chain comprehensive feature data set; the output layer of the model is used to output the material demand in the next n periods of time; the material demand prediction model is an LSTM model; Define the loss function of the model and use the L2 regularized mean square error loss function to measure the difference between the model's predicted value and the true value; use the training set to train the material demand forecasting model and update the model parameters through the back propagation algorithm to minimize the loss function; use the validation set to evaluate the performance of the material demand forecasting model by calculating the accuracy index; The Adam optimization algorithm is selected as the optimizer, and the model is tuned according to the performance feedback of the validation set. The model parameters are adjusted until the performance no longer improves or the preset number of iterations is reached. The performance of the model in the prediction task is evaluated using the test set, and the trained material demand prediction model is used to predict the current supply chain comprehensive feature data set to obtain the material demand in the next n period of time.

7. The integrated platform based on production materials, MRO and temporary procurement according to claim 6 is characterized in that: The method for determining whether inventory adjustment is required based on inventory gap includes: Use RFID technology to obtain real-time inventory data, including current inventory quantity, storage location and material status; Subtract the current inventory from the predicted material demand in the next n periods of time to obtain the inventory gap; preset an inventory gap threshold, and compare the inventory gap with the preset inventory gap threshold; If the inventory gap is less than the preset inventory gap threshold, it is determined that no inventory adjustment is required; if the inventory gap is greater than or equal to the preset inventory gap threshold, it is determined that inventory adjustment is required.

8. The integrated platform based on production materials, MRO and temporary procurement according to claim 7 is characterized in that: The method for obtaining the optimal inventory adjustment plan includes: S81. The goal of the preset inventory adjustment plan is to minimize inventory costs, and the objective function is defined as: ;in, is the objective function; is the unit ordering cost; For the Adjustment amount of this type of material; is the unit inventory holding cost; is the unit out-of-stock cost; For the Demand for materials of this type; The index of the material category; is the total number of material categories; S82. Define the position of each spectral particle to represent an inventory adjustment plan. ;in, For the Adjustment amount of this type of material; The total amount of adjustment for the material; S83, Initialization The position of the spectral particles and the corresponding spectral frequency , initialize the spectral particles: ;in, For the The initial position of each spectral particle; It is the lower bound of the material inventory adjustment amount; It is the upper limit of the material inventory adjustment amount; is the random number of the initial spectral particle position; Initialize the spectral frequencies: ;in, For the The initial frequency of the spectral particles; is the minimum value of the spectral frequency; is the maximum value of the spectral frequency; is the random number of the initial spectrum particle frequency; S84. Based on the energy propagation law of the spectrum, the position and velocity of the spectrum particles are updated through the position update formula and the velocity update formula; the position update formula is: ;in, For the spectral particle The position of the iteration; For the spectral particle The position of the iteration; For the spectral particle The speed of iterations; The speed update formula is: ;in, For the spectral particle The speed of iterations; For the spectral particle The speed of iterations; represents the momentum factor; is the learning factor; is the gradient of the objective function; is the spectrum disturbance factor; is the spectrum oscillation term; For the spectral particle The temperature of the iteration; S85. The temperature of the spectrum particles during iteration is limited by the temperature attenuation formula. The temperature attenuation formula is: ;in, is the initial temperature of the spectral particle; is the temperature control factor; is the current iteration number; The spectrum perturbation factor is adjusted by the spectrum perturbation adjustment formula Perform dynamic adjustment, and the spectrum disturbance adjustment formula is: ;in, is the initial maximum spectrum disturbance factor; To control the disturbance factor with the number of iterations Adjustment parameters of decay speed; is the total number of spectral particles; the momentum factor is restricted by the momentum factor restriction formula; S86. Update the spectrum frequency using a spectrum update formula according to the fitness of the spectrum particle; the spectrum update formula is: ;in, is the current global optimal fitness; is the spectrum adjustment factor; For the The spectral particle is The spectral frequency at the iteration; For the The spectral particle is The spectral frequency at the iteration; S87. In each iteration, calculate the fitness of each spectral particle and update the global optimal solution , preset the global optimal solution threshold, when the spectrum optimization algorithm reaches the maximum number of iterations or the global optimal solution Stop when it is less than the preset global optimal solution threshold; the global optimal solution at this time This is the optimal inventory adjustment plan.

9. The integrated platform based on production materials, MRO and temporary procurement according to claim 8 is characterized in that: The method of limiting the momentum factor by using the momentum factor limiting formula includes: The momentum factor constraint formula is: ;in, is the maximum value of the momentum factor; is the maximum number of iterations; is the absolute value of the objective function gradient; It is a parameter for adjusting the balance between the effect of gradient and particle number on momentum factor.

10. An integrated method based on production materials, MRO and temporary procurement, which is implemented based on the integrated platform based on production materials, MRO and temporary procurement as described in any one of claims 1 to 9, characterized in that: include: S1. Obtain production supply chain data; S2. Process the production supply chain data to obtain a comprehensive supply chain feature data set; S3, using the comprehensive characteristic data of the supply chain as the input of the material demand forecasting model to predict the material demand in the next n periods of time; S4. Use RFID technology to obtain real-time inventory data, combine it with the predicted material demand in the next n periods of time to obtain the inventory gap, and determine whether inventory adjustment is needed based on the inventory gap; If inventory adjustment is required, the optimal inventory adjustment plan is obtained through the spectral particle optimization algorithm combined with spectrum perturbation and momentum factor restriction mechanism; S5. Transmit the optimal inventory adjustment plan to the intelligent monitoring terminal, issue adjustment instructions through the intelligent monitoring terminal, and dynamically adjust the inventory level.

Images