Intelligent Spare Parts Warehouse Inventory Dynamic Monitoring and Replenishment Optimization System

Abstract

The present invention discloses an intelligent spare parts inventory dynamic monitoring and replenishment optimization system, which relates to the technical field of inventory management. It includes collecting environmental parameters, equipment operation data, inventory spare parts images and historical supply data, and performing preprocessing; using artificial intelligence algorithms to analyze the preprocessed environmental parameters, equipment operation data and inventory spare parts images to obtain the spare parts demand and the spare parts inventory; using the spare parts demand and the spare parts inventory to judge the inventory status and generate a difference report; using the preprocessed historical supply data to construct a supply cycle model; performing procurement replenishment according to the difference report, the supply cycle model and the budget to obtain a replenishment record form; using blockchain to store the spare parts inventory, the spare parts demand, the difference report and the replenishment record form on the chain. The present invention dynamically predicts spare parts demand, optimizes the replenishment strategy through data collection and algorithm analysis, and enhances data transparency through blockchain storage.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory management, and particularly to an intelligent spare parts inventory dynamic monitoring and replenishment optimization system. Background Art

[0002] In the prior art in the technical field of inventory management, due to the wide variety and complex structure of modern manufacturing equipment, the demand for spare parts is large and the consumption is frequent. The high price of spare parts and long supply cycle increase the difficulty of inventory management. Traditional inventory management lacks intelligent means and cannot accurately predict the demand for spare parts, resulting in production being affected when the inventory is insufficient and funds and space being wasted when the inventory is excessive.

[0003] The spare parts management process is complex and has a high error rate, unable to quickly respond to equipment failures and emergency needs of the production line, prolonging the equipment repair cycle and affecting production efficiency. There are problems of information islands and lack of transparency in data management, and the process of spare parts transfer cannot be effectively tracked. These problems indicate that the prior art cannot meet the requirements of modern manufacturing for efficient and accurate spare parts management, and there is an urgent need for an intelligent solution. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent spare parts inventory dynamic monitoring and replenishment optimization system to solve the problems in the prior art of being unable to accurately predict the demand for spare parts and reasonably optimize the replenishment strategy.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] The present invention provides an intelligent spare parts inventory dynamic monitoring and replenishment optimization system, which includes a data acquisition module for collecting environmental parameters, equipment operation data, inventory spare parts images and historical supply data, and performing preprocessing;

[0008] A data analysis module for analyzing the preprocessed environmental parameters, equipment operation data and inventory spare parts images by using artificial intelligence algorithms to obtain the demand for spare parts and the inventory of spare parts;

[0009] An inventory status module for judging the inventory status by using the demand for spare parts and the inventory of spare parts, and generating a difference report;

[0010] A supply cycle module for constructing a supply cycle model by using the preprocessed historical supply data;

[0011] A spare parts replenishment module for purchasing and replenishing according to the difference report, the supply cycle model and the budget to obtain a replenishment record form;

[0012] A blockchain module for storing the inventory quantity of spare parts, the demand for spare parts, the discrepancy report, and the replenishment record form on the blockchain using the blockchain.

[0013] As a preferred embodiment of the automated wafer packaging inspection and sorting system of the present invention, wherein: the environmental parameters include temperature, humidity, particulate matter concentration, and noise intensity; the inventory spare part images include the appearance image, packaging image, and stacking image of the spare parts; the equipment operation data includes operating temperature, load, mechanical vibration data, energy consumption data, alarm information, and fault records; the historical supply data includes the time, cycle, number of delays, and production capacity of the supplier for the supplied spare parts; the preprocessing includes performing data cleaning, data smoothing and noise reduction, data normalization, and time series synchronization on the environmental parameters, equipment operation data, and historical supply data respectively, and performing format conversion, image enhancement, noise removal, and image normalization on the inventory spare part images.

[0014] As a preferred embodiment of the automated wafer packaging inspection and sorting system of the present invention, wherein the specific steps for performing format conversion, image enhancement, noise removal, and image normalization on the inventory spare part images are as follows:

[0015] Use the PIL library to convert the inventory spare part image to a grayscale image format to obtain the inventory spare part image in grayscale image format.

[0016] Adopt gamma transformation and histogram stretching to enhance the brightness and contrast of the inventory spare part image in grayscale image format to obtain the inventory spare part image after image enhancement.

[0017] Process the inventory spare part image after image enhancement through rotation, flipping, and cropping to obtain an expanded image dataset.

[0018] Use median filtering and histogram equalization to optimize the expanded image dataset, and normalize the pixel values through numerical mapping to obtain the preprocessed inventory spare part image.

[0019] As a preferred embodiment of the automated wafer packaging inspection and sorting system of the present invention, wherein the specific steps for analyzing the preprocessed environmental parameters using an artificial intelligence algorithm to obtain the dynamic influence coefficient of environmental changes on spare part demand are as follows:

[0020] Divide the preprocessed environmental parameters into an environmental training set, an environmental test set, and an environmental validation set.

[0021] Adopt the ARIMA model as the artificial intelligence algorithm for analyzing the preprocessed environmental parameters, expressed as:

[0022] x t = φ1x t-1 + φ2x t-2+…+φ p x t-p +θ1∈ t-1 +θ2∈ t-2 +…+θ q ∈ t-q +

[0023] ∈ t ;

[0024] where x t is the environmental parameter value at time point t, t is the time point, φ1 is the influence weight of the environmental parameter value at time point t - 1 on the environmental parameter value at time point t, x t-1 is the environmental parameter value at time point t - 1, φ2 is the influence weight of the environmental parameter value at time point t - 2 on the environmental parameter value at time point t, x t-2 is the environmental parameter value at time point t - 2, φ p is the influence weight of the environmental parameter value at time point t - p on the environmental parameter value at time point t, x t-p is the environmental parameter value at time point t - p, θ1 is the influence weight of the random error value at time point t - 1 on the environmental parameter value at time point t, ∈ t-1 is the random error value at time point t - 1, θ2 is the influence weight of the random error value at time point t - 2 on the environmental parameter value at time point t, ∈ t-2 is the random error value at time point t - 2, θ q is the influence weight of the random error value at time point t - q on the environmental parameter value at time point t, ∈ t-q is the random error value at time point t - q, ∈ t is the prediction error value;

[0025] Train and optimize the ARIMA model using the environmental training set, environmental test set, environmental validation set, and grid search to obtain the changing trend of environmental parameters;

[0026] Process the changing trend of environmental parameters using the dynamic impact analysis algorithm to obtain the dynamic impact coefficient of environmental parameters on spare part requirements, expressed as,

[0027]

[0028] where η is the dynamic impact coefficient, N is the time window length, k is the time step index, e is the base of the natural logarithm, α is the time decay coefficient, X t-k is the environmental parameter value at time point t - k, σ x is the standard deviation of the environmental parameter, σ is the standard deviation of the random error.

[0029] As a preferred solution of the automated wafer packaging inspection and sorting system described in the present invention, the following steps are taken to analyze the preprocessed equipment operation data and dynamic influence coefficients using artificial intelligence algorithms to obtain the spare part demand:

[0030] Process the preprocessed equipment operation data using the FFT feature extraction algorithm to obtain frequency domain feature data;

[0031] Use the feature selection algorithm to screen the frequency domain feature data to obtain the key frequency domain features;

[0032] Use the random forest health assessment model to analyze the preprocessed equipment operation data and dynamic influence coefficients, expressed as

[0033]

[0034] where H is the health status evaluation value of the equipment, W is the total number of decision trees in the random forest, u is the index of the decision tree in the random forest, and V u is the health status prediction result of the u-th decision tree for the equipment operation characteristic value, and F b is the b-th equipment operation characteristic value, and b is the index of the equipment operation characteristic value;

[0035] Based on the random forest health assessment model, analyze the key frequency domain features and dynamic influence coefficients to obtain the equipment health status assessment result, expressed as

[0036]

[0037] where H η is the equipment health status evaluation value, ω u is the weight of the decision tree, max is the maximum value function, is the square of the regression weight of the i-th frequency domain feature, is the square of the i-th key frequency domain feature value, and η is the dynamic influence coefficient;

[0038] Use the regression model to process the equipment health status assessment result to obtain the remaining life of the equipment components, expressed as

[0039]

[0040] where R is the remaining life of the equipment components, b0 is the intercept of the regression model, m is the number of input features, and β j is the regression coefficient of the j-th feature in the regression model, and E j is the j-th feature value of the equipment operation state, and j is the index of the equipment operation state feature value;

[0041] According to the remaining life of equipment parts, the demand for spare parts in stock is predicted, and the demand for spare parts is obtained, which is expressed as:

[0042]

[0043] Where D is the demand for spare parts, M is the total number of parts, and λ h is the failure rate of the hth component, R is the remaining life of the equipment component, μ is the environmental impact coefficient, S h is the safety stock of the hth component, and c is a very small positive number.

[0044] As a preferred solution of the automated wafer packaging inspection and sorting system of the present invention, wherein: the pre-processed inventory spare parts image is analyzed using an artificial intelligence algorithm to obtain the spare parts inventory quantity, the specific steps are as follows:

[0045] Label the preprocessed inventory spare parts images and divide them into image training set, image test set and image verification set;

[0046] The convolutional neural network is trained using the image training set, image test set, and image verification set to obtain a spare parts image classification model;

[0047] The spare parts image classification model is used to process the inventory spare parts images to obtain the spare parts inventory quantity.

[0048] As a preferred solution of the automated wafer packaging inspection and sorting system of the present invention, the inventory status is judged by using the spare parts inventory and spare parts demand, and a difference report is generated. The specific steps are as follows:

[0049] Determine the insufficient inventory threshold and the excess inventory threshold based on spare parts inventory, spare parts demand and industry experience;

[0050] Use the insufficient inventory threshold and the excessive inventory threshold to compare and analyze the spare parts inventory and spare parts demand;

[0051] When the inventory level falls below the low inventory threshold, it is recorded as needing replenishment in the variance report;

[0052] When the inventory level is between the insufficient inventory threshold and the excessive inventory threshold, it is recorded in the variance report as not requiring replenishment;

[0053] When the inventory level is above the excess inventory threshold, it is recorded as a need for return in the variance report;

[0054] Obtain inventory variance data and generate variance reports.

[0055] As a preferred solution of the automated wafer packaging inspection and sorting system described in the present invention, the following steps are taken: Using the preprocessed historical supply data, a supply cycle model is constructed, and the specific steps are as follows:

[0056] Divide the preprocessed historical supply data into a supply training set, a supply test set, and a supply validation set;

[0057] Use the supply training set and the supply test set to train the long short-term memory neural network, and optimize the parameters through the supply validation set to obtain the supply cycle model, expressed as

[0058]

[0059] T = f(S, E, D′);

[0060] where T is the predicted supply cycle, f is the long short-term memory neural network, S is the supply historical data, E is the environmental factor, D′ is the demand fluctuation value, D t is the spare part demand quantity at the t-th moment, is the average value of the spare part demand quantity, and O is the length of the time series.

[0061] As a preferred solution of the automated wafer packaging inspection and sorting system described in the present invention, the following steps are taken: According to the difference report, combined with the supply cycle model and the budget, procurement replenishment is carried out to obtain a replenishment record form, and the specific steps are as follows:

[0062] According to the difference report, combined with the supply cycle model and the budget, procurement replenishment is carried out to obtain a replenishment record form, and the specific steps are as follows:

[0063] Calculate according to the difference report and the budget, expressed as

[0064]

[0065] where C is the total procurement cost, r is the total number of spare part types, a is the spare part number, I a is the unit price of the a-th spare part, J a is the demand quantity of the a-th spare part, w a is, g a is the supply cost function of the a-th spare part, and T is the predicted supply cycle;

[0066] Based on the total procurement cost, obtain the spare part list that needs to be replenished;

[0067] Analyze the spare part list using the supply cycle model, expressed as

[0068]

[0069] where P ais the replenishment priority of the a-th spare part, J a is the demand quantity of the ath type of spare parts, T is the predicted supply cycle, U a is the remaining inventory of the a-th spare part, σ a is the standard deviation of the demand for the ath spare part, c is a very small positive number, γ is the inventory elasticity coefficient of the replenishment priority, S′ a is the safety stock of type a spare part;

[0070] Obtain the replenishment order of spare parts based on replenishment priority;

[0071] Use the replenishment sequence to place orders, obtain replenishment order data, and generate a replenishment record table.

[0072] As a preferred solution of the automated wafer packaging inspection and sorting system of the present invention, the spare parts inventory, spare parts demand, difference report and replenishment record table are stored on the blockchain. The specific steps are as follows:

[0073] The Merkle tree structure of the blockchain is used to organize the spare parts inventory, spare parts demand, difference report and replenishment record table data, and generate a unique hash value for each set of data;

[0074] The hashed data is packaged with information such as timestamp, previous block hash value, block number, etc. into a block to obtain block data;

[0075] Use a dynamic voting mechanism to regularly adjust the weight of authorized nodes;

[0076] The PoA consensus mechanism is used to process the block data, and the authorized node verifies the legal status of the block to obtain the block data that has passed the consensus verification;

[0077] The block data verified by consensus is added to the blockchain to form a chain structure.

[0078] The beneficial effects of the present invention are as follows: the present invention realizes accurate analysis of equipment operation data, environmental parameters and inventory spare parts images through data acquisition modules and artificial intelligence algorithms, can dynamically predict spare parts demand and inventory, and improve the scientificity and accuracy of inventory management. Based on the supply cycle model and replenishment priority algorithm, the spare parts procurement and replenishment strategy is optimized to avoid production interruption caused by insufficient inventory or waste of funds and space caused by excess inventory. The present invention introduces blockchain technology to store spare parts inventory, demand, difference reports and replenishment record tables on the chain, thereby enhancing the transparency and traceability of data and effectively solving the problems of information islands and irregular data management in traditional inventory management. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0080] Figure 1 It is a schematic diagram of the intelligent spare parts inventory dynamic monitoring and replenishment optimization system in Embodiment 1;

[0081] Figure 2 It is a judgment diagram of the inventory status in Embodiment 1. Detailed Embodiments

[0082] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0083] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0084] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0085] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides an intelligent spare parts inventory dynamic monitoring and replenishment optimization system, including a data acquisition module, a data analysis module, an inventory status module, a supply cycle module, a spare parts replenishment module, and a blockchain module.

[0086] A data acquisition module for collecting environmental parameters, equipment operation data, inventory spare part images, and historical supply data, and performing preprocessing; a data analysis module for analyzing the preprocessed environmental parameters, equipment operation data, and inventory spare part images using artificial intelligence algorithms to obtain spare part demand and spare part inventory; an inventory status module for judging the inventory status using the spare part demand and spare part inventory, and generating a difference report; a supply cycle module for constructing a supply cycle model using the preprocessed historical supply data; a spare part replenishment module for purchasing and replenishing according to the difference report, supply cycle model, and budget to obtain a replenishment record form; a blockchain module for storing the spare part inventory, spare part demand, difference report, and replenishment record form on the blockchain using blockchain.

[0087] Specifically, collecting environmental parameters, equipment operation data, inventory spare part images, and historical supply data, and performing preprocessing includes the following steps.

[0088] The environmental parameters include temperature, humidity, particulate matter concentration, and noise intensity; the inventory spare part images include the appearance image, packaging image, and stacking image of the spare parts; the equipment operation data includes operating temperature, load, mechanical vibration data, energy consumption data, alarm information, and fault records; the historical supply data includes the time, cycle, number of delays, and production capacity of the supplier for supplying spare parts; the preprocessing includes performing data cleaning, data smoothing and noise reduction, data normalization, and time series synchronization on the environmental parameters, equipment operation data, and historical supply data respectively, and performing format conversion, image enhancement, noise removal, and image normalization on the inventory spare part images.

[0089] It should be noted that data acquisition and preprocessing lay the foundation for the intelligent analysis of the system, improve the quality and consistency of the data, ensure the efficient operation of subsequent demand forecasting, supply cycle modeling, and inventory optimization algorithms, and ultimately achieve precise management and scientific decision-making.

[0090] Use the PIL library to convert the inventory spare part image to a grayscale image format to obtain an inventory spare part image in grayscale image format.

[0091] Use gamma transformation and histogram stretching to enhance the brightness and contrast of the inventory spare part image in grayscale image format to obtain an inventory spare part image with enhanced image. Further, through the convert(L) method of the PIL library, convert the color inventory spare part image to a grayscale image format, remove the color information, retain the brightness information of the image, reduce the complexity of the image data, and provide a more efficient input data format for subsequent image enhancement and feature extraction.

[0092] Process the inventory spare part images enhanced by rotation, flipping, and cropping to obtain an augmented image dataset. Further, enhance the details of the inventory spare part images, especially the visibility of the dark or highlighted areas, by adjusting the non-linear mapping of the gray values. Perform linear stretching on the pixel intensity distribution of the images to expand the gray value range from the original narrow interval (e.g., 50 - 200) to the full range (e.g., 0 - 255), improve the contrast, make the images clearer, and facilitate subsequent feature extraction and classification. Rotate the images at random or fixed angles (e.g., ±90°, 180°) to enhance data diversity and simulate the possible angular changes of spare part stacking in the actual scenario. Perform horizontal flipping, vertical flipping, or diagonal flipping to increase the symmetry features of the data samples. Crop the images randomly or in fixed regions to generate local images of different sizes, enhance the model's recognition ability of the partial features of the spare parts, and improve the classification robustness.

[0093] Optimize the augmented image dataset using median filtering and histogram equalization, and normalize the pixel values through numerical mapping to obtain the preprocessed inventory spare part images. Further, perform denoising on the images, replace the pixel values using the median filtering algorithm, smooth the noise points in the images, while maintaining the image edge details and preventing blurring. Perform equalization processing on the gray distribution of the images to enhance the global contrast of the images, highlight the details of the spare part feature regions, and provide a clearer image structure for feature extraction. Scale the image pixel values proportionally between 0 and 1 to reduce the influence of the numerical amplitude, facilitate the rapid convergence of the deep learning model, and enable more efficient calculation.

[0094] It should be noted that data acquisition and preprocessing are the basis for the intelligent analysis of the system, ensuring the efficient operation of subsequent algorithms and improving the accuracy of management and decision-making.

[0095] Use artificial intelligence algorithms to analyze the preprocessed environmental parameters to obtain the dynamic influence coefficient of environmental changes on spare part requirements, including the following steps.

[0096] Divide the preprocessed environmental parameters into an environmental training set, an environmental test set, and an environmental validation set. Further, the ratio of the environmental training set, the environmental test set, and the environmental validation set is 7:2:1.

[0097] Adopt the ARIMA model as the artificial intelligence algorithm for analyzing the preprocessed environmental parameters, expressed as

[0098] x t = φ1x t-1 + φ2x t-2 +…+ φ p x t-p + θ1∈ t-1 + θ2∈ t-2 +…+ θq ∈ t-q +

[0099] ∈ t ;

[0100] where x t is the environmental parameter value at time point t, t is the time point, φ1 is the influence weight of the environmental parameter value at time point t - 1 on the environmental parameter value at time point t, x t-1 is the environmental parameter value at time point t - 1, φ2 is the influence weight of the environmental parameter value at time point t - 2 on the environmental parameter value at time point t, x t-2 is the environmental parameter value at time point t - 2, φ p is the influence weight of the environmental parameter value at time point t - p on the environmental parameter value at time point t, x t-p is the environmental parameter value at time point t - p, θ1 is the influence weight of the random error value at time point t - 1 on the environmental parameter value at time point t, ∈ t-1 is the random error value at time point t - 1, θ2 is the influence weight of the random error value at time point t - 2 on the environmental parameter value at time point t, ∈ t-2 is the random error value at time point t - 2, θ q is the influence weight of the random error value at time point t - q on the environmental parameter value at time point t, ∈ t-q is the random error value at time point t - q, ∈ t is the prediction error value.

[0101] The ARIMA model is trained and optimized using the environmental training set, environmental test set, environmental validation set, and grid search to obtain the changing trend of environmental parameters. Further, the environmental training set is input into the ARIMA model, and the model parameters are optimized by the maximum likelihood estimation method. During the training process, the grid search method is used to traverse different combinations of the autoregressive order, differencing order, and moving average order, and the parameter combination that minimizes the error of the test set is selected.

[0102] The dynamic impact analysis algorithm is used to process the changing trend of environmental parameters to obtain the dynamic impact coefficient of environmental parameters on spare part demand, denoted as,

[0103]

[0104] where η is the dynamic impact coefficient, N is the time window length, k is the time step index, e is the base of the natural logarithm, α is the time decay coefficient, X t-k is the environmental parameter value at time point t - k, σ x is the standard deviation of the environmental parameter, and σ is the standard deviation of the random error.

[0105] It should be noted that the ARIMA model is used to analyze the time series change trend of environmental parameters and predict the dynamic impact of the future environment on spare part requirements. According to the environmental change trend, the impact on spare part requirements is quantified, and the spare part requirement prediction model is dynamically adjusted.

[0106] The artificial intelligence algorithm is used to analyze the preprocessed equipment operation data and the dynamic impact coefficient to obtain the spare part demand quantity, including the following steps.

[0107] The FFT feature extraction algorithm is used to process the preprocessed equipment operation data to obtain the frequency domain feature data. Further, the fast Fourier transform is performed on the preprocessed equipment operation data (such as vibration data, energy consumption data, load data, etc.) to convert the time domain signal into a frequency domain signal, so as to extract the frequency characteristics in the equipment operation state. This can reveal the periodic laws and hidden abnormal signal characteristics in the equipment operation.

[0108] The feature selection algorithm is used to screen the frequency domain feature data to obtain the key frequency domain features. Further, the frequency domain feature data (such as main frequency, spectral energy, peak frequency, etc.) is screened, the key features that have a significant impact on the equipment operation state and health assessment are retained, the redundant or irrelevant features are removed, the calculation complexity is reduced, and the model performance is improved.

[0109] The random forest health assessment model is used to analyze the preprocessed equipment operation data and the dynamic impact coefficient, which is expressed as

[0110]

[0111] where H is the health status assessment value of the equipment, W is the total number of decision trees in the random forest, u is the index of the decision tree in the random forest, V u is the health status prediction result of the u-th decision tree for the equipment operation characteristic value, F b is the b-th equipment operation characteristic value, and b is the index of the equipment operation characteristic value.

[0112] Based on the random forest health assessment model, the key frequency domain features and the dynamic impact coefficient are analyzed to obtain the equipment health status assessment result, which is expressed as

[0113]

[0114] where H η is the equipment health status assessment value, ω u is the weight of the decision tree, max is the maximum value function, is the square of the regression weight of the i-th frequency domain feature, is the square of the i-th key frequency domain feature value, and η is the dynamic impact coefficient.

[0115] The regression model is used to process the evaluation results of the equipment health status, and the remaining life of the equipment components is obtained, expressed as,

[0116]

[0117] where R is the remaining life of the equipment components, b0 is the intercept of the regression model, m is the number of input features, and β j is the regression coefficient of the j-th feature in the regression model, and E j is the j-th eigenvalue of the equipment operating state, and j is the index of the equipment operating state eigenvalue.

[0118] The demand for inventory spare parts is predicted based on the remaining life of the equipment components, and the spare parts demand is obtained, expressed as,

[0119]

[0120] where D is the spare parts demand, M is the total number of components, and λ h is the failure rate of the h-th component, R is the remaining life of the equipment components, μ is the environmental impact coefficient, and S h is the safety inventory of the h-th component, and c is a very small positive number.

[0121] It should be noted that based on the random forest algorithm, combined with the equipment operation characteristics and dynamic impact coefficients, the health status of the equipment is predicted, and further the remaining life of the components is estimated through the regression model. According to the remaining life, failure rate and safety inventory level of the equipment components, the spare parts demand is predicted.

[0122] The artificial intelligence algorithm is used to analyze the preprocessed inventory spare parts images to obtain the spare parts inventory, including the following steps,

[0123] The preprocessed inventory spare parts images are labeled and divided into an image training set, an image test set and an image validation set. Further, according to the spare parts category, location and quantity, the inventory spare parts images are labeled to generate a labeling file (such as XML or JSON format) containing category labels and quantity information. The image data set is divided in proportion (such as 8:1:1 or 7:2:1).

[0124] The convolutional neural network is trained using the image training set, the image test set and the image validation set to obtain a spare parts image classification model. Further, the training set is used to train the convolutional neural network to learn the mapping relationship between the image features and the categories. The test set is used to test the classification accuracy of the model for unseen images and evaluate the generalization ability. The validation set is used to adjust the network hyperparameters (such as learning rate, number of layers, etc.) during the training process to optimize the model performance.

[0125] The spare part image classification model is used to process the inventory spare part images to obtain the spare part inventory quantity. Further, the trained convolutional neural network is used to extract features and classify the spare part images to identify the spare part categories and quantities, improving the accuracy and efficiency of inventory identification.

[0126] It should be noted that the data analysis module realizes the correlation analysis of equipment operation and environmental changes, evaluates the spare part inventory through image processing, and provides accurate demand prediction and inventory management data.

[0127] The inventory status is judged using the spare part inventory quantity and the spare part demand quantity, and a difference report is generated, including the following steps.

[0128] According to the spare part inventory quantity, the spare part demand quantity, and industry experience, the inventory shortage threshold and the inventory excess threshold are determined. The spare part inventory quantity and the spare part demand quantity are compared and analyzed using the inventory shortage threshold and the inventory excess threshold. When the inventory quantity is lower than the inventory shortage threshold, it is recorded in the difference report that replenishment is needed. When the inventory quantity is between the inventory shortage threshold and the inventory excess threshold, it is recorded in the difference report that replenishment is not needed. When the inventory quantity is higher than the inventory excess threshold, it is recorded in the difference report that a return is needed. The inventory difference data is obtained, and a difference report is generated.

[0129] It should be noted that the difference report provides data support for inventory optimization, ensures a reasonable inventory level, and avoids the problem of excessive or insufficient spare part backlogs.

[0130] Using the preprocessed historical supply data, a supply cycle model is constructed, including the following steps.

[0131] The preprocessed historical supply data is divided into a supply training set, a supply test set, and a supply validation set. Further, the ratio is 7:2:1.

[0132] The long short-term memory neural network is trained using the supply training set and the supply test set, and the parameters are optimized through the supply validation set to obtain the supply cycle model, expressed as

[0133]

[0134] T = f(S, E, D′);

[0135] where T is the predicted supply cycle, f is the long short-term memory neural network, S is the supply historical data, E is the environmental factor, D′ is the demand fluctuation value, D t is the spare part demand quantity at the t-th moment, is the average value of the spare part demand quantity, and O is the length of the time series.

[0136] It should be noted that the supply cycle model provides a reliable time basis for the procurement replenishment plan and reduces the risks caused by delayed supply.

[0137] According to the variance report, combined with the supply cycle model and the budget, conduct procurement replenishment to obtain a replenishment record form, including the following steps.

[0138] Calculate according to the variance report and the budget, expressed as

[0139]

[0140] Among them, C is the total procurement cost, r is the total number of spare part types, a is the spare part number, I a is the unit price of the a-th spare part, J a is the demand quantity of the a-th spare part, w a is, g a is the supply cost function of the a-th spare part, and T is the predicted supply cycle.

[0141] Based on the total procurement cost, obtain the list of spare parts that need to be replenished.

[0142] Analyze the spare part list using the supply cycle model, expressed as

[0143]

[0144] Among them, P a is the replenishment priority of the a-th spare part, J a is the demand quantity of the a-th spare part, T is the predicted supply cycle, U a is the remaining inventory of the a-th spare part, σ a is the demand standard deviation of the a-th spare part, c is a very small positive number, γ is the inventory elasticity coefficient of the replenishment priority, and S′ a is the safety inventory of the a-th spare part.

[0145] Based on the replenishment priority, obtain the replenishment order of the spare parts. Further, by combining the supply cycle model with the demand quantity and remaining inventory of the spare part list, calculate the replenishment priority of each spare part and evaluate its urgency under the current strategy.

[0146] Use the replenishment order to place an order operation, obtain the replenishment order data, and generate a replenishment record form.

[0147] It should be noted that under the budget constraint, by optimizing the replenishment order and quantity, the supply chain efficiency is maximized.

[0148] Use blockchain to store the spare part inventory, spare part demand, variance report, and replenishment record form on the chain, including the following steps.

[0149] Organize the data of spare part inventory, spare part demand, discrepancy report, and replenishment record form using the Merkle tree structure of blockchain to generate a unique hash value for each piece of data. Further, use the hash values of the spare part inventory, demand, discrepancy report, and replenishment record form as leaf nodes, and recursively calculate the hash value of the parent node to finally generate a unique root hash value, ensuring data integrity and immutability. Use the SHA-256 algorithm to generate the hash value of each piece of data and store it in the block, providing a basis for data traceability and verification.

[0150] Pack the hashed data together with information such as timestamp, previous block hash value, and block number into a block to obtain block data. Adopt a dynamic voting mechanism to regularly adjust the weights of authorized nodes. Use the PoA consensus mechanism to perform consensus processing on the block data, and have the authorized nodes verify the legal status of the block to obtain the block data that passes the consensus verification. Add the block data that passes the consensus verification to the blockchain to form a chain structure.

[0151] It should be noted that the blockchain module ensures the storage security and traceability of spare part inventory, demand, discrepancy report, and replenishment records. Improve data transparency and security, and provide a reliable traceability mechanism for spare part management.

[0152] In summary, through the data acquisition module and artificial intelligence algorithm, the present invention realizes the accurate analysis of equipment operation data, environmental parameters, and inventory spare part images, can dynamically predict spare part demand and inventory, and improve the scientificity and accuracy of inventory management. Based on the supply cycle model and replenishment priority algorithm, the spare part procurement and replenishment strategies are optimized, avoiding production interruptions caused by insufficient inventory or waste of funds and space caused by overstock. By introducing blockchain technology, the present invention stores the spare part inventory, demand, discrepancy report, and replenishment record form on the chain, enhancing data transparency and traceability, and effectively solving the problems of information silos and irregular data management in traditional inventory management.

[0153] 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 preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. Intelligent spare parts inventory dynamic monitoring and replenishment optimization system, characterized in that: including a data acquisition module, configured to collect environmental parameters, equipment operation data, inventory spare part images, and historical supply data, and perform preprocessing; a data analysis module, configured to analyze the preprocessed environmental parameters, equipment operation data, and inventory spare part images using artificial intelligence algorithms to obtain spare part demand quantities and spare part inventory quantities; dividing the preprocessed environmental parameters into an environmental training set, an environmental test set, and an environmental validation set; using the ARIMA model as the artificial intelligence algorithm for analyzing the preprocessed environmental parameters, denoted as x t = φ1x t-1 + φ2x t-2 + … + φ p x t-p + θ1 ∈ t-1 + θ2 ∈ t-2 + … + θ q ∈ t-q + ∈ t ; where x t is the environmental parameter value at time point t, t is the time point, φ1 is the influence weight of the environmental parameter value at time point t - 1 on the environmental parameter value at time point t, x t-1 is the environmental parameter value at time point t - 1, φ2 is the influence weight of the environmental parameter value at time point t - 2 on the environmental parameter value at time point t, x t-2 is the environmental parameter value at time point t - 2, φ p is the influence weight of the environmental parameter value at time point t - p on the environmental parameter value at time point t, x t-p is the environmental parameter value at time point t - p, θ1 is the influence weight of the random error value at time point t - 1 on the environmental parameter value at time point t, ∈ t-1 is the random error value at time point t - 1, θ2 is the influence weight of the random error value at time point t - 2 on the environmental parameter value at time point t, ∈ t-2 is the random error value at time point t - 2, θ q is the influence weight of the random error value at time point t - q on the environmental parameter value at time point t, ∈ t-q is the random error value at time point t - q, ∈ t is the prediction error value; training and optimizing the ARIMA model using the environmental training set, the environmental test set, the environmental validation set, and grid search to obtain the changing trend of environmental parameters; processing the changing trend of environmental parameters using a dynamic impact analysis algorithm to obtain the dynamic impact coefficient of environmental parameters on spare part demand, denoted as where η is the dynamic influence coefficient, N is the time window length, k is the time step index, e is the base of the natural logarithm, α is the time decay coefficient, X t-k is the environmental parameter value at time point t - k, σ x is the standard deviation of the environmental parameter, and σ is the standard deviation of the random error; annotating the preprocessed inventory spare part images and dividing them into an image training set, an image test set, and an image validation set; training a convolutional neural network using the image training set, the image test set, and the image validation set to obtain a spare part image classification model; processing the inventory spare part images using the spare part image classification model to obtain the spare part inventory quantity; an inventory status module, configured to judge the inventory status using the spare part demand quantity and the spare part inventory quantity, and generate a difference report; a supply cycle module, configured to construct a supply cycle model using the preprocessed historical supply data; a spare part replenishment module, configured to perform procurement replenishment according to the difference report, the supply cycle model, and the budget to obtain a replenishment record form; a blockchain module, configured to use blockchain to store the spare part inventory quantity, the spare part demand quantity, the difference report, and the replenishment record form on the chain.

2. The intelligent spare parts inventory dynamic monitoring and replenishment optimization system according to claim 1, wherein: The environmental parameters include temperature, humidity, particulate matter concentration, and noise intensity; the inventory spare part images include the appearance image, the packaging image, and the stacking image of the spare parts; the equipment operation data includes operating temperature, load, mechanical vibration data, energy consumption data, alarm information, and fault records; the historical supply data includes the time, cycle, number of delays, and production capacity of the supplier for supplying spare parts; the preprocessing includes performing data cleaning, data smoothing and noise reduction, data normalization, and time series synchronization on the environmental parameters, the equipment operation data, and the historical supply data respectively, and performing format conversion, image enhancement, noise removal, and image normalization on the inventory spare part images.

3. The intelligent spare parts inventory dynamic monitoring and replenishment optimization system according to claim 2, wherein: Performing format conversion, image enhancement, noise removal, and image normalization on the inventory spare part images, the specific steps are as follows using the PIL library to convert the inventory spare part images into grayscale image format to obtain the inventory spare part images in grayscale image format; performing brightness enhancement and contrast enhancement on the inventory spare part images in grayscale image format using gamma transformation and histogram stretching to obtain the inventory spare part images with enhanced images; processing the inventory spare part images with enhanced images through rotation, flipping, and cropping to obtain an expanded image data set; optimizing the expanded image data set using median filtering and histogram equalization, and normalizing the pixel values through numerical mapping to obtain the preprocessed inventory spare part images.

4. The intelligent spare parts library inventory dynamic monitoring and replenishment optimization system according to claim 3, characterized in that: Analyze the preprocessed equipment operation data and dynamic influence coefficients using artificial intelligence algorithms to obtain the spare parts demand. The specific steps are as follows: Process the preprocessed equipment operation data using the FFT feature extraction algorithm to obtain frequency-domain feature data; Use the feature selection algorithm to screen the frequency-domain feature data to obtain the key frequency-domain features; Use the random forest health assessment model to analyze the preprocessed equipment operation data and dynamic influence coefficients, expressed as: Among them, H is the health status evaluation value of the device, W is the total number of decision trees in the random forest, u is the index of the decision tree in the random forest, and V u is the health status prediction result of the u-th decision tree for the device operation characteristic value, and F b is the b-th device operation characteristic value, and b is the index of the device operation characteristic value; Based on the random forest health assessment model, analyze the key frequency-domain features and dynamic influence coefficients to obtain the equipment health status assessment results, expressed as: Among them, H η is the evaluation value of the device health status, ω u is the weight of the decision tree, max is the maximum value function, is the square of the regression weight of the i-th frequency domain feature, is the square of the i-th key frequency domain feature value, and η is the dynamic influence coefficient; Use the regression model to process the equipment health status assessment results to obtain the remaining life of the equipment components, expressed as: Wherein, R is the remaining life of the equipment component, b0 is the intercept of the regression model, m is the number of input features, and β j is the regression coefficient of the j-th feature in the regression model, and E j is the j-th eigenvalue of the equipment operating state, and j is the index of the eigenvalue of the equipment operating state; Predict the inventory spare parts demand based on the remaining life of the equipment components to obtain the spare parts demand, expressed as: Among them, D is the spare part demand, M is the total number of components, λ h is the failure rate of the h-th component, R is the remaining life of the equipment components, μ is the environmental impact coefficient, S h is the safety stock of the h-th component, and c is an extremely small positive number.

5. The intelligent spare parts library inventory dynamic monitoring and replenishment optimization system according to claim 4, characterized in that: Judge the inventory status using the spare parts inventory and spare parts demand, and generate a difference report. The specific steps are as follows: Determine the inventory shortage threshold and inventory surplus threshold according to the spare parts inventory, spare parts demand, and industry experience; Use the inventory shortage threshold and inventory surplus threshold to conduct a comparative analysis of the spare parts inventory and spare parts demand; When the inventory is lower than the inventory shortage threshold, record in the difference report that replenishment is required; When the inventory is between the inventory shortage threshold and the inventory surplus threshold, record in the difference report that replenishment is not required; When the inventory is higher than the inventory surplus threshold, record in the difference report that a return is required; Obtain the inventory difference data and generate a difference report.

6. The intelligent spare parts library inventory dynamic monitoring and replenishment optimization system according to claim 5, characterized in that: Use the preprocessed historical supply data to construct a supply cycle model. The specific steps are as follows: Divide the preprocessed historical supply data into a supply training set, a supply test set, and a supply validation set; Use the supply training set and the supply test set to train the long short-term memory neural network, and optimize the parameters through the supply validation set to obtain the supply cycle model, expressed as: T = f(S, E, D′); Among them, T is the predicted supply cycle, f is the long short-term memory neural network, S is the supply historical data, E is the environmental factor, D′ is the demand fluctuation value, and D t is the spare part demand at the t-th moment, is the average value of the spare part demand, and O is the length of the time series.

7. The intelligent spare parts library inventory dynamic monitoring and replenishment optimization system according to claim 6, characterized in that: According to the difference report, combine the supply cycle model and the budget to conduct procurement replenishment to obtain a replenishment record form. The specific steps are as follows: Calculate according to the difference report and the budget, expressed as: Among them, C is the total procurement cost, r is the total number of spare part types, a is the spare part number, I a is the unit price of the a-th spare part, J a is the demand quantity of the a-th spare part, g a is the supply cost function of the a-th spare part, and T is the predicted supply cycle; Based on the total procurement cost, obtain the list of spare parts that need to be replenished; Analyze the spare parts list using the supply cycle model, expressed as: Among them, P a is the replenishment priority of the a-th spare part, J a is the demand quantity of the ath type of spare parts, T is the predicted supply cycle, U a is the remaining inventory of the a-th spare part, σ a is the standard deviation of the demand for the ath spare part, c is a very small positive number, γ is the inventory elasticity coefficient of the replenishment priority, S′ a is the safety stock of type a spare part; Based on the replenishment priority, obtain the replenishment order of the spare parts; Use the replenishment order to place an order operation to obtain the replenishment order data and generate a replenishment record form.

8. The intelligent spare parts library inventory dynamic monitoring and replenishment optimization system according to claim 7, characterized in that: Use the blockchain to store the spare parts inventory, spare parts demand, difference report, and replenishment record form on the chain. The specific steps are as follows: Use the Merkle tree structure of the blockchain to organize the data of the spare parts inventory, spare parts demand, difference report, and replenishment record form to generate a unique hash value for each group of data; Pack the hashed data with the timestamp, the previous block hash value, and the block number information into a block to obtain the block data; Adopt a dynamic voting mechanism to regularly adjust the weights of authorized nodes; Adopt the PoA consensus mechanism to conduct consensus processing on the block data, and have the authorized nodes verify the legal status of the block to obtain the block data that passes the consensus verification; Add the block data verified by consensus to the blockchain to form a chain structure.

Images