Aerial material spare part demand prediction method based on big data and related equipment

Abstract

The invention discloses an aerial material spare part demand prediction method based on big data and related equipment, and the method comprises the steps: enabling historical data of aerial material consumption to generate a historical data matrix Adn, and storing the historical data matrix Adn; determining a prediction range according to the number s of equipment needing to be predicted and a prediction period t, generating a prediction range matrix Ats of t rows and s columns, and setting a second layer of convolution kernel according to the prediction range matrix Ats; a first layer of convolution kernel is set according to the size of the one-dimensional matrix Aij, the first layer of convolution kernel is one-dimensional, and an initial value is determined according to the position of the spare part needing to be predicted in the matrix Aij; carrying out double convolution operation from the position A11 in the historical data matrix Adn; after double convolution operation, an aerial material spare part demand quantity matrix Bxy is generated; the minimum value bmin and the maximum value bmax of elements in the aerial material demand quantity matrix Bxy are searched, and P (b) obtained through calculation is the corresponding probability when the aerial material demand quantity is b after the prediction equipment quantity s and the prediction period t are given. According to the invention, the accuracy of aviation material spare part demand prediction can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of aviation maintenance and support, and in particular relates to a method for predicting aviation material and spare parts demand based on big data and related equipment. Background Art

[0002] The demand forecast of aviation equipment spare parts has always been the focus of the aviation material procurement department. The accuracy of the demand forecast of aviation material spare parts directly affects the cost control of aviation material procurement and the guarantee capability of aviation equipment. Once the aviation material reserves are excessive, it will not only lead to a backlog of funds, but also occupy the aviation material storage space for a long time, and increase a lot of aviation material management work; insufficient aviation material reserves will affect the equipment maintenance and guarantee work, so that the equipment integrity rate cannot be guaranteed in time.

[0003] At present, the existing technology for forecasting the demand for aviation spare parts is mainly based on the Poisson distribution model, which uses data such as the number of aircraft, flight hours, number of installed aircraft, unplanned replacement time, scrap rate, procurement cycle, repair cycle, management cycle, and spare parts guarantee probability to theoretically predict the demand for aviation spare parts in the future. This method relies too much on the theoretical model. Once the predicted probability distribution of aviation spare parts failure does not meet the Poisson distribution, there will be a large deviation between the prediction result and the actual data, and it is impossible to accurately predict the demand for aviation spare parts.

[0004] In summary, the existing aviation material spare parts demand forecasting methods have the problem of over-reliance on theoretical models and poor accuracy. Summary of the invention

[0005] The purpose of the present invention is to provide an aviation material spare parts demand forecasting method and related equipment based on big data, which is used to solve the problem that the aviation material spare parts demand forecasting method in the prior art is overly dependent on theoretical models and has poor accuracy. The present invention can improve the accuracy of aviation material spare parts demand forecasting.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting demand for aviation spare parts based on big data includes the following steps:

[0008] Step 1: Generate a historical data matrix A with d rows and n columns based on the historical data of aviation material consumption according to equipment number n and date d. dn To store; historical data matrix A dn ElementA ij Used to store historical equipment data with date i and equipment number j. ij is a one-dimensional matrix;

[0009] Step 2: Determine the prediction range based on the number of equipment s and prediction period t to be predicted, and generate a prediction range matrix A with t rows and s columns. ts , according to the prediction range matrix A ts Set the second layer convolution kernel, and set the initial value to 1; according to the one-dimensional matrix A ij The size sets the first convolution kernel. The first convolution kernel is one-dimensional, and the initial value is based on the predicted spare parts in matrix A. ij The initial value of the corresponding position is 1, and the initial values ​​of the other positions are 0;

[0010] Step 3: From the historical data matrix A dn Middle A 11 After the double convolution operation, the aviation material spare parts demand quantity matrix B is generated. xy ;

[0011] Step 4: Find the aviation material demand quantity matrix B xy The minimum value of the element in b min and the maximum value b max , and then count b min 、b min+1 、b min+2 , …, b max In the matrix B xy The proportion of occurrences in P(b min )、P(b min+1 )、P(b min+2 ),…,P(b max ); specifically:

[0012]

[0013] The calculated P(b) is the probability that the aviation material demand quantity is b given the predicted equipment quantity s and the prediction period t.

[0014] Preferably, the matrix A dn It is expressed as:

[0015]

[0016] Among them, element A ij Located in the i-th row and j-th column, it stores the equipment data corresponding to date i and number j. It is a one-dimensional matrix containing data on working hours and the consumption quantity of various types of aviation materials and spare parts.

[0017] Preferably, in step 1, if the matrix A dn If there are elements with empty data in the matrix A, then remove them. dn The empty elements in are filled by moving up the next non-empty element in the same column to generate a new data matrix.

[0018] Preferably, in step 2, if the daily average equipment usage time within the given prediction range is the same as or similar to the historical daily average equipment usage time, the prediction range is directly determined; if the difference is large, the prediction period t needs to be converted, and the converted prediction period is as follows:

[0019]

[0020] At this time, the prediction range is determined according to the number of equipment s to be predicted and the converted prediction period t`. The prediction range size is t` rows and s columns, and the size of the second layer convolution kernel is updated synchronously.

[0021] Preferably, in step 3, from matrix A dn Middle A 11 Starting from position, double convolution operation is performed; the first layer convolution kernel and the one-dimensional matrix A ij Perform convolution operation to extract A ij The daily consumption quantity of spare parts needs to be predicted; the second convolution kernel is obtained from the matrix A dn Middle A 11 The sliding scan starts from the position, and the data after the first convolution operation is subjected to a double convolution operation with a step size of 1; after the double convolution operation, the aviation material spare parts demand quantity matrix B is generated.

[0022] Preferably, in step 4, if the number of spare parts K is given, the probability of spare parts guarantee within the forecast period is given, and the specific calculation method is as follows:

[0023] N is a positive integer

[0024] The spare parts guarantee probability P represents the probability of having no shortage of spare parts when they are needed within the forecast period. It is used to measure the guarantee of the current inventory quantity for the equipment in the future. The larger the P value, the stronger the guarantee capability, and vice versa.

[0025] Preferably, in step 4, if the spare parts guarantee probability P BZ Given, the number of spare parts required within the forecast period is given. The specific calculation method is as follows:

[0026] N is a positive integer

[0027] From P(N min ) and then sum up in sequence until the sum of probabilities is greater than the given spare parts guarantee probability P BZ , then the corresponding K value is the probability of satisfying spare parts guarantee within the forecast period P BZ The number of spare parts required.

[0028] An aviation material spare parts demand forecasting device based on big data, comprising:

[0029] a processor suitable for executing a computer program;

[0030] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, an aviation material spare parts demand forecasting method based on big data as described in any one of the above items is executed.

[0031] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting demand for aviation materials and spare parts based on big data as described in any one of the above items is implemented.

[0032] A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements a method for predicting demand for aviation materials and spare parts based on big data as described in any one of the above.

[0033] Compared with the prior art, the present invention has the following beneficial technical effects:

[0034] The present invention provides a method for predicting demand for aviation materials and spare parts based on big data. Based on the historical aviation material consumption data matrix, a double convolution operation is used to generate a spare parts demand matrix, and then a statistical analysis is performed to obtain the probability of spare parts demand. ij The size of the first convolution kernel is set, and the second convolution kernel is set according to the forecast range of aviation material spare parts demand. Sliding scanning is performed in the aviation material historical consumption data matrix. At the position covered by the second convolution kernel, the first convolution operation is used to extract A ij The daily consumption quantity of spare parts is predicted in the demand forecast, and the historical spare parts demand quantity is calculated by the second convolution operation. After the double convolution operation, the aviation material spare parts demand quantity matrix B is generated. xy ; Quantity matrix B for aviation spare parts demand xy The proportion of each element in the data is statistically analyzed to obtain the probability corresponding to different demand quantities; different spare parts demands correspond to different probabilities, and the greater the probability, the greater the possibility of demand. Compared with the traditional pure theoretical prediction based on the Poisson distribution model, the method of the present invention is more in line with reality, and the prediction results are more accurate and reliable; secondly, for aviation spare parts whose failure probability does not meet the Poisson distribution, this method can still be used for prediction; finally, compared with the traditional prediction method, this method has less calculation and a simpler operation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of aviation spare parts demand forecasting based on big data. DETAILED DESCRIPTION

[0036] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0037] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0038] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0039] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0041] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0042] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0043] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0044] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0045] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0046] The present invention provides a method for predicting demand for aviation material spare parts based on big data, comprising the following steps:

[0047] Step S100: historical data regularization. The historical data of aviation material consumption is generated into a historical data matrix A with d rows and n columns according to the equipment number n and date d. dn For storage, A dn ElementA ij Used to store historical equipment data with date i and equipment number j. ij It is a one-dimensional matrix, which contains data such as the working time of equipment j on day i, the consumption quantity of various aviation materials and spare parts, etc. The data are arranged in a certain order.

[0048] A dn It can be expressed as:

[0049]

[0050] a ij It can be expressed as: ij=[Daily working hours, number of spare parts consumed in 1 day, number of spare parts consumed in 2 days…]

[0051] Step S200: Convolution kernel determination. According to the number of equipment s to be predicted and the prediction period t, the prediction range is determined, and a prediction range matrix A with t rows and s columns is generated. ts , according to the matrix A ts Set the second layer convolution kernel, and set the initial value to 1; according to the one-dimensional matrix A ij The size sets the first convolution kernel. The first convolution kernel is one-dimensional, and the initial value is based on the predicted spare parts in matrix A. ij The initial value of the corresponding position is 1, and the initial values ​​of the other positions are 0;

[0052] Assuming that the demand for spare part 1 for 3 engines within 4 days is predicted, then:

[0053] The second layer of convolution kernel can be expressed as:

[0054]

[0055] The first layer of convolution kernel can be expressed as: a = [0, 1, 0, ...]

[0056] Step S300: Double convolution operation. From the historical data matrix A dn Middle 11 The double convolution operation starts at position .

[0057] The first layer of convolution kernel and one-dimensional matrix a ij Perform convolution operation to extract a ij The daily consumption quantity of spare parts needs to be predicted; after the first layer of convolution operation, a 11 ~a dn These are the consumption quantities of spare part 1.

[0058] Matrix A after one convolution operation dn It can be expressed as:

[0059]

[0060] The second layer of convolution kernels is from matrix A dn Middle 11 The sliding scan starts at the position, and the matrix A after a convolution operation is dn Perform double convolution operation with a step size of 1; after double convolution operation, the aviation material spare parts demand quantity matrix B is generated xy ;

[0061] B xy It can be expressed as:

[0062]

[0063] Step S400: Spare parts demand forecast. Find the aviation material demand quantity matrix B xy The minimum value of the element in b min and the maximum value b max , and then count b min 、b min+1 、b min+2 , …, b max In the matrix B xy The proportion of occurrences in P(b min )、P(b min+1 )、P(b min+2 ),…,P(b max ); specifically:

[0064]

[0065] The calculated P(b) is the probability that the aviation material demand quantity is b when the predicted equipment quantity s and the prediction period t are given. It can be used to predict the aviation material demand quantity. The specific demand will be given in the form of probability. Different spare parts demands correspond to different probabilities. The greater the probability, the greater the possibility of demand.

[0066] The present invention generates a spare parts demand matrix based on the aviation material historical consumption data matrix by using double convolution operation, and obtains the spare parts demand probability by performing statistical analysis.

[0067] The present invention is based on a one-dimensional matrix A ij The size of the first convolution kernel is set, and the second convolution kernel is set according to the forecast range of aviation material spare parts demand. Sliding scanning is performed in the aviation material historical consumption data matrix. At the position covered by the second convolution kernel, the first convolution operation is used to extract A ij The daily consumption quantity of spare parts is predicted in the demand forecast, and the historical spare parts demand quantity is calculated by the second convolution operation. After the double convolution operation, the aviation material spare parts demand quantity matrix B is generated. xy ; Quantity matrix B for aviation spare parts demand xy The proportion of each element is statistically analyzed to obtain the probability corresponding to different demand quantities; different spare parts demands correspond to different probabilities, and the greater the probability, the greater the possibility of demand.

[0068] The method of the present invention is based on historical data for prediction, which is more in line with reality than the traditional purely theoretical prediction based on the Poisson distribution model, and the prediction results are more accurate and reliable; secondly, for aviation materials and spare parts whose failure probability does not satisfy the Poisson distribution, this method can still be used for prediction; finally, compared with traditional prediction methods, this method has less calculation amount and a simpler operation process.

[0069] Embodiment 1:

[0070] A method for forecasting demand for aviation spare parts based on big data, such as Figure 1 As shown, the following steps are included:

[0071] Step S100: historical data regularization. The historical data of aviation material consumption is generated into a historical data matrix A with d rows and n columns according to the equipment number n and date d. dn For storage, A dn ElementA ij Used to store historical equipment data with date i and equipment number j. ij It is a one-dimensional matrix, which contains data such as the working time of equipment j on day i, the consumption quantity of various aviation materials and spare parts, etc. The data are arranged in a certain order.

[0072] A dn It can be expressed as:

[0073]

[0074] a ij It can be expressed as: ij =[Daily working hours, number of spare parts consumed in 1 day, number of spare parts consumed in 2 days…]

[0075] Step S200: Convolution kernel determination. According to the number of equipment s to be predicted and the prediction period t, the prediction range is determined, and a prediction range matrix A with t rows and s columns is generated. ts , according to the matrix A ts Set the second layer convolution kernel, and set the initial value to 1; according to the one-dimensional matrix A ij The size sets the first convolution kernel. The first convolution kernel is one-dimensional, and the initial value is based on the predicted spare parts in matrix A. ij The initial value of the corresponding position is 1, and the initial values ​​of the other positions are 0;

[0076] Assuming that the demand for spare part 1 for 3 engines within 4 days is predicted, then:

[0077] The second layer of convolution kernel can be expressed as:

[0078]

[0079] The first layer of convolution kernel can be expressed as: a = [0, 1, 0, ...]

[0080] Step S300: Double convolution operation. From the historical data matrix A dn Middle 11 The double convolution operation starts at position .

[0081] The first layer of convolution kernel and one-dimensional matrix a ij Perform convolution operation to extract a ijThe daily consumption quantity of spare parts needs to be predicted; after the first layer of convolution operation, a 11 ~a dn These are the consumption quantities of spare part 1.

[0082] Matrix A after one convolution operation dn It can be expressed as:

[0083]

[0084] The second layer of convolution kernels is from matrix A dn Middle 11 The sliding scan starts at the position, and the matrix A after a convolution operation is dn Perform double convolution operation with a step size of 1; after double convolution operation, the aviation material spare parts demand quantity matrix B is generated xy ;

[0085] B xy It can be expressed as:

[0086]

[0087] Step S400: Spare parts demand forecast. Find the aviation material demand quantity matrix B xy The minimum value of the element in b min and the maximum value b max , and then count b min 、b min+1 、b min+2 , …, b max In the matrix B xy The proportion of occurrences in P(b min )、P(b min+1 )、P(b min+2 ),…,P(b max ); specifically:

[0088]

[0089] The calculated P(b) is the probability that the aviation material demand quantity is b when the predicted equipment quantity s and the prediction period t are given. It can be used to predict the aviation material demand quantity, and the specific demand will be given in the form of probability.

[0090] Embodiment 2:

[0091] This embodiment is optimized on the basis of Embodiment 1, mainly focusing on step S100, and is specifically as follows:

[0092] If the matrix A dn If there are elements with empty data in the matrix A, after step S100 is completed, further regularization can be performed to eliminate the elements in the matrix A. dnThe empty elements in the same column are filled by moving up the next non-empty element in the same column to generate a new data matrix. At this time, the data in each element in the matrix may not have a corresponding relationship with the date, but only corresponds to the equipment number. This matrix is ​​only used to predict the demand for aviation materials and spare parts.

[0093] Embodiment 3:

[0094] This embodiment is optimized on the basis of embodiment 1, mainly focusing on step S200, and is specifically as follows:

[0095] If the daily average equipment usage time within the given prediction range is the same as or similar to the historical daily average equipment usage time, the prediction range can be determined directly according to step S200; if the difference is large, the prediction period t needs to be converted, and the converted prediction period is as follows:

[0096]

[0097] At this time, the prediction range is determined by the number of equipment s to be predicted and the converted prediction period t'. The prediction range size is t' rows and s columns. The second layer convolution kernel A ts Size is updated synchronously.

[0098] Embodiment 4:

[0099] This embodiment is optimized on the basis of Embodiment 1, mainly focusing on step S400, and is specifically as follows:

[0100] Step S400: Spare parts demand prediction. P(b) is the probability corresponding to the demand quantity of aviation materials being b given the predicted equipment quantity s and the prediction period t. It can be used to predict the demand quantity of aviation materials. The specific demand quantity will be given in the form of probability.

[0101] At this time, if the number of spare parts K is given, the probability of spare parts guarantee within the prediction period can be given by step S400. The specific calculation method is as follows:

[0102] N is a positive integer.

[0103] The spare parts guarantee probability P represents the probability of having no shortage of spare parts when they are needed within the forecast period. It can measure the guarantee of the current inventory quantity for the equipment in the future. The larger the P value, the stronger the guarantee capability, and vice versa.

[0104] Embodiment 5:

[0105] This embodiment is optimized on the basis of Embodiment 1, mainly focusing on step S400, and is specifically as follows:

[0106] Step S400: Forecasting the demand for aviation materials and spare parts. P(b) is the probability corresponding to the demand for aviation materials being b given the predicted equipment quantity s and the prediction period t. It can be used to predict the demand for aviation materials. The specific demand quantity will be given in the form of probability.

[0107] At this time, if the spare parts guarantee probability P BZ Given, the number of spare parts required within the forecast period can be given by step S400. The specific calculation method is as follows:

[0108] N is a positive integer.

[0109] From P(N min ) and then sum up in sequence until the sum of probabilities is greater than the given spare parts guarantee probability P BZ , then the corresponding K value is the probability of satisfying spare parts guarantee within the forecast period P BZ The number of spare parts required.

[0110] The following are device embodiments of the present invention, which can be used to perform method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0111] In another embodiment of the present invention, a computer device is provided, the computer device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a method for predicting demand for aviation materials and spare parts based on big data.

[0112] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the above-mentioned embodiment of a method for predicting aviation material and spare parts demand based on big data.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0118] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0119] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for forecasting demand for aviation materials and spare parts based on big data, characterized in that: The following steps are included: Step 1: Generate a historical data matrix A with d rows and n columns based on the historical data of aviation material consumption according to equipment number n and date d. dn To store; historical data matrix A dn ElementA ij Used to store historical equipment data with date i and equipment number j. ij is a one-dimensional matrix; Step 2: Determine the prediction range based on the number of equipment s and prediction period t to be predicted, and generate a prediction range matrix A with t rows and s columns. ts , according to the prediction range matrix A ts Set the second layer convolution kernel, and set the initial value to 1; according to the one-dimensional matrix A ij The size sets the first convolution kernel. The first convolution kernel is one-dimensional, and the initial value is based on the predicted spare parts in matrix A. ij The initial value of the corresponding position is 1, and the initial values ​​of the other positions are 0; Step 3: From the historical data matrix A dn Middle A 11 After the double convolution operation, the aviation material spare parts demand quantity matrix B is generated. xy ; Step 4: Find the aviation material demand quantity matrix B xy The minimum value of the element in b min and the maximum value b max , and then count b min , b min+1 , b min+2 , …, b max In the matrix B xy The proportion of occurrences in P(b min )、P(b min+1 )、P(b min+2 ),…,P(b max ); specifically: The calculated P(b) is the probability that the aviation material demand quantity is b given the predicted equipment quantity s and the prediction period t.

2. The method for predicting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: Matrix A dn It is expressed as: Among them, element A ij Located in the i-th row and j-th column, it stores the equipment data corresponding to date i and number j. It is a one-dimensional matrix containing data on working hours and the consumption quantity of various types of aviation materials and spare parts.

3. The method for predicting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: In step 1, if the matrix A dn If there are elements with empty data in the matrix A, then remove them. dn The empty elements in are filled by moving up the next non-empty element in the same column to generate a new data matrix.

4. The method for predicting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: In step 2, if the daily average equipment usage time within the given forecast range is the same as or similar to the historical daily average equipment usage time, the forecast range is determined directly; if the difference is large, the forecast period t needs to be converted, and the converted forecast period is as follows: At this time, the prediction range is determined according to the number of equipment s to be predicted and the converted prediction period t`. The prediction range size is t` rows and s columns, and the size of the second layer convolution kernel is updated synchronously.

5. The method for forecasting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: In step 3, from matrix A dn Middle A 11 Starting from position, double convolution operation is performed; the first layer convolution kernel and the one-dimensional matrix A ij Perform convolution operation to extract A ij The daily consumption quantity of spare parts needs to be predicted; the second layer convolution kernel is from the matrix A dn Middle A 11 The sliding scan starts from the position, and the data after the first convolution operation is subjected to a double convolution operation with a step size of 1; after the double convolution operation, the aviation material spare parts demand quantity matrix B is generated.

6. The method for forecasting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: In step 4, if the number of spare parts K is given, the probability of spare parts guarantee within the forecast period is given. The specific calculation method is as follows: N is a positive integer The spare parts guarantee probability P represents the probability of having no shortage of spare parts when they are needed within the forecast period. It is used to measure the guarantee of the current inventory quantity for the equipment in the future. The larger the P value, the stronger the guarantee capability, and vice versa.

7. The method for predicting demand for aviation materials and spare parts based on big data according to claim 1, characterized in that: In step 4, if the spare parts guarantee probability P BZ Given, the number of spare parts required within the forecast period is given. The specific calculation method is as follows: N is a positive integer From P(N min ) and then sum up in sequence until the sum of probabilities is greater than the given spare parts guarantee probability P BZ , then the corresponding K value is the probability of satisfying spare parts guarantee within the forecast period P BZ The number of spare parts required.

8. A device for predicting demand for aviation materials and spare parts based on big data, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for predicting demand for aviation materials and spare parts based on big data as described in any one of claims 1 to 7 is executed.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for predicting demand for aviation materials and spare parts based on big data as described in any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the aviation material and spare parts demand forecasting method based on big data as described in any one of claims 1 to 7.

Images