Spindle component intelligent warehouse management system based on digital twinning

Abstract

The invention, which relates to the technical field of data processing, discloses an intelligent warehouse management system for a main shaft component based on digital twinning, comprising: a feature extraction module for summarizing all digital features of all usage scenarios of the main shaft component into a digital feature set; the weighting module is used for assigning weights to the digital features; using a scene analysis module to obtain an actual use feature set; matching an inspection module to obtain a target main shaft part and a replaceable main shaft part; and the main shaft component using module uses the target main shaft component as the main shaft component in the actual use situation when the inventory of the target main shaft component is higher than a preset value, and uses the target main shaft component and the replaceable main shaft component to be combined for use when the inventory of the target main shaft component does not exceed the preset value. The use situation is converted into a digital form, so that automatic identification and judgment can be realized more conveniently, errors caused by manual operation can be avoided, and the situation of temporary shortage of main shaft parts can also be avoided.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent warehouse management system for spindle components based on digital twins. Background Art

[0002] With the continuous development and innovation of science and technology, the variety of spindle components is increasing, and the usage is also increasing significantly, which increases management manpower and management costs. Due to the high cost of spindle components, there are high requirements for the correct use of spindle components, otherwise it will lead to waste of spindle components and untimely production and processing. However, the use of spindle components is usually controlled manually. In the complicated production work, it is inevitable that omissions will occur, leading to errors. In addition, spindle components need to be maintained regularly, which is easy to cause temporary shortage of inventory when in use. Summary of the invention

[0003] In order to solve the above technical problems, an intelligent warehouse management system for spindle components based on digital twins is provided. This technical solution solves the problem raised in the above background technology that the use of spindle components is usually manually controlled by volunteers, and omissions are inevitable in complicated production work, leading to errors. In addition, the spindle components are regularly maintained, and when in use, they are prone to temporary shortages of inventory.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] An intelligent storage management system for spindle components based on digital twins, comprising:

[0006] A feature extraction module, wherein the feature extraction module obtains at least one usage scenario of all spindle components based on historical data, performs feature extraction on the usage scenario to obtain at least one digital feature, and summarizes all digital features of all usage scenarios of the spindle components into a digital feature set;

[0007] A weighting module, which is used to calculate and determine the importance of each digital feature based on historical operation and maintenance logs, and assign weights to the digital features according to their importance;

[0008] Using the scenario analysis module, the set selection module obtains the current actual usage scenario and extracts features from the actual usage scenario to obtain an actual usage feature set;

[0009] A matching verification module, wherein the matching verification module performs a matching degree check on the digital feature sets of all spindle components and the actually used feature sets to obtain a target digital feature set, and uses the spindle component corresponding to the target digital feature set as the target spindle component, and obtains at least one replaceable digital feature set, and uses the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component;

[0010] A spindle component use module, which uses the target spindle component as the spindle component for the actual use scenario when the inventory of the target spindle component is higher than a preset value, and uses the target spindle component and a replaceable spindle component in combination when the inventory of the target spindle component does not exceed the preset value, and maintains the inventory of the target spindle component.

[0011] Preferably, extracting features from the usage context to obtain at least one digital feature comprises the following steps:

[0012] Obtain usage context, which includes device status and usage of the device spindle components;

[0013] Extract relevant information about the use of the main shaft components of the equipment from the equipment status of the use scenario, classify and identify the relevant information, and divide the relevant information into basic information elements during the classification and identification;

[0014] Based on big data, the proportion of the cases where the main shaft components and the basic information elements appear at the same time to the cases where the main shaft components appear is counted as the discrimination ratio;

[0015] When the discrimination ratio of the basic information element is greater than a preset value, the basic information element is necessary information, otherwise, the basic information element is non-essential information;

[0016] Clustering the necessary information to obtain at least one clustering information;

[0017] The clustering information is paired and summarized with the usage of the equipment spindle components to obtain digital features.

[0018] Preferably, the step of calculating and determining the importance of each digital feature based on the historical operation and maintenance log comprises the following steps:

[0019] Based on the historical operation and maintenance log, determine at least one usage scenario of the spindle component;

[0020] Based on the logistics regression model, predict the probability of occurrence of each usage scenario;

[0021] Determine at least one usage context in which the digital feature appears, recorded as the corresponding usage context of the digital feature;

[0022] The occurrence probabilities of all corresponding usage scenarios of the digital feature are accumulated to obtain the importance of the digital feature.

[0023] Preferably, the logistics regression model is specifically:

[0024]

[0025] Where P is the probability of occurrence of the usage scenario, x i is the i-th parameter value of the usage scenario, n is the total number of parameters of the usage scenario, α, β1…β i …β n All are parameters of the Logistic regression model, and the parameters of the Logistic regression model are obtained by the least squares method.

[0026] Preferably, assigning weights to digital features according to their importance comprises the following steps:

[0027] Obtain the importance of all digital features and assign weights to each digital feature based on the weight formula;

[0028] The weight formula is specifically:

[0029]

[0030] In the formula, w j is the weight of the jth digital feature, G j is the importance of the jth digital feature, and m is the total number of digital features.

[0031] Preferably, the matching degree check of the digital feature sets of all spindle components with the actually used feature sets to obtain a target digital feature set, using the spindle component corresponding to the target digital feature set as the target spindle component, and obtaining at least one replaceable digital feature set, using the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component comprises the following steps:

[0032] Calculate the Gerard similarity coefficient between the actual used feature set and the digital feature set of each spindle component;

[0033] A digital feature set with the largest Gerard similarity coefficient is selected and recorded as a target digital feature set, and the main shaft component corresponding to the target digital feature set is used as the target main shaft component;

[0034] Several digital feature sets whose Gerard similarity coefficients are greater than a preset value are screened out, and the digital feature sets except the target digital feature set are recorded as replaceable digital feature sets, and the spindle components corresponding to the replaceable digital feature sets are used as replaceable spindle components.

[0035] Preferably, the calculation formula of the Gerard similarity coefficient is:

[0036]

[0037] Among them, J is the Gerard similarity coefficient, T ture To actually use the feature set, T char is a set of digital features, N(T ture ∪T char ) is the number of elements in the union of the actual feature set and the digital feature set, N(T ture ∩T char ) is the number of elements in the intersection of the actual feature set and the digital feature set.

[0038] Preferably, when the inventory of the target spindle component does not exceed a preset value, using the target spindle component and the replaceable spindle component in combination comprises the following steps:

[0039] The difference between the inventory quantity of the target spindle component and the preset value is used as the replenishment quantity of the spindle component;

[0040] Obtaining a replacement weight of the replaceable spindle component based on summing the weight of each digital feature in the digital feature set of the replaceable spindle component;

[0041] All replaceable spindle components are sorted in ascending order of replacement weights of the replaceable spindle components;

[0042] The replaceable spindle component that obtains the spindle component replenishment amount from the replaceable spindle components in sequence is used in combination with the target spindle component.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By setting up a feature extraction module, a weighting module, a matching verification module and a spindle component usage module, the usage scenario is converted into a digital twin, which can facilitate automatic identification and judgment, thereby providing a spindle component that matches the usage scenario, and verifying the spindle component and the usage scenario to ensure that there will be no errors in its use. During use, considering the inventory situation, for spindle components with less inventory, similar spindle components are used for combination and replacement, so that they can be supported until the next purchase, thereby avoiding errors in manual operation and temporary shortages of spindle components. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the process of the intelligent warehouse management system of spindle components based on digital twins of the present invention;

[0046] Figure 2 A schematic diagram of a flow chart of extracting features from a usage scenario to obtain at least one digital feature according to the present invention;

[0047] Figure 3 A flowchart for calculating and determining the importance of each digital feature based on historical operation and maintenance logs;

[0048] Figure 4 A schematic diagram of a process of obtaining a target spindle component and a replaceable spindle component according to the present invention;

[0049] Figure 5 It is a schematic diagram of a flow chart of the combined use of the target spindle component and the replaceable spindle component of the present invention. DETAILED DESCRIPTION

[0050] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0051] An intelligent storage management system for spindle components based on digital twins, comprising:

[0052] A feature extraction module, which obtains at least one usage scenario of all spindle components based on historical data, extracts features of the usage scenario to obtain at least one digital feature, and aggregates all digital features of all usage scenarios of the spindle components into a digital feature set;

[0053] The weighting module is used to calculate the importance of each digital feature based on historical operation and maintenance logs, and assign weights to digital features according to their importance;

[0054] Using the scenario analysis module, the set selection module obtains the current actual usage scenario and extracts features from the actual usage scenario to obtain an actual usage feature set;

[0055] A matching verification module, wherein the matching verification module performs a matching degree check on the digital feature sets of all spindle components and the actually used feature sets to obtain a target digital feature set, and uses the spindle component corresponding to the target digital feature set as the target spindle component, and obtains at least one replaceable digital feature set, and uses the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component;

[0056] The spindle component use module uses the target spindle component as the spindle component for the actual use scenario when the inventory of the target spindle component is higher than the preset value; when the inventory of the target spindle component does not exceed the preset value, the target spindle component and the replaceable spindle component are used in combination, and the inventory of the target spindle component is maintained.

[0057] Reference Figure 1 As shown, the working method of the above system is:

[0058] The feature extraction module obtains at least one usage scenario of all spindle components based on historical data, extracts features of the usage scenario to obtain at least one digital feature, and summarizes all digital features of all usage scenarios of the spindle components into a digital feature set;

[0059] The weighting module calculates the importance of each digital feature based on historical operation and maintenance logs, and assigns weights to the digital features according to their importance;

[0060] The scenario analysis module is used to obtain the current actual usage scenario, and features are extracted from the actual usage scenario to obtain an actual usage feature set;

[0061] The matching verification module performs matching verification on the digital feature sets of all spindle components and the actual use feature sets to obtain a target digital feature set, and uses the spindle component corresponding to the target digital feature set as the target spindle component, and obtains at least one replaceable digital feature set, and uses the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component;

[0062] When the inventory of the target spindle component is higher than a preset value, the spindle component usage module uses the target spindle component as the spindle component for the actual usage scenario; when the inventory of the target spindle component does not exceed the preset value, the target spindle component and the replaceable spindle component are used in combination, and the inventory of the target spindle component is maintained.

[0063] By setting up a feature extraction module, a weighting module, a matching verification module and a spindle component usage module, the usage scenario is converted into a digital twin, which can facilitate automatic identification and judgment, thereby providing a spindle component that matches the usage scenario, and verifying the spindle component and the usage scenario to ensure that there will be no errors in its use. During use, considering the inventory situation, for spindle components with less inventory, similar spindle components are used for combination and replacement, so that they can be supported until the next purchase, thereby avoiding errors in manual operation and temporary shortages of spindle components.

[0064] Reference Figure 2 As shown, extracting features from the usage scenario to obtain at least one digital feature includes the following steps:

[0065] Obtain usage context, which includes device status and usage of the device spindle components;

[0066] Extract relevant information about the use of the main shaft components of the equipment from the equipment status of the use scenario, classify and identify the relevant information, and divide the relevant information into basic information elements during the classification and identification;

[0067] Based on big data, the proportion of the cases where the main shaft components and the basic information elements appear at the same time to the cases where the main shaft components appear is counted as the discrimination ratio;

[0068] When the discrimination ratio of the basic information element is greater than a preset value, the basic information element is necessary information, otherwise, the basic information element is non-essential information;

[0069] Clustering the necessary information to obtain at least one clustering information;

[0070] The clustering information is paired and summarized with the usage of the equipment spindle components to obtain digital features.

[0071] Identification features are used to judge the usage scenario. Otherwise, the usage scenario cannot be directly identified, and the corresponding spindle components cannot be matched for the usage scenario. Features can be extracted based on the equipment status and the purpose of the equipment spindle components, so as to extract sufficient elements to determine the usage scenario. However, the identification feature is text information, and its identification still has certain difficulties. The computer cannot recognize it quickly. Therefore, it needs to be converted into digital features so that the computer can recognize it quickly.

[0072] Reference Figure 3 As shown, based on the historical operation and maintenance logs, calculating and determining the importance of each digital feature includes the following steps:

[0073] Based on the historical operation and maintenance log, determine at least one usage scenario of the spindle component;

[0074] Based on the logistics regression model, predict the probability of occurrence of each usage scenario;

[0075] Determine at least one usage context in which the digital feature appears, recorded as the corresponding usage context of the digital feature;

[0076] The importance of the digital feature is obtained by summing up the occurrence probabilities of all corresponding usage scenarios of the digital feature. The specific logistic regression model is:

[0077]

[0078] Where P is the probability of occurrence of the usage scenario, x i is the i-th parameter value of the usage scenario, n is the total number of parameters of the usage scenario, α, β1…β i …β n These are the parameters of the Logistic regression model, and the parameters of the Logistic regression model are obtained using the least squares method.

[0079] Assigning weights to numerical features based on their importance involves the following steps:

[0080] Obtain the importance of all digital features and assign weights to each digital feature based on the weight formula;

[0081] The specific weight formula is:

[0082]

[0083] In the formula, w j is the weight of the jth digital feature, G j is the importance of the jth digital feature, and m is the total number of digital features.

[0084] The Logistic regression model is a generalized linear regression analysis model, which is commonly used in data mining, automatic disease diagnosis, economic forecasting and other fields. The Logistic regression model estimates the probability of an event based on a given independent variable data set. Since the result is a probability, the range of the dependent variable is between 0 and 1. In this embodiment, the Logistic regression model is used to calculate and identify the probability of occurrence of each usage scenario, and based on the demand for digital features in each usage scenario, the importance of the digital features is comprehensively analyzed. The greater the importance, the greater the probability that the digital feature is required in the actual usage scenario.

[0085] Reference Figure 4 As shown, the matching degree of the digital feature sets of all spindle components and the actually used feature sets is checked to obtain a target digital feature set, the spindle component corresponding to the target digital feature set is used as the target spindle component, and at least one replaceable digital feature set is obtained, and the spindle component corresponding to the replaceable digital feature set is used as the replaceable spindle component, including the following steps:

[0086] Calculate the Gerard similarity coefficient between the actual used feature set and the digital feature set of each spindle component;

[0087] A digital feature set with the largest Gerard similarity coefficient is selected and recorded as a target digital feature set, and the main shaft component corresponding to the target digital feature set is used as the target main shaft component;

[0088] Several digital feature sets whose Gerard similarity coefficients are greater than a preset value are screened out, and the digital feature sets except the target digital feature set are recorded as replaceable digital feature sets, and the spindle components corresponding to the replaceable digital feature sets are used as replaceable spindle components.

[0089] Preferably, the calculation formula of the Gerard similarity coefficient is:

[0090]

[0091] Among them, J is the Gerard similarity coefficient, T ture To actually use the feature set, T char is a set of digital features, N(T ture ∪T char ) is the number of elements in the union of the actual feature set and the digital feature set, N(T ture ∩T char ) is the number of elements in the intersection of the actual feature set and the digital feature set.

[0092] In this solution, the Jaccard coefficient, also commonly known as the Jaccard Similarity Coefficient or the Jaccard Index, is an indicator for measuring the similarity between two sets. It describes the proportion of the intersection elements of the two sets A and B in the union of A and B. In this solution, the Jaccard similarity coefficient between the actual usage feature set required in the actual scenario and the digital feature set of each spindle is calculated to match one or more spindle component types required in the actual scenario, and extract the target spindle component and replaceable spindle component that can be actually used, where the target spindle component is the spindle component type that best matches the current actual scenario and is the spindle component type that can be used in the current actual scenario.

[0093] Reference Figure 5 As shown, when the inventory of the target spindle component does not exceed a preset value, using the target spindle component and the replaceable spindle component in combination includes the following steps:

[0094] The difference between the inventory quantity of the target spindle component and the preset value is used as the replenishment quantity of the spindle component;

[0095] Obtaining a replacement weight of the replaceable spindle component based on summing the weight of each digital feature in the digital feature set of the replaceable spindle component;

[0096] All replaceable spindle components are sorted in ascending order of replacement weights of the replaceable spindle components;

[0097] The replaceable spindle component that obtains the spindle component replenishment amount from the replaceable spindle components in sequence is used in combination with the target spindle component.

[0098] By combining the weights of the digital features corresponding to the spindle components, the replaceable spindle components are intelligently sorted. The larger the replacement weight of the replaceable spindle component, the more likely it is that the replaceable spindle component will be needed in the actual usage scenario. When replacing the combination, the spindle component should be used as little as possible. Therefore, in this scheme, all replaceable spindle components are sorted in order from small to large according to the replacement weight of the replaceable spindle components, and the replaceable spindle components with the replenishment quantity of the spindle components are obtained from the replaceable spindle components in order for combination with the target spindle components, to ensure that the warehouse management of the spindle components can maximize the application scenarios.

[0099] In summary, the advantage of the present invention is that by converting the usage scenario into digital form, automatic identification and judgment can be more conveniently achieved, thereby ensuring the provision of a spindle component that matches the specific usage scenario. At the same time, the spindle component and the usage scenario are strictly checked to ensure the accuracy of their application. In addition, in the actual application process, this solution will fully consider the inventory status: for spindle components with less inventory, similar spindle components will be used for combination replacement to ensure that they can be supported until the next procurement cycle. This can effectively prevent human operational errors and avoid the problem of temporary shortage of spindle components.

[0100] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent warehouse management system for spindle components based on digital twins, characterized in that: include: A feature extraction module, wherein the feature extraction module obtains at least one usage scenario of all spindle components based on historical data, performs feature extraction on the usage scenario to obtain at least one digital feature, and summarizes all digital features of all usage scenarios of the spindle components into a digital feature set; A weighting module, which is used to calculate and determine the importance of each digital feature based on historical operation and maintenance logs, and assign weights to the digital features according to their importance; Using the scenario analysis module, the set selection module obtains the current actual usage scenario and extracts features from the actual usage scenario to obtain an actual usage feature set; A matching verification module, wherein the matching verification module performs a matching degree check on the digital feature sets of all spindle components and the actually used feature sets to obtain a target digital feature set, and uses the spindle component corresponding to the target digital feature set as the target spindle component, and obtains at least one replaceable digital feature set, and uses the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component; A spindle component use module, which uses the target spindle component as the spindle component for the actual use scenario when the inventory of the target spindle component is higher than a preset value, and uses the target spindle component and a replaceable spindle component in combination when the inventory of the target spindle component does not exceed the preset value, and maintains the inventory of the target spindle component.

2. According to claim 1, a spindle component intelligent warehouse management system based on digital twins is characterized in that: The feature extraction of the usage scenario to obtain at least one digital feature comprises the following steps: Obtain usage context, which includes device status and usage of the device spindle components; Extract relevant information about the use of the main shaft components of the equipment from the equipment status of the use scenario, classify and identify the relevant information, and divide the relevant information into basic information elements during the classification and identification; Based on big data, the proportion of the cases where the main shaft components and the basic information elements appear at the same time to the cases where the main shaft components appear is counted as the discrimination ratio; When the discrimination ratio of the basic information element is greater than a preset value, the basic information element is necessary information, otherwise, the basic information element is non-essential information; Clustering the necessary information to obtain at least one clustering information; The clustering information is paired and summarized with the usage of the equipment spindle components to obtain digital features.

3. According to claim 2, a spindle component intelligent warehouse management system based on digital twins is characterized in that: The calculation and determination of the importance of each digital feature based on the historical operation and maintenance log includes the following steps: Based on the historical operation and maintenance log, determine at least one usage scenario of the spindle component; Based on the logistics regression model, predict the probability of occurrence of each usage scenario; Determine at least one usage context in which the digital feature appears, recorded as the corresponding usage context of the digital feature; The occurrence probabilities of all corresponding usage scenarios of the digital feature are accumulated to obtain the importance of the digital feature.

4. According to claim 3, a spindle component intelligent warehouse management system based on digital twins is characterized in that: The logistics regression model is specifically: Where P is the probability of occurrence of the usage scenario, x i is the i-th parameter value of the usage scenario, n is the total number of parameters of the usage scenario, α, β1…β i …β n All are parameters of the Logistic regression model, and the parameters of the Logistic regression model are obtained by the least squares method.

5. According to claim 4, a spindle component intelligent warehouse management system based on digital twins is characterized in that: The step of assigning weights to digital features according to their importance comprises the following steps: Obtain the importance of all digital features and assign weights to each digital feature based on the weight formula; The weight formula is specifically: In the formula, w j is the weight of the jth digital feature, G j is the importance of the jth digital feature, and m is the total number of digital features.

6. According to claim 5, a spindle component intelligent warehouse management system based on digital twins is characterized in that: The process of performing matching check on the digital feature sets of all spindle components and the actually used feature sets to obtain a target digital feature set, using the spindle component corresponding to the target digital feature set as the target spindle component, and obtaining at least one replaceable digital feature set, using the spindle component corresponding to the replaceable digital feature set as the replaceable spindle component comprises the following steps: Calculate the Gerard similarity coefficient between the actual used feature set and the digital feature set of each spindle component; A digital feature set with the largest Gerard similarity coefficient is selected and recorded as a target digital feature set, and the main shaft component corresponding to the target digital feature set is used as the target main shaft component; Several digital feature sets whose Gerard similarity coefficients are greater than a preset value are screened out, and the digital feature sets except the target digital feature set are recorded as replaceable digital feature sets, and the spindle components corresponding to the replaceable digital feature sets are used as replaceable spindle components.

7. The spindle component intelligent warehouse management system based on digital twin according to claim 6 is characterized in that: The calculation formula of the Gerard similarity coefficient is: Among them, J is the Gerard similarity coefficient, T ture To actually use the feature set, T char is a set of digital features, N(T ture ∪T char ) is the number of elements in the union of the actual feature set and the digital feature set, N(T ture ∩T char ) is the number of elements in the intersection of the actual feature set and the digital feature set.

8. The intelligent storage management system for spindle components based on digital twins according to claim 7 is characterized in that: When the inventory of the target spindle component does not exceed a preset value, using the target spindle component and the replaceable spindle component in combination comprises the following steps: The difference between the inventory quantity of the target spindle component and the preset value is used as the replenishment quantity of the spindle component; Obtaining a replacement weight of the replaceable spindle component based on summing the weight of each digital feature in the digital feature set of the replaceable spindle component; All replaceable spindle components are sorted in ascending order of replacement weights of the replaceable spindle components; The replaceable spindle component that obtains the spindle component replenishment amount from the replaceable spindle components in sequence is used in combination with the target spindle component.

Images