CN113449868B - Machining process parameter decision support knowledge mining method and system - Google Patents
Machining process parameter decision support knowledge mining method and system Download PDFInfo
- Publication number
- CN113449868B CN113449868B CN202110780789.7A CN202110780789A CN113449868B CN 113449868 B CN113449868 B CN 113449868B CN 202110780789 A CN202110780789 A CN 202110780789A CN 113449868 B CN113449868 B CN 113449868B
- Authority
- CN
- China
- Prior art keywords
- process parameter
- parameter decision
- decision support
- data
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machining process parameter decision support knowledge mining method and a machining process parameter decision support knowledge mining system, wherein process data are obtained from a part machining process card, and process parameter decision support data are extracted; taking the extracted process parameter decision support data of the same family parts as input; constructing a process parameter decision support item head table; constructing a process parameter decision support FP tree based on the constructed process parameter decision support item head table; excavating the constructed process parameter decision support FP tree to form a process parameter decision support frequent tuple; and storing all the mined process parameter decision support frequent tuples into a knowledge base to support process parameter decision. The invention realizes the mining of the process parameter decision support knowledge, can support the decision of the tool and the cutting amount during the planning of the machining process, can efficiently mine the process parameter decision support knowledge facing the process data accumulated by enterprises and can avoid the occurrence of redundant knowledge.
Description
Technical Field
The invention belongs to the technical field of intelligent information of advanced manufacturing technology, and particularly relates to a machining process parameter decision support knowledge mining method and system.
Background
The process planning is an important content in the technical preparation work of the mechanical manufacturing production process, is a link between product design and processing and manufacturing, and is a decision process which is highly empirical and changes with the environment. In the traditional process planning, process decision is manually made by process designers according to own experience and by referring to relevant data, and the process decision mode comprises a large amount of tedious and repetitive work, so that the process planning efficiency is difficult to improve. In the intelligent manufacturing era, by using a Computer Aided Process Procedure (CAPP), process parameter decision can be performed with the help of a computer on the basis of process parameter decision support knowledge, so that the reuse of historical process knowledge is realized, the repetitive work is reduced, and the efficiency and the quality of process planning are improved.
The process parameter decision support knowledge comes from the process data of the enterprise, which is the summary and summarization thereof. A large amount of manpower and material resources are consumed in a traditional method for extracting knowledge manually, and process parameter decision support knowledge contained in process data is difficult to comprehensively mine. With the development and popularization of data mining technology, researchers begin to apply the data mining technology to the mining of process parameter decision support knowledge. Initially, researchers used Apriori methods to mine process parameter decision support knowledge, but such methods produced large candidate data sets and required repeated scans of the database, which was inefficient. With the continuous accumulation of enterprise data, the efficiency disadvantage of the method is gradually reflected. Then, a researcher adopts an FP-growth method to carry out the excavation of process parameter decision support knowledge, and the problem of low efficiency is solved to a certain extent.
However, the existing method simply applies the FP-growth method to the process parameter decision support knowledge mining, and does not consider that the process data is different from general data, that is, the process data has an association relationship and a dependency relationship. The conventional FP-growth method is adopted to establish the item head table, construct the FP tree and mine the FP tree to realize the process parameter decision support knowledge mining, so that a large amount of redundant knowledge is generated, the knowledge needs to be filtered and screened manually and subsequently, and the mining of the redundant knowledge also influences the overall efficiency of the method.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method and a system for mining machining process parameter decision support knowledge, which are used for acquiring process data from a machining process card, fully considering the relationship among the process data, improving three processes of item head table establishment, FP tree construction and FP tree mining of an FP-growth method, and realizing efficient and redundancy-free intelligent mining of process parameter decision support knowledge so as to support tool and cutting amount decision in process design in machining process planning.
The invention adopts the following technical scheme:
a machining process parameter decision support knowledge mining method comprises the following steps:
s1, acquiring process data from a part machining process card, preprocessing the acquired process data, and extracting process parameter decision support data;
s2, taking the process parameter decision support data of the same family of parts extracted in the step S1 as the input of the FP-growth method, and setting a support degree threshold value alpha fp ；
S3, scanning the process parameter decision support data input in the step S2 for the first time, and constructing a process parameter decision support item head table;
s4, scanning the process parameter decision support data input in the step S2 for the second time, and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed in the step S3;
s5, mining the process parameter decision support FP tree constructed in the step S4 by adopting an improved FP tree mining method, taking each step characteristic information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step characteristic information character f As a corresponding rule consequent;
s6, all the step characteristic information charters in the step S5 and corresponding mined process parameter decision support frequent tuples T f And storing the machining process parameter decision support knowledge into a knowledge base to support process parameter decision, and finding a corresponding cutter and cutting amount decision scheme through the process step characteristic information in the process parameter decision.
Specifically, in step S1, the process parameter decision support data includes operation step, machine tool, material grade, tool, spindle speed, feed rate, and depth of cut, depth of cut; combining the work step operation _ step, the machine tool machine and the material mark material _ descriptor into a data item character representing the work step characteristic information, and taking each of the rest data as an independent data item; all data items of one process step are connected in series to form a process parameter decision support quintuple T i (ii) a A plurality of process parameter decision support quintuple formed by process parameter decision data contained in a complete machining process route form a tuple set T.
Further, the expression of tuple set T is as follows:
T＝{T 1 ,T 2 ,...,T i }
T i ＝(character i ,tool i ,spindle_speed i ,feed_rate i ,depth_of_cut i )
wherein, T i Technological parameter block for forming ith process step data in tuple setPolicy support quintuple, character i Tool is the process step characteristic information formed by combining the process step of the ith process step, a processing machine tool and a material mark i Spindle _ speed, the tool of the ith process step i Feed _ rate, the spindle speed of the i-th process step i Depth of cut is the feed of the ith process step i The cutting depth of the ith process step.
Specifically, in step S3, the step of constructing a process parameter decision support item head table specifically includes:
and counting the frequency of each data item D, and storing all data items with weights larger than a weight threshold weight _ threshold into an item head table according to the weight _ data descending order of the data items.
Further, the weight _ data specifically includes:
wherein weight _ data (D) is the weight of the data item D, F (D) is the frequency of the data item D,
support of quintuple T for process parameter decision in input i Tool is the total number of tools.
Further, the weight threshold weight _ threshold is specifically:
weight_threhold＝α fp ×Num T
wherein, num T Is the total number of input tuple sets T.
Specifically, in step S4, constructing a process parameter decision support FP tree specifically includes:
support each process parameter decision to quintuple T i The data items in the FP tree are inserted into the FP tree in a node mode one by one according to the sequence in the item header table; if the node N is a new node, inserting the node and setting the node frequency F (N) to be 1, and if the new node N is a step characteristic information character, linking the data item corresponding to the item head table to the node through the node linked list; if the node N is an existing node, the frequency F (N) of the corresponding node is increased by one.
Specifically, in step S5, a process parameter decision support frequent tuple T is formed f The method specifically comprises the following steps:
finding all nodes corresponding to each step characteristic information character in the item head table in the FP tree through the node linked list; if the node target is a leaf node, directly searching the ancestor node anecessor upwards until the root node, and if the node target is not the leaf node, searching the child node child downwards once and then searching the ancestor node anecessor upwards until the root node; connecting data items corresponding to paths formed by nodes of which the searched node weights weight _ nodes all meet weight threshold weight _ threshold in series to form process parameter decision support frequent tuple T corresponding to step characteristic information character f 。
Further, process parameter decision supports frequent tuple T f The method comprises the following specific steps:
T f (character f )＝(tool f ,spindle_speed f ,feed_rate f ,depth_of_cut f )
among them, character f Tool as process step characteristic information f Spindle _ speed as tool feature information f Is the spindle speed, feed _ rate f Is the feed amount, depth _ of _ cut f Is the depth of cut.
Another technical solution of the present invention is a machining process parameter decision support knowledge mining system, comprising:
the data module is used for acquiring process data from the part machining process card, preprocessing the acquired process data and extracting process parameter decision support data;
the input module takes the process parameter decision support data of the same family of parts extracted by the data module as the input of the FP-growth method and sets a support degree threshold value alpha fp ；
The first construction module is used for scanning the process parameter decision support data input by the input module for the first time and constructing a process parameter decision support item head table;
the second construction module is used for scanning the process parameter decision support data input by the input module for the second time and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed by the first construction module;
and the mining module is used for mining the process parameter decision support FP tree constructed by the second construction module by adopting an improved FP tree mining method, taking each step characteristic information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step characteristic information character f As a corresponding rule suffix;
a decision module for supporting frequent tuple T by decision of all the step characteristic information character of the mining module and the corresponding process parameter mined f And storing the decision-making support knowledge as machining process parameters into a knowledge base to support process parameter decision-making, and finding a corresponding cutter and cutting amount decision scheme through the step characteristic information in the process parameter decision-making.
Compared with the prior art, the invention at least has the following beneficial effects:
the invention provides a method for mining decision-making support knowledge of machining process parameters, which fully considers the incidence relation and the dependency relation among process data, filters out process data which can be calculated by other decision-making support data items through three processes of item head table establishment, FP tree construction and FP tree mining in an improved algorithm, improves the overall operation efficiency of the method, avoids the occurrence of redundant process parameter decision-making support knowledge, and does not need manual follow-up filtering and screening of knowledge.
Furthermore, by setting process parameter decision support data, filtering out data irrelevant to process parameter decision, and filtering out data relevant to process parameter decision but obtained by calculating other process parameter decision data, the screening of process parameter decision related data in the machining process card is realized; meanwhile, the three process data items of the process step, the machine tool and the material grade have great influence on the decision of a cutter, cutting consumption and the like of one process step, so that the three items are combined to realize the representation of the characteristics of the process step.
Furthermore, by setting the tuple set T, process parameter decision data contained in a complete machining process route is integrated, and meanwhile, structured representation is realized, so that subsequent process parameter decision support knowledge mining is facilitated.
Furthermore, in the process of establishing an item head table of the FP-growth algorithm, the concept of a data item weight is introduced, and a tool data item is placed at the head of the item head table, so that the tool data item can be ensured to be immediately behind a root node when an FP tree is established, and a tool is contained in each path of the FP tree, thereby avoiding the occurrence of redundant knowledge of cutting parameter decision making when the tool decision is not made.
Furthermore, in the calculation of the weight, the frequency of the tool data items is added to the total number of the process parameter decision support quintuple, so that the weight is larger than other non-tool data items, and all the tool data items appear at the head of the item head table.
Furthermore, the weight threshold is set as the product of the support threshold and the total number of the tuple sets instead of the product of the support threshold and the total number of all input data, so that only the number of input process routes needs to be considered when the support threshold is set, and the influence on the setting of the support threshold caused by different process routes with different numbers of steps is avoided.
Furthermore, in the building process of the FP tree of the FP-growth algorithm, only the data items related to the step characteristic information in the item head table are linked with the corresponding nodes through the node linked lists, so that the occurrence of meaningless node linked lists is avoided, and the spatial performance is improved.
Furthermore, in the FP tree mining process of the FP-growth algorithm, the sub-nodes (if existing) of the step characteristic information are used as leaf nodes to perform frequent item mining, so that the operation efficiency is improved, and the data item with relatively low frequency of cutting depth is prevented from not being added into the process parameter decision support frequent tuple; meanwhile, aiming at the adjustment of the FP tree mining mode, the concept of node weight is introduced to calculate the support degree.
Furthermore, the process parameter decision support frequent tuple is set, so that the correspondence between the process step characteristic information and the process parameter decision support data item set is realized, the process step characteristic information and the process parameter decision support data item set are used as process parameter decision support knowledge to be output, a meaningless process parameter decision frequent mode is avoided from being used as the knowledge, the readability and the usability of the knowledge are improved, and the redundancy rate of the knowledge is reduced.
In conclusion, the FP-growth algorithm is improved and applied to the field of manufacturing process knowledge mining, so that the high-efficiency and redundancy-free intelligent mining of machining process parameter decision support knowledge is realized, the decision of a cutter and cutting amount during process design in machining process planning can be effectively supported, and the efficiency and quality of process parameter decision during process planning are improved.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a partial schematic view of a machining process card according to the present invention, wherein (a) is a process card for punching a positioning hole of a 2a60 integrated impeller, and (b) is a process card for milling the integrated impeller of the 2a60 integrated impeller;
FIG. 3 is a detailed flow chart of the improved FP-growth algorithm of the present invention;
FIG. 4 is a schematic diagram of a process parameter decision support FP tree construction, wherein (a) is a schematic diagram of inserting an FP tree in a first step of milling a whole impeller, (b) is a schematic diagram of inserting an FP tree in a second step of milling the whole impeller, and (c) is a schematic diagram of inserting an FP tree in a third step of milling the whole impeller;
FIG. 5 is a schematic diagram of FP tree mining supported by process parameter decision making according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and some details may be omitted for clarity of presentation. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are merely exemplary, and deviations may occur in practice due to manufacturing tolerances or technical limitations, and a person skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions, according to actual needs.
The invention provides a machining process parameter decision support knowledge mining method, which comprises the steps of firstly extracting data for supporting process parameter decision from a part machining process card; taking the preprocessed process parameter decision support data of the same family of parts as input; then, data input by first scanning is used for constructing a process parameter decision support item head table; then, data input by the second scanning is used for constructing a process parameter decision support FP tree; then, excavating a process parameter decision support FP tree to form a process parameter decision support frequent tuple; and finally, storing all the mined process parameter decision support frequent tuples into a knowledge base to support process parameter decision. The invention realizes the excavation of process parameter decision support knowledge, can support the decision of cutter and cutting amount during the planning of the machining process, and compared with the traditional method, the method can efficiently excavate the process parameter decision support knowledge and can avoid the occurrence of redundant knowledge by improving three processes of item head table establishment, FP tree construction and FP tree excavation in the FP-growth algorithm.
Referring to fig. 1, the method for mining knowledge supported by machining process parameter decision of the present invention includes the following steps:
s1, acquiring process data from a part machining process card, preprocessing the process data, extracting process parameter decision support data for supporting process parameter decision, and forming a process parameter decision support quintuple;
the process parameter decision support data comprises a process step operation step, a machine tool, a material grade, a cutter tool, a spindle speed, a feed rate and a cutting depth of cut; combining the step operation step, the machine tool and the material grade mark into a data item character representing the step characteristic information, and taking the rest data as an independent data item; all data items of one process step are connected in series to form a process parameter decision support quintuple T i (ii) a A plurality of process parameter decision support quintuple formed by process parameter decision data contained in a complete machining process route form a tuple set T.
The expression of tuple set T is as follows:
T＝{T 1 ,T 2 ,...,T i }
T i ＝(character i ,tool i ,spindle_speed i ,feed_rate i ,depth_of_cut i )
wherein, T i Five tuple, character, is supported by process parameter decision formed for ith process step data in tuple set i Is the step of the ith process stepTool and tool machine, material grade combined process step characteristic information tool i Spindle _ speed, the tool of the ith process step i Is the spindle speed, feed _ rate, of the ith process step i Depth of cut is the feed of the ith process step i The cutting depth of the ith process step.
S2, taking the process parameter decision support data of the same family of parts preprocessed in the step S1 as input, and setting a support degree threshold alpha fp ；
S3, scanning the process parameter decision support data input in the step S2 for the first time, and constructing a process parameter decision support item head table;
counting the frequency of each data item D, and storing all data items with weights larger than a weight threshold weight _ threshold into an item head table in descending order according to the weight _ data of the data item;
the calculation formula of the weight _ data is as follows:
wherein weight _ data (D) is the weight of the data item D, F (D) is the frequency of the data item D,
support of quintuple T for process parameter decision in input i The tool is the total number of the tool;
the weight threshold weight _ threshold is calculated as:
weight_threhold＝α fp ×Num T
wherein alpha is fp To set a threshold for support in the (0, 1) range, num T Is the total number of tuples T entered.
S4, scanning the process parameter decision support data input in the step S2 for the second time, and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed in the step S3;
support quintuple T for each process parameter decision i The data items are arranged in the sequence of the item header tableInserting the FP trees in a node mode one by one; if the node N is a new node, inserting the node and setting the node frequency F (N) to be 1, and if the new node N is a step characteristic information character, linking the data item corresponding to the item head table to the node through the node linked list; if the node N is an existing node, the frequency F (N) of the corresponding node is increased by one.
S5, mining the process parameter decision support FP tree constructed in the step S4 to form a process parameter decision support frequent tuple T f ；
For each step characteristic information character in the item head table, finding all nodes corresponding to the item head in the FP tree through a node chain table; if the node target is already a leaf node, directly searching the ancestor node processor to the root node, and if the node target is not the leaf node, searching the child node child downwards once and then searching the ancestor node processor to the root node; connecting data items corresponding to paths formed by nodes of which the searched node weights weight _ nodes all meet weight threshold weight _ threshold in series to form process parameter decision support frequent tuple T corresponding to step characteristic information character f ；
The calculation formula of the node weight _ node is as follows:
wherein, weight _ node (N) is the node weight of the node N, F (N) is the node frequency of the node N, child is the child node of the process step characteristic information node, target is the process step characteristic information node, and the processor is the ancestor node of the process step characteristic information node,
accumulating the node frequency numbers of all target sub-nodes of the node N;
process parameter decision support frequent tuple T f The expression of (a) is:
T f (character f )＝(tool f ,spindle_speed f ,feed_rate f ,depth_of_cut f )
wherein, the tool f Supporting frequent tuples T for a process parameter decision f The spindle speed spindle _ speed f Feed amount feed _ rate f Depth of cut f Supporting frequent tuples T for a process parameter decision f Items that may be included in (1).
S6, making decision support on frequent tuples T of all the process parameters mined in the step S5 f And storing the data into a knowledge base to support process parameter decision.
In another embodiment of the present invention, a machining process parameter decision support knowledge mining system is provided, which can be used to implement the above machining process parameter decision support knowledge mining method, and specifically, the machining process parameter decision support knowledge mining system includes a data module, an input module, a first construction module, a second construction module, a mining module, and a decision module.
The data module acquires process data from the part machining process card, preprocesses the acquired process data, and extracts process parameter decision support data;
the input module takes the process parameter decision support data of the same family of parts extracted by the data module as the input of the FP-growth method and sets a support degree threshold value alpha fp ；
The first construction module is used for scanning the process parameter decision support data input by the input module for the first time and constructing a process parameter decision support item head table;
the second construction module is used for scanning the process parameter decision support data input by the input module for the second time and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed by the first construction module;
and the mining module is used for mining the process parameter decision support FP tree constructed by the second construction module by adopting an improved FP tree mining method, taking each step characteristic information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step characteristic information character f As a corresponding rule suffix;
a decision module for supporting frequent tuple T by decision of all the step characteristic information character of the mining module and the corresponding process parameter mined f And storing the decision-making support knowledge as machining process parameters into a knowledge base to support process parameter decision-making, and finding a corresponding cutter and cutting amount decision scheme through the step characteristic information in the process parameter decision-making.
In yet another embodiment of the present invention, a terminal device is provided that includes a processor and a memory for storing a computer program comprising program instructions, the processor being configured to execute the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is adapted to implement one or more instructions, and is specifically adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor provided by the embodiment of the invention can be used for operation of a machining process parameter decision support knowledge mining method, and comprises the following steps:
acquiring process data from a part machining process card, preprocessing the acquired process data, and extracting process parameter decision support data; the extracted process parameter decision support data of the same family parts are used as the input of the FP-growth method, and a support degree threshold value alpha is set fp (ii) a Firstly scanning input process parameter decision support data, and constructing a process parameter decision support item head table; the process parameter decision support data input by the second scanning is constructed into a process parameter decision support FP tree based on the constructed process parameter decision support item head table; the process parameter decision support FP tree excavated and constructed by the improved FP tree excavation method is adopted, using each step characteristic information character as a rule antecedent, and mining each step characteristic information characterFrequent tuple T is supported by all process parameter decisions corresponding to step characteristic information character f As a corresponding rule suffix; decision support frequent tuple T of all step characteristic information characters and corresponding process parameters obtained by mining f And storing the machining process parameter decision support knowledge into a knowledge base to support process parameter decision, and finding a corresponding cutter and cutting amount decision scheme through the process step characteristic information in the process parameter decision.
In still another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a Memory device in a terminal device and is used for storing programs and data. It is understood that the computer readable storage medium herein may include a built-in storage medium in the terminal device, and may also include an extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. It should be noted that the computer-readable storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory.
One or more instructions stored in the computer-readable storage medium may be loaded and executed by the processor to implement the corresponding steps of the method for mining knowledge about machining process parameter decision support in the above embodiments; one or more instructions in the computer-readable storage medium are loaded by the processor and perform the steps of:
acquiring process data from a part machining process card, preprocessing the acquired process data, and extracting process parameter decision support data; the extracted process parameter decision support data of the same family of parts is used as the input of the FP-growth method, and a support degree threshold value alpha is set fp (ii) a The process parameter decision support data of the first scanning input is constructed to the process parameterA decision support item header table; the process parameter decision support data input by the second scanning is constructed into a process parameter decision support FP tree based on the constructed process parameter decision support item head table; mining the constructed process parameter decision support FP tree by adopting an improved FP tree mining method, taking each step characteristic information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step characteristic information character f (ii) a Decision support frequent tuple T of all step characteristic information characters and corresponding process parameters obtained by mining f And storing the machining process parameter decision support knowledge into a knowledge base to support process parameter decision, and finding a corresponding cutter and cutting amount decision scheme through the process step characteristic information in the process parameter decision.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The process data is acquired from machining process cards in Excel form, each Excel file contains all the machining process cards of one part, each Excel file contains a plurality of sub-tables, and each sub-table is a process card of one process. Using a complete machining process card of 30 impeller parts, and obtaining 30 tuple sets T through pretreatment, wherein the tuple sets T totally comprise 620 process parameter decision support quintuple sets T i . A partial process card of an integral impeller component is shown in figure 2.
Please refer to fig. 3, aAnd (3) excavating the decision support knowledge of the machining process parameters by using an improved FP-growth algorithm. The five-tuple set T is supported by the decision of the 30 tuple sets T obtained by the pretreatment and 620 process parameters in total i As an input, a support degree threshold α is set fp 40 percent; scanning 30 tuple sets T input for the first time, counting frequency F (D) of each data item D, calculating weight _ data, and then storing the data items D which are greater than weight threshold weight _ threshold =12 into an item head table in a descending order; and (3) scanning 30 tuple sets T input for the second time, and circularly traversing the process parameter decision support quintuple T i (ii) a Traversal of process parameter decision support quintuple T in order of entry header table i Data item D in (1); judging whether the data item D is an existing node in the FP tree or not; if the node is an existing node, adding one to the corresponding node frequency F (N); if the node is not the existing node, inserting the node N, setting the node frequency F (N) to be 1, and if the node is the step characteristic information character, linking the data item corresponding to the item head table to the node through the node linked list; after all data in the tuple set T are traversed, the construction of the FP tree is completed, and the excavation of the FP tree is started; for each step characteristic information character in the item head table, finding all nodes corresponding to the characteristic information character in the FP tree through a node linked list; if the corresponding node is not a leaf node, searching the child node downwards once, and calculating the weight _ node of the node; then searching the ancestor nodes upwards and calculating the node weights weight _ nodes of all path nodes until reaching the root node; connecting data items corresponding to paths formed by nodes of which the searched node weights weight _ node all meet weight threshold weight _ threshold in series to form process parameter decision support frequent tuple T corresponding to step characteristic information character f As process parameter decision support knowledge.
Process parameter decision support quintuple T i Example of inserting FP Tree referring to FIG. 4, a five tuple T is supported for process parameter decision i From the three process steps in fig. 2 b. Five-tuple T is supported by process parameter decision in FIGS. 4a, 4b i The data items in the item list are all new nodes, therefore, the new nodes are inserted according to the sequence in the item head list, the node frequency is set to be 1, and the item head list is linked with the step characteristic information nodes through the node linked list. The tool, depth of cut, feed rate in FIG. 4c are the existing nodes, so the node count is incremented by one; the spindle speed spindle _ speed and the step characteristic information character are new nodes, so that the new nodes are inserted after the existing nodes.
Process parameter decision support frequent tuple T f Referring to fig. 5, first, two nodes corresponding to the step characteristic information character rough turning rear end-numerically controlled lathe-2 a60 in the FP-tree are found; one node is a leaf node, the corresponding node frequency is 16, so that an ancestor node operator is directly searched upwards, and the node weight _ node of the ancestor node is set to be 16; the other node is not a leaf node, the corresponding node frequency is 14, the child node is searched downwards once, the frequency of the child node child is 14, therefore, the node weight _ node of the child node is 14, the ancestor node anecessor is searched upwards, and 14 is added on the basis of the original 16; two paths are formed by nodes meeting weight threshold weight _ threshold =12, so that data items are connected in series to obtain two process parameter decision-support frequent tuples T f 。
The mined process parameter decision support knowledge (part of) is shown in table 1, and 16 process parameter decision support frequent tuples, namely 16 pieces of process parameter decision support knowledge, are mined.
TABLE 1 Process parameter decision support knowledge (modified FP-growth algorithm)
The process parameter decision support knowledge (part of) mined by the unmodified FP-growth algorithm is shown in Table 2, and 52 frequent patterns are mined in total. It can be seen that a great number of meaningless frequent patterns occur when the traditional FP-growth algorithm is used for process parameter decision knowledge mining, for example, decisions on feed amount and cutting depth are made under the condition that the spindle rotation speed is known; the excavated frequent modes which can be directly used are 10, and account for 19.2%; the number of the usable frequent modes is 7 after adjustment and combination, and 6 knowledge items are generated after combination, which accounts for 13.5%; the rest frequent patterns are invalid contents, and 35 frequent patterns account for 67.3 percent; namely, the redundancy rate of process parameter decision support knowledge mined by the traditional FP-growth algorithm reaches 69.2 percent; and in time consumption, the traditional FP-growth algorithm is 1.5 times of the improved FP-growth algorithm.
TABLE 2 decision support knowledge of process parameters (traditional FP-growth algorithm)
In conclusion, the method and the system for mining the machining process parameter decision support knowledge realize the mining of the process parameter decision support knowledge, can support the tool and cutting dosage decision during process design in the machining process planning, and can efficiently mine the process parameter decision support knowledge for process data accumulated by enterprises and avoid the occurrence of redundant knowledge compared with the traditional method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (10)
1. A machining process parameter decision support knowledge mining method is characterized by comprising the following steps:
s1, acquiring process data from a part machining process card, preprocessing the acquired process data, and extracting process parameter decision support data;
s2, taking the process parameter decision support data of the same family of parts extracted in the step S1 as the input of the FP-growth method, and setting a support degree threshold value alpha fp ；
S3, scanning the process parameter decision support data input in the step S2 for the first time, and constructing a process parameter decision support item head table;
s4, scanning the process parameter decision support data input in the step S2 for the second time, and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed in the step S3;
s5, mining the process parameter decision support FP tree constructed in the step S4 by adopting an improved FP tree mining method, taking each step feature information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step feature information character f As a corresponding rule suffix;
s6, all the step characteristic information characters in the step S5 and the corresponding process parameter decision support frequent tuples T obtained by mining f And storing the decision-making support knowledge as machining process parameters into a knowledge base to support process parameter decision-making, and finding a corresponding cutter and cutting amount decision scheme through the step characteristic information in the process parameter decision-making.
2. The method according to claim 1, wherein in step S1, the process parameter decision support data includes a process step operation step, a machine tool machine, a material grade material track, a tool, a spindle speed, a feed rate, a depth of cut, of cut; combining the step operation step, the machine tool and the material grade mark into a data item character representing the step characteristic information, and taking each of the rest data as an independent data item; all data items of one process step are connected in series to form a process parameter decision support quintuple T i (ii) a A plurality of process parameter decision support quintuple formed by process parameter decision data contained in a complete machining process route form a tuple set T.
3. The method of claim 2, wherein tuple set T is expressed as follows:
T＝{T 1 ,T 2 ,...,T i }
T i ＝(character i ,tool i ,spindle_speed i ,feed_rate i ,depth_of_cut i )
wherein, T i Five tuple, character, is supported by process parameter decision formed for ith process step data in tuple set i Tool is the process step characteristic information formed by combining the process step of the ith process step, a processing machine tool and a material mark i Spindle _ speed, the tool of the ith process step i Is the spindle speed, feed _ rate, of the ith process step i Depth _ of _ cut as the feed amount of the ith process step i The cutting depth of the ith process step.
4. The method according to claim 1, wherein in step S3, the step of constructing a process parameter decision support item header table specifically comprises:
and counting the frequency of each data item D, and storing all data items with weights larger than a weight threshold weight _ threshold into an item head table according to the weight _ data descending order of the data items.
5. The method of claim 4, wherein the weight _ data is specifically:
wherein weight _ data (D) is the weight of the data item D, F (D) is the frequency of the data item D,
support of quintuple T for process parameter decision in input i Tool is the total number of tool.
6. The method according to claim 4, wherein the weight threshold weight _ threshold is specifically:
weight_threhold＝α fp ×Num T
wherein, num T Is the total number of input tuple sets T.
7. The method according to claim 1, wherein in step S4, constructing a process parameter decision support FP-tree specifically comprises:
support each process parameter decision to quintuple T i The data items in the FP tree are inserted into the FP tree in a node mode one by one according to the sequence in the item header table; if the node N is a new node, inserting the node and setting the node frequency F (N) to be 1, and if the new node N is a step characteristic information character, linking the data item corresponding to the item head table to the node through the node linked list; if the node N is an existing node, the frequency F (N) of the corresponding node is increased by one.
8. The method of claim 1, wherein in step S5, forming a process parameter decision support frequent tuple T f The method comprises the following specific steps:
finding all nodes corresponding to each step characteristic information character in the item head table in the FP tree through a node linked list; if the node target is a leaf node, directly searching the ancestor node processor upwards until reaching the root node, and if the node target is not a leaf node, searching the child node child downwards and then searching the ancestor node processor upwards until reaching the root node; connecting data items corresponding to paths formed by nodes of which the searched node weights weight _ nodes all meet weight threshold weight _ threshold in series to form process parameter decision support frequent tuple T corresponding to step characteristic information character f 。
9. The method of claim 8, wherein process parameter decision supports frequent tuples T f The method specifically comprises the following steps:
T f (character f )＝(tool f ,spindle_speed f ,feed_rate f ,depth_of_cut f )
among them, the character f For process step characteristic information, tool f Spindle _ speed as tool feature information f Is the spindle speed, feed _ rate f Is the feed amount, depth _ of _ cut f Is the depth of cut.
10. A machining process parameter decision support knowledge mining system is characterized by comprising:
the data module is used for acquiring process data from the part machining process card, preprocessing the acquired process data and extracting process parameter decision support data;
the input module takes the process parameter decision support data of the same family of parts extracted by the data module as the input of the FP-growth method and sets a support degree threshold value alpha fp ；
The first construction module is used for scanning the process parameter decision support data input by the input module for the first time and constructing a process parameter decision support item head table;
the second construction module is used for scanning the process parameter decision support data input by the input module for the second time and constructing a process parameter decision support FP tree based on the process parameter decision support item head table constructed by the first construction module;
and the mining module is used for mining the process parameter decision support FP tree constructed by the second construction module by adopting an improved FP tree mining method, taking each step characteristic information character as a rule antecedent, mining all process parameter decision support frequent tuples T corresponding to each step characteristic information character f As a corresponding rule suffix;
a decision module for supporting the decision of the frequent tuples T of all the step characteristic information character of the mining module and the corresponding process parameters mined f And storing the decision-making support knowledge as machining process parameters into a knowledge base to support process parameter decision-making, and finding a corresponding cutter and cutting amount decision scheme through the step characteristic information in the process parameter decision-making.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110780789.7A CN113449868B (en) | 2021-07-09 | 2021-07-09 | Machining process parameter decision support knowledge mining method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110780789.7A CN113449868B (en) | 2021-07-09 | 2021-07-09 | Machining process parameter decision support knowledge mining method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113449868A CN113449868A (en) | 2021-09-28 |
| CN113449868B true CN113449868B (en) | 2022-12-09 |
Family
ID=77815921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110780789.7A Active CN113449868B (en) | 2021-07-09 | 2021-07-09 | Machining process parameter decision support knowledge mining method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449868B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258049A (en) * | 2013-05-27 | 2013-08-21 | 重庆邮电大学 | Association rule mining method based on mass data |
| CN104281617A (en) * | 2013-07-10 | 2015-01-14 | 广州中国科学院先进技术研究所 | Domain knowledge-based multilayer association rules mining method and system |
| CN112784899B (en) * | 2021-01-20 | 2023-04-18 | 中国电力科学研究院有限公司 | Method, device and equipment for mining frequent pattern of power transformation operation and maintenance knowledge and storage medium |
-
2021
- 2021-07-09 CN CN202110780789.7A patent/CN113449868B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113449868A (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Morabito et al. | An and—or-graph approach for two-dimensional cutting problems | |
| CN102308533B (en) | Classification method and device for packets | |
| CN103218692B (en) | Workflow mining method based on dependence analysis between activity | |
| CN104360634A (en) | Skin mirror image milling numerical control program fast generating method based on features | |
| CN109002006B (en) | Processing route optimization method based on low-carbon low-cost constraint | |
| CN103341787A (en) | Numerical control machining cutter radius compensation method based on characteristics | |
| US20080109097A1 (en) | Machining step generating apparatus | |
| CN111311004A (en) | Layered iterative layout optimization method considering cutting efficiency and utilization rate | |
| US20030033048A1 (en) | Similar machining data searching apparatus and automatic programming apparatus | |
| CN106227770B (en) | A kind of intelligentized news web page information extraction method | |
| CN106843153A (en) | The reusable NC technology mapping method of process oriented scheme | |
| CN112988305A (en) | Policy flow processing method and device, computer equipment and storage medium | |
| CN113449868B (en) | Machining process parameter decision support knowledge mining method and system | |
| CN101833553B (en) | Method, equipment and system for clustering data | |
| CN115113584B (en) | Numerical control automatic programming method based on example and rule reasoning | |
| CN116305622A (en) | Cutter head module configuration design method based on Internet and shield tunneling machine | |
| CN105335467A (en) | Novelty judgment method and system for hot topics in publishing industry | |
| CN103530436A (en) | Tooling layout drawing parameterization generation method based on AUTOCAD. NET API | |
| CN112464648A (en) | Industry standard blank feature recognition system and method based on multi-source data analysis | |
| JP6160522B2 (en) | Design management apparatus and program | |
| Wang et al. | Optimization of the tool selection based on big data | |
| Geng et al. | A novel approach of automatically designing EDM electrodes for machining uncut regions | |
| JP3185342B2 (en) | Figure pattern data processing method | |
| CN113449397B (en) | Machining process route knowledge mining method and system | |
| CN117494726B (en) | Information keyword extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |