WO2022127797A1 - 生产流水线中的异常环节定位方法、装置及电子设备 - Google Patents

生产流水线中的异常环节定位方法、装置及电子设备 Download PDF

Info

Publication number
WO2022127797A1
WO2022127797A1 PCT/CN2021/138159 CN2021138159W WO2022127797A1 WO 2022127797 A1 WO2022127797 A1 WO 2022127797A1 CN 2021138159 W CN2021138159 W CN 2021138159W WO 2022127797 A1 WO2022127797 A1 WO 2022127797A1
Authority
WO
WIPO (PCT)
Prior art keywords
circulation
product
network
node
production line
Prior art date
Application number
PCT/CN2021/138159
Other languages
English (en)
French (fr)
Inventor
温少扬
张青
宋建华
周振华
Original Assignee
第四范式(北京)技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 第四范式(北京)技术有限公司 filed Critical 第四范式(北京)技术有限公司
Publication of WO2022127797A1 publication Critical patent/WO2022127797A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462Approximate or statistical queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • G06F16/285Clustering or classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/11Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/12Simultaneous equations, e.g. systems of linear equations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04Manufacturing
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Definitions

  • the present disclosure relates to the field of processing and manufacturing, and more particularly, to a method for locating abnormal links in a production line, a device for locating abnormal links in a production line, an electronic device, and a computer-readable storage medium.
  • An object of the embodiments of the present disclosure is to provide a new technical solution for locating abnormal links in a production line.
  • a method for locating abnormal links in a production line includes: acquiring production flow data of each product in a product set on the production line and a label for whether each product is a good product; constructing the The circulation network of the production line, wherein the production circulation data of a product corresponds to a circulation path in the process network; according to the label of whether each product is a good product, the yield rate corresponding to each circulation path in the circulation network is counted; Each circulation path in the circulation network and the yield rate corresponding to each circulation path are used to locate abnormal links in the production line.
  • a device for locating abnormal links in a production line comprising:
  • the acquisition module is configured to acquire the production flow data of each product in the product set on the production line and the label of whether each product is a good product;
  • a building module configured to construct a flow network of the production line, wherein the production flow data of a product corresponds to a flow path in the flow network;
  • the statistics module is configured to count the yield rate corresponding to each circulation path in the circulation network according to the label of whether each product is a good product;
  • the positioning module is configured to locate abnormal links in the production line according to each circulation path in the circulation network and the yield rate corresponding to each circulation path.
  • an apparatus comprising at least one computing device and at least one storage device, wherein the at least one storage device is configured to store instructions configured to control the at least one storage device
  • a computing device performs the method according to the first aspect above.
  • a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method as described in the first aspect above.
  • the production flow data of a product can be corresponding to a flow path of the flow network of the constructed production line, and at the same time, according to whether each product is a good product label , to count the yield rate corresponding to each circulation path in the circulation network, and then locate the abnormal link in the production line according to each circulation path in the circulation network and the yield rate corresponding to each circulation path, that is, the embodiment of the present disclosure Using the production flow data between each process in the product production process, the abnormal links in the production process are quickly and accurately located.
  • FIG. 1 is a block diagram showing an example of a hardware configuration of an electronic device that can be used to implement embodiments of the present disclosure
  • FIG. 2 shows a schematic flowchart of a method for locating abnormal links in a production line according to an embodiment of the present disclosure
  • FIG. 3 shows a schematic diagram of a flow network according to an embodiment of the present disclosure
  • FIG. 4 shows a schematic diagram of a flow network according to another embodiment of the present disclosure.
  • FIG. 5 shows a functional block diagram of an abnormal link device in a production line according to an embodiment of the present disclosure.
  • FIG. 1 shows the hardware structure of an arbitrary electronic device.
  • the electronic device shown in FIG. 1 may be a portable computer, a desktop computer, a workstation, a server, etc., or any other device having a computing device such as a processor and a storage device such as a memory, which is not limited herein.
  • the electronic device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like.
  • the processor 1100 is used for executing computer programs.
  • the computer program can be written using an instruction set of architectures such as x86, Arm, RISC, MIPS, SSE, and the like.
  • the memory 1200 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a nonvolatile memory such as a hard disk, and the like.
  • the interface device 1300 includes, for example, a USB interface, an earphone interface, and the like.
  • the communication device 1400 is capable of, for example, wired or wireless communication, and may specifically include Wifi communication, Bluetooth communication, 2G/3G/4G/5G communication, and the like.
  • the display device 1500 is, for example, a liquid crystal display, a touch display, or the like.
  • the input device 1600 may include, for example, a touch screen, a keyboard, a somatosensory input, and the like.
  • the electronic device 1000 can output voice information through the speaker 1700, and can collect voice information through the microphone 1800, and the like.
  • the memory 1200 of the electronic device 1000 is configured to store instructions, and the instructions are configured to control the processor 1100 to operate to execute an abnormal link in the production pipeline of the embodiment of the present disclosure positioning method.
  • a skilled person can design instructions according to the solutions disclosed in the present disclosure. How the instruction controls the processor to operate is well known in the art, so it will not be described in detail here.
  • an apparatus in one embodiment, includes at least one computing device and at least one storage device, the at least one storage device configured to store instructions configured to control the at least one computing device to perform any Methods of Examples.
  • the device may include at least one electronic device 1000 shown in FIG. 1 to provide at least one computing device such as a processor and at least one storage device such as a memory, which is not limited herein.
  • a method for locating abnormal links in a production line may be implemented by an electronic device, and the electronic device may be the electronic device 1000 shown in FIG. 1 .
  • the device 1000 may be a server or a terminal device. That is, the method in this embodiment may be implemented by a server, may also be implemented by a terminal device, or may be implemented jointly by the server and the terminal device.
  • the interaction may include human-computer interaction.
  • the interaction may include the interaction between the server and the terminal device.
  • the method for locating abnormal links in the production line of this embodiment may include the following steps S2100 to S2400:
  • step S2100 the production flow data of each product in the product set on the production line and the label of whether each product is a good product are acquired.
  • a product set can be a set of the same product produced by any producer, and the same product can usually have the same material.
  • the product set may be a set of vehicles produced by a vehicle manufacturer, and for example, the product set may be a set of parts produced by any part manufacturer.
  • the production flow data of the product includes: the batch information of the material that produces the product, and the identification information of the equipment of each process of the production line through which the material passes.
  • a product usually goes through multiple processing procedures from the material to obtain the final product.
  • the same material A may correspond to multiple production batches, for example, material A corresponds to three batches ⁇ A1, A2, A3 ⁇ , process B corresponds to four equipment ⁇ B1, B2, B3, B4 ⁇ , and the same process C
  • process D corresponds to three pieces of equipment ⁇ D1, D2, D3 ⁇
  • Figure 3 is only an example, the actual production line may also involve a variety of different materials and more. There are many processes, and there will be a variety of equipment corresponding to each process. Secondly, it is also possible to introduce new materials in the intermediate links of production.
  • the label that the product is a good product can be understood as: when the product is a good product, its corresponding label is 1, otherwise, its corresponding label is 0, and the product is a good product can be understood as yes, the product is a qualified product, otherwise, the product is unqualified product.
  • obtaining the production flow data of each product in the product set on the production line and the label of whether each product is a good product in this step S2100 may further include the following steps S2110-S2120:
  • Step S2110 sending a request to the product data system through the obtaining interface to obtain the production flow data of each product in the product set on the production line and the label of whether each product is a good product.
  • the request carries at least any one of the identification information of the product set and the identification information of each product.
  • this step S2110 it can provide a human-computer interaction interface, and obtain the production flow data of each product and the label of whether each product is a good product from the product data system based on the user's request, thereby improving the targeting of data acquisition.
  • Step S2120 receiving the production flow data of each product returned by the product data system in response to the request and a label indicating whether each product is a good product.
  • Step S2200 constructing a circulation network of the production line.
  • the circulation network of the production line may be a network structure diagram constructed according to the structure of the actual assembly line, and the constructed circulation network may be the network structure diagram shown in FIG. 3 .
  • the production flow data of a product corresponds to a flow path in the process network, such as the flow network shown in Figure 3, where the solid line 1 is a flow path, which can correspond to the production flow data of a product, that is, material A1-process B Device B1 in Process C - Device C1 in Process C - Device D2 in Process D.
  • the solid line 2 is a flow path, which can also correspond to the production flow data of a product, that is, material A2-equipment B4 in process B-equipment C2 in process C-equipment D1 in process D.
  • the circulation network of the production line constructed in this step S2200 may further include the following steps S2210-S2220:
  • Step S2210 according to the batch information of the material for producing the product and the identification information of the equipment of each process of the production line, obtain the material for producing the product and the flow relationship and the flow direction between the processes.
  • step S2210 materials and equipment are abstracted as nodes, and the flow relationship between nodes is abstracted as edges.
  • the intermediate products produced by each process will be randomly generated. Distributed to multiple nodes in the subsequent process, each dotted line represents a set of flow relationships.
  • Step S2220 using the batch information of all the materials involved in the product collection and the sign information of the equipment of each process of the production line as the nodes, the flow relationship between the nodes as the edges, and the flow direction as the direction of the edges, construct the structure. transfer network.
  • Step S2300 according to the labels of whether each product is a good product, count the yield rate corresponding to each circulation path in the circulation network.
  • the yield rate refers to the proportion of the number of good products that finally passed the test on the production line to the theoretically produced quantity of the input material.
  • the statistical yield rate corresponding to each circulation path in the circulation network may further include the following steps S2310-S2330:
  • Step S2310 Obtain the first total quantity of products on each circulation path in the circulation network.
  • the circulation network can be calculated by calculating the total number of products on the circulation path 1, and the total number of products on the circulation path 2, etc., to calculate the total number of products on any circulation path.
  • the total quantity is distinguished from the total quantity of good products on the circulation path.
  • the total quantity of products on the circulation path is called the first total quantity
  • the following total quantity of good products on the circulation path is called the first total quantity. Second total number.
  • Step S2320 acquiring the second total quantity of products labeled as good products on each circulation path.
  • the total number of good products on the flow path 1 and the total number of good products on the flow path 2 can be calculated respectively.
  • step S2330 the yield rate on each circulation path is obtained according to the first total quantity and the second total quantity corresponding to each circulation path.
  • the yield rate on the circulation path can be obtained.
  • step S2330 the formula for calculating the yield rate P i on any flow path in the flow network is as follows:
  • i represents the circulation path in the circulation network
  • i is any integer from 1 to n
  • n is the total number of circulation paths in the circulation network
  • M i represents the first total number of products on the i-th circulation path
  • Ni represents the second total quantity of products labeled as good products on the i -th flow path.
  • the yield of flow path 1 For another example, the yield rate on the flow path 2 Wait.
  • Step S2400 according to each circulation path in the circulation network and the yield rate corresponding to each circulation path, locate abnormal links in the production line.
  • any link in the production line is abnormal, which may lead to the yield of the final product.
  • the abnormal links in the production line can be quickly located.
  • each flow path includes batch information nodes of materials for producing products, and identification information nodes of equipment in each process of the production line through which the materials pass, here, in this step S2400, according to the information in the flow network
  • Each flow path and the yield rate corresponding to each flow path locating abnormal links in the production line may further include the following steps S2410-S2430:
  • step S2410 a probability model equation system is constructed with the pass rate of each node on each flow path in the flow network as an unknown parameter, and with the yield rate corresponding to the flow path as a known parameter.
  • the pass rate of material A1 on flow path 1 can be marked as P A1
  • the pass rate of equipment B1 in process B can be marked as P B1
  • the pass rate of equipment C1 in process C can be marked as P B1
  • the yield of 1 is denoted as P C1
  • the yield of the equipment D2 in the process D may be denoted as P D2
  • the yield corresponding to the flow path 1 is P 1 calculated according to the above step S2300 .
  • the pass rate of material A2 on flow path 2 can be marked as P A2
  • the pass rate of equipment B4 in process B can be marked as P B4
  • the pass rate of equipment C2 in process C can be marked as P C2
  • the yield rate of the equipment D1 can be marked as P D1
  • the yield rate corresponding to the flow path 2 is P 2 calculated according to the above step S2300 .
  • it can also be the pass rate of each node that the flow path i passes through, and the yield rate on the flow path i calculated according to the above step S2300.
  • the probability model equation set constructed in this step S2410 Can be:
  • P A1 *P B1 *P C1 *P D2 P 1 means that the pass rate P A1 , P B1 , P C1 , and P D2 of each node on the flow path 1 are unknown parameters, and the flow path 1 corresponds to
  • the yield rate P 1 is a known parameter, and the constructed probability model equation can also be understood as that the yield rate corresponding to the flow path 1 is approximately equal to the product of the pass rates of each node that the flow path 1 passes through.
  • the rate P 2 is a probability model equation constructed by known parameters, which can also be understood as that the yield rate corresponding to the flow path 2 is approximately equal to the product of the pass rates of each node that the flow path 2 passes through.
  • the probability model equation of the circulation path can be constructed, and then the probability model equation group of formula (2) can be obtained.
  • Step S2420 Solve the probability model equation set to obtain the pass rate of each node in the circulation network.
  • step S2410 after the probability model equation set shown in (2) is constructed, the unknown parameters in the probability model equation set can be solved to obtain the pass rate of each node in the circulation network.
  • solving the probability equation group in this step S2420 to obtain the pass rate of each node in the circulation network may further include the following steps S2421-S2422:
  • Step S2421 obtaining the target optimization algorithm.
  • the objective optimization algorithm may include at least one of a quadratic programming algorithm, a particle swarm algorithm, and a genetic algorithm.
  • Step S2422 according to the target optimization algorithm and the set constraints, solve the probability equation group to obtain the pass rate of each node in the circulation network.
  • the set constraints include constraints on the qualification rate of each node in the flow network.
  • the constraint on the pass rate of each node in the flow network is: the pass rate of each node is a natural number between 0 and 1.
  • L X has constraints, the value of each element is between 0 and 1, and the corresponding logarithmic value L X is less than or equal to 0.
  • the present disclosure solves the above-mentioned linear equation system through the objective optimization algorithm with constraints, and can obtain the qualification rate of each node.
  • the optimal L' X minimizes the deviation between A*L' X and L on the right side of the equation, such as but not limited to including mean error (MSE) and mean absolute error (MAE), etc., then the final solution is:
  • n represents the number of flow paths
  • f represents an error function
  • wi represents the weight of each flow path.
  • Step S2430 according to the pass rate of each node in the circulation network, locate the abnormal link in the production line.
  • locating the abnormal link in the production line may further include:
  • Step S2431 according to the pass rate of each node in the circulation network, obtain the abnormal rate of each node.
  • Step S2432 according to the abnormal rate of each node, locate the abnormal link in the production line.
  • locating the abnormal links in the production line according to the abnormal rates of each node may further include: obtaining a preset abnormal rate for each node; It is compared with the corresponding set abnormality rate; if the abnormality rate of the node is greater than the set abnormality rate, the node is determined to be an abnormal node.
  • locating the abnormal links in the production pipeline according to the abnormal rate of each node may further include: sorting the abnormal rate of each node in descending order; The node corresponding to the abnormal rate is regarded as the abnormal node.
  • the method of the embodiment of the present disclosure it is possible to correspond the production flow data of a product with a flow path of the flow network of the constructed production line, and at the same time, according to the label of whether each product is a good product, the flow network can be counted.
  • the yield rate corresponding to each circulation path, and then according to each circulation path in the circulation network and the yield rate corresponding to each circulation path, the abnormal links in the production line are located.
  • the production flow data between the processes can quickly and accurately locate the abnormal links in the production process.
  • the probability model equation set may also include the weight w i corresponding to the i-th circulation path.
  • the link positioning method may further include the following steps S3100-S3300:
  • Step S3100 Obtain the first total quantity of products on each circulation path in the circulation network.
  • Step S3200 according to the first total quantity, adjust the weight of the corresponding flow path in the probability model equation group.
  • the first total number may be proportional to the weight.
  • Another example may be that the less the total number of products on the circulation path, the smaller the weight of the probability model equation set corresponding to the circulation path is adjusted.
  • Step S3300 based on the adjusted weights, according to the target optimization algorithm and the set constraints, solve the probability model equation set, and obtain the pass rate of each node in the circulation network.
  • the weight of the circulation path in the probability model equation system can be adjusted to be smaller, so that it can be used to locate the entire abnormal link. the smaller the impact.
  • all products on a certain flow path may be unqualified products, that is, the labels of whether all products on this flow path are good products are 0, resulting in the The yield rate corresponding to the flow path is 0.
  • the method for locating abnormal links in the production line according to the embodiment of the present disclosure may further include the following steps S4100-S4200:
  • Step S4100 in the case that the yield rate corresponding to any circulation path in the circulation network is lower than the set yield rate threshold, adjust the yield rate on any circulation path.
  • the set yield threshold may be a value set according to actual application scenarios and actual application requirements, and the yield threshold may be 0.
  • the yield rate on the flow path may be adjusted to a value greater than 0 and relatively small.
  • Step S4200 according to each circulation path in the circulation network and the adjusted yield rate corresponding to each circulation path, locate the abnormal link in the production line.
  • the yield rate corresponding to any flow path when the yield rate corresponding to any flow path is 0, it supports the replacement of the yield rate corresponding to the flow path, so that the abnormal links in the production line can be positioned more accurately.
  • the method for locating abnormal links in the production line may further include the following steps S5100- S5200:
  • Step S5100 if any node in the circulation network satisfies the set filtering condition, delete any node from the circulation network to adjust the circulation path in the circulation network.
  • Step S5200 based on the adjusted circulation paths in the circulation network and the yield rates corresponding to the circulation paths, locate abnormal links in the production line.
  • the method for locating abnormal links in the production line may further include the following steps S6100-S6200 :
  • step S6100 when the number of devices in any process exceeds the set threshold for the number of devices, the multiple devices in any process are merged.
  • the set threshold for the number of devices may be a value set according to actual application scenarios and actual application requirements.
  • the multiple devices can be combined into one node.
  • Step S6200 take the batch information of all the materials involved in the product set and the flag information of the equipment after the merge processing of each process of the production line as the node, take the flow relationship between the nodes as the edge, and take the flow direction as the node. For the direction of the edge, rebuild the flow network.
  • the method for locating abnormal links in a production pipeline may further include: in response to a request for acquiring a mining result of mining a circulation network, acquiring a set display mode; displaying the constructed circulation network according to the display mode .
  • the display mode may be in graphic form.
  • the circulation network can be provided according to the set display mode, so that the display output has more friendly visibility.
  • the method for locating abnormal links in the production line may further include: dividing the circulation network, and obtaining a plurality of sub-circulation networks, so as to obtain a yield rate corresponding to each circulation path in the multiple sub-circulation networks, Locating abnormal links in the production line.
  • a complex flow network for a complex flow network, it supports splitting the processes according to the order of flow paths, thereby forming multiple sub-flow networks, and then solving from the last sub-flow network, and recursively solving the preceding word flow network .
  • a virtual node is also introduced downstream of the sub-flow network, and a virtual node E i ' is introduced to each node E i of E.
  • each virtual node E i ' has a bank's pass rate P' Ei , which represents all subsequent processes the overall impact.
  • a model equation system can be constructed.
  • the flow path 1 represented by the solid line 1 in Figure 4 can be counted through nodes B 1 , C 1 , D 1 , and E 1 , and the flow path 1 can be counted at the same time.
  • the yield rate P1, P 1 P' B1 *P C1 *P D1 *P' E1 .
  • the observed product qualification rate of the flow path 2 represented by the solid line 2 in Fig. 4 passing through the nodes B 2 , C 3 , D 3 , and E 2 can be counted, and then the following model equations can be obtained:
  • the qualified rate of the virtual node in the obtained result does not represent the qualified rate of the corresponding node, but is the total impact of all previous or subsequent processes.
  • a device 5000 for locating abnormal links in a production line is provided, as shown in FIG.
  • the obtaining module 5100 is configured to obtain the production flow data of each product in the product set on the production line and the label of whether each product is a good product.
  • the construction module 5200 is configured to construct a flow network of the production line, wherein the production flow data of a product corresponds to a flow path in the process network.
  • the statistics module 5300 is configured to count the yield rate corresponding to each circulation path in the circulation network according to the label of whether each product is a good product.
  • the locating module 5400 is configured to locate abnormal links in the production line according to each circulation path in the circulation network and the yield rate corresponding to each circulation path.
  • the production flow data includes: batch information of materials for producing products, and identification information of equipment through which the materials pass through each process of the production line.
  • the building module 5200 is specifically configured as:
  • the statistics module 5300 is specifically configured to: acquire the first total quantity of products on each circulation path in the circulation network; acquire the labels of good products on each circulation path The second total quantity of products; according to the first total quantity and the second total quantity corresponding to each of the circulation paths, the yield rate on each of the circulation paths is obtained.
  • each of the circulation paths includes batch information nodes of materials for producing products, and identification information nodes of equipment in each process of the production line through which the materials pass.
  • the positioning module 5400 is specifically configured as : using the qualified rate of each node on each circulation path in the circulation network as an unknown parameter, and with the yield rate corresponding to the circulation path as a known parameter, construct a probability model equation system; solve the probability model equation group , obtain the pass rate of each node in the circulation network; locate the abnormal link in the production line according to the pass rate of each node in the circulation network.
  • the positioning module 5400 is specifically configured to: obtain a target optimization algorithm, wherein the target optimization algorithm at least includes at least one of a quadratic programming algorithm, a particle swarm algorithm, and a genetic algorithm; According to the objective optimization algorithm and the set constraints, the probability model equations are solved to obtain the pass rate of each node in the circulation network; wherein, the set constraints include Constraints on the qualification rate of each node.
  • the restriction on the qualification rate of each node in the circulation network is: the value of the qualification rate of each node is a natural number between 0 and 1.
  • the positioning module 5400 is specifically configured to: obtain the abnormality rate of each node according to the pass rate of each node in the circulation network; Locating abnormal links in the production line.
  • the positioning module 5400 is specifically configured to: for each of the nodes, obtain a preset abnormal rate; The abnormality rate is compared; if the abnormality rate of the node is greater than the set abnormality rate, the node is determined to be an abnormal node.
  • the positioning module 5400 is specifically configured to: sort the abnormal rates of each of the nodes in descending order; and acquire the nodes corresponding to the abnormal rates of the first predetermined number as abnormal nodes.
  • the probability model equation set further includes a weight corresponding to each circulation path; the positioning module 5400 is further configured to: acquire the first number of products on each circulation path in the circulation network. a total number; according to the first total number, adjust the weight corresponding to the circulation path in the probability model equation set; based on the adjusted weight, according to the target optimization algorithm and the set constraints, solve the A probability model equation system is used to obtain the qualification rate of each node in the circulation network.
  • the positioning module 5400 is further configured to: in the case that the yield rate corresponding to any circulation path in the circulation network is lower than the set yield rate threshold, place any circulation path in the circulation network.
  • the yield rate on the path is adjusted; according to each circulation path in the circulation network and the yield rate corresponding to the adjusted circulation path, the abnormal links in the production line are located.
  • the positioning module 5400 is further configured to: in the case that any node in the circulation network satisfies the set filtering condition, delete the any node from the circulation network To adjust the circulation paths in the circulation network; locate the abnormal links in the production line based on each circulation path in the adjusted circulation network and the yield rate corresponding to each circulation
  • the building module 5200 is further configured to: in the case that the number of devices in any process exceeds the set threshold of the number of devices, combine multiple devices in any process;
  • the batch information of all the materials involved in the product set, and the identification information of the equipment after the combined processing of each process of the production line are nodes, and the flow relationship between nodes is an edge.
  • the direction is the direction of the edge, and the flow network is reconstructed.
  • the positioning module 5400 is further configured to: segment the flow network to obtain a plurality of sub-flow networks, so as to determine all the flow paths according to the yield rate corresponding to each flow path in the plurality of sub-flow networks.
  • the abnormal links in the production line are located.
  • the apparatus 5000 further includes a display module (not shown in the figure).
  • the display module is configured to acquire a set display mode in response to a request for acquiring a mining result of mining a circulation network; and display the constructed circulation network according to the display mode.
  • the obtaining module is specifically configured to: send a request to the product data system through the obtaining interface to obtain the production flow data of each product in the product set on the production line and the label of whether each product is a good product; Wherein, the request carries at least any one of the identification information of the product set and the identification information of each product; the production flow data of each product returned by the product data system in response to the request and whether each product is Good product label.
  • This embodiment provides a computer-readable storage medium, wherein a computer program is stored thereon, and the computer program implements the method according to any one of the foregoing method embodiments when executed by a processor.
  • the present disclosure may be an apparatus, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon configured to cause a processor to implement various aspects of the present disclosure.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disk read only memory
  • DVD digital versatile disk
  • memory sticks floppy disks
  • mechanically coded devices such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • the computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • the computer program instructions configured to perform the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or in one or more programming languages
  • Source or object code written in any combination of programming languages including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect).
  • LAN local area network
  • WAN wide area network
  • custom electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) can be personalized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present disclosure.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium storing the instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions that contains one or more logical functions configured to implement the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation in hardware, implementation in software, and implementation in a combination of software and hardware are all equivalent.
  • the production flow data of a product is corresponding to a flow path of the flow network of the constructed production line, and at the same time, according to the label of whether each product is a good product, the corresponding flow paths in the flow network are counted. Then, according to each circulation path in the circulation network and the yield rate corresponding to each circulation path, the abnormal links in the production line are located.
  • the flow data can quickly and accurately locate the abnormal links in the production process.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Fuzzy Systems (AREA)
  • Computational Linguistics (AREA)
  • Manufacturing & Machinery (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种生产流水线中的异常环节定位方法、装置及电子设备,该方法包括:获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签(S2100);构建所述生产流水线的流转网络(S2200);根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率(S2300);根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位(S2400)。

Description

生产流水线中的异常环节定位方法、装置及电子设备
本公开要求于2020年12月15日提交中国专利局,申请号为202011473643.X,申请名称为“生产流水线中的异常环节定位方法、装置及电子设备”的中国专利申请的优先权,其全部内容通过引用结合在本公开中。
技术领域
本公开涉及加工制造领域,更具体地,涉及一种生产流水线中的异常环节定位方法、一种生产流水线中的异常环节定位装置、一种电子设备、及一种计算机可读存储介质。
背景技术
制造业流水线生产过程中,由于每个产品从原料开始通常需要经过多道生产加工工序,最后变成产品,在此,原料或者生产设备出现异常都有可能会影响到最终产品的良品率,给生产方带来比较大的损失。
现有技术中,当出现异常之后,生产方往往只能看到最后的产品良品率有异常,很多时候由于生产工艺流程复杂,定位具体是哪个生产环节出现问题导致的异常是一件非常困难的事情,目前很多时候需要依靠工程师的经验,人工实地的去排查,很难精准定位,导致排查时间会比较长,影响生产。
发明内容
本公开实施例的一个目的是提供一种生产流水线中的异常环节定位的新的技术方案。
根据本公开的第一方面,提供一种生产流水线中的异常环节定位方法,其包括:获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签;构建所述生产流水线的流转网络,其中,一个产品的生产流转数据对应所述流程网络中的一条流转路径;根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率;根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
根据本公开的第二方面,还提供一种生产流水线中的异常环节定位装置,其包括:
获取模块,被配置为获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签;
构建模块,被配置为构建所述生产流水线的流转网络,其中,一个产品的生产流转数据对应所述流程网络中的一条流转路径;
统计模块,被配置为根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率;
定位模块,被配置为根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
根据本公开的第三方面,还提供一种包括至少一个计算装置和至少一个存储装置的设备,其中,所述至少一个存储装置被配置为存储指令,所述指令被配置为控制所述至少一个计算装置执行根据以上第一方面所述的方法。
根据本公开的第四方面,还提供一种计算机可读存储介质,其中,其上存储有计算机 程序,所述计算机程序在被处理器执行时实现如以上第一方面所述的方法。
本公开的一个有益效果在于,根据本公开实施例的方法,其能够将一个产品的生产流转数据与所构建的生产流水线的流转网络的一条流转路径对应,同时,根据各产品是否为良品的标签,来统计出流转网络中的各流转路径对应的良品率,进而根据流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位,即,本公开实施例利用产品生产过程中在各道工序间的生产流转数据,对生产过程中的异常环节进行了快速且准确的定位。
附图说明
通过以下参照附图对本公开的示例性实施例的详细描述,本公开的其它特征及其优点将会变得清楚。
图1是显示可用于实现本公开的实施例的电子设备的硬件配置的例子的框图;
图2示出了本公开实施例的生产流水线中的异常环节定位方法的流程示意图;
图3示出了本公开实施例的流转网络的示意图;
图4示出了本公开另一实施例的流转网络的示意图;
图5示出了本公开实施例的生产流水线中的异常环节装置的原理框图。
具体实施方式
现在将参照附图来详细描述本公开的各种示例性实施例。应注意到:除非另外具体说明,否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的,决不作为对本公开及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论,但在适当情况下,所述技术、方法和设备应当被视为说明书的一部分。
在这里示出和讨论的所有例子中,任何具体值应被解释为仅仅是示例性的,而不是作为限制。因此,示例性实施例的其它例子可以具有不同的值。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步讨论。
下面,参照附图描述根据本公开实施例的各个实施例和例子。
<硬件配置>
本公开实施例的方法可以由至少一台电子设备实施,即,用于实施该方法的装置5000可以布置在该至少一台电子设备上。图1示出了任意电子设备的硬件结构。图1所示的电子设备可以是便携式电脑、台式计算机、工作站、服务器等,也可以是任意的具有处理器等计算装置和存储器等存储装置的其他设备,在此不做限定。
如图1所示,该电子设备1000可以包括处理器1100、存储器1200、接口装置1300、通信装置1400、显示装置1500、输入装置1600、扬声器1700、麦克风1800等等。其中,处理器1100用于执行计算机程序。该计算机程序可以采用比如x86、Arm、RISC、MIPS、SSE等架构的指令集编写。存储器1200例如包括ROM(只读存储器)、RAM(随机存取存储器)、诸如硬盘的非易失性存储器等。接口装置1300例如包括USB接口、耳机接口等。通信装置1400例如能够进行有线或无线通信,具体地可以包括Wifi通信、蓝牙通信、2G/3G/4G/5G通信等。显示装置1500例如是液晶显示屏、触摸显示屏等。输入装置1600例如可以包括触摸屏、键盘、体感输入等。电子设备1000可以通过扬声器1700输出语音信息,及可以通过麦克风1800采集语音信息等。
图1所示的电子设备仅仅是说明性的并且决不意味着对本公开、其应用或使用的任何限制。应用于本公开的实施例中,电子设备1000的所述存储器1200被配置为存储指令,所述指令被配置为控制所述处理器1100进行操作以执行本公开实施例的生产流水线中的异常环节定位方法。技术人员可以根据本公开所公开方案设计指令。指令如何控制处理器进行操作,这是本领域公知,故在此不再详细描述。
在一个实施例中,提供了一种包括至少一个计算装置和至少一个存储装置的设备,该至少一个存储装置被配置为存储指令,该指令被配置为控制该至少一个计算装置执行根据本公开任意实施例的方法。
该设备可以包括至少一台图1所示的电子设备1000,以提供至少一个例如是处理器的计算装置和至少一个例如是存储器的存储装置,在此不做限定。
<方法实施例>
在本实施例中,提供一种生产流水线中的异常环节定位方法,该生产流水线中的异常环节定位方法可以是由电子设备实施,该电子设备可以是如图1所示的电子设备1000,电子设备1000可以是服务器,也可以是终端设备。即,本实施例的方法可以是由服务器实施,也可以是由终端设备实施,还可以是由服务器和终端设备共同实施。
在本实施例的方法有终端设备参与实施的应用中,交互可以包括人机交互。在本实施例的方法有服务器参与实施的应用中,交互可以包括服务器与终端设备之间的交互。
根据图2所示,本实施例的生产流水线中的异常环节定位方法可以包括如下步骤S2100~S2400:
步骤S2100,获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签。
产品集合可以是任意生产方所生产的同一种产品的集合,该同一种产品通常可以具有相同的物料。例如,该产品集合可以是车辆生产方所生产的车辆的集合,又例如,该产品集合可以是任意零件生产方所生产的零部件的集合。
产品的生产流转数据包括:生产产品的物料的批次信息、物料所经过生产流水线各道工序的设备的标识信息。
一个产品从物料开始通常会经过多道加工工序,才能得到最终的该产品,参照图3所示,从物料A开始,经过工序B,再经过工序C,最后经过工序D,产出最终的产品,其中,同一种物料A可能对应多个生产批次,例如物料A对应有三个批次{A1,A2,A3},工序B对应四台设备{B1,B2,B3,B4},同样工序C对应两台设备{C1,C2},工序D对应三台设备{D1,D2,D3},当然,图3仅是示例性地,实际生产流水线上可能还会涉及有多种不同的物料以及更多的工序,而且,每道工序对应的设备数量也会有多种,其次,生产中间环节也有可能引入新的物料。
产品为良品的标签可以理解为是:当产品为良品时,其对应的标签为1,反之,其对应的标签为0,产品为良品可以理解为是,产品为合格的产品,反之,产品为不合格的产品。
本实施例中,本步骤S2100中获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签可以进一步包括如下步骤S2110~S2120:
步骤S2110,通过获取接口向产品数据系统发送获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签的请求。
请求中至少携带产品集合的标识信息和各个产品的标识信息中的任意一种。
本步骤S2110中,其可以提供人机交互接口,基于用户请求从产品数据系统中获取各个产品的生产流转数据以及各产品是否为良品的标签,进而提高数据获取的靶向性。
步骤S2120,接收产品数据系统响应于请求返回的各个产品的生产流转数据以及各产品是否为良品的标签。
在获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品 的标签之后,进入:
步骤S2200,构建生产流水线的流转网络。
生产流水线的流转网络可以是根据实际的流水线的结构构建出来的网络结构图,该构建出的流转网络可以是图3所示的网络结构图。
一个产品的生产流转数据对应流程网络中的一条流转路径,如图3所示的流转网络,其中,实线1为一条流转路径,其可以对应一个产品的生产流转数据,即物料A1-工序B中的设备B1-工序C中的设备C1-工序D中的设备D2。实线2为一条流转路径,其也可以对应一个产品的生产流转数据,即物料A2-工序B中的设备B4-工序C中的设备C2-工序D中的设备D1。
本实施例中,本步骤S2200中构建生产流水线的流转网络可以进一步包括如下步骤S2210~S2220:
步骤S2210,根据生产产品的物料的批次信息以及生产流水线的各道工序的设备的标志信息,获得生产产品的物料及各道工序间的流转关系和流转方向。
本步骤S2210中,其是将物料和设备抽象为节点,节点与节点间的流转关系抽象为边,如图3中箭头所示,在生产过程中,每一道工序生产的中间品,会随机的分发到后一道工序的多个节点,每一条虚线表示一组流转关系。
步骤S2220,以产品集合所涉及的所有物料的批次信息以及生产流水线的各道工序的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,构建流转网络。
在构建生产流水线的流转网络之后,进入:
步骤S2300,根据各产品是否为良品的标签,统计流转网络中的各流转路径对应的良品率。
良品率为是指产线上最终通过测试的良品数量占投入材料理论生产出的数量的比例。
本实施例中,本步骤S2300中根据各产品是否为良品的标签,统计流转网络中的各流转路径对应的良品率可以进一步包括如下步骤S2310~S2330:
步骤S2310,获取流转网络中的每条流转路径上的产品的第一总数量。
示例性地,如图3所示的流转网络,可以是分别计算流转路径1上的产品的总数量,以及,流转路径2上的产品的总数量等,为将任意一条流转路径上的产品的总数量和该条流转路径上的良品的总数量进行区分,这里,将流转路径上的产品的总数量称之为第一总数量,将以下该条流转路径上的良品的总数量称之为第二总数量。
步骤S2320,获取每条流转路径上的标签为良品的产品的第二总数量。
继续上述步骤S2320的示例,可以是分别计算流转路径1上的良品的总数量,以及,流转路径2上的良品的总数量等。
步骤S2330,根据每条流转路径对应的第一总数量和第二总数量,获得每条流转路径上的良品率。
本步骤S2330中,根据流转网络中每条流转路径对应的产品的第一总数量和该条流转路径上的良品的第二总数量,便可获得该条流转路径上的良品率。
继续上述步骤S2330的示例,流转网络中任意一条流转路径上的良品率P i的计算公式如下:
Figure PCTCN2021138159-appb-000001
其中,i表示流转网络中的流转路径,i的取值为1至n的任意整数,n为流转网络中的流转路径的总数量,M i表示第i条流转路径上的产品的第一总数量,N i表示第i条流转 路径上的标签为良品的产品的第二总数量。例如,流转路径1的良品率
Figure PCTCN2021138159-appb-000002
又例如,流转路径2上的良品率
Figure PCTCN2021138159-appb-000003
等。
在根据各产品是否为良品的标签,统计流转网络中的各流转路径对应的良品率之后,进入:
步骤S2400,根据流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位。
本实施例中,由于生产流水线复杂,该生产流水线中的任意环节存在异常,均有可能导致最终产品的良品率。
本实施例中,在获得流转网络中的各流转路径和各流转路径对应的良品率之后,便可对生产流水线中的异常环节进行快速定位。
本实施例中,由于每条流转路径上包括生产产品的物料的批次信息节点、及物料所经过生产流水线各道工序的设备的标识信息节点,在此,本步骤S2400中根据流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位可以进一步包括如下步骤S2410~S2430:
步骤S2410,以流转网络中的每条流转路径上的各个节点的合格率为未知参数,以流转路径对应的良品率为已知参数,构建概率模型方程组。
示例性地,如图3所示的流转网络,流转路径1上的物料A1的合格率可以标记为P A1,工序B中的设备B1的合格率可以标记为P B1,工序C中的设备C1的合格率标记为P C1,以及,工序D中的设备D2的合格率可以标记为P D2,并且,流转路径1对应的良品率为根据以上步骤S2300所计算出的P 1。流转路径2上的物料A2的合格率可以标记为P A2,工序B中的设备B4的合格率可以标记为P B4,工序C中的设备C2的合格率标记为P C2,以及,工序D中的设备D1的合格率可以标记为P D1,并且,流转路径2对应的良品率为根据以上步骤S2300所计算出的P 2。当然,还可以是标记流转路径i所经过的各个节点的合格率,以及,根据以上步骤S2300所计算出的流转路径i上的良品率,在此,根据本步骤S2410所构建的概率模型方程组可以为:
Figure PCTCN2021138159-appb-000004
其中,以上P A1*P B1*P C1*P D2=P 1表示以流转路径1上的各个节点的合格率P A1、P B1、P C1、P D2为未知参数,以该流转路径1对应的良品率P 1为已知参数,所构建的概率模型方程,也可以理解为是,该流转路径1对应的良品率近似等于该流转路径1经过的各个节点的合格率的乘积。以上P A2*P B4*P C2*P D1=P 2表示以流转路径2上的各个节点的合格率P A2、P B4、P C2、P D1为未知参数,以该流转路径2对应的良品率P 2为已知参数所构建的概率模型方程,也可以理解为是,该流转路径2对应的良品率近似等于该流转路径2经过的各个节点的合格率的乘积,其中,对于流转网络中的每一条流转路径,均能构建出该条流转路径的概率模型方程,进而获得公式(2)的概率模型方程组。
步骤S2420,求解概率模型方程组,获得流转网络中各个节点的合格率。
继续上述步骤S2410的示例,在构建出(2)所示的概率模型方程组后,便可求解出概率模型方程组中的未知参数,以获得流转网络中各个节点的合格率。
本实施例中,本步骤S2420中求解概率方程组,获得流转网络中各个节点的合格率可以进一步包括如下步骤S2421~S2422:
步骤S2421,获取目标优化算法。
该目标优化算法可以包括二次规划求解算法、粒子群算法和遗传算法中的至少一种算法。
步骤S2422,根据目标优化算法和设定的约束条件,求解概率方程组,获得流转网络中各个节点的合格率。
设定的约束条件包括关于流转网络中各个节点的合格率的约束。该关于流转网络中每个节点的合格率的约束为:每个节点的合格率的取值为0到1之间的自然数。
接下来示出一个例子的求解概率模型方程组的过程,首先,将(2)中的概率模型方程组转换为线性方程组:
Figure PCTCN2021138159-appb-000005
然后,将(3)中的线性方程组转换为矩阵形式:
Figure PCTCN2021138159-appb-000006
在此,以上(4)中的矩阵方程可以简写为A*L X=L形式,其中A矩阵每一行表示一条流转路径,每一列表示一个节点,流转路径经过的节点取1,没经过的节点取0,L X向量表示每个节点的合格率的对数值,为需要求解的未知参数,等号右边L为每条流转路径观测到的良品率的对数值。
其中,L X有约束条件,每个元素取值都在0到1之间,对应的对数取值L X则小于等于0。本公开通过带约束条件的目标优化算法,求解上述线性方程组,可以得到每个节点的合格率,求解过程可以为:针对矩阵方程(4),A*L X=L,需要找到一组最优的L' X使得A*L' X和等式右边L的偏差最小,该偏差例如但不限于包括均分误差(MSE)和平均绝对误差(MAE)等,则最终求解的问题为:
Figure PCTCN2021138159-appb-000007
Figure PCTCN2021138159-appb-000008
其中,上述公式(5)中n表示流转路径的数量,f表示误差函数,w i表示每一条流转路径的权重。
步骤S2430,根据流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位。
本实施例中,本步骤S2430中根据流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位可以进一步包括:
步骤S2431,根据流转网络中各个节点的合格率,获得各个节点的异常率。
步骤S2432,根据各个节点的异常率,对生产流水线中的异常环节进行定位。
在一个例子中,本步骤S2432中根据各个节点的异常率,对生产流水线中的异常环节进行定位可以进一步包括:针对于每一节点,获取预先设定的异常率;将每一节点的异常率和对应的设定的异常率进行比较;在节点的异常率大于设定的异常率的情况下,确定节点为异常节点。
在一个例子中,本步骤S2432中根据各个节点的异常率,对生产流水线中的异常环节进行定位可以进一步包括:将各个节点的异常率按照从大到小的顺序进行排序;获取前预定数量的异常率对应的节点,作为异常节点。
根据本公开实施例的方法,其能够将一个产品的生产流转数据与所构建的生产流水线的流转网络的一条流转路径对应,同时,根据各产品是否为良品的标签,来统计出流转网络中的各流转路径对应的良品率,进而根据流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位,即,本公开实施例利用产品生产过程中在各道工序间的生产流转数据,对生产过程中的异常环节进行了快速且准确的定位。
在一个实施例中,根据以上公式(5)可知,概率模型方程组中还可以包括对应第i条流转路径的权重w i,在此,由于真实的生产过程中,生产流程比较复杂,可能存在大量的流转路径,但是有的流转路径上所对应的产品数量非常少,导致统计到的该条流转路径对应的良品率的置信度不高,在此,本公开实施例的生产流水线中的异常环节定位方法还可以包括如下步骤S3100~S3300:
步骤S3100,获取流转网络中的每条流转路径上的产品的第一总数量。
步骤S3200,根据第一总数量,调整概率模型方程组中对应流转路径的权重。
第一总数量可以和权重成正比。
例如可以是流转路径上的产品的总数量越大,将概率模型方程组中对应该流转路径的权重调的越高。
又例如可以是流转路径上的产品的总数量越少,将概率模型方程组中对应该流转路径的权重调的越小。
步骤S3300,基于调整后的权重,根据目标优化算法和设定的约束条件,求解概率模型方程组,获得流转网络中各个节点的合格率。
根据本公开实施例的方法,其可以在流转路径上的产品的数量特别小的情况下,将概率模型方程组中该条流转路径的权重调的越小,进而使其对整个异常环节定位时所产生的影响越小。
在一个实施例中,实际应用过程中,可能存在某一条流转路径上所有的产品均是不合格的产品,即,该条流转路径上的所有产品是否为良品的标签均为0,导致该条流转路径对应的良品率为0,在此,本公开实施例的生产流水线中的异常环节定位方法还可以包括如下步骤S4100~S4200:
步骤S4100,在流转网络中的任一流转路径对应的良品率低于设定的良品率阈值的情况下,将任一流转路径上的良品率进行调整。
设定的良品率阈值可以是根据实际应用场景和实际应用需求设置的数值,该良品率阈值可以为0。
例如,可以是在某一条流转路径对应的良品率为0的情况下,将该条流转路径上的良品率调整为一个大于0且比较小的数值。
步骤S4200,根据流转网络中的各流转路径和调整后的各流转路径对应的良品率,对生产流水线中的异常环节进行定位。
根据本公开实施例的方法,其在任意一条流转路径对应的良品率为0的情况下,支持对该条流转路径对应的良品率进行置换,使得针对该生产流水线中的异常环节定位更加准确。
在一个实施例中,对于生产过程中不会导致产品不良的工序,支持直接从流转网络中进行删除,在此,本公开实施例的生产流水线中的异常环节定位方法还可以包括如下步骤S5100~S5200:
步骤S5100,在流转网络中的任一节点满足设定的滤除条件的情况下,从流转网络中删除任一节点以调整流转网络中的流转路径。
步骤S5200,基于调整后的流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位。
在一个实施例中,对于一道工序涉及的设备数量较多时,还支持多台设备合并为一个节点,在此,本公开实施例的生产流水线中的异常环节定位方法还可以包括如下步骤S6100~S6200:
步骤S6100,在任一工序的设备数量超过设定的设备数量阈值的情况下,将任一工序的多个设备进行合并处理。
设定的设备数量阈值可以是根据实际应用场景和实际应用需求设置的数值。
例如可以将该多个设备合并为一个节点。
步骤S6200,以产品集合所涉及的所有物料的批次信息、及生产流水线的各道工序的进行合并处理后的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,重新构建流转网络。
在一个实施例中,本公开实施例的生产流水线中的异常环节定位方法还可以包括:响应于获取挖掘流转网络的挖掘结果的请求,获取设定的显示模式;按照显示模式显示构建的流转网络。
该显示模式可以是图形形式。
该实施例中,其可以根据获取挖掘流转网络的挖掘结果的请求,按照设定的显示模式提供流转网络,以使得显示输出具有更友好的可视性。
在一个实施例中,本公开实施例的生产流水线中的异常环节定位方法还可以包括:切分流转网络,获得多个子流转网络,以根据多个子流转网络中的各流转路径对应的良品率,对生产流水线中的异常环节进行定位。
本实施例中,对于复杂的流转网络,其支持对工序按照流转路径顺序进行拆分,进而形成多个子流转网络,然后从最后的一个子流转网络开始求解,并对前面的字流转网络递归求解。
示例性地,如图4所示,由于整个生产工序流程比较长,在此,仅关注工序C和工序D,在工序C之前可能还有很多道工序,工序D之后也可能还有很多工序。要对工序C和工序D所组成的这个子流转网络求解,则先在该子流转网络的上游,引入虚拟节点B',表示B(包括B)之前的所有工序后的中间产出物,B工序的每个节点B i都对应一个虚拟节点B i',每个虚拟节点有一个隐含的合格率P' Bi,该合格率是前面所有工序总的影响。可以看作该子流转网络的物料输入。同样在该子流转网络的下游也引入虚拟节点,对E的每个节点E i引入虚拟节点E i',同样每个虚拟节点E i'有一个银行的合格率P' Ei,表示后面所有工序的总的影响。在引入好虚拟节点后,可以构建模型方程组,比如图4中实线1表示的流转路径1,则可以统计经过节点B 1,C 1,D 1,E 1,同时统计流转路径1上的良品率P1,P 1=P' B1*P C1*P D1*P' E1。同理可以统计图4中实线2表示的流转路径2经过节点B 2,C 3,D 3,E 2的观测到的产品合格率,进而得到以下模型方程组:
Figure PCTCN2021138159-appb-000009
得到方程组之后,可以跟全网络求解的求解进行求解,求解得到的结果中虚拟节点的合格率,不代表对应节点的合格率,是前面或者后面所有工序的总影响。
<装置实施例>
在本实施例中,提供一种生产流水线中的异常环节定位装置5000,如图5所示,包括获取模块5100、构建模块5200、统计模块5300及定位模块5400。
获取模块5100,被配置为获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签。
构建模块5200,被配置为构建所述生产流水线的流转网络,其中,一个产品的生产流转数据对应所述流程网络中的一条流转路径。
统计模块5300,被配置为根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率。
定位模块5400,被配置为根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
在一个实施例中,所述生产流转数据包括:生产产品的物料的批次信息、物料所经过生产流水线各道工序的设备的标识信息。
在一个实施例中,所述构建模块5200,具体被配置为:
根据生产产品的物料的批次信息以及所述生产流水线的各道工序的设备的标志信息,获得生产产品的物料及各道工序间的流转关系和流转方向;
以所述产品集合所涉及的所有物料的批次信息以及所述生产流水线的各道工序的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,构建流转网络。
在一个实施例中,所述统计模块5300,具体被配置为:获取所述流转网络中的每条流转路径上的产品的第一总数量;获取每条所述流转路径上的标签为良品的产品的第二总数量;根据每条所述流转路径对应的所述第一总数量和所述第二总数量,获得每条所述流转路径上的良品率。
在一个实施例中,每条所述流转路径上包括生产产品的物料的批次信息节点、及物料所经过生产流水线各道工序的设备的标识信息节点,所述定位模块5400,具体被配置为:以所述流转网络中的每条流转路径上的各个节点的合格率为未知参数,以所述流转路径对应的良品率为已知参数,构建概率模型方程组;求解所述概率模型方程组,获得所述流转网络中各个节点的合格率;根据所述流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位。
在一个实施例中,所述定位模块5400,具体被配置为:获取目标优化算法,其中,所述目标优化算法至少包括二次规划求解算法、粒子群算法和遗传算法中的至少一种算法;根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所所述流转网络中各个节点的合格率;其中,所述设定的约束条件包括关于所述流转网络中各个节点的合格率的约束。
在一个实施例中,关于所述流转网络中各个节点的合格率的约束为:各个所述节点的合格率的取值为0到1之间的自然数。
在一个实施例中,所述定位模块5400,具体被配置为:根据所述流转网络中各个节点的合格率,获得各个所述节点的异常率;根据各个所述节点的异常率,对所述生产流水线中的异常环节进行定位。
在一个实施例中,所述定位模块5400,具体被配置为:针对于每一所述节点,获取预先设定的异常率;将每一所述节点的异常率和对应的所述设定的异常率进行比较;在所述节点的异常率大于设定的异常率的情况下,确定所述节点为异常节点。
在一个实施例中,所述定位模块5400,具体被配置为:将各个所述节点的异常率按照从大到小的顺序进行排序;获取前预定数量的异常率对应的节点,作为异常节点。
在一个实施例中,所述概率模型方程组中还包括对应每条流转路径的权重;所述定位模块5400,还被配置为:获取所述流转网络中的每条流转路径上的产品的第一总数量;根据所述第一总数量,调整所述概率模型方程组中对应所述流转路径的权重;基于调整后的权重,根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所述流转网络中各个节点的合格率。
在一个实施例中,所述定位模块5400,还被配置为:在所述流转网络中的任一流转路径对应的良品率低于设定的良品率阈值的情况下,将所述任一流转路径上的良品率进行调整;根据所述流转网络中的各流转路径和调整后的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
在一个实施例中,所述定位模块5400,还被配置为:在所述流转网络中的任一节点满足设定的滤除条件的情况下,从所述流转网络中删除所述任一节点以调整所述流转网络中的流转路径;基于所述调整后的流转网络中的各流转路径和各流转对应的良品率,对所述生产流水线中的异常环节进行定位
在一个实施例中,所述构建模块5200,还被配置为:在任一工序的设备数量超过设定的设备数量阈值的情况下,将所述任一工序的多个设备进行合并处理;以所述产品集合所涉及的所有物料的批次信息、及所述生产流水线的各道工序的进行所述合并处理后的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,重新构建流转网络。
在一个实施例中,所述定位模块5400,还被配置为:切分所述流转网络,获得多个子流转网络,以根据所述多个子流转网络中的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
在一个实施例中,装置5000还包括显示模块(图中未示出)。
该显示模块,被配置为响应于获取挖掘流转网络的挖掘结果的请求,获取设定的显示模式;按照所述显示模式显示构建的所述流转网络。
在一个实施例中,所述获取模块,具体被配置为:通过获取接口向产品数据系统发送获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签的请求;其中,所述请求中至少携带所述产品集合的标识信息和各个产品的标识信息中的任意一种;接收所述产品数据系统响应于所述请求返回的各个产品的生产流转数据以及各产品是否为良品的标签。
<存储介质实施例>
本实施例提供了一种计算机可读存储介质,其中,其上存储有计算机程序,所述计算机程序在被处理器执行时实现根据上述方法实施例中任一项所述的方法。
本公开可以是设备、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质,其上载有被配置为使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括:便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身,诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如,通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备,或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令,并转发该计算机可读程序指令,以供存储在各个计算/处理设备中的计算机可读存储介质中。
被配置为执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、 机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码,所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等,以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中,通过利用计算机可读程序指令的状态信息来个性化定制电子电路,例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA),该电子电路可以执行计算机可读程序指令,从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解,流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合,都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器,从而生产出一种机器,使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时,产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中,这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作,从而,存储有指令的计算机可读介质则包括一个制造品,其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上,使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤,以产生计算机实现的过程,从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分,所述模块、程序段或指令的一部分包含一个或多个被配置为实现规定的逻辑功能的可执行指令。在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。对于本领域技术人员来说公知的是,通过硬件方式实现、通过软件方式实现以及通过软件和硬件结合的方式实现都是等价的。
以上已经描述了本公开的各实施例,上述说明是示例性的,并非穷尽性的,并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下,对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择,旨在最好地解释各实施例的原理、实际应用或对市场中的技术改进,或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。本公开的范围由所附权利要求来限定。
工业实用性
通过本公开实施例,将一个产品的生产流转数据与所构建的生产流水线的流转网络的一条流转路径对应,同时,根据各产品是否为良品的标签,来统计出流转网络中的各流转路径对应的良品率,进而根据流转网络中的各流转路径和各流转路径对应的良品率,对生产流水线中的异常环节进行定位,即,本公开实施例利用产品生产过程中在各道工序间的生产流转数据,对生产过程中的异常环节进行了快速且准确的定位。

Claims (36)

  1. 一种生产流水线中的异常环节定位方法,包括:
    获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签;
    构建所述生产流水线的流转网络,其中,一个产品的生产流转数据对应所述流程网络中的一条流转路径;
    根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率;
    根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  2. 根据权利要求1所述的方法,其中,
    所述生产流转数据包括:生产产品的物料的批次信息、物料所经过生产流水线各道工序的设备的标识信息。
  3. 根据权利要求2所述的方法,其中,所述构建所述生产流水线的流转网络,包括:
    根据生产产品的物料的批次信息以及所述生产流水线的各道工序的设备的标志信息,获得生产产品的物料及各道工序间的流转关系和流转方向;
    以所述产品集合所涉及的所有物料的批次信息以及所述生产流水线的各道工序的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,构建流转网络。
  4. 根据权利要求2所述的方法,其中,所述根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率,包括:
    获取所述流转网络中的每条流转路径上的产品的第一总数量;
    获取每条所述流转路径上的标签为良品的产品的第二总数量;
    根据每条所述流转路径对应的所述第一总数量和所述第二总数量,获得每条所述流转路径上的良品率。
  5. 根据权利要求1至4中任一项所述的方法,其中,每条所述流转路径上包括生产产品的物料的批次信息节点、及物料所经过生产流水线各道工序的设备的标识信息节点,
    所述根据所述流转网络中的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位,包括:
    以所述流转网络中的每条流转路径上的各个节点的合格率为未知参数,以所述流转路径对应的良品率为已知参数,构建概率模型方程组;
    求解所述概率模型方程组,获得所述流转网络中各个节点的合格率;
    根据所述流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位。
  6. 根据权利要求5所述的方法,其中,所述求解所述概率模型方程组,获得所述流转网络中各个节点的合格率,包括:
    获取目标优化算法,其中,所述目标优化算法包括二次规划求解算法、粒子群算法和遗传算法中的至少一种算法;
    根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所述流转网络中各个节点的合格率;
    其中,所述设定的约束条件包括关于所述流转网络中各个节点的合格率的约束。
  7. 根据权利要求6所述的方法,其中,关于所述流转网络中各个节点的合格率的约束为:各个所述节点的合格率的取值为0到1之间的自然数。
  8. 根据权利要求5所述的方法,其中,所述根据所述流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位,包括:
    根据所述流转网络中各个节点的合格率,获得各个所述节点的异常率;
    根据各个所述节点的异常率,对所述生产流水线中的异常环节进行定位。
  9. 根据权利要求8所述的方法,其中,所述根据各个所述节点的异常率,对所述生产流水线中的异常环节进行定位,包括:
    针对于每一所述节点,获取预先设定的异常率;
    将每一所述节点的异常率和对应的所述设定的异常率进行比较;
    在所述节点的异常率大于设定的异常率的情况下,确定所述节点为异常节点。
  10. 根据权利要求8所述的方法,其中,所述根据各个所述节点的异常率,对所述生产流水线中的异常环节进行定位,还包括:
    将各个所述节点的异常率按照从大到小的顺序进行排序;
    获取前预定数量的异常率对应的节点,作为异常节点。
  11. 根据权利要求6所述的方法,其中,所述概率模型方程组中还包括对应每条流转路径的权重;
    所述方法还包括:
    获取所述流转网络中的每条流转路径上的产品的第一总数量;
    根据所述第一总数量,调整所述概率模型方程组中对应所述流转路径的权重;
    基于调整后的权重,根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所述流转网络中各个节点的合格率。
  12. 根据权利要求1至11中任一项所述的方法,其中,所述方法还包括:
    在所述流转网络中的任一流转路径对应的良品率低于设定的良品率阈值的情况下,将所述任一流转路径上的良品率进行调整;
    根据所述流转网络中的各流转路径和调整后的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  13. 根据权利要求1至12中任一项所述的方法,其中,所述方法还包括:
    在所述流转网络中的任一节点满足设定的滤除条件的情况下,从所述流转网络中删除所述任一节点以调整所述流转网络中的流转路径;
    基于所述调整后的流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  14. 根据权利要求3所述的方法,其中,所述方法还包括:
    在任一工序的设备数量超过设定的设备数量阈值的情况下,将所述任一工序的多个设备进行合并处理;
    以所述产品集合所涉及的所有物料的批次信息、及所述生产流水线的各道工序的进行所述合并处理后的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,重新构建流转网络。
  15. 根据权利要求1至14中任一项所述的方法,其中,所述方法还包括:
    切分所述流转网络,获得多个子流转网络,以根据所述多个子流转网络中的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  16. 根据权利要求1至15中任一项所述的方法,其中,所述方法还包括:
    响应于获取挖掘流转网络的挖掘结果的请求,获取设定的显示模式;
    按照所述显示模式显示构建的所述流转网络。
  17. 根据权利要求1至16中任一项所述的方法,其中,所述获取产品集合中的各个产品的生产流转线上的生产流转数据以及各产品是否为良品的标签,包括:
    通过获取接口向产品数据系统发送获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签的请求;其中,所述请求中至少携带所述产品集合的标识信息和各个产品的标识信息中的任意一种;
    接收所述产品数据系统响应于所述请求返回的各个产品的生产流转数据以及各产品是否为良品的标签。
  18. 一种生产流水线中的异常环节定位装置,包括:
    获取模块,被配置为获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签;
    构建模块,被配置为构建所述生产流水线的流转网络,其中,一个产品的生产流转数据对应所述流程网络中的一条流转路径;
    统计模块,被配置为根据各产品是否为良品的标签,统计所述流转网络中的各流转路径对应的良品率;
    定位模块,被配置为根据所述流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  19. 根据权利要求18所述的装置,其中,
    所述生产流转数据包括:生产产品的物料的批次信息、物料所经过生产流水线各道工序的设备的标识信息。
  20. 根据权利要求19所述的装置,其中,所述构建模块,具体被配置为:
    根据生产产品的物料的批次信息以及所述生产流水线的各道工序的设备的标志信息,获得生产产品的物料及各道工序间的流转关系和流转方向;
    以所述产品集合所涉及的所有物料的批次信息以及所述生产流水线的各道工序的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,构建流转网络。
  21. 根据权利要求19所述的装置,其中,所述统计模块,具体被配置为:
    获取所述流转网络中的每条流转路径上的产品的第一总数量;
    获取每条所述流转路径上的标签为良品的产品的第二总数量;
    根据每条所述流转路径对应的所述第一总数量和所述第二总数量,获得每条所述流转路径上的良品率。
  22. 根据权利要求18至21中任一项所述的装置,其中,每条所述流转路径上包括生产产品的物料的批次信息节点、及物料所经过生产流水线各道工序的设备的标识信息节点,所述定位模块,具体被配置为:
    以所述流转网络中的每条流转路径上的各个节点的合格率为未知参数,以所述流转路径对应的良品率为已知参数,构建概率模型方程组;
    求解所述概率模型方程组,获得所述流转网络中各个节点的合格率;
    根据所述流转网络中各个节点的合格率,对所述生产流水线中的异常环节进行定位。
  23. 根据权利要求22所述的装置,其中,所述定位模块,具体被配置为:
    获取目标优化算法,其中,所述目标优化算法至少包括二次规划求解算法、粒子群算法和遗传算法中的至少一种算法;
    根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所所述流转网络中各个节点的合格率;
    其中,所述设定的约束条件包括关于所述流转网络中各个节点的合格率的约束。
  24. 根据权利要求23所述的装置,其中,关于所述流转网络中各个节点的合格率的约束为:各个所述节点的合格率的取值为0到1之间的自然数。
  25. 根据权利要求22所述的装置,其中,所述定位模块,具体被配置为:
    根据所述流转网络中各个节点的合格率,获得各个所述节点的异常率;
    根据各个所述节点的异常率,对所述生产流水线中的异常环节进行定位。
  26. 根据权利要求25所述的装置,其中,所述定位模块,具体被配置为:
    针对于每一所述节点,获取预先设定的异常率;
    将每一所述节点的异常率和对应的所述设定的异常率进行比较;
    在所述节点的异常率大于设定的异常率的情况下,确定所述节点为异常节点。
  27. 根据权利要求25所述的装置,其中,所述定位模块,具体被配置为:
    将各个所述节点的异常率按照从大到小的顺序进行排序;
    获取前预定数量的异常率对应的节点,作为异常节点。
  28. 根据权利要求23所述的装置,其中,所述概率模型方程组中还包括对应每条流转路径的权重;所述定位模块,还被配置为:
    获取所述流转网络中的每条流转路径上的产品的第一总数量;
    根据所述第一总数量,调整所述概率模型方程组中对应所述流转路径的权重;
    基于调整后的权重,根据所述目标优化算法和设定的约束条件,求解所述概率模型方程组,获得所述流转网络中各个节点的合格率。
  29. 根据权利要求18至28中任一项所述的装置,其中,所述定位模块,还被配置为:
    在所述流转网络中的任一流转路径对应的良品率低于设定的良品率阈值的情况下,将所述任一流转路径上的良品率进行调整;
    根据所述流转网络中的各流转路径和调整后的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  30. 根据权利要求18至29中任一项所述的装置,其中,所述定位模块,还被配置为:
    在所述流转网络中的任一节点满足设定的滤除条件的情况下,从所述流转网络中删除所述任一节点以调整所述流转网络中的流转路径;
    基于所述调整后的流转网络中的各流转路径和各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  31. 根据权利要求20所述的装置,其中,所述构建模块,还被配置为:
    在任一工序的设备数量超过设定的设备数量阈值的情况下,将所述任一工序的多个设备进行合并处理;
    以所述产品集合所涉及的所有物料的批次信息、及所述生产流水线的各道工序的进行所述合并处理后的设备的标志信息为节点,以节点与节点间的流转关系为边,以流转方向为边的方向,重新构建流转网络。
  32. 根据权利要求18至31中任一项所述的装置,其中,所述定位模块,还被配置为:
    切分所述流转网络,获得多个子流转网络,以根据所述多个子流转网络中的各流转路径对应的良品率,对所述生产流水线中的异常环节进行定位。
  33. 根据权利要求18至32中任一项所述的装置,其中,所述装置还包括显示模块,所述显示模块,被配置为:
    响应于获取挖掘流转网络的挖掘结果的请求,获取设定的显示模式;
    按照所述显示模式显示构建的所述流转网络。
  34. 根据权利要求18至33中任一项所述的装置,其中,所述获取模块,具体被配置为:
    通过获取接口向产品数据系统发送获取产品集合中的各个产品在生产流水线上的生产流转数据以及各产品是否为良品的标签的请求;其中,所述请求中至少携带所述产品集合的标识信息和各个产品的标识信息中的任意一种;
    接收所述产品数据系统响应于所述请求返回的各个产品的生产流转数据以及各产品是否为良品的标签。
  35. 一种包括至少一个计算装置和至少一个存储装置的设备,其中,所述至少一个存储装置被配置为存储指令,所述指令在被所述至少一个计算装置执行时实现根据权利要求1至17中任一项所述的方法。
  36. 一种计算机可读存储介质,其中,其上存储有计算机程序,所述计算机程序在被处理器执行时实现如权利要求1至17中任一项所述的方法。
PCT/CN2021/138159 2020-12-15 2021-12-15 生产流水线中的异常环节定位方法、装置及电子设备 WO2022127797A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011473643.X 2020-12-15
CN202011473643.XA CN112559594A (zh) 2020-12-15 2020-12-15 生产流水线中的异常环节定位方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2022127797A1 true WO2022127797A1 (zh) 2022-06-23

Family

ID=75064755

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/138159 WO2022127797A1 (zh) 2020-12-15 2021-12-15 生产流水线中的异常环节定位方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN112559594A (zh)
WO (1) WO2022127797A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114971433A (zh) * 2022-08-01 2022-08-30 中国工业互联网研究院 基于工业互联网的质量管控方法、装置、设备及存储介质
CN116339265A (zh) * 2023-04-06 2023-06-27 苏州暾达智能装备有限公司 一种陶瓷基片模块化生产的智能管控方法及系统
CN117078278A (zh) * 2023-08-15 2023-11-17 中国人民解放军陆军勤务学院 高原食品制备标签处理方法及设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112559594A (zh) * 2020-12-15 2021-03-26 第四范式(北京)技术有限公司 生产流水线中的异常环节定位方法、装置及电子设备
CN113378332B (zh) * 2021-08-16 2021-11-02 成都数联云算科技有限公司 生产设备组分析方法、装置、电子设备及计算机可读存储介质
CN114063582B (zh) * 2021-11-16 2024-04-12 英特尔产品(成都)有限公司 用于监控产品测试过程的方法和装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103645720A (zh) * 2013-12-17 2014-03-19 上海电机学院 流水线生产成本实时监控装置及流水线生产成本诊断方法
US20170220626A1 (en) * 2016-01-29 2017-08-03 International Business Machines Corporation Systematic approach to determine source of data quality issue in data flow in an enterprise
CN109685386A (zh) * 2018-12-29 2019-04-26 齐鲁工业大学 基于数据信息的多目标作业车间的复杂网络模型构建方法
CN112559594A (zh) * 2020-12-15 2021-03-26 第四范式(北京)技术有限公司 生产流水线中的异常环节定位方法、装置及电子设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0950949A (ja) * 1995-05-26 1997-02-18 Hitachi Ltd 製品の製造方法および生産管理計算システム
US10191107B2 (en) * 2017-02-23 2019-01-29 Globalfoundries Inc. Ranking defects with yield impacts
CN107480873B (zh) * 2017-08-01 2021-04-16 惠科股份有限公司 生产管理方法及系统
CN110084326B (zh) * 2019-05-13 2022-12-06 东北大学 一种基于模糊集的工业设备异常检测方法
CN111127517B (zh) * 2019-12-20 2023-06-09 北京容联易通信息技术有限公司 一种基于监控视频的生产线产品定位方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103645720A (zh) * 2013-12-17 2014-03-19 上海电机学院 流水线生产成本实时监控装置及流水线生产成本诊断方法
US20170220626A1 (en) * 2016-01-29 2017-08-03 International Business Machines Corporation Systematic approach to determine source of data quality issue in data flow in an enterprise
CN109685386A (zh) * 2018-12-29 2019-04-26 齐鲁工业大学 基于数据信息的多目标作业车间的复杂网络模型构建方法
CN112559594A (zh) * 2020-12-15 2021-03-26 第四范式(北京)技术有限公司 生产流水线中的异常环节定位方法、装置及电子设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114971433A (zh) * 2022-08-01 2022-08-30 中国工业互联网研究院 基于工业互联网的质量管控方法、装置、设备及存储介质
CN114971433B (zh) * 2022-08-01 2022-10-25 中国工业互联网研究院 基于工业互联网的质量管控方法、装置、设备及存储介质
CN116339265A (zh) * 2023-04-06 2023-06-27 苏州暾达智能装备有限公司 一种陶瓷基片模块化生产的智能管控方法及系统
CN116339265B (zh) * 2023-04-06 2023-10-24 苏州暾达智能装备有限公司 一种陶瓷基片模块化生产的智能管控方法及系统
CN117078278A (zh) * 2023-08-15 2023-11-17 中国人民解放军陆军勤务学院 高原食品制备标签处理方法及设备
CN117078278B (zh) * 2023-08-15 2024-05-03 中国人民解放军陆军勤务学院 高原食品制备标签处理方法及设备

Also Published As

Publication number Publication date
CN112559594A (zh) 2021-03-26

Similar Documents

Publication Publication Date Title
WO2022127797A1 (zh) 生产流水线中的异常环节定位方法、装置及电子设备
US11232117B2 (en) Apparatuses, methods and systems for relevance scoring in a graph database using multiple pathways
US20180293293A1 (en) Dynamic Clustering For Streaming Data
US10891421B2 (en) Apparatuses, methods and systems for adjusting tagging in a computing environment
US10608879B2 (en) Validation using natural language processing
EP3540653A1 (en) Data processing system and method
US10748116B2 (en) Test vector generation from documentation
CN111008707A (zh) 自动化建模方法、装置及电子设备
CN112434087B (zh) 一种跨系统数据比对方法、装置、电子设备及存储介质
US8990070B2 (en) Computer-based construction of arbitrarily complex formal grammar expressions
US9904744B2 (en) Probabilistic simulation scenario design by using multiple conditional and nested probability distribution input functions
AU2015336259B2 (en) Specifying and applying rules to data
CN109254977A (zh) 数据生成方法、大数据风控平台及计算机存储介质
CN113449498A (zh) 生成表单的方法、装置、存储介质及电子设备
US10311184B2 (en) Circuit verification on a distributed database processing system
Ahmed et al. Deep Q-learning with bit-swapping-based linear feedback shift register fostered built-in self-test and built-in self-repair for SRAM
JP6638739B2 (ja) 表形式データの解析方法、表形式データの解析プログラム及び情報処理装置
US11061811B2 (en) Optimizing software testing via group testing
US10169508B2 (en) Efficient deployment of table lookup (TLU) in an enterprise-level scalable circuit simulation architecture
CN112330427B (zh) 用于商品排序的方法、电子设备和存储介质
CN111367889B (zh) 基于网页界面的跨集群数据迁移方法和装置
Zulfikar et al. Runtime analysis of area-efficient uniform RO-PUF for uniqueness and reliability balancing
CN115062022B (zh) 航空器手册拆分方法、装置、电子设备和计算机可读介质
CN117290380B (zh) 异常维度数据生成方法、装置、设备和计算机可读介质
US20180232292A1 (en) Error checking of a multi-threaded computer processor design under test

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21905724

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21905724

Country of ref document: EP

Kind code of ref document: A1