CN109034452A - Energy consumption prediction technique for auto-parts manufacturing enterprise - Google Patents

Energy consumption prediction technique for auto-parts manufacturing enterprise Download PDF

Info

Publication number
CN109034452A
CN109034452A CN201810635530.1A CN201810635530A CN109034452A CN 109034452 A CN109034452 A CN 109034452A CN 201810635530 A CN201810635530 A CN 201810635530A CN 109034452 A CN109034452 A CN 109034452A
Authority
CN
China
Prior art keywords
neural network
energy consumption
module
auto
manufacturing enterprise
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.)
Pending
Application number
CN201810635530.1A
Other languages
Chinese (zh)
Inventor
李曼洁
陈雷田
洪本浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHANGHAI ANYUE ENERGY-SAVING S&T Co Ltd
Original Assignee
SHANGHAI ANYUE ENERGY-SAVING S&T Co Ltd
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 SHANGHAI ANYUE ENERGY-SAVING S&T Co Ltd filed Critical SHANGHAI ANYUE ENERGY-SAVING S&T Co Ltd
Priority to CN201810635530.1A priority Critical patent/CN109034452A/en
Publication of CN109034452A publication Critical patent/CN109034452A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • 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

Abstract

The invention discloses a kind of energy consumption prediction technique for auto-parts manufacturing enterprise, include the following steps: the energy input that single technology category is predicted using bottom neural network module；Input by the output of multiple bottom neural network modules as the neural network module of a high level makes energy consumption prediction to certain product line, certain workshop or full factory by the neural network module of a high level in conjunction with the input feature vector of a high level.Provided by the present invention for the energy consumption prediction technique of auto-parts manufacturing enterprise, by the neural network model system for establishing multi-layer, changeless concrete technology part in flexible production is distinguished with flexible product difference variable part, so as to avoid the data of single neural network model from inputting the excessively high problem of dimension, the accuracy of model entirety is improved；Better adapt to the features such as product zone indexing is big, product line production flexibility is high in auto-parts manufacturing enterprise production process.

Description

Energy consumption prediction technique for auto-parts manufacturing enterprise
Technical field
The present invention relates to a kind of energy consumption prediction technique more particularly to a kind of energy consumption for auto-parts manufacturing enterprise are pre- Survey method.
Background technique
Nerve network system is a kind of mimic biology neural network structure and function in machine learning and cognitive science field Mathematical model.Neural network is coupled by a large amount of artificial neuron to be calculated, in most cases can be in external information On the basis of change internal structure, be a kind of Adaptable System.There is neural network MPP, distributed information to deposit The features such as storage, good self-organizing self-learning capability, arbitrary function can be theoretically approached, basic structure is by non-linear change Change unit composition, there is very strong non-linear mapping capability, flexibility is big, is often used in the practical problems such as classification and prediction In.
Different from traditional steel, metallurgical class enterprise, there may be huge between the different product that auto-parts enterprise produces Big difference, even similar product, the part assembled in different automobile types also has far different process sequence and feature.With this Meanwhile many auto-parts production line flexible production abilities with higher, same production line is able to produce entirely different Vehicle.For the product structure of such high flexibility and auto-parts manufacturing enterprise complexity, traditional neural network mould Type will appear the problems such as data dimension is high, input feature vector amount mixes, and then influence the convergence of neural network model and accurate Property.Therefore, it is necessary to be directed to the productive prospecting of auto-parts manufacturing enterprise, a kind of modular neural network model system is proposed System, can the more preferable flexible characteristic that must adapt to auto-parts manufacturing enterprise, acquirement the higher energy consumption predicted value of accuracy rate.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of energy consumption prediction sides for auto-parts manufacturing enterprise Method can be avoided the excessively high problem of the data input dimension of single neural network model, improve the accuracy of model entirety；Very well Ground adapts to the features such as product zone indexing is big, product line production flexibility is high in auto-parts manufacturing enterprise production process.
The present invention is to solve above-mentioned technical problem and the technical solution adopted is that provide a kind of for auto-parts production The energy consumption prediction technique of enterprise includes the following steps: the energy input that single technology category is predicted using bottom neural network module； Input by the output of multiple bottom neural network modules as the neural network module of a high level, in conjunction with the defeated of a high level Enter feature, energy consumption prediction is made to certain product line, certain workshop or full factory by the neural network module of a high level.
The above-mentioned energy consumption prediction technique for auto-parts manufacturing enterprise, wherein the bottom neural network module It is divided into three kinds according to technology category: the technical module based on robot, steady state treatment process module and the people based on artificial Work technical module；For the technical module based on robot, the input feature vector of the bottom neural network module is each life It produces the Code Number of part, at the time of part enters each technique and the quality information of part, exports and exist for the robot technique Prediction of energy consumption amount in predetermined time；To steady state treatment process module, the input feature vector of the bottom neural network module is work Skill parameter, equipment operation duration and ambient temperature and humidity export as the prediction energy of steady state treatment process module in the given time Consumption；To the manual process module based on artificial, the input feature vector of the bottom neural network module is part productive temp And scheduled production, export the prediction of energy consumption amount in the given time for the artificial technical module.
The above-mentioned energy consumption prediction technique for auto-parts manufacturing enterprise, wherein the steady state treatment process module For the baking process module of part tempering module, hydraulic oil heating module or automotive lacquer.
The above-mentioned energy consumption prediction technique for auto-parts manufacturing enterprise, wherein each neural network module includes Following processing step: S1) determine the level and input feature vector of neural network model；S2) according to input feature vector to initial data into Row cleaning, excluding outlier, and dimension-reduction treatment and normalization are carried out to data according to the complexity of product line；S3) setting mind The hidden layer number of plies, highest the number of iterations, initialization weight, excitation function and learning rate through network model；S4 it) is randomly assigned Training set and test set in data set repeatedly train neural network model using the method for cross validation；S5) to neural network The degree of fitting and error of model are analyzed, if reaching desired extent, export the energy-output ratio of prediction；If not up to expected model It encloses, return step S3.
The above-mentioned energy consumption prediction technique for auto-parts manufacturing enterprise, wherein the nerve net of a high level Periodical variable is added as input feature vector in network module, and the periodicity variable includes producing line plan for adjustment or festivals or holidays peace Row.
The present invention comparison prior art has following the utility model has the advantages that provided by the present invention for auto-parts manufacturing enterprise Energy consumption prediction technique, establish the neural network model system of multi-layer.Different from single neural network model, the mind of level Through network modeling system can (product be poor with flexible variable part by the part (concrete technology) that immobilizes in flexible production It is different) it distinguishes, it is big so as to preferably learn and adapt to the product zone indexing that auto-parts manufacturing enterprise faces, it is flexible high The features such as, give different levels module different weights, the more acurrate actual production situation that must react auto-parts enterprise.It is logical It crosses and distinguishes different types of neural network model, avoid the excessively high bring prediction of the input feature vector dimension of a certain specific neural network Deviation is excessive, improves the predictablity rate of total system.
Detailed description of the invention
Fig. 1 is the modular neural network system schematic that the present invention has level；
Fig. 2 is the training flow diagram for a certain specific neural network model that the present invention uses.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is the modular neural network system schematic that the present invention has level.
Referring to Figure 1, it provided by the present invention for the energy consumption prediction technique of auto-parts manufacturing enterprise, including walks as follows It is rapid:
The energy input of single technology category is predicted using bottom neural network module；
Input by the output of multiple bottom neural network modules as the neural network module of a high level, in conjunction with high by one It is pre- to make energy consumption to certain product line, certain workshop or full factory by the neural network module of a high level for the input feature vector of level It surveys.
In the production of auto-parts manufacturing enterprise, often relate to many different techniques, different product it Between be not only use technique have any different, the sequence difference of technique also brings along the difference in energy consumption when individual.In Fig. 1 System architecture figure contains the hierarchical structure of the nerve network system, the relationship of input and output, and illustrates three kinds of differences simultaneously The input feature vector amount that bottom neural network module corresponding to type process needs.
Specifically, in numerous production technologies, technique can be divided into three types according to energy consumption feature: the first It is the manufacturing process based on robot, robot must can complete certain one of work of product at regular time and quantity under program control Skill, thus the energy consumption of the technique with have stronger correlation between product yield, equipment mode；Second is when needing long Between remain operational the steady state treatment process of state, such as tempering, the heating of hydraulic oil and the baking process of automotive lacquer of part, In these processes, due to inside equipment will continue keep high temperature state, the energy consumption kept stable state, this The correlation of energy consumption and yield is relatively weak in the technique of seed type, with booting duration, the phase of technological parameter and ambient temperature and humidity Closing property is stronger；The third technique is the technique based on artificial, the link for needing artificially to handle in actual production, due to artificial The time-consuming of technique often has much relations with specific environment, worker's state, is difficult to accomplish the completely the same of productive temp, therefore right In the technique of this type, energy consumption has certain correlation with real-time beat and yield.
The bottom of nerve network system of the invention is made of different technique neural network modules, each bottom nerve net The output of network module can combine the neural network model that certain specific global input feature vectors enter high-level together.
Fig. 2 is the training flow diagram for a certain specific neural network model that the present invention uses.Specific step explanation It is as follows:
Step S1: needing to confirm which the input feature vector of model has, can be according to above for bottom neural network module In different process type confirmation input feature high-rise neural network module is needed to consider to export it in bottom module What outside also need that input feature vector is added；
Step S2: initial data is cleaned, the processing of exceptional value and missing values, further data is normalized With dimension-reduction treatment.In the creation data of auto-parts enterprise, due to the correlation of output and inventory, it may appear that individual The case where number of days yield is negative, needs to be modified yield at this time.In the learning process of neural network model, in order to protect The convergent stability of model of a syndrome, needs that input feature vector is normalized, and normalization formula is as follows, wherein xiFor model The input feature vector of i-th of dimension:
Step S3: setting training parameter to neural network model, including model hidden layers numbers, highest the number of iterations, initial Change weight, excitation function, learning rate etc., the setting of parameter determines the quality of model learning, and suitable parameter can be to avoid Poor fitting and overfitting problem；
Step S4: in the method for cross validation, being repeatedly randomly assigned training set and test set, repeatedly training neural network mould Type reduces random error；
Step S5: the degree of fitting and prediction error of neural network model are analyzed, whether comparison reaches target value, if not reaching It arriving, return step S3 redefines neural network model parameter, if reaching target value, exportable prediction of energy consumption value.
Provided by the present invention for the energy consumption prediction technique of auto-parts manufacturing enterprise, at least possess double-level neural network The technique neural network module of module, bottom chooses different input feature vectors according to different types of process characteristic, exports as this Prediction of energy consumption value of the technique within certain a period of time.High one layer of neural network is input with the output of bottom-layer network, in conjunction with spy Some input feature vectors, training study obtain full product, full producing line, the energy consumption predicted value of full factory.Emphasis of the present invention solves automobile zero The features such as architectural difference is big between aftermarket product, process variations are big, while considering producing line adjustment, gas product flow readjustment etc. in actual production Factor can effectively distinguish the input feature vector between different levels.In the technique neural network model of bottom, according to inhomogeneity The input feature vector that the process modeling of type needs is different.For the technique based on robot, the code of each manufactured parts At the time of number, part enter each technique and the quality information of part can be as the input feature vector of model；For the place of steady state Science and engineering skill, technological parameter, environment temperature, equipment operation duration can be as the input feature vectors of model；For manual process, zero Part productive temp and scheduled production can be as the input feature vectors of model.The output of these bottom neural network models can be together with high by one The mode input feature of level is learnt into the neural network model of a high level together.
Although the present invention is disclosed as above with preferred embodiment, however, it is not to limit the invention, any this field skill Art personnel, without departing from the spirit and scope of the present invention, when can make a little modification and perfect therefore of the invention protection model It encloses to work as and subject to the definition of the claims.

Claims (5)

1. a kind of energy consumption prediction technique for auto-parts manufacturing enterprise, which comprises the steps of:
The energy input of single technology category is predicted using bottom neural network module；
Input by the output of multiple bottom neural network modules as the neural network module of a high level, in conjunction with a high level Input feature vector, energy consumption prediction is made to certain product line, certain workshop or full factory by the neural network module of a high level.
2. being used for the energy consumption prediction technique of auto-parts manufacturing enterprise as described in claim 1, which is characterized in that the bottom Layer neural network module according to technology category is divided into three kinds: the technical module based on robot, steady state treatment process module and Manual process module based on artificial；
For the technical module based on robot, the input feature vector of the bottom neural network module is each manufactured parts Code Number, part enter each technique at the time of and part quality information, export as the robot technique in the predetermined time Interior prediction of energy consumption amount；
To steady state treatment process module, the input feature vector of the bottom neural network module is technological parameter, equipment operation duration And ambient temperature and humidity, it exports as the prediction of energy consumption amount of steady state treatment process module in the given time；
To the manual process module based on artificial, the input feature vector of the bottom neural network module be part productive temp and Scheduled production exports the prediction of energy consumption amount in the given time for the artificial technical module.
3. being used for the energy consumption prediction technique of auto-parts manufacturing enterprise as claimed in claim 2, which is characterized in that the perseverance State treatment process module is part tempering module, the baking process module of hydraulic oil heating module or automotive lacquer.
4. the energy consumption prediction technique as claimed in any one of claims 1 to 3 for auto-parts manufacturing enterprise, feature exist In each neural network module includes following processing step:
S1 the level and input feature vector of neural network model) are determined；
S2) initial data is cleaned according to input feature vector, excluding outlier, and according to the complexity of product line to data Carry out dimension-reduction treatment and normalization；
S3 the hidden layer number of plies, highest the number of iterations, initialization weight, excitation function and the study speed of neural network model) are set Rate；
S4 the training set and test set) being randomly assigned in data set repeatedly train neural network mould using the method for cross validation Type；
S5) degree of fitting of neural network model and error are analyzed, if reaching desired extent, export the energy consumption of prediction Amount；If not up to desired extent, return step S3.
5. being used for the energy consumption prediction technique of auto-parts manufacturing enterprise as described in claim 1, which is characterized in that the height Periodical variable is added as input feature vector in the neural network module of one level, and the periodicity variable includes producing line plan for adjustment Or festivals or holidays arrange.
CN201810635530.1A 2018-06-20 2018-06-20 Energy consumption prediction technique for auto-parts manufacturing enterprise Pending CN109034452A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810635530.1A CN109034452A (en) 2018-06-20 2018-06-20 Energy consumption prediction technique for auto-parts manufacturing enterprise

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810635530.1A CN109034452A (en) 2018-06-20 2018-06-20 Energy consumption prediction technique for auto-parts manufacturing enterprise

Publications (1)

Publication Number Publication Date
CN109034452A true CN109034452A (en) 2018-12-18

Family

ID=64610032

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810635530.1A Pending CN109034452A (en) 2018-06-20 2018-06-20 Energy consumption prediction technique for auto-parts manufacturing enterprise

Country Status (1)

Country Link
CN (1) CN109034452A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110376977A (en) * 2019-06-05 2019-10-25 广州明珞汽车装备有限公司 A kind of calculation method of cycle period, system, device and storage medium
CN112706161A (en) * 2020-11-17 2021-04-27 中国航空工业集团公司北京长城航空测控技术研究所 Gluing control system with intelligent sensing capability
CN112990591A (en) * 2021-03-26 2021-06-18 江西省能源大数据有限公司 Multi-dimensional energy consumption data analysis method based on convolutional neural network and enterprise energy consumption prediction model
CN117875680A (en) * 2024-03-13 2024-04-12 南京理工大学 Flexible control method for hydraulic pump production flow based on process atomic model

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102621932A (en) * 2012-05-02 2012-08-01 重庆大学 Energy consumption prediction method for use in service process of numerically-controlled machine tool
CN103235554A (en) * 2013-03-29 2013-08-07 重庆大学 Numerically controlled lathe processing workpiece energy consumption acquiring method based on NC (numerical control) codes
CN103971019A (en) * 2014-05-23 2014-08-06 武汉科技大学 Method for predicting workpiece machining energy consumption based on geometrical characteristics
CN105320991A (en) * 2014-07-04 2016-02-10 上海宝信软件股份有限公司 Factor-based steel enterprise process energy consumption prediction method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102621932A (en) * 2012-05-02 2012-08-01 重庆大学 Energy consumption prediction method for use in service process of numerically-controlled machine tool
CN103235554A (en) * 2013-03-29 2013-08-07 重庆大学 Numerically controlled lathe processing workpiece energy consumption acquiring method based on NC (numerical control) codes
CN103971019A (en) * 2014-05-23 2014-08-06 武汉科技大学 Method for predicting workpiece machining energy consumption based on geometrical characteristics
CN105320991A (en) * 2014-07-04 2016-02-10 上海宝信软件股份有限公司 Factor-based steel enterprise process energy consumption prediction method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
单汨源 等: "大规模定制产品多级神经网络成本估算方法研究", 《中国机械工程》 *
李然然 等: "基于BP神经网络的建筑物用电能耗预测", 《山东建筑大学学报》 *
胡珉 等: "基于多级神经网络的盾构法隧道施工参数控制", 《计算机工程》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110376977A (en) * 2019-06-05 2019-10-25 广州明珞汽车装备有限公司 A kind of calculation method of cycle period, system, device and storage medium
CN110376977B (en) * 2019-06-05 2020-10-27 广州明珞汽车装备有限公司 Method, system, device and storage medium for calculating cycle period
CN112706161A (en) * 2020-11-17 2021-04-27 中国航空工业集团公司北京长城航空测控技术研究所 Gluing control system with intelligent sensing capability
CN112990591A (en) * 2021-03-26 2021-06-18 江西省能源大数据有限公司 Multi-dimensional energy consumption data analysis method based on convolutional neural network and enterprise energy consumption prediction model
CN117875680A (en) * 2024-03-13 2024-04-12 南京理工大学 Flexible control method for hydraulic pump production flow based on process atomic model

Similar Documents

Publication Publication Date Title
CN109034452A (en) Energy consumption prediction technique for auto-parts manufacturing enterprise
CN108108832B (en) A kind of oil truck oil and gas leakage intelligent monitor system based on wireless sensor network
Kukolj et al. Identification of complex systems based on neural and Takagi-Sugeno fuzzy model
CN105388859B (en) Method and system for the control based on adaptive model of multi- input multi output plant
CN107292702A (en) A kind of intelligence manufacture method and system
Hachicha A simulation metamodelling based neural networks for lot-sizing problem in MTO sector
CN104122796B (en) A kind of Intelligent assembly Sequence Planning method
CN110244557B (en) Closed-loop modeling method of industrial process multi-order inertia closed-loop system
Murtaza et al. Neuromodex—Neural network system for modular construction decision making
CN109100975A (en) A kind of parameter optimization method and system
CN110489707A (en) A kind of solution of Inverse Kinematics method based on GAN network
Beruvides et al. Fault pattern identification in multi-stage assembly processes with non-ideal sheet-metal parts based on reinforcement learning architecture
Gharoun et al. Using an intelligent algorithm for performance improvement of two-sided assembly line balancing problem considering learning effect and allocation of multi-skilled operators
Salmasnia et al. A robust intelligent framework for multiple response statistical optimization problems based on artificial neural network and Taguchi method
CN107511823B (en) The method of robot manipulating task track optimizing analysis
CN106650918B (en) The method and apparatus for constructing system model
Liu et al. Digital twin-driven robotic disassembly sequence dynamic planning under uncertain missing condition
Souza et al. Co-evolutionary genetic multilayer perceptron for feature selection and model design
Kutschenreiter-Praszkiewicz Application of artificial neural network for determination of standard time in machining
Ali et al. Design quality and robustness with neural networks
Fazlollahtabar et al. Producer’s behavior analysis in an uncertain bicriteria AGV-based flexible jobshop manufacturing system with expert system
CN111415051A (en) Power material demand plan prediction method based on BP neural network
CN108319146B (en) Discrete particle swarm training-based method for radial basis function neural network
CN109814389A (en) The tight format non-model control method of the different factor of the MIMO of parameter self-tuning
Stryczek A hybrid approach for manufacturability analysis

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20181218