WO2025200750A1 - 一种面向离散制造的工业数据混成模型构建方法及系统 - Google Patents

一种面向离散制造的工业数据混成模型构建方法及系统

Info

Publication number
WO2025200750A1
WO2025200750A1 PCT/CN2025/073820 CN2025073820W WO2025200750A1 WO 2025200750 A1 WO2025200750 A1 WO 2025200750A1 CN 2025073820 W CN2025073820 W CN 2025073820W WO 2025200750 A1 WO2025200750 A1 WO 2025200750A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
output
data
feature
discrete manufacturing
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
PCT/CN2025/073820
Other languages
English (en)
French (fr)
Inventor
杨海根
张晓林
戴尔晗
葛艳
刘佶鑫
曾凡玉
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.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
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 Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Publication of WO2025200750A1 publication Critical patent/WO2025200750A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067Enterprise or organisation modelling
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/243Classification techniques relating to the number of classes
    • G06F18/24323Tree-organised classifiers
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/01Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; 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 purpose of the present invention is to provide a hybrid model construction method and system based on reinforcement learning for intelligent reasoning of discrete manufacturing industrial data, so as to solve the multi-source, heterogeneous and multi-scale problems of discrete manufacturing industrial data.
  • the method for constructing an industrial data hybrid model for discrete manufacturing comprises the following steps:
  • the first model is used to obtain a fitting curve of the feature data in a discrete space
  • the second model is used to perform ensemble learning on the feature data using a decision tree as a weak learner.
  • the first model calculates the output for each input feature vector
  • l represents industrial loss
  • w t is the weight vector of the input vector
  • xi is the input feature vector
  • i 1, 2, ... n;
  • B is the penalty term
  • y is the actual target value of the sample
  • w is the weight vector
  • is the threshold of tolerable error
  • ei is the slack variable.
  • the objective function of the second model is By iteratively adding tree models to minimize the objective function; where loss is the discrete manufacturing industry dataset loss, M and is the number of decision tree child nodes and their weights, and C is the penalty coefficient.
  • the weight w 1 of the first output and the weight w 2 of the second output are calculated using a least squares weight fusion method.
  • the discrete manufacturing-oriented industrial data hybrid model construction system of the present invention includes:
  • Feature extraction unit used to collect discrete manufacturing industrial data in real time and perform feature extraction to obtain feature vectors
  • the hybrid model establishing unit is configured to perform a weighted summation of the first output and the second output to obtain a hybrid model of the industrial data.
  • the first model calculates the output for each input feature vector
  • l represents industrial loss
  • w t is the weight vector of the input vector
  • xi is the input feature vector
  • i 1, 2, ... n;
  • B is the penalty term
  • y is the actual target value of the sample
  • w is the weight vector
  • is the threshold of tolerable error
  • e i is the slack variable
  • the objective function of the second model is By iteratively adding tree models to minimize the objective function; where loss is the discrete manufacturing industry dataset loss, M and is the number of decision tree child nodes and their weights, and C is the penalty coefficient.
  • the electronic device described in the present invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. It is characterized in that when the computer program is loaded into the processor, it implements the method for constructing an industrial data hybrid model for discrete manufacturing.
  • the computer-readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor, the method for constructing an industrial data hybrid model for discrete manufacturing is implemented.
  • the present invention proposes to pass discrete manufacturing industrial data through two models respectively, apply the least squares weight fusion method, and output a hybrid model of intelligent reasoning of discrete manufacturing industrial data. It intersects with traditional data intelligent reasoning methods, is more adaptable to dynamically changing environments and problems, and better meets the complex and changeable business scenario requirements of the discrete manufacturing industry.
  • FIG1 is a flow chart of a hybrid model construction method according to an embodiment of the present invention.
  • the method for constructing an industrial data hybrid model for discrete manufacturing includes the following steps.
  • S1 collects industrial data from discrete manufacturing in real time (including real-time equipment status data, energy consumption data, lifecycle data, sensor data, production process data, and quality data).
  • the collected data is mapped from the original feature space to a high-dimensional feature space for easy fitting.
  • the discrete manufacturing industrial data are respectively processed by the discrete data vector regression (DSVR) algorithm and the discrete data gradient boosting (DXGB) algorithm.
  • DSVR discrete data vector regression
  • DXGB discrete data gradient boosting
  • w t is the weight vector of the input vector, is a high-dimensional feature space, and xi is the input vector.
  • DSVR The purpose of DSVR is to optimize the model by minimizing the loss l.
  • w t and l are obtained.
  • certain constraints must be observed. ⁇ cannot be set too large or too small, so the variable e i is set for each sample of DSVR to avoid losing rationality:
  • B is the penalty coefficient, which is generally set to 1
  • y is the actual target value of the sample
  • w is the weight vector
  • is the threshold of tolerable error
  • ei is the slack variable.
  • the ensemble mode of the learner is: fK ( xi ) ⁇ R, xi is the input vector of the ith discrete manufacturing industry data, K is the number of weak learners, R is the original feature space of discrete manufacturing industry data, fK is the function in R, representing the model of the Kth tree trained.
  • the DXGB objective function is By iteratively adding tree models to minimize the objective function.
  • loss is the loss of discrete manufacturing industry dataset, M and is the number of child nodes and their weights, and C is the penalty coefficient.
  • the R2 indicator is used to evaluate the model parameters.
  • the discrete manufacturing-oriented industrial data hybrid model construction system of the present invention includes:
  • Feature extraction unit used to collect discrete manufacturing industrial data in real time and perform feature extraction to obtain feature vectors
  • a data processing unit configured to obtain a first output and a second output by passing the feature data through a first model and a second model, respectively;
  • the first model is configured to obtain a fitting curve for the feature data in a discrete space, and the second model is configured to perform ensemble learning on the feature data using a decision tree as a weak learner;
  • the hybrid model establishing unit is configured to perform a weighted summation of the first output and the second output to obtain a hybrid model of the industrial data.
  • the electronic device described in the present invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. It is characterized in that when the computer program is loaded into the processor, it implements the method for constructing an industrial data hybrid model for discrete manufacturing.
  • the computer-readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor, the method for constructing an industrial data hybrid model for discrete manufacturing is implemented.
  • the computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • the processor is configured to execute the computer program stored in the memory to implement the various steps in the method involved in the above embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marketing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Manufacturing & Machinery (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Computational Linguistics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种面向离散制造的工业数据混成模型构建方法及系统,该方法首先实时采集离散制造工业数据并进行特征提取,得到特征向量,然后将特征数据分别通过第一模型和第二模型得到第一输出和第二输出;将第一输出和第二输出加权求和,得到工业数据的混成模型;第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习。针对离散制造业的业务场景复杂多变这一特性,提高了数据智能推理的灵活性。

Description

一种面向离散制造的工业数据混成模型构建方法及系统 技术领域
本发明涉及智能推理领域,尤其是面向离散制造的工业数据混成模型构建方法及系统。
背景技术
随着离散制造工业迎来数字化转型时代,数据驱动的智能推理成为提升生产效率和质量、降低能耗的关键。在离散制造工业中,数据可能来自多个源头,包括传感器、设备、生产线等,而且在制造环境中,许多决策需要实时响应,而不仅仅是对历史数据的分析。工业环境中的条件也可能在不断变化,需要推理系统能够在不断变化的环境中持续优化性能,以适应新的工艺和要求。制造业往往涉及复杂的生产过程,涉及多个环节和阶段,所以,离散制造工业数据具有多源异构,海量,高维,多尺度,多时空,实时性要求高等特点,建立准确的模型来推理这些复杂过程非常具有挑战性。
传统的数据智能推理的方法一般较为静态、简单,难以灵活地适应动态变化的环境和问题。对于实时性要求高的应用场景,传统方法可能显得不够灵活,针对某种单一类型的工业数据表现较好,但如果数据来源为多源数据或者多时空多尺度数据,则需要不断地手动更新规则和逻辑或者选择更合适的模型,这使得基于传统模型的数据推理显得不够灵活。
发明内容
发明目的:本发明的目的是提供一种基于强化学习的混成模型构建方法及系统,用于离散制造工业数据智能推理,以解决离散制造工业数据多源异构、多尺度的问题。
技术方案:本发明所述的面向离散制造的工业数据混成模型构建方法,包括如下步骤:
实时采集离散制造工业数据并进行特征提取,得到特征向量;
将所述特征数据分别通过第一模型和第二模型得到第一输出和第二输出;
将所述第一输出和第二输出加权求和,得到工业数据的混成模型;
所述第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习。
进一步地,所述第一模型对于每个输入的特征向量计算输出其中l代表工业损耗,wt为输入向量的权重向量,为高维特征空间,xi为输入的特征向量,i=1,2,…n;
通过最小化l求解得到l和wt,求解过程中满足约束条件:
其中,B为惩罚项,y为样本的实际目标值,w为权重向量,ε为可容忍误差的阈值,ei为松弛变量。
进一步地,所述第二模型对于每个输入的特征向量计算输出fK(xi)∈R,其中K为弱学习器数量,R为离散制造工业数据原始特征空间,xi为输入的特征向量,i=1,2,…n;fK为R中的函数,代表的是训练的第K棵树的模型;
所述第二模型的目标函数为通过迭代地添加树模型,以最小化目标函数;其中loss为离散制造工业数据集损耗,M和为决策树子节点数量及其权重,C为惩罚系数。
进一步地,所述混成模型为Y=w1y1+w2y2,其中y1为第一输出,w1为第一输出的权重,y2为第二输出,w2为第二输出的权重。
进一步地,利用最小二乘权值融合法计算所述第一输出的权重w1和第二输出的权重w2
进一步地,采用R2指标对所述混成模型的参数进行评价。
本发明所述的面向离散制造的工业数据混成模型构建系统,包括:
特征提取单元,用于实时采集离散制造工业数据并进行特征提取,得到特征向量;
数据处理单元,用于将所述特征数据分别通过第一模型和第二模型得到第一输出和第二输出;所述第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习;
混成模型建立单元,用于将所述第一输出和第二输出加权求和,得到工业数据的混成模型。
进一步地,所述第一模型对于每个输入的特征向量计算输出其中l代表工业损耗,wt为输入向量的权重向量,为高维特征空间,xi为输入的特征向量,i=1,2,…n;
通过最小化l求解得到l和wt,求解过程中满足约束条件:
其中,B为惩罚项,y为样本的实际目标值,w为权重向量,ε为可容忍误差的阈值,ei为松弛变量;
所述第二模型对于每个输入的特征向量计算输出fK(xi)∈R,其中K为弱学习器数量,R为离散制造工业数据原始特征空间,xi为输入的特征向量,i=1,2,…n;fK为R中的函数,代表的是训练的第K棵树的模型;
所述第二模型的目标函数为通过迭代地添加树模型,以最小化目标函数;其中loss为离散制造工业数据集损耗,M和为决策树子节点数量及其权重,C为惩罚系数。
本发明所述的电子设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其特征在于,所述计算机程序被加载至处理器时实现所述的面向离散制造的工业数据混成模型构建方法。
本发明所述的计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现所述的面向离散制造的工业数据混成模型构建方法。
有益效果:与现有技术相比,本发明的优点在于:本发明提出了将离散制造工业数据分别通过两种模型,应用最小二乘权值融合法,输出得到离散制造工业数据智能推理的混成模型,相交传统的数据智能推理方法,更够适应动态变化的环境和问题,更加满足离散制造业复杂多变的业务场景需求。
附图说明
图1为本发明实施例的混成模型构建方法流程图。
具体实施方式
下面结合附图对本发明的技术方案作进一步说明。
如图1所示,所述面向离散制造的工业数据混成模型构建方法,包括以下步骤。
S1,实时采集离散制造上工业数据(包括诸如:实时设备状态数据、能源消耗数据、生命周期数据、传感器数据、生产过程数据和质量数据等)。将采集到的数据从原始特征空间映射到高维特征空间,以便于拟合。
S2,将离散制造工业数据分别通过离散数据向量回归(DSVR)算法、离散数据梯度增强(DXGB)算法。
(1)DSVR算法:
通过在离散空间中找到一条曲线并使所有数据点都尽量离该曲线足够近,以使其损耗最小,以便用于后续的数据推理。
其中l代表工业损耗,wt为输入向量的权重向量,为高维特征空间,xi为输入向量。
DSVR的目的是通过得到最小化损耗l来优化模型,通过求解得到wt和l,但在求解过程中,要遵守一定的约束条件ε不能设置太大也不能设置太小,因此为DSVR每个样本设置变量ei,以避免丢失合理性:
其中,B为惩罚系数,一般设置为1,y为样本的实际目标值,w为权重向量,ε为可容忍误差的阈值,ei为松弛变量。
(2)DXGB算法:
以决策树为弱学习器,其学习器的集成模式为:fK(xi)∈R,xi为第i个离散制造工业数据的输入向量,K为弱学习器数量,R为离散制造工业数据原始特征空间,fK为R中的函数,代表的是训练的第K棵树的模型。DXGB目标函数为通过迭代地添加树模型,以最小化目标函数。loss为离散制造工业数据集损耗,M和为子节点数量及其权重,C为惩罚系数。
S3,离散制造工业数据通过两种模型后,应用最小二乘权值融合法,可得组合权重,输出即为混成模型:Y=w1y1+w2y2,其中w1为DSVR在混成模型所占的权值,w2为DXGB在混成模型中所占的权值,其损失函数为满足约束条件w1+w2=1,对综合权值进行最优求解,使损失函数H最小,即minH,同时得到w1和w2。其中w1为DSVR在混成模型所占的权值,w2为DXGB在混成模型中所占的权值。
S4,采用R2指标对模型参数进行评价。
其中,λ2为方差,MSE为均方误差。R2的评分越接近于1,表示混成模型效果越好。
本发明所述的面向离散制造的工业数据混成模型构建系统,包括:
特征提取单元,用于实时采集离散制造工业数据并进行特征提取,得到特征向量;
数据处理单元,用于将所述特征数据分别通过第一模型和第二模型得到第一输出和第二输出;所述第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习;
混成模型建立单元,用于将所述第一输出和第二输出加权求和,得到工业数据的混成模型。
本发明所述的电子设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其特征在于,所述计算机程序被加载至处理器时实现所述的面向离散制造的工业数据混成模型构建方法。
本发明所述的计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现所述的面向离散制造的工业数据混成模型构建方法。
所述计算机可读存储媒体可包括RAM、ROM、EEPROM、CD-ROM或其它光盘存储装置、磁盘存储装置或其它磁性存储装置、快闪存储器或可用来存储指令或数据结构的形式的所要程序代码并且可由计算机存取的任何其它媒体。
处理器用于执行存储器存储的计算机程序,以实现上述实施例涉及的方法中的各个步骤。

Claims (7)

  1. 一种面向离散制造的工业数据混成模型构建方法,其特征在于,包括如下步骤:
    实时采集离散制造工业数据并进行特征提取,得到特征向量;
    将特征数据分别通过第一模型和第二模型得到第一输出和第二输出;
    将所述第一输出和第二输出加权求和,得到工业数据的混成模型;
    所述第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习;
    所述第一模型对于每个输入的特征向量计算输出其中l代表工业损耗,wt为输入向量的权重向量,为高维特征空间,xi为输入的特征向量,i=1,2,…n;
    通过最小化l求解得到l和wt,求解过程中满足约束条件:
    其中,B为惩罚项,y为样本的实际目标值,w为权重向量,ε为可容忍误差的阈值,ei为松弛变量;
    所述第二模型对于每个输入的特征向量计算输出其中K为弱学习器数量,R为离散制造工业数据原始特征空间,xi为输入的特征向量,i=1,2,…n;fK为R中的函数,代表的是训练的第K棵树的模型;
    所述第二模型的目标函数为通过迭代地添加树模型,以最小化目标函数;其中loss为离散制造工业数据集损耗,M和为决策树子节点数量及其权重,C为惩罚系数。
  2. 根据权利要求1所述的面向离散制造的工业数据混成模型构建方法,其特征在于,所述混成模型为Y=w1y1+w2y2,其中y1为第一输出,w1为第一输出的权重,y2为第二输出,w2为第二输出的权重。
  3. 根据权利要求2所述的面向离散制造的工业数据混成模型构建方法,其特征在于,利用最小二乘权值融合法计算所述第一输出的权重w1和第二输出的权重w2
  4. 根据权利要求1所述的面向离散制造的工业数据混成模型构建方法,其特征在于,采用R2指标对所述混成模型的参数进行评价。
  5. 一种面向离散制造的工业数据混成模型构建系统,其特征在于,包括:
    特征提取单元,用于实时采集离散制造工业数据并进行特征提取,得到特征向量;
    数据处理单元,用于将特征数据分别通过第一模型和第二模型得到第一输出和第二输出;所述第一模型用于在离散空间中得到所述特征数据的一条拟合曲线,所述第二模型用于以决策树为弱学习器对所述特征数据进行集成学习;
    混成模型建立单元,用于将所述第一输出和第二输出加权求和,得到工业数据的混成模型;
    所述第一模型对于每个输入的特征向量计算输出其中l代表工业损耗,wt为输入向量的权重向量,为高维特征空间,xi为输入的特征向量,i=1,2,…n;
    通过最小化l求解得到l和wt,求解过程中满足约束条件:
    其中,B为惩罚项,y为样本的实际目标值,w为权重向量,ε为可容忍误差的阈值,ei为松弛变量;
    所述第二模型对于每个输入的特征向量计算输出其中K为弱学习器数量,R为离散制造工业数据原始特征空间,xi为输入的特征向量,i=1,2,…n;fK为R中的函数,代表的是训练的第K棵树的模型;
    所述第二模型的目标函数为通过迭代地添加树模型,以最小化目标函数;其中loss为离散制造工业数据集损耗,M和为决策树子节点数量及其权重,C为惩罚系数。
  6. 一种电子设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其特征在于,所述计算机程序被加载至处理器时实现根据权利要求1-4任一项所述的面向离散制造的工业数据混成模型构建方法。
  7. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现根据权利要求1-4任一项所述的面向离散制造的工业数据混成模型构建方法。
PCT/CN2025/073820 2024-10-15 2025-01-22 一种面向离散制造的工业数据混成模型构建方法及系统 Pending WO2025200750A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202411435720.0 2024-10-15
CN202411435720.0A CN118941174B (zh) 2024-10-15 2024-10-15 一种面向离散制造的工业数据混成模型构建方法及系统

Publications (1)

Publication Number Publication Date
WO2025200750A1 true WO2025200750A1 (zh) 2025-10-02

Family

ID=93353703

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/073820 Pending WO2025200750A1 (zh) 2024-10-15 2025-01-22 一种面向离散制造的工业数据混成模型构建方法及系统

Country Status (2)

Country Link
CN (1) CN118941174B (zh)
WO (1) WO2025200750A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118941174B (zh) * 2024-10-15 2024-12-06 南京邮电大学 一种面向离散制造的工业数据混成模型构建方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160189058A1 (en) * 2013-07-22 2016-06-30 Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi Incremental learner via an adaptive mixture of weak learners distributed on a non-rigid binary tree
CN110837921A (zh) * 2019-10-29 2020-02-25 西安建筑科技大学 基于梯度提升决策树混合模型的房地产价格预测研究方法
CN115130741A (zh) * 2022-06-20 2022-09-30 北京工业大学 基于多模型融合的多因素电力需求中短期预测方法
CN116128316A (zh) * 2022-12-22 2023-05-16 南京邮电大学 一种基于深度强化学习的离散制造工业数据表征方法
CN116301817A (zh) * 2023-03-28 2023-06-23 重庆大学 一种适用于信息物理系统的建模与验证方法
CN117973600A (zh) * 2024-01-12 2024-05-03 杭州华辰电力控制工程有限公司 一种基于多源数据融合集成的水库水位预测方法
CN118941174A (zh) * 2024-10-15 2024-11-12 南京邮电大学 一种面向离散制造的工业数据混成模型构建方法及系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240385315A1 (en) * 2021-08-24 2024-11-21 Provizio Limited Automotive sensor fusion of radar, lidar, camera systems with improved safety by use of machine learning

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160189058A1 (en) * 2013-07-22 2016-06-30 Aselsan Elektronik Sanayi Ve Ticaret Anonim Sirketi Incremental learner via an adaptive mixture of weak learners distributed on a non-rigid binary tree
CN110837921A (zh) * 2019-10-29 2020-02-25 西安建筑科技大学 基于梯度提升决策树混合模型的房地产价格预测研究方法
CN115130741A (zh) * 2022-06-20 2022-09-30 北京工业大学 基于多模型融合的多因素电力需求中短期预测方法
CN116128316A (zh) * 2022-12-22 2023-05-16 南京邮电大学 一种基于深度强化学习的离散制造工业数据表征方法
CN116301817A (zh) * 2023-03-28 2023-06-23 重庆大学 一种适用于信息物理系统的建模与验证方法
CN117973600A (zh) * 2024-01-12 2024-05-03 杭州华辰电力控制工程有限公司 一种基于多源数据融合集成的水库水位预测方法
CN118941174A (zh) * 2024-10-15 2024-11-12 南京邮电大学 一种面向离散制造的工业数据混成模型构建方法及系统

Also Published As

Publication number Publication date
CN118941174B (zh) 2024-12-06
CN118941174A (zh) 2024-11-12

Similar Documents

Publication Publication Date Title
CN119067028B (zh) 基于机器学习的集成电路工艺参数优化方法及系统
CN116151581B (zh) 一种柔性车间调度方法、系统及电子设备
CN109241291A (zh) 基于深度强化学习的知识图谱最优路径查询系统及其方法
CN114047706B (zh) 面向可重入工业制造系统的模糊动态积分滑模控制方法
CN111127246A (zh) 一种输电线路工程造价的智能预测方法
CN118760100B (zh) 一种大规模模糊柔性作业车间调度方法及相关设备
CN116500986B (zh) 一种分布式作业车间的优先调度规则生成方法及系统
CN118368306B (zh) 一种基于元学习多变图网络的电气自动化生态物联网系统
CN114529040A (zh) 一种机电产品装配误差在线预测方法
CN114463596A (zh) 一种超图神经网络的小样本图像识别方法、装置及设备
CN115454988A (zh) 基于随机森林网络的卫星电源系统缺失数据补全方法
CN120069615A (zh) 一种电力交易趋势预测与决策支持系统及方法
Caballero et al. Optimized neural networks in industrial data analysis
CN117592385B (zh) 基于影响因子的体系设计优化方法、服务器及存储介质
CN119589193A (zh) 一种汽车白车身焊接工艺规划方法
CN118941174B (zh) 一种面向离散制造的工业数据混成模型构建方法及系统
CN113591398A (zh) 基于深度强化学习的智能作业分批方法、装置及电子设备
CN116718198A (zh) 基于时序知识图谱的无人机集群的路径规划方法及系统
CN119270736B (zh) 基于人工智能的机器人远程协同调度方法及系统
CN112862211A (zh) 通信管理系统动环缺陷派单方法及装置
CN118605407A (zh) 一种集成遗传表达式编程和双延迟深度确定性策略梯度算法的装配车间物流任务实时调度方法及系统
KR20250077737A (ko) 전이 최적화된 객체 탐지를 위한 신경망 구조 탐색 방법
CN115374686B (zh) 自主增量知识提取和表示方法、终端及介质
CN117764192A (zh) 构建对比矩阵的方法和系统以及层次分析方法和系统
CN115620807A (zh) 靶点蛋白分子与药物分子之间相互作用强度的预测方法

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: 25776336

Country of ref document: EP

Kind code of ref document: A1