WO2019041734A1 - 潜在过程参数挖掘方法及装置 - Google Patents

潜在过程参数挖掘方法及装置 Download PDF

Info

Publication number
WO2019041734A1
WO2019041734A1 PCT/CN2018/073667 CN2018073667W WO2019041734A1 WO 2019041734 A1 WO2019041734 A1 WO 2019041734A1 CN 2018073667 W CN2018073667 W CN 2018073667W WO 2019041734 A1 WO2019041734 A1 WO 2019041734A1
Authority
WO
WIPO (PCT)
Prior art keywords
process parameters
potential
potential process
test
key
Prior art date
Application number
PCT/CN2018/073667
Other languages
English (en)
French (fr)
Inventor
萧伟
刘雪松
凌娅
陈勇
王振中
姜晓红
毕宇安
李页瑞
包乐伟
章晨峰
王磊
陈永杰
Original Assignee
江苏康缘药业股份有限公司
浙江大学
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 江苏康缘药业股份有限公司, 浙江大学 filed Critical 江苏康缘药业股份有限公司
Publication of WO2019041734A1 publication Critical patent/WO2019041734A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • 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
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C3/00Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
    • 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 invention relates to the field of process knowledge systems, in particular to a method and device for mining potential process parameters.
  • PKS Process Knowledge System
  • the result of parameter design is often a single point parameter.
  • honeysuckle extraction temperature parameter as an example, firstly, multiple batches of honeysuckle extraction section temperature parameter data are collected, and then each batch is subjected to data processing to extract The key point of the reaction temperature change, again, processing each key point, the normalized distribution of the processed key points of multiple batches, with a certain fitness as the final parameter design point.
  • the single-point design causes the PKS parameters to be released in a narrow range. Even if the process capability is low, the design space cannot be optimized, which is not conducive to PKS. Play a role in smart manufacturing. There is currently no method for mining potential process parameters in the PKS parameter design space.
  • the present invention provides a method and apparatus for mining potential process parameters, testing potential process parameters, screening out potential process parameters to be verified related to key quality attributes, and utilizing potential process parameters to be verified. Update the optimized design space to provide an effective and reliable solution for parameter release.
  • the technical solution is as follows:
  • the present invention provides a method for mining potential process parameters, including:
  • performing the second test on the process parameter to obtain the potential process parameters to be verified includes:
  • the process parameter corresponding to the significant coefficient smaller than the significant coefficient threshold is taken as the potential process parameter to be verified.
  • the performing the second test on the process parameter to obtain the potential process parameters to be verified includes:
  • Correlation analysis is performed on the process parameters that meet the deviation threshold, and a correlation coefficient between the process parameters and the key quality attributes is obtained;
  • the process parameter corresponding to the significant coefficient smaller than the significant coefficient threshold is taken as the potential process parameter to be verified.
  • the first test of the proposed potential process parameters includes:
  • the first test of the proposed potential process parameters includes:
  • a Plackett-Burman test is performed on the proposed potential process parameters, and the process parameters are screened according to the screening rules.
  • verifying the potential process parameters to be verified includes:
  • the design space being a specific interval range corresponding to the key quality attribute.
  • relationship model between establishing the key quality attribute and the updated key process parameter includes:
  • a stepwise regression method is used to fit the standardized key process parameters and key quality attributes to obtain a relationship model, and the stepwise regression includes:
  • the determination coefficient is lower than the deterministic threshold, the confidence of the selection is expanded until the determination coefficient is greater than the deterministic threshold.
  • the potential process parameter mining request further includes a release parameter of the design space
  • the obtaining the key quality attribute corresponding to the work segment and formulating the potential process parameter set according to the section condition information includes:
  • Potential process parameters related to the key quality attributes are formulated within a range other than the release parameters to form a set of potential process parameters.
  • the present invention provides a potential process parameter mining device, the device comprising the following modules:
  • a requesting module configured to receive a potential process parameter mining request, where the request includes the section condition information corresponding to the design space
  • a module configured to acquire a key quality attribute corresponding to the work section and formulate a set of potential process parameters according to the condition information of the work section;
  • a first test module configured to perform a first test on the proposed potential process parameters to obtain a plurality of process parameters
  • a second test module configured to perform a second test on the process parameter to obtain a potential process parameter to be verified
  • a verification module for verifying potential process parameters for verification and obtaining potential process parameters.
  • the second test module includes:
  • Test design unit for designing orthogonal tests to obtain inter-group test data and test data within the group
  • the variance analysis unit is configured to perform variance analysis on the inter-group test data and the test data in the group to obtain a squared deviation ratio of the mean square deviation;
  • a significant coefficient unit configured to match a corresponding significant coefficient according to the squared deviation ratio of the mean square dispersion
  • a screening unit configured to screen, according to the significant coefficient, a potential process parameter to be verified.
  • the verification module includes:
  • the key process parameter library updating unit includes adding a potential process parameter to be verified to the key process parameter library of the design space, and updating the key process parameter set;
  • a model unit for establishing a relationship model between key quality attributes and updated key process parameters
  • the design space update unit includes updating a design space according to the relationship model, the design space being a specific range of intervals corresponding to the key quality attribute.
  • FIG. 1 is a flowchart of a method for mining a potential process parameter according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a screening method for a potential process parameter to be verified according to an embodiment of the present invention
  • FIG. 3 is a flowchart of a method for screening potential process parameters to be verified according to an embodiment of the present invention
  • FIG. 4 is a flowchart of a method for verifying a potential process parameter to be verified according to an embodiment of the present invention
  • FIG. 5 is a flowchart of a method for establishing a relationship model according to an embodiment of the present invention
  • FIG. 6 is a block diagram of a module of a potential process parameter mining apparatus according to an embodiment of the present invention.
  • Figure 7 is a graph showing the relationship between the temperature of the chemical solution and the index A of the index of the present invention.
  • FIG. 8 is a flowchart of a method for performing a second test on a process parameter according to an embodiment of the present invention.
  • a potential process parameter mining method for mining potential process parameters, see FIG.
  • the method includes the following processes:
  • the potential process parameter mining request further includes a release parameter of the design space.
  • a release parameter of the design space For example, in the alcohol precipitation section of botanical injection, the transfer rate of indicator components and the removal rate of impurities are Critical Quality Attributes (CQA), plus The index component A has the highest content, so the indicator component A can be selected as the indicator component.
  • CQA Critical Quality Attributes
  • the release parameter of the design space is found in the design space search process, and CQA Critical Process Parameter (CPP).
  • the section condition information determine the corresponding key quality attribute (CQA); query the release parameter of the design space, ie CPP Deriving potential process parameters related to the key quality attributes in a range other than the release parameters to form a set of potential process parameters.
  • CQA key quality attribute
  • the principle of this step is to select as many potential process parameters as possible under the premise of analysis and judgment. .
  • the mining of potential process parameters can be considered from two aspects.
  • One aspect is the comparison of small test research and factory-produced SOP.
  • Excavate process parameters not considered in actual production such as production ambient temperature.
  • the following three ways can be used to excavate the process parameters that are not considered in actual production: First, according to the accumulated production experience, if the quality management personnel find that the product quality is different in winter and summer, the environmental temperature can be listed as a potential process. Secondly, the quality index with insufficient process capability is the object, and the related process research is consulted, and the process parameters of the literature design are compared and screened in many aspects.
  • the first test is a preliminary screening of the proposed potential process parameters.
  • the purpose of the screening is to exclude some less relevant process parameters from the set of potential process parameters, so as to lay the foundation for the next test.
  • the set of potential process parameters to be investigated (you can first collect data on a certain number of potential process parameters in production, and float up and down 50% in this range) Set the scope of the experiment), set 5 or more levels for each factor for single factor investigation.
  • the temperature of the traditional Chinese medicine solution is generally between 10 and 20 °C.
  • the single factor is used to set the temperature level of the liquid medicine to 5, 10, 15 , 20 , 25 ° C, see Table 1 below to select the appropriate number of test repetitions.
  • the relationship between the temperature of the liquid and the index of the component A is shown in Figure 7.
  • the temperature of the liquid is generally controlled at 10-15. °C, however, in the present example, the single factor preliminary analysis found that the temperature of the liquid solution had an effect on the transfer rate of the index component A. At 20 °C, the transfer rate of the extracted component A was the highest, and it was seen that the previous production was neglected.
  • the temperature of the liquid solution of °C should be taken as the potential process parameter to be investigated.
  • only the example is selected, and the selection of the index can be analyzed according to the specific situation.
  • the second test is to further screen the preliminary screening results obtained after the first test, and obtain the more relevant potential process parameters that are highly likely to improve the spatial ability.
  • the second test uses an orthogonal design experiment to screen the range of factors for each factor based on the results of the single factor study, each factor setting 3
  • the level is analyzed and the variance of the experimental design results is analyzed to obtain the potential process parameters and the optimal process values to be investigated.
  • the parameters with significant influence in the single factor investigation were selected to further orthogonal design, and the influence of the investigation factors on the quality indicators was confirmed.
  • the single factor investigation found that the pre-intermediate solid content and the temperature of the liquid have a great influence on the quality index.
  • the orthogonal design of the two factors is used to further confirm the influence of the investigation factors on the quality index. See the following table. 2 :
  • the former intermediate solid content has an effect on the index component A transfer rate, but it is not significant, and the liquid temperature is on the index component A.
  • the transfer rate effect is more pronounced (the smaller the p, the more significant the effect), so the liquid temperature is ultimately used as a potential process parameter to be verified.
  • Embodiment 2 the method flow of the second test is detailed in Embodiment 2.
  • the data acquisition device that installs the potential process parameters is updated based on the results of the verified potential process parameters.
  • the determined potential process parameter data is added to the process parameter data for the design space search, specifically, the verification method flow is in the embodiment. Detailed in 3.
  • the first testing process is as follows: keeping other parameters unchanged, performing the transformation of the proposed potential process parameters one by one, observing the changing state of the key quality attributes, and changing the key quality attributes.
  • the potential process parameters are used as test process parameters, called single factor tests.
  • the first testing process is as follows: performing the proposed potential process parameters In the Plackett-Burman test, the process parameters are screened according to the screening rules.
  • the screening rule is that the significant coefficient obtained by the Plackett-Burman test is less than or equal to
  • the proposed parameters of 0.05 are the process parameters obtained by the screening.
  • a method for screening potential process parameters to be verified using orthogonal testing includes the following processes:
  • the inter-assay test data is test data between different groups (for different process parameters), and the test data in the group is the test data of the same group (for the same process parameter).
  • the process of analysis of variance is as follows: according to the orthogonal test of the design, the degree of freedom between groups and the degree of freedom within the group are determined, and the sum of squared deviations and intra-group dispersions are calculated according to the inter-group test data and the test data in the group. Sum of squares; then, according to the sum of squared deviations between groups and the degrees of freedom between groups, the mean square between groups is calculated. According to the squared sum of dispersions within the group and the degrees of freedom within the group, the mean square in the group is calculated; according to the mean square between groups The mean square within the group, the squared sum of squared deviations is obtained ( F value).
  • the lookup table can determine the significant coefficient P value corresponding to the F value match.
  • FIG. 3 the method for screening potential process parameters to be verified is shown in FIG. 3, and includes the following processes:
  • a process parameter corresponding to a significant coefficient smaller than a significant coefficient threshold is used as a potential process parameter to be verified.
  • the CQA in the production process and the potential process parameters to be verified are found out.
  • the preliminary rules provide a good basis for the following design space optimization updates.
  • the above two second test methods are only listed as preferred embodiments, and are not specifically limited by the claims. In fact, there are other classical analysis methods, which can also be applied to the technical solutions of the present invention. List one by one.
  • a method for verifying potential process parameters to be verified includes the following processes:
  • the potential process parameter range is in the release parameter (ie CPP) In the range other than the formula, and the potential process parameters to be verified are selected from the range of the potential process parameters, in this embodiment, the process of verifying the potential process parameters is the process of design space optimization. , that is, using the potential process parameters to be verified and the release parameters to form a new CPP, looking for new design spaces.
  • stepwise regression includes:
  • the determination coefficient is lower than the deterministic threshold, the confidence of the selection is expanded until the determination coefficient is greater than the deterministic threshold.
  • the stepwise regression method is used to fit the key process parameters and key quality attributes of the standardized operation to obtain a relational model.
  • the methods that can be tried include SVM, MLR, and BP. Wait.
  • Minitab for stepwise regression specifically selecting 'Statistics' ® 'Regression' in minitab ® 'Fitting the model', select the response variable and the independent variable.
  • Minitab for stepwise regression, specifically selecting 'Statistics' ® 'Regression' in minitab ® 'Fitting the model', select the response variable and the independent variable.
  • the 'Step-by' option set the selection a and delete with a and stepwise type. After the regression is completed, get the mathematical model, ie the regression equation.
  • the updated design space it is also possible to verify the updated design space to see if the potential process parameters of the mining are for PKS.
  • the system's production capacity and performance have a beneficial impact.
  • the verification method can calculate the system process capability before and after optimization. If the process capability is improved, the potential process parameters of the mining are successful. If the process capability decreases, the design space is restored to the pre-optimization design space.
  • a potential process parameter mining device is provided, see Fig. 6, the device comprising the following modules:
  • the requesting module 610 is configured to receive a potential process parameter mining request, where the request includes the section condition information corresponding to the design space;
  • Drafting module 620 And acquiring, according to the section condition information, a key quality attribute corresponding to the work section and formulating a set of potential process parameters;
  • a first test module 630 configured to perform a first test on the proposed potential process parameters to obtain a plurality of process parameters
  • a second test module 640 configured to perform a second test on the process parameter to obtain a potential process parameter to be verified
  • the verification module 650 is configured to verify the potential process parameters to be verified, and obtain potential process parameters.
  • the second test module 640 includes:
  • Test design unit 641 for designing orthogonal tests to obtain inter-group test data and intra-group test data
  • the variance analysis unit 642 is configured to perform variance analysis on the test data between the groups and the test data in the group to obtain a squared deviation ratio of the mean square deviation;
  • a significant coefficient unit 643, configured to match the corresponding significant coefficient according to the squared deviation ratio of the mean square deviation
  • the screening unit 644 is configured to filter, according to the significant coefficient, a potential process parameter to be verified.
  • the verification module 650 includes:
  • Key Process Parameter Library Update Unit 651 including adding a potential process parameter to be verified to the key process parameter library of the design space, and updating the key process parameter set;
  • Model unit 652 is configured to establish a relationship model between key quality attributes and updated key process parameters
  • Design Space Update Unit 653 And updating the design space according to the relationship model, the design space being a specific range of intervals corresponding to the key quality attribute.
  • the potential process parameter mining device provided by the embodiment is only illustrated by the division of each functional module in the process of performing potential process parameter mining. In actual applications, the function distribution may be completed by different functional modules as needed.
  • the internal structure of the potential process parameter mining device is divided into different functional modules to perform all or part of the functions described above.
  • the embodiment of the potential process parameter mining apparatus provided in this embodiment is the same as the method of the potential process parameter mining provided by the foregoing embodiment. For details, refer to the method embodiment, and details are not described herein again.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Manufacturing & Machinery (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了一种潜在过程参数挖掘方法及装置,所述挖掘方法包括:接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;对拟定的潜在过程参数进行第一测试,得到多个过程参数;对所述过程参数进行第二测试,得到待验证潜在过程参数;对待验证潜在过程参数进行验证,得到潜在过程参数。本发明通过对潜在过程参数进行测试,筛选出与关键质量属性相关的待验证潜在过程参数,并利用待验证潜在过程参数更新优化设计空间,为参数放行提供一种有效、可靠的解决方案。

Description

潜在过程参数挖掘方法及装置
技术领域
本发明涉及过程知识系统领域,特别涉及一种潜在过程参数挖掘方法及装置。
背景技术
在过程知识系统( Process Knowledge System ,简称 PKS )中,参数设计空间的设定是对 PKS 系统参数放行的一种设定。
在现有技术中,参数设计的结果往往是单点参数,以金银花提取温度参数为例,首先收集多个批次的金银花提取工段温度参数数据,其次对每个批次进行数据处理,提取出反应温度变化的关键点,再次,对每个关键点进行处理,多个批次的经过处理的关键点正态分布拟合,以某个拟合度作为最终的参数设计点。
而单点的设计造成 PKS 参数放行的范围狭隘,即使过程能力较低也无法作出设计空间的优化,非常不利于 PKS 在智能制造中发挥作用。目前尚没有一种针对于 PKS 参数设计空间的潜在过程参数进行挖掘的方法。
在设计空间的寻找过程往往不是一步到位的,在大量数据积累后若发现空间方程的解释能力不足,就得考虑是否有潜在过程参数尚未被发掘。
发明内容
为了解决现有技术的问题,本发明提供了一种潜在过程参数挖掘方法及装置,对潜在过程参数进行测试,筛选出与关键质量属性相关的待验证潜在过程参数,并利用待验证潜在过程参数更新优化设计空间,为参数放行提供一种有效、可靠的解决方案。所述技术方案如下:
一方面,本发明提供了一种潜在过程参数挖掘方法,包括:
接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;
根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;
对拟定的潜在过程参数进行第一测试,得到多个过程参数;
对所述过程参数进行第二测试,得到待验证潜在过程参数;
对待验证潜在过程参数进行验证,得到潜在过程参数。
进一步地,所述对所述过程参数进行第二测试,得到待验证潜在过程参数包括:
设计正交试验,得到组间试验数据和组内试验数据;
对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值;
根据所述均方离差平方和比值,匹配相应的显著系数;
将小于显著系数阈值的显著系数所对应的过程参数作为待验证潜在过程参数。
可选地,所述对所述过程参数进行第二测试,得到待验证潜在过程参数包括:
对过程参数进行相对标准偏差分析,得到符合偏差阈值的过程参数;
对所述符合偏差阈值的过程参数进行相关性分析,得到过程参数与关键质量属性之间的相关系数;
根据所述相关系数,获取所述过程参数与关键质量属性之间的显著系数;
将小于显著系数阈值的显著系数所对应的过程参数作为待验证潜在过程参数。
进一步地,所述对拟定的潜在过程参数进行第一测试包括:
保持其他参数不变,对拟定的潜在过程参数进行逐一变换,测试关键质量属性,并将使关键质量属性发生变化的潜在过程参数作为测试得到的过程参数。
进一步地,所述对拟定的潜在过程参数进行第一测试包括:
对拟定的潜在过程参数进行 Plackett-Burman 试验,按照筛选规则筛选得到过程参数。
进一步地,所述对待验证潜在过程参数进行验证包括:
将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合;
建立关键质量属性与更新后的关键过程参数之间的关系模型;
根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
进一步地,所述建立关键质量属性与更新后的关键过程参数之间的关系模型包括:
对关键过程参数和关键质量属性进行数据标准化操作;
利用逐步回归方法,对标准化的关键过程参数和关键质量属性进行拟合操作,得到关系模型,所述逐步回归包括:
获取关系模型的决定系数;
比较所述决定系数与决定度阈值的大小;
若所述决定系数低于所述决定度阈值,则扩大入选的置信度,直至所述决定系数大于决定度阈值。
进一步地,所述潜在过程参数挖掘请求还包括设计空间的放行参数;
所述根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合包括:
根据工段条件信息,确定对应的关键质量属性;
查询所述设计空间的放行参数;
在所述放行参数以外的范围内拟定与所述关键质量属性相关的潜在过程参数,组成潜在过程参数集合。
另一方面,本发明提供了一种潜在过程参数挖掘装置,所述装置包括以下模块:
请求模块,用于接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;
拟定模块,用于根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;
第一测试模块,用于对拟定的潜在过程参数进行第一测试,得到多个过程参数;
第二测试模块,用于对所述过程参数进行第二测试,得到待验证潜在过程参数;
验证模块,用于对待验证潜在过程参数进行验证,得到潜在过程参数。
进一步地,所述第二测试模块包括:
测试设计单元,用于设计正交试验,得到组间试验数据和组内试验数据;
方差分析单元,用于对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值;
显著系数单元,用于根据所述均方离差平方和比值,匹配相应的显著系数;
筛选单元,用于根据所述显著系数,筛选得到待验证潜在过程参数。
进一步地,所述验证模块包括:
关键过程参数库更新单元,包括将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合;
模型单元,用于建立关键质量属性与更新后的关键过程参数之间的关系模型;
设计空间更新单元,包括根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
本发明提供的技术方案带来的有益效果如下:
  1. 1) 对潜在过程参数进行单因素测试,得到多个过程参数,为潜在过程参数挖掘提供了基础;
  1. 2) 对潜在过程参数进行正交测试,通过方差分析,筛选出与关键质量属性相关的待验证潜在过程参数,为设计空间的重新构造提供可靠的参数素材;
  1. 3) 利用待验证潜在过程参数更新优化设计空间,具体通过逐步回归方法建立关键过程参数与关键质量属性之间的关系模型,避免多重共线性的影响,模型可靠性高;
  1. 4) 依照新设计空间进行参数放行,以验证挖掘的潜在过程参数的影响力。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图 1 是本发明实施例提供的潜在过程参数挖掘方法流程图;
图 2 是本发明实施例提供的待验证潜在过程参数的筛选方法流程图;
图 3 是本发明实施例提供的筛选待验证潜在过程参数的 方法 流程图;
图 4 是本发明实施例提供的待验证潜在过程参数进行验证方法流程图;
图 5 是本发明实施例提供的建立关系模型的方法流程图;
图 6 是本发明实施例提供的潜在过程参数挖掘装置的模块框图;
图 7 是本发明实施例提供的药液温度与指标成分 A 转移率的关系图;
图 8 是本发明实施例提供的对过程参数进行第二测试的方法流程图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分的实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都应当属于本发明保护的范围。
需要说明的是,本发明的说明书和权利要求书及上述附图中的术语'第一'、'第二'等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语'包括'和'具有'以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、装置、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例 1
在设计空间寻找的过程中,在大量数据积累后发现方程的解释能力不足,比如:决定系数 R2 小于 0.7 或者发现过程能力虽然有提高,但是仍没有达到预期的目标,就得考虑是否有潜在过程参数尚未被发掘 。
在本发明的一个实施例中,提供了一种潜在过程参数挖掘方法,用于挖掘潜在过程参数,参见图 1 ,所述方法包括以下流程:
S1 、接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息。
具体地,除了工段条件信息,所述潜在过程参数挖掘请求还包括设计空间的放行参数。比如,在 植物药注射液的醇沉工段,指标成分的转移率、杂质的去除率是 关键质量属性( Critical Quality Attributes , CQA ) ,再加上 指标成分 A 的含量最高,因此可以选择 指标成分 A 作为指标成分。所述 设计空间的放行参数即为在设计空间寻找过程中,找到的与 CQA 紧密联系的关键过程参数( Critical Process Parameter , CPP )。
S2 、根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合。
首先,根据工段条件信息,确定对应的关键质量属性( CQA );查询所述设计空间的放行参数,即 CPP ;在所述放行参数以外的范围内拟定与所述关键质量属性相关的潜在过程参数,组成潜在过程参数集合,此步骤的原则是在分析判断的前提下,尽可能地选择多种潜在过程参数。
潜在过程参数的挖掘可以从两个方面考虑,一个方面是比较小试研究和工厂生产的 SOP ,挖掘实际生产未考虑到的工艺参数,如生产环境温度。另一方面,可以考察前中间体或者生产原料的质量属性,如蛋白和多糖含量。可以通过以下三种方式来挖掘实际生产中未考虑到的工艺参数:第一、根据积累的生产经验判断,如质管人员发现冬夏季节产品质量差异较大,则可以把环境温度列为潜在过程参数;第二、以过程能力不足的质量指标为对象,查阅相关工艺研究,多方面筛选比较文献设计的工艺参数。如发现某关键质量属性易受溶液 pH 影响而实际生产未考虑溶液 pH ,则可以把溶液 pH 列为潜在过程参数;第三、经验判断和查阅文献仍未能找出潜在过程参数,则可以邀请领域专家集中讨论,拟定潜在过程参数,如醇沉工段,质管人员发现醇沉时药液温度对产品质量影响较大而生产中尚未控制,因此把醇沉时药液温度列为潜在过程参数。
S3 、对拟定的潜在过程参数进行第一测试,得到多个过程参数。
第一测试是对拟定的潜在过程参数进行初步的筛选,筛选的目的是将一些相关性较小的过程参数从所述潜在过程参数集合中排除,以为下一步测试做基础。
合理设定考察的潜在过程参数集合(可以先采集一定数量生产中潜在过程参数的数据,在此范围上下浮动 50% 设定实验的范围),每种因素设置 5 个或以上水平进行单因素的考察。如生产中药液温度一般在 10~20 ℃之间,单因素考察设置药液温度水平为 5 、 10 、 15 、 20 、 25 ℃,参见以下表 1 ,选择适合的试验重复次数。
表 1
编号 1 2 3 4 5
药液温度水平 ℃ 5 10 15 20 25
药液温度与指标成分 A 转移率的关系如图 7 所示,比如在实际生产中,药液温度一般控制在 10-15 ℃,然而在本实施例中单因素初步分析发现药液温度对指标成分 A 转移率有影响, 20 ℃时提取指标成分 A 转移率最高,则看出以往实际生产中忽略的 20 ℃的药液温度应当作为待考察的潜在过程参数,此处只做示例,指标的选择可根据具体情况分析。
S4 、对所述过程参数进行第二测试,得到待验证潜在过程参数。
第二测试为对第一测试后得到的初步筛选结果进行进一步的筛选,得到相关性较大的极有可能提高空间能力的潜在过程参数。
在本发明的一个实施例中,所述第二测试使用正交设计实验,根据单因素考察的结果,筛选各个因素进行考察的范围,每个因素设置 3 个水平,并对实验设计结果进行方差分析,得到待考察潜在过程参数和最优工艺值。选择单因素考察中影响显著的参数进一步进行正交实验设计,确认考察因素对质量指标的影响。如单因素考察发现前中间体固含、药液温度对质量指标影响较大,对两种因素建立正交设计进一步确认考察因素对质量指标的影响程度,参见以下表 2 :
表 2
因素 p
前中间体固含 % 0.10
药液温度 ℃ 0.03
可以发现前中间体固含对指标成分 A 转移率虽然有影响,但不显著,药液温度对指标成分 A 转移率影响更为显著( p 越小影响越显著),因此最终把药液温度作为待验证的潜在过程参数。
具体地,第二测试的方法流程在实施例 2 中详述。
S5 、对待验证潜在过程参数进行验证,得到潜在过程参数。
根据验证后的潜在过程参数结果,更新安装潜在过程参数的数据采集设备。参考设计空间方法,将确定的潜在过程参数数据加入工段过程参数数据进行设计空间的寻找,具体地,验证方法流程在实施例 3 中详述。
实施例 2
在本发明的一个实施例中,所述第一测试过程如下:保持其他参数不变,对拟定的潜在过程参数进行逐一变换,观察关键质量属性的变化状态,并将使关键质量属性发生变化的潜在过程参数作为测试得到的过程参数,称为单因素测试。
在本发明的另一个实施例中,所述第一测试过程如下:对拟定的潜在过程参数进行 Plackett-Burman 试验,按照筛选规则筛选得到过程参数,在本实施例中,筛选规则为 Plackett-Burman 试验得到的显著系数小于等于 0.05 的拟定参数为筛选得到的过程参数。
以上两种第一测试方法只是作为优选实施例列出,而不作为权利要求的具体限定,实际上,还有其他经典的筛选方法,同样可以应用到本发明的技术方案中去,在此不一一列出。
经过以上任意一种第一测试进行初步筛选后,可以进行以下第二测试:
在本发明的一个实施例中,提供了一种利用正交测试进行筛选待验证潜在过程参数的方法,参见图 2 ,所述方法包括以下流程:
S41 、设计正交试验,得到组间试验数据和组内试验数据。
具体地,所述组间试验数据即为不同组之间(针对不同过程参数)的试验数据,所述组内试验数据即为同一组(针对同一过程参数)的试验数据。
S42 、对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值。
所述方差分析的过程如下:根据设计的正交试验,确定组间自由度和组内自由度,并根据组间试验数据和组内试验数据,计算组间离差平方和和组内离差平方和;然后根据组间离差平方和与组间自由度,计算得到组间均方,根据组内离差平方和与组内自由度,计算得到组内均方;根据组间均方和组内均方,得到均方离差平方和比值( F 值)。
S43 、根据所述均方离差平方和比值,匹配相应的显著系数。
查表可以确定与所述 F 值匹配对应的显著系数 P 值。
S44 、根据所述显著系数,筛选得到待验证潜在过程参数。
具体地,所述筛选待验证潜在过程参数的方法参见图 3 ,包括以下流程:
S441 、确定显著系数阈值,得到小于所述显著系数阈值的目标显著系数;
S442 、根据所述目标显著系数,获取对应的过程参数,作为待验证潜在过程参数。即 选择 显著系数 P 值小于 0.05 (或根据实际情况进行分析选择)的参数作为 待验证潜在过程参数 。
在另一个实施例中,提供了 另一种对过程参数进行第二测试的方法,参见图 8 ,包括以下流程:
S401 、对过程参数进行相对标准偏差分析,得到符合偏差阈值的过程参数;
S402 、对所述符合偏差阈值的过程参数进行相关性分析,得到过程参数与关键质量属性之间的相关系数;
S403 、根据所述相关系数,获取所述过程参数与关键质量属性之间的显著系数;
S404 、将小于显著系数阈值的显著系数所对应的过程参数作为待验证潜在过程参数。
通过本实施例中筛选待验证潜在过程参数的方法, 找出生产过程中 CQA 与 待验证潜在过程参数的 初步规律,为下面的设计空间优化更新提供良好的基础。 以上两种第二测试方法只是作为优选实施例列出,而不作为权利要求的具体限定,实际上,还有其他经典的分析方法,同样可以应用到本发明的技术方案中去,在此不一一列出。
实施例 3
在本发明的一个实施例中,提供了一种对待验证潜在过程参数进行验证的方法,参见图 4 ,所述方法包括以下流程:
S51 、将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合。
正如实施例 1 所述的,潜在过程参数范围是在所述放行参数(即 CPP )以外的范围内拟定的,而待验证潜在过程参数又是从所述潜在过程参数范围中筛选出来的,在本实施例中,对待验证潜在过程参数进行验证的过程即为设计空间优化的过程,即利用待验证潜在过程参数与放行参数组成新的 CPP ,寻找新的设计空间。
S52 、建立关键质量属性与更新后的关键过程参数之间的关系模型。
具体地,建立模型的方法参见图 5 ,包括以下流程:
S521 、对关键过程参数和关键质量属性进行数据标准化操作;
S522 、利用逐步回归方法,对标准化的关键过程参数和关键质量属性进行拟合操作,得到关系模型。
其中,所述逐步回归包括:
获取关系模型的决定系数;
比较所述决定系数与决定度阈值的大小;
若所述决定系数低于所述决定度阈值,则扩大入选的置信度,直至所述决定系数大于决定度阈值。
具体地,利用逐步回归方法,对进行标准化操作的关键过程参数和关键质量属性进行拟合操作,得到关系模型。 回归的方法也有很多,包括线性和非线性的。此处使用的是逐步回归的方法(避免多重共线性的影响),可以尝试的方法还包括 SVM 、 MLR 、 BP 等。在本发明实施例中,使用 Minitab 进行逐步回归,具体为在 minitab 中选中'统计' ® '回归' ® '拟合模型',选定响应变量和自变量,在'逐步'选项中,设置入选用 a 和删除用 a 和逐步类型,回归结束后,得到数学模型,即回归方程。
S53 、根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
具体地,还可以对更新后的设计空间进行验证,看挖掘的潜在过程参数是否对 PKS 系统的生产能力和性能产生有益的影响。验证方式可以通过计算优化前后的系统过程能力,若过程能力有所提高,则说明挖掘的潜在过程参数成功,若过程能力反而下降,则恢复到优化前的设计空间。
实施例 4
在本发明的一个实施例中,提供了一种潜在过程参数挖掘装置,参见图 6 ,所述装置包括以下模块:
请求模块 610 ,用于接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;
拟定模块 620 ,用于根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;
第一测试模块 630 ,用于对拟定的潜在过程参数进行第一测试,得到多个过程参数;
第二测试模块 640 ,用于对所述过程参数进行第二测试,得到待验证潜在过程参数;
验证模块 650 ,用于对待验证潜在过程参数进行验证,得到潜在过程参数。
在一个优选的实施例中,所述第二测试模块 640 包括:
测试设计单元 641 ,用于设计正交试验,得到组间试验数据和组内试验数据;
方差分析单元 642 ,用于对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值;
显著系数单元 643 ,用于根据所述均方离差平方和比值,匹配相应的显著系数;
筛选单元 644 ,用于根据所述显著系数,筛选得到待验证潜在过程参数。
在一个优选的实施例中,所述验证模块 650 包括:
关键过程参数库更新单元 651 ,包括将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合;
模型单元 652 ,用于建立关键质量属性与更新后的关键过程参数之间的关系模型;
设计空间更新单元 653 ,包括根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
需要说明的是:上 述实施例提供的潜在过程参数挖掘装置在进行潜在过程参数挖掘时,仅以上述各功能模块的划分进行举例说明,实际应用中,可以根据需要而将上述功能分配由不同的功能模块完成,即将潜在过程参数挖掘装置的内部结构划分成不同的功能模块,以完成以上描述的全部或者部分功能。另外,本实施例提供的潜在过程参数挖掘装置实施例与上述实施例提供的潜在过程参数挖掘方法属于同一构思,其具体实现过程详见方法实施例,这里不再赘述。
以上所述仅为本发明的较佳实施例,并不用以限制本发明,凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。

Claims (11)

  1. 一种潜在过程参数挖掘方法,其特征在于,包括:
    接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;
    根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;
    对拟定的潜在过程参数进行第一测试,得到多个过程参数;
    对所述过程参数进行第二测试,得到待验证 潜在过程参数;
    对待验证潜在过程参数进行验证,得到潜在过程参数。
  2. 根据权利要求 1 所述的方法,其特征在于,所述对所述过程参数进行第二测试,得到待验证潜在过程参数包括:
    设计正交试验,得到组间试验数据和组内试验数据;
    对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值;
    根据所述均方离差平方和比值,匹配相应的显著系数;
    将小于显著系数阈值的显著系数所对应的过程参数作为待验证潜在过程参数。
  3. 根据权利要求 1 所述的方法,其特征在于,所述对所述过程参数进行第二测试,得到待验证潜在过程参数包括:
    对过程参数进行相对标准偏差分析,得到符合偏差阈值的过程参数;
    对所述符合偏差阈值的过程参数进行相关性分析,得到过程参数与关键质量属性之间的相关系数;
    根据所述相关系数,获取所述过程参数与关键质量属性之间的显著系数;
    将小于显著系数阈值的显著系数所对应的过程参数作为待验证潜在过程参数。
  4. 根据权利要求 1 所述的方法,其特征在于,所述对拟定的潜在过程参数进行第一测试包括:
    保持其他参数不变,对拟定的潜在过程参数进行逐一变换,测试关键质量属性,并将使关键质量属性发生变化的潜在过程参数作为测试得到的过程参数。
  5. 根据权利要求 1 所述的方法,其特征在于,所述对拟定的潜在过程参数进行第一测试包括:
    对拟定的潜在过程参数进行 Plackett-Burman 试验,按照筛选规则筛选得到过程参数。
  6. 根据权利要求 1 所述的方法,其特征在于,所述对待验证潜在过程参数进行验证包括:
    将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合;
    建立关键质量属性与更新后的关键过程参数之间的关系模型;
    根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
  7. 根据权利要求 6 所述的方法,其特征在于,所述建立关键质量属性与更新后的关键过程参数之间的关系模型包括:
    对关键过程参数和关键质量属性进行数据标准化操作;
    利用逐步回归方法,对标准化的关键过程参数和关键质量属性进行拟合操作,得到关系模型,所述逐步回归包括:
    获取关系模型的决定系数;
    比较所述决定系数与决定度阈值的大小;
    若所述决定系数低于所述决定度阈值,则扩大入选的置信度,直至所述决定系数大于决定度阈值。
  8. 根据权利要求 1 所述的方法,其特征在于,所述潜在过程参数挖掘请求还包括设计空间的放行参数;
    所述根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合包括:
    根据工段条件信息,确定对应的关键质量属性;
    查询所述设计空间的放行参数;
    在所述放行参数以外的范围内拟定与所述关键质量属性相关的潜在过程参数,组成潜在过程参数集合。
  9. 一种潜在过程参数挖掘装置,其特征在于,包括以下模块:
    请求模块,用于接收潜在过程参数挖掘请求,所述请求包括设计空间对应的工段条件信息;
    拟定模块,用于根据所述工段条件信息,获取与工段对应的关键质量属性及拟定潜在过程参数集合;
    第一测试模块 ,用于对拟定的潜在过程参数进行第一测试,得到多个过程参数;
    第二测试模块,用于对所述过程参数进行第二测试,得到待验证潜在过程参数;
    验证模块,用于对待验证潜在过程参数进行验证,得到潜在过程参数。
  10. 根据权利要求 9 所述的装置,其特征在于,所述第二测试模块包括:
    测试设计单元,用于设计正交试验,得到组间试验数据和组内试验数据;
    方差分析单元,用于对组间试验数据和组内试验数据进行方差分析,得到均方离差平方和比值;
    显著系数单元,用于根据所述均方离差平方和比值,匹配相应的显著系数;
    筛选单元,用于根据所述显著系数,筛选得到待验证潜在过程参数。
  11. 根据权利要求 9 所述的装置,其特征在于,所述验证模块包括:
    关键过程参数库更新单元,包括将待验证潜在过程参数加入设计空间的关键过程参数库,更新关键过程参数集合;
    模型单元,用于建立关键质量属性与更新后的关键过程参数之间的关系模型;
    设计空间更新单元,包括根据所述关系模型,更新设计空间,所述设计空间为对应于所述关键质量属性的特定区间范围。
PCT/CN2018/073667 2017-08-31 2018-01-22 潜在过程参数挖掘方法及装置 WO2019041734A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710770966.7 2017-08-31
CN201710770966.7A CN107563515B (zh) 2017-08-31 2017-08-31 潜在过程参数挖掘方法及装置

Publications (1)

Publication Number Publication Date
WO2019041734A1 true WO2019041734A1 (zh) 2019-03-07

Family

ID=60977901

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/073667 WO2019041734A1 (zh) 2017-08-31 2018-01-22 潜在过程参数挖掘方法及装置

Country Status (2)

Country Link
CN (1) CN107563515B (zh)
WO (1) WO2019041734A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114663250A (zh) * 2022-04-02 2022-06-24 成都秦川物联网科技股份有限公司 双独立平台式工业物联网及其控制方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107563515B (zh) * 2017-08-31 2018-11-06 江苏康缘药业股份有限公司 潜在过程参数挖掘方法及装置
CN110675014B (zh) * 2019-07-24 2023-04-07 中国电子科技集团公司电子科学研究院 国产电子器件替代验证项目确定方法及设备
CN113053455A (zh) * 2021-03-05 2021-06-29 北京中医药大学 一种潜在味效关联关键质量属性辨识方法在小儿消积止咳口服液中的应用

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103257923A (zh) * 2013-04-16 2013-08-21 中国科学院计算技术研究所 数据中心数据分析类基准测试程序的应用选取方法及系统
US20170206468A1 (en) * 2016-01-20 2017-07-20 Robert Bosch Gmbh Value addition dependent data mining techniques for assembly lines
CN107563515A (zh) * 2017-08-31 2018-01-09 江苏康缘药业股份有限公司 潜在过程参数挖掘方法及装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0101043D0 (en) * 2001-01-15 2001-02-28 Univ Aberdeen Input parameter selection process
CN103235859B (zh) * 2013-05-04 2015-08-05 四川虹欧显示器件有限公司 等离子显示屏制造过程中最佳工艺参数组合的确定方法
DE102014106916A1 (de) * 2013-05-28 2014-12-04 Endress + Hauser Conducta Gesellschaft für Mess- und Regeltechnik mbH + Co. KG Vorrichtung zur automatisierten Bestimmung von mindestens zwei unterschiedlichen Prozessparametern
CN104898430B (zh) * 2015-06-03 2017-07-18 北京首钢自动化信息技术有限公司 基于数据挖掘的单机架冷轧轧制力模型参数优化方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103257923A (zh) * 2013-04-16 2013-08-21 中国科学院计算技术研究所 数据中心数据分析类基准测试程序的应用选取方法及系统
US20170206468A1 (en) * 2016-01-20 2017-07-20 Robert Bosch Gmbh Value addition dependent data mining techniques for assembly lines
CN107563515A (zh) * 2017-08-31 2018-01-09 江苏康缘药业股份有限公司 潜在过程参数挖掘方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WAN LEI ET AL.: "Study on Manufacturing Process Performance Index of Extraction and Concentration Process of Lonicerae Japonicae Flos of ........", CHINESE TRADITIONAL AND HERBAL DRUGS, vol. 48, no. 14, 31 July 2017 (2017-07-31), ISSN: 0253-2670 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114663250A (zh) * 2022-04-02 2022-06-24 成都秦川物联网科技股份有限公司 双独立平台式工业物联网及其控制方法
CN114663250B (zh) * 2022-04-02 2022-08-16 成都秦川物联网科技股份有限公司 双独立平台式工业物联网系统及其控制方法
US11625028B1 (en) 2022-04-02 2023-04-11 Chengdu Qinchuan Iot Technology Co., Ltd. Industrial internet of things with dual independent platform and control methods thereof
US11874650B2 (en) 2022-04-02 2024-01-16 Chengdu Qinchuan Iot Technology Co., Ltd. Industrial internet of things system for automatic control of production line manufacturing parameters and control methods thereof

Also Published As

Publication number Publication date
CN107563515B (zh) 2018-11-06
CN107563515A (zh) 2018-01-09

Similar Documents

Publication Publication Date Title
WO2019041734A1 (zh) 潜在过程参数挖掘方法及装置
WO2019041406A1 (zh) 不雅图片识别方法、终端、设备及计算机可读存储介质
WO2017107388A1 (zh) Hdmi版本切换方法及显示设备
WO2019019493A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2019114269A1 (zh) 一种节目续播方法、电视设备及计算机可读存储介质
WO2019024336A1 (zh) 数据查询方法、装置及计算机可读存储介质
WO2017201899A1 (zh) 连接蓝牙设备的方法及装置
WO2019041851A1 (zh) 家电售后咨询方法、电子设备和计算机可读存储介质
WO2018233367A1 (zh) 立案方法、装置、终端和计算机可读存储介质
WO2018227869A1 (zh) 显示屏画面调整方法、显示终端及可读存储介质
WO2019237505A1 (zh) 基于区域调光的画质优化方法、装置、设备及存储介质
WO2018233221A1 (zh) 多窗口声音输出方法、电视机以及计算机可读存储介质
WO2018149191A1 (zh) 保单核保的方法、装置、设备及计算机可读存储介质
WO2018094812A1 (zh) 调节液晶显示装置屏幕背光亮度的方法及装置
WO2019104874A1 (zh) 理财产品购买方法、装置、设备及可读存储介质
WO2018153133A1 (zh) 一种家用电器检测方法及系统
WO2016107249A1 (zh) 卫星电视搜台的方法和装置
WO2019071771A1 (zh) 无线信号指纹信息的校准方法、系统、服务器和介质
WO2018090461A1 (zh) 多声道无线音箱之间数据同步的方法及系统
WO2017185480A1 (zh) 多屏互动连接方法、装置及系统
WO2018032679A1 (zh) 电视定时开关机的设置方法和装置
WO2018227768A1 (zh) 管理ivr进线的方法、装置、设备及计算机可读存储介质
WO2017152527A1 (zh) 智能电视从设备应用的控制方法及智能电视
WO2018018680A1 (zh) 应用提示信息显示方法及装置
WO2016101305A1 (zh) 视频文件处理方法及显示装置

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: 18849624

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: 18849624

Country of ref document: EP

Kind code of ref document: A1