CN115809795A - Digitalized production team bearing capacity evaluation method and device - Google Patents
Digitalized production team bearing capacity evaluation method and device Download PDFInfo
- Publication number
- CN115809795A CN115809795A CN202310054043.7A CN202310054043A CN115809795A CN 115809795 A CN115809795 A CN 115809795A CN 202310054043 A CN202310054043 A CN 202310054043A CN 115809795 A CN115809795 A CN 115809795A
- Authority
- CN
- China
- Prior art keywords
- production
- data
- vacation
- target
- team
- 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.)
- Granted
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 653
- 238000011156 evaluation Methods 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 88
- 238000004140 cleaning Methods 0.000 claims abstract description 16
- 239000013598 vector Substances 0.000 claims description 39
- 238000012216 screening Methods 0.000 claims description 31
- 238000000034 method Methods 0.000 claims description 25
- 238000003491 array Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000004931 aggregating effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- 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 relates to a production evaluation technology, and discloses a digital production team bearing capacity evaluation method and a digital production team bearing capacity evaluation device, which comprise the following steps: performing data cleaning on historical production data to obtain standard production data, and splitting the standard production data into a plurality of right-level production data; extracting a vacation data sequence from the right-level production data, generating a vacation analysis model corresponding to a target right-level type by using the vacation data sequence, extracting tool production data from the standard production data, and extracting a target production parameter set from the tool production data; generating team production models by using the target production parameter set, and collecting all team production models into a team model set; and acquiring production information of the team to be analyzed, and analyzing the bearing capacity of the team to be analyzed by utilizing the team model and the vacation model. The invention can improve the accuracy of the bearing capacity evaluation of the production team.
Description
Technical Field
The invention relates to the technical field of production evaluation, in particular to a digitalized production team bearing capacity evaluation method and device.
Background
With the aggravation of the modernization process, more and more mechanisms and organizations begin to expand production, which greatly increases the number of production activities, a production team is a main production unit in the production activities, one production team comprises a plurality of production employees with different proficiency, and in order to improve the production efficiency, the bearing capacity of the production team needs to be evaluated;
most of the existing methods for evaluating the bearing capacity of the production teams are large data-based evaluation methods, for example, a production model is built for each production team by querying historical production data of each production team, and then the bearing capacity of the production team for a production task is analyzed.
Disclosure of Invention
The invention provides a digitalized production team bearing capacity evaluation method and device, and mainly aims to solve the problem of low accuracy in production team bearing capacity evaluation.
In order to achieve the above object, the present invention provides a digitalized-based method for evaluating the bearing capacity of a production team, comprising:
acquiring historical production data of a target mechanism, performing data cleaning on the historical production data to obtain standard production data, and dividing the standard production data into a plurality of right-level production data according to the right-level types of production personnel;
selecting the right-level types one by one as target right-level types, extracting vacation data sequences corresponding to the target right-level types from the right-level production data, performing iterative update on a preset primary vacation model by using the vacation data sequences to obtain a vacation analysis model corresponding to the target right-level types, and assembling all the vacation analysis models into a vacation model set, wherein the vacation data sequences are used for performing iterative update on the preset primary vacation model to obtain the vacation analysis model corresponding to the target right-level types, and the method comprises the following steps: extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model; generating an analysis vacation data sequence according to the long and short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence; calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is meant to refer to the value of the deviation,
means the total number of data of the analysis vacation data sequence, and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as the first
The number of the data is one,
is the first in the analysis vacation data sequence
The number of the data is one,
is the first in the target vacation data sequence
The number of the data is one,
is a preset reference coefficient of the reference signal,
is a preset balance coefficient; iteratively updating the model parameters of the initial vacation model according to the deviation values to obtain a vacation analysis model corresponding to the target authority class;
selecting production tools one by one as target production tools, extracting tool production data corresponding to the target production tools from the standard production data, and splitting the tool production data into tool period sequences according to a production period;
generating a target production parameter set according to the tool period sequence, establishing a primary team production model according to the target production parameter set, performing iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and collecting all team production models into a team model set;
the method comprises the steps of obtaining production information of a team to be analyzed, extracting configuration information and expected production duration from the production information, updating the expected production duration to standard production duration by using a vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production duration and the configuration information.
Optionally, the performing data cleaning on the historical production data to obtain standard production data includes:
screening out the scrambled data and the offside data from the historical production data to obtain screened production data;
vectorizing the screening production data to obtain a screening production vector set, and adding a position vector to each screening production vector in the screening production vector set to obtain a position production vector set;
performing feature clustering on the position production vector set to obtain a plurality of production vector classes, and gathering the clustering centers of the production vector classes into a production center vector set;
mapping the production center vector set to the screening production data to obtain a clustering center data set;
and filling each null value data in the screened production data according to the clustering center data set to obtain standard production data.
Optionally, the filling, according to the cluster center data set, each null value data in the screened production data to obtain standard production data includes:
selecting null value data in the screening production data one by one as target null value data;
calculating Euclidean distances between the target null data and each clustering center data in the clustering center data set;
selecting clustering center data with the minimum Euclidean distance as target clustering data;
and filling the target null value data by using the target clustering data until the target null value data is the last null value data in the screening production data, and taking the filled screening production data as standard production data.
Optionally, the extracting, from the rights level production data, a vacation data sequence corresponding to the target rights level category includes:
arranging the right-level production data according to a time sequence to obtain time sequence production data;
extracting a production data sequence from the time sequence production data by using a preset time domain window;
selecting the production data in the production data sequence one by one as target production data, and extracting the primary vacation data of each producer from the target production data;
and calculating vacation data corresponding to the target production data according to all the primary vacation data, and arranging all the vacation data into a vacation data sequence.
Optionally, the extracting, by using a preset initial vacation model, the length-time sequence feature and the self-attention time sequence feature of the vacation data sequence includes:
screening a memory characteristic sequence from the vacation data sequence by utilizing a forgetting gate in a long and short memory layer of a preset initial vacation model;
performing characteristic updating on the memory characteristic sequence and the vacation data sequence by using a characteristic state gate in the long and short memory layers to obtain an updated state characteristic;
performing feature fusion on the updating state feature and the memory feature sequence by using an output gate in the long and short memory layer to obtain long and short time sequence features;
extracting self-attention time sequence features from the vacation data sequence by utilizing a self-attention layer of the initial vacation model.
Optionally, the generating a target production parameter set according to the tool cycle sequence includes:
selecting tool period data in the tool period sequence one by one as target tool period data;
taking production group data in the target tool cycle data as target production group data, extracting yield parameters from the target production group data, and splitting the target production group data into a plurality of personnel arrays according to production personnel;
selecting the personnel arrays one by one as target personnel arrays, extracting right-level parameters and duration parameters from the target personnel arrays, and gathering all the right-level parameters and all the duration parameters of the target production team group data into standard parameter sets;
and the production parameters and the standard parameter groups are assembled into standard production parameter groups of the target production group data, and all the standard production parameter groups are assembled into target production parameter groups.
Optionally, the establishing a primary team production model according to the target production parameter set includes:
counting the total number of types of the right-level parameters in the target production parameter set, and establishing a primary team production model according to the total number of types:
wherein ,
Is the analysis production total amount corresponding to the primary team production model,
is referred to as the first
The right class category is used as a seed,
refers to the total number of the species in question,
is that the target production parameter set is first
In a class of said right class
A set of personal members is provided,
is that the target production parameter set is first
The total number of people arrays seeded by the class of authority,
is referred to as
A production weight for the class of rights is seeded,
is that the target production parameter set is first
In a class of said right class
Authority parameter corresponding to personal member arrayThe number of the first and second groups is,
is that the target production parameter set is first
In a class of said right class
And the time length parameter corresponds to the personal member array.
Optionally, the iteratively updating the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool includes:
selecting standard production parameter groups in the target production parameter set one by one as target standard production parameter groups, taking yield parameters in the target standard production parameter groups as real yield parameters, and taking standard parameter groups in the target standard production parameter groups as target standard parameter groups;
substituting the target standard parameter group into the primary team production model to obtain an analysis production parameter;
and iteratively updating the model parameters of the primary team production model according to the loss values between the analysis production parameters and the real yield parameters until the loss values are smaller than a preset loss threshold value, and taking the updated primary team production model as the team production model corresponding to the target production tool.
Optionally, the updating the expected production duration to a standard production duration using the set of vacation models comprises:
calculating a right-level vacation data sequence corresponding to each right-level type by using the vacation model set;
selecting the right-level vacation data sequences one by one as target vacation data sequences, and generating target working data sequences according to the target vacation data sequences;
and calculating a working coefficient according to the target working data sequence, multiplying the working coefficient by the expected production time to obtain standard right-level production time corresponding to each right-level type, and collecting all the standard right-level production time into standard production time.
In order to solve the above problem, the present invention further provides a digital-based load-bearing capacity evaluation device for a production team, the device comprising:
the data cleaning module is used for acquiring historical production data of a target mechanism, performing data cleaning on the historical production data to obtain standard production data, and dividing the standard production data into a plurality of right-level production data according to the right-level types of producers;
the vacation model module is configured to select the right class types one by one as a target right class type, extract a vacation data sequence corresponding to the target right class type from the right production data, perform iterative update on a preset primary vacation model by using the vacation data sequence to obtain a vacation analysis model corresponding to the target right class type, and assemble all the vacation analysis models into a vacation model set, where the vacation data sequence is used to perform iterative update on the preset primary vacation model to obtain the vacation analysis model corresponding to the target right class type, and includes: extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model; generating an analysis vacation data sequence according to the long-short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence; calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is referred to as the value of the deviation,
means the total number of data of the analysis vacation data sequence and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as
The number of the data is one,
is the first in the analysis vacation data sequence
The number of the data is one,
is the first in the target vacation data sequence
The number of the data is set to be,
is a preset reference coefficient of the reference signal,
is a preset equilibrium coefficient; iteratively updating the model parameters of the initial vacation model according to the deviation values to obtain a vacation analysis model corresponding to the target authority class;
the tool cycle module is used for selecting production tools one by one as target production tools, extracting tool production data corresponding to the target production tools from the standard production data, and splitting the tool production data into tool cycle sequences according to a production cycle;
the team model module is used for generating a target production parameter set according to the tool period sequence, establishing a primary team production model according to the target production parameter set, performing iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and collecting all team production models into a team model set;
and the bearing evaluation module is used for acquiring the production information of the team to be analyzed, extracting configuration information and expected production duration from the production information, updating the expected production duration into standard production duration by using the vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production duration and the configuration information.
The method comprises the steps of obtaining historical production data of a target mechanism, carrying out data cleaning on the historical production data to obtain standard production data, improving the accuracy of the historical production data, improving the accuracy of a subsequent data set, conveniently extracting vacation models of producers of different right types in a subsequent mode by splitting the standard production data into a plurality of right types according to the right types of the producers, extracting vacation data sequences corresponding to the target right types from the right production data, extracting vacation time sequence characteristics of each right type, iteratively updating preset primary vacation models by using the vacation data sequences to obtain vacation analysis models corresponding to the target right types, integrating all the vacation analysis models into a vacation model set, analyzing vacation time sequence characteristics of the producers of each right type, improving the accuracy of group bearing capacity, extracting tool production data corresponding to the target production tools from the standard production data, assembling the tool production data into a vacation model set according to a production cycle, and conveniently extracting target production data according to the production cycle and the subsequent production data;
the class production model corresponding to the target production tool is obtained by utilizing the target production parameter set to iteratively update the primary class production model, the relationship between production personnel configuration and production time and production total amount can be established for each production tool, the accuracy of bearing capacity evaluation is improved, the configuration information and the expected production time length are extracted from the production information by obtaining the production information of the class to be analyzed, the expected production time length is updated to the standard production time length by utilizing the vacation model set, the bearing capacity of the class to be analyzed is analyzed by utilizing the class model set, the standard production time length and the configuration information, the production capacity can be analyzed according to the authority types of all production personnel in the class to be analyzed, the types of the used production tools and the effective production analysis time length, the bearing capacity is analyzed according to the production capacity, and the accuracy of bearing capacity analysis is improved. Therefore, the digital-based method and device for evaluating the bearing capacity of the production team can solve the problem of low accuracy in evaluating the bearing capacity of the production team.
Drawings
Fig. 1 is a schematic flowchart of a digital-based method for evaluating load-bearing capacity of a production team according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of generating standard production data according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of generating vacation data sequences according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a digital-based load-bearing capacity assessment apparatus for a production team according to an embodiment of the present invention;
the implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a digital-based bearing capacity evaluation method for production teams. The execution subject of the digital production team bearing capacity evaluation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the digital production team based load bearing capacity evaluation method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a schematic flow chart of a method for evaluating the carrying capacity of a production team based on digitization according to an embodiment of the present invention is shown. In this embodiment, the method for evaluating the carrying capacity of the production team based on the digitization includes:
s1, obtaining historical production data of a target mechanism, carrying out data cleaning on the historical production data to obtain standard production data, and splitting the standard production data into a plurality of right-level production data according to the right-level types of production personnel.
In the embodiment of the present invention, the target mechanism refers to a mechanism that needs to perform load bearing capacity analysis of production teams, the mechanism may be a factory or a company, and the historical production data refers to data such as personnel configuration, machine configuration, production time period, and production quantity of each production team in past historical time of the target mechanism.
In the embodiment of the present invention, the performing data cleaning on the historical production data to obtain standard production data includes:
screening the scrambled data and offside data from the historical production data to obtain screened production data;
vectorizing the screening production data to obtain a screening production vector set, and adding a position vector to each screening production vector in the screening production vector set to obtain a position production vector set;
performing feature clustering on the position production vector set to obtain a plurality of production vector classes, and gathering the clustering centers of the production vector classes into a production center vector set;
mapping the production center vector set to the screening production data to obtain a clustering center data set;
and filling each null value data in the screened production data according to the clustering center data set to obtain standard production data.
In detail, the scrambling code data refers to data without practical meaning such as @, # and ^ and the offside data refers to data beyond a data value range, such as the production amount is-50; vectorization operation can be carried out on the screened production data by using unique hot code or word2vec algorithm to obtain a screened production vector set.
Specifically, a transform model may be used to add a position vector to each of the screened production vectors in the screened production vector set, so as to obtain a position production vector set; feature clustering can be performed on the position production vector set by using a k nearest neighbor algorithm to obtain a plurality of production vector classes, wherein the clustering center refers to a vector corresponding to a central point of the production vector classes, and the null data refers to data on positions corresponding to jumbled code data and offside data which are screened out from the screened production data.
In detail, referring to fig. 2, the filling each null value data in the screened production data according to the cluster center data set to obtain standard production data includes:
s21, selecting null value data in the screening production data one by one as target null value data;
s22, calculating Euclidean distances between the target null value data and each piece of clustering center data in the clustering center data set;
s23, selecting the clustering center data with the minimum Euclidean distance as target clustering data;
and S24, filling the target null value data by using the target clustering data until the target null value data is the last null value data in the screening production data, and taking the filled screening production data as standard production data.
In detail, the producer refers to a worker in a production team of the target facility, and the authority level refers to a level of the producer, such as a skilled producer, a general producer, a novice producer, and the like.
In detail, the splitting the standard production data into a plurality of right-level production data according to the right-level categories of the production personnel includes: and selecting the right class types of one kind of production personnel one by one as target right class types, and extracting right production data corresponding to the target right class types from the standard production data.
In the embodiment of the invention, the historical production data of the target mechanism is obtained, the historical production data is subjected to data cleaning to obtain the standard production data, the accuracy of the historical production data can be improved, the accuracy of a subsequent data set is improved, and the vacation models of the producers with different authority classes can be conveniently extracted subsequently by splitting the standard production data into the plurality of authority classes according to the authority classes of the producers.
S2, selecting the right class types one by one as target right class types, extracting vacation data sequences corresponding to the target right class types from the right production data, performing iterative updating on a preset primary vacation model by using the vacation data sequences to obtain a vacation analysis model corresponding to the target right class types, and converging all the vacation analysis models into a vacation model set.
In the embodiment of the present invention, the vacation data sequence is a sequence of vacation proportions formed in a time domain, and each vacation data in the vacation data sequence is a vacation proportion of all production staff of the target right class within a fixed time period.
In the embodiment of the present invention, as shown in fig. 3, the extracting a vacation data sequence corresponding to the target authority class type from the authority class production data includes:
s31, arranging the authority level production data according to a time sequence to obtain time sequence production data;
s32, extracting a production data sequence from the time sequence production data by using a preset time domain window;
s33, selecting the production data in the production data sequence one by one as target production data, and extracting the primary vacation data of each production staff from the target production data;
and S34, calculating vacation data corresponding to the target production data according to all the primary vacation data, and arranging all the vacation data into a vacation data sequence.
In detail, the window length of the time domain window may be one day, and the extracting of the production data sequence from the time series production data by using the preset time domain window means that the preset time domain window is used to slide on the time series production data, and the production data corresponding to the time domain window at each moment is arranged into the production data sequence.
Specifically, the preliminary vacation data refers to data of whether each of the production staff is vacated, for example, a value of 1 for the preliminary vacation data indicates that the corresponding production staff in the goal production data has not vacated, and a value of 0 for the preliminary vacation data indicates that the corresponding production staff in the goal production data has vacated.
Specifically, the calculating vacation data corresponding to the target production data according to all the preliminary vacation data means calculating vacation sum of all the preliminary vacation data, and dividing the vacation sum by total number of the preliminary vacation data to obtain the vacation data corresponding to the target production data.
In the embodiment of the present invention, the iteratively updating the preset primary vacation model by using the vacation data sequence to obtain the vacation analysis model corresponding to the target right class type includes:
extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model;
generating an analysis vacation data sequence according to the long and short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence;
calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is meant to refer to the value of the deviation,
means the total number of data of the analysis vacation data sequence and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as the first
The number of the data is set to be,
is the first in the analysis vacation data sequence
The number of the data is set to be,
is the first in the target vacation data sequence
The number of the data is set to be,
is a preset reference coefficient of the reference signal,
is a preset equilibrium coefficient;
and iteratively updating the model parameters of the initial vacation model according to the deviation value to obtain a vacation analysis model corresponding to the target right class type.
In detail, by calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using the vacation deviation algorithm, a difference between the target vacation data sequence and the analysis vacation data sequence can be analyzed according to an average of the target vacation data sequence and an average of the analysis vacation data sequence, and a characterization range of the deviation value is improved.
In detail, the initial vacation model includes a long-short memory layer and a self-attention layer, and the forgetting gate may be a forget gate of the long-short memory network, the feature state gate may be a cell state of the long-short memory network, and the output gate may be an output gate of the long-short memory network; the autonomous layer may be an encoder of a transform model.
In detail, the extracting, by using a preset initial vacation model, the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence includes:
screening a memory characteristic sequence from the vacation data sequence by utilizing a forgetting gate in a long and short memory layer of a preset initial vacation model;
performing characteristic updating on the memory characteristic sequence and the vacation data sequence by using a characteristic state gate in the long and short memory layers to obtain an updated state characteristic;
performing feature fusion on the updating state feature and the memory feature sequence by using an output gate in the long and short memory layer to obtain long and short time sequence features;
extracting self-attention time sequence characteristics from the vacation data sequence by utilizing a self-attention layer of the initial vacation model.
In detail, the generating of an analysis vacation data sequence according to the long and short time sequence features and the self-attention time sequence features refers to performing full connection operation on the long and short time sequence features to obtain long and short time sequence data, performing transcoding operation on the self-attention time sequence features to obtain self-attention time sequence data, and adding the long and short time sequence data and the self-attention time sequence data to form an analysis vacation data sequence, wherein a decoder of a transform model can be used for transcoding operation on the self-attention time sequence features to obtain self-attention time sequence data.
In the embodiment of the invention, the vacation time sequence characteristics of each right class can be extracted by extracting the vacation data sequence corresponding to the target right class from the right production data, the preset primary vacation model is iteratively updated by using the vacation data sequence to obtain the vacation analysis model corresponding to the target right class, and all the vacation analysis models are collected into the vacation model set, so that the vacation trend of the production personnel of each right class can be analyzed, and the accuracy of the bearing capacity of the team is improved.
S3, selecting production tools one by one as target production tools, extracting tool production data corresponding to the target production tools from the standard production data, and splitting the tool production data into tool period sequences according to a production period.
In an embodiment of the present invention, the production tool is the target mechanism production machine, the production tool may be a type of robot or a pipelining workbench, and selecting production tools one by one as target production tools refers to selecting one production tool one by one as target production tools.
In detail, the extracting of the tool production data corresponding to the target production tool from the standard production data refers to aggregating data, such as production team data, production cycle data, and production volume, used in the target production tool from the standard production data into tool production data.
Specifically, the production cycle refers to a time period from the beginning of one production to the end of the production of each production team, and the splitting of the tool production data into the tool cycle sequence according to the production cycle refers to extracting the tool cycle data from the tool production data according to a time sequence and arranging all the tool cycle data into the tool cycle sequence.
In the embodiment of the invention, the tool production data corresponding to the target production tool is extracted from the standard production data, and the tool production data is split into the tool cycle sequence according to the production cycle, so that the standard production data can be split according to the production tool and the production cycle, and the subsequent extraction of the target production parameter set is facilitated.
And S4, generating a target production parameter set according to the tool period sequence, establishing a primary team production model according to the target production parameter set, performing iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and collecting all team production models into a team model set.
In the embodiment of the present invention, the target production parameter set includes personnel configuration data, production duration data, and production volume data of each production cycle.
In an embodiment of the present invention, the generating a target production parameter set according to the tool cycle sequence includes:
selecting tool period data in the tool period sequence one by one as target tool period data;
taking production group data in the target tool cycle data as target production group data, extracting yield parameters from the target production group data, and splitting the target production group data into a plurality of personnel arrays according to production personnel;
selecting the personnel arrays one by one as target personnel arrays, extracting right parameters and duration parameters from the target personnel arrays, and aggregating all the right parameters and all the duration parameters of the target production team data into standard parameter sets;
and aggregating the production parameters and the standard parameter groups into standard production parameter groups of the target production shift group data, and aggregating all the standard production parameter groups into a target production parameter group.
In detail, the production team data refers to relevant data of a production team corresponding to the target tool cycle data in the current production cycle, the right parameter refers to the right type of a producer corresponding to the target personnel array, the duration parameter refers to the working duration corresponding to the target personnel array, and the yield parameter refers to the yield of the production cycle corresponding to the production team data.
In detail, the establishing of the primary team production model according to the target production parameter set comprises:
counting the total number of the types of the right-level parameters in the target production parameter set, and establishing a primary team production model according to the total number of the types:
wherein ,
is the analysis production total amount corresponding to the primary team production model,
is referred to as
The right class category is used as a seed,
it is meant the total number of the species in question,
is that the target production parameter set is first
Second of said right class kind
A set of personal members is provided,
is that the target production parameter set is first
The total number of people arrays seeded by the class of authority,
is referred to as
A production weight for the class of rights is seeded,
is that the target production parameter set is first
In a class of said right class
The corresponding privilege level parameter of the personal membership array,
is that the target production parameter set is first
In a class of said right class
And the time length parameter corresponds to the personal member array.
In detail, the production weight is a model parameter in the production model of the primary team, and is used for representing the production efficiency of the production personnel corresponding to each weight class.
In an embodiment of the present invention, the iteratively updating the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool includes:
selecting standard production parameter groups in the target production parameter set one by one as target standard production parameter groups, taking yield parameters in the target standard production parameter groups as real yield parameters, and taking standard parameter groups in the target standard production parameter groups as target standard parameter groups;
substituting the target standard parameter group into the primary team production model to obtain an analysis production parameter;
and iteratively updating the model parameters of the primary team production model according to the loss values between the analysis production parameters and the real yield parameters until the loss values are smaller than a preset loss threshold value, and taking the updated primary team production model as the team production model corresponding to the target production tool.
In the embodiment of the invention, the primary team production model is iteratively updated by utilizing the target production parameter set to obtain the team production model corresponding to the target production tool, so that the relation between the configuration of production personnel and the production time and the production total amount can be established for each production tool, and the accuracy of bearing capacity evaluation is improved.
S5, obtaining production information of a team to be analyzed, extracting configuration information and expected production duration from the production information, updating the expected production duration to standard production duration by using the vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production duration and the configuration information.
In the embodiment of the present invention, the production information includes the number of production employees of each authority class, the expected production duration of the current production cycle, and the type of production tools, and the configuration information includes the number of production employees of each authority class, the type of production tools, and the expected total production amount.
In an embodiment of the present invention, the updating the expected production duration to a standard production duration by using the vacation model set includes:
calculating a right class vacation data sequence corresponding to each right class type by using the vacation model set;
selecting the right-level vacation data sequences one by one as target vacation data sequences, and generating target working data sequences according to the target vacation data sequences;
and calculating a working coefficient according to the target working data sequence, multiplying the working coefficient by the expected production duration to obtain standard right-level production durations corresponding to all right-level types, and aggregating all the standard right-level production durations into a standard production duration.
In detail, the analyzing the carrying capacity of the to-be-analyzed team by using the team model set, the standard production duration and the configuration information refers to selecting a corresponding team production model from the team model set according to the type of the production tool in the configuration information, calculating an analysis production total amount of the to-be-analyzed team by using the standard weight production duration of each weight category in the team production model and the standard production duration and the number of the production staff of each weight category in the configuration information, and evaluating the carrying capacity of the to-be-analyzed team according to the analysis production total amount and the expected production total amount in the configuration information.
Specifically, the step of generating the target working data sequence according to the target vacation data sequence means that an absolute value of a numerical value obtained by subtracting 1 from each data in the target vacation data sequence replaces the number to obtain the target working data sequence, and the step of calculating the working coefficient according to the target working data sequence means that an average value of the target working data sequence is used as the working coefficient.
In the embodiment of the invention, by acquiring the production information of the team to be analyzed, extracting the configuration information and the expected production time from the production information, updating the expected production time to the standard production time by using the vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production time and the configuration information, the production capacity can be analyzed according to the authority class of each producer in the team to be analyzed, the type of a used production tool and the effective production time, and the bearing capacity is analyzed according to the production capacity, so that the accuracy of bearing capacity analysis is improved.
According to the embodiment of the invention, the historical production data of a target mechanism is obtained, the historical production data is subjected to data cleaning to obtain standard production data, the accuracy of the historical production data can be improved, the accuracy of a subsequent data set is improved, the standard production data is divided into a plurality of right-level production data according to the right-level types of producers, vacation models of different right-level types of producers can be conveniently extracted subsequently, vacation time sequence characteristics of each right-level type can be extracted by extracting vacation data sequences corresponding to the target right-level types from the right-level production data, preset primary vacation models are subjected to iterative updating by using the vacation data sequences to obtain vacation analysis models corresponding to the target right-level types, all the vacation analysis models are integrated into a vacation model set, the vacation time sequence characteristics of each right-level type of producer can be analyzed, the accuracy of bearing capacity of a team is improved, the tool production data corresponding to the target production tool is collected from the standard production data, the production data is divided into a production tool sequence according to a production cycle, the subsequent production data can be extracted according to a production cycle, and the target production data can be extracted according to the production cycle, and the target production data;
the class production model corresponding to the target production tool is obtained by utilizing the target production parameter set to iteratively update the primary class production model, the relationship between the configuration of production personnel and the production time and the total production quantity can be established for each production tool, the accuracy of bearing capacity evaluation is improved, the configuration information and the expected production time length are extracted from the production information by obtaining the production information of the class to be analyzed, the expected production time length is updated to the standard production time length by utilizing the vacation model set, the standard production time length and the configuration information are utilized to analyze the bearing capacity of the class to be analyzed, the production capacity can be analyzed according to the authority class type of each production personnel in the class to be analyzed, the type of the used production tool and the effective production time length, the bearing capacity is analyzed according to the production capacity, and the accuracy of bearing capacity analysis is improved. Therefore, the digital-based bearing capacity evaluation method for the production team can solve the problem of low accuracy in the process of carrying out bearing capacity evaluation on the production team.
Fig. 4 is a functional block diagram of a digital-based load-bearing capacity evaluating apparatus for a production team according to an embodiment of the present invention.
The digital production team based bearing capacity assessment device 100 can be installed in electronic equipment. According to the implemented functions, the digital production team load capacity assessment device 100 can include a data washing module 101, a vacation model module 102, a tool cycle module 103, a team model module 104, and a load assessment module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and are stored in a memory of the electronic device.
In the present embodiment, the functions of the respective modules/units are as follows:
the data cleaning module 101 is configured to obtain historical production data of a target mechanism, perform data cleaning on the historical production data to obtain standard production data, and split the standard production data into multiple right-level production data according to right-level categories of production staff;
the vacation model module 102 is configured to select the right class types one by one as target right class types, extract a vacation data sequence corresponding to the target right class types from the right production data, perform iterative update on a preset primary vacation model by using the vacation data sequence to obtain a vacation analysis model corresponding to the target right class types, and assemble all the vacation analysis models into a vacation model set, where the vacation data sequence is used to perform iterative update on the preset primary vacation model to obtain the vacation analysis model corresponding to the target right class types, and includes: extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model; generating an analysis vacation data sequence according to the long-short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence; calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is referred to as the value of the deviation,
means the total number of data of the analysis vacation data sequence, and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as
The number of the data is set to be,
is the first in the analysis vacation data sequence
The number of the data is set to be,
is the first in the target vacation data sequence
The number of the data is one,
is a preset reference coefficient of the reference signal,
is a preset equilibrium coefficient; iteratively updating the model parameters of the initial vacation model according to the deviation value to obtain a vacation analysis model corresponding to the target authority class;
the tool cycle module 103 is configured to select production tools one by one as target production tools, extract tool production data corresponding to the target production tools from the standard production data, and split the tool production data into a tool cycle sequence according to a production cycle;
the team model module 104 is configured to generate a target production parameter set according to the tool cycle sequence, establish a primary team production model according to the target production parameter set, perform iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and assemble all team production models into a team model set;
the bearing evaluation module 105 is configured to obtain production information of a to-be-analyzed team, extract configuration information and expected production duration from the production information, update the expected production duration to a standard production duration by using the vacation model set, and analyze bearing capacity of the to-be-analyzed team by using the team model set, the standard production duration and the configuration information.
In detail, in the embodiment of the present invention, when the modules in the digital production team based bearing capacity evaluation apparatus 100 are used, the same technical means as the digital production team based bearing capacity evaluation method described in fig. 1 to 3 are adopted, and the same technical effects can be produced, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A digitalized production team bearing capacity assessment method is characterized by comprising the following steps:
s1: acquiring historical production data of a target mechanism, performing data cleaning on the historical production data to obtain standard production data, and dividing the standard production data into a plurality of right-level production data according to the right-level types of production personnel;
s2: selecting the right-level types one by one as target right-level types, extracting vacation data sequences corresponding to the target right-level types from the right-level production data, performing iterative update on a preset primary vacation model by using the vacation data sequences to obtain a vacation analysis model corresponding to the target right-level types, and assembling all the vacation analysis models into a vacation model set, wherein the vacation data sequences are used for performing iterative update on the preset primary vacation model to obtain the vacation analysis model corresponding to the target right-level types, and the method comprises the following steps:
s21: extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model;
s23: generating an analysis vacation data sequence according to the long-short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence;
s23: calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is meant to refer to the value of the deviation,
means the total number of data of the analysis vacation data sequence and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as the first
The number of the data is one,
is the first in the analysis vacation data sequence
The number of the data is set to be,
is the first in the target vacation data sequence
The number of the data is set to be,
is a preset reference coefficient of the reference signal,
is a preset balance coefficient;
s24: iteratively updating the model parameters of the initial vacation model according to the deviation value to obtain a vacation analysis model corresponding to the target authority class;
s3: selecting production tools one by one as target production tools, extracting tool production data corresponding to the target production tools from the standard production data, and splitting the tool production data into tool cycle sequences according to a production cycle;
s4: generating a target production parameter set according to the tool period sequence, establishing a primary team production model according to the target production parameter set, performing iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and collecting all team production models into a team model set;
s5: the method comprises the steps of obtaining production information of a team to be analyzed, extracting configuration information and expected production duration from the production information, updating the expected production duration to standard production duration by using a vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production duration and the configuration information.
2. The method for evaluating the carrying capacity of the production team based on the digitization of claim 1, wherein the data cleaning of the historical production data to obtain the standard production data comprises:
screening the scrambled data and offside data from the historical production data to obtain screened production data;
vectorizing the screening production data to obtain a screening production vector set, and adding a position vector to each screening production vector in the screening production vector set to obtain a position production vector set;
performing feature clustering on the position production vector set to obtain a plurality of production vector classes, and gathering the clustering centers of the production vector classes into a production center vector set;
mapping the production center vector set to the screening production data to obtain a clustering center data set;
and filling each null value data in the screened production data according to the clustering center data set to obtain standard production data.
3. The method of claim 2, wherein the populating each null data in the screening production data according to the cluster center data set to obtain standard production data comprises:
selecting null value data in the screening production data one by one as target null value data;
calculating Euclidean distances between the target null data and each clustering center data in the clustering center data set;
selecting clustering center data with the minimum Euclidean distance as target clustering data;
and filling the target null value data by using the target clustering data until the target null value data is the last null value data in the screening production data, and taking the filled screening production data as standard production data.
4. The method for evaluating the bearing capacity of the production team based on the digitization of claim 1, wherein the extracting of the vacation data sequence corresponding to the target right class from the right production data comprises:
arranging the right-level production data according to a time sequence to obtain time sequence production data;
extracting a production data sequence from the time sequence production data by using a preset time domain window;
selecting the production data in the production data sequence one by one as target production data, and extracting the primary vacation data of each production staff from the target production data;
and calculating vacation data corresponding to the target production data according to all the primary vacation data, and arranging all the vacation data into a vacation data sequence.
5. The digitalized production team bearing capacity evaluation method according to claim 1, wherein the extracting of the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequences by using a preset initial vacation model comprises:
screening a memory characteristic sequence from the vacation data sequence by utilizing a forgetting gate in a long and short memory layer of a preset initial vacation model;
performing characteristic updating on the memory characteristic sequence and the vacation data sequence by using a characteristic state gate in the long and short memory layers to obtain an updated state characteristic;
performing feature fusion on the updating state feature and the memory feature sequence by using an output gate in the long and short memory layer to obtain long and short time sequence features;
extracting self-attention time sequence features from the vacation data sequence by utilizing a self-attention layer of the initial vacation model.
6. The method of claim 1, wherein the generating the target set of production parameters according to the sequence of tool cycles comprises:
selecting tool period data in the tool period sequence one by one as target tool period data;
taking production group data in the target tool cycle data as target production group data, extracting yield parameters from the target production group data, and splitting the target production group data into a plurality of personnel arrays according to production personnel;
selecting the personnel arrays one by one as target personnel arrays, extracting right-level parameters and duration parameters from the target personnel arrays, and gathering all the right-level parameters and all the duration parameters of the target production team group data into standard parameter sets;
and the production parameters and the standard parameter groups are assembled into standard production parameter groups of the target production group data, and all the standard production parameter groups are assembled into target production parameter groups.
7. The method of claim 6, wherein the building a preliminary team production model based on the target set of production parameters comprises:
counting the total number of types of the right-level parameters in the target production parameter set, and establishing a primary team production model according to the total number of types:
wherein , 
is the analysis production total amount corresponding to the production model of the primary team,
is referred to as the first
The right class category is used as a seed,
it is meant the total number of the species in question,
is that the target production parameter set is first
In a class of said right class
A set of personal members is provided for each of the plurality of persons,
is that the target production parameter set is first
The total number of people arrays seeded by the class of authority,
is referred to as
A production weight for the class of rights is seeded,
is that the target production parameter set is first
Second of said right class kind
The corresponding right level parameter of the personal membership array,
is that the target production parameter set is first
Second of said right class kind
And the time length parameter corresponds to the personal member array.
8. The digitalized production team bearing capacity evaluation method according to claim 1, wherein the iteratively updating the primary team production model by using the target production parameter set to obtain the team production model corresponding to the target production tool includes:
selecting standard production parameter groups in the target production parameter set one by one as target standard production parameter groups, taking yield parameters in the target standard production parameter groups as real yield parameters, and taking standard parameter groups in the target standard production parameter groups as target standard parameter groups;
substituting the target standard parameter group into the primary team production model to obtain an analysis production parameter;
and iteratively updating the model parameters of the primary team production model according to the loss values between the analysis production parameters and the real yield parameters until the loss values are smaller than a preset loss threshold value, and taking the updated primary team production model as the team production model corresponding to the target production tool.
9. The method of claim 1, wherein the updating the expected production hours to standard production hours using the set of vacation models comprises:
calculating a right class vacation data sequence corresponding to each right class type by using the vacation model set;
selecting the right-level vacation data sequences one by one as target vacation data sequences, and generating target working data sequences according to the target vacation data sequences;
and calculating a working coefficient according to the target working data sequence, multiplying the working coefficient by the expected production time to obtain standard right-level production time corresponding to each right-level type, and collecting all the standard right-level production time into standard production time.
10. A digital production team based capacity assessment apparatus, the apparatus comprising:
the data cleaning module is used for acquiring historical production data of a target mechanism, performing data cleaning on the historical production data to obtain standard production data, and dividing the standard production data into a plurality of right-level production data according to the right-level types of producers;
the vacation model module is configured to select the right-level categories one by one as target right-level categories, extract vacation data sequences corresponding to the target right-level categories from the right-level production data, perform iterative update on a preset primary vacation model by using the vacation data sequences to obtain vacation analysis models corresponding to the target right-level categories, and assemble all the vacation analysis models into a vacation model set, where the vacation analysis models corresponding to the target right-level categories are obtained by using the vacation data sequences to perform iterative update on the preset primary vacation model, and includes: extracting the length time sequence characteristics and the self-attention time sequence characteristics of the vacation data sequence by using a preset initial vacation model; generating an analysis vacation data sequence according to the long and short time sequence characteristics and the self-attention time sequence characteristics, and extracting a partial sequence corresponding to the analysis vacation data sequence from the vacation data sequence as a target vacation data sequence; calculating a deviation value between the target vacation data sequence and the analysis vacation data sequence by using a vacation deviation algorithm as follows:
wherein ,
is meant to refer to the value of the deviation,
means the total number of data of the analysis vacation data sequence and the total number of data of the analysis vacation data sequence is equal to the total number of data of the target vacation data sequence,
is referred to as the first
The number of the data is one,
is the first in the analysis vacation data sequence
The number of the data is set to be,
is the first in the target vacation data sequence
The number of the data is one,
is a preset reference coefficient of the reference signal,
is a preset equilibrium coefficient; iteratively updating the model parameters of the initial vacation model according to the deviation value to obtain a vacation analysis model corresponding to the target authority class;
the tool cycle module is used for selecting production tools one by one as target production tools, extracting tool production data corresponding to the target production tools from the standard production data, and splitting the tool production data into tool cycle sequences according to a production cycle;
the team model module is used for generating a target production parameter set according to the tool period sequence, establishing a primary team production model according to the target production parameter set, performing iterative update on the primary team production model by using the target production parameter set to obtain a team production model corresponding to the target production tool, and collecting all team production models into a team model set;
and the bearing evaluation module is used for acquiring the production information of the team to be analyzed, extracting configuration information and expected production duration from the production information, updating the expected production duration into standard production duration by using the vacation model set, and analyzing the bearing capacity of the team to be analyzed by using the team model set, the standard production duration and the configuration information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310054043.7A CN115809795B (en) | 2023-02-03 | 2023-02-03 | Method and device for evaluating bearing capacity of production team based on digitalization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310054043.7A CN115809795B (en) | 2023-02-03 | 2023-02-03 | Method and device for evaluating bearing capacity of production team based on digitalization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115809795A true CN115809795A (en) | 2023-03-17 |
| CN115809795B CN115809795B (en) | 2023-04-25 |
Family
ID=85487785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310054043.7A Active CN115809795B (en) | 2023-02-03 | 2023-02-03 | Method and device for evaluating bearing capacity of production team based on digitalization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115809795B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116154239A (en) * | 2023-04-14 | 2023-05-23 | 湖南省计量检测研究院 | Multi-level implementation-based hydrogen fuel cell energy conversion method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040107133A1 (en) * | 2002-12-02 | 2004-06-03 | Pershing Investments, Llc. | Capacity planning method and system |
| JP2009289056A (en) * | 2008-05-29 | 2009-12-10 | Renesas Technology Corp | Device for supporting personnel arrangement planning |
| CN103400221A (en) * | 2013-07-22 | 2013-11-20 | 无锡中科泛在信息技术研发中心有限公司 | Multidimensional multi-level productivity accounting method |
| WO2014103248A1 (en) * | 2012-12-26 | 2014-07-03 | 日本電気株式会社 | Productivity calculation device and calculation method |
| CN104123672A (en) * | 2014-07-22 | 2014-10-29 | 西北工业大学 | Method for calculating production capability of airplane assembly line workers |
| CN111880502A (en) * | 2020-07-30 | 2020-11-03 | 上海数策软件股份有限公司 | Factory equipment preventive maintenance scheduling system and method based on delivery satisfaction |
-
2023
- 2023-02-03 CN CN202310054043.7A patent/CN115809795B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040107133A1 (en) * | 2002-12-02 | 2004-06-03 | Pershing Investments, Llc. | Capacity planning method and system |
| JP2009289056A (en) * | 2008-05-29 | 2009-12-10 | Renesas Technology Corp | Device for supporting personnel arrangement planning |
| WO2014103248A1 (en) * | 2012-12-26 | 2014-07-03 | 日本電気株式会社 | Productivity calculation device and calculation method |
| CN103400221A (en) * | 2013-07-22 | 2013-11-20 | 无锡中科泛在信息技术研发中心有限公司 | Multidimensional multi-level productivity accounting method |
| CN104123672A (en) * | 2014-07-22 | 2014-10-29 | 西北工业大学 | Method for calculating production capability of airplane assembly line workers |
| CN111880502A (en) * | 2020-07-30 | 2020-11-03 | 上海数策软件股份有限公司 | Factory equipment preventive maintenance scheduling system and method based on delivery satisfaction |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116154239A (en) * | 2023-04-14 | 2023-05-23 | 湖南省计量检测研究院 | Multi-level implementation-based hydrogen fuel cell energy conversion method and device |
| CN116154239B (en) * | 2023-04-14 | 2023-11-21 | 湖南省计量检测研究院 | Multi-level implementation-based hydrogen fuel cell energy conversion method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115809795B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110198310A (en) | A kind of anti-cheat method of network behavior, device and storage medium | |
| CN110336838B (en) | Account abnormity detection method, device, terminal and storage medium | |
| CN106992994A (en) | A kind of automatically-monitored method and system of cloud service | |
| CN108199795A (en) | The monitoring method and device of a kind of equipment state | |
| CN105471647B (en) | A kind of power communication network fault positioning method | |
| CN114332984B (en) | Training data processing method, device and storage medium | |
| CN115809795A (en) | Digitalized production team bearing capacity evaluation method and device | |
| CN111882157A (en) | Demand prediction method and system based on deep space-time neural network and computer readable storage medium | |
| CN115795329A (en) | Power utilization abnormal behavior analysis method and device based on big data grid | |
| CN115545331A (en) | Control strategy prediction method and device, equipment and storage medium | |
| CN114841268A (en) | Abnormal power customer identification method based on Transformer and LSTM fusion algorithm | |
| CN116862454B (en) | Indoor building design management method and system | |
| CN113962660A (en) | AI technology-based construction worker behavior safety management correction method and system | |
| CN111738348B (en) | Power data anomaly detection method and device | |
| CN115713044B (en) | Method and device for analyzing residual life of electromechanical equipment under multi-condition switching | |
| CN115759885B (en) | Material sampling inspection method and device based on distributed material supply | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN115809280A (en) | Group house renting identification and iteration identification method | |
| CN114971053A (en) | Training method and device for online prediction model of network line loss rate of low-voltage transformer area | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| CN111860598A (en) | Data analysis method and electronic equipment for identifying sports behaviors and relationships | |
| CN116993307B (en) | Collaborative office method and system with artificial intelligence learning capability | |
| CN113064962B (en) | Environment complaint reporting event similarity analysis method | |
| CN110401727B (en) | IP address analysis method and device | |
| CN115983434A (en) | Short-term wind field wind speed prediction method and system based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |