CN117873605B - Equipment end loading method, device, equipment and storage medium - Google Patents
Equipment end loading method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117873605B CN117873605B CN202410275396.4A CN202410275396A CN117873605B CN 117873605 B CN117873605 B CN 117873605B CN 202410275396 A CN202410275396 A CN 202410275396A CN 117873605 B CN117873605 B CN 117873605B
- Authority
- CN
- China
- Prior art keywords
- equipment end
- target
- service logic
- data
- service
- 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.)
- Active
Links
- 238000011068 loading method Methods 0.000 title claims abstract description 93
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000004519 manufacturing process Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 34
- 239000013598 vector Substances 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 27
- 230000009466 transformation Effects 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010224 classification analysis Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a device end loading method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring equipment end data of a target equipment end according to a loading request of the target equipment end, wherein the loading request comprises service demand data; determining the service logic type of the target equipment based on the equipment data and the service demand data; judging whether the target equipment terminal generates service logic adjustment according to the service logic type; if yes, determining configurable parameters corresponding to the service logic types, and determining managed target service logic codes; and dynamically compiling the target business logic code through the just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through the equipment end interface. The method combines the service demand data of the target equipment end with the equipment end data to dynamically determine the service logic type of the equipment end, and the scheme allows the equipment end to adjust the service logic of the equipment end according to the change of the production demand without stopping the machine.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a device end loading method, apparatus, device, and storage medium.
Background
In the field of modern manufacturing and automation, efficient operation of equipment ends and rapid adaptation to changing demands on production lines are key factors for achieving high production efficiency and product quality. With the increasing trend of diversification and individualization of market demands, manufacturing equipment end must have the ability to quickly adjust its operating logic to meet the demands of specific production tasks. Conventional equipment-side business logic adjustment methods typically involve downtime and manual programming, which are time-consuming and labor-consuming, as well as impacting production efficiency and equipment-side utilization.
Disclosure of Invention
The invention mainly aims to solve the technical problem that the existing equipment end loading needs to be stopped.
The first aspect of the present invention provides a device side loading method, where the device side loading method includes:
Acquiring a loading request of a target equipment end, and acquiring equipment end data of the target equipment end according to the loading request, wherein the loading request comprises service demand data of the target equipment end;
Determining the service logic type of the target equipment based on the equipment side data and the service demand data;
Judging whether the target equipment terminal generates service logic adjustment according to the service logic type;
If yes, determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform, and adjusting a managed target service logic code according to the configurable parameter through the manufacturing execution system platform;
And dynamically compiling the target business logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface to realize the non-stop loading of the target equipment end.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining a load request of a target device side, and obtaining device side data of the target device side according to the load request includes:
acquiring a loading request of a target equipment end, and acquiring initial running state data and initial performance index data of the target equipment end according to the loading request;
filtering the initial running state data to obtain the running state data of the target equipment end;
performing standard deviation threshold calculation according to the initial performance index data to obtain a standard deviation threshold of the initial performance index data;
And performing anomaly detection on the initial performance index data through the standard deviation threshold value to obtain the performance index data of the target equipment end.
Optionally, in a second implementation manner of the first aspect of the present invention, the determining, based on the device side data and the service requirement data, a service logic type of the target device side includes:
Performing primary feature extraction on the running state data and the performance index data in the equipment end data respectively to obtain running state features and performance index features respectively;
Performing feature coding on the running state data and the performance index features to obtain device-end features of the target device end;
performing secondary feature extraction on the service demand data to obtain service features of the target equipment end;
And inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, and determining the service logic type of the target equipment end according to the equipment end characteristics and the service characteristics through the service logic identification model.
Optionally, in a third implementation manner of the first aspect of the present invention, inputting the device side feature and the service feature into a preset service logic identification model, and determining, by the service logic identification model, a service logic type of the target device side according to the device side feature and the service feature includes:
inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, wherein the service logic identification model comprises an input layer, an attention mechanism layer, a characteristic fusion layer, a classification layer and an output layer;
The input layer is used for carrying out data preprocessing on the equipment end characteristics and the service characteristics, and the attention mechanism layer is used for respectively calculating attention weight vectors of the equipment end characteristics and the service characteristics after data preprocessing;
The feature fusion layer is used for carrying out feature fusion on the equipment end features and the service features of the target equipment end according to the attention weight vector to obtain a feature fusion vector;
and carrying out classification analysis on the current business logic of the target equipment end according to the feature fusion vector by the classification layer to obtain the business logic type of the target equipment end, and outputting the business logic type by the output layer.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the classifying, by the classifying layer, the current service logic of the target device according to the feature fusion vector to obtain a service logic type of the target device, and outputting, by the output layer, the service logic type includes:
the feature fusion vector is mapped to a high-dimensional feature space through the classification layer in a linear transformation mode, and a linear transformation result is obtained;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
Calculating the probability of the target equipment end corresponding to different service logic types according to the nonlinear transformation result through a full connection layer in the classification layer;
And taking the service logic type with the highest probability as the service logic type of the target equipment end, and outputting the service logic type through the output layer.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform, and determining, by the manufacturing execution system platform, a managed target service logic code according to the configurable parameter includes:
Determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform;
Carrying out parameter analysis on the configurable parameters through the manufacturing execution system platform, and carrying out logic mapping according to analysis results of the parameter analysis to determine corresponding service logic code blocks;
And adjusting the current execution code of the target equipment based on the service logic code block to obtain a target service logic code.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the dynamically compiling, by a preset just-in-time compiling engine, the target service logic code to obtain a corresponding dynamic link library file, and controlling, by a preset device end interface, the target device end to execute the dynamic link library file, where implementing non-stop loading of the target device end includes:
a preset just-in-time compiling engine determines the compiling type of the target business logic code, wherein the compiling type comprises asynchronous compiling and synchronous compiling;
Dynamically compiling the target business logic code according to the compiling type through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file;
And controlling the target equipment end to execute the dynamic link library file through a preset southbound interface, so as to realize the non-stop loading of the target equipment end.
The second aspect of the present invention provides an apparatus end loading device, including:
The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a loading request of a target equipment end and acquiring equipment end data of the target equipment end according to the loading request, wherein the loading request comprises service demand data of the target equipment end;
The type determining module is used for determining the service logic type of the target equipment based on the equipment side data and the service demand data;
the judging module is used for judging whether the target equipment end generates service logic adjustment according to the service logic type;
The code determining module is used for determining the corresponding configurable parameters of the service logic type in a preset manufacturing execution system platform if yes, and adjusting the managed target service logic codes according to the configurable parameters through the manufacturing execution system platform;
And the dynamic compiling module is used for dynamically compiling the target business logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface to realize the non-stop loading of the target equipment end.
A third aspect of the present invention provides an apparatus end loading device, including: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line; the at least one processor invokes the instructions in the memory to cause the device side loading apparatus to perform the steps of the device side loading method described above.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the steps of the device side loading method described above.
The device end loading method, the device, the equipment and the storage medium acquire the device end data of the target device end according to the loading request of the target device end, wherein the loading request comprises the service demand data of the target device end; determining the service logic type of the target equipment based on the equipment data and the service demand data; judging whether the target equipment terminal generates service logic adjustment according to the service logic type; if yes, determining configurable parameters corresponding to the service logic types and managed target service logic codes; and dynamically compiling the target business logic code through the just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface. The method obtains the service demand data of the target equipment end, and dynamically determines the service logic type of the equipment end by combining the equipment end data.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a device end loading method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of an apparatus end loading device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a device end loading device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "comprising" and "having" and any variations thereof, as used in the embodiments of the present invention, are intended to cover non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed or inherent to such process, method, article, or apparatus but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.
For the sake of understanding the present embodiment, first, a device end loading method disclosed in the present embodiment is described in detail. As shown in fig. 1, the method comprises the following steps:
101. Acquiring a loading request of a target equipment end, and acquiring equipment end data of the target equipment end according to the loading request, wherein the loading request comprises service demand data of the target equipment end;
In one embodiment of the present invention, the obtaining a load request of a target device side, and obtaining device side data of the target device side according to the load request includes: acquiring a loading request of a target equipment end, and acquiring initial running state data and initial performance index data of the target equipment end according to the loading request; filtering the initial running state data to obtain the running state data of the target equipment end; performing standard deviation threshold calculation according to the initial performance index data to obtain a standard deviation threshold of the initial performance index data; and performing anomaly detection on the initial performance index data through the standard deviation threshold value to obtain the performance index data of the target equipment end.
Specifically, the load request of the target device side generally refers to an instruction or data request sent when an operation or task is allocated to the device side. Such a request may include information about the particular task that the device side needs to perform, operating parameters, expected performance metrics, etc. The load request is a way to interact between the device side control system and the device side to instruct the device side to prepare to execute a new workload or adjust its current operating state to accommodate new production requirements. Acquiring initial operating state data and initial performance index data of a target device side according to a load request generally involves reading data from a sensor, a control system, or an internal log of the device side. The initial operation state data includes the current operation state of the equipment end, such as temperature, pressure, speed, switching state and the like, and the initial performance index data includes key indexes for evaluating the performance of the equipment end, such as yield, efficiency, failure rate, energy consumption and the like. The filtering process is a data preprocessing operation performed on the initial operating state data in order to remove noise or irrelevant fluctuations to obtain more accurate and reliable operating state data. The filtering method may be a simple moving average filtering, a median filtering, or more complex such as a kalman filtering, etc. Which filtering method is selected depends on the nature of the data and the particular problem to be solved. The standard deviation threshold calculation is based on the initial performance index data in order to determine a threshold for subsequent anomaly detection. First, the average value and standard deviation of the initial performance index data are calculated. Then, a factor can be determined according to the specific application scene and experience, and the standard deviation is multiplied by the factor to obtain a standard deviation threshold value. This threshold defines what is considered to be a fluctuation in the normal range and what is considered to be an anomaly. Abnormality detection based on the standard deviation threshold is achieved by comparing whether the absolute value of the difference between each performance index data and the average value exceeds the standard deviation threshold. If the absolute value of the difference is greater than the standard deviation threshold, the data point is considered anomalous. This approach may help identify sudden changes or degradation in equipment-side performance, which may be early signs of equipment-side failure, performance degradation, or operational errors.
102. Determining the service logic type of the target equipment based on the equipment data and the service demand data;
In one embodiment of the present invention, the determining the service logic type of the target device based on the device side data and the service requirement data includes: performing primary feature extraction on the running state data and the performance index data in the equipment end data respectively to obtain running state features and performance index features respectively; performing feature coding on the running state data and the performance index features to obtain device-end features of the target device end; performing secondary feature extraction on the service demand data to obtain service features of the target equipment end; and inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, and determining the service logic type of the target equipment end according to the equipment end characteristics and the service characteristics through the service logic identification model.
Specifically, one feature extraction is a process of extracting key information from raw data that facilitates subsequent analysis and decision making. For one feature extraction of the operation state data and the performance index data, the following steps are generally implemented: data preprocessing: including cleaning the data (removing missing or outliers), normalizing (scaling the data to the same range or distribution), etc., to improve data quality. Feature selection: the variable most relevant to the target variable (such as the service logic type of the equipment side) is selected from a large amount of original data. This may be done through statistical testing, model coefficients, or expert experience. Characteristic structure: and constructing new features according to service understanding and data analysis results, wherein the features can better reflect the running state and performance of the equipment end. For example, the characteristic "average hourly temperature change rate" is constructed from temperature and time data. The obtained running state characteristics may include average running speed, stability index, failure frequency and the like of the equipment end; and performance index features may include yield, quality scores, energy consumption, etc.
Specifically, feature encoding of the operating state features and performance index features is the process of converting these features into a format that can be processed by the model. The feature coding method mainly comprises single-heat coding, label coding, binary coding, frequency coding and the like, and the device end features can be obtained through feature coding and represent the running state and performance index of the device end in a structured numerical form. Secondary feature extraction of business requirement data refers to further analysis and processing of the extracted features to better accommodate specific analysis or model requirements. By combining multiple related features into a new feature, interactions between them are captured. For example, yield data for different time periods are combined into a "daily yield fluctuation" feature. Based on the existing features, new features are constructed by mathematical transformations (e.g., squaring, logarithming, etc.) to reveal complex nonlinear relationships. When the feature space is very large, the number of features is reduced through an algorithm (such as Principal Component Analysis (PCA) and an automatic feature selection method), and the features with the most information are reserved.
Further, inputting the device-side feature and the service feature into a preset service logic identification model, and determining the service logic type of the target device-side according to the device-side feature and the service feature through the service logic identification model includes: inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, wherein the service logic identification model comprises an input layer, an attention mechanism layer, a characteristic fusion layer, a classification layer and an output layer; the input layer is used for carrying out data preprocessing on the equipment end characteristics and the service characteristics, and the attention mechanism layer is used for respectively calculating attention weight vectors of the equipment end characteristics and the service characteristics after data preprocessing; the feature fusion layer is used for carrying out feature fusion on the equipment end features and the service features of the target equipment end according to the attention weight vector to obtain a feature fusion vector; and carrying out classification analysis on the current business logic of the target equipment end according to the feature fusion vector by the classification layer to obtain the business logic type of the target equipment end, and outputting the business logic type by the output layer.
In particular, the main task of the input layer is to perform preliminary data preprocessing on the input device-side features and business features to ensure that these data can be effectively processed by the model. The pretreatment process mainly comprises the following steps: normalization: all numerical features are scaled to a uniform range (e.g., between 0 and 1) to avoid model training inefficiency due to excessive differences in the range of feature values. Standardization: the characteristic data are converted into the distribution with the mean value of 0 and the standard deviation of 1, so that the model convergence speed is increased. Missing value processing: for missing data, padding (using average, median, etc.), deletion, interpolation, or the like may be employed. The role of the attention mechanism layer is to automatically identify and emphasize the most important feature information for the current task. In this layer, the model calculates an attention weight vector for the device-side features and the business features after data preprocessing, respectively. The model learns to derive importance scores for each feature, which are expressed as values in weight vectors. The calculated weight vector is used for weighting the characteristics, so that the influence of important characteristics is enhanced, and the interference of unimportant characteristics is reduced. At the feature fusion layer, the model fuses the equipment end features and the service features according to the attention weight vector to generate a feature fusion vector comprehensively considering the importance of the two types of features. This process helps the model to better understand the interrelationship and interactions between features. And carrying out weighted summation on the features according to the weights corresponding to the weight vectors to generate a single vector fused with all the important information. The classification layer is responsible for classifying and analyzing the current business logic of the target equipment according to the feature fusion vector. This layer typically consists of one or more fully connected layers (DENSE LAYER) that process feature fusion vectors through nonlinear activation functions to achieve a business logic type decision. The output of the classification layer is a probability distribution representing the predictive confidence of the model for each business logic type. The output layer functions to present the prediction results of the classification layer in an easily understood format. Typically, the output layer will use, for example, a softmax function to convert the output of the classification layer into probability values, each probability value corresponding to a particular service logic type. Finally, the model outputs the service logic type with the highest probability value as the identification and classification of the current service logic of the target equipment.
Further, the classifying, by the classifying layer, the current service logic of the target device according to the feature fusion vector to obtain a service logic type of the target device, and outputting, by the output layer, the service logic type includes: the feature fusion vector is mapped to a high-dimensional feature space through the classification layer in a linear transformation mode, and a linear transformation result is obtained; nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained; calculating the probability of the target equipment end corresponding to different service logic types according to the nonlinear transformation result through a full connection layer in the classification layer; and taking the service logic type with the highest probability as the service logic type of the target equipment end, and outputting the service logic type through the output layer.
Specifically, the full connection layer (or called dense layer) of the classification layer. Each neuron in the full-connection layer is connected with all neurons of the previous layer, and the input feature fusion vectors are weighted and summed, and the bias term is added to complete the linear transformation. Mathematically, this can be expressed as: where, (x) is the input feature fusion vector, (W) is the weight matrix, (b) is the bias term, and (y) is the result of the linear transformation. The result of the linear transformation is processed by a preset activation function (e.g., reLU, sigmoid, tanh, etc.). For example, the ReLU activation function is defined as: [ f (y) =max (0, y) ] it will convert all negative values to 0, leaving positive values unchanged, thereby introducing nonlinearity. Here, (f (y)) is the result of the nonlinear transformation. Typically after the last fully connected layer of the model, this is done using the softmax function. The softmax function may convert a vector of arbitrary real values into a true probability distribution. For each service logic type, the softmax function computes the probability of that type, which is formulated as: [ P (y_i) = \frac { e { y_i } { \sum_ j e { y_j } ], where (y_i) is the (i) th element in the nonlinear transformation result vector and (P (y_i)) is the probability corresponding to that element. The model selects the type with highest probability as the service logic type of the target equipment by comparing probability values of all the service logic types. This process typically occurs at the output layer, which is responsible for outputting the highest probability business logic type in an easily understood format (e.g., type number or name).
103. Judging whether the target equipment terminal generates service logic adjustment according to the service logic type;
In one embodiment of the present invention, whether the service logic type is different from the service logic type of the previous target device is determined according to the service logic type output by the model, and if yes, the target device performs service logic adjustment.
104. Determining a corresponding configurable parameter of the service logic type in a preset manufacturing execution system platform, and adjusting a managed target service logic code according to the configurable parameter through the manufacturing execution system platform;
In one embodiment of the present invention, the determining the configurable parameters corresponding to the service logic types in the preset manufacturing execution system platform, and determining, by the manufacturing execution system platform, the managed target service logic codes according to the configurable parameters includes: determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform; carrying out parameter analysis on the configurable parameters through the manufacturing execution system platform, and carrying out logic mapping according to analysis results of the parameter analysis to determine corresponding service logic code blocks; and adjusting the current execution code of the target equipment based on the service logic code block to obtain a target service logic code.
Specifically, in a preset manufacturing execution system platform, configurable parameters related to business logic types are defined and configured. These parameters may include equipment end state, production process, workflow, quality requirements, etc. The configurable parameters are parsed by a manufacturing execution system platform to be converted into specific numerical values or logical expressions. This process may involve data conversion, format verification, rule matching, etc. And mapping the parameter analysis result to a preset service logic code block. These code blocks may be general purpose logic that has been implemented, or specific logic that has been custom developed according to specific needs. And adjusting the current execution code of the target equipment based on the determined business logic code block. This may include adding, deleting, modifying code segments, and adjusting execution order and parameter delivery, among others. And obtaining a new target business logic code through code adjustment, wherein the code is customized and optimized according to the business logic type and parameters.
105. And dynamically compiling the target business logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface to realize the non-stop loading of the target equipment end.
In one embodiment of the present invention, the dynamically compiling the target service logic code by a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target device to execute the dynamic link library file by a preset device interface, so as to implement non-stop loading of the target device includes: a preset just-in-time compiling engine determines the compiling type of the target business logic code, wherein the compiling type comprises asynchronous compiling and synchronous compiling; dynamically compiling the target business logic code according to the compiling type through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file; and controlling the target equipment end to execute the dynamic link library file through a preset southbound interface, so as to realize the non-stop loading of the target equipment end.
Specifically, the preset just-in-time compilation engine may determine the compilation type of the target business logic code according to some conditions or configurations. Asynchronous compiling and synchronous compiling have different characteristics and purposes, and proper compiling types are selected according to requirements. And according to the determined compiling type, the target business logic code is dynamically compiled by a preset just-in-time compiling engine. Asynchronous compilation typically converts code into a form that can be executed in parallel to improve performance and responsiveness; while synchronized compilation generates code that is executed sequentially. The dynamic compiling process may involve steps such as lexical analysis, grammar analysis and optimization processing. And obtaining a corresponding dynamic link library file through dynamic compiling. This linked library file contains compiled target business logic code that can be loaded and executed at runtime. And transmitting the generated dynamic link library files to a target equipment end by using a preset southbound interface, and controlling the target equipment end to execute the dynamic link library files through the interface.
Specifically, in the dynamic compiling process, a source code file to be compiled needs to be prepared first. These source codes may be business logic codes written in a particular programming language (e.g., C, C ++, java, etc.), which is required to ensure the correctness and integrity of the code. And transmitting the source code file to a compiler for compiling by using a preset just-in-time compiling engine or a corresponding compiling tool. The compiler translates the source code into machine code executable by the target platform and generates a corresponding target file. Next, the generated object files need to be connected by using a linker to form a dynamic link library file. The linker processes the symbol table, resolves external dependencies, and ultimately generates a dynamic link library (DLL file) containing executable code and data. After the linking process is completed, a final dynamic link library file can be obtained. The file contains compiled business logic code, which can be loaded into memory at run-time and share functions and data with other programs. And finally, loading the generated dynamic link library file into a memory of the target equipment end through a preset southbound interface or loader, and executing service logic codes in the dynamic link library file. The target equipment side can dynamically call the codes according to the needs, so that flexible function expansion and customization are realized.
In this embodiment, device side data of a target device side is obtained according to a loading request of the target device side, where the loading request includes service requirement data of the target device side; determining the service logic type of the target equipment based on the equipment data and the service demand data; judging whether the target equipment terminal generates service logic adjustment according to the service logic type; if yes, determining configurable parameters corresponding to the service logic types and managed target service logic codes; and dynamically compiling the target business logic code through the just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface. The method obtains the service demand data of the target equipment end, and dynamically determines the service logic type of the equipment end by combining the equipment end data.
The method for loading the device end in the embodiment of the present invention is described above, and the device end loading apparatus in the embodiment of the present invention is described below, referring to fig. 2, where an embodiment of the device end loading apparatus in the embodiment of the present invention includes:
The data acquisition module 201 is configured to acquire a load request of a target device, and acquire device side data of the target device according to the load request, where the load request includes service requirement data of the target device;
A type determining module 202, configured to determine a service logic type of the target device based on the device side data and the service requirement data;
A judging module 203, configured to judge whether service logic adjustment occurs at the target device according to the service logic type;
The code determining module 204 is configured to determine a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform if yes, and adjust a managed target service logic code according to the configurable parameter through the manufacturing execution system platform;
And the dynamic compiling module 205 is configured to dynamically compile the target service logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and control the target device terminal to execute the dynamic link library file through a preset device terminal interface, so as to realize non-stop loading of the target device terminal.
In the embodiment of the invention, the device side loading device runs the device side loading method, and the device side loading device acquires the device side data of the target device side according to the loading request of the target device side, wherein the loading request comprises the service demand data of the target device side; determining the service logic type of the target equipment based on the equipment data and the service demand data; judging whether the target equipment terminal generates service logic adjustment according to the service logic type; if yes, determining configurable parameters corresponding to the service logic types and managed target service logic codes; and dynamically compiling the target business logic code through the just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface. The method obtains the service demand data of the target equipment end, and dynamically determines the service logic type of the equipment end by combining the equipment end data.
The device side loading apparatus in the embodiment of the present invention is described in detail above in fig. 2 from the point of view of modularized functional entities, and the device side loading device in the embodiment of the present invention is described in detail below from the point of view of hardware processing.
Fig. 3 is a schematic diagram of a device side loading device according to an embodiment of the present invention, where the device side loading device 300 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (e.g., one or more processors) and a memory 320, and one or more storage mediums 330 (e.g., one or more mass storage devices) storing applications 333 or data 332. Wherein memory 320 and storage medium 330 may be transitory or persistent storage. The program stored on the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations in the device side loading device 300. Still further, the processor 310 may be configured to communicate with the storage medium 330 and execute a series of instruction operations in the storage medium 330 on the device side loading apparatus 300 to implement the steps of the device side loading method described above.
The device end-loading device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input/output interfaces 360, and/or one or more operating systems 331, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the device end-loading device structure shown in fig. 3 is not limiting of the device end-loading device provided by the present invention and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the device side loading method.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An apparatus end loading method, characterized in that the apparatus end loading method comprises:
Acquiring a loading request of a target equipment end, and acquiring equipment end data of the target equipment end according to the loading request, wherein the loading request comprises service demand data of the target equipment end;
Determining the service logic type of the target equipment based on the equipment side data and the service demand data;
Judging whether the target equipment terminal generates service logic adjustment according to the service logic type;
If yes, determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform, and adjusting a managed target service logic code according to the configurable parameter through the manufacturing execution system platform;
And dynamically compiling the target business logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface to realize the non-stop loading of the target equipment end.
2. The device-side loading method according to claim 1, wherein the obtaining a loading request of a target device side, and obtaining device-side data of the target device side according to the loading request, includes:
acquiring a loading request of a target equipment end, and acquiring initial running state data and initial performance index data of the target equipment end according to the loading request;
filtering the initial running state data to obtain the running state data of the target equipment end;
performing standard deviation threshold calculation according to the initial performance index data to obtain a standard deviation threshold of the initial performance index data;
And performing anomaly detection on the initial performance index data through the standard deviation threshold value to obtain the performance index data of the target equipment end.
3. The device side loading method according to claim 2, wherein the determining the service logic type of the target device side based on the device side data and the service requirement data includes:
Performing primary feature extraction on the running state data and the performance index data in the equipment end data respectively to obtain running state features and performance index features respectively;
performing feature coding on the running state features and the performance index features to obtain equipment end features of the target equipment end;
performing secondary feature extraction on the service demand data to obtain service features of the target equipment end;
And inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, and determining the service logic type of the target equipment end according to the equipment end characteristics and the service characteristics through the service logic identification model.
4. The device-side loading method according to claim 3, wherein the inputting the device-side feature and the service feature into a preset service logic identification model, and determining, by the service logic identification model, the service logic type of the target device-side according to the device-side feature and the service feature includes:
inputting the equipment end characteristics and the service characteristics into a preset service logic identification model, wherein the service logic identification model comprises an input layer, an attention mechanism layer, a characteristic fusion layer, a classification layer and an output layer;
The input layer is used for carrying out data preprocessing on the equipment end characteristics and the service characteristics, and the attention mechanism layer is used for respectively calculating attention weight vectors of the equipment end characteristics and the service characteristics after data preprocessing;
The feature fusion layer is used for carrying out feature fusion on the equipment end features and the service features of the target equipment end according to the attention weight vector to obtain a feature fusion vector;
and carrying out classification analysis on the current business logic of the target equipment end according to the feature fusion vector by the classification layer to obtain the business logic type of the target equipment end, and outputting the business logic type by the output layer.
5. The device-side loading method according to claim 4, wherein the classifying, by the classifying layer, the current service logic of the target device side according to the feature fusion vector to obtain a service logic type of the target device side, and outputting, by the output layer, the service logic type comprises:
the feature fusion vector is mapped to a high-dimensional feature space through the classification layer in a linear transformation mode, and a linear transformation result is obtained;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
Calculating the probability of the target equipment end corresponding to different service logic types according to the nonlinear transformation result through a full connection layer in the classification layer;
And taking the service logic type with the highest probability as the service logic type of the target equipment end, and outputting the service logic type through the output layer.
6. The method for loading equipment end according to claim 1, wherein determining the configurable parameters corresponding to the service logic types in a preset manufacturing execution system platform, and determining, by the manufacturing execution system platform, the managed target service logic codes according to the configurable parameters includes:
Determining a configurable parameter corresponding to the service logic type in a preset manufacturing execution system platform;
Carrying out parameter analysis on the configurable parameters through the manufacturing execution system platform, and carrying out logic mapping according to analysis results of the parameter analysis to determine corresponding service logic code blocks;
And adjusting the current execution code of the target equipment based on the service logic code block to obtain a target service logic code.
7. The device-side loading method according to claim 6, wherein the dynamically compiling the target service logic code by a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target device side to execute the dynamic link library file by a preset device-side interface, so as to implement non-stop loading of the target device side includes:
a preset just-in-time compiling engine determines the compiling type of the target business logic code, wherein the compiling type comprises asynchronous compiling and synchronous compiling;
Dynamically compiling the target business logic code according to the compiling type through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file;
And controlling the target equipment end to execute the dynamic link library file through a preset southbound interface, so as to realize the non-stop loading of the target equipment end.
8. An apparatus end loading device, the apparatus end loading device comprising:
The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a loading request of a target equipment end and acquiring equipment end data of the target equipment end according to the loading request, wherein the loading request comprises service demand data of the target equipment end;
The type determining module is used for determining the service logic type of the target equipment based on the equipment side data and the service demand data;
the judging module is used for judging whether the target equipment end generates service logic adjustment according to the service logic type;
The code determining module is used for determining the corresponding configurable parameters of the service logic type in a preset manufacturing execution system platform if yes, and adjusting the managed target service logic codes according to the configurable parameters through the manufacturing execution system platform;
And the dynamic compiling module is used for dynamically compiling the target business logic code through a preset just-in-time compiling engine to obtain a corresponding dynamic link library file, and controlling the target equipment end to execute the dynamic link library file through a preset equipment end interface to realize the non-stop loading of the target equipment end.
9. A device side loading device, the device side loading device comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invoking the instructions in the memory to cause the device side loading device to perform the steps of the device side loading method of any of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the steps of the device side loading method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275396.4A CN117873605B (en) | 2024-03-12 | 2024-03-12 | Equipment end loading method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275396.4A CN117873605B (en) | 2024-03-12 | 2024-03-12 | Equipment end loading method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117873605A CN117873605A (en) | 2024-04-12 |
| CN117873605B true CN117873605B (en) | 2024-05-24 |
Family
ID=90583407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410275396.4A Active CN117873605B (en) | 2024-03-12 | 2024-03-12 | Equipment end loading method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117873605B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888834A (en) * | 2019-11-06 | 2020-03-17 | 武汉船舶通信研究所（中国船舶重工集团公司第七二二研究所） | Method and system for dynamically reconstructing FPGA function in PCIE equipment |
| CN112950299A (en) * | 2019-11-26 | 2021-06-11 | 浙江大搜车软件技术有限公司 | Scheme design method, device, computer equipment and storage medium |
| CN113312037A (en) * | 2021-06-15 | 2021-08-27 | 北京百度网讯科技有限公司 | Data processing method, device and equipment applied to microservice and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050204340A1 (en) * | 2004-03-10 | 2005-09-15 | Ruminer Michael D. | Attribute-based automated business rule identifier and methods of implementing same |
| US7523461B2 (en) * | 2005-07-01 | 2009-04-21 | Microsoft Corporation | Modification of logic in an application |
-
2024
- 2024-03-12 CN CN202410275396.4A patent/CN117873605B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888834A (en) * | 2019-11-06 | 2020-03-17 | 武汉船舶通信研究所（中国船舶重工集团公司第七二二研究所） | Method and system for dynamically reconstructing FPGA function in PCIE equipment |
| CN112950299A (en) * | 2019-11-26 | 2021-06-11 | 浙江大搜车软件技术有限公司 | Scheme design method, device, computer equipment and storage medium |
| CN113312037A (en) * | 2021-06-15 | 2021-08-27 | 北京百度网讯科技有限公司 | Data processing method, device and equipment applied to microservice and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 规则引擎在制造企业MES中的研究与应用;闫欢 等;计算机工程;20070405;第33卷(第7期);210-212、224 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117873605A (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12093011B2 (en) | Method and system for generating an artificial intelligence model | |
| Kumar et al. | Hybrid functional link artificial neural network approach for predicting maintainability of object-oriented software | |
| CN116760772B (en) | Control system and method for converging flow divider | |
| US20210304073A1 (en) | Method and system for developing a machine learning model | |
| CN116466672B (en) | Data center machine room parameter regulation and control method based on artificial intelligence and related device | |
| CN118114955B (en) | Power scheduling method of virtual power plant and related equipment | |
| CN117826618B (en) | Adaptive control method and system based on cold rolling mill control system | |
| CN113535522A (en) | Abnormal condition detection method, device and equipment | |
| CN118333338A (en) | Data processing method and system of charging management platform | |
| CN117873605B (en) | Equipment end loading method, device, equipment and storage medium | |
| CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
| CN117312208A (en) | IO module multi-adapter control method, device, equipment and storage medium | |
| CN117131022A (en) | Heterogeneous data migration method of electric power information system | |
| CN111783487A (en) | Fault early warning method and device for card reader equipment | |
| EP3945471A1 (en) | Method for automated determination of a model compression technique for compression of an artificial intelligence-based model | |
| CN113076217A (en) | Disk fault prediction method based on domestic platform | |
| Pascual-Pañach et al. | Optimizing Online Time-Series Data Imputation Through Case-Based Reasoning | |
| CN117934931B (en) | Model updating method and device, optical cable intelligent operation and maintenance system and storage medium | |
| US20240054175A1 (en) | Ai-assisted linear programming solver methods, systems, and media | |
| US20240176310A1 (en) | Machine controller and method for configuring the machine controller | |
| CN116541714B (en) | Power grid regulation model training method, system, computer equipment and storage medium | |
| CN118311914B (en) | Production line data acquisition control method and system for intelligent workshop | |
| CN118193151A (en) | Distributed industrial task collaborative scheduling method and system based on group intelligence | |
| CN118502808A (en) | Intelligent packaging system and method in automatic deployment process | |
| More et al. | Multivariate Nonlinear Regression with Artificial Neural Networks on Dynamic and Static Data |
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 |