CN117114226B - Intelligent dynamic optimization and process scheduling system of automation equipment - Google Patents
Intelligent dynamic optimization and process scheduling system of automation equipment Download PDFInfo
- Publication number
- CN117114226B CN117114226B CN202311359939.2A CN202311359939A CN117114226B CN 117114226 B CN117114226 B CN 117114226B CN 202311359939 A CN202311359939 A CN 202311359939A CN 117114226 B CN117114226 B CN 117114226B
- Authority
- CN
- China
- Prior art keywords
- data
- production
- equipment
- similarity
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 149
- 230000008569 process Effects 0.000 title claims abstract description 111
- 238000005457 optimization Methods 0.000 title claims abstract description 110
- 238000012544 monitoring process Methods 0.000 claims abstract description 44
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- 230000000007 visual effect Effects 0.000 claims abstract description 21
- 238000004519 manufacturing process Methods 0.000 claims description 260
- 238000004422 calculation algorithm Methods 0.000 claims description 95
- 230000002159 abnormal effect Effects 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000005065 mining Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 22
- 230000006854 communication Effects 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 238000012163 sequencing technique Methods 0.000 claims description 17
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 7
- 238000005299 abrasion Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000013499 data model Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000003754 machining Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000007175 bidirectional communication Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Abstract
The invention discloses an intelligent dynamic optimization and process scheduling system of automatic equipment, which relates to the field of automatic equipment and comprises an online monitoring module, a data preprocessing module, a dynamic optimization module, a process scheduling module, an intelligent control module and a visual monitoring center, wherein the output end of the online monitoring module is connected with the input end of the data preprocessing module, the output end of the data preprocessing module is connected with the input end of the dynamic optimization module, the output end of the dynamic optimization module is connected with the input end of the process scheduling module, the output end of the data preprocessing module is connected with the input end of the process scheduling module, the output end of the process scheduling module is connected with the input end of the intelligent control module, and the output end of the dynamic optimization module is connected with the input end of the intelligent control module; and the automation degree and the intelligent degree are high.
Description
Technical Field
The invention relates to the field of automation equipment, in particular to an intelligent dynamic optimization and process scheduling system of the automation equipment.
Background
The automatic production equipment is widely applied in modern industrial production, so that the production efficiency and the product quality are greatly improved, but with the improvement of the complexity and the digitization degree of the industrial production, the traditional regular maintenance and equipment adjustment mode cannot adapt to the production requirement, and a more intelligent equipment optimization and scheduling method is needed. Thus, intelligent dynamic optimization of automation equipment and process scheduling systems have evolved. The intelligent dynamic optimization and process scheduling system of the automatic equipment are combined with the actual production and manufacturing conditions, so that the automatic optimization and scheduling of the equipment are realized, the production efficiency and the product quality are improved, and the resource waste and the resource loss are reduced. The system is widely applied to the fields of manufacturing industry, logistics, traffic and the like, and has remarkable effects in improving production efficiency, guaranteeing production safety, reducing production cost and the like.
However, existing systems do not perform adequate cleaning and preprocessing of the acquired data, resulting in unstable data quality. This can affect the accuracy and robustness of the subsequent optimization algorithm. The optimization algorithm in the existing system only considers one aspect of the equipment operation state data or the production process data, and cannot comprehensively consider the relevance between the equipment operation state data and the production process data. This may lead to an insufficiently accurate and reliable optimization result. The process scheduling module in the system has slower calculation speed when processing large-scale tasks. This results in an extended scheduling decision time, which does not meet the real-time requirements. The intelligent control module in the existing system often lacks flexibility and cannot be dynamically adjusted according to the real-time change condition. This may result in poor control or inability to accommodate complex and varied production environments.
Therefore, the invention discloses an intelligent dynamic optimization and process scheduling system of automation equipment.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an intelligent dynamic optimization and process scheduling system of automation equipment, which can optimize and schedule the automation equipment in real time so as to improve the production efficiency, reduce the energy consumption, reduce the production cost and other targets; adopting a processing accelerator GPU to perform process scheduling acceleration; abnormal state mining and prediction are carried out on the running state data of the automatic equipment by adopting a supervision superposition learning prediction algorithm, and dynamic optimization decision of the production process is realized by adopting a self-adaptive strategy optimization algorithm, so that the production efficiency and the reliability are improved; the intelligent sorting of the production tasks is carried out by adopting a depth-associated priority matching algorithm, the similarity of the production tasks is calculated by adopting a similarity refinement comparison algorithm, and if the similarity of the production tasks is greater than a threshold value, the production tasks are combined and executed, so that the production efficiency and the product quality are improved; and the automation degree and the intelligent degree are high.
The invention adopts the following technical scheme:
an intelligent dynamic optimization and process scheduling system for an automation device, the system comprising:
the on-line monitoring module is used for monitoring the running state data and the production process data of the automatic equipment in real time;
The data preprocessing module is used for preprocessing the monitoring data, and the data preprocessing module adopts a data preprocessing tool KNIE to carry out data cleaning, conversion, feature extraction and reconstruction;
the dynamic optimization module is used for dynamically optimizing the automatic equipment, the dynamic optimization module adopts a server CH225V3 to identify the collected running state data of the automatic equipment and dynamically optimizes the equipment, the server CH225V3 is embedded into a supervision and superposition learning prediction algorithm to carry out abnormal state mining and prediction on the running state data of the automatic equipment, and an adaptive strategy optimization algorithm is embedded into the abnormal state mining and prediction algorithm to realize the dynamic optimization decision of the production process;
the process scheduling module is used for planning, scheduling and coordinating the production process of the automatic equipment so as to improve the production efficiency and the equipment utilization rate, the process scheduling module adopts a processing accelerator GPU to accelerate the process scheduling, the processing accelerator GPU is embedded into a depth-associated priority matching algorithm to intelligently sort production tasks, the similarity is embedded into a similarity refinement comparison algorithm to calculate the similarity of the production tasks, and the similarity of the production tasks is greater than a threshold value, and the processing accelerator GPU is combined and executed;
The intelligent control module is used for automatically controlling and adjusting the production process according to the dynamic optimization decision of the production process and the intelligent sequencing of the production tasks;
the visual monitoring center is used for remotely monitoring intelligent dynamic optimization and process scheduling process information of the automation equipment, and the visual monitoring center realizes the monitoring of the intelligent dynamic optimization and process scheduling process through a visual data platform QlikView;
the output end of the on-line monitoring module is connected with the input end of the data preprocessing module, the output end of the data preprocessing module is connected with the input end of the dynamic optimizing module, the output end of the dynamic optimizing module is connected with the input end of the process scheduling module, the output end of the data preprocessing module is connected with the input end of the process scheduling module, the output end of the process scheduling module is connected with the input end of the intelligent control module, the output end of the dynamic optimizing module is connected with the input end of the intelligent control module, and the visual monitoring center works in the whole course.
As a further technical scheme of the invention, the on-line monitoring module adopts an acceleration sensor, a temperature sensor and a current sensor to monitor the running state data of the automatic equipment in real time, and monitors the production process data in real time through a visual sensor and an infrared sensor, wherein the running state data of the automatic equipment comprises vibration frequency, processing efficiency, wear degree and failure rate, and the production process data comprises process parameters and product quality.
As a further technical scheme of the invention, the supervision superposition learning prediction algorithm performs abnormal state mining and prediction on the running state data of the automation equipment according to the running state data of the historical automation equipment and the running state data of the real-time automation equipment, wherein the data sets of the running state data of the historical automation equipment and the running state data of the real-time automation equipment are as followsT is the time of collecting the running state data of the automation equipment, kt is the data of the running state data t of the automation equipment, and the running state data sample of the automation equipment is divided into different characteristic data sets according to the vibration frequency, the processing efficiency, the abrasion degree and the failure rate parameter characteristics, wherein the matrix expression is as follows:
K= （1）
in the formula (1), the vibration frequency parameter characteristic data set isThe processing efficiency parameter characteristic data set is +.>The wear degree parameter characteristic data set is +.>The fault rate parameter characteristic data set is +.>The running state data trend prediction output function formula of the automation equipment at the time t+1 is as follows:
（2）
in the formula (2) of the present invention,for the trend of the operating state data of the automation device at time t+1,/->For the characteristic data of the vibration frequency parameter at time t, +.>For the processing efficiency parameter characteristic data at the moment t, +. >For the characteristic data of the wear degree parameter at the time t, +.>For the characteristic data of the fault rate parameter at the moment t, +.>For the characteristic data maximum value of the vibration frequency, the machining efficiency, the abrasion degree and the failure rate parameters at the moment t, +.>As a function of the maximum value.
As a further technical scheme of the present invention, the adaptive policy optimization algorithm performs a dynamic optimization decision of a production process based on abnormal state mining and prediction results of operation state data of an automation device, the adaptive policy optimization algorithm includes an input layer, a data layer, a model layer, an algorithm layer, an optimization layer and an output layer, and the working method of the adaptive policy optimization algorithm includes the following steps:
s1, inputting data, namely performing format conversion on abnormal state mining and prediction results of running state data of the automatic equipment, and inputting the abnormal state mining and prediction results into a data layer through an input layer;
s2, determining calculated targets and parameters, and acquiring calculation parameters and limiting conditions from input data through a data layer, wherein the calculation parameters and limiting conditions comprise requirements and targets of a production process, optimized indexes and targets, calculation scale, constraint conditions and feasible fields so as to ensure the rationality and effectiveness of a decision process, and the optimized indexes and targets comprise production efficiency, resource utilization rate and product quality;
S3, establishing a dynamic optimization decision model of the production process, wherein the model layer establishes a dynamic optimization decision mathematical model of the production process according to the requirements and targets of the production process, the optimized indexes and targets, the calculation scale, the constraint conditions and the feasible region, and sets a dynamic optimization decision objective function of the production process;
s4, solving a dynamic optimization decision objective function in the production process, wherein the self-adaptive strategy optimization algorithm adopts an algorithm layer to carry out iterative computation, parameter correction and comparison between a computation result and a true value, and optimizes the computation speed by maintaining a neighbor list of a computation node;
s5, carrying out fine control and optimization on the solving process, merging or splitting the measurement units by an optimization layer, setting a threshold value and iteration times in a self-adaptive parameter selection mode, and distributing calculation tasks to a plurality of processors or calculation nodes by the optimization layer in a parallel calculation mode so as to improve the calculation speed;
s6, outputting results, namely outputting the data results of the operation of the automation equipment through an output layer.
As a further technical solution of the present invention, the depth-associated priority matching algorithm includes the following steps:
step 1, setting association priority of training feature quantity, counting the value of each feature quantity in a training data set, scanning the whole data set to determine the support degree of each feature quantity and the influence degree on the operation state of a production task and equipment, quantifying the association degree and direction between each feature quantity and a target production task by using Pearson correlation coefficient, and carrying out weight distribution according to the quantification result;
Step 2, extracting characteristics of real-time monitoring of running state data and production process data information of the automatic equipment, and converting the information characteristics into characteristic vector representations, wherein the information characteristics comprise production task types, production quantity, production period, equipment requirements, equipment load conditions and process parameters;
step 3, carrying out association matching on the training characteristic quantity and the real-time monitoring characteristic quantity, calculating the similarity between the training characteristic quantity and the real-time monitoring characteristic quantity, selecting the characteristic quantity with the highest similarity as a candidate matching point, and sequencing according to the association priority of the set training characteristic quantity;
step 4, adjusting and optimizing the matching points, taking the correct matching points as new reference points through continuous iteration, carrying out feature matching and association operation again so as to find new correct matching points, deleting incorrect matching points and adjusting matching priorities;
and 5, outputting the sequencing result.
As a further technical scheme of the invention, the similarity refinement comparison algorithm calculates the similarity of the production task by comparing the process parameters, the process steps and the equipment states of the production task, and calculates the threshold value based on the similarity of the historical production task, wherein the process parameters, the process steps and the equipment state data sets of the production task of the section A are respectively as follows ，/>Process parameter data set for A production task, < >>Process step data set for A production task, < >>The equipment state data set of the production task A is obtained, and the technological parameters, the technological steps and the equipment state data set of the production task B are respectively +.>，/>Process parameters for the B production taskData set->Process step data set for production task B, < >>For the equipment state data set of the production task B, the similarity output function formula of the production tasks A and B is as follows:
（3）
in the formula (3) of the present invention,similarity of production tasks for A and B, < >>Weighting coefficients for the similarity of process parameters of a production task, < >>Weighting coefficients for the similarity of process steps of a production task, < >>Device state weighting factor of production task, +.>For the maximum value of the process parameters of the A production task, +.>Maximum value of the process parameter for the production task B, +.>For the process parameters of the A production task, +.>For the process parameters of the B production task, +.>For A production tasksThe maximum value of the process steps is that,maximum value of the process steps for the production task B, +.>For the process step of the A production task, +.>For the process step of the B production task, +.>For the device state maximum of the A production task, +.>Maximum device state for the B production task, +. >For the device state of the A production task, +.>For the device state of the B production task, the historical production task similarity dataset is s= =>，/>m, the similarity threshold output function formula is:
（4）
in the formula (4) of the present invention,for similarity threshold, ++>As an auxiliary value, +.>Weighting value for similarity threshold value, < >>Maximum similarity, +_A->Is the minimum value of similarity->Is the j-th similarity.
As a further technical scheme of the invention, the intelligent control module adopts the STM32 microcontroller to generate a control decision instruction, and adjusts the state and parameters of production equipment through a motor driver and an electromagnetic valve to realize automatic control and adjustment of the production process, and the STM32 microcontroller carries out remote control on the production process through a high-speed communication network.
As a further technical scheme of the invention, the high-speed communication network adopts an MQTT lightweight bottom layer protocol, a UDP transport layer protocol, an HTTP/2 secure transport protocol and a WebSocket bidirectional communication protocol to realize real-time data interaction between a client and a server so as to reduce network communication delay, and distributes data to a transmission node through server load balancing logic and message queue service so as to realize rapid retransmission of node faults.
As a further technical scheme of the invention, the visualized data platform QlikView acquires mass data source association data based on an association data model so as to realize multidimensional data association analysis, and adopts an interactive chart, a heat point diagram, a map and a dashboard to realize real-time monitoring of trend, relationship and change rule of data, and the visualized data platform QlikView adopts a Token user identity verification mechanism to verify the identity of an access user so as to improve the safety of information access.
Has the positive beneficial effects that:
the invention discloses an intelligent dynamic optimization and process scheduling system of automation equipment, which can optimize and schedule the automation equipment in real time so as to improve the production efficiency, reduce the energy consumption, reduce the production cost and other targets; adopting a processing accelerator GPU to perform process scheduling acceleration; abnormal state mining and prediction are carried out on the running state data of the automatic equipment by adopting a supervision superposition learning prediction algorithm, and dynamic optimization decision of the production process is realized by adopting a self-adaptive strategy optimization algorithm, so that the production efficiency and the reliability are improved; the intelligent sorting of the production tasks is carried out by adopting a depth-associated priority matching algorithm, the similarity of the production tasks is calculated by adopting a similarity refinement comparison algorithm, and if the similarity of the production tasks is greater than a threshold value, the production tasks are combined and executed, so that the production efficiency and the product quality are improved; and the automation degree and the intelligent degree are high.
Drawings
FIG. 1 is a schematic diagram of an overall architecture of an intelligent dynamic optimization and process scheduling system for an automation device according to the present invention;
FIG. 2 is a schematic diagram of a high-speed communication network in an intelligent dynamic optimization and process scheduling system of an automation device according to the present invention;
FIG. 3 is a schematic diagram of a model of an adaptive strategy optimization algorithm in an intelligent dynamic optimization and process scheduling system of an automation device according to the present invention;
FIG. 4 is a circuit diagram illustrating the operation of an on-line monitoring module in an intelligent dynamic optimization and process scheduling system for an automation device according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only 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.
An intelligent dynamic optimization and process scheduling system for an automation device, the system comprising:
the on-line monitoring module is used for monitoring the running state data and the production process data of the automatic equipment in real time;
The data preprocessing module is used for preprocessing the monitoring data, and the data preprocessing module adopts a data preprocessing tool KNIE to carry out data cleaning, conversion, feature extraction and reconstruction;
the dynamic optimization module is used for dynamically optimizing the automatic equipment, the dynamic optimization module adopts a server CH225V3 to identify the collected running state data of the automatic equipment and dynamically optimizes the equipment, the server CH225V3 is embedded into a supervision and superposition learning prediction algorithm to carry out abnormal state mining and prediction on the running state data of the automatic equipment, and an adaptive strategy optimization algorithm is embedded into the abnormal state mining and prediction algorithm to realize the dynamic optimization decision of the production process;
the process scheduling module is used for planning, scheduling and coordinating the production process of the automatic equipment so as to improve the production efficiency and the equipment utilization rate, the process scheduling module adopts a processing accelerator GPU to accelerate the process scheduling, the processing accelerator GPU is embedded into a depth-associated priority matching algorithm to intelligently sort production tasks, the similarity is embedded into a similarity refinement comparison algorithm to calculate the similarity of the production tasks, and the similarity of the production tasks is greater than a threshold value, and the processing accelerator GPU is combined and executed;
The intelligent control module is used for automatically controlling and adjusting the production process according to the dynamic optimization decision of the production process and the intelligent sequencing of the production tasks;
the visual monitoring center is used for remotely monitoring intelligent dynamic optimization and process scheduling process information of the automation equipment, and the visual monitoring center realizes the monitoring of the intelligent dynamic optimization and process scheduling process through a visual data platform QlikView;
the output end of the on-line monitoring module is connected with the input end of the data preprocessing module, the output end of the data preprocessing module is connected with the input end of the dynamic optimizing module, the output end of the dynamic optimizing module is connected with the input end of the process scheduling module, the output end of the data preprocessing module is connected with the input end of the process scheduling module, the output end of the process scheduling module is connected with the input end of the intelligent control module, the output end of the dynamic optimizing module is connected with the input end of the intelligent control module, and the visual monitoring center works in the whole course.
In a specific embodiment, advanced data processing, dynamic optimization and visual monitoring technologies are adopted, so that intelligent control and optimization of the production process are realized. The system has higher intelligent degree and adaptability by adopting the algorithms such as a supervised superposition learning prediction algorithm, a self-adaptive strategy optimization algorithm, a depth-associated priority matching algorithm, a similarity refinement comparison algorithm and the like. Meanwhile, the system has the synergistic effect of a plurality of modules such as on-line monitoring, data preprocessing, dynamic optimization, process scheduling, intelligent control, visual monitoring and the like, and can comprehensively improve the production efficiency and the product quality and improve the enterprise competitiveness and market share.
In the above embodiment, the on-line monitoring module monitors the running state data of the automation device in real time by using an acceleration sensor, a temperature sensor and a current sensor, and monitors the production process data in real time by using a visual sensor and an infrared sensor, wherein the running state data of the automation device comprises a vibration frequency, a processing efficiency, a wear degree and a failure rate, and the production process data comprises a process parameter and a product quality.
In a specific embodiment, an acceleration sensor, a temperature sensor and a current sensor are installed on an automation device to monitor parameters such as vibration frequency, temperature change and current consumption of the device in real time. Meanwhile, a visual sensor and an infrared sensor are used for monitoring process parameters and product quality in real time in the production process. By means of the deployed sensors, the operating state data and the production process data of the automation device are continuously collected. These data may be continuous time series data or discrete event data. Preprocessing the collected original data, including operations such as noise removal, missing value filling, normalization and the like. Thus, the accuracy and stability of the subsequent analysis algorithm can be improved. Meaningful features are extracted from the preprocessed data. Aiming at the equipment running state data, the characteristics such as vibration frequency, machining efficiency, wear degree, failure rate and the like can be extracted; for production process data, characteristics such as process parameters, product quality indexes and the like can be extracted. Using a supervised additive learning prediction algorithm, a model is built for training based on the extracted features and known labels (normal/abnormal). The method can be realized by adopting random forest algorithm. And (5) carrying out abnormal state mining and prediction on the new data by using the trained model. Judging whether the equipment is in an abnormal state or not according to the set threshold value or the probability output by the model, and sending out an alarm in time. Result monitoring and feedback: monitoring abnormal state detection and prediction results, and continuously optimizing algorithms and parameters. And simultaneously, the abnormal state information is fed back to equipment operators or related departments so as to take repairing measures or adjust the production process in time.
In the above embodiment, the supervised superposition learning prediction algorithm performs abnormal state mining and prediction on the automation device operation state data according to the historical automation device operation state data and the real-time automation device operation state data, where the data set of the historical automation device operation state data and the real-time automation device operation state data isT is the time of collecting the running state data of the automatic equipment, and k is t For the data of the running state data t time of the automatic equipment, dividing the running state data sample of the automatic equipment into different characteristic data sets according to the vibration frequency, the processing efficiency, the abrasion degree and the failure rate parameter characteristics, wherein the matrix expression is as follows:
K= （1）
in the formula (1), the vibration frequency parameter characteristic data set isThe processing efficiency parameter characteristic data set is +.>The wear degree parameter characteristic data set is +.>The fault rate parameter characteristic data set is +.>The running state data trend prediction output function formula of the automation equipment at the time t+1 is as follows:
（2）
in the formula (2) of the present invention,for the trend of the operating state data of the automation device at time t+1,/->For the characteristic data of the vibration frequency parameter at time t, +.>For the processing efficiency parameter characteristic data at the moment t, +. >For the characteristic data of the wear degree parameter at the time t, +.>For the characteristic data of the fault rate parameter at the moment t, +.>For the characteristic data maximum value of the vibration frequency, the machining efficiency, the abrasion degree and the failure rate parameters at the moment t, +.>As a function of the maximum value.
In a specific embodiment, the supervised additive learning prediction algorithm is a neural network-based algorithm that can be used for abnormal state mining and prediction of the operational state data of the automated equipment. The algorithm utilizes superposition of a basic regression model and a residual regression model, and improves prediction accuracy by independently training the basic model and the residual model.
The specific implementation mode is as follows: preprocessing the collected device data, including data cleaning, outlier removal, missing value filling, and the like. The basic regression model is built by using a neural network algorithm, the model outputs the normal state of the operation of the automation equipment, the residual value of the basic regression model is used as an input variable to build a residual regression model, the model models the abnormal state, and the training of the residual regression model requires the use of data sets of the normal state and the abnormal state. And superposing the output of the basic regression model and the output of the residual regression model to form a cascade prediction model. The model may predict an abnormal state of the device. And verifying the cascade prediction model by using a verification set, and evaluating the prediction accuracy of the model. And updating and optimizing the model according to the verification result, and improving the prediction accuracy and robustness. The supervised superposition learning prediction algorithm can effectively solve the problems of abnormal state mining and prediction of the equipment running state data, and has higher precision and robustness. The effects are shown in Table 1.
Table 1 comparison statistics of prediction accuracy
As shown in table 1, the running state data trend of the automation equipment at time t+1 is predicted by adopting the formula (2), and the prediction accuracy is remarkably improved.
In the above embodiment, the adaptive policy optimization algorithm performs a dynamic optimization decision of a production process based on abnormal state mining and prediction results of operation state data of an automation device, where the adaptive policy optimization algorithm includes an input layer, a data layer, a model layer, an algorithm layer, an optimization layer and an output layer, and the working method of the adaptive policy optimization algorithm includes the following steps:
s1, inputting data, namely performing format conversion on abnormal state mining and prediction results of running state data of the automatic equipment, and inputting the abnormal state mining and prediction results into a data layer through an input layer;
s2, determining calculated targets and parameters, and acquiring calculation parameters and limiting conditions from input data through a data layer, wherein the calculation parameters and limiting conditions comprise requirements and targets of a production process, optimized indexes and targets, calculation scale, constraint conditions and feasible fields so as to ensure the rationality and effectiveness of a decision process, and the optimized indexes and targets comprise production efficiency, resource utilization rate and product quality;
S3, establishing a dynamic optimization decision model of the production process, wherein the model layer establishes a dynamic optimization decision mathematical model of the production process according to the requirements and targets of the production process, the optimized indexes and targets, the calculation scale, the constraint conditions and the feasible region, and sets a dynamic optimization decision objective function of the production process;
s4, solving a dynamic optimization decision objective function in the production process, wherein the self-adaptive strategy optimization algorithm adopts an algorithm layer to carry out iterative computation, parameter correction and comparison between a computation result and a true value, and optimizes the computation speed by maintaining a neighbor list of a computation node;
s5, carrying out fine control and optimization on the solving process, merging or splitting the measurement units by an optimization layer, setting a threshold value and iteration times in a self-adaptive parameter selection mode, and distributing calculation tasks to a plurality of processors or calculation nodes by the optimization layer in a parallel calculation mode so as to improve the calculation speed;
s6, outputting results, namely outputting the data results of the operation of the automation equipment through an output layer.
In a specific embodiment, the adaptive strategy optimization algorithm determines optimized indexes and targets according to the requirements and targets of the production process, including production efficiency, resource utilization rate, product quality and the like. And collecting data of each node in the production process, including equipment state, product quality, production process parameters, energy consumption and the like. And carrying out preprocessing operations such as denoising, normalization and the like on the data so as to facilitate subsequent analysis and modeling. And selecting a proper self-adaptive strategy optimization algorithm, such as a genetic algorithm, an ant colony algorithm, a simulated annealing algorithm and the like, according to the data characteristics, the optimization targets, the feasible domains and other factors. The algorithm should have the ability to adaptively adjust the strategy and be interpretable while taking into account the complexity and performance of the algorithm. According to the algorithm requirement, setting optimization parameters including population size, iteration times, crossing rate, variation rate and the like. And the collected data set is used for training an algorithm, and is verified and tested, so that the accuracy and reliability of the algorithm are ensured. And further optimizing parameters and structures of the algorithm according to the result of the training algorithm to improve the performance and efficiency of the algorithm and adapt to the change and the requirement in the actual production process. And deploying the trained and tested algorithm into the production process, performing real-time monitoring and control, and realizing dynamic optimization decision of the production process.
The self-adaptive strategy optimization algorithm is established, so that the problem that the traditional fixed strategy is difficult to adapt to the change of the production process and special conditions can be solved, and more efficient and accurate production process control can be realized. At the same time, the algorithm should be improved and optimized according to the actual production process conditions and requirements. The effects are shown in Table 2.
Table 2 effect comparison statistics table
As can be seen from Table 2, the adaptive strategy optimization algorithm is established, which can solve the problem that the conventional fixed strategy is difficult to adapt to the change and special conditions of the production process, and can realize more efficient and accurate production process control.
In the above embodiment, the depth-associated priority matching algorithm includes the following steps:
step 1, setting association priority of training feature quantity, counting the value of each feature quantity in a training data set, scanning the whole data set to determine the support degree of each feature quantity and the influence degree on the operation state of a production task and equipment, quantifying the association degree and direction between each feature quantity and a target production task by using Pearson correlation coefficient, and carrying out weight distribution according to the quantification result;
step 2, extracting characteristics of real-time monitoring of running state data and production process data information of the automatic equipment, and converting the information characteristics into characteristic vector representations, wherein the information characteristics comprise production task types, production quantity, production period, equipment requirements, equipment load conditions and process parameters;
Step 3, carrying out association matching on the training characteristic quantity and the real-time monitoring characteristic quantity, calculating the similarity between the training characteristic quantity and the real-time monitoring characteristic quantity, selecting the characteristic quantity with the highest similarity as a candidate matching point, and sequencing according to the association priority of the set training characteristic quantity;
step 4, adjusting and optimizing the matching points, taking the correct matching points as new reference points through continuous iteration, carrying out feature matching and association operation again so as to find new correct matching points, deleting incorrect matching points and adjusting matching priorities;
and 5, outputting the sequencing result.
In a specific embodiment, when the intelligent sorting of the production tasks is performed by embedding the depth-associated priority matching algorithm, information features (production task types, production quantity, production period, equipment requirements, equipment load conditions, process parameters and the like) of all the production tasks are converted into vector representations, and similarity of each production task and the feature vector is calculated by utilizing the depth-associated priority matching algorithm, so that the score (or weight) of each production task is obtained. And sequencing all the production tasks from large to small according to the scores to obtain intelligent sequencing results of the production tasks. And transmitting the intelligent sequencing result of the tasks to a process scheduling module, and optimizing and adjusting the process scheduling according to the intelligent sequencing result of each task.
In the process of optimizing and adjusting the process schedule, the following measures can be adopted:
1. and (3) reasonably planning and distributing the equipment according to the intelligent sequencing result of the production task, so that the equipment utilization rate and the production efficiency are maximized, and meanwhile, the reliability and the stability of the equipment are ensured.
2. And optimizing and adjusting the technological parameters according to the intelligent sequencing result of the production tasks, so that the quality and the technological efficiency of the production tasks are optimally balanced.
3. According to the intelligent sequencing result of the production tasks, priority adjustment and task withdrawal are carried out, so that urgent tasks and lagging tasks caused by faults, insufficient materials and the like are timely solved, and the controllability and stability of the production plan are improved.
4. And tracking and monitoring the task progress according to the intelligent sequencing result of the production tasks, and timely adjusting and coordinating the production plan, so that the production tasks can be delivered on time, and the customer satisfaction is improved.
The intelligent sorting of the production tasks is carried out by embedding the depth-associated priority matching algorithm, and the process scheduling is carried out according to the sorting result, so that the automation and the intellectualization in the production process can be realized, the production efficiency and the quality are improved, and the production cost and the resource waste are reduced. The effects are shown in Table 3.
Table 3 effect comparison statistics
As shown in Table 3, the intelligent sorting of the production tasks is performed by embedding the depth-associated priority matching algorithm, and the process scheduling is performed according to the sorting result, so that the automation and the intellectualization in the production process can be realized, and the production efficiency and the quality can be improved.
In the above embodiment, the similarity refinement comparison algorithm calculates the similarity of the production task by comparing the process parameters, the process steps, and the equipment states of the production task, and calculates the threshold based on the similarity of the historical production task, where the process parameters, the process steps, and the equipment states of the production task in the period a are respectively，/>Process parameter data set for A production task, < >>Process step data set for A production task, < >>Process parameters, process steps and equipment shape for a production task of section BThe state data sets are +.>，/>Process parameter data set for production task B, < >>Process step data set for production task B, < >>For the equipment state data set of the production task B, the similarity output function formula of the production tasks A and B is as follows:
（3）
in the formula (3) of the present invention,similarity of production tasks for A and B, < >>Weighting coefficients for the similarity of process parameters of a production task, < > >Weighting coefficients for the similarity of process steps of a production task, < >>Device state weighting factor of production task, +.>For the maximum value of the process parameters of the A production task, +.>Maximum value of the process parameter for the production task B, +.>Process parameters for A production task，/>For the process parameters of the B production task, +.>For the maximum value of the process steps of the production task a,maximum value of the process steps for the production task B, +.>For the process step of the A production task, +.>For the process step of the B production task, +.>For the device state maximum of the A production task, +.>Maximum device state for the B production task, +.>For the device state of the A production task, +.>For the device state of the B production task, the historical production task similarity dataset is s= =>，/>m, the similarity threshold output function formula is:
（4）
in the formula (4) of the present invention,for similarity threshold, ++>As an auxiliary value, +.>Weighting value for similarity threshold value, < >>Maximum similarity, +_A->Is the minimum value of similarity->Is the j-th similarity.
In a specific embodiment, an intelligent dynamic optimization and process scheduling system of the automation equipment calculates the similarity of production tasks by adopting a similarity refinement comparison algorithm, and judges whether different tasks can be combined and executed. Firstly, processing the original data, ensuring the accuracy and consistency of the data, and simultaneously extracting useful data characteristics such as process parameters, process steps, equipment states and the like of production tasks. And then calculating the similarity between different production tasks by adopting a similarity calculation algorithm. Common similarity calculation algorithms include cosine similarity, euclidean distance, pearson similarity, and the like. And setting a similarity threshold according to actual production requirements, and setting a proper similarity threshold for judging whether different tasks can be combined and executed. This can avoid production task merge mistake, improves production efficiency. And merging the production tasks with the similarity larger than the threshold value. The similarity index calculated based on the similarity refinement comparison algorithm can be used for carrying out accurate matching on production tasks, and accuracy and efficiency of task merging are improved.
The system adopts a deep learning technology to carry out model learning, and combines a deep association priority matching algorithm and a GPU acceleration technology to realize intelligent dynamic optimization and process scheduling of the automation equipment. Compared with the traditional dynamic optimization scheme, the system has the advantages of high calculation speed, accurate task merging, high resource utilization rate and the like, can remarkably improve the production efficiency, and brings considerable economic benefit for enterprises. The calculation results of the formulas (3) and (4) are adopted to judge the similarity of the production task and the comparison statistics of the manual judgment result are shown in the table 4;
table 4 results vs. statistics table
As can be seen from table 4, the calculation results of formulas (3) and (4) are adopted to determine that the similarity of the production task is substantially the same as that of the manual determination result, and when the calculation result is approximately close to the threshold value, a misjudgment may be caused to prove the availability of the algorithm.
In the above embodiment, the intelligent control module generates the control decision instruction by using the STM32 microcontroller, adjusts the state and parameters of the production equipment through the motor driver and the electromagnetic valve, and realizes automatic control and adjustment of the production process, and the STM32 microcontroller remotely controls the production process through the high-speed communication network.
In a particular embodiment, the STM32 microcontroller receives output information from the dynamic optimization module and the process scheduling module, including operational state data, optimization decision results, production task instructions, and the like. Based on the received information, the STM32 microcontroller performs algorithm calculation and logic judgment to generate a corresponding control decision instruction. The STM32 microcontroller sends the generated control decision instruction to the motor driver, the electromagnetic valve and other executing mechanisms so as to adjust the state and parameters of the production equipment. Through the connection with motor driver and solenoid valve, STM32 microcontroller realizes the automatic control and the adjustment to production facility. At the same time, the STM32 microcontroller communicates with a monitoring center or other remote terminal via a high-speed communications network (e.g., ethernet or wireless communications). And the remote control function is realized by carrying out data exchange and instruction transmission with the remote terminal through a remote communication protocol.
Summarizing, the intelligent control module generates a control decision instruction by utilizing the STM32 microcontroller, and realizes automatic control and adjustment of production equipment by being connected with executing mechanisms such as a motor driver, an electromagnetic valve and the like. Meanwhile, the remote control function is realized by remote communication with a monitoring center or other remote terminals through a high-speed communication network.
In the above embodiment, the high-speed communication network adopts the MQTT lightweight bottom layer protocol, the UDP transport layer protocol, the HTTP/2 secure transport protocol and the WebSocket bidirectional communication protocol to implement real-time data interaction between the client and the server, so as to reduce network communication delay, and distributes data to the transport nodes through the server load balancing logic and the message queue service, so as to implement rapid retransmission of node faults.
In particular embodiments, the MQTT protocol is used for communication between the device and the server. The protocol has the characteristics of low bandwidth and low power consumption, and is suitable for the scene of the Internet of things. Devices can exchange information with servers through both publish and subscribe modes. And carrying out data transmission by using the UDP protocol. UDP is a connectionless transport protocol with lower latency and less overhead than TCP. By using UDP, network communication delay can be reduced and real-time performance can be improved. HTTP/2 is adopted as an application layer protocol, and TLS/SSL encryption technology is combined to ensure the security of data. HTTP/2 has higher efficiency and better performance than HTTP version 1.X, providing better user experience in real-time data interactions. The WebSocket protocol is used to enable two-way communication between the client and the server. The WebSocket protocol allows the server to actively send data to the client and can maintain long connections, reducing the overhead of establishing new connections for each communication. And the client requests are scattered to a plurality of server nodes by using a load balancing technology, so that the reliability and expansibility of the system are improved. Meanwhile, the data are distributed and deployed to the transmission nodes by adopting the message queue service, so that the rapid retransmission of the nodes in case of failure is realized, and the reliability and stability of the data are ensured.
In summary, the high-speed communication network utilizes protocols of MQTT, UDP, HTTP/2, webSocket and the like to realize real-time data interaction between the client and the server, and improves the reliability and expansibility of the system and improves the data interaction speed through server load balancing logic and message queue service. The effects are shown in Table 5.
Table 5 speed comparison statistics
In the above embodiment, the visualized data platform QlikView acquires the related data of the mass data source based on the related data model to realize multidimensional data related analysis, and adopts an interactive chart, a heat point diagram, a map and an instrument board to realize real-time monitoring of trend, relationship and change rule of the data, and the visualized data platform QlikView adopts Token user identity verification mechanism to verify the identity of the accessing user so as to improve the security of information access.
In particular embodiments, the visualization data platform QlikView efficiently acquires, integrates, and analyzes heterogeneous data from different data sources by building a relational data model, and builds data visualization charts and reports for data analysis. QlikView supports data acquisition from various data sources, including relational databases, large data platforms, ERP, CRM, cloud data, and the like, and data extraction and integration are performed through data acquisition tools and interfaces. QlikView builds a data structure based on the relevance data model, builds the relation among all data sources according to the data characteristics, and builds a data model which can adapt to the service requirements. QlikView provides a multidimensional data analysis function to realize multi-angle and all-round analysis of data, thereby deeply mining the intrinsic value of the data. The user can monitor the data change and trend in real time by using various visualization tools such as interactive charts, dashboards, hot maps, maps and the like. QlikView uses Token user authentication mechanisms to generate a Token key for each user that the user needs to provide to authenticate the identity. The method can ensure the security of information by using the method for identity authentication.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (5)
1. An intelligent dynamic optimization and process scheduling system of automation equipment is characterized in that: the system comprises:
the on-line monitoring module is used for monitoring the running state data and the production process data of the automatic equipment in real time;
the data preprocessing module is used for preprocessing the monitoring data, and the data preprocessing module adopts a data preprocessing tool KNIE to carry out data cleaning, conversion, feature extraction and reconstruction;
the dynamic optimization module is used for dynamically optimizing the automatic equipment, the dynamic optimization module adopts a server CH225V3 to identify the collected running state data of the automatic equipment and dynamically optimizes the equipment, the server CH225V3 is embedded into a supervision and superposition learning prediction algorithm to carry out abnormal state mining and prediction on the running state data of the automatic equipment, and an adaptive strategy optimization algorithm is embedded into the abnormal state mining and prediction algorithm to realize the dynamic optimization decision of the production process;
The process scheduling module is used for planning, scheduling and coordinating the production process of the automation equipment, the process scheduling module adopts a processing accelerator GPU to accelerate the process scheduling, the processing accelerator GPU is embedded into a depth-related priority matching algorithm to intelligently sequence production tasks, the similarity refinement comparison algorithm is embedded to calculate the similarity of the production tasks, and the similarity of the production tasks is greater than a threshold value, and the process tasks are combined and executed;
the intelligent control module is used for automatically controlling and adjusting the production process according to the dynamic optimization decision of the production process and the intelligent sequencing of the production tasks;
the visual monitoring center is used for remotely monitoring intelligent dynamic optimization and process scheduling process information of the automation equipment, and the visual monitoring center realizes the monitoring of the intelligent dynamic optimization and process scheduling process through a visual data platform QlikView;
the output end of the on-line monitoring module is connected with the input end of the data preprocessing module, the output end of the data preprocessing module is connected with the input end of the dynamic optimizing module, the output end of the dynamic optimizing module is connected with the input end of the process scheduling module, the output end of the data preprocessing module is connected with the input end of the process scheduling module, the output end of the process scheduling module is connected with the input end of the intelligent control module, the output end of the dynamic optimizing module is connected with the input end of the intelligent control module, and the visual monitoring center works in the whole course;
The supervision superposition learning prediction algorithm performs abnormal state mining and prediction on the operation state data of the automation equipment according to the operation state data of the historical automation equipment and the operation state data of the real-time automation equipment, wherein the data set of the operation state data of the historical automation equipment and the operation state data of the real-time automation equipment is as followsT is the time of collecting the running state data of the automation equipment, kt is the data of the running state data t of the automation equipment, and the running state data sample of the automation equipment is divided into different characteristic data sets according to the vibration frequency, the processing efficiency, the abrasion degree and the failure rate parameter characteristics, wherein the matrix expression is as follows:
（1）
in the formula (1), the vibration frequency parameter characteristic data set isThe processing efficiency parameter characteristic data set is +.>The wear degree parameter characteristic data set is +.>The fault rate parameter characteristic data set is +.>The running state data trend prediction output function formula of the automation equipment at the time t+1 is as follows:
（2）
in the formula (2) of the present invention,for the trend of the operating state data of the automation device at time t+1,/->For the characteristic data of the vibration frequency parameter at time t, +.>For the processing efficiency parameter characteristic data at the moment t, +.>For the characteristic data of the wear degree parameter at the time t, +. >For the characteristic data of the fault rate parameter at the moment t, +.>For the characteristic data maximum value of the vibration frequency, the machining efficiency, the abrasion degree and the failure rate parameters at the moment t, +.>Is a maximum function;
the self-adaptive strategy optimization algorithm carries out dynamic optimization decision of the production process based on abnormal state mining and prediction results of running state data of the automatic equipment, the self-adaptive strategy optimization algorithm comprises an input layer, a data layer, a model layer, an algorithm layer, an optimization layer and an output layer, and the working method of the self-adaptive strategy optimization algorithm comprises the following steps:
s1, inputting data, namely performing format conversion on abnormal state mining and prediction results of running state data of the automatic equipment, and inputting the abnormal state mining and prediction results into a data layer through an input layer;
s2, determining calculated targets and parameters, and acquiring calculation parameters and limiting conditions from input data through a data layer, wherein the calculation parameters and limiting conditions comprise requirements and targets of a production process, optimized indexes and targets, calculation scale, constraint conditions and feasible fields so as to ensure the rationality and effectiveness of a decision process, and the optimized indexes and targets comprise production efficiency, resource utilization rate and product quality;
s3, establishing a dynamic optimization decision model of the production process, wherein the model layer establishes a dynamic optimization decision mathematical model of the production process according to the requirements and targets of the production process, the optimized indexes and targets, the calculation scale, the constraint conditions and the feasible region, and sets a dynamic optimization decision objective function of the production process;
S4, solving a dynamic optimization decision objective function in the production process, wherein the self-adaptive strategy optimization algorithm adopts an algorithm layer to carry out iterative computation, parameter correction and comparison between a computation result and a true value, and optimizes the computation speed by maintaining a neighbor list of a computation node;
s5, carrying out fine control and optimization on the solving process, merging or splitting the measurement units by an optimization layer, setting a threshold value and iteration times in a self-adaptive parameter selection mode, and distributing calculation tasks to a plurality of processors or calculation nodes by the optimization layer in a parallel calculation mode;
s6, outputting results, namely outputting data results of the operation of the automatic equipment through an output layer;
the depth-associated priority matching algorithm comprises the following steps:
step 1, setting association priority of training feature quantity, counting the value of each feature quantity in a training data set, scanning the whole data set to determine the support degree of each feature quantity and the influence degree on the operation state of a production task and equipment, quantifying the association degree and direction between each feature quantity and a target production task by using Pearson correlation coefficient, and carrying out weight distribution according to the quantification result;
step 2, extracting characteristics of real-time monitoring of running state data and production process data information of the automatic equipment, and converting the information characteristics into characteristic vector representations, wherein the information characteristics comprise production task types, production quantity, production period, equipment requirements, equipment load conditions and process parameters;
Step 3, carrying out association matching on the training characteristic quantity and the real-time monitoring characteristic quantity, calculating the similarity between the training characteristic quantity and the real-time monitoring characteristic quantity, selecting the characteristic quantity with the highest similarity as a candidate matching point, and sequencing according to the association priority of the set training characteristic quantity;
step 4, adjusting and optimizing the matching points, taking the correct matching points as new reference points through continuous iteration, carrying out feature matching and association operation again so as to find new correct matching points, deleting incorrect matching points and adjusting matching priorities;
step 5, outputting the sequencing result;
the similarity refinement comparison algorithm calculates the similarity of the production task by comparing the process parameters, the process steps and the equipment states of the production task, calculates the threshold value based on the similarity of the historical production task, and respectively sets the process parameters, the process steps and the equipment states of the production task of the section A as follows，/>Process parameter data set for A production task, < >>Process step data set for A production task, < >>The equipment state data set of the production task A is obtained, and the technological parameters, the technological steps and the equipment state data set of the production task B are respectively +. >，/>Process parameter data set for production task B, < >>Process step data set for production task B, < >>For the equipment state data set of the production task B, the similarity output function formula of the production tasks A and B is as follows:
（3）
in the formula (3) of the present invention,similarity of production tasks for A and B, < >>To produce the process parameter similarity weighting coefficients for the task,weighting coefficients for the similarity of process steps of a production task, < >>Device state weighting factor of production task, +.>For the maximum value of the process parameters of the A production task, +.>Maximum value of the process parameter for the production task B, +.>For the process parameters of the A production task, +.>For the process parameters of the B production task, +.>Maximum value of the process steps for the production task A, +.>Maximum value of the process steps for the production task B, +.>For the process step of the A production task, +.>For the process step of the B production task, +.>For the device state maximum of the A production task, +.>Maximum device state for the B production task, +.>For the device state of the A production task, +.>For the equipment state of the B production task, the historical production task phaseSimilarity dataset s=，/>m, the similarity threshold output function formula is:
（4）
in the formula (4) of the present invention,for similarity threshold, ++>As an auxiliary value, +. >Weighting value for similarity threshold value, < >>Maximum similarity, +_A->Is the minimum value of similarity->Is the j-th similarity.
2. An intelligent dynamic optimization and process scheduling system for an automation device according to claim 1, wherein: the on-line monitoring module monitors running state data of the automatic equipment in real time by adopting an acceleration sensor, a temperature sensor and a current sensor, monitors production process data in real time by adopting a visual sensor and an infrared sensor, wherein the running state data of the automatic equipment comprises vibration frequency, machining efficiency, wear degree and failure rate, and the production process data comprises process parameters and product quality.
3. An intelligent dynamic optimization and process scheduling system for an automation device according to claim 1, wherein: the intelligent control module generates a control decision instruction by adopting an STM32 microcontroller, adjusts the state and parameters of production equipment through a motor driver and an electromagnetic valve, realizes automatic control and adjusts the production process, and the STM32 microcontroller carries out remote control on the production process through a high-speed communication network.
4. An intelligent dynamic optimization and process scheduling system for an automation device according to claim 3, wherein: the high-speed communication network adopts an MQTT lightweight bottom layer protocol, a UDP transport layer protocol, an HTTP/2 secure transport protocol and a WebSocket bidirectional communication protocol to realize real-time data interaction between a client and a server so as to reduce network communication delay, and distributes data to a transmission node through server load balancing logic and message queue service so as to realize rapid retransmission of node faults.
5. An intelligent dynamic optimization and process scheduling system for an automation device according to claim 1, wherein: the visual data platform QlikView acquires mass data source associated data based on an associated data model to realize multidimensional data associated analysis, and adopts an interactive chart, a hot point diagram, a map and an instrument board to realize real-time monitoring of trend, relationship and change rule of data, and the visual data platform QlikView adopts a Token user identity verification mechanism to verify the identity of an access user so as to improve the safety of information access.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311359939.2A CN117114226B (en) | 2023-10-20 | 2023-10-20 | Intelligent dynamic optimization and process scheduling system of automation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311359939.2A CN117114226B (en) | 2023-10-20 | 2023-10-20 | Intelligent dynamic optimization and process scheduling system of automation equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117114226A CN117114226A (en) | 2023-11-24 |
| CN117114226B true CN117114226B (en) | 2024-01-30 |
Family
ID=88795015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311359939.2A Active CN117114226B (en) | 2023-10-20 | 2023-10-20 | Intelligent dynamic optimization and process scheduling system of automation equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114226B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247450A (en) * | 2017-05-05 | 2017-10-13 | 武汉理工大学 | Circuit breaker failure diagnostic method based on Bayesian network |
| CN113256066A (en) * | 2021-04-23 | 2021-08-13 | 新疆大学 | PCA-XGboost-IRF-based job shop real-time scheduling method |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN116586199A (en) * | 2023-07-17 | 2023-08-15 | 山东九曲圣基新型建材有限公司 | Flotation control system for gold tailing treatment |
| CN116599602A (en) * | 2023-07-18 | 2023-08-15 | 北京航天华腾科技有限公司 | Low-energy-consumption long-distance sonar communication system for ocean monitoring |
| CN116633978A (en) * | 2023-07-24 | 2023-08-22 | 珠水(广东)生态环境研究院有限公司 | Sewage treatment remote monitoring system based on Internet of things |
| CN116680459A (en) * | 2023-07-31 | 2023-09-01 | 长沙紫喇叭电子商务有限公司 | Foreign trade content data processing system based on AI technology |
| CN116709243A (en) * | 2023-08-07 | 2023-09-05 | 北京这房行信息技术有限公司 | Intelligent power exchange station system |
-
2023
- 2023-10-20 CN CN202311359939.2A patent/CN117114226B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247450A (en) * | 2017-05-05 | 2017-10-13 | 武汉理工大学 | Circuit breaker failure diagnostic method based on Bayesian network |
| CN113256066A (en) * | 2021-04-23 | 2021-08-13 | 新疆大学 | PCA-XGboost-IRF-based job shop real-time scheduling method |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN116586199A (en) * | 2023-07-17 | 2023-08-15 | 山东九曲圣基新型建材有限公司 | Flotation control system for gold tailing treatment |
| CN116599602A (en) * | 2023-07-18 | 2023-08-15 | 北京航天华腾科技有限公司 | Low-energy-consumption long-distance sonar communication system for ocean monitoring |
| CN116633978A (en) * | 2023-07-24 | 2023-08-22 | 珠水(广东)生态环境研究院有限公司 | Sewage treatment remote monitoring system based on Internet of things |
| CN116680459A (en) * | 2023-07-31 | 2023-09-01 | 长沙紫喇叭电子商务有限公司 | Foreign trade content data processing system based on AI technology |
| CN116709243A (en) * | 2023-08-07 | 2023-09-05 | 北京这房行信息技术有限公司 | Intelligent power exchange station system |
Non-Patent Citations (1)
| Title |
|---|
| 基于变结构神经网络控制的决策树预测算法;单冬红;吕琼帅;赵伟艇;;微电子学与计算机(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117114226A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11959653B2 (en) | Cloud and edge integrated energy optimizer | |
| US11036211B2 (en) | Orchestration of learning and execution of model predictive control tool for manufacturing processes | |
| CN107767022A (en) | A kind of Dynamic Job-shop Scheduling rule intelligent selecting method of creation data driving | |
| CN113222224A (en) | Real-time scheduling method for Internet of things workshop based on twin intelligent workpiece | |
| Xie et al. | FedKL: Tackling data heterogeneity in federated reinforcement learning by penalizing KL divergence | |
| CN110363355B (en) | Cloud-edge collaborative forecasting system and method for alumina production index | |
| CN117494032B (en) | Building energy consumption real-time monitoring control system and method | |
| CN113988627A (en) | Collaborative cloud production scheduling method and system based on deep reinforcement learning | |
| CN111258984A (en) | Product quality end-edge-cloud collaborative forecasting method under industrial big data environment | |
| Al-Aomar | A robust simulation-based multicriteria optimization methodology | |
| CN115129003A (en) | Automatic production line intelligent monitoring system based on self-learning time-varying digital twin | |
| CN117114226B (en) | Intelligent dynamic optimization and process scheduling system of automation equipment | |
| CN117240887B (en) | Wisdom thing networking energy management platform system | |
| CN113379135A (en) | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing | |
| CN117709617A (en) | MES-based intelligent scheduling system for production workshop | |
| CN116224791A (en) | Collaborative training control method for intelligent manufacturing collaborative robot edge system | |
| CN112596457B (en) | Intelligent control method and system for kitchen disposal, collection and transportation | |
| KR20210075358A (en) | Smart factory operation analysis system and method | |
| CN116822319A (en) | Industrial product manufacturing quality active prediction control method based on cloud edge cooperative computing | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| Luo et al. | Research on manufacturing productivity based on improved genetic algorithms under internet information technology | |
| CN110705914A (en) | Industrial electricity data processing system | |
| CN116594367B (en) | Cooking degree control system of sweet potato juice spiral precooking machine | |
| Yan | Adaptive scheduling of agricultural machinery equipment production lines for intelligent manufacturing | |
| CN117923331A (en) | Load control system and method based on crane hoisting |
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 |