CN117311283B - Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger - Google Patents
Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger Download PDFInfo
- Publication number
- CN117311283B CN117311283B CN202311380374.6A CN202311380374A CN117311283B CN 117311283 B CN117311283 B CN 117311283B CN 202311380374 A CN202311380374 A CN 202311380374A CN 117311283 B CN117311283 B CN 117311283B
- Authority
- CN
- China
- Prior art keywords
- task
- driving
- execution
- early warning
- workshop
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 50
- 239000013598 vector Substances 0.000 claims abstract description 17
- 230000004931 aggregating effect Effects 0.000 claims abstract description 9
- 238000012163 sequencing technique Methods 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 9
- 230000002776 aggregation Effects 0.000 claims description 7
- 238000004220 aggregation Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002699 waste material Substances 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] or 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] or 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of workshop traveling control monitoring, in particular to an intelligent workshop traveling control monitoring method and system for a preassembled body in a heat exchanger, wherein the method comprises the following steps: acquiring a task traveling vector; establishing a driving task queue, and grouping according to task travelling vectors; acquiring a driving execution task, and entering a driving task queue after corresponding grouping according to time sequence; aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set; acquiring motion parameter information of each driving execution task in a driving execution task set; building an early warning monitoring model, and inputting motion parameter information into the early warning monitoring model to obtain an early warning monitoring result; and adjusting the task scheduling of the workshop travelling crane according to the early warning monitoring result. According to the invention, through an independent control monitoring method and a corresponding system, the running operation flow is optimized, the efficiency and the safety of the installation and transportation of the heat exchanger preassembly are effectively improved, and the accident risk is reduced.
Description
Technical Field
The invention relates to the technical field of workshop traveling control monitoring, in particular to an intelligent workshop traveling control monitoring method and system for a preassembled body in a heat exchanger.
Background
The heat exchanger pre-assembly is a pre-assembled heat exchanger element, the components are pre-assembled in a workshop, and because the heat exchanger pre-assembly is quite large in size, the heat exchanger pre-assembly comprises a plurality of metal plates, tubes, sealing parts and other components, and accessories required for connecting a pipeline system are assembled, so that enough space is required for assembly, and the workshop running becomes necessary equipment for installation and transportation.
Then, due to structural differences among components of the preassembly of the heat exchanger, safety accidents can be caused by mutual influence and even collision among travelling cranes in transportation, and therefore, an independent control and monitoring method and a corresponding system are required to be designed for the travelling cranes in the installation workshop of the preassembly of the heat exchanger.
The information disclosed in this background section is only for enhancement of understanding of the general background of the disclosure and is not to be taken as an admission or any form of suggestion that this information forms the prior art that is well known to a person skilled in the art.
Disclosure of Invention
The invention provides a patent name, which can effectively solve the problems in the background technology.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the intelligent monitoring method for workshop running control of the preassembly body in the heat exchanger comprises the following steps:
distance measurement is carried out on the travelling rail, and a task travelling vector is obtained;
establishing a driving task queue, and grouping the driving task queue according to the task advancing vector;
acquiring a driving execution task, and entering the driving execution task into the driving task queue after corresponding grouping according to time sequence;
aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set;
acquiring motion parameter information of each driving execution task in the driving execution task set;
building an early warning monitoring model, and inputting the motion parameter information into the early warning monitoring model to obtain an early warning monitoring result;
and adjusting the task scheduling of the workshop traveling crane according to the early warning monitoring result.
Further, predicting the task execution time length includes:
acquiring execution time of various tasks in the workshop driving history execution task, and acquiring time length information of the history task;
extracting the characteristics of the task attributes of the historical execution task to obtain a task characteristic set;
constructing a time length prediction model according to the historical task time length information and the task feature set;
and predicting the task execution time length through the time length prediction model.
Further, extracting features of task attributes of the history execution task includes:
dividing task attributes of the history execution task into continuous information and discrete information;
carrying out box division processing on the continuous information, dividing continuous data into discrete intervals, and converting the discrete intervals into discrete data to obtain continuous characteristic information;
performing feature processing on the discrete information set by using the single-heat coding, and converting the discrete features into binary features to obtain discrete feature information;
and combining the continuous characteristic information and the discrete characteristic information into a task characteristic set.
Further, after the discrete characteristic information is obtained, dimension reduction processing is performed on the discrete characteristic information.
Further, aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set, including:
respectively distributing execution task weights for the driving execution tasks according to the time sequence, the emergency degree and the importance of the driving execution tasks;
dividing the task execution time length, and assigning the driving execution tasks according to the divided task execution time length to obtain a plurality of driving execution task groups;
calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a sum of weights for establishing task time sequence, emergency degree and importance;
sequencing the weighted sum of each driving executing task in each group to obtain a weighted sum sequencing result;
sequencing the plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
and determining the priority order of the driving execution tasks according to the weighted sum sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set.
Further, constructing an early warning monitoring model, including:
acquiring a historical motion parameter information set of the workshop travelling crane, wherein the historical motion parameter information set comprises sensor data and corresponding timestamp information;
extracting the characteristics of the historical motion parameter information set to obtain a historical motion parameter information characteristic set;
based on the neural network model, a proper loss function and an optimization algorithm are selected to construct an early warning monitoring model.
Further, preprocessing the historical motion parameter information set, and calculating the related motion parameters of the workshop traveling crane through sensor data.
Further, training and evaluating the constructed early warning and monitoring model comprises the following steps:
dividing the historical motion parameter information set into a training set and a testing set;
training the early warning monitoring model by using the training set, and minimizing a loss function by using an optimization algorithm to obtain early warning monitoring model parameters;
and evaluating the early warning monitoring model by using the test set, wherein the performance evaluation index comprises the following steps: the mean square error, the accuracy and the recall rate are used for obtaining the performance evaluation result of the early warning monitoring model;
and according to the performance evaluation result, carrying out parameter adjustment and algorithm optimization on the early warning monitoring model.
Workshop running control intelligent monitoring system of heat exchanger inside preassembly body, the system includes:
and a ranging module: the distance measurement device is used for measuring distance of the driving track and obtaining a task traveling vector;
task queue establishment module: the method comprises the steps of establishing a driving task queue, and grouping the driving task queue according to the task advancing vector;
the task acquisition module is used for: the driving task queue is used for acquiring driving execution tasks, and enabling the driving execution tasks to enter the driving task queues after corresponding grouping according to time sequence;
task aggregation module: the method comprises the steps of aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set;
the motion parameter acquisition module: the motion parameter information is used for acquiring motion parameter information of each driving execution task in the driving execution task set;
early warning monitoring module: the method comprises the steps of constructing an early warning monitoring model, inputting the motion parameter information into the early warning monitoring model, and obtaining an early warning monitoring result;
task scheduling module: and adjusting the task scheduling of the workshop traveling crane according to the early warning monitoring result.
Further, the task aggregation module includes:
task weight assignment unit: respectively distributing execution task weights for the driving execution tasks according to the time sequence, the emergency degree and the importance of the driving execution tasks;
task assigning unit: dividing the task execution time length, and assigning the driving execution tasks according to the divided task execution time length to obtain a plurality of driving execution task groups;
task weight calculation unit: calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a sum of weights for establishing task time sequence, emergency degree and importance;
task ordering unit: sequencing the weighted sum of each driving executing task in each group to obtain a weighted sum sequencing result; sequencing the plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
a priority order determination unit: and determining the priority order of the driving execution tasks according to the weighted sum sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set.
By the technical scheme of the invention, the following technical effects can be realized:
according to the invention, the running vehicle in the installation workshop is monitored and regulated in real time through the independent control monitoring method and the corresponding system, so that the running vehicle operation flow is optimized, the efficiency and the safety of the installation and transportation of the preassembled body of the heat exchanger are effectively improved, and the accident risk is reduced.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent monitoring method for workshop running control of a preassembly body in a heat exchanger;
FIG. 2 is a flow chart of predicting task execution time;
FIG. 3 is a flow chart of feature extraction of task attributes of a historically performed task;
FIG. 4 is a schematic flow chart of obtaining a driving execution task set;
FIG. 5 is a schematic flow chart of the construction of the early warning monitoring model;
FIG. 6 is a schematic flow chart of training and evaluating the construction of an early warning monitoring model;
FIG. 7 is a schematic diagram of a shop front control intelligent monitoring system of a pre-assembled body inside a heat exchanger;
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.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
As shown in fig. 1, the intelligent monitoring method for workshop running control of the preassembly body in the heat exchanger comprises the following steps:
s100: distance measurement is carried out on the travelling rail, and a task travelling vector is obtained;
s200: establishing a driving task queue, and grouping the driving task queue according to task travelling vectors;
specifically, the distance measurement is a process of measuring the distance between two objects by using different sensors or technologies, the main purpose of the distance measurement in the step is to determine the position of a traveling crane relative to a traveling track, the track path length of the traveling crane and the movement direction of traveling crane work, the traveling crane track can be measured by a laser distance meter, an ultrasonic sensor and other methods, and a task traveling vector is obtained according to the measurement result, wherein the task traveling vector comprises the traveling direction of a working task of the traveling crane and the track distance travelled by the working task; because a plurality of traveling cranes need to simultaneously execute different tasks on the heat exchanger inner preassembly body in one workshop, or the track directions are different, or the traveling cranes carrying the heat exchanger preassembly body collide with each other in the past, the task execution efficiency is low, and therefore, the traveling crane task queues need to be divided into different groups, for example, the traveling crane task queues are divided into east and west directions, and then the traveling cranes can execute the same batch of tasks first in the same direction without frequently changing the directions, thereby not only improving the efficiency, but also reducing the accident risk.
S300: acquiring a driving execution task, and entering the driving execution task into a driving task queue after corresponding grouping according to time sequence;
s400: aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set;
specifically, after the running task queues established in step S200 initialize and group the running queues, task carrying information to be executed by the running is obtained, and the running execution tasks are entered into the running task queues in the corresponding directions according to the time established by the tasks, so that the running of the tasks can be orderly grouped and arranged, and the stability and predictability of the task execution queues are ensured; the reason that the running execution tasks in the same group are aggregated according to the task execution time length is that the running execution time length is long or short, meanwhile, the running tasks in the aggregation time length can be executed, the utilization rate of the running track can be effectively improved, time and resources are prevented from being wasted, the running track can further execute a plurality of tasks in similar time, the time and resource waste is effectively reduced, and the running work efficiency and effect are improved.
S500: acquiring motion parameter information of each driving execution task in a driving execution task set;
specifically, firstly, a proper sensor is installed on a workshop crane, the acquisition frequency is determined, after the workshop crane is ensured to normally operate, the sensor is used for acquiring the motion parameter information of each crane execution task in a crane execution task set, including the speed, acceleration, position and other information of the crane, and the corresponding timestamp information is recorded, so that the real-time state of the workshop crane is known, and the monitoring, safety guarantee and task scheduling requirements of the crane motion process are facilitated.
S600: building an early warning monitoring model, and inputting motion parameter information into the early warning monitoring model to obtain an early warning monitoring result;
s700: and adjusting the task scheduling of the workshop travelling crane according to the early warning monitoring result.
Firstly, a proper machine learning algorithm or a deep learning model is selected to construct an early warning monitoring model, the common method comprises decision trees, support vector machines, neural networks, random forests and the like, whether abnormal conditions exist in the workshop traveling crane in the operation process can be accurately predicted through the early warning monitoring model, task scheduling of the workshop traveling crane is adjusted according to monitoring results, automatic monitoring and processing of the abnormal conditions in the workshop traveling crane process can be achieved, the abnormal conditions can be effectively processed on the premise of ensuring the operation safety and efficiency of the workshop through timely adjustment, and potential danger or loss is avoided.
According to the technical scheme, the running vehicle in the installation workshop is monitored and regulated in real time by the independent control monitoring method and the corresponding system, so that the running vehicle operation flow is optimized, the efficiency and the safety of the installation and transportation of the heat exchanger preassembly are effectively improved, and the accident risk is reduced.
Further, as shown in fig. 2, predicting the task execution time length includes:
s410: acquiring execution time of various tasks in the workshop driving history execution task, and acquiring time length information of the history task;
s420: extracting the characteristics of task attributes of the history execution task to obtain a task characteristic set;
in the implementation process, firstly, the execution time data of the historical execution task can be obtained from a workshop travelling system or a related record, then the task attribute data of the historical execution task, including parameter information such as task type, cargo weight, start-stop position and the like, is obtained, and a proper feature extraction method is selected to perform feature extraction on the task attribute data of the historical execution task, including classification features, correlation coefficient analysis, chi-square test and other methods, and the features can help understand the influence of the task attribute on the execution time, for example, the internal preassembly of the heat exchanger of the same kind is used as a feature extraction, or the same working time, the same track direction and the same path enable the subsequent time length prediction model to learn the historical time length more accurately, promote the subsequent prediction and simulation capability of the model, and the obtained task feature set can be used for subsequent task prediction and decision.
S430: constructing a time length prediction model according to the historical task time length information and the task feature set;
s440: and predicting the task execution time length through a time length prediction model.
Specifically, one model can be selected from models such as a regression model, a convolutional neural network and a support vector machine to serve as a task execution time length prediction model, historical task time length information and task feature sets are used for providing deep learning for the model, the model can be trained and evaluated after the time length prediction model is built, the model can accurately predict the historical task time length, and the model can be applied to prediction of the task execution time length after expected performance and generalization capability are achieved.
Further, as shown in fig. 3, feature extraction is performed on task attributes of the historically performed tasks, including:
s421: dividing task attributes of the history execution task into continuous information and discrete information;
s422: carrying out box division processing on continuous information, dividing continuous data into discrete intervals, and converting the discrete intervals into discrete data to obtain continuous characteristic information;
s423: performing feature processing on the discrete information set by using the independent thermal coding, and converting the discrete features into binary features to obtain discrete feature information;
s424: and combining the continuous characteristic information and the discrete characteristic information into a task characteristic set.
In this embodiment, the task attribute is divided to extract task information from the original data to form a suitable feature set, so that the task attribute of the history execution task can be divided into continuous information and discrete information, however, the continuous information and the discrete information have different characteristics and numerical types, different feature processing methods are required to be adopted to divide the task attribute, corresponding processing modes are also convenient to be adopted for different types of task attributes, an equidistant binning or equal frequency binning method can be adopted for the continuous information to perform binning processing, the continuous data is divided into a plurality of discrete intervals, so that the data is easier to process, and after the binning processing, the continuous features can be converted into discrete features; and the discrete type information can be subjected to feature processing in a single-heat encoding mode, each discrete value is encoded, a single-heat encoded binary feature vector is constructed, wherein only the position corresponding to the value is 1, the other positions are all 0, the discrete type features in the original data are replaced by the single-heat encoded binary features, the discrete type feature information is obtained, and finally the continuous type feature information and the discrete type feature information are combined to obtain a final task feature set, so that the construction of a model for accurately predicting the task time length is facilitated.
Further, after the discrete feature information is obtained, the discrete feature information is subjected to dimension reduction processing.
As a preference of the above embodiment, the feature processing of discrete information using the single thermal encoding may result in a high-dimensional dataset, and feature dimension reduction techniques such as principal component analysis and linear discriminant analysis are required to reduce the dimension of the data, reduce the number of features, simplify the complexity of the model, and facilitate better understanding and interpretation of the data, and it should be noted that when performing dimension reduction processing, excessive dimension reduction is also avoided to cause information loss and performance degradation of the model.
Further, as shown in fig. 4, aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set, including:
s401: according to the time sequence, emergency degree and importance of the running execution tasks, the running execution tasks are respectively allocated with execution task weights;
the time sequence of the established tasks in the step reflects the sequence of the tasks, the emergency degree of the tasks represents the degree of the tasks needing to be processed as soon as possible, the importance of the tasks represents the criticality of the tasks to the system or the service, the weight is allocated for the three factors, and different aspects of the tasks can be comprehensively considered so as to better schedule and process the tasks, but before the weight coefficient is allocated, the tasks are required to be normalized by using methods such as linear scaling, standardization and the like, and the value ranges of different attributes are mapped to the same interval, so that the tasks are comparable.
S402: dividing the task execution time length, and assigning running execution tasks according to the divided task execution time length to obtain a plurality of running execution task groups;
specifically, the task execution time length is firstly divided according to a fixed time period, and then the tasks with the task execution time within different time periods are distributed into corresponding driving execution task groups, so that a basis is provided for determining the execution sequence and the priority of the tasks subsequently.
S403: calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a weighted sum for establishing task time sequence, emergency degree and importance;
s404: sequencing the weighted sum of each driving execution task in each group to obtain a weighted sum sequencing result;
s405: sequencing a plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
s406: and determining the priority order of the driving execution tasks according to the weighted sum sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set.
On the basis of the above embodiment, the priority order of the running execution tasks may be determined by a method of assigning weights and sorting, in which a weight coefficient has been assigned to each task and a running execution task group has been established, the weighted sum of each running execution task may be calculated by adding the weight coefficients that establish the time order, the degree of urgency, and the importance of the tasks, and then the weighted sum of each running execution task in each group is sorted in descending order, so as to obtain the priority order of the running execution tasks in each group; and selecting the shortest job scheduling algorithm to order the plurality of running execution task groups, so that waiting time of the running execution task groups can be reduced, and because the shortest job scheduling algorithm is a method for selecting the task with the shortest execution time to be processed first, the running execution task groups with shorter time can be executed preferentially, the running execution task groups with longer time can be executed after each other, thus obtaining the execution priority of the plurality of running execution task groups, and finally, the priority of the running execution task groups can be obtained by combining the priority of the running execution tasks in each group, and the running execution task set can be obtained.
Further, as shown in fig. 5, constructing an early warning monitoring model includes:
s610: acquiring a historical motion parameter information set of a workshop travelling crane, wherein the historical motion parameter information set comprises sensor data and corresponding timestamp information;
s620: extracting features of the historical motion parameter information set to obtain a historical motion parameter information feature set;
s630: based on the neural network model, a proper loss function and an optimization algorithm are selected to construct an early warning monitoring model.
Specifically, the vehicle driving recording system and the sensor log file can be consulted, the stored sensor data and the corresponding timestamp information including speed, acceleration, displacement and the like are obtained, accurate timestamp information is required to be ensured for each data point so as to carry out subsequent analysis and processing, then the historical motion parameter information set is subjected to feature extraction through a feature extraction method of basic statistical features, frequency domain features, time domain features and the like to obtain the historical motion parameter information feature set capable of representing motion parameter information, then a proper neural network architecture is required to be selected as an early warning monitoring model, such as a deep neural network, a convolutional neural network, a cyclic neural network and the like, a proper loss function and an optimization algorithm are selected for the model, and the model is trained and evaluated by utilizing the historical motion parameter information feature set so that the model can accurately predict abnormal conditions in the driving process.
Further, the historical motion parameter information set is preprocessed, and then the relevant motion parameters of the workshop traveling crane are calculated through sensor data.
Before feature extraction, a certain preprocessing is usually required to be performed on the data, including steps of data cleaning, data normalization, data smoothing and the like, so as to ensure the quality and usability of the data, and after the data preprocessing is completed, corresponding features including various mathematical and statistical techniques, such as calculation of statistical indexes, transformation and the like, can be calculated according to the requirements and the selected feature extraction method, so as to provide preparation for subsequent model training and analysis.
Further, as shown in fig. 6, training and evaluating the early warning monitoring model includes:
s631: dividing the historical motion parameter information set into a training set and a testing set;
s632: training the early warning monitoring model by using a training set, and minimizing a loss function by using an optimization algorithm to obtain parameters of the early warning monitoring model;
s633: evaluating the early warning monitoring model by using a test set, wherein the performance evaluation index comprises: the mean square error, the accuracy and the recall rate are used for obtaining the performance evaluation result of the early warning monitoring model;
s634: and according to the performance evaluation result, carrying out parameter adjustment and algorithm optimization on the early warning monitoring model.
The method comprises the steps of establishing an early warning monitoring model by adopting a deep learning algorithm, dividing historical data into a training set and a testing set, training the early warning monitoring model by using the training set to improve the accuracy and generalization capability of the model, inputting the characteristics of the training set into the model to obtain a training set prediction result, comparing the training set prediction result with a real label of the training set, calculating a loss function through functions such as a cross entropy loss function, a mean square error loss function and the like, and then selecting a proper optimization algorithm such as a gradient descent method, adam and the like to adjust parameters of the training set to minimize defined loss functions; and (3) evaluating and verifying the trained model by using the test set, wherein the characteristics of the test set are input into the trained early warning monitoring model to obtain a test set prediction result, calculating the performance index of the model according to the real label of the test set and the test set prediction result, further obtaining the evaluation result of the model, and adjusting further parameters and optimizing the algorithm of the model according to the performance evaluation result until the expected performance index is reached.
Embodiment two:
as shown in fig. 7, the intelligent monitoring system for workshop running control of the preassembly body in the heat exchanger comprises:
and a ranging module: the distance measurement device is used for measuring distance of the driving track and obtaining a task traveling vector;
task queue establishment module: the method comprises the steps of establishing a driving task queue, and grouping the driving task queue according to task traveling vectors;
the task acquisition module is used for: the system comprises a driving task queue, a driving task queue and a driving task processing unit, wherein the driving task queue is used for acquiring driving execution tasks, and the driving execution tasks enter the driving task queue after corresponding grouping according to time sequence;
task aggregation module: the method comprises the steps of aggregating driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set;
the motion parameter acquisition module: the motion parameter information is used for acquiring motion parameter information of each driving execution task in the driving execution task set;
early warning monitoring module: the method comprises the steps of constructing an early warning monitoring model, inputting motion parameter information into the early warning monitoring model, and obtaining an early warning monitoring result;
task scheduling module: and adjusting the task scheduling of the workshop travelling crane according to the early warning monitoring result.
The adjusting system can effectively realize the intelligent monitoring method for workshop running control of the preassembly body in the heat exchanger, and has the technical effects as described in the embodiment, and the detailed description is omitted.
Further, the task aggregation module includes:
task weight assignment unit: according to the time sequence, emergency degree and importance of the running execution tasks, the running execution tasks are respectively allocated with execution task weights;
task assigning unit: dividing the task execution time length, and assigning running execution tasks according to the divided task execution time length to obtain a plurality of running execution task groups;
task weight calculation unit: calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a weighted sum for establishing task time sequence, emergency degree and importance;
task ordering unit: sequencing the weighted sum of each driving execution task in each group to obtain a weighted sum sequencing result; sequencing a plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
a priority order determination unit: and determining the priority order of the driving execution tasks according to the weighted sum sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set.
Similarly, the above-mentioned optimization schemes of the system may also respectively correspond to the optimization effects corresponding to the methods in the first embodiment, which are not described herein again.
Although the present application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary illustrations of the application as defined in the appended claims and are to be construed as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (8)
1. The intelligent monitoring method for workshop running control of the preassembly body in the heat exchanger is characterized by comprising the following steps of:
distance measurement is carried out on the travelling rail, and a task travelling vector is obtained;
establishing a driving task queue, and grouping the driving task queue according to the task advancing vector;
acquiring a driving execution task, and entering the driving execution task into the driving task queue after corresponding grouping according to time sequence;
aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set, wherein the method comprises the following steps:
respectively distributing execution task weights for the driving execution tasks according to the time sequence, the emergency degree and the importance of the driving execution tasks;
dividing the task execution time length, and assigning the driving execution tasks according to the divided task execution time length to obtain a plurality of driving execution task groups;
calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a sum of weights for establishing task time sequence, emergency degree and importance;
sequencing the weighted sum of each driving executing task in each group to obtain a weighted sum sequencing result;
sequencing the plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
determining the priority order of the driving execution tasks according to the weighting and sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set;
acquiring motion parameter information of each driving execution task in the driving execution task set;
building an early warning monitoring model, and inputting the motion parameter information into the early warning monitoring model to obtain an early warning monitoring result;
and adjusting the task scheduling of the workshop traveling crane according to the early warning monitoring result.
2. The intelligent monitoring method for shop front truck control of a pre-assembly inside a heat exchanger according to claim 1, wherein predicting the task execution time length comprises:
acquiring execution time of various tasks in the workshop driving history execution task, and acquiring time length information of the history task;
extracting the characteristics of the task attributes of the historical execution task to obtain a task characteristic set;
constructing a time length prediction model according to the historical task time length information and the task feature set;
and predicting the task execution time length through the time length prediction model.
3. The intelligent monitoring method for workshop running control of a pre-assembly in a heat exchanger according to claim 2, wherein the feature extraction of the task attribute of the history execution task comprises:
dividing task attributes of the history execution task into continuous information and discrete information;
carrying out box division processing on the continuous information, dividing continuous data into discrete intervals, and converting the discrete intervals into discrete data to obtain continuous characteristic information;
performing feature processing on the discrete information set by using the single-heat coding, and converting the discrete features into binary features to obtain discrete feature information;
and combining the continuous characteristic information and the discrete characteristic information into a task characteristic set.
4. The intelligent monitoring method for workshop running control of a pre-assembly in a heat exchanger according to claim 3, wherein after the discrete characteristic information is obtained, dimension reduction processing is performed on the discrete characteristic information.
5. The intelligent monitoring method for workshop running control of a preassembly in a heat exchanger according to claim 1, wherein the constructing an early warning monitoring model comprises:
acquiring a historical motion parameter information set of the workshop travelling crane, wherein the historical motion parameter information set comprises sensor data and corresponding timestamp information;
extracting the characteristics of the historical motion parameter information set to obtain a historical motion parameter information characteristic set;
based on the neural network model, a proper loss function and an optimization algorithm are selected to construct an early warning monitoring model.
6. The intelligent monitoring method for controlling the driving of the workshop of the preassembly body in the heat exchanger according to claim 5, wherein the intelligent monitoring method comprises the steps of preprocessing the historical motion parameter information set and calculating the related motion parameters of the driving of the workshop through sensor data.
7. The intelligent monitoring method for shop front truck control of a pre-assembly inside a heat exchanger according to claim 5, further comprising training and evaluating the constructed pre-warning and monitoring model, comprising:
dividing the historical motion parameter information set into a training set and a testing set;
training the early warning monitoring model by using the training set, and minimizing a loss function by using an optimization algorithm to obtain early warning monitoring model parameters;
and evaluating the early warning monitoring model by using the test set, wherein the performance evaluation index comprises the following steps: the mean square error, the accuracy and the recall rate are used for obtaining the performance evaluation result of the early warning monitoring model;
and according to the performance evaluation result, carrying out parameter adjustment and algorithm optimization on the early warning monitoring model.
8. Workshop running control intelligent monitoring system of heat exchanger inside preassembly body, its characterized in that, the system includes:
and a ranging module: the distance measurement device is used for measuring distance of the driving track and obtaining a task traveling vector;
task queue establishment module: the method comprises the steps of establishing a driving task queue, and grouping the driving task queue according to the task advancing vector;
the task acquisition module is used for: the driving task queue is used for acquiring driving execution tasks, and enabling the driving execution tasks to enter the driving task queues after corresponding grouping according to time sequence;
task aggregation module: the method comprises the steps of aggregating the driving execution tasks in the same group according to the task execution time length to obtain a driving execution task set;
the task aggregation module comprises:
task weight assignment unit: respectively distributing execution task weights for the driving execution tasks according to the time sequence, the emergency degree and the importance of the driving execution tasks;
task assigning unit: dividing the task execution time length, and assigning the driving execution tasks according to the divided task execution time length to obtain a plurality of driving execution task groups;
task weight calculation unit: calculating a weighted sum of each driving executing task in each group, wherein the weighted sum is a sum of weights for establishing task time sequence, emergency degree and importance;
task ordering unit: sequencing the weighted sum of each driving executing task in each group to obtain a weighted sum sequencing result; sequencing the plurality of running execution task groups according to a shortest job scheduling algorithm to obtain a running execution task group sequencing result;
a priority order determination unit: determining the priority order of the driving execution tasks according to the weighting and sequencing result and the driving execution task group sequencing result, and obtaining a driving execution task set;
the motion parameter acquisition module: the motion parameter information is used for acquiring motion parameter information of each driving execution task in the driving execution task set;
early warning monitoring module: the method comprises the steps of constructing an early warning monitoring model, inputting the motion parameter information into the early warning monitoring model, and obtaining an early warning monitoring result;
task scheduling module: and adjusting the task scheduling of the workshop traveling crane according to the early warning monitoring result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380374.6A CN117311283B (en) | 2023-10-24 | 2023-10-24 | Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380374.6A CN117311283B (en) | 2023-10-24 | 2023-10-24 | Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117311283A CN117311283A (en) | 2023-12-29 |
| CN117311283B true CN117311283B (en) | 2024-03-19 |
Family
ID=89297141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311380374.6A Active CN117311283B (en) | 2023-10-24 | 2023-10-24 | Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117311283B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107533630A (en) * | 2015-01-20 | 2018-01-02 | 索菲斯研究股份有限公司 | For the real time machine vision of remote sense and wagon control and put cloud analysis |
| CN111123929A (en) * | 2019-12-23 | 2020-05-08 | 天行智控(成都)科技有限公司 | Rail transport partition scheduling system |
| CN111417871A (en) * | 2017-11-17 | 2020-07-14 | 迪普迈普有限公司 | Iterative closest point processing for integrated motion estimation using high definition maps based on lidar |
| CN113610336A (en) * | 2021-06-16 | 2021-11-05 | 物泊科技有限公司 | Molten iron cross-car dispatching system |
| CN114035468A (en) * | 2021-11-08 | 2022-02-11 | 山东理工大学 | Predictive monitoring method and system for fan overhaul process based on XGboost algorithm |
| CN115469268A (en) * | 2022-09-13 | 2022-12-13 | 山东大学 | Port operation system based on multi-sensor fusion positioning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11264128B2 (en) * | 2019-06-28 | 2022-03-01 | University Hospitals Cleveland Medical Center | Machine-learning framework for coordinating and optimizing healthcare resource utilization and delivery of healthcare services across an integrated healthcare system |
| US11392195B2 (en) * | 2020-06-15 | 2022-07-19 | Strongarm Technologies, Inc. | Methods and apparatus for actions, activities and tasks classifications based on machine learning techniques |
| US20220327650A1 (en) * | 2021-04-01 | 2022-10-13 | Beijing Didi Infinity Technology And Development Co., Ltd. | Transportation bubbling at a ride-hailing platform and machine learning |
-
2023
- 2023-10-24 CN CN202311380374.6A patent/CN117311283B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107533630A (en) * | 2015-01-20 | 2018-01-02 | 索菲斯研究股份有限公司 | For the real time machine vision of remote sense and wagon control and put cloud analysis |
| CN111417871A (en) * | 2017-11-17 | 2020-07-14 | 迪普迈普有限公司 | Iterative closest point processing for integrated motion estimation using high definition maps based on lidar |
| CN111123929A (en) * | 2019-12-23 | 2020-05-08 | 天行智控(成都)科技有限公司 | Rail transport partition scheduling system |
| CN113610336A (en) * | 2021-06-16 | 2021-11-05 | 物泊科技有限公司 | Molten iron cross-car dispatching system |
| CN114035468A (en) * | 2021-11-08 | 2022-02-11 | 山东理工大学 | Predictive monitoring method and system for fan overhaul process based on XGboost algorithm |
| CN115469268A (en) * | 2022-09-13 | 2022-12-13 | 山东大学 | Port operation system based on multi-sensor fusion positioning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117311283A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610260B (en) | Driving energy consumption prediction system, method, storage medium and equipment | |
| CN113222387B (en) | Multi-objective scheduling and collaborative optimization method for hydrogen fuel vehicle | |
| CN110599767A (en) | Long-term and short-term prediction method based on network taxi appointment travel demands | |
| US9552270B2 (en) | System and method for receiving analysis requests and configuring analytics systems | |
| Fernández et al. | Dynamic fuzzy logic elevator group control system with relative waiting time consideration | |
| Xinghao et al. | Predicting bus real-time travel time basing on both GPS and RFID data | |
| CN106600047A (en) | Method for fault identification and early warning of air conditioners in passenger compartments of motor train unit based on BP neural network | |
| CN112883648A (en) | Training method and device for automobile fuel consumption prediction model and computer equipment | |
| CN114169254A (en) | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model | |
| CN109978026B (en) | Elevator position detection method and system based on LSTM network | |
| CN112850387B (en) | Elevator state acquisition and diagnosis system and method | |
| CN117311283B (en) | Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger | |
| CN116737804B (en) | Gas data hierarchical processing method and system based on intelligent gas Internet of things | |
| Li et al. | A decision-based framework for predictive maintenance technique selection in industry 4.0 | |
| CN112766771A (en) | SVM (support vector machine) -based whole heavy-duty automobile mass prediction method | |
| Kretzschmar et al. | Range prediction models for e-vehicles in urban freight logistics based on machine learning | |
| Cross et al. | Prediction of landing gear loads from flight test data using Gaussian process regression | |
| CN117196266B (en) | Unmanned shared automobile area scheduling method and device based on neural network | |
| JP2000322682A (en) | System, device and method for predicting traffic flow | |
| CN116485137B (en) | Intelligent bus scheduling method, device and medium based on big data | |
| CN117922538B (en) | Measurement and control method and system for hybrid electric vehicle based on digital twin technology | |
| CN116915122B (en) | Self-adaptive control method and system for coal mine frequency conversion equipment | |
| Medykovskyy et al. | An approach towards AGV battery cell voltage prediction using DL and data pre-processing | |
| WO2023084701A1 (en) | Automatic train operation assistance device, automatic train operation assistance system, and automatic train operation assistance method | |
| WO2023165697A1 (en) | A solution for providing condition data of an elevator rope |
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 |