CN112817289A - Glass factory data analysis and intelligent prediction system - Google Patents
Glass factory data analysis and intelligent prediction system Download PDFInfo
- Publication number
- CN112817289A CN112817289A CN202110174215.5A CN202110174215A CN112817289A CN 112817289 A CN112817289 A CN 112817289A CN 202110174215 A CN202110174215 A CN 202110174215A CN 112817289 A CN112817289 A CN 112817289A
- Authority
- CN
- China
- Prior art keywords
- module
- analysis
- prediction system
- prediction
- monitoring
- 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.)
- Pending
Links
- 239000011521 glass Substances 0.000 title claims abstract description 39
- 238000007405 data analysis Methods 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 96
- 238000004458 analytical method Methods 0.000 claims abstract description 45
- 238000013500 data storage Methods 0.000 claims abstract description 17
- 238000002844 melting Methods 0.000 claims description 68
- 230000008018 melting Effects 0.000 claims description 68
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 44
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 22
- 239000003345 natural gas Substances 0.000 claims description 22
- 239000001301 oxygen Substances 0.000 claims description 22
- 229910052760 oxygen Inorganic materials 0.000 claims description 22
- 238000000137 annealing Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 238000003723 Smelting Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 12
- 238000000034 method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 239000002283 diesel fuel Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005816 glass manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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)
- General Factory Administration (AREA)
Abstract
The invention discloses a glass factory data analysis and intelligent prediction system, which relates to the technical field of glass factory systems and comprises a display module, a forwarding station, an interface machine, a recommendation control module, an analysis and prediction system module, a data storage module, a state prediction module and a real-time monitoring module, wherein the real-time monitoring module is connected with the analysis and prediction system module and the state prediction module, the state prediction module is connected with the recommendation control module and the analysis and prediction system module, the recommendation control module is connected with the analysis and prediction system module, the analysis and prediction system module is connected with the data storage module, the analysis and prediction system module is provided with the interface machine, and the interface machine is connected with the display module through the forwarding station, and has the advantages that: the system has the characteristics of system integration, technical advancement, high expansibility of the system and the like, can well meet the requirements of users without changing the original system too much, and saves the cost of system maintenance and updating.
Description
Technical Field
The invention relates to the technical field of glass factory systems, in particular to a glass factory data analysis and intelligent prediction system.
Background
The glass manufacturing process is a complex process with long dynamics and associated high energy consumption, while the glass melting furnace is the core production process consuming about 70% to 80% of the total energy consumed by the whole manufacturing process, and any effort by researchers to optimize their operation to save energy is worth. On the other hand, with the increasing number of regulations such as the kyoto protocol, the most important challenge for the glass industry in many countries of the world is to meet the increasingly strict environmental constraints on pollutant emission at low cost, and to maintain competitiveness, it is important to optimize the control of the glass melting furnace.
The generation process of the glass melting furnace has a large number of physical reactions and chemical reactions, and if modeling is carried out, the generation process is a complex nonlinear system with multiple distributed parameters, and the process is very difficult, so that the process is difficult to control accurately. The current method for controlling each parameter of the glass melting furnace in China is single-loop PID control. Conventional PID controllers are widely used in industry due to their availability for linear systems, ease of design and low cost. Yamamoto and Hashimoto reported in 1991, for example, in Japan, more than 90% of all control loops are of the PID type. Conventional PID controllers, while effective for linear systems, are not suitable for non-linear, high order, and time-lapse systems. For these reasons, many researchers have attempted to combine conventional PID controllers with Fuzzy Logic Controllers (FLCs) to achieve better system performance than conventional PID controllers. Jianling Q and Zhenjie D, and the like, apply a fuzzy PID control method to a temperature control system of a glass melting furnace, and experiments prove that the FLC system can actually improve high-quality production for the glass melting furnace and reduce the labor intensity of workers. Sardeshpande V et al [6] developed a simulation model of the glass furnace using mass, energy balance, and heat loss equations for different regions and empirical formulas based on operational practices. The model is checked against field data of the India end Industrial glass furnace to enable calculation of the energy performance for a given furnace design. The model results show the potential for such improvements and the impact of different operational and design preferences on specific energy consumption. Furnaces operating at actual production scale have an energy consumption reduction potential of approximately 20% -25%.
The traditional glass production process has a plurality of defects under the influence of the laggard production technology in the past, so when the production problem of the heat accumulating type horseshoe flame glass melting furnace is solved, a neural network control algorithm is introduced based on the field bus technology, and the real-time monitoring, analysis and optimization of the production process are realized. Artificial neural networks are parallel in nature and have great potential applications due to their ability to learn nonlinear relationships. Theoretically, it does not require a priori knowledge of the system, thereby circumventing the difficulties of modeling first principles. Kumaran Rajarathinam et al implements a decision support system using an artificial neural network, called "FUNN" (furnace processing system using neural networks), which has the functions of process model identification, setpoint control, and interpretation of input factors.
Disclosure of Invention
The invention aims to provide a glass factory data analysis and intelligent prediction system aiming at the defects and shortcomings in the prior art, and the system has the characteristics of system integration, technical advancement, high expansibility of the system and the like.
In order to achieve the purpose, the invention adopts the following technical scheme: a glass factory data analysis and intelligent prediction system comprises a display module 1, a forwarding station 2, an interface machine 3, a recommendation control module 4, an analysis and prediction system module 5, a data storage module 6, a state prediction module 7 and a real-time monitoring module 8, wherein the real-time monitoring module 8 is connected with the analysis and prediction system module 5 and the state prediction module 7, the state prediction module 7 is connected with the recommendation control module 4 and the analysis and prediction system module 5, the recommendation control module 4 and the analysis and prediction system module 5 are connected with each other, the analysis and prediction system module 5 and the data storage module 6 are connected with each other, the analysis and prediction system module 5 is provided with the interface machine 3, and the interface machine 3 is connected with the display module 1 through the forwarding station 2.
Further, the display module 1 is provided with an oxygen information module 11, a natural gas information module 12, a pressure information module 13, a temperature information module 14 and a recommendation control information module 15, and the oxygen information module 11, the natural gas information module 12, the pressure information module 13 and the temperature information module 14 are connected with the interface machine 3 through the forwarding station 2.
Further, the data storage module 6 is provided with a setting value module 61, a monitoring value module 62, a prediction value module 63 and a recommendation value module 64.
Further, the real-time monitoring module 8 includes a melting furnace pressure monitoring module 81, a melting furnace temperature monitoring module 82, a melting furnace oxygen monitoring module 83, a natural gas monitoring module 84, and an annealing furnace monitoring module 85, wherein the melting furnace pressure monitoring module 81, the melting furnace temperature monitoring module 82, the melting furnace oxygen monitoring module 83, the natural gas monitoring module 84, and the annealing furnace monitoring module 85 are connected with the analysis and prediction system module 5.
Further, the melting furnace pressure monitoring module 81 and the melting furnace temperature monitoring module 82 are connected to the state prediction module 7.
Further, the recommendation control module 4 is provided with an LSTM neural network algorithm module 41.
Further, the display module 1 is connected to the forwarding station 2, and the connection mode includes but is not limited to wireless connection modes such as wifi and ZigBee or wired connection modes such as cable.
Further, the learning manner of the recommendation control module 4 is learned by the following steps: starting; acquiring data through a real-time monitoring module 8; the information of the real-time monitoring module 8 is preprocessed through the analysis and prediction system module 5; training is carried out through an LSTM neural network algorithm module 41, and a prediction model is provided by a state prediction module 7; the model training of the recommendation control module 4 is finished; and (6) ending.
Further, the data storage module 6 uses a non-relational database MongoDB as a background storage medium to store sensor data at different time intervals.
Further, the setting value module 61, the monitoring value module 62, the prediction value module 63 and the recommendation value module 64 are all connected with the analysis and prediction system module 5.
The working principle of the invention is as follows: the analysis and prediction system module 5 is mainly embodied by a real-time monitoring module 8, a state prediction module 7 and a recommendation control module 4 of the characteristic data of the glass melting furnace, the analysis and prediction system module 5 is mainly used for carrying out real-time acquisition, monitoring and comprehensive analysis on the sensor data of each characteristic of the melting furnace, the control of the melting furnace is decided, the state prediction module 7 mainly predicts the temperature and the pressure of the melting furnace, namely, the information of the melting furnace pressure monitoring module 81 and the melting furnace temperature monitoring module 82 is obtained for establishing a deep learning model for the melting furnace later to realize the automatic control of the melting furnace temperature and pressure, the recommendation control module 4 is used for realizing a recommendation decision for controlling the temperature and the pressure of the melting furnace, outputting a control operation which can enable the real-time temperature and the pressure to be closer to a set value according to the current real-time state and the state set value of the melting furnace, and mainly using an LSTM neural network algorithm module 41; the real-time monitoring module 8 monitors and displays the sensor data of the oxygen, natural gas, melting furnace pressure, temperature and annealing furnace part of the melting furnace in real time through a melting furnace pressure monitoring module 81, a melting furnace temperature monitoring module 82, a melting furnace oxygen monitoring module 83, a natural gas monitoring module 84 and an annealing furnace monitoring module 85, and transmits the data to the prediction system module 5, the analysis prediction system module 5 transmits the data to the display module 1 in real time through the interface machine 3 and the forwarding station 2, and displays the data of the oxygen information module 11, the natural gas information module 12, the pressure information module 13, the temperature information module 14 and the recommendation control information module 15, so that technicians can master the production state of each submodule at any time, the data storage module 6 adopts a non-relational database MongoDB as a background storage medium to store the sensor data at different time intervals, and comprises a set value module 61, The monitoring value module 62, the prediction value module 63 and the recommendation value module 64 enable a user to query corresponding historical records through time selection. Wherein the learning mode of the recommendation control module 4 comprises start; acquiring data through a real-time monitoring module 8; the information of the real-time monitoring module 8 is preprocessed through the analysis and prediction system module 5; training is carried out through an LSTM neural network algorithm module 41, and a prediction model is provided by a state prediction module 7; the model training of the recommendation control module 4 is finished; to conclude, it should be clear that: considering that a glass melting furnace is a complex nonlinear system with a plurality of variables, more than 1000 sensors are deployed on the glass melting furnace for monitoring and adjusting variable indexes, and on the other hand, historical data is cluttered and must be processed for use, we intend to perform three-step processing on the historical data before running experiments, and reject annealing furnace data and furnace useless data: after the meaning of the parameter index of the glass production process is corrected in detail, all annealing kiln data in historical data, such as the speed of a driving machine, the speed of a calender and the like, are removed. Meanwhile, in the process of treatment, after being engaged with a project party, the conventional smelting furnace does not use diesel oil but uses natural gas as fuel, so that all data related to the diesel oil are deleted from the original data. On the other hand, all the quantity data with the value of 0 or 1 of the switching quantity is deleted at the same time, because the switching quantity indicates whether the valve is switched or not, whether the system is in operation or not, and whether the system is in failure or not, and the values are kept constant as long as the system can be operated normally. Supplementing missing data: the pace of data collection of each sensor by the original melting furnace RY database is not consistent. Part of the data was collected every minute and part of the data was collected every ten minutes. All sensors have data loss, and the loss ratio is 0-2% generally. Thus the data derived from the database cannot be used directly and we will fill in missing values with the last minute values at one minute intervals. Data classification: raw data is cluttered, for example, more than thirty sensors for monitoring oxygen indexes are adopted, but the sensors do not indicate that the types only have ID attributes, and the detection quantity of the state of the smelting furnace and the actual control quantity are mixed together and must be carefully classified to use.
After the technical scheme is adopted, the invention has the beneficial effects that: the system integration comprises the integration capability of the internal service of the system, provides complete and comprehensive functions on one platform, and reduces the extra burden of developing other systems; the glass big data analysis and intelligent decision system adopts the current advanced development technology and applies a plurality of state evaluation algorithms; the high expansibility of the system, the glass big data analysis and intelligent decision system can facilitate the user to expand the functions of the system to meet the requirement of continuous development, when a new function module needs to be added, the user requirement can be well met without changing the original system too much, and the cost of system maintenance and updating is saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic structural view of the present invention.
Fig. 2 is a learning block diagram of the recommendation control module 4 in the present invention.
Description of reference numerals: the system comprises a display module 1, a forwarding station 2, an interface machine 3, a recommendation control module 4, an analysis and prediction system module 5, a data storage module 6, a state prediction module 7, a real-time monitoring module 8, an oxygen information module 11, a natural gas information module 12, a pressure information module 13, a temperature information module 14, a recommendation control information module 15, a set value module 61, a monitoring value module 62, a prediction value module 63, a recommendation value module 64, a melting furnace pressure monitoring module 81, a melting furnace temperature monitoring module 82, a melting furnace oxygen monitoring module 83, a natural gas monitoring module 84, an annealing furnace monitoring module 85 and an LSTM neural network algorithm module 41.
Detailed Description
Referring to fig. 1 to 2, the technical solution adopted by the present embodiment is: the system comprises a display module 1, a forwarding station 2, an interface machine 3, a recommendation control module 4, an analysis and prediction system module 5, a data storage module 6, a state prediction module 7 and a real-time monitoring module 8, wherein the real-time monitoring module 8 is connected with the analysis and prediction system module 5 and the state prediction module 7, the state prediction module 7 is connected with the recommendation control module 4 and the analysis and prediction system module 5, the recommendation control module 4 is connected with the analysis and prediction system module 5, the analysis and prediction system module 5 is connected with the data storage module 6, the analysis and prediction system module 5 is provided with the interface machine 3, and the interface machine 3 is connected with the display module 1 through the forwarding station 2.
The display module 1 is provided with an oxygen information module 11, a natural gas information module 12, a pressure information module 13, a temperature information module 14 and a recommendation control information module 15, the oxygen information module 11, the natural gas information module 12, the pressure information module 13 and the temperature information module 14 are connected with the interface machine 3 through the forwarding station 2, the data storage module 6 is provided with a set value module 61, a monitoring value module 62, a prediction value module 63 and a recommendation value module 64, the real-time monitoring module 8 comprises a melting furnace pressure monitoring module 81, a melting furnace temperature monitoring module 82, a melting furnace oxygen monitoring module 83, a natural gas monitoring module 84 and an annealing furnace monitoring module 85, the melting furnace pressure monitoring module 81, the melting furnace temperature monitoring module 82, the melting furnace oxygen monitoring module 83, the natural gas monitoring module 84 and the annealing furnace monitoring module 85 are connected with the analysis and prediction system module 5, the melting furnace pressure monitoring module 81 and the melting furnace temperature monitoring module 82 are connected with the state prediction module 7, and the recommendation control module 4 is provided with an LSTM neural network algorithm module 41.
The display module 1 is connected with the forwarding station 2 in a wireless connection mode including but not limited to wifi, ZigBee and the like or in a wired connection mode including cable and the like, the data storage module 6 uses a non-relational database mongoDB as a background storage medium to store sensor data at different time intervals, and the set value module 61, the monitoring value module 62, the prediction value module 63 and the recommendation value module 64 are connected with the analysis and prediction system module 5.
The learning mode of the recommendation control module 4 is learned by the following steps: starting; acquiring data through a real-time monitoring module 8; the information of the real-time monitoring module 8 is preprocessed through the analysis and prediction system module 5; training is carried out through an LSTM neural network algorithm module 41, and a prediction model is provided by a state prediction module 7; the model training of the recommendation control module 4 is finished; and (6) ending.
The working principle of the invention is as follows: the analysis and prediction system module 5 is mainly embodied by a real-time monitoring module 8, a state prediction module 7 and a recommendation control module 4 of the characteristic data of the glass melting furnace, the analysis and prediction system module 5 is mainly used for carrying out real-time acquisition, monitoring and comprehensive analysis on the sensor data of each characteristic of the melting furnace, the control of the melting furnace is decided, the state prediction module 7 mainly predicts the temperature and the pressure of the melting furnace, namely, the information of the melting furnace pressure monitoring module 81 and the melting furnace temperature monitoring module 82 is obtained for establishing a deep learning model for the melting furnace later to realize the automatic control of the melting furnace temperature and pressure, the recommendation control module 4 is used for realizing a recommendation decision for controlling the temperature and the pressure of the melting furnace, outputting a control operation which can enable the real-time temperature and the pressure to be closer to a set value according to the current real-time state and the state set value of the melting furnace, and mainly using an LSTM neural network algorithm module 41; the real-time monitoring module 8 monitors and displays the sensor data of the oxygen, natural gas, melting furnace pressure, temperature and annealing furnace part of the melting furnace in real time through a melting furnace pressure monitoring module 81, a melting furnace temperature monitoring module 82, a melting furnace oxygen monitoring module 83, a natural gas monitoring module 84 and an annealing furnace monitoring module 85, and transmits the data to the prediction system module 5, the analysis prediction system module 5 transmits the data to the display module 1 in real time through the interface machine 3 and the forwarding station 2, and displays the data of the oxygen information module 11, the natural gas information module 12, the pressure information module 13, the temperature information module 14 and the recommendation control information module 15, so that technicians can master the production state of each submodule at any time, the data storage module 6 adopts a non-relational database MongoDB as a background storage medium to store the sensor data at different time intervals, and comprises a set value module 61, The monitoring value module 62, the prediction value module 63 and the recommendation value module 64 enable a user to query corresponding historical records through time selection. Wherein the learning mode of the recommendation control module 4 comprises start; acquiring data through a real-time monitoring module 8; the information of the real-time monitoring module 8 is preprocessed through the analysis and prediction system module 5; training is carried out through an LSTM neural network algorithm module 41, and a prediction model is provided by a state prediction module 7; the model training of the recommendation control module 4 is finished; to conclude, it should be clear that: considering that a glass melting furnace is a complex nonlinear system with a plurality of variables, more than 1000 sensors are deployed on the glass melting furnace for monitoring and adjusting variable indexes, and on the other hand, historical data is cluttered and must be processed for use, we intend to perform three-step processing on the historical data before running experiments, and reject annealing furnace data and furnace useless data: after the meaning of the parameter index of the glass production process is corrected in detail, all annealing kiln data in historical data, such as the speed of a driving machine, the speed of a calender and the like, are removed. Meanwhile, in the process of treatment, after being engaged with a project party, the conventional smelting furnace does not use diesel oil but uses natural gas as fuel, so that all data related to the diesel oil are deleted from the original data. On the other hand, all the quantity data with the value of 0 or 1 of the switching quantity is deleted at the same time, because the switching quantity indicates whether the valve is switched or not, whether the system is in operation or not, and whether the system is in failure or not, and the values are kept constant as long as the system can be operated normally. Supplementing missing data: the pace of data collection of each sensor by the original melting furnace RY database is not consistent. Part of the data was collected every minute and part of the data was collected every ten minutes. All sensors have data loss, and the loss ratio is 0-2% generally. Thus the data derived from the database cannot be used directly and we will fill in missing values with the last minute values at one minute intervals. Data classification: raw data is cluttered, for example, more than thirty sensors for monitoring oxygen indexes are adopted, but the sensors do not indicate that the types only have ID attributes, and the detection quantity of the state of the smelting furnace and the actual control quantity are mixed together and must be carefully classified to use.
The above description is only for the purpose of illustrating the technical solutions of the present invention and not for the purpose of limiting the same, and other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention should be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. The utility model provides a glass factory data analysis and intelligent prediction system which characterized in that: the system comprises a display module (1), a forwarding station (2), an interface machine (3), a recommendation control module (4), an analysis and prediction system module (5), a data storage module (6), a state prediction module (7) and a real-time monitoring module (8), wherein the real-time monitoring module (8) is connected with the analysis and prediction system module (5) and the state prediction module (7), the state prediction module (7) is connected with the recommendation control module (4) and the analysis and prediction system module (5), the recommendation control module (4) is connected with the analysis and prediction system module (5), the analysis and prediction system module (5) is connected with the data storage module (6), the analysis and prediction system module (5) is provided with the interface machine (3), and the interface machine (3) is connected with the display module (1) through the forwarding station (2).
2. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the display module (1) is provided with an oxygen information module (11), a natural gas information module (12), a pressure information module (13), a temperature information module (14) and a recommendation control information module (15), and the oxygen information module (11), the natural gas information module (12), the pressure information module (13) and the temperature information module (14) are connected with the interface machine (3) through the forwarding station (2).
3. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the data storage module (6) is provided with a set value module (61), a monitoring value module (62), a prediction value module (63) and a recommendation value module (64).
4. The glass factory data analysis and intelligent prediction system of claim 1, wherein: real-time supervision module (8) have included melting furnace pressure monitoring module (81), melting furnace temperature monitoring module (82), smelting pot oxygen monitoring module (83), natural gas monitoring module (84), annealing kiln monitoring module (85), melting furnace pressure monitoring module (81), melting furnace temperature monitoring module (82), smelting pot oxygen monitoring module (83), natural gas monitoring module (84) and annealing kiln monitoring module (85) are connected analysis prediction system module (5).
5. The glass factory data analysis and intelligent prediction system of claim 4, wherein: and the melting furnace pressure monitoring module (81) and the melting furnace temperature monitoring module (82) are connected with the state prediction module (7).
6. The glass factory data analysis and intelligent prediction system of claim 1, wherein: and an LSTM neural network algorithm module (41) is arranged on the recommendation control module (4).
7. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the display module (1) is connected with the forwarding station (2) in a wireless connection mode such as wifi and ZigBee or in a wired connection mode such as cable.
8. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the learning mode of the recommendation control module (4) is learned by the following steps:
1) starting;
2) acquiring data through a real-time monitoring module (8);
3) the information of the real-time monitoring module (8) is preprocessed through the analysis and prediction system module (5);
4) training through an LSTM neural network algorithm module (41), and providing a prediction model through a state prediction module (7);
5) the model training of the recommendation control module (4) is finished;
6) and (6) ending.
9. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the data storage module (6) adopts a non-relational database MongoDB as a background storage medium to store sensor data at different time intervals.
10. The glass factory data analysis and intelligent prediction system of claim 1, wherein: the set value module (61), the monitoring value module (62), the prediction value module (63) and the recommendation value module (64) are all connected with the analysis and prediction system module (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110174215.5A CN112817289A (en) | 2021-02-09 | 2021-02-09 | Glass factory data analysis and intelligent prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110174215.5A CN112817289A (en) | 2021-02-09 | 2021-02-09 | Glass factory data analysis and intelligent prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112817289A true CN112817289A (en) | 2021-05-18 |
Family
ID=75864255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110174215.5A Pending CN112817289A (en) | 2021-02-09 | 2021-02-09 | Glass factory data analysis and intelligent prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112817289A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773682A (en) * | 2016-12-05 | 2017-05-31 | 清华大学 | Based on the glass furnace bottom of pond temperature intelligent forecast Control Algorithm that time lag is dynamically determined |
| CN110187727A (en) * | 2019-06-17 | 2019-08-30 | 武汉理工大学 | A kind of Glass Furnace Temperature control method based on deep learning and intensified learning |
| CN110347192A (en) * | 2019-06-17 | 2019-10-18 | 武汉理工大学 | Glass furnace temperature Intelligent predictive control method based on attention mechanism and self-encoding encoder |
-
2021
- 2021-02-09 CN CN202110174215.5A patent/CN112817289A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773682A (en) * | 2016-12-05 | 2017-05-31 | 清华大学 | Based on the glass furnace bottom of pond temperature intelligent forecast Control Algorithm that time lag is dynamically determined |
| CN110187727A (en) * | 2019-06-17 | 2019-08-30 | 武汉理工大学 | A kind of Glass Furnace Temperature control method based on deep learning and intensified learning |
| CN110347192A (en) * | 2019-06-17 | 2019-10-18 | 武汉理工大学 | Glass furnace temperature Intelligent predictive control method based on attention mechanism and self-encoding encoder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103453580B (en) | Heat exchange station integrated intelligent control method | |
| CN102809928A (en) | Control optimizing method for energy consumption of thermal equipment of industrial enterprise | |
| CN102109827B (en) | Method for synchronously and automatically controlling material feeding and power supplying in production of polysilicon | |
| CN110161999A (en) | Coking intelligent manufacturing system based on big data | |
| CN102915027A (en) | Blast furnace smelting expert system built based on pattern recognition technology and method thereof | |
| CN109489261A (en) | A kind of hot-blast stove Intellectualized controller that can be monitored in real time | |
| CN105259827A (en) | Real-time monitoring system and real-time monitoring method for solid fermentation process condition | |
| CN109886471A (en) | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm | |
| CN106773682A (en) | Based on the glass furnace bottom of pond temperature intelligent forecast Control Algorithm that time lag is dynamically determined | |
| CN112000075A (en) | Dry quenching optimization control method and system | |
| CN103014204A (en) | Blast furnace burden distribution optimization method based on mode recognition and expert system as well as system | |
| CN101598927B (en) | Control system of soda carbonization technique based on neural network and control method thereof | |
| CN109685283A (en) | A kind of mineral hot furnace operating condition prediction technique based on confidence rule base reasoning | |
| CN113282119B (en) | Temperature control method for oil field heating furnace | |
| CN112817289A (en) | Glass factory data analysis and intelligent prediction system | |
| CN214067660U (en) | Monitoring system based on Internet of things | |
| CN107463152A (en) | A kind of cane sugar factory production scheduling system and its operation method | |
| CN213182351U (en) | Intelligent control terminal of compressed air system | |
| Wang et al. | Application research of a fault diagnosis expert system for cement kiln based on. Net Platform | |
| CN112094050A (en) | Optical fiber preform rod tail wire drawing control system and method | |
| CN115198047B (en) | Hot blast stove combustion monitoring system and method based on big data analysis | |
| CN109870922A (en) | Multi-functional oil expression production line control method, device, equipment and storage medium | |
| CN114881207A (en) | Steam pressure prediction method and device based on LSTM deep circulation neural network | |
| CN111635071B (en) | Leachate treatment intelligent industrial control method based on multivariate data method | |
| CN102830659B (en) | Blast furnace data filtering method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |
|
| RJ01 | Rejection of invention patent application after publication |