CN115328044A - Identification model-based industrial device variable load man-machine fusion operation evaluation method - Google Patents
Identification model-based industrial device variable load man-machine fusion operation evaluation method Download PDFInfo
- Publication number
- CN115328044A CN115328044A CN202210979236.9A CN202210979236A CN115328044A CN 115328044 A CN115328044 A CN 115328044A CN 202210979236 A CN202210979236 A CN 202210979236A CN 115328044 A CN115328044 A CN 115328044A
- Authority
- CN
- China
- Prior art keywords
- constraint
- product quality
- impc
- variable load
- data
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 25
- 230000004927 fusion Effects 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000005265 energy consumption Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000009776 industrial production Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 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]
- G05B19/41845—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 system universality, reconfigurability, modularity
-
- 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
- G05B2219/33—Director till display
- G05B2219/33273—DCS distributed, decentralised controlsystem, multiprocessor
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 discloses an industrial device variable load man-machine fusion operation evaluation method based on an identification model. The method comprises the steps of firstly, acquiring various operation data and bit number data in variable load operation of an industrial device, then acquiring operation data of IMPC as a skill evaluation reference, and finally evaluating the skill of an operator according to performance indexes in four variable load processes of safety constraint, product quality constraint, task completion time and energy consumption; the method uses variable load operation data of a double-layer industrial model predictive control algorithm as a skill evaluation benchmark. The invention can objectively reflect and distinguish the operating skill levels of different operators from multiple dimensions.
Description
Technical Field
The invention relates to the technical field of process operation training of industrial devices, in particular to a variable-load man-machine fusion operation evaluation method of an industrial device based on an identification model.
Background
Load regulation is the most common operation task of process plants, such as industrial gas production plants, nuclear power plants, oil refining plants, etc., and they all need to regulate the load of the plant safely, stably and efficiently to meet the urgent demands of the downstream. For a large-scale process production device, joint and cooperative adjustment of a plurality of operation variables are often related in the dynamic load adjustment process, and complicated nonlinear operation is involved in the large-scale load adjustment process, so that a process device operator which is not provided with an automatic load changing system is required to have skilled manual load changing operation skills.
In recent years, a variable load Operation Training System (OTS) is deployed in most process apparatuses in the chemical industry. However, in the existing OTS system, the operation evaluation function is single, and most operators' skills are evaluated only from the aspects of completeness of operation steps and correctness of operation sequence, and the function of performing multi-dimensional objective evaluation and guidance on the operators from the aspect of man-machine integration is lacked.
Disclosure of Invention
The invention aims to provide a variable-load man-machine fusion operation evaluation method for an industrial device based on an identification model, aiming at the defects of the prior art.
The purpose of the invention is realized by the following technical scheme: an industrial device variable load man-machine fusion operation evaluation method based on an identification model comprises the following steps:
(1) Acquiring various operation data and bit number data in variable load operation of the industrial device: connecting an industrial device DCS platform through an industrial communication protocol, acquiring various production data in the production process of the industrial device in real time, and automatically recording various operation data of an operator;
(2) Acquiring operation data of IMPC as skill evaluation benchmark: designing a double-layer IMPC to complete the switching task between any two working conditions in a plurality of typical working conditions, wherein the double-layer IMPC consists of an upper steady-state optimization calculation module and a lower dynamic prediction control module; the steady state optimization calculation module provides an optimal tracking set target of the process for the lower layer, and the dynamic prediction control module stably and quickly controls the load adjustment process to a set target given by the upper layer under the condition of not violating the constraint; after all tasks are completed, variable load operation data of the IMPC is collected.
(3) Evaluating the skill of an operator according to performance indexes in four variable load processes of safety constraint, product quality constraint, task completion time and energy consumption;
further, the step (3) is divided into the following substeps.
And (3.1) determining DCS alarm constraint in the industrial production process.
(3.2) determining four evaluation indexes of the variable load operation skill: safety constraints, product quality constraints, task completion time and energy consumption;
(3.3) designing safety constraint indexes: the safety constraint is a key index reflecting the safety of production, and the score of the safety constraint is recorded as T 1 。T 1 Is 100, when the operator's manual operation triggers the advanced alarm constraint, T 1 Is gradually subtracted.
(3.4) designing product quality constraint indexes: the product quality constraint index consists of two parts, namely hard product quality constraint and soft product quality constraint, wherein the hard product quality constraint is related to the quality of an industrial device product and is determined by whether the value of a key process variable triggers low-level alarm constraint or not; soft product quality constraints are related to whether the relationships between several important materials match each other at the end of the manual operation. The steady state material matching relationship is obtained by the following steps. Firstly, actual data are collected, and steady-state working condition data are identified through a steady-state detection algorithm. And secondly, fitting a second-order polynomial model through steady-state working condition data to obtain a steady-state material matching relation. Recording the score of product quality constraint as T 2 ，T 2 Is 100. If the operator triggers a low-level alarm constraint of the industrial plant during manual operation or the material relationship does not satisfy the constraint condition at the end of the manual operation, T 2 Will be gradually deducted.
(3.5) designing an operation speed index: according to the running data of the IMPC, the task completion time index score is calculated as follows:
wherein, T MPC And T Operator Respectively, the time for IMPC and human operator to complete the same operational task.
(3.6) designing an energy consumption index: from the IMPC operating data, the energy expenditure indicator score is calculated as follows:
wherein, E MPC And E Operator Respectively, the IMPC and human operator are energy consuming to accomplish the same task of operation.
And (3.7) designing a multi-index weighting method.
Obtaining a final operation evaluation result T by weighting the four indexes Final As follows:
wherein q is i A weighting coefficient representing the ith index.
The method has the beneficial effect that the method is designed to evaluate the dynamic variable load operation skill of the industrial device operator through a multi-dimensional operation skill evaluation method. The method evaluates the variable load skills of an industrial plant operator according to the following four performance indicators: safety constraints, product quality constraints, task completion time, and energy consumption. The method uses variable load operation data of a double-layer industrial model predictive control algorithm as a skill evaluation benchmark. The operating skill levels of different operators can be objectively reflected and distinguished from multiple dimensions.
Drawings
Fig. 1 is a final skill score radar chart.
Detailed Description
The invention discloses an industrial device variable load man-machine fusion operation evaluation method based on an identification model, which comprises the following steps:
the method comprises the following steps: acquiring various operation data and bit number data in variable load operation of the industrial device: connecting an industrial device DCS platform through an industrial communication protocol, acquiring various production data in the production process of the industrial device in real time, and automatically recording various operation data of an operator;
step two: obtaining operation data of IMPC as skill evaluation benchmark: on the basis of the original development of a variable load operation training system of an industrial device, a double-layer IMPC is designed to complete the switching task between any two working conditions in a plurality of typical working conditions. The IMPC of the double-layer is composed of a steady state optimization calculation module at the upper layer and a dynamic prediction control module at the lower layer. The steady state optimization calculation module provides an optimal tracking set target of the process for the lower layer, and the dynamic prediction control module stably and quickly controls the load adjustment process to the set target given by the upper layer under the condition of not violating the constraint. After all tasks are completed, variable load operation data of the IMPC is collected and serves as a benchmark for manual operation skill evaluation.
Step three: evaluating the skill of an operator according to performance indexes in four variable load processes of safety constraint, product quality constraint, task completion time and energy consumption;
this step is the core of the present invention and is divided into the following substeps.
1) And determining DCS alarm constraint in the industrial production process.
And determining quality requirements including DCS low-level and high-level alarm constraints in the variable load production process of the industrial device by combining process and historical data.
2) And determining four evaluation indexes of the variable load operation skill.
By incorporating process knowledge, the operator's variable load operating skills are generally evaluated from four perspectives: (1) safety of operation; (2) product quality constraints; (3) operating speed index; and (4) energy consumption index.
3) Designing a safety constraint index: and (4) safety restraint.
The safety constraint indicator is related to the safety of the industrial device and is determined by whether the key process variable value triggers a high-level alarm constraint. The advanced alarm will trigger the safety interlock system of the DCS to protect the industrial equipment.The safety constraint is a key index reflecting the safety of production, and the score of the safety constraint is recorded as T 1 。T 1 Is 100, when the operator's manual operation triggers the advanced alarm constraint, T 1 Is gradually subtracted.
4) Designing a product quality constraint index: and (5) restricting the product quality.
The product quality constraint index consists of two parts of hard product quality constraint and soft product quality constraint. Hard product quality constraints are related to the quality of the industrial plant product and are determined by whether the value of a key process variable triggers a low-level alarm constraint. Soft product quality constraints are related to whether the relationships between several important materials match each other at the end of the manual operation. If the relationship between the important materials does not match at the end of the manual operation, the operating conditions of the industrial plant cannot be kept stable in subsequent simulations.
The steady state material matching relationship is obtained by the following steps. Firstly, actual data are collected, and steady-state working condition data are identified through a steady-state detection algorithm. Note that the steady state operating condition data herein includes not only typical steady state operating condition data, but also some non-typical steady state operating condition data. And secondly, fitting a second-order polynomial model through steady-state working condition data to obtain a steady-state material matching relation.
Score of product quality constraint is T 2 ，T 2 Is 100. If the operator triggers a low-level alarm constraint of the industrial plant during manual operation or the material relationship does not satisfy the constraint condition at the end of the manual operation, T 2 Will be gradually deducted. The contribution of different bit numbers to the quality constraint index of hard products is different because of their different importance to the production of industrial plants. Similarly, different product quality constraints are also set to contribute differently to the soft product quality constraint index.
5) Designing an operation speed index: and (4) task completion time.
The task completion time index reflects the speed of response to downstream demand. While ensuring plant safety and product quality, operators need to adjust industrial plant loads as quickly as possible to meet downstream demands. According to the running data of the IMPC, the task completion time index score is calculated as follows:
wherein, T MPC And T Operator Respectively, the IMPC and the human operator are time to complete the same operational task.
6) Designing an energy consumption index: and (4) energy consumption.
The energy consumption index reflects the economy of manual operation. From the IMPC operating data, the energy consumption index score is calculated as follows:
wherein, E MPC And E Operator Respectively, the IMPC and human operator are energy consuming to accomplish the same task of operation.
7) And designing a multi-index weighting method.
The method obtains a final operation evaluation result T by weighting the four indexes Final As follows:
wherein q is i A weighting coefficient representing the ith index.
Claims (2)
1. A variable load man-machine fusion operation evaluation method of an industrial device based on an identification model is characterized by comprising the following steps:
(1) Acquiring various operation data and bit number data in variable load operation of the industrial device: connecting an industrial device DCS platform through an industrial communication protocol, acquiring various production data in the production process of the industrial device in real time, and automatically recording various operation data of an operator;
(2) Acquiring operation data of IMPC as skill evaluation benchmark: the method comprises the following steps that a double-layer IMPC is designed to complete switching tasks between any two working conditions in a plurality of typical working conditions, wherein the double-layer IMPC consists of an upper steady-state optimization calculation module and a lower dynamic prediction control module; the steady state optimization calculation module provides an optimal tracking set target of the process for the lower layer, and the dynamic prediction control module stably and quickly controls the load adjustment process to a set target given by the upper layer under the condition of not violating the constraint; after all tasks are completed, variable load operation data of the IMPC is collected.
(3) Evaluating the skill of an operator according to performance indexes in four variable load processes of safety constraint, product quality constraint, task completion time and energy consumption;
2. the identification model-based evaluation method for variable-load man-machine fusion operation of industrial equipment according to claim 1, wherein the step (3) is divided into the following substeps.
And (3.1) determining DCS alarm constraint in the industrial production process.
(3.2) determining four evaluation indexes of the variable load operation skill: safety constraints, product quality constraints, task completion time and energy consumption;
(3.3) designing safety constraint indexes: the safety constraint is a key index reflecting the safety of production, and the score of the safety constraint is recorded as T 1 。T 1 Is 100, when the operator's manual operation triggers the advanced alarm constraint, T 1 Is gradually subtracted.
(3.4) designing product quality constraint indexes: the product quality constraint index consists of a hard product quality constraint part and a soft product quality constraint part, wherein the hard product quality constraint part is related to the quality of an industrial device product and is determined by whether the value of a key process variable triggers a low-level alarm constraint; soft product quality constraints are related to whether the relationships between several important materials match each other at the end of the manual operation. The steady state material matching relationship is obtained by the following steps. Firstly, actual data are collected, and steady-state working condition data are identified through a steady-state detection algorithm. Second, fitting a second order polynomial through steady state operating condition dataThe formula model obtains a steady-state material matching relationship. Score of product quality constraint is T 2 ，T 2 Is 100. If the operator triggers a low-level alarm constraint of the industrial plant during manual operation or the material relationship does not satisfy the constraint condition at the end of the manual operation, T 2 Will be gradually deducted.
(3.5) designing an operation speed index: according to the running data of the IMPC, the task completion time index score is calculated as follows:
wherein, T MPC And T Operator Respectively, the IMPC and the human operator are time to complete the same operational task.
(3.6) designing an energy consumption index: from the IMPC operating data, the energy expenditure indicator score is calculated as follows:
wherein, E MPC And E Operator Respectively, the IMPC and human operator are energy consuming to accomplish the same task of operation.
And (3.7) designing a multi-index weighting method.
Obtaining a final operation evaluation result T by weighting the four indexes Final As follows:
wherein q is i A weighting coefficient representing the ith index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210979236.9A CN115328044A (en) | 2022-08-16 | 2022-08-16 | Identification model-based industrial device variable load man-machine fusion operation evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210979236.9A CN115328044A (en) | 2022-08-16 | 2022-08-16 | Identification model-based industrial device variable load man-machine fusion operation evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115328044A true CN115328044A (en) | 2022-11-11 |
Family
ID=83923388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210979236.9A Pending CN115328044A (en) | 2022-08-16 | 2022-08-16 | Identification model-based industrial device variable load man-machine fusion operation evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115328044A (en) |
-
2022
- 2022-08-16 CN CN202210979236.9A patent/CN115328044A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| CN108363836B (en) | Multi-working-condition self-adaptive industrial robot health degree assessment method and system | |
| CN107341349A (en) | Method, system, memory and the controller of blower fan health evaluating | |
| CN101349893A (en) | Forecast control device of adaptive model | |
| CN116681187B (en) | Enterprise carbon quota prediction method based on enterprise operation data | |
| CN111380686A (en) | XGboost algorithm model-based fan main bearing fault monitoring and diagnosis method | |
| EP2895926A1 (en) | Method for the computer-assisted monitoring of the operation of a technical system, particularly of an electrical energy-generating installation | |
| CN109032117B (en) | ARMA model-based single-loop control system performance evaluation method | |
| CN113515049A (en) | Operation regulation and control system and method for gas-steam combined cycle generator set | |
| CN117495356B (en) | Intelligent gas pipeline maintenance method based on man-machine linkage and Internet of things system | |
| CN112418682A (en) | Security assessment method fusing multi-source information | |
| CN110298385A (en) | One kind is based on * information and the online incipient fault detection method of increment SVDD | |
| CN114326395B (en) | Intelligent generator set control model online updating method based on working condition discrimination | |
| Takalo-Mattila et al. | Explainable steel quality prediction system based on gradient boosting decision trees | |
| CN111142488B (en) | Process industrial optimization method based on working condition comparison driving | |
| JP7252703B2 (en) | Operation support device, operation support method, operation support program, and recording medium | |
| CN117592906A (en) | Auto-parts intelligence warehouse management system based on data analysis | |
| CN115238573A (en) | Hydroelectric generating set performance degradation trend prediction method and system considering working condition parameters | |
| CN118386024A (en) | Machine tool based on artificial intelligence and fault detection method thereof | |
| CN117742273A (en) | Papermaking process optimization system and method based on deep reinforcement learning | |
| CN113689072A (en) | Offshore wind turbine generator running state evaluation method based on Markov chain | |
| CN115328044A (en) | Identification model-based industrial device variable load man-machine fusion operation evaluation method | |
| Tidriri et al. | Data-driven decision-making methodology for prognostic and health management of wind turbines | |
| CN113705076B (en) | Wind turbine generator system gearbox state monitoring method and control device based on partial least square method | |
| Rojek et al. | Methods of computational intelligence in the context of quality assurance in foundry products |
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 |