Calcium carbide furnace intelligent electrode regulation and control system and anti-crusting control method

Abstract

The invention discloses a calcium carbide furnace intelligent electrode regulation and control system and an anti-crusting control method, and relates to the technical field of calcium carbide furnace intelligent electrode regulation and control. The intelligent electrode regulation and control system for the calcium carbide furnace comprises an intelligent electrode regulation and control module, an active anti-crusting control module, a data acquisition and preprocessing module and an intelligent decision support module, and the intelligent electrode regulation and control module, the active anti-crusting control module and the intelligent decision support module are respectively connected with the data acquisition and preprocessing module. The active anti-crusting control module is connected with the intelligent electrode regulation and control module, the operation stability is improved, the operation fluctuation range of the calcium carbide furnace is reduced through multivariable coordinated regulation and control, electrode consumption is reduced, crusting prevention and control are strengthened, the crusting occurrence rate is reduced through an active pre-judgment and linkage intervention mechanism, and the production interruption time is shortened.

Description

Technical Field

[0001] This invention relates to the field of intelligent electrode control technology for calcium carbide furnaces, and particularly to an intelligent electrode control system and anti-crusting control method for calcium carbide furnaces. Background Technology

[0002] The calcium carbide furnace is the core equipment in calcium carbide production. Electrode regulation and anti-crust control directly determine production efficiency and stability. Currently, most electrode regulation systems in the industry are based on a single current parameter and lack a multi-variable coordination mechanism such as current, voltage, and furnace pressure. Electrode imbalance is prone to occur when operating conditions fluctuate, and the measurement accuracy is insufficient and the feedback is lagging, relying on manual intervention.

[0003] Anti-crusting measures mainly rely on passive treatment after crust formation, without establishing a predictive model based on process parameters, and are independent of electrode control, failing to eliminate the causes of crust formation at the source. Currently, there is an urgent need for energy conservation, emission reduction, and intelligent upgrading. Existing technologies have become a bottleneck restricting the development of the industry due to problems such as low control precision, poor crust control effect, high energy consumption, and strong reliance on manual labor.

[0004] Therefore, developing a multi-variable collaborative, proactive anti-shelling, and adaptive intelligent control system has become a key direction for solving industry pain points and meeting urgent industrial needs, possessing significant technological innovation value and application prospects. Summary of the Invention

[0005] The purpose of this invention is to at least solve one of the technical problems existing in the prior art, and to provide an intelligent electrode control system and anti-crusting control method for calcium carbide furnaces, which can solve the above-mentioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent electrode control system and anti-crust control method for a calcium carbide furnace, comprising an intelligent electrode control module, an active anti-crust control module, a data acquisition and preprocessing module, and an intelligent decision support module. The intelligent electrode control module, the active anti-crust control module, and the intelligent decision support module are respectively connected to the data acquisition and preprocessing module, and the active anti-crust control module is connected to the intelligent electrode control module.

[0007] Preferably, the intelligent electrode control module includes a multivariable collaborative control algorithm unit, an electrode position execution unit, and a load optimization unit, wherein the multivariable collaborative control algorithm unit is connected to the electrode position execution unit and the load optimization unit, respectively.

[0008] Preferably, the electrode position execution unit includes a servo driver, a high-precision stepper motor, a ball screw transmission assembly, a laser displacement feedback sensor, and a limit protection switch. The servo driver is connected to the high-precision stepper motor, the high-precision stepper motor is connected to the ball screw transmission assembly, and the laser displacement feedback sensor and the limit protection switch are respectively connected to the multivariable collaborative control algorithm unit.

[0009] Preferably, the active anti-crust control module includes a crust early warning model unit, a linkage intervention execution unit, and a risk index assessment unit. The crust early warning model unit is connected to the risk index assessment unit, the risk index assessment unit is connected to the linkage intervention execution unit, and the linkage intervention execution unit is connected to the intelligent electrode control module.

[0010] Preferably, the data acquisition and preprocessing module includes a sensing layer sensor cluster, a data synchronization unit, and an outlier removal and calibration unit. The sensing layer sensor cluster is connected to the data synchronization unit, the data synchronization unit is connected to the outlier removal and calibration unit, and the outlier removal and calibration unit is connected to the intelligent electrode control module and the active anti-shelling control module, respectively.

[0011] Preferably, the intelligent decision support module includes a historical database, a furnace condition diagnosis unit, an energy consumption analysis unit, and a control parameter optimization suggestion unit. The historical database is connected to the furnace condition diagnosis unit, the energy consumption analysis unit, and the control parameter optimization suggestion unit, respectively, and the control parameter optimization suggestion unit is connected to the intelligent electrode control module.

[0012] Preferably, the historical database is an industrial-grade time-series database, which is connected to a data storage strategy manager and a data backup and recovery component. The data storage strategy manager is configured with a tiered strategy for storing hot data at high frequency and storing cold data in archives.

[0013] Preferably, a three-layer architecture is adopted, consisting of a perception layer, an edge computing layer, and a cloud application layer. The perception layer deploys a perception layer sensor cluster, the edge computing layer deploys a multivariable collaborative control algorithm unit and a shelling early warning model unit, and the cloud application layer deploys a historical database and an energy consumption analysis unit.

[0014] The method for preventing crust formation in the intelligent electrode control system of a calcium carbide furnace includes the following steps:

[0015] S1. Multi-source parameter acquisition: The sensor cluster in the sensing layer (laser displacement sensor, array infrared thermometer, etc.) acquires data such as electrode position, furnace temperature field, raw material moisture, electrode current / voltage, and furnace pressure.

[0016] S2. Data preprocessing: The data synchronization unit adds timestamps and aligns multi-source data. The outlier removal and calibration unit filters out and completes outlier data through the 3σ criterion and trend judgment, and converts it into OPCUA protocol for transmission.

[0017] S3. Intelligent electrode regulation: The multivariable collaborative control algorithm unit performs coupled optimization and MPC prediction correction on the preprocessed data, outputs control commands, the electrode position execution unit drives the electrode to rise and fall smoothly (including position closed-loop feedback), and the load optimization unit dynamically allocates the three-phase electrode load.

[0018] S4. Active anti-crust control: The crust early warning model unit inputs parameters such as raw material composition and temperature gradient to calculate the crust probability value, the risk index assessment unit determines the risk level, and the linkage intervention execution unit triggers feeding adjustment, electrode position fine-tuning or power-electrode coordinated adjustment according to the level.

[0019] S5. Decision and Optimization: The intelligent decision support module outputs furnace condition diagnosis reports and energy consumption analysis curves based on historical databases and real-time operating conditions. The control parameter optimization suggestion unit generates the optimal parameter combination, which is then sent to the control module for iterative optimization after user confirmation.

[0020] Compared with the prior art, the beneficial effects of the present invention are:

[0021] 1. This intelligent electrode control system for calcium carbide furnace improves operational stability. Multi-variable collaborative control reduces the fluctuation range of calcium carbide furnace operation, reduces electrode consumption, strengthens crust prevention and control, and the proactive prediction and linkage intervention mechanism reduces the occurrence rate of crust formation and reduces production interruption time.

[0022] 2. The intelligent electrode control system for the calcium carbide furnace optimizes energy consumption levels. Dynamic load distribution and parameter optimization reduce production energy consumption, save costs, reduce reliance on manual labor, and the adaptive working condition algorithm reduces the labor intensity of operators and avoids the risks of manual operation in high temperature and high dust environments.

[0023] 3. This intelligent electrode control system for calcium carbide furnaces is flexible and adaptable, supporting mainstream furnace types from 3000kVA to 12500kVA and different raw material compositions and operating conditions. It has a short modification cycle and strong expansion capabilities, meeting the requirements of industry intelligent upgrading and priority review for technological innovation and urgent industrial needs. Attached Figure Description

[0024] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0025] Figure 1 This is a schematic diagram of the intelligent electrode control system for the calcium carbide furnace of the present invention. Detailed Implementation

[0026] This section will describe in detail specific embodiments of the present invention. Preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the drawings is to supplement the textual description with graphics, so that people can intuitively and vividly understand each technical feature and overall technical solution of the present invention, but they should not be construed as limiting the scope of protection of the present invention.

[0027] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0028] In the description of this invention, terms such as greater than, less than, and exceeding are understood to exclude the stated number, while terms such as above, below, and within are understood to include the stated number. The use of terms like "first" and "second" is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0029] In the description of this invention, unless otherwise explicitly defined, terms such as "set up," "install," and "connect" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.

[0030] Please see Figure 1 The present invention provides a technical solution: an intelligent electrode control system for a calcium carbide furnace, comprising an intelligent electrode control module, an active anti-crust control module, a data acquisition and preprocessing module, and an intelligent decision support module;

[0031] The intelligent electrode control module includes a multivariable collaborative control algorithm unit, an electrode position execution unit, and a load optimization unit;

[0032] Multivariable Cooperative Control Algorithm Unit: Includes PID neural network algorithm module, model predictive control algorithm module, parameter coupling solver and control command generator. It receives pre-processed multi-source parameters such as current, voltage, electrode position, furnace pressure, etc., realizes dynamic coupling optimization of parameters through PID neural network algorithm, performs rolling prediction and error correction in combination with MPC algorithm, and then processes the correlation between variables by parameter coupling solver. Finally, it outputs precise control commands such as electrode lifting and lowering, transformer tap adjustment through control command generator, avoiding the lag and overshoot problems of single parameter control.

[0033] Electrode position execution unit: includes servo driver, high-precision stepper motor, ball screw transmission assembly, laser displacement feedback sensor and limit protection switch. It receives electrode position control commands output by the algorithm unit, drives the stepper motor by servo driver, and realizes smooth lifting and lowering of the electrode through ball screw transmission assembly. The laser displacement feedback sensor collects electrode position data in real time and feeds it back to the algorithm unit to form a position closed-loop control. The limit protection switch triggers a shutdown protection when the electrode reaches the limit position to ensure equipment safety.

[0034] The load optimization unit includes a power monitoring module, a transformer tap position controller, and a load distribution calculator. The power monitoring module collects the three-phase power data of the electrodes in real time. The load distribution calculator calculates the optimal load ratio of each phase electrode based on the arc balance requirements in the furnace. Then, the transformer tap position controller adjusts the output tap of the corresponding phase transformer to achieve dynamic load distribution and avoid local overheating or energy waste caused by uneven load.

[0035] The active anti-crust control module includes a crust early warning model unit, a linkage intervention execution unit, and a risk index assessment unit;

[0036] The crusting early warning model unit includes a feature parameter input interface, a random forest algorithm model, a model training and updating module, and a risk threshold setting module. The feature parameter input interface receives parameters such as raw material composition, furnace temperature gradient, material layer permeability, and electrode embedment depth. The random forest algorithm model extracts features and calculates risks from the parameters, outputting a crusting probability value. The model training and updating module periodically incorporates new operating data to iteratively optimize the model. The risk threshold setting module allows users to set high, medium, and low risk thresholds based on production experience.

[0037] The linkage intervention execution unit includes an electrode control interface, a feeding system adjustment interface, a power adjustment interface, and an intervention logic controller. Based on the risk level output by the risk index assessment unit, the intervention logic controller triggers the corresponding intervention strategy. In low-risk situations, only the raw material feeding speed is adjusted through the feeding system adjustment interface. In medium-risk situations, the electrode control interface is linked to fine-tune the electrode embedment depth. In high-risk situations, the power adjustment interface is activated simultaneously to reduce local power and adjust the electrode position, thereby achieving multi-system collaborative anti-crusting and avoiding the problem of limited effectiveness of single intervention measures.

[0038] Risk index assessment unit: includes a probability value processing module, a risk level determiner, a historical risk database, and an alarm signal generator. The probability value processing module smooths and filters the probability values ​​output by the crusting early warning model to remove instantaneous interference. The risk level determiner outputs the risk level according to a preset threshold. The historical risk database stores the parameters and processing results of each risk event, providing data support for model optimization. When the risk level reaches a high level, the alarm signal generator triggers an audible and visual alarm to remind operators to pay attention.

[0039] The data acquisition and preprocessing module includes a sensor cluster in the sensing layer, a data synchronization unit, and an outlier removal and calibration unit;

[0040] The sensor cluster in the sensing layer includes: laser displacement sensors (3 units, corresponding to three-phase electrodes), array infrared thermometers (8-12 temperature measuring points, distributed at different heights on the furnace wall), microwave moisture meters (installed on the raw material conveyor belt), current transformers (3 units, measuring electrode current), voltage transformers (3 units, measuring electrode voltage), and pressure sensors.

[0041] Laser displacement sensors accurately measure the lifting and lowering displacement of the electrodes, array-type infrared thermometers acquire data on the temperature field distribution inside the furnace, and microwave moisture meters detect the moisture content of raw materials in real time; current / voltage transformers collect the electrical parameters of the electrodes, and pressure sensors monitor pressure changes inside the furnace, providing comprehensive raw data input for each module.

[0042] Data synchronization unit: includes a timestamp generator, a data alignment processor, and a communication protocol converter. The timestamp generator adds a precise timestamp to the data collected by each sensor. The data alignment processor synchronizes and aligns the data from different sensors according to the timestamps to avoid parameter mismatch caused by acquisition delay. The communication protocol converter converts the analog signals and RS485 digital signals output by the sensors into the OPCUA protocol to achieve compatible communication with the edge computing layer.

[0043] Outlier Removal and Calibration Unit: Includes a 3σ criterion processor, a trend judgment algorithm module, a linear interpolation completer, and a sensor calibration interface. The 3σ criterion processor identifies and removes outlier data that exceeds the statistical range. The trend judgment algorithm module analyzes data change trends and filters out jump data caused by momentary sensor malfunctions. The linear interpolation completer completes the removed outlier data to ensure data continuity. The sensor calibration interface supports periodic parameter calibration of the sensor to maintain measurement accuracy.

[0044] The intelligent decision support module includes a historical database, a furnace condition diagnosis unit, an energy consumption analysis unit, and a control parameter optimization suggestion unit;

[0045] Historical database: Includes industrial-grade time-series database (InfluxDB), data storage strategy manager and data backup and recovery component. The time-series database stores more than one year of operating parameters and supports fast query by time range and parameter type. The data storage strategy manager sets a tiered strategy for storing hot data for high-frequency access and cold data for archive storage. The data backup and recovery component realizes daily automatic backup and data recovery after failure to ensure data security.

[0046] Furnace condition diagnostic unit: includes a standard operating condition threshold library, a real-time parameter comparator, a fault mode identifier, and a diagnostic report generator. The standard operating condition threshold library contains normal parameter ranges for different furnace types and loads. The real-time parameter comparator compares pre-processed real-time data with the thresholds. The fault mode identifier identifies common fault modes such as electrode imbalance, excessive furnace pressure, and crust formation risk based on the comparison results. The diagnostic report generator outputs a diagnostic report that includes the fault type, occurrence time, and recommended handling measures.

[0047] Energy consumption analysis unit: includes energy consumption data calculator, energy consumption curve generator, unit product energy consumption statistician, and energy consumption benchmarking analyzer. The energy consumption data calculator calculates real-time energy consumption based on power monitoring data. The energy consumption curve generator plots daily / weekly / monthly energy consumption change curves. The unit product energy consumption statistician calculates energy consumption per ton of calcium carbide based on production data. The energy consumption benchmarking analyzer compares actual energy consumption with industry advanced levels and historical best levels, and outputs energy consumption gap analysis.

[0048] The control parameter optimization suggestion unit includes a machine learning model (XGBoost algorithm), a historical optimal parameter retrieval tool, an optimization suggestion generator, and a parameter distribution interface. The machine learning model analyzes historical operating data to discover the optimal combination of control parameters under different operating conditions. The historical optimal parameter retrieval tool retrieves the matching historical optimal parameters based on the current operating conditions. The optimization suggestion generator outputs parameter adjustment suggestions. The parameter distribution interface allows users to confirm and send the optimized parameters to the control module with one click, realizing iterative parameter optimization.

[0049] Working principle: The system achieves closed-loop control through a three-layer architecture of perception layer, edge computing layer and cloud application layer. The sensor cluster in the perception layer collects multi-source parameters such as electrode position, furnace temperature and raw material composition. After the data acquisition and preprocessing module performs synchronization alignment, outlier removal and calibration, the data is transmitted to the edge computing layer.

[0050] The multivariable collaborative control algorithm unit of the intelligent electrode control module performs coupled optimization and predictive correction of parameters, and outputs electrode lifting and load adjustment commands, which are executed by the electrode position execution unit and the load optimization unit.

[0051] The active anti-crust control module calculates the crust risk index through the crust early warning model unit. After the risk index assessment unit determines the risk level, the linkage intervention execution unit triggers coordinated intervention measures such as electrode adjustment and feeding adjustment.

[0052] Based on historical data and real-time operating conditions, the intelligent decision support module outputs furnace condition diagnostic reports, energy consumption analysis and parameter optimization suggestions to achieve adaptive operation and continuous optimization of the system.

[0053] To improve operational stability, multi-variable coordinated regulation reduces the fluctuation range of calcium carbide furnace operation and reduces electrode consumption.

[0054] Strengthening crust control and proactive prediction and coordinated intervention mechanisms can reduce the occurrence rate of crust formation and reduce production downtime.

[0055] Optimize energy consumption levels; dynamic load allocation and parameter optimization reduce production energy consumption, save costs, reduce reliance on manual labor, and the adaptive working condition algorithm reduces the labor intensity of operators and avoids the risks of manual operation in high temperature and high dust environments.

[0056] It is flexible and adaptable, supporting mainstream furnace types from 3000kVA to 12500kVA and different raw material compositions and operating conditions. It has a short transformation cycle and strong expansion capabilities, meeting the requirements of industry intelligent upgrading and priority review for technological innovation and urgent industrial needs.

[0057] The method for preventing crust formation in the intelligent electrode control system of a calcium carbide furnace includes the following steps:

[0058] S1. Multi-source parameter acquisition: The sensor cluster in the sensing layer (laser displacement sensor, array infrared thermometer, etc.) acquires data such as electrode position, furnace temperature field, raw material moisture, electrode current / voltage, and furnace pressure.

[0059] S2. Data preprocessing: The data synchronization unit adds timestamps and aligns multi-source data. The outlier removal and calibration unit filters out and completes outlier data through the 3σ criterion and trend judgment, and converts it into OPCUA protocol for transmission.

[0060] S3. Intelligent electrode regulation: The multivariable collaborative control algorithm unit performs coupled optimization and MPC prediction correction on the preprocessed data, outputs control commands, the electrode position execution unit drives the electrode to rise and fall smoothly (including position closed-loop feedback), and the load optimization unit dynamically allocates the three-phase electrode load.

[0061] S4. Active anti-crust control: The crust early warning model unit inputs parameters such as raw material composition and temperature gradient to calculate the crust probability value, the risk index assessment unit determines the risk level, and the linkage intervention execution unit triggers feeding adjustment, electrode position fine-tuning or power-electrode coordinated adjustment according to the level.

[0062] S5. Decision and Optimization: The intelligent decision support module outputs furnace condition diagnosis reports and energy consumption analysis curves based on historical databases and real-time operating conditions. The control parameter optimization suggestion unit generates the optimal parameter combination, which is then sent to the control module for iterative optimization after user confirmation.

[0063] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. An intelligent electrode control system for a calcium carbide furnace, comprising an intelligent electrode control module, an active anti-crust control module, a data acquisition and preprocessing module, and an intelligent decision support module, characterized in that: The intelligent electrode control module, the active anti-crust control module, and the intelligent decision support module are respectively connected to the data acquisition and preprocessing module, and the active anti-crust control module is connected to the intelligent electrode control module.

2. The intelligent electrode control system for a calcium carbide furnace according to claim 1, characterized in that: The intelligent electrode control module includes a multivariable collaborative control algorithm unit, an electrode position execution unit, and a load optimization unit. The multivariable collaborative control algorithm unit is connected to the electrode position execution unit and the load optimization unit, respectively.

3. The intelligent electrode control system for a calcium carbide furnace according to claim 2, characterized in that: The electrode position execution unit includes a servo driver, a high-precision stepper motor, a ball screw transmission assembly, a laser displacement feedback sensor, and a limit protection switch. The servo driver is connected to the high-precision stepper motor, the high-precision stepper motor is connected to the ball screw transmission assembly, and the laser displacement feedback sensor and the limit protection switch are respectively connected to the multivariable collaborative control algorithm unit.

4. The intelligent electrode control system for a calcium carbide furnace according to claim 1, characterized in that: The active anti-crust control module includes a crust early warning model unit, a linkage intervention execution unit, and a risk index assessment unit. The crust early warning model unit is connected to the risk index assessment unit, the risk index assessment unit is connected to the linkage intervention execution unit, and the linkage intervention execution unit is connected to the intelligent electrode control module.

5. The intelligent electrode control system for a calcium carbide furnace according to claim 1, characterized in that: The data acquisition and preprocessing module includes a sensing layer sensor cluster, a data synchronization unit, and an outlier removal and calibration unit. The sensing layer sensor cluster is connected to the data synchronization unit, the data synchronization unit is connected to the outlier removal and calibration unit, and the outlier removal and calibration unit is connected to the intelligent electrode control module and the active anti-shelling control module, respectively.

6. The intelligent electrode control system for a calcium carbide furnace according to claim 1, characterized in that: The intelligent decision support module includes a historical database, a furnace condition diagnosis unit, an energy consumption analysis unit, and a control parameter optimization suggestion unit. The historical database is connected to the furnace condition diagnosis unit, the energy consumption analysis unit, and the control parameter optimization suggestion unit, respectively. The control parameter optimization suggestion unit is connected to the intelligent electrode control module.

7. The intelligent electrode control system for a calcium carbide furnace according to claim 6, characterized in that: The historical database adopts an industrial-grade time-series database, which is connected to a data storage strategy manager and a data backup and recovery component. The data storage strategy manager is configured with a tiered strategy for storing hot data at high frequency and storing cold data in archives.

8. The intelligent electrode control system for a calcium carbide furnace according to claim 1, characterized in that: The system adopts a three-layer architecture consisting of a perception layer, an edge computing layer, and a cloud application layer. The perception layer deploys a perception layer sensor cluster, the edge computing layer deploys a multivariable collaborative control algorithm unit and a crusting early warning model unit, and the cloud application layer deploys a historical database and an energy consumption analysis unit.

9. The intelligent electrode control system and anti-crusting control method for calcium carbide furnaces according to claims 1-8, characterized in that: The method for preventing crust formation in the intelligent electrode control system of a calcium carbide furnace includes the following steps: S1. Multi-source parameter acquisition: The sensor cluster in the sensing layer (laser displacement sensor, array infrared thermometer, etc.) acquires data such as electrode position, furnace temperature field, raw material moisture, electrode current / voltage, and furnace pressure. S2. Data preprocessing: The data synchronization unit adds timestamps and aligns multi-source data. The outlier removal and calibration unit filters out and completes outlier data through the 3σ criterion and trend judgment, and converts it into OPCUA protocol for transmission. S3. Intelligent electrode regulation: The multivariable collaborative control algorithm unit performs coupled optimization and MPC prediction correction on the preprocessed data, outputs control commands, the electrode position execution unit drives the electrode to rise and fall smoothly (including position closed-loop feedback), and the load optimization unit dynamically allocates the three-phase electrode load. S4. Active anti-crust control: The crust early warning model unit inputs parameters such as raw material composition and temperature gradient to calculate the crust probability value, the risk index assessment unit determines the risk level, and the linkage intervention execution unit triggers feeding adjustment, electrode position fine-tuning or power-electrode coordinated adjustment according to the level. S5. Decision and Optimization: The intelligent decision support module outputs furnace condition diagnosis reports and energy consumption analysis curves based on historical databases and real-time operating conditions. The control parameter optimization suggestion unit generates the optimal parameter combination, which is then sent to the control module for iterative optimization after user confirmation.

Images