CN113514239A - On-line detection method, system and storage medium for air distribution board - Google Patents

Abstract

The present application provides an on-line detection method, system and storage medium for an air distribution plate, which are used to detect the blockage of the air distribution plate in real time, quickly and accurately. The method for on-line detection of an air distribution plate includes: obtaining at least state information of an air distribution plate and a discharge scraper in a fluidized bed, where the state information includes operating state information and/or structural state information; Perform preprocessing to obtain target feature data; input the target feature data into a detection model, the detection model is at least used to detect the hole blocking situation of the air distribution board; obtain feedback from the detection model about the air distribution Hole plugging information for the board. By adopting the solution provided in this application, manpower and time costs are saved, and real-time detection of the air distribution panel can be performed quickly and effectively.

Description

On-line detection method, system and storage medium for air distribution board

technical field

The application relates to the technical field of dry heavy medium fluidized bed coal preparation, and in particular, to an on-line detection method, equipment and storage medium for an air distribution plate.

Background technique

Dry heavy medium fluidized bed technology is a technology that utilizes gas-solid two-phase fluidization properties to form a "quasi-fluid" gas-solid suspension with a certain density in the bed. The selected material is in the bed according to its own density difference. It realizes the stratification of floating and sinking, and collects the floating/sinking products through scraper and other discharge devices to realize the separation process of materials, and has been successfully applied in the field of coal preparation, with obvious technical advantages.

With the industrial application of dry heavy medium fluidized bed in the field of coal preparation, the air distribution effect and blockage of the stepped air distribution plate have attracted more and more attention. The blockage of the stepped air distribution plate generally includes: the leakage of fine-grained particles and the accumulation of gangue. On the one hand, the air distribution effect is an important factor that directly affects the stability of the bed density, and the blockage of the step air distribution plate will cause the local instability of the bed step air distribution, reduce its air distribution capacity, and be unfavorable for the bed density. On the other hand, in the actual continuous separation process, the accumulation of gangue layer on the air distribution plate will not only cause certain resistance to the gangue discharge scraper, increase energy consumption, but also cause wear and tear of the scraper sometimes. At the same time, a certain thickness of the gangue layer will also seriously affect the air distribution effect of the cascade air distribution board, and the secondary air distribution formed by it will cause a certain degree of disturbance to the cascade air distribution effect. At present, manual inspection is used to check whether the stepped air distribution plate is blocked, and when the stepped air distribution plate is blocked, it is also manually inspected for the position and area of the blocked holes, which requires a lot of manpower and time. The cost is extremely detrimental to the production.

SUMMARY OF THE INVENTION

The present application provides an on-line detection method, system and storage medium for an air distribution plate, which are used to detect the blockage of the air distribution plate in real time, quickly and accurately.

The present application provides an on-line detection method for an air distribution panel, including:

Obtain at least the status information of the air distribution plate and the discharge scraper in the fluidized bed, where the status information includes operating status information and/or structural status information;

Preprocessing the state information to obtain target feature data;

Inputting the target feature data into a detection model, where the detection model is at least used to detect the hole blocking condition of the air distribution plate;

Obtain the hole blocking information about the air distribution plate fed back by the detection model.

Optionally, also include:

build a target model;

Obtain the historical state information of the air distribution plate and the discharge scraper and the hole blocking information of the air distribution plate corresponding to the historical state information;

The target model is trained based on at least the historical state information and hole blocking information to obtain the detection model.

Optionally, the status information includes air tightness information of the air distribution plate, pressure drop information, material thickness accumulated on the air distribution plate, motor torque information of the discharge scraper, and the discharge scraper. One or more of the force information of the panel on the air distribution panel.

Optionally, the plugged hole information includes plugged hole area and plugged hole location information.

Optionally, the preprocessing of the state information to obtain target feature data includes:

Feature extraction is performed on the state information based on feature engineering to obtain the target feature data, where the target feature data includes information in the state information that is directly affected by the hole blocking state of the air distribution plate.

Optionally, also include:

Obtain the pressure signal of the pressure of the fluidized bed bed corresponding to the historical plugging information;

The training of the target model based on at least the historical state information and hole blocking information to obtain the detection model, including:

The target model is trained based on the historical state information, hole blocking information and pressure signal, so as to obtain the detection model capable of detecting the hole blocking situation of the air distribution plate and the influence of the hole blocking area on the pressure fluctuation of the bed. .

Optionally, before the preprocessing of the state information to obtain the target feature data, the method further includes:

Determine the air tightness of the air distribution plate and the pressure drop in different areas based on the state information, and determine the motor power and motor torque of the discharge scraper at the same time;

When it is determined that one or more of the air tightness, pressure drop in different areas, motor power, and motor torque are abnormal, adjust the air distribution plate and/or the discharge scraper based on the abnormal data and the abnormal position If the abnormal position generated data is still abnormal after adjustment, the state information is preprocessed to obtain the target feature data.

Optionally, also include:

Determine whether the hole blocking information is consistent with the actual hole blocking situation of the air distribution plate, and obtain the corresponding result;

The detection model is trained based on the target feature data, hole blocking information, and the corresponding results.

Another embodiment of the present application also provides an on-line detection system for an air distribution panel, including:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions that can be executed by the one processor, and the instructions are executed by the at least one processor to implement the online detection method for an air distribution panel described in any of the foregoing embodiments.

Another embodiment of the present application further provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the air distribution panel online detection system, the air distribution panel detection system can realize the description in any of the above embodiments. The online detection method of the air distribution board.

Other features and advantages of the present application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description, claims, and drawings.

The technical solutions of the present application will be described in further detail below through the accompanying drawings and embodiments.

Description of drawings

The accompanying drawings are used to provide a further understanding of the application, and constitute a part of the specification, and together with the embodiments of the application, they are used to explain the application, and do not constitute a limitation to the application. In the attached image:

Fig. 1 is the flow chart of the online detection method of the air distribution plate in the embodiment of the application;

2 is a flowchart of an on-line detection method for an air distribution panel in another embodiment of the application;

3 is a flowchart of an on-line detection method for an air distribution panel in another embodiment of the application;

4 is a flowchart of an on-line detection method for an air distribution panel in another embodiment of the application;

Fig. 5 is the actual application flow chart of the on-line detection method of the air distribution plate in another embodiment of the application;

FIG. 6 is a schematic diagram of a connection relationship between components of an on-line detection system for an air distribution panel in an embodiment of the present application.

Detailed ways

The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, but not to limit the present application.

FIG. 1 is a flowchart of an on-line detection method for an air distribution panel in an embodiment of the application. As shown in FIG. 1 , the method can be implemented as the following steps S11-S14:

In step S11, at least state information of the air distribution plate and the discharge scraper in the fluidized bed is obtained, and the state information includes operation state information and/or structural state information;

In step S12, the state information is preprocessed to obtain target feature data;

In step S13, the target feature data is input into a detection model, and the detection model is at least used to detect the hole blocking condition of the air distribution plate;

In step S14, the hole blocking information about the air distribution plate fed back by the detection model is obtained.

The solutions provided in the examples of this application are applicable to fluidized bed systems, such as dry heavy medium fluidized bed systems, and can also be applied to platforms that provide on-line detection of air distribution plates for fluidized beds. In application programs, for example, users can Download detection applications based on mobile devices or central control devices, and then realize online monitoring and online detection of air distribution panels.

In this application, when the air distribution plate is detected, it is necessary to obtain at least the status information of the air distribution plate and the discharge scraper in the fluidized bed. , for example, including the pressure information on the air distribution plate, whether the structure is deformed, air tightness, the opening rate of all air holes, etc., and can also include the operation status of the discharge scraper used to move the air distribution plate to scrape materials. Information, such as motor running status information including the discharge scraper, determines whether the discharge scraper is operating efficiently and whether there is any obstruction that affects efficiency. The above state information can be obtained by setting sensors with different functions. For devices such as motors, the operating state can also be obtained by communicating with the central control equipment and processing platform of the fluidized bed. The specific method is uncertain. After the required state information is obtained, the state information is preprocessed to obtain the target feature data that can be input to the detection model and used for calculation by the detected model. The target feature data is closely related to the blockage of the air holes of the air distribution plate. related feature data. The detection model is at least a model for detecting the hole blocking of the air distribution plate. Based on the detection model, the hole blocking situation of the air distribution plate can be quickly and accurately detected, and the hole blocking data can be obtained. Based on the hole blocking Data, the staff can know the status of the air distribution board in time, and take corresponding cleaning measures, which improves the maintenance efficiency of the air distribution board, saves time and labor costs, and can effectively ensure the normal operation of the fluidized bed.

Optionally, the air distribution board can be a common air distribution board or a stepped air distribution board. In this embodiment, the stepped air distribution board is used as an example for description. Before performing step S11, it is necessary to assemble the cascade air distribution plate to ensure that the opening ratio of the air distribution plate at the raw coal feed end is greater than that of the clean coal discharge end, so as to ensure the coal preparation effect and accuracy. Then, check the air tightness of the assembled air distribution plate, so that there is no side leakage in the area of the air distribution plate of the dry heavy medium fluidized bed, and then determine the pressure drop of the air distribution plate in each area of the fluidized bed, and according to It is necessary to debug the pressure drop of the air distribution plate at different areas to ensure that the pressure drop of the air distribution plate at the raw coal feed end is small, and the pressure drop of the air distribution plate at the clean coal discharge end is large, so as to achieve the cascade air distribution effect.

Further, a plurality of sensors with different functions are installed on the fluidized bed in this embodiment to at least sense the structural state and/or operating state information of the air distribution plate and the discharge scraper, so as to enable the execution of this The processing device/processing device of the embodiment method (such as the central control device, detection platform, mobile device, etc. described above) obtains required state information. Specifically, in this embodiment, before the air distribution plate is detected, the thickness of the accumulated material on the air distribution plate, such as the thickness of the accumulated gangue layer, is also detected online by a sensor, and then the gangue discharge scraper motor is adjusted based on the thickness of the material. power to operate properly. In addition, in this embodiment, the torque of the driving motor of the gangue discharge scraper is detected online, so as to control the fluidization gas velocity of the fluidized bed based on the torque, so as to improve the fluidization quality of the bed. Optionally, in this embodiment, on-line real-time detection of the bed density of the fluidized bed is also performed, so that the bed can maintain an optimal sorting density in real time. The sorting density may refer to the theoretical sorting density, which is determined on the selectivity curve according to the ash content requirements of the re-selected clean coal.

FIG. 2 is a flowchart of an on-line detection method for an air distribution panel in another embodiment of the application. As shown in FIG. 2 , the method in this embodiment further includes:

Step S15: establish a target model;

Step S16: obtaining the historical state information of the air distribution plate and the discharge scraper and the hole blocking information of the air distribution plate corresponding to the historical state information;

Step S17: Train the target model based on at least the historical state information and hole blocking information to obtain the detection model.

Specifically, in order to realize the online and real-time detection of the air distribution panel, the detection process needs to be efficient and accurate. Therefore, in order to achieve this purpose, a detection model is trained in this embodiment to realize the detection of the air distribution panel based on the detection model. real-time online detection. When applying, a target model needs to be established first, and the target model can be any model used to achieve prediction, or any model used to achieve classification, including convolutional neural network models, binary neural network models, specific Multiple linear regression models and the like may also be included. When the target model is determined and the structure of the target model is obtained, the historical state information of the air distribution board and the discharge scraper will be obtained, that is, the historical operation information and/or structural state information of the air distribution board and the discharge scraper, and The hole blocking information about the air distribution board corresponding to the historical status information, that is, the information on whether the air distribution board is blocked, is preprocessed and input into the target model to train the target model. For example, the target model can be changed from a large number of The preprocessing data obtained by the training and learning, and then obtain a detection model that can predict whether the air distribution plate is blocked based on the state information of the air distribution plate and the discharge scraper.

The preprocessing of the historical state information described in the above embodiment and the preprocessing of the currently obtained state information described in step S12 include the same processing steps, which are both used to obtain target feature data. The preprocessing process is specific. include:

Feature extraction is performed on the state information based on feature engineering to obtain the target feature data, where the target feature data includes information in the state information that is directly affected by the hole blocking state of the air distribution plate.

Feature engineering is to perform a series of engineering processing on the original data, and extract it into features, which are used as input for algorithms and models. Essentially, feature engineering is a process of representing and presenting data. In practical work, feature engineering aims to remove impurities and redundancy in the original data, and design more efficient features to characterize the relationship between the solved problem and the predictive model. In this embodiment, the obtained state information is preprocessed based on feature engineering, for example, feature normalization is performed on the state information, so as to obtain the information in the state information that is directly affected by the hole blocking state of the air distribution plate, that is, the target feature data, For example, it can be the motor power of the discharge scraper, the torque of the motor, whether it can run normally, the pressure drop of the air distribution plate, the pressure and so on. The above target model is trained based on the obtained historical target feature data as input data, and the blockage of the air distribution plate corresponding to the historical target feature data is used as output data for training. The detection model obtained by training is also based on the input target features. The data is used to predict the current blockage of the air distribution board.

Further, the status information in this embodiment includes air tightness information, pressure drop information of the air distribution plate, material thickness accumulated on the air distribution plate, motor torque information of the discharge scraper, and air distribution plate. One or more of the force information of the material on the air distribution board. For example, when the air distribution plate is blocked, the material cannot be discharged normally, and the discharge scraper is affected by the material accumulated on the air distribution plate, and when the material cannot be discharged normally, the material accumulation will squeeze the air distribution plate, making the air distribution plate Abnormal pressure is generated, that is, the force on the air distribution plate will exceed the preset range (the pressure value can assist in determining the blocking position and area of the air distribution plate). At the same time, affected by this, the motor torque of the discharge scraper , the power is abnormal, so it is not within the required range. At this time, the detection model can predict whether the current air distribution board is blocked according to the eigenvalues of the above features.

Optionally, the plugged hole information in this embodiment includes plugged hole area and plugged hole location information. After the detection model is input with the target feature data, it will calculate and predict according to the target feature data to obtain the information about whether the current air distribution plate is blocked. What is the total area and the location of the blocked holes to assist the staff to quickly determine the blocked air distribution board and the location of the blockage on it, and clean it in time to ensure the normal operation of the fluidized bed. Through the above method of this embodiment, not only the real-time detection of the blocked holes of the air distribution plate can be realized, but also the detection and maintenance efficiency of the blocked holes of the air distribution plate can be effectively improved, which saves manpower and time costs. Compared with manual detection, the accuracy is higher. Also stronger.

Further, in order to enrich the functions of the detection model, so that it can not only detect the blockage of the air distribution plate, but also determine the influence on the fluctuation of the bed pressure of the fluidized bed when the air distribution plate is blocked. A flowchart of the method for detecting an air distribution panel according to another embodiment of the application, as shown in FIG. 3 , in this embodiment, when training the detection model, the method further includes:

Step S18: obtaining the pressure signal of the pressure of the fluidized bed bed corresponding to the historical hole plugging information;

The training of the target model based on at least the historical state information and hole blocking information to obtain the detection model, including:

Step S19: Train the target model based on the historical state information, the hole blocking information and the pressure signal, so as to obtain the hole blocking situation that can detect the air distribution plate, and the effect of the hole blocking area on the pressure fluctuation of the bed. the detection model.

For example, when the fluidized bed is running in historical time, the pressure on the bed can be detected by a pressure sensor arranged on the bed. Specifically, the pressure signal can be received, and the time domain and frequency domain of the pressure signal can be used to detect the bed. Whether the pressure on the layer is qualified. The time domain and the frequency domain are the basic properties of the signal. Based on the time domain and the frequency domain, the interaction between the signal and third-party objects such as interconnects can be clearly reflected. When the air distribution plate is blocked, the pressure on the bed will fluctuate at the position and area of the blocked hole. Therefore, when the user collects training data, he can also collect the historical plugging information corresponding to the fluidized bed bed. The pressure signal of pressure and its related attribute information are integrated in the training data, that is, the training data includes pressure signal information, historical state information and hole blocking information. By training the detection model through the above training data, the detection model can also have the ability to detect blocked holes. The ability of the zone to influence fluctuations in the pressure of the bed.

Further, the method in this embodiment also includes:

Determine whether the hole blocking information is consistent with the actual hole blocking situation of the air distribution plate, and obtain the corresponding result;

The detection model is trained based on the target feature data, hole blocking information, and the corresponding results.

For example, when the hole blocking information output by the detection model is inspected by the staff, it is found that the data detected by the detection model is consistent with the hole blocking situation of the actual air distribution board, then the data input to the detection model and the output of the detection model can be used. The data is added to the training data to further train the detection model. Currently, if the detection is correct, the training may not be performed based on this data. However, only the detected data, that is, the hole blocking information output by the detection model, does not match the actual hole blocking situation of the air distribution plate. At this time, the input data, output data and actual hole blocking data can be input into the detection model. To further train the detection model, correct its weights to improve its detection accuracy.

Optionally, FIG. 4 is a flow chart of a method for detecting an air distribution plate according to another embodiment of the present application. In order to reduce the detection load of the detection model and at the same time realize a more rapid and targeted detection of blockage of the air distribution plate, this embodiment Before the detection is performed, that is, before the currently obtained state information is preprocessed to obtain the target feature data, as shown in Figure 4, it also includes:

Step S20: determine the air tightness of the air distribution plate and the pressure drop situation in different regions based on the state information, and determine the motor power and motor torque of the discharge scraper simultaneously;

Step S21: When it is determined that one or more of the air tightness, the pressure drop in different areas, the motor power, and the motor torque are abnormal, adjust the air distribution plate and/or based on the abnormal data and abnormal position. For the discharge scraper, if the data generated at the abnormal position after adjustment is still abnormal, the state information is preprocessed to obtain the target feature data.

For example, before the air distribution board is put into detection, the air tightness and pressure drop of the air distribution board can be determined based on the obtained state information, and the motor power and motor torque of the discharge scraper can be determined at the same time. If any of the above One or more parameters are abnormal. If they do not meet the corresponding threshold range, they can be adjusted based on the preset adjustment strategy and the currently detected parameter values. If the motor power is low, increase the power and the air tightness is poor. , then notify the staff to check the air tightness and make repairs. If the current situation cannot be improved after the inspection, the plugging of the air distribution board can be detected. That is, after checking and adjusting the functional devices such as the air distribution plate of the fluidized bed, if the situation improves after adjustment, it means that the air distribution plate is not blocked, and if the situation cannot be improved after adjustment, it can be determined that it is the air distribution. If there is a problem with the board, it needs to be checked for hole plugging. In this way, the processing load of the detection model can be reduced, and at the same time, the operation of the fluidized bed can be adjusted more quickly, so as to ensure the normal operation of the fluidized bed as a whole.

Specifically, FIG. 5 is a flow chart of the practical application of the online detection method of the air distribution panel in the embodiment of the application. As shown in FIG. 5 , in order to better illustrate the method of this embodiment, the following is a more detailed description in conjunction with specific embodiments. illustrate:

Taking the fluidized bed as a dry heavy medium fluidized bed and the air distribution plate as an example, the cascade air distribution plate needs to be assembled first, and ensure that the opening rate of the air distribution plate at the feed end of the raw coal is greater than that of the clean coal. discharge end;

Check the air tightness of the assembled step air distribution board, so that there is no side leakage in the area of the dry heavy medium fluidized bed air distribution board;

Adjust the pressure drop of the air distribution plate at different areas to ensure that the pressure drop of the air distribution plate at the raw coal feeding end is small, and the pressure drop of the air distribution plate at the clean coal discharge end is large, so as to achieve the effect of cascade air distribution;

After the stepped air distribution board is assembled, the sensor can be used to detect the thickness of the gangue layer on the air distribution board online, and the motor power of the gangue discharge scraper can be adjusted to make it run normally;

Through online detection of the torque of the gangue discharge scraper driving motor, the fluidization gas velocity is controlled and the fluidization quality of the bed is improved;

On-line real-time detection of the bed density, so that the bed reaches the best sorting density;

When the air distribution board is blocked, collect the torque information of the gangue discharge scraper motor;

Use the strain sensor installed in the air distribution plate to collect the force of the gangue layer on the stepped air distribution plate, and obtain the blockage position and area information according to its size;

Collect the original data of the effect of plugging area and plugging position on the time domain and frequency domain analysis of the bed pressure signal;

Characterize the above-obtained data based on feature engineering, that is, preprocess the data;

The random forest algorithm is used to enable the machine to train and learn from a large amount of preprocessed data, such as the motor torque, the strain sensor detection data of the air distribution plate, the data of the area and position of the blocked holes, and the data of the area of the blocked holes and the position of the blocked holes to the bed. The data affected by layer pressure fluctuations are used as training data to train the target model;

Modify the initially established target model, divide the obtained training data into training set and test set, then analyze the revised target model based ^on the results obtained from the training set and test set, and determine the target model according to the coefficient of determination R2. Finally, a stable and reliable detection model is formed. The detection model is shown in Figure 5. It can be regarded as a combination of the motor torque model, the bed pressure fluctuation model, and the air distribution plate strain sensor model. The motor torque model is used for According to the characteristic parameters of the motor torque, it is determined whether the air distribution plate is blocked. The bed pressure fluctuation model is used to determine whether the air distribution plate is blocked by the bed pressure according to the bed pressure characteristic parameters, and then determine whether the air distribution plate is blocked. It is used to obtain the material accumulation thickness parameter on the air distribution plate, and based on this parameter to determine whether the air distribution plate is blocked, and can assist in determining the position and area of the blockage. Whether the air panel is blocked, if it is blocked, determine its blockage position and area information, that is, the detection model in this embodiment has the functions of the above three models at the same time, and then realizes the blockage of the air distribution panel. In order to detect the internal structure of the model, the detection model described above and the detection model in this embodiment are the same detection model;

When using the detection model to detect the blockage of the air distribution board online, the relevant information of the basic data obtained online is used as the input feature, and the state information that is about to be obtained is processed to form the target feature data as the input data of the model;

Input the above input features into the trained detection model;

The blockage information of the air distribution board fed back by the detection model is obtained, and the staff can quickly and accurately locate the blocked hole area and the blocked hole position on the air distribution board based on the blockage information;

Characterize the basic data immediately obtained online, and re-input the characterized data and the data output by the detection model into the detection model to retrain it, and then improve the detection model's ability to locate the blockage of the air distribution board. Detection accuracy.

FIG. 6 is a schematic diagram of the hardware structure of an on-line inspection system 600 for an air distribution panel according to an embodiment of the application, as shown in FIG. 6 , including:

at least one processor 602; and,

a memory 604 in communication with the at least one processor; wherein,

The memory stores instructions that can be executed by the one processor, and the instructions are executed by the at least one processor to implement the online detection method for an air distribution panel described in any of the foregoing embodiments.

6, the air distribution panel online detection system 600 may include one or more of the following components: a processing component 602, a memory 604, a power supply component 606, a multimedia component 608, an audio component 610, an input/output (I/O) interface 612 , sensor component 614 , and communication component 616 .

The processing component 602 generally controls the overall operation of the air distribution plate online detection system 600, such as obtaining the state information of the air distribution plate and the discharge scraper in the fluidized bed, and preprocessing the state information to obtain target characteristic data. The processing component 602 may include one or more processors 620 to execute instructions to perform all or some of the steps of the methods described above. Additionally, processing component 602 may include one or more modules that facilitate interaction between processing component 602 and other components. For example, processing component 602 may include a multimedia module to facilitate interaction between multimedia component 608 and processing component 602.

The memory 604 is configured to store various types of data to support the operation of the air distribution panel online inspection system 600 . Examples of such data include instructions for any application or method operating on the air distribution panel in-line inspection system 600, such as text, pictures, video, and the like. Memory 604 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

Power supply assembly 606 provides power for the various components of air distribution panel in-line inspection system 600 . Power supply components 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to onboard control system 600 .

The multimedia component 608 includes a screen that provides an output interface between the air distribution panel on-line inspection system 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. A touch sensor can sense not only the boundaries of a touch or swipe action, but also the duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 608 may also include a front-facing camera and/or a rear-facing camera. When the air distribution panel online detection system 600 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.

Audio component 610 is configured to output and/or input audio signals. For example, audio component 610 includes a microphone (MIC) configured to receive external audio signals when air distribution panel online inspection system 600 is in operating modes, such as alarm mode, recording mode, voice recognition mode, and voice output mode. The received audio signal may be further stored in memory 604 or transmitted via communication component 616 . In some embodiments, audio component 610 also includes a speaker for outputting audio signals.

The I/O interface 612 provides an interface between the processing component 602 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.

Sensor assembly 614 includes one or more sensors for providing various aspects of condition assessment for air distribution panel online inspection system 600 . For example, sensor assembly 614 may include a sound sensor. In addition, the sensor component 614 can detect the open/closed state of the air distribution panel online detection system 600, the relative positioning of the components, for example, the components are the display and keypad of the air distribution panel online detection system 600, and the sensor component 614 can also detect the air distribution panel. The operating state of the panel online detection system 600 or a component of the air distribution panel online inspection system 600, such as the air distribution panel operating state, structural state, discharge scraper operating state, etc., the orientation or acceleration of the air distribution panel online inspection system 600 The temperature change of the system 600 is detected online by deceleration/deceleration and air distribution panels. Sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, a material accumulation thickness sensor, or a temperature sensor.

The communication component 616 is configured to enable the air distribution panel online inspection system 600 to provide wired or wireless communication capabilities with other devices and the cloud platform. The air distribution panel online detection system 600 can be connected to a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 616 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the air distribution panel online inspection system 600 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs) ), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to implement the online detection method for an air distribution panel described in any of the above embodiments.

The present application also provides a computer-readable storage medium. When the instructions in the storage medium are executed by a processor corresponding to the air distribution panel online detection system, the air distribution panel detection system can realize the air distribution panel described in any of the above embodiments. Online detection method.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein, including but not limited to disk storage, optical storage, and the like.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims (10)

1. An online detection method for a wind distribution plate is characterized by comprising the following steps:

at least obtaining state information of an air distribution plate and a discharging scraper in the fluidized bed, wherein the state information comprises operation state information and/or structure state information;

preprocessing the state information to obtain target characteristic data;

inputting the target characteristic data into a detection model, wherein the detection model is at least used for detecting the hole blocking condition of the air distribution plate;

and obtaining hole blocking information which is fed back by the detection model and related to the air distribution plate.

2. The method of claim 1, further comprising:

establishing a target model;

acquiring historical state information of the air distribution plate and the discharge scraper and hole plugging information of the air distribution plate corresponding to the historical state information;

and training the target model at least based on the historical state information and the hole blocking information to obtain the detection model.

3. The method of claim 2, wherein the status information comprises one or more of air tightness information of the grid plate, pressure drop information, thickness of material stacked on the grid plate, motor torque information of the discharge scraper, and force information of the material stacked on the grid plate.

4. The method of claim 3, wherein the plugged hole information comprises plugged hole area and plugged hole location information.

5. The method of claim 4, wherein the preprocessing the state information to obtain target feature data comprises:

and extracting the characteristics of the state information based on characteristic engineering to obtain the target characteristic data, wherein the target characteristic data comprises information which is directly influenced by the hole plugging state of the air distribution plate in the state information.

6. The method of claim 2, further comprising:

obtaining a pressure signal of the pressure applied to the fluidized bed layer corresponding to the historical hole plugging information;

the training the target model based on at least the historical state information and the hole plugging information to obtain the detection model comprises:

and training the target model based on the historical state information, the hole plugging information and the pressure signal to obtain a detection model capable of detecting the hole plugging condition of the air distribution plate and the influence of a hole plugging area on the bed pressure fluctuation.

7. The method according to claim 1, wherein before preprocessing the state information to obtain target feature data, further comprising:

determining the air tightness and pressure drop condition of the air distribution plate based on the state information, and simultaneously determining the motor power and the motor torque of the discharging scraper plate;

and when one or more of the air tightness, the pressure drop conditions of different areas, the motor power and the motor torque are determined to be abnormal, adjusting the air distribution plate and/or the discharging scraper plate based on abnormal data and abnormal positions, and preprocessing the state information to obtain the target characteristic data if the data generated at the abnormal positions after adjustment are still abnormal.

8. The method of claim 1, further comprising:

determining whether the hole plugging information is consistent with the actual hole plugging condition of the air distribution plate or not, and obtaining a corresponding result;

training the detection model based on the target feature data, the hole plugging information and the corresponding results.

9. The utility model provides a grid plate on-line measuring system which characterized in that includes:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the one processor to perform the method of online test of a wind panel according to any one of claims 1 to 8.

10. A computer-readable storage medium, wherein when executed by a processor corresponding to the air distribution plate online detection system, the instructions enable the air distribution plate online detection system to implement the air distribution plate online detection method according to any one of claims 1 to 8.

Images