Intelligent coal sample treatment system
Through the intelligent coal sample treatment system, the drying and humidification device combined with machine learning algorithms are used to solve the problems of uneven treatment of wet coal sample and insufficient distribution accuracy, achieving high accuracy and high efficiency of coal sample treatment, and adapting to different coal samples need.
Patent Information
- Application Number
- CN202411678777.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-22
- Publication Date
- 2025-01-07
AI Technical Summary
Traditional coal sample treatment methods have problems such as uneven wet coal sample treatment and insufficient coal sample allocation accuracy, resulting in low accuracy and efficiency of coal quality detection.
An intelligent coal sample treatment system was designed, including mixing module, sensor module and control module. Through drying devices, humidification devices and machine learning algorithms, the moisture content of coal sample is dynamically adjusted to ensure that it meets the standards, and through the screening and analysis modules Improve particle size and chemical composition detection accuracy.
It achieves high accuracy and consistency in coal sample treatment, reduces artificial errors, improves the efficiency and accuracy of the coal quality detection process, and adapts to the treatment needs of different types of coal samples.
Smart Images
Figure CN119269199A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of coal quality testing, and in particular to an intelligent coal sample processing system. Background Art
[0002] In the coal industry, quality control of incoming coal is one of the key links to ensure fuel supply and efficient operation of boiler equipment. In order to accurately test coal samples, the representativeness and uniformity of the samples must be guaranteed. Traditional coal sample processing methods rely on manual operations, such as manual sampling, distribution, mixing, screening, etc. These manual operations inevitably have certain errors.
[0003] The existing technology introduces an intelligent coal sample processing system to ensure high precision and high consistency of coal sample processing and reduce the impact of human errors. Although the introduction of an intelligent coal sample processing system has achieved certain results in practical applications, it still faces problems such as uneven processing of wet coal samples. Summary of the invention
[0004] In response to the above problems, the present application provides an intelligent coal sample processing system that can solve the problems of uneven processing of wet coal samples and insufficient coal sample distribution accuracy.
[0005] To achieve the purpose of this application, this application provides the following technical solutions:
[0006] The present application provides an intelligent coal sample processing system, comprising: a mixing module, a sensor module and a control module; the mixing module comprises a mixing device, a drying device and a humidifying device; the mixing device is connected to the drying device and the humidifying device respectively, and the drying device and the humidifying device are used to adjust the moisture content of the coal sample; the sensor module comprises a humidity sensor, and the humidity sensor is connected to the mixing device, and is used to monitor the characteristic data of the coal sample and transmit the characteristic data of the coal sample to the control module;
[0007] The control module includes: a data storage unit, used to store the characteristic data and system operating parameters; an intelligent processing unit, used to establish an association model between the coal sample characteristic data and the system operating parameters based on a machine learning algorithm, and to determine whether the moisture content of the coal sample meets the standard; the machine learning algorithm includes a regression algorithm and a classification algorithm, the regression algorithm is used to establish an association model between the coal sample characteristic data and the system operating parameters, and the classification algorithm is used to determine whether the moisture content of the coal sample meets the standard; a dynamic control unit, used to adjust the system operating parameters of the mixing device according to the association model; the coal sample characteristic data includes: the moisture content of the coal sample; the system operating parameters include: coal sample drying temperature, coal sample humidification intensity and ambient temperature.
[0008] In a possible implementation, the intelligent processing unit includes a feature extraction module; the feature extraction module is used to perform dynamic feature extraction on the data stored in the data storage unit; the feature extraction module extracts key features in the coal sample characteristic data, including: the moisture change trend of the coal sample, the moisture change rate; the intelligent processing unit establishes an association mapping relationship between the key features in the coal sample characteristic data and the system operating parameters through a regression algorithm.
[0009] In a possible implementation, the control module also includes a prediction unit; the prediction unit is based on a deep learning algorithm and is used to predict the optimal system operating parameters of the system; the deep learning algorithm includes a multilayer perceptron, which is used to train and predict the system historical data and coal sample characteristic data; the input data obtained by the prediction unit includes the moisture content of the coal sample, historical operating parameters and ambient temperature; the output of the prediction unit includes the optimal drying temperature, humidification intensity and the operating time of the mixing device; the prediction result is transmitted to the dynamic control unit for adjusting the operating state of the mixing module.
[0010] In a possible implementation, the control module also includes a feedback control unit; the feedback control unit is connected to the data storage unit, and is used to receive the coal sample characteristic data, and compare it with the optimal system operating parameters output by the prediction unit to calculate the deviation; the deviation value is used to generate a correction signal; the correction signal includes a drying temperature increment, a humidification intensity adjustment value or a mixing time correction amount, and the feedback control unit transmits the correction signal to the dynamic control unit to adjust the operating state of the mixing module.
[0011] In a possible implementation, the system also includes a screening module, the inlet of which is connected to the outlet of the mixing module; the screening module includes a screening device, and the mesh aperture of the screening device is adjustable; the sensor module is connected to the screening device, and is used to monitor the coal sample particle size data and transmit it to the control module; the control module adjusts the mesh aperture according to the particle size data to achieve screening of coal samples of different particle sizes.
[0012] In a possible implementation, the system also includes an analysis module, the inlet of the analysis module is connected to the outlet of the screening module; the analysis module includes an analysis device and a data processing unit, the analysis device is used to analyze the coal sample to obtain analysis data; the control module is connected to the data processing device, and is used to receive the analysis data and generate a coal sample report; the analysis data includes: chemical composition, calorific value, and ash content of the coal sample.
[0013] In a possible implementation, the system also includes a sampling module; the outlet of the sampling module is connected to the inlet of the mixing module; the sampling module includes a sampling device and a scanning device, and the sampling device is used to collect coal samples; the scanning device includes an image processing unit, and the image processing unit is used to generate a three-dimensional distribution map of the coal pile and transmit it to the control module; the sensor module includes a force sensor, and the force sensor is used to monitor the force data of the sampling device and transmit it to the control module; the control module adjusts the force and position of the sampling device according to the force data and the coal sample distribution map.
[0014] In a possible implementation, the scanning device also includes a multi-angle image acquisition unit; the multi-angle image acquisition unit is used to generate a three-dimensional distribution map of the coal pile by capturing multi-perspective images of the coal sample; the control module analyzes the distribution density and irregular distribution of the coal sample according to the three-dimensional distribution map, and adjusts the position of the sampling device.
[0015] In a possible implementation, the sampling module also includes at least two sampling devices, which are arranged at different positions and used to collect coal samples at different positions; the control module adjusts the sampling ratio and position of each sampling device according to the three-dimensional distribution map of the coal sample and the monitoring data generated by the scanning device.
[0016] In a possible implementation, the system further includes a distribution module, the inlet of the distribution module is connected to the outlet of the sampling module; the distribution module includes a flow control device and a distribution device; the sensor module is connected to the flow control device, for monitoring the coal sample particle size data, and transmitting it to the control module; the control module controls the coal sample flow output by the flow control device according to the coal sample particle size data; the distribution device receives the coal sample output by the flow control device, and distributes it to the mixing module.
[0017] Through the intelligent coal sample processing system provided by the present application, the sensor module collects data, and the control module calculates the control parameters, and the system operation parameters of the drying device and the humidifying device can be dynamically adjusted so that the moisture content of coal samples with different moisture contents meets the standard when mixed. The system of the present application flexibly responds to the processing needs of different types of coal samples, reduces human intervention and errors, and improves the efficiency and accuracy of the entire coal quality detection process. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application.
[0019] Figure 1A schematic diagram of the structure of the system provided in the embodiment of the present application;
[0020] Figure 2 A schematic diagram of module interaction of a control module provided in an embodiment of the present application;
[0021] Figure 3 A schematic diagram of a flow chart of a prediction unit provided in an embodiment of the present application;
[0022] Figure 4 A schematic diagram of a coal pile of various different types of coal provided in an embodiment of the present application;
[0023] Figure 5 This is a schematic diagram of a coal pile with a particle size distribution provided in an embodiment of the present application.
[0024] In the figure, 11. mixing device, 12. drying device, 13. humidifying device, 21. humidity sensor, 22. particle size sensor, 23. force sensor, 24. flow sensor, 25. weight sensor, 3. control module, 41. screening device, 51. sampling device, 52. scanning device, 53. conveying device, 61. flow control device, 62. distribution device; 7. analysis module, 8. display module, 9. alarm module, 101. Yijia coal, 102. Huai mixed coal, 103. gas coal, 104. lignite, 105. long flame coal. DETAILED DESCRIPTION
[0025] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0026] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features; in the description of this application, unless otherwise specified, "plurality" means two or more.
[0027] The inventors of the present invention have found that coal sample processing systems are widely used in the field of coal quality monitoring and analysis, and their main functions include coal sample collection, mixing, moisture adjustment, particle size screening and analysis. Traditional coal sample processing systems mostly rely on manual operation or semi-automatic equipment, which is difficult to meet the requirements of industrial production for efficient, accurate and repeatable coal sample processing. Based on this, in the embodiment of the present invention provided by the inventor, an intelligent coal sample processing process is realized through the cooperation of a drying device, a humidifying device, a control module and a sensor module. Through the present invention, the processing efficiency and accuracy of coal samples with different moisture contents can be significantly improved, meeting the needs of industrial production for high-quality coal sample detection.
[0028] Combine the following Figures 1 to 3 Describe the technical solution of the present invention:
[0029] like Figure 1-Figure 2 As shown, an intelligent coal sample processing system provided by an embodiment of the present application includes: a mixing module, a sensor module and a control module 3; the mixing module includes a mixing device 11, a drying device 12 and a humidifying device 13; the mixing device 11 is connected to the drying device 12 and the humidifying device 13 respectively, and the drying device 12 and the humidifying device 13 are used to adjust the moisture content of the coal sample;
[0030] The sensor module includes a humidity sensor 21, which is connected to the mixing device 11 and is used to monitor the characteristic data of the coal sample and transmit the characteristic data of the coal sample to the control module 3; the control module 3 includes: a data storage unit, which is used to store the characteristic data and system operating parameters; an intelligent processing unit, which is used to establish an association model between the characteristic data of the coal sample and the system operating parameters based on the machine learning algorithm, and to determine whether the moisture content of the coal sample meets the standard; the machine learning algorithm includes a regression algorithm and a classification algorithm, the regression algorithm is used to establish an association model between the characteristic data of the coal sample and the system operating parameters, and the classification algorithm is used to determine whether the moisture content of the coal sample meets the standard; a dynamic control unit, which is used to adjust the system operating parameters of the mixing device 11 according to the association model; the coal sample characteristic data includes: the moisture content of the coal sample; the system operating parameters include: the drying temperature of the coal sample, the humidification intensity of the coal sample and the ambient temperature.
[0031] In an embodiment of the present application, by setting a humidity sensor 21 in the mixing device 11, it is possible to monitor the moisture content of the coal sample in the mixing device 11 and transmit it to the control module 3. The data unit of the control module 3 stores the moisture content data of the coal sample. In addition, it is also necessary to store the operating parameters of the system, such as: the drying temperature of the coal sample by the drying device 12, the humidification intensity of the coal sample by the humidifying device 13, and the ambient temperature of the system. After the intelligent processing unit obtains the above data, it preprocesses the data, such as removing invalid data. Then, a regression algorithm is used to analyze the data to generate a correlation model between the moisture content of the coal sample and the system operating parameters, so as to calculate the optimal drying temperature or humidification intensity according to the correlation model. After that, the dynamic control unit adjusts the mixing device 11 or the drying device 12 according to the data so that the moisture content of the coal sample meets the standard.
[0032] Specifically, if the moisture content standard of the coal sample is 15%, and the humidity sensor 21 detects that the moisture content of the coal sample is 30%, the data storage unit saves the real-time data, and combines the previously stored historical data, and predicts that the optimal drying temperature is 70°C through the regression algorithm in the intelligent processing unit, and the dynamic control unit adjusts the drying device 12 to dry the coal sample in the mixing device 11. After the drying device 12 is completed, the humidity sensor 21 continues to transmit the moisture content of the coal sample to the dynamic control unit, and the control unit uses the classification algorithm to determine whether the moisture content of the coal sample after drying meets the standard. If it meets the standard, the dynamic control unit controls the drying device 12 to close.
[0033] In addition, when the humidity sensor 21 detects that the moisture content of the coal sample is 10%, the intelligent processing unit calculates that the optimal humidification intensity is 20%, and the dynamic control unit adjusts the humidification device 13 to humidify the coal sample so that its moisture content reaches the standard.
[0034] It should be noted that in the system of the present application, the reason why the ambient temperature is used as the system operation parameter is that the ambient temperature is one of the important factors affecting the treatment effect. For example, the coal sample heats up quickly at a low ambient temperature, and the drying device 12 has low efficiency, thus requiring a higher drying temperature. At a high ambient temperature, the humidification efficiency is high, but excessive humidification will cause the moisture content of the coal sample to exceed the standard.
[0035] The present application collects data through the sensor module, and the control module 3 calculates the control parameters, and can dynamically adjust the system operation parameters of the drying device 12 and the humidifying device 13, so that the moisture content of coal samples with different moisture contents meets the standard when they are mixed. The system of the present application flexibly responds to the processing requirements of different types of coal samples, reduces human intervention and errors, and improves the efficiency and accuracy of the entire coal quality detection process.
[0036] In a feasible implementation, the intelligent processing unit includes a feature extraction module; the feature extraction module is used to perform dynamic feature extraction on the data stored in the data storage unit; the feature extraction module extracts key features in the coal sample feature data, including: the moisture change trend and moisture change rate of the coal sample; the intelligent processing unit establishes an association mapping relationship between the key features in the coal sample feature data and the system operation parameters through a regression algorithm.
[0037] In the embodiment of the present application, the feature extraction module needs to perform feature extraction on the historical data stored in the data storage unit. In order to ensure accurate extraction, the acquisition frequency of the sensor module can be set to sample once every 1 second or 5 seconds to generate high-frequency time series data. Through the analysis and calculation of the system historical data by the feature extraction module, the system can automatically adjust the drying and humidification strategies according to the historical data for different types of coal samples, such as coal samples with high moisture content or uneven particle size, thereby improving the system's ability to handle complex working conditions and reducing the need for human intervention.
[0038] It should be noted that after the data collection is completed, the feature extraction module needs to extract the dynamic features of the data. For example, the sliding window analysis method can be used. The sliding window method is a local statistical analysis tool suitable for extracting the dynamic features of time series data. One input parameter of the sliding window analysis method is the window time length n, and the input is, for example, 30 seconds. Correspondingly, the sampling frequency is once every 5 seconds; at this time, the window collects 6 data in total. Another input parameter is the sliding step length Δt, and the input is, for example, 10 seconds. The sliding step length will be recalculated after each sliding. After the parameter input is completed, combined with the system operation, when the sliding window collects 6 data in total within 30 seconds, it will be calculated, calculated and output. The result data includes: the rate of change of the moisture content of the coal sample, the instantaneous change trend of the moisture content, and the variance, which is used to quantify the volatility of the moisture data.
[0039] The calculation method of the above result data is as follows:
[0040] The rate of change of moisture content of coal sample:
[0041]
[0042] Among them, ΔW is the average rate of change, W t+n is the moisture content at the end of the window, W t is the moisture content at the beginning of the window, and n is the window time.
[0043] Instantaneous change trend of moisture content:
[0044]
[0045] Where, ΔW t+n Moisture change rate at the end of the current window, ΔWt-1 The moisture change rate of the previous window, Δt represents the sliding step of the window.
[0046] After calculating according to the sliding window, the moisture change rate and gradient of the coal sample can be extracted in sections. Then the mean value and variance σ within the sliding window can be further calculated. 2 Data is collected and plotted based on the data to obtain the moisture change curve of the coal sample.
[0047] As a feasible implementation method, Figure 2 As shown, the control module 3 of the embodiment of the present application further includes: a prediction unit and a feedback control unit; the prediction unit is based on a deep learning algorithm and is used to predict the optimal system operating parameters of the system;
[0048] The deep learning algorithm includes a multilayer perceptron, which is used to train and predict the system historical data and coal sample characteristic data; the input data obtained by the prediction unit includes the moisture content of the coal sample, the historical operating parameters and the ambient temperature; the output of the prediction unit includes the optimal drying temperature, the humidification intensity and the operating time of the mixing device 11; the prediction result is transmitted to the dynamic control unit for adjusting the operating state of the mixing module. The feedback control unit is connected to the data storage unit, and is used to receive the coal sample characteristic data, and compare it with the optimal system operating parameters output by the prediction unit to calculate the deviation; the deviation value is used to generate a correction signal; the correction signal includes a drying temperature increment, a humidification intensity adjustment value or a mixing time correction value, and the feedback control unit transmits the correction signal to the dynamic control unit to adjust the operating state of the mixing module.
[0049] In the embodiment of the present application, the prediction unit uses a deep learning algorithm to predict the optimal system operating parameters, including drying temperature, humidification intensity, and the operating time of the mixing device 11. The model specifically uses, for example, a multilayer perceptron. After the prediction data is transmitted to the dynamic control unit, the dynamic control unit receives the data provided by the correction prediction unit and adjusts the mixing module device to ensure that the coal sample processing process is always stable within the target range.
[0050] Specifically, Figure 3As shown, step S1: prepare input parameters and output parameters: input parameters: coal sample moisture content, ambient temperature, rate of change of coal sample moisture content and instantaneous change trend of moisture content; system current system operating parameters: such as drying temperature, humidification intensity and running time of mixing device 11, system historical data, etc. Prepare output parameters: optimal drying temperature, humidification intensity and running time of mixing device 11. Step S2: conduct training, the first step of training S201: clean the data to remove abnormal data; the second step of training S202: divide the data set into 80% training set and 20% test set. The third step of training S203: conduct model training on the training set, and the model training adopts multi-layer perceptron MLP. The input layer of MLP: accepts coal sample feature data, such as moisture content, particle size distribution, etc. Hidden layer: nonlinearly transforms the input feature data through activation function (such as ReLU) to extract deep relationship. Output layer: outputs predicted value, such as optimal drying temperature and humidification intensity. The fourth step of training S204: Use the test set to verify the model: evaluate the model performance through the mean square error or accuracy. Step S3: Output the prediction results and transmit them to the dynamic control unit to achieve dynamic adjustment of the moisture content of the coal sample.
[0051] Feedback control also needs to receive prediction unit data, and at the same time receive the monitoring data of the sensor module stored in the data storage module, compare the two sets of data, and calculate the deviation. If the deviation exceeds the threshold range, the feedback control unit will generate a correction signal based on PID control, and transmit the correction signal to the dynamic control unit, and the dynamic control unit will adjust the drying device 12 or the humidification device 13. PID control is a prior art. By monitoring the deviation in real time and generating a correction signal, PID control can dynamically adjust the operating parameters of the coal sample processing system, significantly improving the stability and efficiency of the system. Applying PID control to the coal sample drying and humidification process can achieve precise closed-loop control and ensure the accuracy and uniformity of the moisture adjustment of the coal sample.
[0052] Deviation calculation method:
[0053] e(t) = predicted value - detected value
[0054] Where e(t) is the deviation.
[0055] Generate correction signal based on PID control:
[0056]
[0057] Where u(t) is the correction signal, K p is the proportional coefficient, which is the direct influence of the control deviation on the correction signal. is the integral coefficient, which controls the correction strength of the cumulative error, K dis the differential coefficient, which controls the response speed of the deviation change rate. is the derivative of the deviation, which represents the rate of change of the deviation.
[0058] In the embodiment of the present application, the feature extraction module, prediction unit, feedback control unit and dynamic control unit are combined to achieve accurate adjustment of the moisture content of the coal sample of the present application. At the same time, the coal sample processing efficiency can be improved by dynamically optimizing the operating parameters. The embodiment of the present application combines machine learning and deep learning technology, and the system has adaptive capabilities and can automatically adjust the processing strategy according to the characteristics of different coal samples. At the same time, the stability of the system is improved, and the various modules of the control center are used to ensure stable system operation and reduce manual intervention.
[0059] In a possible implementation, Figure 1 As shown, the system also includes a screening module, the inlet of the screening module is connected to the outlet of the mixing module; the screening module includes a screening device 41, and the mesh aperture of the screening device 41 is adjustable; the sensor module is connected to the screening device 41, and is used to monitor the coal sample particle size data and transmit it to the control module 3; the control module 3 adjusts the mesh aperture according to the particle size data to achieve screening of coal samples of different particle sizes.
[0060] In the embodiment of the present application, the particle size sensor 22, the feature extraction module, the prediction unit and the feedback control unit can also realize the dynamic adjustment of the aperture of the sieve hole of the screening device 41. The screening device 41 can screen coal samples of different particle sizes, while improving the screening efficiency and accuracy.
[0061] As a feasible implementation method, Figure 1 As shown, the coal sample processing system provided in the embodiment of the present application also includes a sampling module; the outlet of the sampling module is connected to the inlet of the mixing module; the sampling module includes a sampling device 51 and a scanning device 52, the sampling device 51 is used to collect coal samples; the scanning device 52 includes an image processing unit, the image processing unit is used to generate a distribution map of the coal pile, and transmit it to the control module 3; the sensor module includes a force sensor 23, the force sensor 23 is used to monitor the force data of the sampling device 51, and transmit it to the control module 3; the control module 3 adjusts the force and position of the sampling device 51 according to the force data and the coal sample distribution map.
[0062] In the embodiment of the present application, the sampling device 51 cooperates with the scanning device 52, and can dynamically adjust the sampling position according to the distribution state of the coal sample, so that the coal sample taken is accurate and uniform. A force sensor 23 is installed on the sampling device 51, and the force data of the sampling device 51 is fed back to the control module 3 in real time. The control module 3 dynamically adjusts the force of the sampling device 51 to avoid affecting the sampling quality due to excessive or insufficient force of the sampling device 51. Through the automated sampling process, the complexity and error of manual operation are reduced, and the efficiency of coal sample collection is improved. In a possible implementation, the sampling module includes a conveying device 53 for conveying the collected coal sample to the next station of the system.
[0063] In a possible implementation, the scanning device 52 further includes a multi-angle image acquisition unit; the multi-angle image acquisition unit is used to generate a three-dimensional distribution map of the coal pile by capturing multi-viewing angle images of the coal sample;
[0064] The control module 3 analyzes the distribution density and irregular distribution of the coal sample according to the three-dimensional distribution diagram, and adjusts the position of the sampling device 51 .
[0065] In the embodiment of the present application, the detailed processing process of the three-dimensional distribution map is as follows:
[0066] Step 1: Collecting point cloud data: First, collect point cloud data through the scanning device 52 deployed in the coal yard. In order to ensure the integrity of the data, scan and obtain coal pile data from multiple angles. In the scanning process, in order to make the data clearer, a high-resolution scanning device 52 is used to make the coal pile particle details more clearly displayed. In addition, the ground calibration point tool can be used to improve the measurement accuracy. The ground calibration point is an important tool for improving the accuracy of data acquisition in the three-dimensional modeling of the coal pile. Especially when using drone photogrammetry or laser scanning technology, high-density calibration points can ensure that the three-dimensional model has higher spatial accuracy. Step 2: Perform point cloud processing: De-noise the scanned data and optimize the resolution. Then perform point cloud splicing to splice the multi-angle scan data into a complete coal pile model. The above process can use point cloud processing software such as CloudCompare or Geomatic. Step 3: Density distribution analysis, analyze the surface density of the coal pile, and the changes in the density inside the coal pile, so as to generate a density isosurface distribution. Step 4: 3D model construction, import the processed point cloud and density data into the modeling tool, and the modeling tool uses, for example, Blender or 3DMax. Pseudo-color rendering is added to intuitively display density distribution, height changes and abnormal particle positions. Step 5: Generate a three-dimensional distribution map. Use visualization tools to generate a three-dimensional distribution map, such as a density map, a morphology map, etc. The generated data is transmitted to the data storage unit and the dynamic processing unit. The dynamic processing unit controls the sampling device 51 to perform sampling according to the three-dimensional distribution map of the coal pile.
[0067] Among them, Figure 4 As shown, it is a picture of a plurality of different types of coal piled together. Table 1 is the specific data of the coal pile, which can specifically show the length, width, height, weight and volume data of various types of coal. The control module 3 can reasonably set the position of the sampling device 51 according to the length, width and height of the coal pile.
[0068]
[0069]
[0070] Table 1
[0071] like Figure 5 As shown, the particle size of the coal pile can be specifically scanned, and the control module 3 can adjust the position of the sampling device 51 according to the particle size of the coal pile.
[0072] By setting up a multi-angle image acquisition unit, the three-dimensional distribution map of the coal pile can be obtained more accurately, and it is easier to determine the boundary and sampling position of the coal sample.
[0073] In a possible implementation, the sampling module further includes at least two sampling devices 51, which are arranged at different positions for collecting coal samples at different positions; the control module 3 adjusts the sampling ratio and position of each sampling device 51 according to the three-dimensional distribution map of the coal sample and the monitoring data generated by the scanning device 52;
[0074] By setting up multiple sampling points, it is convenient to sample from different positions, which can reduce the sample error caused by uneven sampling positions, ensure that the coal samples are more representative, and cover the coal sample characteristics at different positions of the coal pile.
[0075] As a feasible implementation method, Figure 1 As shown, the coal sample processing system provided in the embodiment of the present application also includes a distribution module, the inlet of the distribution module is connected to the outlet of the sampling module; the distribution module includes a flow control device 61 and a distribution device 62; the sensor module is connected to the flow control device 61, for monitoring the coal sample particle size data, and transmitting it to the control module 3; the control module 3 controls the coal sample flow output by the flow control device 61 according to the coal sample particle size data; the distribution device 62 receives the coal sample output by the flow control device 61, and distributes it to the mixing module or the screening module.
[0076] In an embodiment of the present application, the distribution module receives the coal sample delivered by the conveying device 53 of the sampling module, and then uses the particle size sensor 22 to monitor whether the particle size of the coal sample meets the screening requirements. If the requirements are met, the distribution module directly distributes the coal sample to the screening module. If the requirements are not met, the coal sample needs to be distributed to the mixing module. In addition, if the wet coal sample is prone to adhesion and agglomeration, it also needs to be distributed to the mixing module. During the distribution process, a flow sensor 24 is needed to monitor the flow of the coal sample. For example, for wet coal samples, the flow rate can be reduced to ensure that the coal sample does not block the distribution device 62. The weight sensor 25 can ensure that the weight of the coal sample during the distribution process meets the requirements to avoid causing the system to be overloaded. The flow controller is used to accurately control the flow of the coal sample through the distribution device 62 to ensure that the distribution amount of the coal sample meets the predetermined requirements during the entire distribution process. The coordination of the particle size sensor 22, the flow controller and the distribution device 62 ensures the consistency and accuracy of the entire distribution process.
[0077] As a feasible implementation method, Figure 1 As shown, the coal sample processing system provided in the embodiment of the present application also includes an analysis module 7, the inlet of the analysis module 7 is connected to the outlet of the screening module; the analysis module 7 includes an analysis device and a data processing unit, and the analysis device is used to analyze the coal sample to obtain analysis data; the control module 3 is connected to the data processing device, and is used to receive the analysis data and generate a coal sample report; the analysis data includes: chemical composition, calorific value, and ash content of the coal sample.
[0078] In the embodiment of the present application, after the analysis module 7 obtains the coal sample processed by the screening module, it uses an analysis device such as a high-precision analysis instrument to analyze and detect the coal sample, mainly detecting the chemical composition, calorific value, ash content, etc. of the coal sample. The analysis module 7 interacts with the control module 3 to transmit the analysis results to the control module 3, and the control module 3 generates a coal sample report.
[0079] In a possible embodiment, the system further includes a display module 8, which is connected to the output end of the control module 3 and is used to display the system operation status and coal sample data; the display module 8 provides a parameter adjustment function and adjusts each module according to the data transmitted by the control module 3.
[0080] In a possible implementation, the system further includes an alarm module 9, which is connected to the control module 3. The sensor monitors abnormal data of the coal sample and transmits it to the control module 3. The control module 3 sends the abnormal data to the alarm module 9, and the alarm module 9 issues an alarm.
[0081] Working principle: In actual use, a scanning device 52 will be arranged in advance to obtain the distribution map of the coal pile, and a sampling device 51 needs to be arranged in advance. Multiple sampling devices 51 can be deployed, such as the top and bottom of the coal pile. Some sampling devices 51 need to be deployed on the track, so that the control system can dynamically adjust the position of the sampling device 51 after receiving the distribution map of the coal pile to ensure that the sampling is reasonable and representative. After the sampling is completed, the coal sample is transported to the distribution module through the conveying device 53. The distribution module distributes the coal sample to the mixing module or the screening module according to the particle size of the coal sample and whether the coal sample is adhered and agglomerated. During the distribution process, the flow sensor 24, the weight sensor 25 and the flow controller are used to control the flow and weight of the distributed coal sample to prevent the coal sample from piling up and the system from being overloaded. The coal sample entering the mixing module enters the mixing device 11, and the humidity sensor 21 installed on the mixing device 11 monitors the moisture content of the coal sample and transmits it to the control module 3. The control module 3 controls the moisture content of the coal sample within a reasonable range through the drying device 12 and the humidifying device 13. Specifically, for dry coal samples with too low moisture content, the control module 3 adjusts the humidifying device 13 to humidify the coal samples. For dry coal samples with too high moisture content, the control module 3 adjusts the drying device 12 to dry the coal samples. After the moisture content reaches a reasonable standard, the mixing device 11 mixes the coal sample. After the mixing is completed, the coal sample enters the screening module, and the screening module promptly feeds back the particle size of the coal sample to the control module 3 according to the particle size sensor 22. The control module 3 adjusts the mesh aperture according to the coal sample particle size data to screen the coal sample. After the screening is completed, the coal sample enters the analysis module 7, and the analysis device is used to analyze the coal sample to obtain analysis data; after receiving the analysis data, the control module 3 generates a coal sample report.
[0082] In the several embodiments provided in the present application, it should be understood that the disclosed systems, modules and methods can be implemented in other ways. For example, the module embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, modules or units, which can be electrical, mechanical or other forms.
[0083] The above embodiments are only used to illustrate the technical solution of the present application, but not to limit it. The present application is not limited to the exact structure described above and illustrated in the accompanying drawings, and it cannot be determined that the specific implementation of the present application is limited to these descriptions. For ordinary technicians in the technical field to which the present application belongs, various changes and modifications made without departing from the concept of the present application should be deemed to belong to the protection scope of the present application.
Claims
1. An intelligent coal sample processing system, characterized in that: include: Mixing module, sensor module and control module; The mixing module includes a mixing device, a drying device and a humidifying device; The mixing device is connected to the drying device and the humidifying device respectively, and the drying device and the humidifying device are used to adjust the moisture content of the coal sample; The sensor module includes a humidity sensor, which is connected to the mixing device and is used to monitor the coal sample characteristic data and transmit the coal sample characteristic data to the control module; The control module comprises: A data storage unit, used to store the characteristic data and system operation parameters; An intelligent processing unit, used to establish a correlation model between the coal sample characteristic data and the system operation parameters based on a machine learning algorithm, and to determine whether the moisture content of the coal sample meets the standard; The machine learning algorithm includes a regression algorithm and a classification algorithm. The regression algorithm is used to establish a correlation model between the coal sample characteristic data and the system operation parameters. The classification algorithm is used to determine whether the moisture content of the coal sample meets the standard. A dynamic control unit, used for adjusting the system operating parameters of the mixing device according to the correlation model; The coal sample characteristic data includes: the moisture content of the coal sample; The system operating parameters include: coal sample drying temperature, coal sample humidification intensity and ambient temperature.
2. The intelligent coal sample processing system according to claim 1, characterized in that: The intelligent processing unit includes a feature extraction module; The feature extraction module is used to perform dynamic feature extraction on the data stored in the data storage unit; The feature extraction module extracts key features from the coal sample feature data, including: the moisture change trend and moisture change rate of the coal sample; The intelligent processing unit establishes an association mapping relationship between the key features in the coal sample characteristic data and the system operation parameters through a regression algorithm.
3. The intelligent coal sample processing system according to claim 2, characterized in that: The control module also includes a prediction unit; The prediction unit is based on a deep learning algorithm and is used to predict optimal system operating parameters of the system; The deep learning algorithm includes a multi-layer perceptron for training and predicting the system historical data and coal sample characteristic data; The input data acquired by the prediction unit include the moisture content of the coal sample, historical operating parameters and ambient temperature; The output of the prediction unit includes the optimal drying temperature, humidification intensity and operation time of the mixing device; The prediction result is transmitted to the dynamic control unit for adjusting the operating state of the mixing module.
4. The intelligent coal sample processing system according to claim 3, characterized in that: The control module also includes a feedback control unit; The feedback control unit is connected to the data storage unit and is used to receive the coal sample characteristic data and compare it with the optimal system operation parameters output by the prediction unit to calculate the deviation; The deviation value is used to generate a correction signal; The correction signal includes a drying temperature increment, a humidification intensity adjustment value or a mixing time correction value. The feedback control unit transmits the correction signal to the dynamic control unit to adjust the operating state of the mixing module.
5. The intelligent coal sample processing system according to claim 1, characterized in that: The system further comprises a screening module, wherein an inlet of the screening module is connected to an outlet of the mixing module; The screening module comprises a screening device, and the aperture of the screen of the screening device is adjustable; The sensor module is connected to the screening device and is used to monitor the coal sample particle size data and transmit it to the control module; The control module adjusts the aperture of the sieve according to the particle size data to achieve screening of coal samples with different particle sizes.
6. The intelligent coal sample processing system according to claim 5, characterized in that: The system further comprises an analysis module, wherein an inlet of the analysis module is connected to an outlet of the screening module; The analysis module includes an analysis device and a data processing unit, wherein the analysis device is used to analyze the coal sample to obtain analysis data; The control module is connected to the data processing device and is used to receive analysis data and generate a coal sample report; The analysis data include: chemical composition, calorific value and ash content of the coal sample.
7. The intelligent coal sample processing system according to claim 1, characterized in that: The system also includes a sampling module; The outlet of the sampling module is connected to the inlet of the mixing module; The sampling module includes a sampling device and a scanning device, wherein the sampling device is used to collect coal samples; the scanning device includes an image processing unit, and the image processing unit is used to generate a three-dimensional distribution map of the coal pile and transmit it to the control module; The sensor module includes a force sensor, and the force sensor is used to monitor the force data of the sampling device and transmit the data to the control module; The control module adjusts the force and position of the sampling device according to the force data and the coal sample distribution map.
8. An intelligent coal sample processing system according to claim 7, characterized in that: The scanning device also includes a multi-angle image acquisition unit; The multi-angle image acquisition unit is used to generate a three-dimensional distribution map of the coal pile by capturing multi-viewing angle images of the coal sample; The control module analyzes the distribution density and irregular distribution of the coal sample according to the three-dimensional distribution diagram, and adjusts the position of the sampling device.
9. The intelligent coal sample processing system according to claim 8, characterized in that: The sampling module also includes at least two sampling devices, The at least two sampling devices are arranged at different positions and are used to collect coal samples at different positions; The control module adjusts the sampling ratio and position of each sampling device according to the three-dimensional distribution map of the coal sample and the monitoring data generated by the scanning device.
10. The intelligent coal sample processing system according to claim 7, characterized in that: The system further comprises a distribution module, wherein an inlet of the distribution module is connected to an outlet of the sampling module; The distribution module includes a flow control device and a distribution device; The sensor module is connected to the flow control device and is used to monitor the coal sample particle size data and transmit it to the control module; The control module controls the flow rate of the coal sample output by the flow control device according to the coal sample particle size data; The distribution device receives the coal sample output by the flow control device and distributes it to the mixing module.