Automatic mining filling system based on machine vision and Internet of Things and control method

Abstract

The invention discloses an automatic mining filling system based on machine vision and Internet of Things and a control method. The system comprises a machine vision module, an Internet of Things monitoring module, a data fusion analysis module, an autonomous optimization module and a multistage early warning maintenance module. The data fusion analysis module processes the identification data, the equipment operation parameters and the environment parameters, generates a comparison report and transmits the comparison report to the autonomous optimization module; and the autonomous optimization module adjusts working parameters of the mining equipment and the filling equipment based on the comparison report. According to the invention, based on information data obtained by the machine vision module and the Internet of Things monitoring module, fusion analysis is carried out, then a control strategy is optimized, and working parameters of each device are adjusted, so that dependence on artificial experience is reduced, efficiency is improved, and resource waste and potential safety hazards are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of mining and filling, in particular to an automatic mining and filling system, and also to a mining and filling control method. Background Art

[0002] As global demand for resources continues to increase, the mining industry faces multiple challenges such as improving production efficiency, reducing operating costs, ensuring operational safety, and protecting the environment. Traditional mining operations are highly dependent on manual judgment and operation, resulting in low efficiency, frequent safety hazards, and serious waste of resources. With the rapid development of machine vision and Internet of Things technologies, such technologies are increasingly widely used in the field of industrial automation, opening up new ideas and solutions for the transformation and upgrading of the mining industry.

[0003] Existing technical means have the following shortcomings: strong manual dependence, widespread data island phenomenon, delayed fault warning, and lack of effective basis for optimization decision-making. In traditional mining operations, the judgment of ore type and quality, the adjustment of mining and filling strategies, and the adjustment of equipment operating parameters mainly rely on manual experience. This not only leads to inefficiency and difficulty in achieving accurate resource utilization and efficient output, but is also easily affected by human factors, which in turn leads to resource waste and safety hazards. Secondly, multi-source data such as equipment operation data and environmental parameters in the mining process are often stored in a scattered manner, lacking effective integration and analysis, and it is difficult to form valuable decision support information. On the other hand, traditional early warning systems mainly rely on post-analysis, making it difficult to achieve early warning of equipment failures and environmental risks, resulting in long downtime, high maintenance costs, and increased safety hazards. Summary of the invention

[0004] The present invention proposes an automated mining and filling system and control method based on machine vision and the Internet of Things, the purposes of which are: 1. To reduce the reliance on manual experience; 2. To achieve effective integration and analysis of data to provide support for control decisions; 3. To achieve early warning of equipment failures and environmental risks.

[0005] The technical solution of the present invention is as follows: An automated mining and filling system based on machine vision and the Internet of Things, comprising a machine vision module, an Internet of Things monitoring module, a data fusion analysis module, and an autonomous optimization module; The machine vision module is used to identify the type, distribution and quality of the ore, and transmit the identification data to the data fusion analysis module; The IoT monitoring module is used to collect the operating parameters and environmental parameters of each device during the mining and filling process, and transmit the operating parameters and environmental parameters to the data fusion analysis module; The data fusion analysis module processes the identification data, equipment operation parameters and environmental parameters, generates a comparison report and transmits it to the autonomous optimization module; The autonomous optimization module adjusts the operating parameters of the mining equipment and filling equipment based on the comparison report.

[0006] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things: it also includes a multi-level early warning maintenance module; The comparison report generated by the data fusion analysis module is also transmitted to the multi-level early warning maintenance module; the multi-level early warning maintenance module determines whether there is a failure risk based on the comparison report and issues an early warning.

[0007] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things: the machine vision module collects spectral data of the mining surface through a spectrometer, performs noise removal, endmember extraction, spectral unmixing and abundance inversion operations on the spectral data, and obtains spectral analysis data; the spectral analysis data is the identification data, including ore type, distribution and quality.

[0008] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things: the Internet of Things monitoring module uses an Internet of Things sensor to collect data.

[0009] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things: the data fusion analysis module includes a real-time database, a historical database, a reference data storage unit and a data analysis unit; The input end of the real-time database is connected to the output end of the machine vision module and the output end of the Internet of Things monitoring module respectively; The input end of the historical database is connected to the output end of the real-time database; The input end of the data analysis unit is respectively connected with the output end of the real-time database, the output end of the historical database and the output end of the reference data storage unit.

[0010] As a further improvement of the described automated mining and filling system based on machine vision and the Internet of Things: The real-time database receives the identification data from the machine vision module and the equipment operation parameters and environmental parameters from the Internet of Things monitoring module, and then performs data standardization processing on the received data according to the data source to generate a real-time data set; a real-time data set contains the values ​​of each data item at the current time point, and the data item refers to multiple data types from the identification data, operation parameters and environmental parameters; the real-time database transmits the obtained real-time data set to the historical database and the data analysis unit respectively; The historical database stores the real-time data set from the real-time database as a historical data set; The reference data storage unit stores a plurality of reference data sets corresponding to different working conditions; a reference data set contains standard values ​​of each data item; the reference data storage unit also stores standard solutions corresponding to each reference data set, each standard solution records recommended values ​​of working parameters of mining equipment and filling equipment under the corresponding working conditions; The data analysis unit reads all reference data sets and compares them with the real-time data sets horizontally, and also compares the real-time data sets vertically with the historical data sets corresponding to a previous time point stored in the historical database to obtain a comparison report.

[0011] As a further improvement of the automated mining filling system based on machine vision and the Internet of Things: when comparing, the real-time data set is compared with the historical data set or reference data set as the comparison data set in the following manner: Suppose the sequence of values ​​of each data item in the real-time data set is , is the number of data items, and the sequence formed by the values ​​of each data item in the comparison data set is , calculate the Pearson correlation coefficient: ; in, and Sequence and sequence The mean of The Pearson correlation coefficient between the real-time data set and the historical data set is recorded as the historical trend , the real-time dataset is compared with the The Pearson correlation coefficient of the reference data set is recorded as the working condition trend .

[0012] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things: the way to adjust the working parameters of the mining equipment and the filling equipment in the autonomous optimization module is: The working condition trend The working condition corresponding to the maximum value is regarded as the current working condition, and then the recommended values ​​of the working parameters of the mining equipment and the filling equipment in the standard solution corresponding to the working condition are obtained; The difference between the vector formed by the obtained recommended working parameter values ​​and the vector formed by the current working parameter setting values ​​of the mining equipment and the filling equipment is recorded as the parameter adjustment benchmark. ; Based on the historical trends reported in the comparison Calculate the parameter adjustment coefficient ; Vector Each element in is sent to all devices as the adjustment amount of the corresponding working parameters to adjust the parameters in real time.

[0013] As a further improvement of the automated mining and filling system based on machine vision and the Internet of Things, in the multi-level early warning maintenance module, early warning is performed in the following ways: The threshold setting identification unit compares all data items in the current real-time data set element with the threshold of each data item, finds out the data items that exceed the threshold range, and determines the potential fault risk type according to these data items; For each data item that exceeds the threshold range, the The corresponding threshold range size Calculate the excess ratio , then based on the excess ratio Compare the historical trends in the report with the current Calculate the warning level of the fault risk type corresponding to the data item: ; In the formula, is the floor rounding function; After determining the fault risk type and the warning level, the warning level and the warning content are transmitted as warning instructions to the warning maintenance disposal unit (52) corresponding to the fault risk type; After receiving the warning instruction, the warning maintenance handling unit (52) immediately reminds the construction personnel through at least one of voice, short message and alarm, and instructs them to take intervention measures. At the same time, the warning maintenance handling unit (52) records the detailed information in each warning instruction and the warning handling situation for subsequent analysis and improvement.

[0014] The present invention also discloses an automatic mining filling control method based on machine vision and the Internet of Things, the steps comprising: S1. The spectrometer in the machine vision module is used to collect spectral data of the mining operation surface, and the collected spectral data is subjected to noise removal, end member extraction, spectral unmixing and abundance inversion to identify the type, distribution and quality of the ore; S2, the IoT monitoring module collects the operating parameters and environmental parameters of each device during the mining and filling process through sensors; S3, the real-time database receives the recognition data from the machine vision module and the equipment operation parameters and environmental parameters from the IoT monitoring module, generates a real-time data set, and synchronizes it to the historical database for storage; S4, the data analysis unit reads the real-time data set, the historical data set and the reference data set in the reference data storage unit, performs horizontal and vertical comparisons using the Pearson correlation coefficient, and generates a comparison report; S5. The autonomous optimization module adjusts the working parameters of the mining equipment and the filling equipment according to the comparison report; S6. The threshold setting identification unit determines whether there is a fault risk based on the comparison report and the comparison between the real-time data set and the preset warning threshold. If a fault risk is found, a warning instruction is generated and transmitted to the corresponding warning maintenance disposal unit.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention performs fusion analysis based on the information data obtained by the machine vision module and the Internet of Things monitoring module, optimizes the control strategy, and adjusts the working parameters of each device, thereby reducing dependence on manual experience, improving efficiency, and reducing resource waste and safety hazards.

[0016] 2. The data fusion analysis module realizes the effective analysis and integration of multi-source data, and generates comparative reports based on historical data, providing a scientific basis for optimizing decision-making.

[0017] 3. The autonomous optimization module can automatically adjust the mining and filling strategies and equipment working parameters according to the comparison report to achieve accurate utilization of resources and efficient output, thereby reducing operating costs.

[0018] 4. The multi-level early warning maintenance module achieves early warning of equipment failures and environmental risks through preset early warning thresholds, and reminds construction personnel to intervene in time through various means, effectively reducing downtime and safety hazards.

[0019] 5. The machine vision module uses spectral analysis technology to accurately identify the type, distribution and quality of ore, providing a reliable data basis for mining and filling, significantly improving recognition accuracy and operating efficiency, while also further reducing reliance on manual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the overall structure of the automated mining and filling system of the present invention; Figure 2 This is a structural diagram of the data fusion analysis module in the present invention; Figure 3 This is a schematic diagram of the structure of the multi-level early warning maintenance module in the present invention; Figure 4 A schematic diagram of a specific structure provided for an embodiment of the present invention; Figure 5 The figure is a flow chart of the automatic mining filling control method of the present invention.

[0021] Description of reference numerals: 1. Machine vision module; 2. Internet of Things monitoring module; 3. Data fusion analysis module; 31. Real-time database; 32. Historical database; 33. Reference data storage unit; 34. Data analysis unit; 4. Autonomous optimization module; 5. Multi-level early warning maintenance module; 51. Threshold setting recognition unit; 52. Early warning maintenance disposal unit. DETAILED DESCRIPTION

[0022] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0023] like Figure 1 , an automated mining and filling system based on machine vision and the Internet of Things, including a machine vision module 1, an Internet of Things monitoring module 2, a data fusion analysis module 3 and an autonomous optimization module 4, and also includes a multi-level early warning maintenance module 5.

[0024] The machine vision module 1 is used to identify the type, distribution and quality of the ore, and transmit the identification data to the data fusion analysis module 3.

[0025] In this embodiment, the machine vision module 1 collects spectral data of the mining operation surface through a spectrometer, performs noise removal, end member extraction, spectral unmixing and abundance inversion operations on the spectral data, and obtains spectral analysis data. The spectral analysis data is the identification data, including ore type, distribution and quality.

[0026] Specifically, a spectrometer is first used to collect spectral data of the mining surface. The spectrometer can measure the wavelength distribution of light reflected or emitted by the surface of an object. These spectral information contains key information such as the chemical composition and physical state of the ore.

[0027] Since the acquisition process may be interfered by various noises including ambient light and instrument noise, it is necessary to remove noise from the collected spectral data. This can be achieved through a low-pass filtering algorithm to reduce the impact of noise on subsequent analysis. The low-pass filtering algorithm specifically includes the following steps: Low-pass filtering allows low-frequency signals to pass through and attenuates high-frequency signals. For one-dimensional signals , the output of the low-pass filter It can be calculated by the following convolution formula: ;

[0028] in It is the impulse response of the filter, which determines the characteristics of the filter. For the moving average filter, the impulse response are equally weighted, specifically: ,for ; in is the filter length or window size.

[0029] Endmembers refer to the basic components in spectral data, which usually correspond to different mineral components in ores. The purpose of endmember extraction is to separate these basic components from complex spectral data and provide a basis for subsequent spectral unmixing. The VCA algorithm can be used for endmember extraction. The VCA algorithm specifically includes the following steps: Goal: Find a set of endmember spectra ,in yes The vector ( is the number of bands), so that the mixed spectral data It can be approximately expressed as ,in is the abundance matrix.

[0030] Constraint: Abundance Matrix Each column of (corresponding to the abundance of a mixed pixel) is non-negative and sums to 1 (i.e. ,in yes A column of is a vector of all 1s); Method: The VCA algorithm approximates the endmembers by iteratively searching for the vertices of a convex polyhedron.

[0031] In mining operations, the ore is often not composed of a single mineral, but a mixture of multiple minerals. The purpose of spectral unmixing is to decompose the mixed spectrum into the spectra of each end member, so as to obtain the abundance of each end member in the mixture. This process can be achieved using the N-FINDR algorithm, which specifically includes the following steps: Initialization: Select any spectral vector in the data set as the first end member , initialize the end member set ; Iterative process (for ,in is the number of endmembers expected to be extracted): Projection calculation: For each spectral vector in the dataset ( ,in is the total number of spectral vectors), calculate its The projection length on the Zhang Cheng subspace is calculated by and It is realized by projecting the column vectors of the subspace onto the orthogonal complement space, using an approximate method, namely calculating and The residual of each end member in , and select the direction with the smallest residual as the projection direction, that is, to find the maximum In by The spectral vector of the projection length on the subspace spanned by the column vector .

[0032] Select new endmember: Select the spectral vector with the largest projection length as the new endmember , and add it to the endmember collection: .

[0033] Termination condition: When the number of extracted end members reaches the preset When , the algorithm terminates.

[0034] After the relative content of each end member is obtained by spectral unmixing, it is necessary to further perform abundance inversion to obtain the specific distribution and quality information of various minerals in the ore. The results of abundance inversion are usually presented in the form of images or data tables, showing detailed information on the type, distribution and quality of the ore. The least squares algorithm can be used to achieve this. The least squares algorithm includes the following steps: When the endmember matrix is ​​known, the abundance is solved by minimizing the sum of squares of the errors between the observed spectrum and the linear combination of the endmember spectra, which can be expressed as solving the following optimization problem: ; in, is the observed mixed spectral data matrix, is the endmember matrix, is the abundance matrix to be determined, is a vector of all 1s, represents the two-norm, and the optimization problem is subject to two constraints: non-negativity constraint ( ) and the "sum equals one" constraint ( ), the former ensures that the abundance is non-negative, and the latter ensures that the sum of the abundances of all end members in each mixed pixel is 1.

[0035] The spectral analysis data (including ore type, distribution and quality) obtained through the above processing will be transmitted to the data fusion analysis module 3 for further processing and analysis. These data are important bases for the subsequent optimization of mining and filling strategies, and the prediction of equipment failures and environmental accidents.

[0036] The Internet of Things monitoring module 2 is used to collect the operating parameters and environmental parameters of each device during the mining and filling process, and transmit the operating parameters and environmental parameters to the data fusion analysis module 3. Specifically, the Internet of Things monitoring module 2 uses Internet of Things sensors to collect data.

[0037] Specifically, the IoT monitoring module 2 relies on various types of sensors to collect data. These sensors are usually installed in different parts of mining equipment and key locations in the mining area. Sensor types include but are not limited to: Temperature sensor: used to monitor the internal temperature of the equipment, ambient temperature, etc., to ensure that the equipment operates within the appropriate temperature range and prevent failures caused by overheating; Pressure sensor: installed on pumps, compressors and other equipment to monitor working pressure and prevent overpressure; Vibration sensor: used to monitor the vibration of the equipment. Vibration data analysis can be used to determine the operating status of the equipment and potential mechanical failures. Flow sensor: installed in the filling pipeline to monitor the flow of filling materials and ensure the accuracy of filling operations; Humidity sensor: Monitoring the ambient humidity in mining areas is critical to preventing safety issues such as dust explosions; Gas sensor: monitors the concentration of harmful gases (such as methane, oxygen, carbon monoxide, etc.) in mines to ensure personnel safety; Each sensor converts the sensed physical quantity into an electrical signal according to its physical or chemical properties. These electrical signals are then processed by the IoT monitoring module 2 and transmitted to the data fusion analysis module 3 by wire or wireless means. In the data fusion analysis module 3, the data is stored in the real-time database 31 for subsequent analysis and synchronized to the historical database 32 for long-term storage, so as to perform historical data analysis and trend prediction.

[0038] The data fusion analysis module 3 processes the identification data, equipment operation parameters and environmental parameters, generates a comparison report and transmits it to the autonomous optimization module 4.

[0039] like Figure 2 and 4 The data fusion analysis module 3 includes a real-time database 31, a historical database 32, a reference data storage unit 33 and a data analysis unit 34.

[0040] The input end of the real-time database 31 is connected to the output end of the machine vision module 1 and the output end of the Internet of Things monitoring module 2 respectively.

[0041] The input end of the historical database 32 is connected to the output end of the real-time database 31 .

[0042] The input end of the data analysis unit 34 is connected to the output end of the real-time database 31 , the output end of the history database 32 , and the output end of the reference data storage unit 33 , respectively.

[0043] The real-time database 31 receives the identification data from the machine vision module 1 and the equipment operation parameters and environmental parameters from the Internet of Things monitoring module 2, and then performs data standardization processing on the received data according to the data source to generate a real-time data set; a real-time data set contains the values ​​of each data item at the current time point, and the data item refers to multiple data types from the identification data, operation parameters and environmental parameters; the real-time database 31 transmits the obtained real-time data set to the historical database 32 and the data analysis unit 34 respectively; The historical database 32 stores the real-time data set from the real-time database 31 as a historical data set.

[0044] The reference data storage unit 33 stores a plurality of reference data sets corresponding to different working conditions; a reference data set contains standard values ​​for each data item; the reference data storage unit 33 also stores standard solutions corresponding to each reference data set, each standard solution records the recommended values ​​of working parameters of the mining equipment and the filling equipment under the corresponding working conditions.

[0045] The working parameters of mining equipment include but are not limited to: crusher feed opening size, crushing chamber gap, rotation speed and crushing force. The working parameters of filling equipment include but are not limited to: filling material flow, quality, conveying speed, density and pressure. The specific explanation is as follows: Crusher feed opening size: According to the type and distribution of ore, adjust the feed opening size to optimize crushing efficiency and reduce energy consumption; Crushing chamber gap: According to the hardness and particle size distribution of the ore, adjust the crushing chamber gap to avoid over-crushing or blockage; Crusher speed: According to the difficulty of crushing the ore, adjust the crusher speed to achieve the best crushing effect; Crushing force: The crushing force is controlled by adjusting the power of the crusher or the pressure of the hydraulic system to ensure that the ore is fully crushed.

[0046] Filling material flow rate: According to the mining progress and filling requirements, the filling material flow rate is adjusted to maintain a stable filling speed.

[0047] Filling material quality: Ensure that the quality of filling materials meets the requirements by adjusting the raw material ratio or screening process; Conveying speed: According to the filling distance and the performance of the filling equipment, the conveying speed is adjusted to balance the filling efficiency and energy consumption.

[0048] Density and pressure: By adjusting the compaction equipment or vibration equipment during the filling process, the density and pressure of the filling body can be controlled to improve the stability and bearing capacity of the filling body.

[0049] The data analysis unit 34 reads all reference data sets and compares them with the real-time data sets horizontally, and also compares the real-time data sets with the historical data sets corresponding to a previous time point stored in the historical database 32 vertically, to obtain a comparison report.

[0050] When comparing, the real-time data set is compared with the historical data set or reference data set used as the comparison data set in the following manner: Suppose the sequence of values ​​of each data item in the real-time data set is , is the number of data items, and the sequence formed by the values ​​of each data item in the comparison data set is , calculate the Pearson correlation coefficient: ; in, and Sequence and sequence The mean of .

[0051] The Pearson correlation coefficient between the real-time data set and the historical data set is recorded as the historical trend , the Pearson correlation coefficient between the real-time data set and the reference data set is recorded as the working condition trend .

[0052] The autonomous optimization module 4 adjusts the working parameters of the mining equipment and the filling equipment based on the comparison report.

[0053] The way to adjust the working parameters of mining equipment and filling equipment in autonomous optimization module 4 is as follows: The working condition trend The working condition corresponding to the maximum value is regarded as the current working condition, and then the recommended values ​​of the working parameters of the mining equipment and the filling equipment in the standard solution corresponding to the working condition are obtained.

[0054] The difference between the vector formed by the obtained recommended working parameter values ​​and the vector formed by the current working parameter setting values ​​of the mining equipment and the filling equipment is recorded as the parameter adjustment benchmark. .

[0055] Based on the historical trends reported in the comparison Calculate the parameter adjustment coefficient .

[0056] Vector Each element in is sent to all devices as the adjustment amount of the corresponding working parameters to adjust the parameters in real time.

[0057] Using the above method, when the historical trend degree is low (that is, the current operating conditions are greatly different from the historical conditions), the parameter adjustment amplitude coefficient is large, so a larger adjustment is made; when the historical trend degree is high, the parameter adjustment amplitude coefficient is small, and a smaller adjustment is made.

[0058] The multi-level early warning maintenance module 5 determines whether there is a failure risk based on the comparison report and issues an early warning.

[0059] Specifically, Figure 3 and 4 In the multi-level early warning maintenance module 5, early warning is performed in the following ways: The threshold setting identification unit 51 compares all data items in the current real-time data set element with the threshold of each data item, finds out the data items that exceed the threshold range, and determines the potential fault risk type according to these data items. The threshold includes but is not limited to abnormal values ​​of equipment operating parameters (such as temperature, pressure, vibration, etc.), critical values ​​of environmental parameters (such as gas concentration, humidity, etc.), and abnormal range of ore identification data.

[0060] For each data item that exceeds the threshold range, the The corresponding threshold range size Calculate the excess ratio , then based on the excess ratio Compare the historical trends in the report with the current Calculate the warning level of the fault risk type corresponding to the data item: ; In the formula, The above formula divides the warning into 5 levels based on the limit-exceeding ratio and historical trend degree.

[0061] After the fault risk type and the warning level are determined, the warning level and the warning content are transmitted as warning instructions to the warning maintenance handling unit 52 corresponding to the fault risk type.

[0062] After receiving the warning instruction, the early warning maintenance handling unit 52 immediately reminds the construction personnel by at least one of voice, short message and alarm.

[0063] In addition to issuing warning information, the warning maintenance disposal unit 52 also provides specific intervention operation guidance. For example, in the equipment failure warning, it guides the construction personnel on how to quickly locate the fault point, take temporary remedial measures or prepare maintenance tools, etc. The warning maintenance disposal unit 52 is also responsible for recording the detailed information and subsequent processing of each warning to form a warning maintenance log. These logs are of great significance for analyzing the causes of warnings, optimizing warning thresholds, and improving maintenance strategies.

[0064] like Figure 5 This embodiment also provides an automated mining and filling control method based on machine vision and the Internet of Things, the steps comprising: S1. The spectrometer in the machine vision module 1 is used to collect spectral data of the mining operation surface, and the collected spectral data is subjected to noise removal, end member extraction, spectral unmixing and abundance inversion to identify the type, distribution and quality of the ore.

[0065] S2, the Internet of Things monitoring module 2 collects the operating parameters and environmental parameters of each equipment during the mining and filling process through sensors.

[0066] S3. The real-time database 31 receives the recognition data from the machine vision module 1 and the equipment operation parameters and environmental parameters of the Internet of Things monitoring module 2, generates a real-time data set, and synchronizes it to the historical database 32 for storage.

[0067] S4. The data analysis unit 34 reads the real-time data set, the historical data set and the reference data set in the reference data storage unit 33, performs horizontal and vertical comparisons using the Pearson correlation coefficient, and generates a comparison report.

[0068] S5. The autonomous optimization module 4 adjusts the working parameters of the mining equipment and the filling equipment according to the comparison report.

[0069] S6. The threshold setting identification unit 51 determines whether there is a fault risk based on the comparison report and the comparison between the real-time data set and the preset warning threshold. If a fault risk is found, a warning instruction is generated and transmitted to the corresponding warning maintenance disposal unit 52.

[0070] It should be noted that it is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. The scope of the present invention is defined by the claims rather than the above description.

Claims

1. An automated mining and filling system based on machine vision and the Internet of Things, characterized by: It includes a machine vision module (1), an Internet of Things monitoring module (2), a data fusion analysis module (3) and an autonomous optimization module (4); The machine vision module (1) is used to identify the type, distribution and quality of the ore, and transmit the identification data to the data fusion analysis module (3); The Internet of Things monitoring module (2) is used to collect operating parameters and environmental parameters of each device during the mining and filling process, and transmit the operating parameters and environmental parameters to the data fusion analysis module (3); The data fusion analysis module (3) processes the identification data, equipment operation parameters and environmental parameters, generates a comparison report and transmits it to the autonomous optimization module (4); The autonomous optimization module (4) adjusts the working parameters of the mining equipment and the filling equipment based on the comparison report.

2. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 1, characterized in that: It also includes a multi-level early warning maintenance module (5); The comparison report generated by the data fusion analysis module (3) is also transmitted to the multi-level early warning maintenance module (5); the multi-level early warning maintenance module (5) determines whether there is a failure risk based on the comparison report and issues an early warning.

3. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 1, characterized in that: The machine vision module (1) collects spectral data of the mining operation surface through a spectrometer, performs noise removal, end member extraction, spectral unmixing and abundance inversion operations on the spectral data, and obtains spectral analysis data; the spectral analysis data is the identification data, including ore type, distribution and quality.

4. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 1, characterized in that: The Internet of Things monitoring module (2) uses Internet of Things sensors to collect data.

5. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 2, characterized in that: The data fusion analysis module (3) comprises a real-time database (31), a historical database (32), a reference data storage unit (33) and a data analysis unit (34); The input end of the real-time database (31) is respectively connected to the output end of the machine vision module (1) and the output end of the Internet of Things monitoring module (2); The input end of the historical database (32) is connected to the output end of the real-time database (31); The input end of the data analysis unit (34) is respectively connected to the output end of the real-time database (31), the output end of the historical database (32) and the output end of the reference data storage unit (33).

6. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 5, characterized in that: The real-time database (31) receives the identification data from the machine vision module (1) and the equipment operating parameters and environmental parameters from the Internet of Things monitoring module (2), and then performs data standardization processing on the received data according to the data source to generate a real-time data set; a real-time data set includes the value of each data item at the current time point, and the data item refers to multiple data types from the identification data, operating parameters and environmental parameters; the real-time database (31) transmits the obtained real-time data set to the historical database (32) and the data analysis unit (34) respectively; The historical database (32) stores the real-time data set from the real-time database (31) as a historical data set; The reference data storage unit (33) stores a plurality of reference data sets corresponding to different working conditions; A reference data set includes standard values ​​of various data items; the reference data storage unit (33) also stores standard solutions corresponding to each reference data set, each standard solution recording recommended values ​​of working parameters of mining equipment and filling equipment under corresponding working conditions; The data analysis unit (34) reads all reference data sets and compares them horizontally with the real-time data sets, and also compares the real-time data sets vertically with the historical data sets corresponding to a previous time point stored in the historical database (32), thereby obtaining a comparison report.

7. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 6, characterized in that: When comparing, the real-time data set is compared with the historical data set or reference data set used as the comparison data set in the following manner: Suppose the sequence of values ​​of each data item in the real-time data set is , is the number of data items, and the sequence formed by the values ​​of each data item in the comparison data set is , calculate the Pearson correlation coefficient: ； in, and Sequence and sequence The mean of The Pearson correlation coefficient between the real-time data set and the historical data set is recorded as the historical trend , the real-time dataset is compared with the The Pearson correlation coefficient of the reference data set is recorded as the working condition trend .

8. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 7, characterized in that: The method for adjusting the working parameters of the mining equipment and the filling equipment in the autonomous optimization module (4) is as follows: The working condition trend The working condition corresponding to the maximum value is regarded as the current working condition, and then the recommended values ​​of the working parameters of the mining equipment and the filling equipment in the standard solution corresponding to the working condition are obtained; The difference between the vector formed by the obtained recommended working parameter values ​​and the vector formed by the current working parameter setting values ​​of the mining equipment and the filling equipment is recorded as the parameter adjustment benchmark. ; Based on the historical trends reported in the comparison Calculate the parameter adjustment coefficient ; Vector Each element in is sent to all devices as the adjustment amount of the corresponding working parameters to adjust the parameters in real time.

9. The automated mining and filling system based on machine vision and the Internet of Things as claimed in claim 7, characterized in that: In the multi-level warning maintenance module (5), warnings are issued in the following ways: The threshold setting identification unit (51) compares all data items in the current real-time data set element with the threshold of each data item, finds out the data items that exceed the threshold range, and determines the potential fault risk type according to these data items; For each data item that exceeds the threshold range, the The corresponding threshold range size Calculate the excess ratio , then based on the excess ratio Compare the historical trends in the report with the current Calculate the warning level of the fault risk type corresponding to the data item: ； In the formula, is the floor rounding function; After determining the fault risk type and the warning level, the warning level and the warning content are transmitted as warning instructions to the warning maintenance disposal unit (52) corresponding to the fault risk type; After receiving the warning instruction, the warning maintenance handling unit (52) immediately reminds the construction personnel through at least one of voice, short message and alarm, and instructs them to take intervention measures. At the same time, the warning maintenance handling unit (52) records the detailed information in each warning instruction and the warning handling situation for subsequent analysis and improvement.

10. An automated mining and filling control method based on machine vision and the Internet of Things, characterized in that The steps include: S1. Collect spectral data of the mining operation surface through the spectrometer in the machine vision module (1), remove noise, extract end members, perform spectral unmixing and abundance inversion on the collected spectral data, and identify the type, distribution and quality of the ore; S2, the Internet of Things monitoring module (2) collects the operating parameters and environmental parameters of each device during the mining and filling process through sensors; S3, the real-time database (31) receives the recognition data from the machine vision module (1) and the equipment operation parameters and environmental parameters of the Internet of Things monitoring module (2), generates a real-time data set, and synchronizes it to the historical database (32) for storage; S4, the data analysis unit (34) reads the real-time data set, the historical data set and the reference data set in the reference data storage unit (33), performs horizontal and vertical comparisons using the Pearson correlation coefficient, and generates a comparison report; S5, the autonomous optimization module (4) adjusts the working parameters of the mining equipment and the filling equipment according to the comparison report; S6. The threshold setting identification unit (51) determines whether there is a fault risk based on the comparison report and the comparison between the real-time data set and the preset warning threshold value. If a fault risk is found, a warning instruction is generated and transmitted to the corresponding warning maintenance disposal unit (52).

Images