Intelligent monitoring method and system for production process based on smart mine

Abstract

The application provides a production process intelligent monitoring method and system based on a smart mine. First, target monitoring data sets in real-time production processes of mine equipment are collected, covering equipment vibration time series signals, environmental temperature and humidity distribution data, and equipment energy consumption fluctuation curves. Then, dynamic standardization processing is performed to obtain standardized monitoring data sets matching equipment types and production process stages. A pre-trained multi-dimensional feature extraction model is then called to perform joint feature mapping to generate equipment operation state, environment correlation, and data abnormal fluctuation features. Based on a pre-set abnormal pattern recognition model, the features are dynamically fused and analyzed to obtain equipment operation risk levels and production process optimization strategy sets. Finally, an alarm instruction is triggered according to the risk level, and the optimization strategy is fed back to the production control terminal to adjust the equipment operation parameters, thereby achieving intelligent monitoring and optimization of the production process of the smart mine.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart mines, in particular to a production process intelligent monitoring method and system based on a smart mine. BACKGROUND

[0002] In the field of mine production, with the continuous expansion of production scale and the increasing complexity of production process, the traditional production process monitoring method has been difficult to meet the needs of modern mine efficient and safe production. The existing mine production monitoring technology has many limitations, which seriously restricts the intelligent development of mine production.

[0003] The existing method usually adopts a fixed data processing method, which cannot be dynamically adjusted according to the types of equipment and the stages of production process, so that the processed data is difficult to accurately reflect the characteristics of different equipment and process stages, reducing the usability and analysis value of the data, and cannot provide strong support for subsequent risk assessment and optimization strategy formulation. SUMMARY

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present application, the embodiments of the present application provide a production process intelligent monitoring method based on a smart mine, which comprises:

[0005] Collecting a target monitoring data set of mine equipment in a real-time production process, the target monitoring data set comprising equipment vibration time series signals, environmental temperature and humidity distribution data and equipment energy consumption fluctuation curves;

[0006] Performing dynamic standardization processing on the target monitoring data set to generate a standardized monitoring data set matched with the types of equipment and the stages of production process;

[0007] Calling a pre-trained multi-dimensional feature extraction model to perform joint feature mapping processing on the standardized monitoring data set to generate equipment running state features, environmental correlation features and data abnormal fluctuation features;

[0008] Based on a preset abnormal pattern recognition model, dynamically fusing and analyzing the equipment running state features, environmental correlation features and data abnormal fluctuation features to generate an equipment running risk level and a production process optimization strategy set;

[0009] According to the equipment running risk level, triggering a corresponding alarm instruction, and feeding back the production process optimization strategy set to a production control terminal to adjust the equipment running parameters.

[0010] In still another aspect, the embodiment of the present application also provides a production process intelligent monitoring system based on a smart mine, comprising a processor, a machine readable storage medium, the machine readable storage medium is connected with the processor, the machine readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, instructions or codes in the machine readable storage medium to realize the above method.

[0011] Based on the above aspects, the embodiment of the present application can effectively eliminate the differences between different devices and process stage data by collecting a target monitoring data set of the mine equipment in the real-time production process, comprehensively obtaining key information such as device vibration, environmental temperature and humidity, and device energy consumption, performing dynamic standardization processing on the target monitoring data set, and generating a standardized monitoring data set matched with the device type and the production process stage. The pre-trained multi-dimensional feature extraction model is called to perform joint feature mapping processing on the standardized monitoring data set, extract key features such as device running state, environmental correlation and data abnormal fluctuation, perform dynamic fusion analysis on the extracted features based on a preset abnormal pattern recognition model, generate a device running risk level and a production process optimization strategy set, can real-time understand the device running condition, discover potential risks in advance, and develop optimization strategies accordingly. According to the device running risk level, the corresponding alarm instruction is triggered, and the production process optimization strategy set is fed back to the production control terminal to adjust the device running parameters, realizing real-time and accurate regulation and control of the mine production process, effectively solving the problems of insufficient data utilization, untimely risk warning and inaccurate optimization strategy in traditional mine production monitoring, improving the automation and intelligent degree of mine production, and reducing the occurrence rate of production accidents. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 is the execution flow diagram of the production process intelligent monitoring method based on a smart mine provided by the embodiment of the present application.

[0013] Figure 2 is the schematic diagram of exemplary hardware and software components of the production process intelligent monitoring system based on a smart mine provided by the embodiment of the present application. DETAILED DESCRIPTION

[0014] The present application will be described in detail below with reference to the accompanying drawings, Figure 1 is the flow diagram of the production process intelligent monitoring method based on a smart mine provided by an embodiment of the present application, and the production process intelligent monitoring method based on a smart mine will be described in detail below.

[0015] In step S110, a target monitoring data set of the mine equipment in the real-time production process is collected, and the target monitoring data set includes device vibration time series signals, environmental temperature and humidity distribution data, and device energy consumption fluctuation curves.

[0016] In this embodiment, in the real-time production process of the mine, comprehensive monitoring and optimization work can be carried out for various types of mine equipment. In detail, the mine has multiple types of equipment, covering multiple production process links such as mining, transportation, crushing, etc. For example, in the mining process, for a large mining machine of ABC-100 type, high-precision vibration sensors are installed at key parts such as the motor, transmission gear and excavating arm, etc. to collect real-time vibration time sequence signals of the equipment. For example, the above-mentioned sensor can collect 100 data points per second, continuously record the vibration of the equipment during the mining process, and form a continuous vibration time sequence signal data stream.

[0017] At the same time, multiple temperature and humidity sensors are arranged in the working area of the mining machine to obtain environmental temperature and humidity distribution data. For example, the above-mentioned temperature and humidity sensors can be evenly distributed within a radius of 10 meters, and record temperature and humidity data every 5 minutes, so as to depict the environmental temperature and humidity distribution of the area. For example, at a certain time, the sensor records that the temperature is 28 degrees Celsius and the humidity is 60%.

[0018] In addition, through the energy consumption monitoring system connected to the mining machine, the equipment energy consumption fluctuation curve can be monitored in real time, which can accurately record the power consumption of the mining machine under different working conditions, generate energy consumption data in units of minutes, and form the equipment energy consumption fluctuation curve. Within a certain mining operation time, it is recorded that the energy consumption gradually rises from the initial 50 kilowatts to 80 kilowatts, and then stabilizes at about 70 kilowatts.

[0019] In the transportation process, similar data collection is also carried out for a transportation truck of DEF-20 type. For example, vibration sensors are installed on the engine, tires and suspension system of the truck to collect vibration time sequence signals of the equipment. At the same time, temperature and humidity sensors are installed inside and outside the truck cabin to obtain environmental temperature and humidity distribution data during transportation. And through the vehicle-mounted energy consumption monitoring device, the equipment energy consumption fluctuation curve during transportation is recorded. For example, in a transportation process, the energy consumption of the truck is 10 kilowatts when starting, the average energy consumption is maintained at 30 kilowatts during driving, and the energy consumption can reach 50 kilowatts when accelerating and climbing.

[0020] In the crushing process, for a GHI-300 type crusher, vibration sensors are installed at positions such as the motor, crushing cavity and transmission belt to collect vibration time sequence signals. For example, temperature and humidity sensors are arranged around the crusher to obtain environmental temperature and humidity distribution data. Through the energy consumption monitoring device connected to the crusher, the equipment energy consumption fluctuation curve is recorded. For example, when the crusher starts, the energy consumption rapidly rises to 100 kilowatts, and after stable operation, the energy consumption remains at about 80 kilowatts.

[0021] Thus, the device vibration time sequence signals, the environment temperature and humidity distribution data, and the device energy consumption fluctuation curves from different processes and different devices can be integrated together to form a target monitoring data set.

[0022] In step S120, dynamic standardization processing is performed on the target monitoring data set to generate a standardized monitoring data set matched with the device type and the production process stage.

[0023] For example, for an ABC-100 mining machine in the mining process, first, a historical running parameter set thereof is obtained, wherein the device rated vibration threshold range is 0-50 mm / s2, the standard temperature and humidity adaptation interval is 20-30 degrees Celsius and 40%-70% humidity, and the maximum energy consumption critical value is 100 kW.

[0024] According to the device rated vibration threshold range, amplitude normalization processing is performed on the collected device vibration time sequence signals. For example, assuming that the amplitude range of the collected vibration signals is 10-60 mm / s2, the following processing is performed: subtracting the minimum value 10 from each data point and dividing by the difference 50 (60-10) between the maximum value and the minimum value to obtain a standardized vibration signal sequence. For example, the amplitude of the vibration signal collected at a certain time is 30 mm / s2, and after processing, it is (30-10)÷50=0.4.

[0025] Then, the current environment temperature and humidity reference values are determined according to the current mining process stage, and it is assumed that the current reference temperature is 25 degrees Celsius and the reference humidity is 50%. Deviation correction processing is performed on the environment temperature and humidity distribution data based on the standard temperature and humidity adaptation interval. For the collected temperature data, if it is 28 degrees Celsius, the deviation is 28-25=3 degrees Celsius, which is corrected within the standard temperature and humidity adaptation interval, and the corrected temperature is (28-20)÷(30-20)=0.8. For the humidity data, if the collected humidity is 60%, the deviation is 60-50=10%, and the corrected humidity is (60-40)÷(70-40)=0.67, generating the corrected temperature and humidity distribution data.

[0026] Next, dynamic scaling processing is performed on the device energy consumption fluctuation curve according to the maximum energy consumption critical value. Assuming that the energy consumption value in the collected energy consumption fluctuation curve is between 50-80 kW, scaling processing is performed: subtracting the minimum value 50 from each energy consumption data point and dividing by the difference 30 (80-50) between the maximum value and the minimum value to generate a standardized energy consumption curve. For example, the energy consumption value at a certain time is 70 kW, and after processing, it is (70-50)÷30=0.67.

[0027] Thus, the standardized vibration signal sequence, the corrected temperature and humidity distribution data, and the standardized energy consumption curve can be integrated into a standardized monitoring data set for the ABC-100 mining machine in the mining process stage.

[0028] For the DEF-20 type transport truck in the transportation process, a set of historical operating parameters thereof is obtained, the rated vibration threshold range of the equipment is 0-30 mm / s2, the standard temperature and humidity adaptation interval is 15-25 degrees Celsius in temperature and 30%-60% in humidity, and the maximum energy consumption critical value is 60 kW. The collected target monitoring data is processed according to the above method, and a standardized monitoring data set for the DEF-20 type transport truck in the transportation process stage is generated.

[0029] For the GHI-300 type crusher in the crushing process, a set of historical operating parameters thereof is obtained, the rated vibration threshold range of the equipment is 0-80 mm / s2, the standard temperature and humidity adaptation interval is 22-32 degrees Celsius in temperature and 45%-75% in humidity, and the maximum energy consumption critical value is 120 kW. The collected data is processed accordingly, and a standardized monitoring data set for the GHI-300 type crusher in the crushing process stage is generated.

[0030] In step S130, a pre-trained multi-dimensional feature extraction model is called to perform joint feature mapping processing on the standardized monitoring data set to generate device operating state features, environment-related features and data abnormal fluctuation features.

[0031] For example, for the standardized vibration signal sequence of the ABC-100 type mining machine in the mining process, time-frequency conversion processing can be performed. For example, first, the standardized vibration signal sequence is subjected to windowed Fourier transform, assuming that the window function length is 100 data points and the overlap rate is 50%, a vibration spectrum graph is generated. Then, the energy integral value of each frequency interval in the vibration spectrum graph is calculated, for example, the frequency range is divided into 0-100 Hz, 100-200 Hz and other intervals, the energy integral value in each interval is calculated, and a frequency energy distribution histogram is generated. The main resonance peak frequency in the vibration spectrum graph is detected, assuming that the standard resonance frequency is 150 Hz and the detected main resonance peak frequency is 160 Hz, the difference 160-150=10 Hz is calculated, and the resonance peak shift amount is generated. The frequency energy distribution histogram is subjected to sliding window statistics, the window size is 10 intervals, and the low-frequency energy proportion feature and the high-frequency mutation number feature are extracted. Assuming that the low-frequency energy proportion is 30% and the high-frequency mutation number is 5 times, the two features are combined into a vibration frequency energy distribution feature after logarithmic transformation, such as the low-frequency energy proportion feature after logarithmic transformation ln(0.3) and the high-frequency mutation number feature ln(5), and the combined vibration frequency energy distribution feature is formed.

[0032] Then, the corrected temperature and humidity distribution data are subjected to spatial interpolation processing. Assuming that there are 5 temperature and humidity sensors in a 10*10 square meter operation area, the temperature and humidity gradient change characteristics of the entire area are generated through the interpolation algorithm. For example, the temperature change rate and humidity change rate between adjacent sensors are calculated to generate the temperature and humidity gradient change characteristics. At the same time, local abnormal temperature zones are marked, such as a region whose temperature is significantly higher than the surrounding area, which is marked as a local abnormal temperature zone, and a local abnormal temperature zone mark is generated.

[0033] The slope change of the standardized energy consumption curve is analyzed. The first-order difference of the standardized energy consumption curve is calculated to generate the energy consumption change rate sequence. Assuming that the energy consumption data points in a certain period of time are 0.5, 0.6, 0.7, etc., the first-order difference calculation obtains the energy consumption change rate sequence as 0.1, 0.1, etc. The time interval in which the continuous energy consumption change rate exceeds the rated slope threshold value (assuming 0.15) is detected, and the start time stamp and end time stamp are recorded. The average slope value in the time interval is calculated as the energy consumption rise rate feature, assuming that the slope values in the time interval are 0.2, 0.2, and 0.18, and the average slope value is (0.2+0.2+0.18)÷3=0.193, which is taken as the energy consumption rise rate feature. The difference between the start time stamp and the end time stamp is used to determine the peak duration feature, assuming that the start time stamp is 10 minutes and the end time stamp is 15 minutes, and the peak duration feature is 5 minutes. The extreme point detection is performed on the energy consumption change rate sequence to generate the energy consumption mutation event mark and the corresponding event duration.

[0034] The vibration frequency energy distribution characteristics, resonance peak shift, temperature and humidity gradient change characteristics, local abnormal temperature zone mark, energy consumption rise rate feature and peak duration feature are input into the multi-dimensional feature extraction model. The correlation weighting of the vibration frequency energy distribution characteristics and the temperature and humidity gradient change characteristics is performed through the cross-modal attention mechanism. The vibration frequency energy distribution characteristics are mapped into a query vector set, and the temperature and humidity gradient change characteristics are mapped into a key vector set. Then, the cosine similarity between each query vector and key vector is calculated to generate an initial attention weight matrix. Assuming that the query vector is [0.5, 0.3] and the key vector is [0.4, 0.6], the cosine similarity is calculated as (0.5*0.4+0.3*0.6)÷(sqrt(0.52+0.3 2 )×sqrt(0.4 2= 0.78, and an initial attention weight matrix is generated. The initial attention weight matrix is subjected to temperature parameter adjustment (assuming a temperature parameter of 0.1) and Softmax normalization processing, and a standardized attention weight is generated. The environmental sensitive vibration feature is generated by dynamically weighting and summing the temperature and humidity gradient change features according to the standardized attention weight. The environmental sensitive vibration feature and the temperature and humidity gradient change features are multiplied element by element to generate the environment correlation feature.

[0035] The resonance peak shift and the energy consumption rise rate features are jointly encoded by the time sequence convolution network to generate the device operation state feature. The local abnormal temperature zone label and the peak duration feature are matched by the anomaly detection algorithm to generate the data abnormal fluctuation feature.

[0036] For the devices in the transportation process and the crushing process, the above method is also used for processing, and the device operation state feature, the environment correlation feature, and the data abnormal fluctuation feature of the corresponding device are generated respectively.

[0037] In step S140, the device operation state feature, the environment correlation feature, and the data abnormal fluctuation feature are dynamically fused and analyzed based on a preset anomaly pattern recognition model to generate a device operation risk level and a production process optimization strategy set.

[0038] In this embodiment, the device operation state feature and the environment correlation feature of the ABC-100 mining machine in the mining process can be spliced to generate a device environment coupling feature. Then, the device environment coupling feature is convoluted by calling the risk level prediction branch of the anomaly pattern recognition model, and the device failure probability value and the environmental interference coefficient are output. Assuming that the output device failure probability value is 0.3 and the environmental interference coefficient is 0.2.

[0039] Next, the data abnormal fluctuation feature is pattern analyzed by calling the strategy generation branch of the anomaly pattern recognition model, and the abnormal trigger condition and the fluctuation propagation path are extracted. Assuming that the abnormal trigger condition is that the number of high-frequency mutations in the vibration frequency domain energy distribution feature exceeds 8 times, and the fluctuation propagation path is from the mining machine motor to the transmission gear and then to the excavating arm.

[0040] The device operation risk level is determined according to the weighted sum of the device failure probability value and the environmental interference coefficient. Assuming that the device failure probability value weight is 0.6 and the environmental interference coefficient weight is 0.4, the weighted sum is calculated as 0.3*0.6+0.2*0.4=0.26, and according to the preset risk level division standard, the value is in the medium risk range, and the device operation risk level is medium risk.

[0041] Then, based on the abnormal trigger condition matching the preset optimization operation template library, a device parameter adjustment instruction and an environment control scheme are generated. For example, for the abnormal trigger condition of the high frequency mutation number exceeding 8 times, the device parameter adjustment instruction is to reduce the working speed of the mining machine digging arm by 20%, and the cooling system starting threshold is reduced by 5 degrees Celsius; the environment control scheme is to increase the ventilation volume of the working area by 30%.

[0042] Then, according to the fluctuation propagation path, a list of affected devices is determined, and a production process cooperative optimization strategy is generated. Based on the fluctuation propagation path, the production process topology graph is traversed to determine that the affected devices are the transmission gear and the digging arm related devices. The device load rate and task priority of each process segment are redistributed, such as reducing the load rate of the transmission gear related device by 15% and increasing the task priority of the digging arm device. The above device parameter adjustment instruction, environment control scheme and production process cooperative optimization strategy are integrated into a production process optimization strategy set.

[0043] For the devices in the transportation process and the crushing process, the above dynamic fusion analysis is also performed to generate the respective device operation risk level and production process optimization strategy set.

[0044] Step S150, according to the device operation risk level, the corresponding alarm instruction is triggered, and the production process optimization strategy set is fed back to the production control terminal to adjust the device operation parameters.

[0045] In this embodiment, when the device operation risk level of the ABC-100 type mining machine in the mining process is medium risk, a device maintenance warning instruction is generated and a spare parts inventory checking process is started. At the same time, the device parameter adjustment instruction in the production process optimization strategy set is parsed into the speed adjustment value of the target device, the cooling system starting threshold and the power supply frequency correction parameter. According to the device historical operation database, the reference speed range of the target device under the current production process is 1000-1500 revolutions per minute. Based on the percentage coefficient corresponding to the speed adjustment value (assuming 20%), the actual value of the target speed is calculated, such as the reference speed of 1200 revolutions per minute, the adjusted speed is 1200x(1-0.2) = 960 revolutions per minute, and a speed control instruction containing an acceleration time curve is generated. According to the device heat dissipation performance parameters and the current environment temperature, the compensation amount of the cooling system starting threshold is determined, assuming that the device heat dissipation performance parameters indicate that the cooling system starting threshold should be reduced by 5 degrees Celsius at the current environment temperature, and a dynamically changing cooling trigger condition is generated. The power supply frequency correction parameter is converted into the phase adjustment amount of the inverter modulation waveform through the power supply network impedance characteristic model.

[0046] The environment control scheme is converted into a ventilation device operation mode and a dust removal system work schedule. For example, the ventilation device operation mode is adjusted to increase the ventilation volume by 30%, and the dust removal system work schedule is adjusted to increase the dust removal operation once every hour.

[0047] According to the production process collaborative optimization strategy, the equipment load rate and task priority of each process section are redistributed. For example, the load rate of the transmission gear related equipment is reduced by 15%, and the task priority of the excavator equipment is increased.

[0048] The speed adjustment value, cooling system start threshold, power supply frequency correction parameter, ventilation equipment operation mode, dust removal system working schedule, equipment load rate and task priority are issued to the corresponding execution mechanism through the production control terminal to realize the adjustment of the equipment operation parameters, and ensure the stable and efficient operation of the mine production process.

[0049] For the equipment in the transportation process and the crushing process, the corresponding alarm instruction is triggered according to the respective equipment operation risk level, and the corresponding production process optimization strategy set is fed back to the production control terminal to adjust the equipment operation parameters. For example, when the equipment operation risk level in the transportation process is low risk, the device state monitoring prompt information is generated and sent to the inspection terminal; when the equipment operation risk level in the crushing process is high risk, the device emergency stop instruction and personnel evacuation alarm signal are generated, and the corresponding parameter adjustment and strategy implementation are performed.

[0050] Based on the above steps, the embodiment of the present application collects the target monitoring data set of the mine equipment in the real-time production process, comprehensively obtains the key information such as equipment vibration, environmental temperature and humidity, and equipment energy consumption, performs dynamic standardization processing on the target monitoring data set, generates a standardized monitoring data set matched with the equipment type and the production process stage, effectively eliminates the differences between different equipment and process stage data, calls a pre-trained multi-dimensional feature extraction model to perform joint feature mapping processing on the standardized monitoring data set, extracts key features such as equipment operation state, environmental correlation and data abnormal fluctuation, performs dynamic fusion analysis on the extracted features based on a pre-set abnormal pattern recognition model, generates an equipment operation risk level and a production process optimization strategy set, can real-time understand the equipment operation condition, discover potential risks in advance, and develop optimization strategies accordingly. According to the equipment operation risk level, the corresponding alarm instruction is triggered, and the production process optimization strategy set is fed back to the production control terminal to adjust the equipment operation parameters, realizing real-time and accurate regulation and control of the mine production process, effectively solving the problems of insufficient data utilization, untimely risk warning and inaccurate optimization strategy in traditional mine production monitoring, improving the automation and intelligentization degree of mine production, and reducing the occurrence rate of production accidents.

[0051] In one possible implementation, step S120 includes:

[0052] Step S121, obtaining a historical operation parameter set of the mine equipment, the historical operation parameter set including a device rated vibration threshold range, a standard temperature and humidity adaptation interval, and a maximum energy consumption critical value.

[0053] In this embodiment, in the above mine, various types of mine equipment are continuously running, ensuring the orderly progress of multiple production processes such as mining, transportation, crushing, etc. For the target monitoring data set collected for each device, dynamic standardization processing and joint feature mapping processing are required to obtain key features such as device operating status, environmental correlation, and data abnormal fluctuations.

[0054] For the ABC-100 mining machine in the mining process, first, the historical operating parameter set of the ABC-100 mining machine is obtained. This set covers the device rated vibration threshold range, the standard temperature and humidity adaptation interval, and the maximum energy consumption critical value. After long-term data accumulation and analysis, it is known that the device rated vibration threshold range of the ABC-100 mining machine is 10 mm / s2 to 50 mm / s2, the standard temperature and humidity adaptation interval is temperature 20-30°C, humidity 40-70%, and the maximum energy consumption critical value is 100 kW.

[0055] Step S122, according to the device type, match the corresponding device rated vibration threshold range, and perform amplitude normalization processing on the device vibration time series signal to generate a standardized vibration signal sequence.

[0056] In this embodiment, within a certain mining time period, the amplitude of the collected device vibration time series signal fluctuates between 15 mm / s2 and 60 mm / s2. The amplitude normalization process is to first determine the minimum value 15 mm / s2 and the maximum value 60 mm / s2 in the data set, and then for each collected vibration signal amplitude data point, subtract the minimum value 15 from the data point and divide by the difference between the maximum value and the minimum value (60-15=45). For example, one of the collected vibration signal amplitudes is 30 mm / s2, then after amplitude normalization processing, (30-15) ÷ 45 = 15 ÷ 45 = 1 / 3 is obtained. In this way, a standardized vibration signal sequence is generated.

[0057] Step S123, according to the production process stage, determine the current environment temperature and humidity reference value, based on the standard temperature and humidity adaptation interval, perform deviation correction processing on the environment temperature and humidity distribution data, and generate corrected temperature and humidity distribution data.

[0058] In this embodiment, it is assumed that the current mining operation is in an area 200 meters deep underground, and through long-term environmental monitoring and analysis of the area, it is determined that the current environmental temperature and humidity reference value is 25 degrees Celsius and 50% humidity. Based on the standard temperature and humidity adaptation range, the environmental temperature and humidity distribution data is processed for deviation correction. In the operation area, multiple temperature and humidity sensors are arranged, and the temperature data collected at a certain time is 28 degrees Celsius, and the humidity data is 60%. For temperature data, the deviation from the reference temperature is 28-25=3 degrees Celsius, which is corrected within the standard temperature and humidity adaptation range. The correction process is (28-20)÷(30-20)=8÷10=0.8. For humidity data, the deviation is 60-50=10%, and the correction process is (60-40)÷(70-40)=20÷30=2 / 3, thereby generating corrected temperature and humidity distribution data.

[0059] Step S124, according to the maximum energy consumption critical value, the device energy consumption fluctuation curve is processed dynamically to generate a standardized energy consumption curve.

[0060] Step S125, the standardized vibration signal sequence, the corrected temperature and humidity distribution data and the standardized energy consumption curve are integrated into the standardized monitoring data set.

[0061] For example, in this mining operation, the collected device energy consumption fluctuation curve shows that the energy consumption value changes between 30 kilowatts and 80 kilowatts. During dynamic scaling, first find the minimum value 30 kilowatts and the maximum value 80 kilowatts. For each energy consumption data point, subtract the minimum value 30 from the data point, and then divide by the difference between the maximum value and the minimum value (80-30=50). For example, the energy consumption value at a certain time is 60 kilowatts, after processing it is (60-30)÷50=30÷50=0.6, thereby generating a standardized energy consumption curve. Finally, the standardized vibration signal sequence, the corrected temperature and humidity distribution data and the standardized energy consumption curve are integrated into the standardized monitoring data set for ABC-100 type mining machine in the mining process stage.

[0062] In the transportation process, the DEF-20 type transportation truck also carries out similar data processing. For example, its historical running parameter set can be obtained, and it is known that the equipment rated vibration threshold range is 5-30 mm / s2, the standard temperature and humidity adaptation interval is temperature 15-25 degrees Celsius, humidity 30%-60%, and the maximum energy consumption critical value is 60 kW. The collected equipment vibration time sequence signal amplitude is between 8-25 mm / s2, and the amplitude is normalized. Taking one of the amplitudes 15 mm / s2 as an example, (15-8) / (25-8) = 7 / 17 = 0.41, and a standardized vibration signal sequence is generated. The current transportation route is in an open pit mine, and the current environment temperature and humidity reference value is determined to be temperature 20 degrees Celsius and humidity 40%. At a certain time, the temperature is collected to be 22 degrees Celsius, and the humidity is 50%. The temperature correction is (22-15) / (25-15) = 7 / 10 = 0.7, the humidity correction is (50-30) / (60-30) = 20 / 30 = 2 / 3, and the corrected temperature and humidity distribution data is obtained. The energy consumption value in the collected equipment energy consumption fluctuation curve is between 10-40 kW, and the energy consumption value 30 kW is dynamically scaled, (30-10) / (40-10) = 20 / 30 = 2 / 3, a standardized energy consumption curve is generated, and the integrated standardized monitoring data set for the DEF-20 type transportation truck in the transportation process stage is formed.

[0063] The GHI-300 type crusher in the crushing process is also the same. Its historical running parameter set shows that the equipment rated vibration threshold range is 20-80 mm / s2, the standard temperature and humidity adaptation interval is temperature 22-32 degrees Celsius, humidity 45%-75%, and the maximum energy consumption critical value is 120 kW. The collected vibration signal amplitude is between 30-70 mm / s2, and the amplitude 40 mm / s2 is normalized, (40-30) / (70-30) = 10 / 40 = 0.25, and a standardized vibration signal sequence is generated. The environment temperature and humidity reference value in the current crushing workshop is determined to be temperature 25 degrees Celsius and humidity 55%. At a certain time, the temperature is collected to be 27 degrees Celsius, and the humidity is 65%. The temperature correction is (27-22) / (32-22) = 5 / 10 = 0.5, the humidity correction is (65-45) / (75-45) = 20 / 30 = 2 / 3, and the corrected temperature and humidity distribution data is obtained. The energy consumption value in the collected energy consumption fluctuation curve is between 40-100 kW, and the energy consumption value 70 kW is dynamically scaled, (70-40) / (100-40) = 30 / 60 = 0.5, a standardized energy consumption curve is generated, and then integrated into a standardized monitoring data set for the GHI-300 type crusher in the crushing process stage.

[0064] In a possible implementation, step S130 comprises:

[0065] Step S131, the normalized vibration signal sequence is subjected to time-frequency conversion processing to extract vibration frequency energy distribution features and resonance peak shift.

[0066] For example, for the normalized vibration signal sequence of the ABC-100 mining machine in the mining process, time-frequency conversion processing is performed to extract vibration frequency energy distribution features and resonance peak shift. The normalized vibration signal sequence is subjected to windowed Fourier transform, the window function is selected to have a length of 128 data points, and the overlap rate is set to 50%, thereby generating a vibration spectrum graph. In the vibration spectrum graph, the frequency range is divided into multiple intervals, such as 0-50 Hz, 50-100 Hz, 100-150 Hz, etc. The energy integral value in each interval is calculated, and a frequency energy distribution histogram is generated by cumulative calculation of the energy of each interval. Through detection, the main resonance peak frequency in the vibration spectrum graph is 160 Hz, and the standard resonance frequency of the device is 150 Hz, the difference between them is 160-150=10 Hz, and the resonance peak shift is obtained. The frequency energy distribution histogram is subjected to sliding window statistics, and the window size is set to 10 intervals. During the statistics process, it is found that the low-frequency energy proportion is 35%, and the high-frequency mutation times are 6. The two features are subjected to logarithmic transformation, the low-frequency energy proportion feature is transformed into ln(0.35), and the high-frequency mutation times feature is transformed into ln(6), and the transformed features are combined into vibration frequency energy distribution features.

[0067] Step S132, the corrected temperature and humidity distribution data is subjected to spatial interpolation processing to generate temperature and humidity gradient change features and local abnormal temperature zone markers.

[0068] For example, in the working area of the ABC-100 mining machine, 9 temperature and humidity sensors are arranged in a range of 15x15 square meters. Through a spatial interpolation algorithm, the temperature change rate and humidity change rate between adjacent sensors are calculated according to the data collected by each sensor. For example, the temperatures of two adjacent sensors are 27 degrees Celsius and 28 degrees Celsius, and the distance is 3 meters, so the temperature change rate is (28-27)÷3=1÷3≈0.33 degrees Celsius / meter. The temperature and humidity gradient change features of the entire area are calculated in the same way. At the same time, through analysis of the data of each point, local abnormal temperature zones are marked, such as a region whose temperature is significantly higher than the surrounding area, with a temperature of 32 degrees Celsius, which is marked as a local abnormal temperature zone, and a local abnormal temperature zone marker is generated.

[0069] Step S133, the normalized energy consumption curve is subjected to slope change analysis to extract energy consumption rise rate features and peak duration features.

[0070] In this embodiment, the first-order difference of the normalized energy consumption curve is calculated, that is, the difference between adjacent data points is calculated. Assuming that the normalized energy consumption curve data points in a certain period of time are 0.4, 0.5, 0.6, 0.7, etc., the energy consumption rate sequence obtained after first-order difference calculation is 0.1, 0.1, 0.1, etc. The rated slope threshold is set to 0.15, and the time interval in which the energy consumption rate continuously exceeds the threshold is detected. After investigation, it is found that the energy consumption rate from the 10th minute to the 15th minute continuously exceeds 0.15 in a certain period of time, and the starting time stamp 10 minutes and the ending time stamp 15 minutes are recorded. In this time interval, the energy consumption rate is 0.16, 0.18, 0.2, and 0.17, respectively, and the average slope value is calculated as (0.16+0.18+0.2+0.17)÷4=0.71÷4=0.1775, which is taken as the energy consumption rising rate feature. According to the difference between the starting time stamp and the ending time stamp, 15-10=5 minutes, the peak duration feature is determined to be 5 minutes. The extreme point detection is performed on the energy consumption rate sequence, and it is found that there is an energy consumption mutation event, and the corresponding event duration is recorded to generate the energy consumption mutation event label and the corresponding event duration.

[0071] In step S134, the vibration frequency energy distribution feature, the resonance peak shift, the temperature and humidity gradient change feature, the local abnormal temperature zone label, the energy consumption rising rate feature and the peak duration feature are input into the multi-dimensional feature extraction model, and the correlation weighting of the vibration frequency energy distribution feature and the temperature and humidity gradient change feature is performed through the cross-modal attention mechanism to generate the environment correlation feature.

[0072] In this embodiment, the vibration frequency energy distribution feature can be mapped to a query vector set, which is assumed to be [ln(0.35), ln(6)], and the temperature and humidity gradient change feature is mapped to a key vector set, which is assumed to be [0.33, 0.25]. The cosine similarity between each query vector and key vector is calculated. Taking the first query vector and the first key vector as an example, the cosine similarity is calculated as (ln(0.35)×0.33)÷(sqrt(ln2(0.35)+ln2(6))×sqrt(0.33 2 +0.252)), and a specific value is obtained after calculation. Similarly, an initial attention weight matrix is generated. The temperature parameter of the initial attention weight matrix is adjusted to 0.1, and then the Softmax normalization processing is performed to generate the standardized attention weight. The temperature and humidity gradient change feature is dynamically weighted and summed according to the standardized attention weight to generate the environment sensitive vibration feature. The environment sensitive vibration feature and the temperature and humidity gradient change feature are multiplied element by element to generate the environment correlation feature.

[0073] Step S135, jointly encode the formant shift and the energy rise rate features through a time convolution network to generate a device running state feature.

[0074] Step S136, perform pattern matching on the local abnormal temperature zone label and the peak duration feature through an anomaly detection algorithm to generate a data anomaly fluctuation feature.

[0075] For example, the formant shift 10Hz and the energy rise rate feature 0.1775 can be taken as input, and after a series of processing such as convolution layer, pooling layer, etc. in the network, a device running state feature is generated. The local abnormal temperature zone label and the peak duration feature are matched through an anomaly detection algorithm. For example, the preset anomaly mode stipulates that when the local abnormal temperature zone temperature exceeds 30 degrees Celsius and the peak duration exceeds 4 minutes, it is an abnormal situation. The current local abnormal temperature zone temperature is 32 degrees Celsius, and the peak duration is 5 minutes, which meets the anomaly mode condition, and a data anomaly fluctuation feature is generated.

[0076] For the DEF-20 type transport truck in the transportation process and the GHI-300 type crusher in the crushing process, the joint feature mapping processing is also carried out according to the above detailed process, and the respective device running state features, environment correlation features and data anomaly fluctuation features are generated.

[0077] In one possible implementation, step S131 includes:

[0078] Step S1311, performs windowed Fourier transform on the standardized vibration signal sequence to generate a vibration spectrum.

[0079] In this embodiment, for the ABC-100 type mining machine in the mining process, the standardized vibration signal sequence is processed for time-frequency conversion to extract key features, and the slope change of the standardized energy consumption curve is analyzed, and the environment correlation feature is generated through a cross-modal attention mechanism.

[0080] For the standardized vibration signal sequence of the ABC-100 mining machine, a windowed Fourier transform is first performed to generate a vibration spectrum diagram. In actual operation, a Hanning window with a length of 256 data points is selected as the window function, and the Hanning window is selected because it has good performance in reducing spectral leakage. At the same time, the overlap rate is set to 75%, which means that there are 75% of the data points overlapping between adjacent windows. In the collected standardized vibration signal sequence, taking a sequence containing 1024 data points as an example, the windowed Fourier transform is performed according to the set parameters. Starting from the first data point, each group of 256 data points is processed by applying the Hanning window function. For each group of data, the time domain signal is converted to the frequency domain by Fourier transform to obtain the corresponding frequency spectrum information. In this way, after processing a plurality of groups of data, a vibration spectrum diagram reflecting the frequency characteristics of the standardized vibration signal sequence is generated.

[0081] Step S1312, the energy integral value of each frequency interval in the vibration spectrum diagram is calculated, and a frequency energy distribution histogram is generated.

[0082] In this embodiment, the frequency range of the vibration spectrum diagram can be divided into a plurality of intervals, for example, from 0 Hz to 500 Hz, divided into 20 equal-width intervals, each interval width is 25 Hz. For each interval, the sum of the squares of the spectrum values in the interval is calculated to approximately represent the energy of the interval. Taking the first interval 0 Hz to 25 Hz as an example, find all the spectrum values in the interval in the vibration spectrum diagram, and add the squares of the above spectrum values. Assuming that there are 10 spectrum values in the interval, which are 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, then the energy integral value of the interval is the square of 0.1 plus the square of 0.2 plus the square of 0.3 plus the square of 0.4 plus the square of 0.5 plus the square of 0.6 plus the square of 0.7 plus the square of 0.8 plus the square of 0.9 plus the square of 1.0, that is, 0.01+0.04+0.09+0.16+0.25+0.36+0.49+0.64+0.81+1.0=3.85. In the same way, the energy integral value of each frequency interval is calculated, and then the frequency interval is taken as the abscissa and the energy integral value is taken as the ordinate to draw a frequency energy distribution histogram.

[0083] Step S1313, detecting the main resonance peak frequency in the vibration spectrum diagram, and calculating the difference value with the device standard resonance frequency to generate a resonance peak shift.

[0084] In this embodiment, by analyzing the vibration spectrum, the frequency point with the maximum spectrum value is found, which is the main resonance peak frequency. After detection, it is found that the main resonance peak frequency is 180 Hz. The standard resonance frequency of ABC-100 mining machine is 150 Hz, and the difference between the two is 180-150=30 Hz, which is the resonance peak shift. The resonance peak shift can reflect the difference between the current vibration state and the standard state of the device.

[0085] Step S1314, the frequency domain energy distribution histogram is counted by sliding window, and the low frequency energy proportion feature and the high frequency mutation number feature are extracted.

[0086] In this embodiment, the size of the sliding window is set to 5 intervals, and the sliding is performed with a step of 1 interval. For each window position, the proportion of the total energy of the low frequency interval (assuming 0 Hz to 100 Hz, a total of 4 intervals) in the total energy of the entire window is calculated as the low frequency energy proportion feature. For example, at a certain window position, the energy integral values of the 5 intervals in the window are 2.0, 3.0, 4.0, 5.0, and 6.0, respectively. The total energy of the low frequency interval (the first 4 intervals) is 2.0+3.0+4.0+5.0=14.0, and the total energy of the entire window is 2.0+3.0+4.0+5.0+6.0=20.0. Therefore, the low frequency energy proportion is 14.0 divided by 20.0, i.e. 0.7. At the same time, in the sliding process, the change of the energy integral value of the high frequency interval (assuming 300 Hz to 500 Hz, a total of 8 intervals) is detected. If the energy integral value of a certain interval changes more than a certain threshold (assuming 2 times) compared with the adjacent interval, it is determined as a high frequency mutation. In the entire sliding window counting process, the number of high frequency mutations is recorded. Assuming that 3 high frequency mutations are found in the counting process, the high frequency mutation number feature is 3.

[0087] Step S1315, the low frequency energy proportion feature and the high frequency mutation number feature are combined after logarithmic transformation to form the vibration frequency domain energy distribution feature.

[0088] In this embodiment, for example, the low frequency energy proportion feature 0.7 is logarithmically transformed to obtain ln(0.7). The high frequency mutation number feature 3 is logarithmically transformed to obtain ln(3). The two features after logarithmic transformation are combined to form the vibration frequency domain energy distribution feature, which integrates the low frequency energy distribution and the high frequency mutation, and more comprehensively reflects the characteristics of the device vibration signal in the frequency domain.

[0089] In one possible implementation, step S133 includes:

[0090] Step S1331, first-order difference calculation is performed on the standardized energy consumption curve to generate an energy consumption rate of change sequence.

[0091] For example, for the standardized energy consumption curve of the ABC-100 mining machine, first-order difference calculation is performed to generate an energy consumption rate of change sequence. The standardized energy consumption curve is a curve composed of a series of energy consumption data points changing over time. Taking a certain segment of the standardized energy consumption curve data containing 100 time points as an example, the data points are 0.4, 0.45, 0.5, 0.55, 0.6, and so on. First-order difference calculation is to calculate the difference between adjacent two data points. For the first data point 0.4 and the second data point 0.45, the difference is 0.45-0.4=0.05; for the second data point 0.45 and the third data point 0.5, the difference is 0.5-0.45=0.05. In this way, after calculating the 100 data points, the energy consumption rate of change sequence is obtained as 0.05, 0.05, 0.05, 0.05, and so on.

[0092] Step S1332, detecting a time interval in the energy consumption rate of change sequence that continuously exceeds the rated slope threshold value, and recording the start time stamp and the end time stamp.

[0093] For example, the rated slope threshold value is set to 0.08. In the energy consumption rate of change sequence, the first data point is checked in sequence. When it is found that a certain data point and the subsequent continuous data points all exceed 0.08, the start time stamp is recorded. Assuming that at the 10th time point, the energy consumption rate of change is 0.09, which exceeds the rated slope threshold value, and the subsequent data points are found to exceed 0.08 from the 10th time point to the 20th time point, then the start time stamp is the 10th time point and the end time stamp is the 20th time point.

[0094] Step S1333, calculating the average slope value in the time interval as the energy consumption rate of rise feature.

[0095] For example, in the above-mentioned time interval (from the 10th time point to the 20th time point), the energy consumption rate of change sequence is 0.09, 0.1, 0.11, 0.12, 0.13, 0.14, 0.15, 0.16, 0.17, 0.18, 0.19, 0.2. The average value of the above-mentioned data is calculated, i.e. (0.09+0.1+0.11+0.12+0.13+0.14+0.15+0.16+0.17+0.18+0.19+0.2) divided by 11 (the number of data points), which is (1.74) divided by 11≈0.158, and this 0.158 is the energy consumption rate of rise feature.

[0096] Step S1334, determining the peak duration feature according to the difference between the start timestamp and the end timestamp.

[0097] For example, the start timestamp is the 10th time point, the end timestamp is the 20th time point, and the difference between the two is 20-10=10 time units (assuming that each time point interval is 1 minute, then the peak duration is 10 minutes), which is the peak duration feature.

[0098] Step S1335, performing extreme point detection on the energy consumption change rate sequence to generate energy consumption mutation event labels and corresponding event duration.

[0099] For example, in the energy consumption change rate sequence, find points that are greater than or less than adjacent data points, which are extreme points. For example, in the sequence 0.05, 0.05, 0.05, 0.06, 0.05, 0.04, 0.06 is a maximum point and 0.04 is a minimum point. When an extreme point is detected, record the time point at which the extreme point appears and the duration of the extreme point. Assuming that the maximum value 0.06 appears from the 25th time point and lasts until the 27th time point, then mark it as an energy consumption mutation event, and the event duration is 3 time units (3 minutes), and generate energy consumption mutation event labels and corresponding event duration.

[0100] In one possible implementation, step S134 includes:

[0101] Step S1341, mapping the vibration frequency energy distribution feature into a query vector set and mapping the temperature and humidity gradient change feature into a key vector set.

[0102] For example, for the ABC-100 type mining machine, assuming that the vibration frequency energy distribution feature is processed into [ln(0.7), ln(3)], it is mapped into a query vector set Q=[[ln(0.7), ln(3)]]. Assuming that the temperature and humidity gradient change feature is processed into [0.2, 0.3], it is mapped into a key vector set K=[[0.2, 0.3]].

[0103] Step S1342, calculating the cosine similarity between each query vector and key vector to generate an initial attention weight matrix.

[0104] For example, for a query vector [ln(0.7), ln(3)] and a key vector [0.2, 0.3], the formula for calculating the cosine similarity is the dot product of the two vectors divided by the product of their magnitudes. First, calculate the dot product, ln(0.7) * 0.2 + ln(3) * 0.3. ln(0.7) is approximately -0.357, and ln(3) is approximately 1.099, so the dot product is -0.357 * 0.2 + 1.099 * 0.3 = -0.0714 + 0.3297 = 0.2583. Next, calculate the magnitude of the query vector, sqrt(ln 2(0.7) + ln 2(3)) = sqrt((-0.357) 2 + (1.099) 2) = sqrt(0.127449 + 1.207801) = sqrt(1.33525) ≈ 1.155. The magnitude of the key vector is sqrt(0.22 + 0.3 2 ) = sqrt(0.04 + 0.09) = sqrt(0.13) ≈ 0.361. Then the cosine similarity is 0.2583 divided by (1.155 * 0.361), 0.2583 ÷ (1.155 * 0.361) = 0.2583 ÷ 0.417955 ≈ 0.618, thus generating an initial attention weight matrix, assuming that the initial attention weight matrix has only one element, 0.618.

[0105] In step S1343, the initial attention weight matrix is temperature parameter adjusted and Softmax normalized to generate a standardized attention weight.

[0106] For example, set the temperature parameter τ = 0.1. Temperature parameter adjustment is performed on each element in the initial attention weight matrix, and the element value is divided by the temperature parameter to obtain 0.618 ÷ 0.1 = 6.18. Softmax normalization processing is to perform exponential operation on the adjusted element value, and then divide by the sum of all element values after exponential operation. Here, there is only one element, and after exponential operation, it is e 6.18, which is approximately 485.5. The standardized attention weight is this value divided by the sum of all element values after exponential operation (here, there is only one element, so it is itself), i.e. the standardized attention weight is 485.5 ÷ 485.5 = 1.

[0107] In step S1344, the temperature and humidity gradient change feature is dynamically weighted and summed according to the standardized attention weight to generate an environment-sensitive vibration feature.

[0108] For example, the temperature and humidity gradient change feature is [0.2, 0.3], and the standardized attention weight is 1. Dynamic weighted sum is to multiply the standardized attention weight by each element of the temperature and humidity gradient change feature and then add them up, i.e. 1 * 0.2 + 1 * 0.3 = 0.5, generating an environment-sensitive vibration feature 0.5.

[0109] Step S1345, element-wise multiplication of the environment-sensitive vibration feature and the temperature-humidity gradient change feature is performed to generate the environment-related feature.

[0110] For example, the environment-sensitive vibration feature is 0.5, and the temperature-humidity gradient change feature is [0.2, 0.3]. Element-wise multiplication is performed to obtain [0.5 x 0.2, 0.5 x 0.3] = [0.1, 0.15], which is the generated environment-related feature.

[0111] For the DEF-20 type transport truck in the transportation process and the GHI-300 type crusher in the crushing process, the above detailed process is also performed. When the time-frequency conversion processing of the standardized vibration signal sequence of the equipment is performed, the slope change analysis of the standardized energy consumption curve is performed, and the environment-related feature is generated through the cross-modal attention mechanism, according to the characteristics of the respective equipment and the collected data, the corresponding calculation and processing are performed to obtain the key features reflecting the running state, energy consumption and environment-related of the equipment.

[0112] In one possible implementation, step S140 includes:

[0113] Step S141, the device running state feature and the environment-related feature are spliced to generate a device environment coupling feature.

[0114] In this embodiment, the device running state feature of the ABC-100 type mining machine is obtained by jointly encoding the resonance peak shift and the energy consumption rate of rise features, and the value is assumed to be [0.6, 0.8]. These two values respectively reflect the running state of the device in terms of vibration and energy consumption. The environment-related feature is generated by the cross-modal attention mechanism by correlating the vibration frequency energy distribution feature and the temperature-humidity gradient change feature, and is assumed to be [0.4, 0.5], which reflects the correlation between the device running and environmental factors. Splicing these two features, i.e., combining them in order, forms the device environment coupling feature [0.6, 0.8, 0.4, 0.5], which integrates the information of the device running state and environmental factors.

[0115] Step S142, calling the risk level prediction branch in the abnormal pattern recognition model to perform convolution processing on the device environment coupling feature, and outputting a device failure probability value and an environmental interference coefficient.

[0116] In this embodiment, the risk level prediction branch in the abnormal pattern recognition model includes a series of convolutional layers, activation functions, and fully connected layers, etc. When the device environment coupling features [0.6, 0.8, 0.4, 0.5] are convolved, they are first processed by the first convolutional layer, which has multiple convolutional kernels. Each convolutional kernel is convolved with the device environment coupling features. For example, one of the convolutional kernels is [0.2, 0.3, 0.1, 0.4], which is convolved with the device environment coupling features by multiplying the corresponding elements and summing them up: 0.6x0.2+0.8x0.3+0.4x0.1+0.5x0.4=0.12+0.24+0.04+0.2=0.6. After the operation of multiple convolutional kernels, a new set of data is obtained. Then the data is processed by an activation function, such as the ReLU function, which sets values less than 0 to 0 and keeps values greater than 0 unchanged. After multiple layers of convolution and activation function processing, the data is input into the fully connected layer. The fully connected layer performs comprehensive calculations on the processed data and finally outputs the device failure probability value and the environmental interference coefficient. Assuming that after this series of processing, the output device failure probability value is 0.3 and the environmental interference coefficient is 0.2. The device failure probability value reflects the possibility of device failure, and the environmental interference coefficient reflects the degree of influence of environmental factors on device operation.

[0117] Step S143, calling the strategy generation branch in the abnormal pattern recognition model to analyze the data abnormal fluctuation features, extract the abnormal trigger conditions and fluctuation propagation path.

[0118] In this embodiment, the data abnormal fluctuation features are obtained by pattern matching of the local abnormal temperature zone label and the peak duration feature. Assuming that the data abnormal fluctuation features show that the temperature of the local abnormal temperature zone reaches 35 degrees Celsius (higher than the normal range) and the peak duration is 8 minutes (exceeding the normal standard) in a certain time period. The strategy generation branch can analyze the above data abnormal fluctuation features in depth, compare them with the pre-set abnormal pattern library, and identify that this is an abnormal pattern caused by excessive environmental temperature leading to abnormal increase of device energy consumption. Further, the abnormal trigger condition is extracted as the temperature of the local abnormal temperature zone exceeding 32 degrees Celsius and the peak duration exceeding 6 minutes. The fluctuation propagation path is from the local high temperature area affecting the heat dissipation system of the device, then affecting the energy consumption of the device, and further affecting other associated devices through the power transmission system between devices. Identifying the abnormal trigger condition and the fluctuation propagation path is crucial for formulating targeted optimization strategies subsequently.

[0119] Step S144, determining the device operation risk level according to the weighted sum of the device failure probability value and the environmental interference coefficient, the device operation risk level including low risk, medium risk and high risk.

[0120] In this example, assume that the weight of the equipment failure probability value is pre-set to 0.6, and the weight of the environmental interference coefficient is pre-set to 0.4. The calculated weighted sum is: 0.3 × 0.6 + 0.2 × 0.4 = 0.18 + 0.08 = 0.26. According to the pre-established risk level classification criteria, a weighted sum less than 0.3 indicates low risk, between 0.3 and 0.6 indicates medium risk, and greater than 0.6 indicates high risk. Since the calculated weighted sum is 0.26, the current equipment operation risk level of the ABC-100 mining machine is low risk. Accurately determining the risk level allows timely implementation of appropriate measures to ensure stable equipment operation.

[0121] Step S145 , generating equipment parameter adjustment instructions and environmental control solutions based on matching the abnormal triggering conditions with a preset optimization operation template library.

[0122] For example, the previously identified abnormal trigger condition—a local abnormal temperature zone exceeding 32°C with a peak duration exceeding 6 minutes—is matched against a pre-set optimization operation template library. The template library includes corresponding optimization measures for this situation, generating equipment parameter adjustment instructions to lower the mining machine's cooling system activation threshold by 3°C, enabling the cooling system to activate earlier to cope with the high temperature environment. Simultaneously, the equipment's digging speed is appropriately reduced to reduce the load and, therefore, energy consumption. Specifically, the digging speed is adjusted from 10 cubic meters per minute to 8 cubic meters per minute. The environmental control plan involves increasing ventilation in the work area and boosting the ventilation system's operating power by 20% to reduce the temperature in the local abnormal temperature zone. Furthermore, the dust removal system's operating schedule is adjusted, increasing dust removal frequency during high-temperature periods from once per hour to every half hour to improve the working environment and reduce the impact of dust on the equipment. These instructions and solutions are designed to eliminate or mitigate the impact of abnormal trigger conditions on equipment operation and enhance equipment stability and reliability.

[0123] Step S146: determining a list of affected equipment based on the wave propagation path, and generating a collaborative optimization strategy for the production process.

[0124] In this embodiment, according to the previously determined fluctuation propagation path, that is, the influence of the local high-temperature area on the heat dissipation system of the equipment, and then on the energy consumption of the equipment, and then through the power transmission system between the equipment to affect the associated other equipment. After analysis, it is determined that the affected equipment includes the transport equipment that shares the power transmission system with the ABC-100 mining machine, and other auxiliary equipment located in the same operation area. In order to ensure the coordinated operation of the entire production process, a production process coordination optimization strategy is generated. For the affected transport equipment, the transport speed is appropriately reduced, and the load is reduced to reduce the pressure on the power transmission system. For example, the transport speed of the transport equipment is reduced from 30 kilometers per hour to 25 kilometers per hour, and the amount of ore transported each time is reduced from 20 tons to 18 tons. For other auxiliary equipment, adjust its working time to avoid full load work at the same time when the mining machine is in high temperature operation period. Reallocate the equipment load rate and task priority of each process section, appropriately reduce the task priority of the mining machine, and at the same time improve the task priority of the transport equipment and auxiliary equipment in ensuring the normal operation of the equipment. Through the above production process coordination optimization strategy, the coordinated work between each equipment is realized, and the influence of abnormal fluctuation on the entire production process is reduced.

[0125] Step S147, integrate the equipment parameter adjustment instruction, environment regulation scheme and production process coordination optimization strategy into the production process optimization strategy set.

[0126] In this embodiment, the production process optimization strategy set contains comprehensive optimization measures for the ABC-100 mining machine and its related production links, aiming to improve the equipment operation efficiency, reduce the risk, and ensure the stability and efficiency of the entire production process.

[0127] In a possible implementation, step S150 includes:

[0128] Step S151, when the equipment operation risk level is low risk, generating equipment state monitoring prompt information and sending it to the inspection terminal.

[0129] For example, when the equipment operation risk level of the ABC-100 mining machine is low risk, the equipment state monitoring prompt information is generated and sent to the inspection terminal. The content of the prompt information is "the current operation risk level of the ABC-100 mining machine is low risk, but the local abnormal temperature area and the energy consumption change should still be paid attention to, and it is suggested that the inspection personnel strengthen the inspection of the relevant area". After receiving the information, the inspection personnel will focus on the above aspects in the daily inspection, and timely find potential problems.

[0130] Step S152, when the equipment operation risk level is medium risk, generating equipment maintenance warning instruction and starting spare parts inventory checking process.

[0131] For example, the device maintenance early warning instruction informs the maintenance team to conduct a comprehensive inspection and maintenance of the ABC-100 mining machine to prevent possible failures in advance. At the same time, the spare parts inventory checking process is started to check the spare parts inventory related to the mining machine, such as the cooling system components, transmission components, etc. Ensure that there are enough spare parts in stock so that they can be replaced in time when needed, reducing equipment downtime. For example, after checking, it is found that the spare parts of a key valve of the cooling system are insufficient, and timely procurement is arranged to supplement them.

[0132] Step S153, when the device operation risk level is high risk, generating a device emergency shutdown instruction and a personnel evacuation warning signal.

[0133] For example, an emergency shutdown instruction can be immediately sent to the ABC-100 mining machine to stop running to avoid more serious damage to the device and personnel caused by possible serious failures. At the same time, the personnel evacuation warning signal is started to notify personnel in the nearby work area to quickly evacuate to a safe area. Through the broadcast system and warning lights, etc., ensure that personnel can receive evacuation information in time and evacuate safely.

[0134] Step S154, parsing the device parameter adjustment instruction in the production process optimization strategy set into the speed adjustment value of the target device, the cooling system start threshold, and the power supply frequency correction parameter.

[0135] For example, the adjustment of the mining machine digging speed in the device parameter adjustment instruction is converted into the speed adjustment value. Assuming that the digging speed of the mining machine is proportional to the motor speed, the motor speed is adjusted from 1500 rpm to 1200 rpm after calculation. The cooling system start threshold is reduced from 38 degrees Celsius to 35 degrees Celsius. For the power supply frequency correction parameter, according to the electrical characteristics and operation requirements of the device, the power supply frequency is fine-tuned from 50 Hz to 49.5 Hz to adapt to the needs of the device in the new operating state.

[0136] Step S155, converting the environment regulation scheme into the ventilation device operation mode and the dust removal system work schedule.

[0137] For example, the ventilation device operation mode is adjusted to increase the operating power of the ventilation device by 20%. The original operating power of the ventilation device is 50 kW, which is increased to 50x(1+20%) = 50x1.2 = 60 kW after adjustment, and the operation time of the ventilation device is adjusted to run continuously during the high temperature period. The dust removal system work schedule is increased from once an hour to once every half hour, and the specific work time is reasonably arranged according to the production operation time to ensure that the dust concentration can be effectively reduced during the operation of the device.

[0138] Step S156, according to the production process optimization strategy, re-allocate the equipment load rate and task priority of each process segment.

[0139] For example, for the mining process, the load rate of the ABC-100 mining machine is reduced from the original 80% to 60%, and the excavation amount is reduced to reduce the working intensity of the equipment. For the transportation process, the load rate of the transportation equipment is reduced from the original 70% to 60%, and the transportation task priority is adjusted to ensure the transportation demand of the mining machine. For other auxiliary processes, according to the degree of association with the mining machine, the equipment load rate and task priority are reasonably adjusted to ensure the coordinated operation of the entire production process.

[0140] Step S157, through the production control terminal, the speed adjustment value, the cooling system starting threshold, the power supply frequency correction parameter, the ventilation equipment operation mode, the dust removal system work schedule, the equipment load rate and the task priority are issued to the corresponding execution mechanism.

[0141] For example, the production control terminal accurately sends the above adjustment parameters and instructions to the controllers and execution mechanisms of each device through wired or wireless communication networks. For example, the speed adjustment value is sent to the motor controller of the mining machine, and the motor controller adjusts the speed of the motor according to the received instruction; the cooling system starting threshold is sent to the control module of the cooling system, and the cooling system starts automatically when the temperature reaches the new threshold; the power supply frequency correction parameter is sent to the inverter of the power supply system, and the inverter adjusts the output power supply frequency. The execution mechanisms of the ventilation equipment and the dust removal system adjust according to the received operation mode and work schedule. The equipment of each process segment adjusts its running state according to the re-allocated load rate and task priority, realizes the optimization and adjustment of the entire production process, and ensures the safe, stable and efficient operation of the mine production.

[0142] For the DEF-20 type transport truck in the transportation process and the GHI-300 type crusher in the crushing process, the dynamic fusion analysis, risk level evaluation, strategy generation and instruction execution are also carried out according to the above detailed process. According to their respective equipment running state characteristics, environmental association characteristics and data abnormal fluctuation characteristics, combined with the preset abnormal mode recognition model, the corresponding equipment running risk level is determined, the corresponding production process optimization strategy set is generated, and the equipment running parameters are adjusted through the production control terminal to ensure the stable operation of the entire mine production system.

[0143] In one possible implementation, step S146 includes:

[0144] Step S1461, based on the fluctuation propagation path, traverse the production process topology graph, and extract a set of adjacent process nodes that have a signal transmission path with the current data abnormal fluctuation characteristics.

[0145] For example, a production process topology diagram details the connections and signal transmission paths between the various processes in a mining operation. Taking the ABC-100 mining machine as an example, assuming that its abnormal data fluctuations stem from excessively high temperatures in a local abnormal temperature zone, which affects the equipment's energy consumption, a traversal of the topology diagram reveals that the adjacent process nodes directly associated with the mining machine include the ore transportation link and the pre-crushing pre-processing link. The ore transportation link is responsible for transporting the mined ore to the designated location, while the pre-crushing pre-processing link performs preliminary screening and processing of the ore. Material transmission and signal interaction occur between these links and the mining machine, forming a path for the potential propagation of abnormal data fluctuations. Therefore, the extracted set of adjacent process nodes includes the node for the DEF-20 transport truck in the transportation process and some of the screening equipment nodes in the pre-processing process.

[0146] Step S1462 , querying the equipment identifiers of the shared power supply system or transmission belt connection in the adjacent process node set according to the equipment dependency graph, and generating a target equipment set.

[0147] In this embodiment, the equipment dependency graph records the power supply and mechanical connection relationships between various types of equipment in the mine. In the above-mentioned adjacent process node set, it can be seen by querying the graph that the DEF-20 transport truck and the ABC-100 mining machine share part of the same power supply system, which means that abnormal fluctuations in the mining machine may affect the transport truck through the power system. At the same time, the screening equipment in the pretreatment process is connected to the mining machine through a conveyor belt. During the process of transporting the ore from the mining machine to the screening equipment, abnormal fluctuations may also be transmitted. Based on the above relationship, it is determined that the target equipment set includes the DEF-20 transport truck, the GHI-10 screening equipment in the pretreatment process, and other auxiliary equipment closely related to them. The above-mentioned equipment is interrelated in the production process, and the abnormality of one equipment may trigger a chain reaction, so they are all included in the target equipment set for further analysis.

[0148] Step S1463: Obtain historical operating parameters of each device in the target device set, and calculate the signal attenuation coefficient of the abnormal data fluctuation feature on the fluctuation propagation path.

[0149] For example, for the DEF-20 type transport truck, the historical operation parameters include speed, energy consumption and other data under different load conditions, as well as operation stability records under various environmental conditions. For the GHI-10 type screening device, the historical operation parameters cover information such as vibration frequency of the device, screening efficiency, and wear condition of different parts. By analyzing the above historical data and combining the specific situation of the current ABC-100 type mining machine data abnormal fluctuation, the signal attenuation coefficient is calculated. Assuming that the abnormal fluctuation of the mining machine is in the form of energy, it is transmitted to other devices through the power supply system and the transmission belt. Taking the power supply system as an example, when calculating the signal attenuation coefficient from the mining machine to the transport truck, the influence of factors such as resistance and capacitance of the power line on energy transmission is considered. Assuming that the resistance of the power line will attenuate the transmitted energy by a certain percentage, after a series of analysis and data comparison, it is calculated that the signal attenuation coefficient from the mining machine to the transport truck is 0.6. This means that when the abnormal fluctuation of the mining machine is transmitted to the transport truck, its intensity will be weakened to 60% of the original. For the screening device connected by the transmission belt, considering the influence of factors such as the material, length of the transmission belt and the conveying capacity of the ore on signal transmission, the signal attenuation coefficient is calculated to be 0.7. The above signal attenuation coefficient reflects the difference in the degree of influence of abnormal fluctuations on different devices in different propagation paths.

[0150] In step S1464, the affected device identifier list in which the affected degree exceeds a preset threshold is screened from the target device set according to the signal attenuation coefficient.

[0151] In this embodiment, the preset threshold is determined according to long-term production experience and equipment performance research, which is used to judge whether the equipment is significantly affected. Assuming that the preset threshold is 0.5, that is, when the signal attenuation coefficient is greater than 0.5, it is considered that the equipment is significantly affected. Based on this standard, the signal attenuation coefficient of the DEF-20 type transport truck is 0.6, which exceeds the preset threshold; the signal attenuation coefficient of the GHI-10 type screening device is 0.7, which also exceeds the preset threshold. Therefore, the affected device identifier list screened includes the DEF-20 type transport truck and the GHI-10 type screening device. The above devices may be greatly affected when the mining machine has data abnormal fluctuation, and need to be optimized and adjusted accordingly.

[0152] In step S1465, the start order of each device in the affected device identifier list is rearranged based on the process timing dependency relationship of the affected device identifier list.

[0153] In this embodiment, the process timing dependency describes the sequence of each process in time and the constraint relationship between each other. In mine production, the mining work of the mining machine is the starting point of the whole process, and the mined ore will enter the transportation and pretreatment links. Therefore, the start of the DEF-20 type transport truck and the GHI-10 type screening equipment needs to rely on the normal operation of the mining machine. However, due to the abnormal fluctuation of the mining machine data, in order to ensure the continuity and stability of production, it is necessary to re-adjust the start sequence of the above-mentioned equipment. After detailed analysis, the new start sequence is determined as follows: after the mining machine is started and runs for a period of time to ensure that its running state is relatively stable, the GHI-10 type screening equipment is started first, because the screening equipment can preliminarily process the mined ore of the mining machine, reducing the pressure of the subsequent transportation link. After the screening equipment is stably running, the DEF-20 type transport truck is started to transport the screened ore to the designated location. Such start sequence adjustment can avoid the production confusion caused by the blind start of the subsequent equipment when the mining machine is abnormally fluctuating.

[0154] In step S1466, a dynamic buffer time window configuration is generated according to the signal attenuation coefficient and the preset buffer time window parameter mapping table.

[0155] In this embodiment, the preset buffer time window parameter mapping table is formulated according to a large number of production experiments and data analysis, which specifies the buffer time window corresponding to different signal attenuation coefficients. For the DEF-20 type transport truck, the signal attenuation coefficient is 0.6, and the corresponding buffer time window is found in the mapping table. Assuming that the mapping table specifies that when the signal attenuation coefficient is between 0.5-0.7, the buffer time window is 5-10 minutes. Considering the actual running situation of the transport truck and the degree of possible influence, it is determined to configure an 8-minute buffer time window for it. For the GHI-10 type screening equipment, the signal attenuation coefficient is 0.7, and according to the mapping table, the corresponding buffer time window is 8-12 minutes, and finally it is determined to configure a 10-minute buffer time window. The above-mentioned buffer time window is set in order to give enough time for the equipment to adapt to the possible influence of abnormal fluctuation after the equipment is started, and to avoid the equipment running in an unstable state.

[0156] In step S1467, the start sequence is matched with the dynamic buffer time window configuration to generate a production process coordination optimization strategy containing equipment execution timing and buffer interval.

[0157] For example, a specific production process coordination optimization strategy can be formulated according to the newly determined start-up sequence and buffer time window configuration. First, the ABC-100 mining machine is started, and after it runs for 10 minutes (which is used for the initialization and stable operation of the mining machine itself), the GHI-10 screening device is started, and a 10-minute buffer time window is set for the GHI-10 screening device. Within the 10 minutes, the screening device can gradually adapt to the abnormal fluctuation signals that may come from the mining machine, and make parameter adjustments and operation state optimizations. After the GHI-10 screening device runs for 8 minutes (i.e. within its buffer time window), the DEF-20 transport truck is started, and an 8-minute buffer time window is set for the transport truck. Within the buffer time window of the transport truck, it can adjust the transport speed, load, and other parameters according to the abnormal fluctuation signals it receives, to ensure the smoothness of the transport process. In this way, the start-up sequence of the equipment is combined with the buffer time window to form a complete production process coordination optimization strategy, effectively reducing the impact of data abnormal fluctuations on the entire production process, and improving the coordination and stability of production.

[0158] For example, in one possible implementation, step S154 includes:

[0159] Step S1541, querying the reference speed range of the target device under the current production process from the device historical operation database.

[0160] In this embodiment, the device historical operation database stores the operation data of the transport truck under different production conditions. For example, it is learned through the query that the reference speed range of the DEF-20 transport truck under the current production process of transporting ore is 1200-1800 revolutions / minute.

[0161] Step S1542, calculating the target speed actual value based on the percentage coefficient corresponding to the speed adjustment value, and generating a speed control instruction containing an acceleration time curve.

[0162] For example, assume that according to the optimization strategy, the rotation speed of the transport truck needs to be reduced by 20%. Then in the range of the reference rotation speed, take the middle value 1500 rpm as the calculation basis. The calculated target rotation speed actual value is 1500 x (1-20%) = 1500 x 0.8 = 1200 rpm. At the same time, in order to ensure that the transport truck adjusts smoothly from the current rotation speed to the target rotation speed, it is necessary to generate a rotation speed control instruction containing an acceleration time curve. Considering the inertia and mechanical performance of the transport truck, set the acceleration time to 5 minutes, and within these 5 minutes, the rotation speed gradually decreases from the current rotation speed to 1200 rpm according to a certain curve. For example, in the first 2 minutes, the rotation speed slowly decreases by 50 rpm per minute; in the next 2 minutes, the rotation speed decreases faster, by 100 rpm per minute; and in the last 1 minute, the rotation speed is fine-tuned to 1200 rpm. Such an acceleration time curve can avoid damage to the equipment caused by too fast rotation speed adjustment, and ensure the safety and stability of the transportation process.

[0163] Step S1543, determine the compensation amount of the cooling system starting threshold value according to the equipment heat dissipation performance parameter and the current environment temperature, and generate a dynamically changing cooling trigger condition.

[0164] For example, the heat dissipation performance parameter of the DEF-20 type transport truck records its heat dissipation capacity under different temperature and load conditions. The current environment temperature is assumed to be 30 degrees Celsius, and according to the heat dissipation performance parameter, it is known that in this temperature, in order to ensure the normal operation of the key components such as the engine of the transport truck, the cooling system needs to be started in advance. After analysis and calculation, it is determined that the compensation amount of the cooling system starting threshold value is 5 degrees Celsius. That is, the original cooling system starting threshold value is 40 degrees Celsius, and now it is adjusted to 40-5 = 35 degrees Celsius. The generated dynamically changing cooling trigger condition is: when the engine temperature of the transport truck reaches 35 degrees Celsius, the cooling system automatically starts to ensure that the engine works in an appropriate temperature range and prevents equipment failure due to high temperature.

[0165] Step S1544, convert the power supply frequency correction parameter into a phase adjustment amount of the inverter modulation waveform through the power supply network impedance characteristic model.

[0166] In this embodiment, the power supply network impedance characteristic model describes the relationship between impedance and parameters such as frequency, voltage in the power supply network. For example, according to the optimization strategy, it is necessary to adjust the power supply frequency correction parameter to reduce 0.5Hz, that is, from the original 50Hz to 49.5Hz. Through calculation and analysis by the power supply network impedance characteristic model, considering the influence of factors such as resistance, inductance, capacitance of the power supply line on power transmission, as well as the working principle and performance requirements of the inverter, the phase adjustment amount of the inverter modulation waveform is calculated. The specific calculation process involves the comprehensive use of multiple electrical parameters and formulas, for example, according to Ohm's law and electromagnetic induction principle, the current and voltage changes in the power supply line are analyzed, and then the influence on the phase of the inverter modulation waveform is determined. After a series of calculations, it is finally determined that the phase of the inverter modulation waveform needs to be adjusted by 15 degrees to ensure that the transport truck can operate normally under the new power supply frequency, and to ensure the stability and reliability of the power supply of the equipment.

[0167] For the GHI-10 type screening equipment, the device parameter adjustment instruction is parsed according to the above detailed process. According to the device historical operation database query reference speed range, the target speed actual value is calculated and the speed control instruction is generated; the compensation amount of the cooling system starting threshold is determined according to the device heat dissipation performance parameters and the current environment temperature, and the dynamically changing cooling trigger condition is generated; the power supply frequency correction parameter is converted into the phase adjustment amount of the inverter modulation waveform through the power supply network impedance characteristic model. Through the accurate adjustment and optimization of the above device parameters, the coordination and stability of the entire production process are further improved, the device operation risk is reduced, and the efficient and safe production of the mine is ensured.

[0168] Figure 2 A schematic diagram of exemplary hardware and software components of the intelligent monitoring system for production process based on smart mine 100 that can implement the inventive concept provided by some embodiments of the present application is shown. For example, the processor 120 can be used in the intelligent monitoring system for production process based on smart mine 100 and used to execute the functions in the present application.

[0169] The intelligent monitoring system for production process based on smart mine 100 can be a general server or a special-purpose server, both of which can be used to implement the intelligent monitoring method for production process based on smart mine of the present application. Although only one server is shown in the present application, for the sake of convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0170] For example, the intelligent monitoring system 100 for production process of smart mine can include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as a disk, a ROM, or a RAM, or any combination thereof. The intelligent monitoring system 100 for production process of smart mine can also include program instructions stored in a ROM, a RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The intelligent monitoring system 100 for production process of smart mine also includes an input / output (I / O) interface 150 between the computer and other input / output devices.

[0171] For ease of illustration, only one processor is described in the intelligent monitoring system 100 for production process of smart mine. However, it should be noted that the intelligent monitoring system 100 for production process of smart mine in the present application can also include multiple processors, so the steps performed by one processor described in the present application can also be jointly performed or separately performed by multiple processors. For example, if the processor of the intelligent monitoring system 100 for production process of smart mine performs steps A and B, it should be understood that steps A and B can also be jointly performed by two different processors or separately performed in one processor. For example, a first processor performs step A, a second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0172] In addition, the embodiment of the present application also provides a readable storage medium, wherein computer executable instructions are preset in the readable storage medium, and when a processor executes the computer executable instructions, the above method for intelligent monitoring of production process of smart mine is implemented.

[0173] It should be noted that, in order to simplify the description of the present application and to help the understanding of one or more embodiments of the present application, in the foregoing description of the embodiments of the present application, various features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A production process intelligent monitoring method based on smart mines, characterized in that: The method comprises: Collecting target monitoring data sets of mining equipment in real-time production processes, including equipment vibration time series signals, ambient temperature and humidity distribution data, and equipment energy consumption fluctuation curves; Performing dynamic standardization on the target monitoring data set to generate a standardized monitoring data set that matches the equipment type and production process stage, specifically including: Obtaining a set of historical operating parameters of mining equipment, wherein the set of historical operating parameters includes a rated vibration threshold range of the equipment, a standard temperature and humidity adaptation range, and a maximum energy consumption critical value; According to the device type matching corresponding device rated vibration threshold range, the device vibration time series signal is amplitude normalized to generate a standardized vibration signal sequence; Determine the current ambient temperature and humidity reference value according to the production process stage, perform deviation correction processing on the ambient temperature and humidity distribution data based on the standard temperature and humidity adaptation range, and generate corrected temperature and humidity distribution data; Dynamically scaling the device energy consumption fluctuation curve according to the maximum energy consumption critical value to generate a standardized energy consumption curve; Integrating the standardized vibration signal sequence, the corrected temperature and humidity distribution data, and the standardized energy consumption curve into the standardized monitoring data set; The pre-trained multi-dimensional feature extraction model is called to perform joint feature mapping processing on the standardized monitoring data set to generate equipment operation status features, environment-related features, and data abnormal fluctuation features, specifically including: Performing time-frequency conversion on the standardized vibration signal sequence to extract vibration frequency domain energy distribution characteristics and resonance peak offset; Performing spatial interpolation processing on the corrected temperature and humidity distribution data to generate temperature and humidity gradient change characteristics and local abnormal temperature zone marks; Performing slope change analysis on the standardized energy consumption curve to extract energy consumption rising rate characteristics and peak duration characteristics; The vibration frequency domain energy distribution features, resonance peak offset, temperature and humidity gradient change features, local abnormal temperature zone markers, energy consumption increase rate features, and peak duration features are input into the multi-dimensional feature extraction model, and the vibration frequency domain energy distribution features and the temperature and humidity gradient change features are weighted by correlation using a cross-modal attention mechanism to generate environment-related features; The resonance peak offset and the energy consumption increase rate feature are jointly encoded through a temporal convolutional network to generate a device operation status feature; Performing pattern matching on the local abnormal temperature zone mark and peak duration characteristics through an anomaly detection algorithm to generate data abnormal fluctuation characteristics; Based on a preset abnormal pattern recognition model, a dynamic fusion analysis is performed on the equipment operation status characteristics, environmental correlation characteristics, and data abnormal fluctuation characteristics to generate an equipment operation risk level and a production process optimization strategy set; The corresponding alarm instruction is triggered according to the equipment operation risk level, and the production process optimization strategy set is fed back to the production control terminal to adjust the equipment operation parameters.

2. The production process intelligent monitoring method based on smart mine according to claim 1 is characterized in that: The step of performing time-frequency conversion on the standardized vibration signal sequence to extract the vibration frequency domain energy distribution characteristics and the resonance peak offset includes: Performing a windowed Fourier transform on the standardized vibration signal sequence to generate a vibration spectrum; Calculating the energy integral value of each frequency interval in the vibration spectrum to generate a frequency domain energy distribution histogram; Detecting the main resonance peak frequency in the vibration spectrum, and performing difference calculation with the standard resonance frequency of the device to generate a resonance peak offset; Perform sliding window statistics on the frequency domain energy distribution histogram to extract low-frequency energy proportion characteristics and high-frequency mutation frequency characteristics; The low-frequency energy proportion feature and the high-frequency mutation number feature are logarithmically transformed and then merged into the vibration frequency domain energy distribution feature.

3. The production process intelligent monitoring method based on smart mine according to claim 1 is characterized in that: The slope change analysis of the standardized energy consumption curve is performed to extract the energy consumption rising rate characteristics and peak duration characteristics, including: Performing first-order difference calculation on the standardized energy consumption curve to generate an energy consumption change rate sequence; Detecting a time interval in the energy consumption change rate sequence that continuously exceeds a rated slope threshold, and recording a start timestamp and an end timestamp thereof; Calculating an average slope value within the time interval as the energy consumption increase rate characteristic; Determining the peak duration feature according to a difference between the start timestamp and the end timestamp; The energy consumption change rate sequence is subjected to extreme point detection to generate an energy consumption mutation event marker and a corresponding event duration.

4. The production process intelligent monitoring method based on smart mine according to claim 1 is characterized in that: The cross-modal attention mechanism is used to perform correlation weighting on the vibration frequency domain energy distribution feature and the temperature and humidity gradient change feature to generate environment-related features, including: Mapping the vibration frequency domain energy distribution characteristics into a query vector set, and mapping the temperature and humidity gradient change characteristics into a key vector set; Calculate the cosine similarity between each query vector and the key vector to generate the initial attention weight matrix; Performing temperature parameter adjustment and Softmax normalization on the initial attention weight matrix to generate standardized attention weights; Performing dynamic weighted summation on the temperature and humidity gradient change features according to the standardized attention weight to generate an environment-sensitive vibration feature; The environment-sensitive vibration feature is multiplied element-by-element by the temperature and humidity gradient change feature to generate the environment-related feature.

5. The intelligent monitoring method for production process based on smart mine according to claim 1 is characterized in that: The preset abnormal pattern recognition model is used to dynamically integrate and analyze the equipment operation status characteristics, environmental correlation characteristics, and data abnormal fluctuation characteristics to generate an equipment operation risk level and a production process optimization strategy set, including: Perform feature splicing on the device operation status feature and the environment correlation feature to generate a device environment coupling feature; Calling the risk level prediction branch in the abnormal pattern recognition model to perform convolution processing on the device environment coupling feature, and outputting a device failure probability value and an environmental interference coefficient; Calling the strategy generation branch in the abnormal pattern recognition model to perform pattern analysis on the abnormal fluctuation characteristics of the data, and extracting the abnormal triggering conditions and fluctuation propagation paths; Determining the equipment operation risk level according to the weighted sum of the equipment failure probability value and the environmental interference coefficient, wherein the equipment operation risk level includes low risk, medium risk and high risk; Generate equipment parameter adjustment instructions and environmental control plans based on the matching of the abnormal trigger conditions with a preset optimization operation template library; Determine a list of affected equipment based on the wave propagation path and generate a collaborative optimization strategy for the production process; The equipment parameter adjustment instructions, environmental control scheme and production process collaborative optimization strategy are integrated into the production process optimization strategy set.

6. The production process intelligent monitoring method based on smart mine according to claim 5 is characterized in that: The triggering of corresponding alarm instructions according to the equipment operation risk level and feeding back the production process optimization strategy set to the production control terminal to adjust equipment operation parameters include: When the equipment operation risk level is low risk, an equipment status monitoring prompt message is generated and sent to the inspection terminal; When the equipment operation risk level is medium risk, an equipment maintenance warning instruction is generated and a spare parts inventory verification process is initiated; When the equipment operation risk level is high, an equipment emergency shutdown instruction and a personnel evacuation alarm signal are generated; Parsing the equipment parameter adjustment instructions in the production process optimization strategy set into a speed adjustment value, a cooling system start threshold, and a power supply frequency correction parameter for the target equipment; Convert the environmental control plan into a ventilation equipment operation mode and a dust removal system work schedule; Re-allocate the equipment load rate and task priority of each process section according to the production process collaborative optimization strategy; The speed adjustment value, cooling system start threshold, power supply frequency correction parameter, ventilation equipment operation mode, dust removal system work schedule, equipment load rate and task priority are sent to the corresponding execution agency through the production control terminal.

7. The intelligent monitoring method for production process based on smart mine according to claim 5 is characterized in that: Determining a list of affected equipment based on the wave propagation path and generating a collaborative optimization strategy for production processes includes: Traversing the production process topology graph based on the fluctuation propagation path, extracting a set of adjacent process nodes that have a signal transmission path with the abnormal fluctuation characteristics of the current data; Querying the equipment identifiers of the shared power supply system or transmission belt connection in the adjacent process node set according to the equipment dependency graph to generate a target equipment set; Obtaining historical operating parameters of each device in the target device set, and calculating a signal attenuation coefficient of the abnormal data fluctuation feature on the fluctuation propagation path; Filtering a list of affected device identifiers in the target device set whose affected degree exceeds a preset threshold according to the signal attenuation coefficient; Based on the time sequence dependency of the parsing process of the influencing device identification list, rearrange the startup order of each device in the influencing device identification list; Generate a dynamic buffer time window configuration according to the signal attenuation coefficient and the preset buffer time window parameter mapping table; The startup sequence is matched with the dynamic buffer time window configuration to generate a production process collaborative optimization strategy including the equipment execution timing and the buffer interval.

8. An intelligent production process monitoring system based on smart mines, characterized by: The intelligent production process monitoring system based on the smart mine includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the intelligent production process monitoring method based on the smart mine as described in any one of claims 1 to 7 above.

Images