Fault identification method and system based on operating condition of continuous system in open-pit mine

Abstract

Disclosed in the present invention are a fault identification method and system based on the operating condition of a continuous system in an open-pit mine. The method comprises: establishing a simulation model for a continuous system in an open-pit mine, and monitoring device data in real time; pre-processing the data, and performing potential fault identification; on the basis of a system pressure change rate and an adaptive adjustment mechanism of the continuous system in the open-pit mine, optimizing fault identification output; and designing a fault response and real-time adjustment mechanism to prevent fault occurrence. The fault identification method and system based on the operating condition of a continuous system in an open-pit mine provided in the present invention improve the speed and accuracy of fault diagnosis, particularly the rapid processing capability for complex data relationships. A breakthrough is achieved in fault prevention, thus enabling early warning and adaptive adjustment to be implemented before faults occur. Thus, the stability and safety of continuous systems in open-pit mines are significantly improved, and a more efficient technical solution is provided for operation management of modern open-pit mines.

Description

A fault identification method and system based on the operation of a continuous system of an open-pit mine TECHNICAL FIELD

[0001] The present application relates to the technical field, in particular to a fault identification method and system based on the operation of a continuous system of an open-pit mine. BACKGROUND

[0002] The operation of a continuous system of an open-pit mine is a highly complex and integrated process, involving the coordinated work of multiple devices and technologies. These devices are often in harsh environments and need to be continuously operated for a long time, so device failures occur frequently, affecting production efficiency and safety. Existing fault diagnosis methods often rely on traditional physical sensor data and post-fault analysis, which not only has a long response time, but also is difficult to handle complex data relationships, and is difficult to meet the needs of real-time preventive maintenance. The fault diagnosis system of the prior art often ignores the influence of environmental factors on the device, and lacks targeted optimization in data preprocessing and fault identification algorithm, which limits the fault handling capacity and stability of the system. SUMMARY

[0003] In view of the above problems, the present application is proposed.

[0004] Therefore, the technical problem solved by the present application is to ensure the comprehensiveness and real-time nature of device data by establishing a simulation model and performing real-time monitoring. Through highly specialized feature extraction functions and adaptive adjustment mechanisms, fault identification is more accurate and efficient. The fault response and real-time adjustment mechanism not only quickly reacts to solve problems, but also preventsively adjusts system parameters before potential faults occur, thereby avoiding the occurrence of faults.

[0005] To solve the above technical problems, the present application provides the following technical scheme: a fault identification method based on the operation of a continuous system of an open-pit mine, comprising: establishing a simulation model of a continuous system of an open-pit mine, and monitoring device data in real time.

[0006] Preprocess the data and identify potential faults.

[0007] According to the adaptive adjustment mechanism of the system pressure change rate and the continuous system of the open-pit mine, optimize the fault identification output.

[0008] Design a fault response and real-time adjustment mechanism to avoid faults.

[0009] As a preferred scheme of the fault identification method based on the operation of a continuous system of an open-pit mine, the establishment of a simulation model of a continuous system of an open-pit mine and real-time monitoring of device data includes creating a system simulation model that comprehensively simulates the operation of an open-pit mine, including all key devices and their interactions.

[0010] Simulation operations include device operation, environmental impact, and failure scenarios.

[0011] Device operation simulates the operation of various devices under normal, high load, and potential failure conditions.

[0012] Environmental impact simulates the impact of different environmental conditions on device performance.

[0013] Failure scenarios are intentionally designed failure scenario simulations, including mechanical failures, electrical failures, and operational errors to test the system.

[0014] Real-time monitoring of device data includes device status data, operating parameters, and environmental monitoring data.

[0015] Device status data includes device vibration data, temperature readings, current and voltage.

[0016] Operating parameters include device operating speed, load size, and operating frequency.

[0017] Environmental monitoring data includes temperature, humidity, and wind speed.

[0018] As a preferred scheme of the fault identification method based on the operation of the continuous system of the open-pit mine, the data preprocessing includes data cleaning, data standardization and noise filtering.

[0019] Data cleaning targets invalid, erroneous and incomplete data records. For incomplete data points, the average of the previous and subsequent data points is used to fill in, and for invalid and erroneous data points, they are directly removed.

[0020] Data standardization eliminates the influence of different dimensions and orders of magnitude, so that the data is in the same order of magnitude, expressed as:

[0021] Where X represents the original data, μ represents the average value of the data, σ represents the standard deviation of the data, and represents the fluctuation of the data.

[0022] Low-pass filter is used to remove noise in the data and improve data quality.

[0023] As a preferred scheme of the fault identification method based on the operation of the continuous system of the open-pit mine, the potential fault identification includes, due to the complexity of the equipment in the open-pit mine system, a single data source may not be sufficient to fully predict the fault, a highly specialized feature extraction function is established by integrating the features of multiple data, combined with vibration signal analysis, temperature change trend, rotational speed periodicity and current abnormal index extraction to fully reflect the running state of the equipment, the feature extraction formula is expressed as:

[0024] where T represents time, ω represents an adjustment coefficient, V(t) represents equipment vibration data, α represents an equipment vibration index parameter, T(t) represents equipment temperature data, β represents an equipment temperature adjustment coefficient, λ represents an equipment speed adjustment coefficient, S(t) represents equipment speed data, μ represents a current adjustment coefficient, C(t) represents current data, and v represents a current index parameter.

[0025] The occurrence of faults is not only related to the intrinsic characteristics of the system, but also influenced by external environment and operating conditions. By dynamic threshold determination, the threshold is adjusted according to real-time environmental and operating data to respond to changes in the state of the system, which is expressed as:

[0026] where ζ represents a baseline threshold, which is set according to historical operating data of the system. κ represents an adjustment factor, which adjusts the threshold according to the deviation of the characteristic value. ξ represents an exponential adjustment parameter.

[0027] The results of the comprehensive feature extraction and dynamic threshold adjustment are obtained as follows:

[0028] where Φ(x(t)) represents the characteristic value extracted from real-time data, and Θ(Φ) represents the threshold dynamically determined according to the current characteristics.

[0029] As a preferred scheme of the fault identification method based on the continuous system operation of the open-pit mine according to the present application, the system pressure change rate and the adaptive adjustment mechanism of the open-pit continuous system include that in the open-pit continuous system, heavy mechanical equipment such as crushers and conveyors bear huge mechanical pressure, and the pressure state of the system is not only affected by the operating conditions of the equipment, but also changes due to environmental factors and external factors of material accumulation. Rapid changes in system pressure often indicate abnormal equipment load or potential failure.

[0030] Abnormal changes in system pressure can trigger an adaptive adjustment mechanism to automatically adjust the speed of the conveyor belt and the working intensity of the crusher to reduce the wear of the equipment and prevent potential failure.

[0031] First, the system pressure change rate is calculated, which is expressed as:

[0032] where ΔP(t) represents the pressure difference in a specified time period, and Δt represents the time interval.

[0033] The system pressure change rate is used in the adaptive adjustment mechanism to help the system automatically adjust the parameters of fault identification according to the current operating state. The adaptive adjustment function is expressed as:

[0034] where μ RCSPMean of historical system pressure rate of change, used for baseline adjustment. σ RCSP Standard deviation of historical system pressure rate of change, used for normalization and sensitivity adjustment. ω represents a weight factor, used to adjust the sensitivity of adaptive adjustment.

[0035] A(RCSP) is introduced as an adjustment factor into the fault identification formula, dynamically adjusting the sensitivity of fault identification, optimizing the fault identification output, and finally integrating the completed fault identification formula as:

[0036] Where Θ(Φ) represents the original fault identification threshold based on feature extraction value Φ(x(t)), and the threshold is adjusted according to the real-time state of the system by multiplying the adaptive adjustment factor A(RCSP(t)).

[0037] As a preferred scheme of the fault identification method based on the continuous system operation of the open-pit mine according to the present application, wherein the fault response and real-time adjustment mechanism includes, first of all, the accuracy of the fault identification output result needs to be comprehensively evaluated, based on the normal operation parameters of the system and the expected result model defined by the known fault theory, represented as:

[0038] Where a i represents the intensity of the influence of different fault types on the system; b i represents the speed of the influence of different fault types on the system; c represents the baseline offset, representing the normal operation level of the system in the fault-free state.

[0039] Compare the actual output of F(t) with the theoretical value of Θ(t), evaluate the performance and deviation of F(t) in actual situation, represented as:

[0040] Where T represents the evaluation time window, and D(t) represents the overall deviation between F(t) and Θ(t), and the smaller D(t) is, the more accurate F(t) is.

[0041] Convert the deviation into an accuracy score, map the deviation value to [0, 1] through accuracy evaluation, represented as:

[0042] Where D max represents the theoretical maximum deviation value.

[0043] As a preferred scheme of the fault identification method based on the continuous system operation of the open-pit mine according to the present application, wherein the fault response and real-time adjustment mechanism further includes that when A(t) is lower than 0.5, it is considered that the fault identification accuracy is insufficient.

[0044] Initiate a comprehensive system review, including hardware checks and software audits, to determine if there are undetected faults and data collection issues.

[0045] Re-evaluate the data set used to train the model, checking data integrity, accuracy, and timeliness. Clean outliers and noise from the data to ensure the quality of the data can support accurate fault prediction.

[0046] Adjust the parameters of the fault identification formula by increasing the number of fault scenario simulations to increase the number of fault case samples and increase data sampling in underperforming areas. Recalculate for new data.

[0047] When A(t) is between 0.5 and 0.75, the fault identification accuracy performs well, initiate data re-collection and model re-training procedures, collect more data from areas with inaccurate predictions, and recalculate for new data.

[0048] When A(t) is higher than 0.75, the model performs well.

[0049] A fault identification system based on the continuous operation of an open-pit mine system, characterized by comprising,

[0050] Data acquisition module, establish an open-pit mine continuous system simulation model, real-time monitoring equipment data.

[0051] Preprocessing module, pre-process data, and identify potential faults.

[0052] Fault identification module, according to the system pressure change rate and the adaptive adjustment mechanism of the open-pit mine continuous system, optimize the fault identification output.

[0053] Fault response module, design fault response and real-time adjustment mechanism to avoid faults.

[0054] A computer device comprising a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method as described above.

[0055] A computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method as described above.

[0056] The beneficial effects of the present application: improve the speed and accuracy of fault diagnosis, especially the rapid processing ability of complex data relationship. Breakthrough in fault prevention, can implement early warning and adaptive adjustment before fault occurs. Significantly improve the stability and safety of open-pit mine continuous system, provide a more efficient technical solution for the operation and management of modern open-pit mine. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings. Among them:

[0058] Fig. 1 is a whole flow chart of a method and system provided by the first embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are only some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should be within the protection scope of the present application.

[0060] Embodiment 1

[0061] Referring to Fig. 1, a method is provided in an embodiment of the present application, comprising:

[0062] S1: Establishing an open-pit mine continuous system simulation model to monitor equipment data in real time.

[0063] Establishing an open-pit mine continuous system simulation model to monitor equipment data in real time includes creating a system simulation model that comprehensively simulates the operation of an open-pit mine, including all key equipment and their interactions.

[0064] The simulation operation includes equipment operation, environmental impact and failure scenarios.

[0065] The equipment operation simulates the operation of various equipment under normal, high load and potential failure conditions.

[0066] The environmental impact simulates the impact of different environmental conditions on equipment performance.

[0067] The failure scenario is a deliberately designed failure scenario simulation, including mechanical failure, electrical failure and operation error to test the system.

[0068] The real-time monitoring of equipment data includes equipment status data, operation parameters and environmental monitoring data.

[0069] The equipment status data includes equipment vibration data, temperature readings, current and voltage.

[0070] The operation parameters include equipment running speed, load size and operation frequency.

[0071] The environmental monitoring data includes temperature, humidity and wind speed.

[0072] S2: Preprocess the data and identify potential faults.

[0073] The preprocessing includes data cleaning, data standardization and noise filtering.

[0074] The data cleaning targets invalid, erroneous and incomplete data records. For incomplete data points, the average of the previous and subsequent data points is used to fill in. For invalid and erroneous data points, they are directly removed.

[0075] Data standardization eliminates the influence of different dimensions and magnitudes, so that the data is in the same order of magnitude, expressed as:

[0076] Where X represents the original data, μ represents the average value of the data, σ represents the standard deviation of the data, and represents the fluctuation of the data.

[0077] A low-pass filter is used to remove noise in the data and improve data quality.

[0078] In the open-pit mine system, due to the complexity of the equipment, a single data source may not be sufficient to fully predict the fault. By integrating the features of multiple data sources, a highly specialized feature extraction function is established, combined with vibration signal analysis, temperature change trend, rotational speed periodicity and current anomaly index extraction to fully reflect the running state of the equipment. The feature extraction formula is expressed as:

[0079] Where T represents time, ω represents adjustment coefficient, V(t) represents equipment vibration data, α represents equipment vibration index parameter, T(t) represents equipment temperature data, β represents equipment temperature adjustment coefficient, λ represents equipment speed adjustment coefficient, S(t) represents equipment speed data, μ represents current adjustment coefficient, C(t) represents current data, and ν represents current index parameter.

[0080] It should be noted that the design of the feature extraction formula not only enhances the pertinence and accuracy of the fault identification model, but also significantly improves the practicality and reliability of the model by incorporating specific operating parameters into the calculation. By combining multiple data sources and performing complex mathematical operations for feature fusion, this fault identification method can consider multiple aspects of the equipment, detect potential faults early, and provide a scientific basis and powerful tool for open-pit mine maintenance.

[0081] The occurrence of faults is not only related to the intrinsic characteristics of the system, but also influenced by external environment and operating conditions. By dynamically determining the threshold, the threshold is adjusted according to real-time environmental and operating data to respond to changes in system state, expressed as:

[0082] where ζ represents the baseline threshold, which is set according to the system historical running data. κ represents the adjustment factor, which adjusts the threshold according to the deviation of the feature value. ξ represents the exponential adjustment parameter.

[0083] The result of the comprehensive feature extraction and dynamic threshold adjustment is obtained as the fault recognition formula:

[0084] where Φ(x(t)) represents the feature value extracted from real-time data, and Θ(Φ) represents the threshold dynamically determined according to the current feature.

[0085] S3: According to the adaptive adjustment mechanism of the system pressure change rate and the open-pit continuous system, the fault recognition output is optimized.

[0086] In the open-pit continuous system, heavy mechanical equipment such as crushers and conveyors bear huge mechanical pressure. The pressure state of the system is not only affected by the running conditions of the equipment, but also changes due to environmental factors and external factors such as material accumulation. Rapid changes in system pressure often indicate abnormal equipment load or potential failure.

[0087] Abnormal changes in system pressure can trigger an adaptive adjustment mechanism to automatically adjust the speed of the conveyor belt and the working intensity of the crusher, thereby reducing the wear and tear on the equipment and preventing potential failures.

[0088] It should be noted that abnormal changes in system pressure can trigger an adaptive adjustment mechanism, such as automatically adjusting the speed of the conveyor belt or the working intensity of the crusher, to reduce wear and tear on the equipment and prevent potential failures.

[0089] By monitoring the RCSP in real time, the system can adjust the maintenance plan in advance and prioritize the processing of equipment parts that may have problems due to abnormal pressure.

[0090] First, calculate the system pressure change rate, which is represented as:

[0091] where ΔP(t) represents the pressure difference in a specified time period, and Δt represents the time interval.

[0092] This system pressure change rate is used in the adaptive adjustment mechanism to help the system automatically adjust the parameters of fault recognition according to the current running state. The adaptive adjustment function is represented as:

[0093] where μ RCSP represents the mean of the historical system pressure change rate, which is used for baseline adjustment. σ RCSP represents the standard deviation of the historical system pressure change rate, which is used for normalization and sensitivity adjustment. ω represents the weight factor, which is used to adjust the sensitivity of adaptive adjustment.

[0094] It should be noted that the introduction of RCSP as a parameter for optimizing fault identification can make the system more sensitive to pressure-related faults, while dynamically adjusting the fault identification mechanism to improve the accuracy of diagnosis. This adaptive optimization method can ensure that the open-pit system maintains optimal operating efficiency under different operating conditions, responds to potential fault risks in a timely manner, and minimizes unplanned downtime.

[0095] A(RCSP) is introduced as a regulating factor into the fault identification formula, dynamically adjusting the sensitivity of fault identification, optimizing fault identification output, and finally integrating the completed fault identification formula as:

[0096] where Θ(Φ) represents the original fault identification threshold based on the feature extraction value Φ(x(t)), and the threshold is adjusted according to the real-time state of the system by multiplying the adaptive regulating factor A(RCSP(t)).

[0097] S4: Design a fault response and real-time adjustment mechanism to avoid faults.

[0098] First, the accuracy of the fault identification output needs to be evaluated comprehensively. Based on the normal operating parameters of the system and the expected result model defined by the known fault theory, it is represented as:

[0099] where a i represents the intensity of the impact of different fault types on the system; b i represents the speed of the impact of different fault types on the system; and c represents the baseline offset, representing the normal operating level of the system in the absence of faults.

[0100] Compare the actual output of F(t) with the theoretical value of Θ(t) to evaluate the performance and deviation of F(t) in actual situations, represented as:

[0101] where T represents the evaluation time window, and D(t) represents the overall deviation between F(t) and Θ(t). The smaller D(t) is, the more accurate F(t) is.

[0102] Convert the deviation into an accuracy score by mapping the deviation value to [0, 1] through accuracy evaluation, represented as:

[0103] where D max represents the theoretical maximum deviation value.

[0104] When A(t) is less than 0.5, it is considered that the fault identification accuracy is insufficient.

[0105] Initiate a comprehensive system review, including hardware checks and software audits, to determine if there are undetected faults and data collection issues.

[0106] Re-evaluate the data set used to train the model, checking data integrity, accuracy, and timeliness. Clean outliers and noise from the data to ensure the quality of the data can support accurate fault prediction.

[0107] Adjust the parameters of the fault identification formula, increase the number of fault scenario simulations to increase the number of fault case samples, and increase the data sampling of underperforming areas, and recalculate for new data.

[0108] When A(t) is between 0.5 and 0.75, the fault identification accuracy performs well, initiate data re-collection and model re-training procedures, collect more data from areas with inaccurate predictions, and recalculate for new data.

[0109] When A(t) is higher than 0.75, the model performs well.

[0110] In the above embodiments, a fault identification system based on the continuous operation of the open-pit mine system is also included, specifically:

[0111] Data acquisition module, establish an open-pit mine continuous system simulation model, real-time monitoring of equipment data.

[0112] Preprocessing module, pre-process the data, and identify potential faults.

[0113] Fault identification module, according to the system pressure change rate and the adaptive adjustment mechanism of the open-pit mine continuous system, optimize the fault identification output.

[0114] Fault response module, design fault response and real-time adjustment mechanism to avoid faults.

[0115] The computer device can be a server. The computer device comprises a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store data cluster data of a power monitoring system. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a method.

[0116] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of each method can be included. Any reference to memory, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0117] Embodiment 2

[0118] In one embodiment of the present application, a fault identification method and system based on the operation of a continuous system of an open-pit mine are provided. In order to verify the beneficial effects of the present application, a simulation comparison experiment is carried out for scientific demonstration.

[0119] An experiment of the fault identification method was carried out in an open-pit mine. First, a detailed simulation model of the continuous system of the open-pit mine was established, including all key devices and their interaction, and various normal, high-load and potential fault states were simulated. Using sensor and data acquisition technology, the device state, operation parameter and environmental data were monitored in real time. These data include data collected from device vibration sensors, temperature sensors and current and voltage monitors.

[0120] The collected data was normalized, missing value filled, and low-pass filtered to clean and standardize, reducing noise and inconsistencies. Periodic vibration, temperature, speed, and current anomaly data were integrated to establish feature extraction functions that could reflect the running state of the equipment and identify potential faults.

[0121] Using feature extraction and dynamic threshold adjustment formulas, potential faults were identified, and an adaptive adjustment mechanism was implemented based on system pressure rate of change and real-time environmental data. The effectiveness of the optimization method was evaluated by comparing the fault response of the experimental model with that of the prior art. The experimental results are shown in Table 1.

[0122] Table 1 Experimental results

[0123] The table shows that the invention in the example has significantly improved in response time and fault identification rate. In terms of equipment vibration monitoring, the invention has shortened the response time from 10 seconds to 2 seconds, and the fault identification rate has increased from 80% to 95%. This significant improvement is mainly due to the application of real-time monitoring technology and highly specialized feature extraction formulas, which make fault identification more rapid and accurate.

[0124] In terms of temperature change monitoring, the response time has been significantly reduced, and the fault identification rate has increased by 20 percentage points. In addition, the invention in the example significantly increases the frequency of preventive adjustments through the adaptive adjustment mechanism, thereby achieving timely adjustment before the occurrence of faults.

[0125] By comparing with the prior art, the invention not only improves the speed and accuracy of fault diagnosis, but also significantly improves the stability and safety of the system through the real-time adjustment mechanism. For example, the preventive adjustment of the prior art in current anomalies is only once a year, while the invention can be performed once a month, which is crucial for preventing faults caused by current anomalies.

[0126] Overall, the application of the invention significantly improves the fault diagnosis capability of the continuous system of the open-pit mine, reduces the system downtime, and improves the overall operation efficiency. These advantages provide a more reliable and efficient fault diagnosis method for the continuous system operation of the open-pit mine, proving the innovation and superiority of the invention content in practical application.

[0127] It should be noted that the above examples are only used to illustrate the technical solutions of the invention and are not limiting. Although the invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the invention can be modified or replaced equivalently without departing from the spirit and scope of the invention, which should be covered by the scope of the claims of the invention.

Claims

1. A method for failure identification based on the operation of a continuous system of an open-pit mine, characterized by, The application relates to a system and method for real-time monitoring and adaptive adjustment of a continuous open-pit mining system. The system comprises: Establishing a continuous open-pit mining system simulation model to monitor equipment data in real time; Preprocessing data and identifying potential faults; Optimizing fault identification output based on system pressure change rate and adaptive adjustment mechanism of the continuous open-pit mining system; 2. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 1, characterized in that: Designing a fault response and real-time adjustment mechanism to avoid faults. The establishment of a continuous open-pit mining system simulation model to monitor equipment data in real time includes creating a system simulation model that comprehensively simulates open-pit mining operations, including all key equipment and their interactions; Simulation operations include equipment operation, environmental impact, and fault scenarios; Equipment operation simulates the operation of various equipment under normal, high load, and potential fault conditions; Environmental impact simulates the impact of different environmental conditions on equipment performance; Fault scenarios are intentionally designed to simulate mechanical, electrical, and operational errors to test the system; Real-time monitoring of equipment data includes equipment status data, operating parameters, and environmental monitoring data; Equipment status data includes equipment vibration data, temperature readings, current, and voltage; Operating parameters include equipment operating speed, load size, and operating frequency; 3. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 2, characterized in that: Environmental monitoring data includes temperature, humidity, and wind speed. Data preprocessing includes data cleaning, data standardization, and noise filtering; Data standardization eliminates the influence of different dimensions and orders of magnitude, so that the data is in the same order of magnitude, expressed as: Invalid, erroneous, and incomplete data records are cleaned, and for incomplete data points, the average of the previous and subsequent data points is used to fill in the missing data, and for invalid and erroneous data points, they are directly removed; Where X represents the original data, mu represents the average value of the data, sigma represents the standard deviation of the data, and represents the fluctuation of the data; 4. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 3, characterized in that: The potential fault identification includes that, in the open-pit mine system, due to the complexity of the equipment, a single data source can not be sufficient to comprehensively predict the fault, a highly specialized feature extraction function is established by comprehensively multiple data characteristics, combined with vibration signal analysis, temperature change trend, speed periodicity and current abnormal index extraction to comprehensively reflect the running state of the equipment, and the feature extraction formula is expressed as: A low-pass filter is used to remove noise from the data, improving data quality. The occurrence of faults is not only related to the intrinsic characteristics of the system, but also influenced by external environment and operating conditions. By dynamic threshold determination, the threshold is adjusted according to real-time environmental and operating data to respond to changes in system state, which is expressed as: Where T represents time, omega represents the adjustment coefficient, V(t) represents equipment vibration data, alpha represents the equipment vibration index parameter, T(t) represents equipment temperature data, beta represents the equipment temperature adjustment coefficient, lambda represents the equipment speed adjustment coefficient, S(t) represents equipment speed data, mu represents the current adjustment coefficient, C(t) represents current data, and nu represents the current index parameter; The result of the comprehensive feature extraction and dynamic threshold adjustment is obtained as a fault recognition formula: Where zeta represents the baseline threshold value, which is set based on historical system operation data; kappa represents the adjustment factor, which adjusts the threshold value based on the deviation of the characteristic value; and xi represents the exponential adjustment parameter; 5. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 4, characterized in that: Where Phi(x(t)) represents the characteristic value extracted from real-time data, and Theta(Phi) represents the threshold value dynamically determined based on the current characteristics. The system pressure change rate and the adaptive adjustment mechanism of the continuous open-pit mining system include that in the continuous open-pit mining system, heavy machinery such as crushers and conveyors bear a lot of mechanical pressure, and the pressure state of the system is not only affected by the operating conditions of the equipment, but also changes due to environmental factors and external factors such as material accumulation, and rapid changes in system pressure often indicate abnormal equipment load or potential faults; The system pressure rate of change is first calculated and expressed as: And the adaptive adjustment mechanism can be triggered by abnormal changes in system pressure to automatically adjust the speed of the conveyor belt and the working intensity of the crusher to reduce the wear of the equipment and prevent potential faults; Where Delta P(t) represents the pressure difference in a specified time period, and Delta t represents the time interval. In using this system pressure rate of change for adaptive adjustment mechanism, help system according to the current operating state automatically adjust the parameters of fault identification, adaptive adjustment function is expressed as: where μ RCSP represents the mean of the historical system pressure rate of change, used for baseline adjustment; σ RCSP represents the standard deviation of the historical system pressure rate of change, used for normalization and sensitivity adjustment; ω represents a weight factor, used to adjust the sensitivity of the adaptive regulation; The A(RCSP) is introduced into the fault identification formula as an adjustment factor, the sensitivity of the fault identification is dynamically adjusted, the fault identification output is optimized, and finally the completed fault identification formula is expressed as: Wherein, Θ(Φ) represents the original fault identification threshold based on the feature extraction value Φ(x(t)), by multiplying the adaptive adjustment factor A(RCSP(t)), the threshold is adjusted according to the real-time state of the system.

6. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 5, characterized in that: The failure response and real-time adjustment mechanism includes, first of all, the comprehensive evaluation of the result accuracy of the failure identification output, based on the normal operation parameters of the system and the expected result model of the known failure definition theory, expressed as: where a i represents the strength of the impact of different failure types on the system; b i represents the speed of the impact of different failure types on the system; c represents the baseline shift, representing the normal operating level of the system in the absence of failures; Comparing the actual output of F(t) with the theoretical value of Θ(t), the performance and deviation of F(t) in actual situation are evaluated, denoted as: Wherein, T represents the evaluation time window, D(t) represents the overall deviation between F(t) and Θ(t), the smaller D(t) is, the more accurate F(t) is; Converting the bias into an accuracy score, the bias value is mapped to [0, 1] by an accuracy evaluation, denoted as: where D max represents the theoretical maximum deviation value.

7. The method for failure identification based on the operation of the continuous system of the strip mine according to claim 6, characterized in that: When A(t) is lower than 0.5, it is considered that the fault identification accuracy is insufficient; A comprehensive system review is initiated, including hardware inspection and software audit, to determine whether there are undetected faults and data collection problems; The data set used to train the model is re-evaluated to check the data integrity, accuracy and timeliness; outliers and noise in the data are cleaned up to ensure the quality of the data to support accurate fault prediction; The parameters of the fault identification formula are adjusted, the number of fault scenario simulations is increased to increase the sample size of fault cases, and the data sampling of underperforming areas is increased, and the new data is recalculated; When A(t) is between 0.5 and 0.75, the fault identification accuracy performs well, the data re-collection and model re-training program is initiated, more data is collected from the areas where the prediction is not accurate, and the new data is recalculated; A(t) is higher than 0.75, the model performs well.

8. A fault identification system based on the operation of a continuous system of an open-pit mine, which adopts the method of any one of claims 1-7, characterized in that: A data collection module is established to build a simulation model of the continuous system of the open-pit mine and monitor equipment data in real time; A preprocessing module is used to preprocess the data and identify potential faults; A fault identification module is used to optimize fault identification output according to the system pressure change rate and the adaptive adjustment mechanism of the continuous system of the open-pit mine; A fault response module is designed to design a fault response and real-time adjustment mechanism to avoid faults. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 7.

Images