Intelligent concentrator operation monitoring method based on Internet of Things

Abstract

The invention relates to the technical field of liquid removal equipment, and particularly discloses an intelligent thickener operation monitoring method based on Internet of Things, which comprises the following steps: forming multi-dimensional dynamic operation state information; an action rhythm fluctuation difference value between adjacent operation time periods is calculated, a personnel operation stability characteristic value is generated, and the consistency and efficiency level of operation behaviors of the operation personnel are evaluated; extracting the load fluctuation amplitude and start-stop frequency characteristics of the thickener, generating the running health degree characteristic value of the thickener, and identifying the potential fault risk of the thickener; and fusing the personnel operation stability characteristic value and the thickener operation health degree characteristic value into an operation state comprehensive evaluation coordinate, and carrying out comprehensive evaluation on the conditions of the operator and the thickener. Analysis is carried out from two aspects of personnel control and thickener operation, and meanwhile, fusion analysis is carried out on the two aspects, so that possible abnormities can be accurately and timely found, and the monitoring quality is improved.

Description

Technical Field

[0001] This invention relates to the field of liquid removal equipment technology, and specifically to an intelligent concentrator operation monitoring method based on the Internet of Things. Background Technology

[0002] Thickeners are suitable for dewatering concentrates and tailings in mineral processing plants and are widely used in metallurgy, chemical industry, coal, non-metallic mineral processing, environmental protection and other industries. High-efficiency thickeners are not simply sedimentation equipment, but a new type of dewatering equipment that incorporates the filtration characteristics of mud layers.

[0003] Abnormalities in the operation of the thickener mainly stem from two aspects: abnormalities in human operation and abnormalities during the thickener's operation. Traditional operation monitoring methods rely primarily on human experience, making it difficult to grasp the real-time status of personnel and the thickener at the operation site. Furthermore, monitoring and analysis are subject to lag, and it is difficult to perform compatible analysis of information from both human operation and thickener operation, resulting in room for improvement in monitoring accuracy. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent concentrator operation monitoring method based on the Internet of Things to solve the problems mentioned above.

[0005] The objective of this invention can be achieved through the following technical solutions: A smart concentrator operation monitoring method based on the Internet of Things includes: Real-time collection of operator behavior data, condenser operating status data, and environmental parameter data to form multi-dimensional dynamic operating status information; Time series analysis is performed on the action frequency sequence in the operator behavior data to calculate the difference in action rhythm fluctuation between adjacent work periods, generate personnel operation stability characteristic values, and evaluate the consistency and efficiency level of operator operation behavior. Spatiotemporal modeling is performed on the changing trends of key parameters in the operating status data of the condenser, the characteristics of load fluctuation amplitude and start-stop frequency of the condenser are extracted, the operating health feature value of the condenser is generated, and potential failure risks of the condenser are identified. The stability characteristics of personnel operation and the health characteristics of the thickener are integrated into a comprehensive evaluation coordinate system to comprehensively assess the condition of the operators and the thickener.

[0006] Preferably, the assessment of the consistency and efficiency level of the operator's work behavior specifically includes: Collect operator movement frequency data over multiple consecutive work periods. The movement frequency data includes the number of limb movements per unit time, tool usage frequency, and movement trajectory density. By comparing the motion frequency data of two adjacent work periods, the changes in motion rhythm are identified, and information reflecting the differences in the degree of rhythm fluctuation is generated. Based on the aforementioned difference information, a rhythm change model within a time window is constructed, from which core indicators that can represent overall stability are extracted as characteristic values ​​of personnel work stability. The operator's operational stability characteristic value is compared with a preset behavioral benchmark range to determine whether the operator's operational behavior in the current task remains consistent and to assess whether the operator's operational efficiency is within the normal range.

[0007] Preferably, generating the personnel job stability feature value includes the following steps: Normalize the motion frequency data collected within adjacent work time periods to eliminate data bias caused by different task types or work intensity. Based on the normalized motion frequency data, the intensity of rhythm fluctuations between adjacent time periods is calculated, and abnormal fluctuation segments with accelerated or decelerated rhythms are identified. Within a set time window, the intensity of rhythm fluctuations is aggregated and analyzed, and the number of times the fluctuation amplitude exceeds a preset threshold within the window is counted to form a rhythm instability index. By combining the rhythm instability index with the average action frequency within the time window, a comprehensive feature value is generated to characterize the overall operational stability of the operator, which serves as the operational stability feature value for the operator.

[0008] Preferably, the identification of potential malfunction risks of the condenser specifically includes: The system acquires historical operating conditions in which at least one concentrator has failed, collects key operating parameter data of the concentrator under at least one historical operating condition, and collects historical fault data of the concentrator under at least one historical operating condition. The key operating parameters include the load variation of the concentrator and the number of start-stop cycles per unit time. Based on the time series changes of the key operating parameters, the historical operating fluctuation trend of the concentrator under at least one historical operating condition is obtained. By summarizing the consistent historical operational fluctuation trends of historical faults, at least one set of operational fluctuation trends can be obtained. Take at least one sampling point from the historical operational fluctuation trend, and take the average value of the condenser's operational health characteristic value at at least one sampling point to obtain the control value; The range of the distribution of the reference values ​​of the historical operating fluctuation trends in the set of operating fluctuation trends is used as the characteristic interval, and the historical faults that generated the set of operating fluctuation trends are paired with the characteristic interval of the set of operating fluctuation trends. Historical faults corresponding to feature intervals containing the current health status characteristics of the condenser are considered as potential fault risks of the condenser. If no feature interval contains the current health status characteristics of the condenser, then the condenser has no potential fault risks.

[0009] Preferably, the process of generating the health characteristic value of the concentrator includes the following steps: The load fluctuation amplitude index and start-stop frequency index are standardized to eliminate data differences caused by different types of concentrators and operating environments; Based on historical condenser failure data and operational performance records, dynamic weighting coefficients reflecting the importance of each indicator are set. Among them, the load fluctuation amplitude weight is used to reflect the condenser's operational stability, and the start-stop frequency weight is used to reflect the condenser's usage intensity. The two standardized indicators are multiplied by their corresponding dynamic weights and then summed to obtain a preliminary health score for the concentrator. The initial health score of the condenser is corrected by combining the current continuous running time and cumulative working time, and a condenser health feature value that can comprehensively reflect the overall operating status of the condenser is generated.

[0010] Preferably, the process of integrating the personnel's operational stability characteristic value and the concentrator's operational health characteristic value into a comprehensive operational status evaluation coordinate system includes the following steps: The stability characteristics of personnel operations and the health characteristics of the condenser operation were normalized separately. Based on the different degrees of dependence on operators and concentrators at the current stage of operation, weights are formed for the characteristic values ​​of personnel operation stability and concentrator operation health. The weighted personnel operation stability characteristic value and the thickener operation health characteristic value are sequentially combined into coordinates to form a comprehensive operation status assessment coordinate that reflects the overall operation status of the site.

[0011] Preferably, the step of correcting the initial health score of the condenser by combining the current continuous operating time and the cumulative working time of the condenser includes the following steps: Based on big data, the average normal operating life of existing thickeners is obtained as a reference value. The continuous operation of existing thickeners is analyzed, and the maximum continuous working time during which the performance of existing thickeners degrades is statistically analyzed. The average value of at least one maximum continuous working time is taken to obtain the target value. The portion of the current continuous running time that exceeds the target value is recorded as the first amplitude; if the current continuous running time does not exceed the target value, the first amplitude is 0. The portion of the cumulative working hours that exceeds the reference value is recorded as the second range; if the cumulative working hours do not exceed the reference value, the second range is 0. Divide the first amplitude by the target value to get the first ratio, divide the second amplitude by the reference value to get the second ratio, use the ratio formula to calculate the third ratio, and use the reciprocal of the third ratio as the correction coefficient. Multiply the initial health score of the condenser by the correction coefficient to obtain the characteristic value of the condenser's operational health. The proportion formula is as follows: , In this context, A represents the third proportion, B represents the first proportion, and C represents the second proportion.

[0012] Preferably, the weighting of the personnel operational stability characteristic value and the concentrator operational health characteristic value includes the following steps: From the historical operation data of the thickener, at least one historical operation phase is obtained. During the historical operation phase, any abnormal situations that occur in the thickener are obtained. If the abnormal situation is caused by the operator, it is treated as a personnel abnormal situation; otherwise, it is treated as an equipment abnormal situation. The proportion of personnel abnormalities among abnormal situations is used as the first weight, and the proportion of equipment abnormalities among abnormal situations is used as the second weight. Both the first and second weights are paired with historical operation phases. The first weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the personnel operation stability characteristic value, and the second weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the concentrator operation health characteristic value.

[0013] Preferably, the comprehensive assessment of the operator and the condenser includes the following steps: Obtain at least one historical value of the comprehensive evaluation coordinate of the operating status from the historical normal operation data; Establish a planar coordinate system, mark at least one historical value in the planar coordinate system to obtain at least one historical point, and take the smallest region in the planar coordinate system that contains all historical points as the feature region. If the overall evaluation coordinates of the operating status are contained within the characteristic area, the concentrator is operating normally; otherwise, the concentrator is operating abnormally and an early warning will be issued.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By deploying wearable sensors, video surveillance, and condenser status sensors at the operation site, real-time data on personnel behavior, condenser operation, and environmental parameters are collected. Personnel operational stability characteristic values ​​and condenser operational health characteristic values ​​are generated separately. These two values ​​are normalized and dynamically weighted and fused to form a comprehensive operational status assessment coordinate system. Furthermore, online parameter correction of the monitoring results effectively improves the scientific rigor, accuracy, and response speed of the monitoring. It possesses good adaptability and scalability, and the entire process is automated. During identification, analysis is performed from both personnel operation and condenser operation perspectives, and the two aspects are also fused for analysis. This allows for accurate and timely detection of potential anomalies, improving the quality of monitoring. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the IoT-based intelligent concentrator operation monitoring method of the present invention. Figure 2 This is a flowchart illustrating the process of evaluating the consistency and efficiency of operator behavior according to the present invention. Figure 3 This is a schematic diagram of the process for generating personnel job stability feature values ​​according to the present invention; Figure 4 This is a schematic diagram of the process for identifying potential malfunction risks of a concentrator according to the present invention; Figure 5 This is a schematic diagram of the process for generating the health characteristic values ​​of the concentrator in this invention; Figure 6 This is a schematic diagram of the process of integrating the personnel operation stability characteristic value and the concentrator operation health characteristic value into a comprehensive evaluation coordinate of the operation status according to the present invention; Figure 7 This is a schematic diagram of the process for correcting the initial health score of the condenser by combining the current continuous running time and the cumulative working time of the condenser according to the present invention; Figure 8 This is a schematic diagram illustrating the process of forming the weights of the personnel operation stability characteristic value and the concentrator operation health characteristic value according to the present invention; Figure 9 This is a schematic diagram of the process for comprehensively evaluating the situation of the operator and the concentrator according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Reference Figure 1 As shown, this invention is an intelligent concentrator operation monitoring method based on the Internet of Things, comprising: Real-time collection of operator behavior data, condenser operating status data, and environmental parameter data to form multi-dimensional dynamic operating status information; Time series analysis is performed on the action frequency sequence in the operator behavior data to calculate the difference in action rhythm fluctuation between adjacent work periods, generate personnel operation stability characteristic values, and evaluate the consistency and efficiency level of operator operation behavior. Spatiotemporal modeling is performed on the changing trends of key parameters in the operating status data of the condenser, the characteristics of load fluctuation amplitude and start-stop frequency of the condenser are extracted, the operating health feature value of the condenser is generated, and potential failure risks of the condenser are identified. The stability characteristics of personnel operation and the health characteristics of the thickener are integrated into a comprehensive evaluation coordinate system to comprehensively assess the condition of the operators and the thickener.

[0018] Traditional monitoring only monitors the operation of the condenser. In this solution, not only is the operation of the condenser monitored, but also the behavior of the personnel operating the condenser. The situations of both are identified separately and then combined for analysis, thus monitoring from multiple perspectives. This ensures the effectiveness of the monitoring because although an anomaly in one aspect may be small and negligible, the superposition of anomalies in two aspects may exceed the allowable range, which needs to be considered separately. Otherwise, it is easy to overlook minor anomalies in one aspect.

[0019] Reference Figure 2 As shown, assessing the consistency and efficiency of operator behavior specifically includes: Collect operator movement frequency data over multiple consecutive work periods. The movement frequency data includes the number of limb movements per unit time, tool usage frequency, and movement trajectory density. By comparing the motion frequency data of two adjacent work periods, the changes in motion rhythm are identified, and information reflecting the differences in the degree of rhythm fluctuation is generated. Based on the aforementioned difference information, a rhythm change model within a time window is constructed, from which core indicators that can represent overall stability are extracted as characteristic values ​​of personnel work stability. The operator's operational stability characteristic value is compared with a preset behavioral benchmark range to determine whether the operator's operational behavior in the current task remains consistent and to assess whether the operator's operational efficiency is within the normal range.

[0020] The preset behavioral benchmark range is the range of values ​​formed by the historical operation of personnel to ensure consistency. During comparison, it is determined whether the personnel's operational stability characteristic value belongs to the preset behavioral benchmark range. If yes, the operator's operation behavior in the current task is consistent; otherwise, the operator's operation behavior in the current task is not consistent. The normal range is the range of values ​​formed by the historical operation stability characteristic values ​​of personnel whose operational efficiency meets the requirements. If the operational stability characteristic value of personnel is within the normal range, their operational efficiency is qualified; otherwise, their operational efficiency is unqualified. The effectiveness of personnel operation is mainly reflected in its timeliness and stability. Abnormal personnel setting parameters will not be considered, because the abnormality of parameters will be reflected during the operation of the thickener, which will be taken into account later.

[0021] Reference Figure 3 As shown, generating personnel job stability characteristic values ​​includes the following steps: Normalize the motion frequency data collected within adjacent work time periods to eliminate data bias caused by different task types or work intensity. Based on the normalized motion frequency data, the intensity of rhythm fluctuations between adjacent time periods is calculated, and abnormal fluctuation segments with accelerated or decelerated rhythms are identified. Within a set time window, the intensity of rhythm fluctuations is aggregated and analyzed, and the number of times the fluctuation amplitude exceeds a preset threshold within the window is counted to form a rhythm instability index. By combining the rhythm instability index with the average action frequency within the time window, a comprehensive feature value is generated to characterize the overall operational stability of the operator, which serves as the operational stability feature value for the operator.

[0022] Before generating the stability feature value of personnel's work, the action frequency data collected in adjacent work time periods are first normalized. The normalization process is based on the current task type, work intensity level and environmental interference factors for weighted correction to eliminate data deviation caused by differences in working conditions and ensure that the evaluation results under different task scenarios are comparable. Based on the normalized motion frequency data, the intensity of rhythm fluctuation between adjacent time periods is calculated, and abnormal fluctuation segments with significantly accelerated or slowed rhythm are identified. These abnormal fluctuation segments are combined with the characteristics of the control phase for contextual analysis to help determine whether the operator is fatigued, distracted, or has non-standardized operating behavior. Within a set time window, the intensity of rhythm fluctuations is aggregated and statistically analyzed. The number of times the fluctuation amplitude exceeds a preset threshold within the window is calculated to form a rhythm instability index. The rhythm instability index is used to quantify the irregularity and potential risks of the operator's work rhythm. By combining the rhythm instability index with the average action frequency within the time window, a comprehensive feature value is generated through a multi-dimensional weighted fusion algorithm to characterize the overall operational stability of the operator, which serves as the final operational stability feature value.

[0023] Reference Figure 4 As shown, identifying potential malfunction risks of the thiocyanate specifically includes: The system acquires historical operating conditions in which at least one concentrator has failed, collects key operating parameter data of the concentrator under at least one historical operating condition, and collects historical fault data of the concentrator under at least one historical operating condition. The key operating parameters include the load variation of the concentrator and the number of start-stop cycles per unit time. Based on the time series changes of the key operating parameters, the historical operating fluctuation trend of the concentrator under at least one historical operating condition is obtained. By summarizing the consistent historical operational fluctuation trends of historical faults, at least one set of operational fluctuation trends can be obtained. Take at least one sampling point from the historical operational fluctuation trend, and take the average value of the condenser's operational health characteristic value at at least one sampling point to obtain the control value; The range of the distribution of the reference values ​​of the historical operating fluctuation trends in the set of operating fluctuation trends is used as the characteristic interval, and the historical faults that generated the set of operating fluctuation trends are paired with the characteristic interval of the set of operating fluctuation trends. Historical faults corresponding to feature intervals containing the current health status characteristics of the condenser are considered as potential fault risks of the condenser. If no feature interval contains the current health status characteristics of the condenser, then the condenser has no potential fault risks.

[0024] When performing fault identification, historical fault data is volatile and is a range rather than a single value. Therefore, in order to form a judgment interval corresponding to historical faults, it is necessary to sample the trend in historical faults to obtain the feature interval corresponding to historical faults. The feature interval can then be used for fault identification.

[0025] Reference Figure 5 As shown, generating the health characteristic value of the condenser includes the following steps: Collect key operating parameter data of the thickener in multiple continuous operating cycles, and statistically analyze the load change amplitude and the number of start-stop times per unit time from the key operating parameter data within the set analysis window. Standardize the load fluctuation amplitude index and start-stop frequency index to eliminate data differences caused by different thickener types and operating environments. Based on historical condenser failure data and operational performance records, dynamic weighting coefficients reflecting the importance of each indicator are set. Among them, the load fluctuation amplitude weight is used to reflect the condenser's operational stability, and the start-stop frequency weight is used to reflect the condenser's usage intensity. The two standardized indicators are multiplied by their corresponding dynamic weights and then summed to obtain a preliminary health score for the concentrator. The initial health score of the condenser is corrected by combining the current continuous running time and cumulative working time, and a condenser health feature value that can comprehensively reflect the overall operating status of the condenser is generated.

[0026] An increase in the overall usage time of the condenser will have a slight impact on its operation, specifically a decrease in the condenser's operational health characteristic value. This applies to the condenser's existing usage. Continuous usage time refers to the uninterrupted working time after the condenser starts operating, which applies to the current usage. When its continuous operating time increases, the condenser's operational health characteristic value will decrease. However, these decreases are normal factors and will not cause malfunctions. Nevertheless, the preliminary condenser health score calculated based on these factors includes these effects. Therefore, the preliminary condenser health score needs to be corrected to eliminate these effects, which will be addressed in subsequent steps.

[0027] Reference Figure 6 As shown, the process of integrating personnel operational stability characteristics with concentrator operational health characteristics into a comprehensive operational status evaluation coordinate system includes the following steps: The stability characteristics of personnel operations and the health characteristics of the condenser operation were normalized separately. Based on the different degrees of dependence on operators and concentrators at the current stage of operation, weights are formed for the characteristic values ​​of personnel operation stability and concentrator operation health. The weighted personnel operation stability characteristic value and the thickener operation health characteristic value are sequentially combined into coordinates to form a comprehensive operation status assessment coordinate that reflects the overall operation status of the site.

[0028] Since the stability characteristic value of personnel operation and the health characteristic value of the concentrator operation are obtained from different physical quantities, they cannot be directly combined to form coordinates because the coordinates are not generated in the same dimension. Therefore, it is necessary to form corresponding weights so that after multiplying with the corresponding weights, they can be in the same dimension, eliminating the influence of different physical quantities, and thus combining them to generate coordinates.

[0029] Reference Figure 7 As shown, the steps to correct the initial health score of the condenser by combining its current continuous operating time and cumulative working time include: Based on big data, the average normal operating life of existing thickeners is obtained as a reference value. The continuous operation of existing thickeners is analyzed, and the maximum continuous working time during which the performance of existing thickeners degrades is statistically analyzed. The average value of at least one maximum continuous working time is taken to obtain the target value. The portion of the current continuous running time that exceeds the target value is recorded as the first amplitude; if the current continuous running time does not exceed the target value, the first amplitude is 0. The portion of the cumulative working hours that exceeds the reference value is recorded as the second range; if the cumulative working hours do not exceed the reference value, the second range is 0. Divide the first amplitude by the target value to get the first ratio, divide the second amplitude by the reference value to get the second ratio, use the ratio formula to calculate the third ratio, and use the reciprocal of the third ratio as the correction coefficient. Multiply the initial health score of the condenser by the correction coefficient to obtain the characteristic value of the condenser's operational health. The proportion formula is as follows: , In this context, A represents the third proportion, B represents the first proportion, and C represents the second proportion.

[0030] If the current continuous running time does not exceed the target value and the cumulative working time does not exceed the reference value, then A equals 1, meaning no correction is needed, which is consistent with common sense. However, if the current continuous running time exceeds the target value and the cumulative working time exceeds the reference value, the greater the excess, the greater the performance degradation of the condenser. Therefore, the preliminary condenser health score generated under this condition is less than the condenser operating health characteristic value under normal conditions. There is a proportional coefficient between the two. If the proportion of the current continuous running time exceeding the target value is B, then its degradation contribution is 1-B. Similarly, if the proportion of the cumulative working time exceeding the reference value is C, then its degradation contribution is 1-C. The sum of the two effects is 1-B multiplied by 1-C. That is, the coefficient for the condenser operating health characteristic value to decay to the preliminary condenser health score is A. Therefore, in order to calculate the condenser operating health characteristic value, the correction coefficient is set to the reciprocal of the third proportion.

[0031] Reference Figure 8 As shown, the weighting of the personnel operational stability characteristic value and the concentrator operational health characteristic value includes the following steps: From the historical operation data of the thickener, at least one historical operation phase is obtained. During the historical operation phase, any abnormal situations that occur in the thickener are obtained. If the abnormal situation is caused by the operator, it is treated as a personnel abnormal situation; otherwise, it is treated as an equipment abnormal situation. The proportion of personnel abnormalities among abnormal situations is used as the first weight, and the proportion of equipment abnormalities among abnormal situations is used as the second weight. Both the first and second weights are paired with historical operation phases. The first weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the personnel operation stability characteristic value, and the second weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the concentrator operation health characteristic value.

[0032] The weights of the personnel operation stability characteristic value and the thickener operation health characteristic value are related to the degree of the thickener's dependence on the two. In order to characterize the degree of dependence, the causes of abnormalities are classified, and the degree of the thickener's dependence on the two is determined according to the classification ratio.

[0033] Reference Figure 9 As shown, a comprehensive assessment of the operator and the condenser's condition includes the following steps: Obtain at least one historical value of the comprehensive evaluation coordinate of the operating status from the historical normal operation data; Establish a planar coordinate system, mark at least one historical value in the planar coordinate system to obtain at least one historical point, and take the smallest region in the planar coordinate system that contains all historical points as the feature region. If the overall evaluation coordinates of the operating status are contained within the characteristic area, the concentrator is operating normally; otherwise, the concentrator is operating abnormally and an early warning will be issued.

[0034] The comprehensive evaluation coordinates of operational status are coordinates, not numerical values. Therefore, they cannot be evaluated by comparing their size with a range. However, since the comprehensive evaluation coordinates of operational status are a set of points, the distribution range of the comprehensive evaluation coordinates of operational status can be generated based on historical data. For example, if there are several historical points, the area formed by connecting the outermost few historical points can be used as the feature area. The feature area can contain all historical points, and it is also the smallest area that can contain all historical points. Therefore, the anomalies of the comprehensive evaluation coordinates of operational status can be determined by using the feature area.

[0035] Furthermore, this solution also proposes a storage medium on which a computer-readable program is stored. When the computer-readable program is invoked, the above-mentioned IoT-based intelligent concentrator operation monitoring method is executed.

[0036] It is understandable that the storage medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid-state drive (SSD).

[0037] In summary, the advantages of this invention are as follows: By deploying wearable sensors, video surveillance, and condenser status sensors at the operating site, real-time data on personnel behavior, condenser operation, and environmental parameters are collected. Personnel operational stability characteristic values ​​and condenser operational health characteristic values ​​are generated separately. These two values ​​are normalized and dynamically weighted and fused to form a comprehensive operational status evaluation coordinate system. Furthermore, by performing online parameter correction on the monitoring results, this technical solution effectively improves the scientific rigor, accuracy, and response speed of monitoring. It possesses good adaptability and scalability, and the entire process is automated. During identification, analysis is performed from both personnel operation and condenser operation perspectives, and the two aspects are also fused for analysis. This allows for accurate and timely detection of potential anomalies, improving the quality of monitoring.

[0038] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A smart concentrator operation monitoring method based on the Internet of Things, characterized in that, include: Real-time collection of operator behavior data, condenser operating status data, and environmental parameter data to form multi-dimensional dynamic operating status information; Time series analysis is performed on the action frequency sequence in the operator behavior data to calculate the difference in action rhythm fluctuation between adjacent work periods, generate personnel operation stability characteristic values, and evaluate the consistency and efficiency level of operator operation behavior. Spatiotemporal modeling is performed on the changing trends of key parameters in the operating status data of the condenser, the characteristics of load fluctuation amplitude and start-stop frequency of the condenser are extracted, the operating health feature value of the condenser is generated, and potential failure risks of the condenser are identified. The stability characteristics of personnel operation and the health characteristics of the thickener are integrated into a comprehensive evaluation coordinate system to comprehensively assess the condition of the operators and the thickener.

2. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 1, characterized in that, The assessment of the consistency and efficiency of the operator's work behavior specifically includes: Collect operator movement frequency data over multiple consecutive work periods. The movement frequency data includes the number of limb movements per unit time, tool usage frequency, and movement trajectory density. By comparing the motion frequency data of two adjacent work periods, the changes in motion rhythm are identified, and information reflecting the differences in the degree of rhythm fluctuation is generated. Based on the aforementioned difference information, a rhythm change model within a time window is constructed, from which core indicators that can represent overall stability are extracted as characteristic values ​​of personnel work stability. The operator's operational stability characteristic value is compared with a preset behavioral benchmark range to determine whether the operator's operational behavior in the current task remains consistent and to assess whether the operator's operational efficiency is within the normal range.

3. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 2, characterized in that, The process of generating personnel job stability feature values ​​includes the following steps: Normalize the motion frequency data collected within adjacent work time periods to eliminate data bias caused by different task types or work intensity. Based on the normalized motion frequency data, the intensity of rhythm fluctuations between adjacent time periods is calculated, and abnormal fluctuation segments with accelerated or decelerated rhythms are identified. Within a set time window, the intensity of rhythm fluctuations is aggregated and analyzed, and the number of times the fluctuation amplitude exceeds a preset threshold within the window is counted to form a rhythm instability index. By combining the rhythm instability index with the average action frequency within the time window, a comprehensive feature value is generated to characterize the overall operational stability of the operator, which serves as the operational stability feature value for the operator.

4. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 3, characterized in that, The identification of potential malfunction risks of the thiocyanate specifically includes: The system acquires historical operating conditions in which at least one concentrator has failed, collects key operating parameter data of the concentrator under at least one historical operating condition, and collects historical fault data of the concentrator under at least one historical operating condition. The key operating parameters include the load variation of the concentrator and the number of start-stop cycles per unit time. Based on the time series changes of the key operating parameters, the historical operating fluctuation trend of the concentrator under at least one historical operating condition is obtained. By summarizing the consistent historical operational fluctuation trends of historical faults, at least one set of operational fluctuation trends can be obtained. Take at least one sampling point from the historical operational fluctuation trend, and take the average value of the condenser's operational health characteristic value at at least one sampling point to obtain the control value; The range of the distribution of the reference values ​​of the historical operating fluctuation trends in the set of operating fluctuation trends is used as the characteristic interval, and the historical faults that generated the set of operating fluctuation trends are paired with the characteristic interval of the set of operating fluctuation trends. Historical faults corresponding to feature intervals containing the current health status characteristics of the condenser are considered as potential fault risks of the condenser. If no feature interval contains the current health status characteristics of the condenser, then the condenser has no potential fault risks.

5. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 4, characterized in that, The process of generating the health characteristic value of the concentrator includes the following steps: The load fluctuation amplitude index and start-stop frequency index are standardized to eliminate data differences caused by different types of concentrators and operating environments; Based on historical condenser failure data and operational performance records, dynamic weighting coefficients reflecting the importance of each indicator are set. Among them, the load fluctuation amplitude weight is used to reflect the condenser's operational stability, and the start-stop frequency weight is used to reflect the condenser's usage intensity. The two standardized indicators are multiplied by their corresponding dynamic weights and then summed to obtain a preliminary health score for the concentrator. The initial health score of the condenser is corrected by combining the current continuous running time and cumulative working time, and a condenser health feature value that can comprehensively reflect the overall operating status of the condenser is generated.

6. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 5, characterized in that, The process of integrating personnel operational stability characteristics and concentrator operational health characteristics into a comprehensive operational status evaluation coordinate system includes the following steps: The stability characteristics of personnel operations and the health characteristics of the condenser operation were normalized separately. Based on the different degrees of dependence on operators and concentrators at the current stage of operation, weights are formed for the characteristic values ​​of personnel operation stability and concentrator operation health. The weighted personnel operation stability characteristic value and the thickener operation health characteristic value are sequentially combined into coordinates to form a comprehensive operation status assessment coordinate that reflects the overall operation status of the site.

7. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 6, characterized in that, The process of revising the initial health score of the condenser by combining its current continuous operating time and cumulative working time includes the following steps: Based on big data, the average normal operating life of existing thickeners is obtained as a reference value. The continuous operation of existing thickeners is analyzed, and the maximum continuous working time during which the performance of existing thickeners degrades is statistically analyzed. The average value of at least one maximum continuous working time is taken to obtain the target value. The portion of the current continuous running time that exceeds the target value is recorded as the first amplitude; if the current continuous running time does not exceed the target value, the first amplitude is 0. The portion of the cumulative working hours that exceeds the reference value is recorded as the second range; if the cumulative working hours do not exceed the reference value, the second range is 0. Divide the first amplitude by the target value to get the first ratio, divide the second amplitude by the reference value to get the second ratio, use the ratio formula to calculate the third ratio, and use the reciprocal of the third ratio as the correction coefficient. Multiply the initial health score of the condenser by the correction coefficient to obtain the characteristic value of the condenser's operational health. The proportion formula is as follows: ， In this context, A represents the third proportion, B represents the first proportion, and C represents the second proportion.

8. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 7, characterized in that, The weighting of the personnel's operational stability characteristic value and the concentrator's operational health characteristic value includes the following steps: From the historical operation data of the thickener, at least one historical operation phase is obtained. During the historical operation phase, any abnormal situations that occur in the thickener are obtained. If the abnormal situation is caused by the operator, it is treated as a personnel abnormal situation; otherwise, it is treated as an equipment abnormal situation. The proportion of personnel abnormalities among abnormal situations is used as the first weight, and the proportion of equipment abnormalities among abnormal situations is used as the second weight. Both the first and second weights are paired with historical operation phases. The first weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the personnel operation stability characteristic value, and the second weight corresponding to the historical operating stage with the smallest difference from the current operating stage will be used as the weight of the concentrator operation health characteristic value.

9. The method for monitoring the operation of an intelligent concentrator based on the Internet of Things according to claim 8, characterized in that, The comprehensive assessment of the operator and the condenser includes the following steps: Obtain at least one historical value of the comprehensive evaluation coordinate of the operating status from the historical normal operation data; Establish a planar coordinate system, mark at least one historical value in the planar coordinate system to obtain at least one historical point, and take the smallest region in the planar coordinate system that contains all historical points as the feature region. If the overall evaluation coordinates of the operating status are contained within the characteristic area, the concentrator is operating normally; otherwise, the concentrator is operating abnormally and an early warning will be issued.

Images