Metal open-pit mine production scheduling optimization system based on multi-source data fusion

Abstract

The present application relates to the technical field of data processing, and especially relates to a metal open-pit mine production scheduling optimization system based on multi-source data fusion, comprising: a data processing module, comprising a data acquisition unit for acquiring metal open-pit mine data of a plurality of data sources; a model training module, comprising a model generation unit for model training according to the feature extraction unit to generate a genetic algorithm model; a production scheduling module connected with the model training module, comprising an analysis unit connected with the model generation unit for analyzing the metal open-pit mine data through the genetic algorithm model to output an analysis result; and an optimization module connected with the data processing module, the model training module and the production scheduling module respectively, for determining time alignment tolerance of different data sources according to a loss rate of the metal open-pit mine data. The present application improves the optimization stability of metal open-pit mine production scheduling.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a production scheduling optimization system for open-pit metal mines based on multi-source data fusion. Background Technology

[0002] In existing technologies, efficient and precise production scheduling is crucial for ensuring the rational development of resources and improving economic benefits in the production process of open-pit metal mines. With the continuous expansion of open-pit mining scale and the increasing complexity of production systems, traditional production scheduling methods based on experience or simple rules have gradually revealed many drawbacks. With the gradual application of technologies such as the Internet of Things, sensors, and big data in the mining field, open-pit metal mines can collect a large amount of production data covering equipment operation, geological conditions, environmental parameters, market demand, and other aspects. However, this multi-source data suffers from problems such as inconsistent formats, varying data quality, and fragmented information. Without effective processing, it not only fails to provide strong support for production scheduling but also increases the difficulty and complexity of data processing.

[0003] Chinese Patent Publication No. CN113222460A discloses a multi-objective scheduling optimization method for open-pit mine trucks based on a high-dimensional multi-objective evolutionary algorithm, comprising the following steps: Step 1, establishing a main index system based on the actual production scheduling of open-pit mines; Step 2, constructing a multi-objective scheduling model for metal open-pit mines with the objectives of minimizing transportation costs, shortest transportation distances, and minimum waiting times; Step 3, improving the NSGA-III algorithm to obtain an NSGA-III algorithm based on distance dominance relationships; Step 4, solving the multi-objective scheduling model for metal open-pit mines using the improved algorithm. It is evident that the aforementioned multi-objective scheduling optimization method for open-pit mine trucks based on a high-dimensional multi-objective evolutionary algorithm suffers from the problem that, due to the numerous factors involved in actual open-pit mine production scheduling, considering only transportation costs, transportation distances, and waiting times may not be comprehensive enough, leading to scheduling schemes that cannot fully meet complex production needs in practical applications. Summary of the Invention

[0004] To address this issue, the present invention provides a metal open-pit mine production scheduling optimization system based on multi-source data fusion, which overcomes the problem in the prior art that the scheduling scheme cannot fully meet the complex production needs in actual applications because the actual open-pit mine production scheduling involves many factors, and considering only transportation costs, transportation distances and waiting times may not be comprehensive enough.

[0005] To achieve the above objectives, this invention provides a production scheduling optimization system for open-pit metal mines based on multi-source data fusion, comprising:

[0006] The data processing module includes a data acquisition unit for collecting open-pit metal mine data from several data sources, a data processing unit connected to the data acquisition unit for processing the open-pit metal mine data to output optimized metal mine data, and a feature extraction unit connected to the data processing unit for extracting features from the optimized metal mine data.

[0007] The model training module, which is connected to the data processing module, includes a model generation unit for training the model according to the feature extraction unit to generate a genetic algorithm model, and a model update unit connected to the model generation unit for updating the genetic algorithm model.

[0008] The production scheduling module, which is connected to the model training module, includes an analysis unit connected to the model generation unit for analyzing the data of the open-pit metal mine through a genetic algorithm model to output analysis results, and a scheduling unit connected to the analysis unit for scheduling the production process of the open-pit metal mine according to the analysis results.

[0009] An optimization module, which is connected to the data processing module, the model training module, and the production scheduling module, is used to determine the time alignment tolerance of different data sources based on the loss rate of metal open-pit mine data, or to determine the proportion of training quantity of fault features during model training based on the error rate of metal open-pit mine production scheduling, and to determine the update frequency of the genetic algorithm model based on the delay duration of metal open-pit mine production scheduling.

[0010] Furthermore, the optimization module is used to determine whether the optimization stability of the metal open-pit mine production scheduling meets the requirements based on the data loss rate of the metal open-pit mine. If the data loss rate of the metal open-pit mine is greater than the preset first loss rate, it is determined that the optimization stability of the metal open-pit mine production scheduling does not meet the requirements.

[0011] Furthermore, the optimization module is used to preliminarily determine that the accuracy of the genetic algorithm model does not meet the requirements when the data loss rate of the open-pit metal mine is greater than the preset first loss rate and less than or equal to the preset second loss rate, and to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the open-pit metal mine production scheduling.

[0012] Furthermore, the optimization module is used to increase the time alignment tolerance of different data sources when the loss rate of the metal open-pit mine data is greater than the preset second loss rate;

[0013] The increase in time alignment tolerance for different data sources is determined by the difference between the loss rate of open-pit metal mine data and a preset second loss rate.

[0014] Furthermore, the optimization module is used to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the metal open-pit mine production scheduling. If the error rate of the metal open-pit mine production scheduling is greater than the preset first error rate, then it is determined that the accuracy of the genetic algorithm model does not meet the requirements.

[0015] Furthermore, the optimization module is used to increase the proportion of fault features trained during model training when the error rate of the metal open-pit mine production scheduling is greater than the preset first error rate and less than or equal to the preset second error rate.

[0016] Furthermore, the optimization module is used to initially determine that the anti-interference capability of the genetic algorithm model does not meet the requirements when the error rate of the metal open-pit mine production scheduling is greater than the preset second error rate, and to determine whether the anti-interference capability of the genetic algorithm model meets the requirements based on the delay time of the metal open-pit mine production scheduling.

[0017] Furthermore, the increase in the proportion of training fault features during the model training process is determined by the difference between the error rate of metal open-pit mine production scheduling and the preset first error rate.

[0018] Furthermore, the optimization module is used to determine whether the anti-interference capability of the genetic algorithm model meets the requirements based on the delay time of the metal open-pit mine production scheduling. If the delay time of the metal open-pit mine production scheduling is greater than the preset delay time, it is determined that the anti-interference capability of the genetic algorithm model does not meet the requirements, and the update frequency of the genetic algorithm model is increased.

[0019] Furthermore, the increase in the update frequency of the genetic algorithm model is determined by the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time.

[0020] Compared with existing technologies, the beneficial effects of this invention are as follows: The system of this invention, by setting up a data processing module, a model training module, a production scheduling module, and an optimization module, determines the time alignment tolerance of different data sources based on the data loss rate of open-pit metal mine data. Since some data may be lost or corrupted due to conversion algorithm errors when converting data from one format to another, increasing the time alignment tolerance of different data sources allows for a larger time range to find matching data, thereby improving the success rate of data fusion and reducing the impact of data loss or corruption on the production scheduling optimization system. The system also determines the proportion of training data on fault features during model training based on the error rate of production scheduling in open-pit metal mines. Because random faults occur suddenly and are difficult to predict in advance, the model cannot take these factors into account beforehand, resulting in discrepancies between the model's predictions of equipment operating status and production progress and the actual situation when a fault occurs. To reduce prediction bias, increasing the proportion of fault features trained during model training allows the model to learn more fault features of different types and degrees, thereby more accurately identifying various fault situations and reducing prediction bias caused by random faults. The update frequency of the genetic algorithm model is determined based on the delay time of production scheduling in metal open-pit mines. Since the model may be trained and optimized based on certain historical data and specific weather conditions, it may lack sufficient dynamic adaptability for new, rare weather conditions or rapid changes in weather conditions, and cannot adjust the scheduling strategy in time, resulting in a large deviation between prediction and actual situation. By increasing the update frequency of the genetic algorithm model, the model can incorporate new weather data and the resulting actual production data more quickly, thereby adjusting model parameters and scheduling strategies in a timely manner, better adapting to new situations, reducing the deviation between prediction and actual situation, and improving the optimization stability of production scheduling in metal open-pit mines.

[0021] Furthermore, the system of the present invention determines the time alignment tolerance of different data sources by setting a preset first loss rate and a preset second loss rate. Since some data may be lost or damaged due to conversion algorithm errors when converting data from one format to another, increasing the time alignment tolerance of different data sources can provide a larger time range to find matching data, thereby improving the success rate of data fusion and reducing the impact of data loss or damage on the production scheduling optimization system, thus further improving the optimization stability of metal open-pit mine production scheduling.

[0022] Furthermore, the system of the present invention determines the proportion of training quantities of fault features during model training by setting a preset first error rate and a preset second error rate. Since random faults occur suddenly and are difficult to predict in advance, the model cannot take these factors into account in advance, resulting in deviations between the model's prediction of the equipment's operating status and production progress and the actual situation when a fault occurs. By increasing the proportion of training quantities of fault features during model training, the model can learn more fault features of different types and degrees, thereby more accurately identifying various fault situations, reducing prediction deviations caused by random faults, and further improving the optimization stability of production scheduling in metal open-pit mines.

[0023] Furthermore, the system described in this invention determines the update frequency of the genetic algorithm model by setting a preset delay duration. Since the model may be trained and optimized based on certain historical data and specific weather conditions when it is established, it may lack sufficient dynamic adaptability for new or rare weather conditions or rapid changes in weather conditions, and may be unable to adjust the scheduling strategy in time, resulting in a large deviation between the prediction and the actual situation. By increasing the update frequency of the genetic algorithm model, the model can incorporate new weather data and the resulting actual production data more quickly, thereby adjusting the model parameters and scheduling strategy in a timely manner, better adapting to new situations, reducing the deviation between the prediction and the actual situation, and further improving the optimization stability of production scheduling in metal open-pit mines. Attached Figure Description

[0024] Figure 1 This is a block diagram of the overall structure of the metal open-pit mine production scheduling optimization system based on multi-source data fusion, according to an embodiment of the present invention.

[0025] Figure 2 This is a flowchart illustrating the process of determining the time alignment tolerance of different data sources in the metal open-pit mine production scheduling optimization system based on multi-source data fusion, according to an embodiment of the present invention.

[0026] Figure 3 This is a flowchart illustrating the process of determining the proportion of training fault features in the model training process of the metal open-pit mine production scheduling optimization system based on multi-source data fusion, according to an embodiment of the present invention.

[0027] Figure 4 This is a flowchart illustrating the process of determining the update frequency of the genetic algorithm model in a metal open-pit mine production scheduling optimization system based on multi-source data fusion, according to an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0029] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0030] Please see Figure 1 , Figure 2 , Figure 3 as well as Figure 4 The diagrams shown are, respectively, the overall structural block diagram of the metal open-pit mine production scheduling optimization system based on multi-source data fusion according to an embodiment of the present invention, the logical flowchart of the process for determining the time alignment tolerance of different data sources, the logical flowchart of the process for determining the proportion of training quantities of fault features during model training, and the logical flowchart of the process for determining the update frequency of the genetic algorithm model. The present invention provides a metal open-pit mine production scheduling optimization system based on multi-source data fusion, comprising:

[0031] The data processing module includes a data acquisition unit for collecting open-pit metal mine data from several data sources, a data processing unit connected to the data acquisition unit for processing the open-pit metal mine data to output optimized metal mine data, and a feature extraction unit connected to the data processing unit for extracting features from the optimized metal mine data.

[0032] The model training module, which is connected to the data processing module, includes a model generation unit for training the model according to the feature extraction unit to generate a genetic algorithm model, and a model update unit connected to the model generation unit for updating the genetic algorithm model.

[0033] The production scheduling module, which is connected to the model training module, includes an analysis unit connected to the model generation unit for analyzing the data of the open-pit metal mine through a genetic algorithm model to output analysis results, and a scheduling unit connected to the analysis unit for scheduling the production process of the open-pit metal mine according to the analysis results.

[0034] An optimization module, which is connected to the data processing module, the model training module, and the production scheduling module, is used to determine the time alignment tolerance of different data sources based on the loss rate of metal open-pit mine data, or to determine the proportion of training quantity of fault features during model training based on the error rate of metal open-pit mine production scheduling, and to determine the update frequency of the genetic algorithm model based on the delay duration of metal open-pit mine production scheduling.

[0035] Specifically, data sources include geological exploration data, production data, and market demand data.

[0036] Specifically, data for open-pit metal mines includes the strike of the ore body, the hardness of the rock, and the location of the mining operation.

[0037] Specifically, the process includes cleaning, conversion, and fusion.

[0038] Specifically, optimizing metal ore data includes the orientation of the cleaned ore body, the location of the converted mining site, and the hardness of the fused rock.

[0039] Specifically, the characteristics include the composition and content of the ore, the reserves of the ore, and the condition of the production equipment.

[0040] Specifically, genetic algorithm models include encoding models, fitness evaluation models, and genetic operation models.

[0041] Specifically, the analysis results include ore mining sequence planning, transportation route optimization, and production forecasting.

[0042] Specifically, the fault characteristics include abnormal operating parameters of the production equipment, decreased production efficiency, and abnormal operating temperature of the production equipment itself.

[0043] In implementation, the system of this invention sets up a data processing module, a model training module, a production scheduling module, and an optimization module. It determines the time alignment tolerance of different data sources based on the data loss rate of open-pit metal mine data. Since data may be lost or corrupted due to conversion algorithm errors during conversion from one format to another, increasing the time alignment tolerance of different data sources allows for a larger time range to find matching data, thereby improving the success rate of data fusion and reducing the impact of data loss or corruption on the production scheduling optimization system. The system also determines the proportion of fault features trained during model training based on the error rate of open-pit metal mine production scheduling. Because random faults occur suddenly and are difficult to predict in advance, the model cannot incorporate these factors in advance, leading to deviations between the model's predictions of equipment operating status and production progress and the actual situation when a fault occurs. By increasing the time alignment tolerance of different data sources... The proportion of fault features trained during model training allows the model to learn more fault features of different types and degrees, thereby more accurately identifying various fault situations and reducing prediction bias caused by random faults. The update frequency of the genetic algorithm model is determined based on the delay time of production scheduling in metal open-pit mines. Since the model may be trained and optimized based on certain historical data and specific weather conditions, it may lack sufficient dynamic adaptability for new, rare weather conditions or rapid changes in weather conditions, and may be unable to adjust the scheduling strategy in time, resulting in a large deviation between prediction and actual situation. By increasing the update frequency of the genetic algorithm model, the model can incorporate new weather data and the resulting actual production data more quickly, thereby adjusting model parameters and scheduling strategies in a timely manner, better adapting to new situations, reducing the deviation between prediction and actual situation, and improving the optimization stability of production scheduling in metal open-pit mines.

[0044] Specifically, the optimization module is used to determine whether the optimization stability of the metal open-pit mine production scheduling meets the requirements based on the data loss rate of the metal open-pit mine. If the data loss rate of the metal open-pit mine is greater than the preset first loss rate, it is determined that the optimization stability of the metal open-pit mine production scheduling does not meet the requirements.

[0045] Specifically, the optimization module is used to initially determine that the accuracy of the genetic algorithm model does not meet the requirements when the data loss rate of the open-pit metal mine is greater than the preset first loss rate and less than or equal to the preset second loss rate, and to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the open-pit metal mine production scheduling.

[0046] It is understandable that the three intervals defined by the preset first loss rate and the preset second loss rate correspond to three different scenarios:

[0047] The first interval is when the data loss rate of the open-pit metal mine is less than or equal to the preset first loss rate, which corresponds to the situation that the optimized stability of the production scheduling of the open-pit metal mine meets the requirements.

[0048] The second interval is when the data loss rate of open-pit metal mines is greater than the preset first loss rate and less than or equal to the preset second loss rate. The corresponding situation is that since random failures occur suddenly and are difficult to predict in advance, the model cannot take these factors into account in advance, which leads to a deviation between the model's prediction of the equipment's operating status and production progress and the actual situation when the failure occurs.

[0049] The third interval is when the data loss rate of open-pit metal mines is greater than the preset second loss rate. The corresponding situation is that when converting data from one format to another, some data may be lost or damaged due to errors in the conversion algorithm.

[0050] In practice, the preset first loss rate is generally selected in the range of [0.4%, 0.6%], and the preset second loss rate is generally selected in the range of [0.7%, 0.9%].

[0051] Preferably, the first loss rate is 0.5% in a preferred embodiment, and the second loss rate is 0.8% in a preferred embodiment.

[0052] Specifically, the data loss rate of open-pit metal mines is the ratio of the amount of lost data to the total amount of data in open-pit metal mines.

[0053] In practice, the system of the present invention determines the optimization stability of metal open-pit mine production scheduling by setting a preset first loss rate and a preset second loss rate, thereby reducing the impact of the decrease in optimization accuracy of metal open-pit mine production scheduling due to inaccurate determination of the optimization stability of metal open-pit mine production scheduling, and further improving the optimization stability of metal open-pit mine production scheduling.

[0054] Specifically, the optimization module is used to increase the time alignment tolerance of different data sources when the loss rate of the metal open-pit mine data is greater than the preset second loss rate;

[0055] The increase in time alignment tolerance for different data sources is determined by the difference between the loss rate of open-pit metal mine data and a preset second loss rate.

[0056] Specifically, when the difference between the data loss rate of open-pit metal mines and the preset second loss rate is within 0.3%, the time alignment tolerance of different data sources increases to 1.1 times the original value. When the difference between the data loss rate of open-pit metal mines and the preset second loss rate exceeds 0.3%, in addition to increasing to 1.1 times the original value, for every 0.2% exceeding the original value, the time alignment tolerance of different data sources increases by 0.5 seconds. For example, if the difference between the data loss rate of open-pit metal mines and the preset second loss rate is 0.7%, and the current time alignment tolerance of different data sources is 3 seconds, the increased time alignment tolerance of different data sources will be 3 × 1.1 + 0.5 × 2 = 4.3 seconds.

[0057] In implementation, the system of the present invention determines the time alignment tolerance of different data sources by setting a preset first loss rate and a preset second loss rate. Since some data may be lost or damaged due to conversion algorithm errors when converting data from one format to another, increasing the time alignment tolerance of different data sources can provide a larger time range to find matching data, thereby improving the success rate of data fusion and reducing the impact of data loss or damage on the production scheduling optimization system, further improving the optimization stability of metal open-pit mine production scheduling.

[0058] Specifically, the optimization module is used to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the metal open-pit mine production scheduling. If the error rate of the metal open-pit mine production scheduling is greater than the preset first error rate, then it is determined that the accuracy of the genetic algorithm model does not meet the requirements.

[0059] Specifically, the optimization module is used to increase the proportion of fault features trained during model training when the error rate of the metal open-pit mine production scheduling is greater than the preset first error rate and less than or equal to the preset second error rate.

[0060] Specifically, the optimization module is used to initially determine that the anti-interference ability of the genetic algorithm model does not meet the requirements when the error rate of the metal open-pit mine production scheduling is greater than the preset second error rate, and to determine whether the anti-interference ability of the genetic algorithm model meets the requirements based on the delay time of the metal open-pit mine production scheduling.

[0061] It is understandable that the three intervals defined by the preset first error rate and the preset second error rate correspond to three different scenarios:

[0062] The first interval is when the error rate of production scheduling in open-pit metal mines is less than or equal to the preset first error rate, which corresponds to the situation where the accuracy of the genetic algorithm model meets the requirements.

[0063] The second interval is when the error rate of production scheduling in open-pit metal mines is greater than the preset first error rate and less than or equal to the preset second error rate. The corresponding situation is that since random failures occur suddenly and are difficult to predict in advance, the model cannot take these factors into account in advance, which leads to a deviation between the model's prediction of the equipment's operating status and production progress and the actual situation when the failure occurs.

[0064] The third interval is where the error rate of production scheduling in open-pit metal mines is greater than the preset second error rate. The corresponding situation is that the model may be trained and optimized based on certain historical data and specific weather conditions when it is built. However, for new and rare weather conditions or rapid changes in weather conditions, the model may lack sufficient dynamic adaptability and cannot adjust the scheduling strategy in time, resulting in a large deviation between the prediction and the actual situation.

[0065] In practice, the preset first error rate is generally selected within the range of [1%, 3%], and the preset second error rate is generally selected within the range of [4%, 6%].

[0066] Preferably, the preset first error rate is 2% in a preferred embodiment, and the preset second error rate is 5% in a preferred embodiment.

[0067] Specifically, the error rate of production scheduling in open-pit metal mines is the ratio of the number of production scheduling errors to the total number of production scheduling errors in open-pit metal mines.

[0068] In practice, the system of the present invention determines the accuracy of the genetic algorithm model by setting a preset first error rate and a preset second error rate, thereby reducing the impact of the decrease in optimization stability of metal open-pit mine production scheduling caused by the inaccurate determination of the accuracy of the genetic algorithm, and further improving the optimization stability of metal open-pit mine production scheduling.

[0069] Specifically, the increase in the proportion of training fault features during the model training process is determined by the difference between the error rate of metal open-pit mine production scheduling and the preset first error rate.

[0070] Specifically, when the difference between the error rate of open-pit metal mine production scheduling and the preset first error rate is within 1%, the proportion of training fault features during model training increases to 1.2 times the original value. When the difference between the error rate of open-pit metal mine production scheduling and the preset first error rate exceeds 1%, in addition to increasing to 1.2 times the original value, for every additional 1% exceeding the original value, the proportion of training fault features during model training increases by 2%. For example, if the difference between the error rate of open-pit metal mine production scheduling and the preset first error rate is 3%, and the current proportion of training fault features during model training is 20%, the increased proportion of training fault features during model training will be 20 × 1.2 + 2 × 2 = 28%.

[0071] In practice, the system of the present invention determines the proportion of training quantities of fault features during model training by setting a preset first error rate and a preset second error rate. Since random faults occur suddenly and are difficult to predict in advance, the model cannot take these factors into account in advance. As a result, when a fault occurs, the model's prediction of the equipment's operating status and production progress deviates from the actual situation. By increasing the proportion of training quantities of fault features during model training, the model can learn more fault features of different types and degrees, thereby more accurately identifying various fault situations, reducing prediction deviations caused by random faults, and further improving the optimization stability of production scheduling in metal open-pit mines.

[0072] Specifically, the optimization module is used to determine whether the anti-interference capability of the genetic algorithm model meets the requirements based on the delay time of the metal open-pit mine production scheduling. If the delay time of the metal open-pit mine production scheduling is greater than the preset delay time, it is determined that the anti-interference capability of the genetic algorithm model does not meet the requirements, and the update frequency of the genetic algorithm model is increased.

[0073] It is understandable that the two intervals of the preset delay duration correspond to two different scenarios:

[0074] The first interval is when the delay time of production scheduling in open-pit metal mines is less than or equal to the preset delay time, which corresponds to the situation where the anti-interference ability of the genetic algorithm model meets the requirements.

[0075] The second interval is when the delay time of production scheduling in open-pit metal mines is longer than the preset delay time. The corresponding situation is that the model may be trained and optimized based on certain historical data and specific weather conditions when it is built. However, for new and rare weather conditions or rapid changes in weather conditions, the model may lack sufficient dynamic adaptability and cannot adjust the scheduling strategy in time, resulting in a large deviation between the prediction and the actual situation.

[0076] In practice, the preset delay time is generally selected within the range of [2 min, 4 min].

[0077] Preferably, the preset delay time is 3 minutes.

[0078] In practice, the system of the present invention determines the anti-interference ability of the genetic algorithm model by setting a preset delay time, thereby reducing the impact of the decrease in optimization stability of metal open-pit mine production scheduling due to inaccurate determination of the anti-interference ability of the genetic algorithm model, and further improving the optimization stability of metal open-pit mine production scheduling.

[0079] Specifically, the increase in the update frequency of the genetic algorithm model is determined by the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time.

[0080] Specifically, when the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time is within 2 minutes, the update frequency of the genetic algorithm model increases by 1.2 times. When the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time exceeds 2 minutes, in addition to increasing to 1.2 times the original value, the update frequency of the genetic algorithm model increases by 1 time per day for every 1 minute exceeding the preset delay time. For example, if the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time is 4 minutes, the current update frequency of the genetic algorithm model is 5 times per day, and the increased update frequency of the genetic algorithm model is 5 × 1.2 + 1 × 2 = 8 times per day.

[0081] In implementation, the system of the present invention determines the update frequency of the genetic algorithm model by setting a preset delay time. Since the model may be trained and optimized based on certain historical data and specific weather conditions when it is established, it may lack sufficient dynamic adaptability for new, rare weather conditions or rapid changes in weather conditions, and may be unable to adjust the scheduling strategy in time, resulting in a large deviation between the prediction and the actual situation. By increasing the update frequency of the genetic algorithm model, the model can incorporate new weather data and the resulting actual production data more quickly, thereby adjusting the model parameters and scheduling strategy in a timely manner, better adapting to new situations, reducing the deviation between the prediction and the actual situation, and further improving the optimization stability of production scheduling in metal open-pit mines.

[0082] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A production scheduling optimization system for open-pit metal mines based on multi-source data fusion, characterized in that, include: The data processing module includes a data acquisition unit for collecting open-pit metal mine data from several data sources, a data processing unit connected to the data acquisition unit for processing the open-pit metal mine data to output optimized metal mine data, and a feature extraction unit connected to the data processing unit for extracting features from the optimized metal mine data. The model training module, which is connected to the data processing module, includes a model generation unit for training the model according to the feature extraction unit to generate a genetic algorithm model, and a model update unit connected to the model generation unit for updating the genetic algorithm model. The production scheduling module, which is connected to the model training module, includes an analysis unit connected to the model generation unit for analyzing the data of the open-pit metal mine through a genetic algorithm model to output analysis results, and a scheduling unit connected to the analysis unit for scheduling the production process of the open-pit metal mine according to the analysis results. An optimization module, which is connected to the data processing module, the model training module and the production scheduling module respectively, is used to determine the time alignment tolerance of different data sources based on the loss rate of metal open-pit mine data, or to determine the proportion of training quantity of fault features during model training based on the error rate of metal open-pit mine production scheduling, and to determine the update frequency of the genetic algorithm model based on the delay time of metal open-pit mine production scheduling. The optimization module is used to determine whether the optimization stability of the metal open-pit mine production scheduling meets the requirements based on the data loss rate of the metal open-pit mine. If the data loss rate of the metal open-pit mine is greater than the preset first loss rate, it is determined that the optimization stability of the metal open-pit mine production scheduling does not meet the requirements. The optimization module is used to initially determine that the accuracy of the genetic algorithm model does not meet the requirements when the data loss rate of the open-pit metal mine is greater than the preset first loss rate and less than or equal to the preset second loss rate, and to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the open-pit metal mine production scheduling. The optimization module is used to increase the time alignment tolerance of different data sources when the loss rate of the metal open-pit mine data is greater than the preset second loss rate; The increase in time alignment tolerance for different data sources is determined by the difference between the loss rate of open-pit metal mine data and a preset second loss rate.

2. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 1, characterized in that, The optimization module is used to determine whether the accuracy of the genetic algorithm model meets the requirements based on the error rate of the metal open-pit mine production scheduling. If the error rate of the metal open-pit mine production scheduling is greater than the preset first error rate, then it is determined that the accuracy of the genetic algorithm model does not meet the requirements.

3. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 2, characterized in that, The optimization module is used to increase the proportion of fault features trained during model training when the error rate of production scheduling in the open-pit metal mine is greater than the preset first error rate and less than or equal to the preset second error rate.

4. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 3, characterized in that, The optimization module is used to initially determine that the anti-interference ability of the genetic algorithm model does not meet the requirements when the error rate of the production scheduling of the open-pit metal mine is greater than the preset second error rate, and to determine whether the anti-interference ability of the genetic algorithm model meets the requirements based on the delay time of the production scheduling of the open-pit metal mine.

5. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 4, characterized in that, The increase in the proportion of training fault features during the model training process is determined by the difference between the error rate of metal open-pit mine production scheduling and the preset first error rate.

6. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 5, characterized in that, The optimization module is used to determine whether the anti-interference capability of the genetic algorithm model meets the requirements based on the delay time of the metal open-pit mine production scheduling. If the delay time of the metal open-pit mine production scheduling is greater than the preset delay time, it is determined that the anti-interference capability of the genetic algorithm model does not meet the requirements, and the update frequency of the genetic algorithm model is increased.

7. The metal open-pit mine production scheduling optimization system based on multi-source data fusion according to claim 6, characterized in that, The increase in the update frequency of the genetic algorithm model is determined by the difference between the delay time of the metal open-pit mine production scheduling and the preset delay time.

Images