Method and device for predicting dam break risk of tailings pond, electronic equipment and storage medium
By collecting and analyzing a variety of data to be tested, and the weighted calculation of the prediction model, it solves the problem of difficulty evaluating the risk of tailings and dam -losing risks in the existing technology, and achieves more accurate and reliable risk predictions.
Patent Information
- Application Number
- CN202411345613.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-25
- Publication Date
- 2025-01-24
Smart Images
Figure CN119359015A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device for predicting the risk of tailings dam breach, an electronic device and a storage medium. Background Art
[0002] Tailings are solid waste materials discharged from metal or non-metal mines after ore selection. Tailings ponds are a group of structures formed with other facilities to store tailings, regulate flood water, ensure backwater, protect the environment, build dams to block valley mouths, enclose land or utilize depressions.
[0003] The causes of tailings dam failure are diverse and complex, involving many disciplines. At present, most research work tends to conduct safety assessment and prediction of tailings dams based on a single failure mode. However, in actual situations, tailings dam failure is often the result of multiple factors. The specific composition and state of each tailings dam are different. It is difficult to reflect the real risk by relying on a single failure mode for evaluation. Summary of the invention
[0004] The present invention provides a method, device, electronic device and storage medium for predicting the risk of tailings dam breach.
[0005] According to a first aspect of the present disclosure, a method for predicting the risk of tailings dam breach is provided, which includes:
[0006] Collect at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0007] Inputting the at least two types of data to be detected into corresponding prediction models respectively to obtain prediction data corresponding to the at least two types of data to be detected;
[0008] According to the identification results of the prediction data corresponding to the at least two types of data to be detected, it is determined that the tailings pond has a risk of dam break.
[0009] In some embodiments, determining that the tailings pond has a dam break risk according to the recognition result of the prediction data corresponding to the at least two types of data to be detected includes:
[0010] When at least two types of prediction data exceed their respective corresponding warning thresholds, it is determined that the tailings pond is at risk of dam break.
[0011] In some embodiments, determining that the tailings pond has a dam break risk according to the recognition result of the prediction data corresponding to the at least two types of data to be detected includes:
[0012] According to the weighted calculation results of various prediction data, the prediction result of the risk of dam break in the tailings pond is obtained.
[0013] In some embodiments, the at least two types of data to be detected include: surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0014] The step of respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected includes:
[0015] Inputting the surface displacement data into a surface displacement data prediction model to obtain a prediction result of the surface displacement;
[0016] Inputting the internal displacement data into an internal displacement prediction model to obtain a prediction result of the internal displacement;
[0017] Inputting the infiltration line data into an infiltration line prediction model to obtain an infiltration line prediction result;
[0018] Inputting the reservoir water level data into a reservoir water level prediction model to obtain a reservoir water level prediction result;
[0019] Inputting the dry beach length data into a dry beach length prediction model to obtain a prediction result of the dry beach length;
[0020] The rainfall data is input into a rainfall prediction model to obtain a rainfall prediction result.
[0021] In some embodiments, the prediction result of the tailings storage having a dam break risk obtained based on the weighted calculation results of various prediction data includes:
[0022] Performing weighted calculation on the predicted result of the surface displacement and a first weight, the predicted result of the internal displacement and a second weight, the predicted result of the infiltration line and a third weight, the predicted result of the reservoir water level and a fourth weight, the predicted result of the dry beach length and a fifth weight, and the predicted result of the rainfall and a sixth weight to obtain the risk prediction result;
[0023] The sum of the first weight, the second weight, the third weight, the fifth weight and the sixth weight is 1.
[0024] In some embodiments, after obtaining a prediction result that the tailings pond has a dam break risk according to the weighted calculation results of each prediction data, the method further includes:
[0025] Determining whether the risk prediction result falls into the risk range corresponding to different levels of risk;
[0026] The level corresponding to the target risk range in which the risk prediction result falls is determined as the target risk level;
[0027] Output defense prompt information corresponding to the target risk level.
[0028] In some embodiments, before respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected, the method further includes:
[0029] The surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model are trained separately to obtain the corresponding trained surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model.
[0030] In a second aspect, an embodiment of the present application provides a device for predicting the risk of tailings dam breach, including:
[0031] A collection unit, used for collecting at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0032] An input unit, used for inputting the at least two types of data to be detected into corresponding prediction models respectively, so as to obtain prediction data corresponding to the at least two types of data to be detected;
[0033] The prediction unit is used to determine whether the tailings pond has a risk of dam breach based on the recognition result of the prediction data corresponding to the at least two types of data to be detected.
[0034] In some embodiments, the prediction unit is further used to determine that the tailings pond is at risk of dam break when at least two types of prediction data exceed their respective corresponding warning thresholds.
[0035] In some embodiments, the prediction unit is further used to obtain a prediction result of the risk of dam breach in the tailings pond based on a weighted calculation result of each prediction data.
[0036] In some embodiments, the at least two types of data to be detected include: surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0037] The input unit is further used for:
[0038] Inputting the surface displacement data into a surface displacement data prediction model to obtain a prediction result of the surface displacement;
[0039] Inputting the internal displacement data into an internal displacement prediction model to obtain a prediction result of the internal displacement;
[0040] Inputting the infiltration line data into an infiltration line prediction model to obtain an infiltration line prediction result;
[0041] Inputting the reservoir water level data into a reservoir water level prediction model to obtain a reservoir water level prediction result;
[0042] Inputting the dry beach length data into a dry beach length prediction model to obtain a prediction result of the dry beach length;
[0043] The rainfall data is input into a rainfall prediction model to obtain a rainfall prediction result.
[0044] In some embodiments, the prediction unit is further configured to:
[0045] Performing weighted calculation on the predicted result of the surface displacement and a first weight, the predicted result of the internal displacement and a second weight, the predicted result of the infiltration line and a third weight, the predicted result of the reservoir water level and a fourth weight, the predicted result of the dry beach length and a fifth weight, and the predicted result of the rainfall and a sixth weight to obtain the risk prediction result;
[0046] The sum of the first weight, the second weight, the third weight, the fifth weight and the sixth weight is 1.
[0047] In some embodiments, the apparatus further comprises:
[0048] After obtaining the prediction result that the tailings pond has the risk of dam break according to the weighted calculation results of each prediction data, the device further includes:
[0049] A first determining unit, used to determine whether the risk prediction result falls into a risk range corresponding to different levels of risk;
[0050] A second determining unit is used to determine the level corresponding to the target risk range in which the risk prediction result falls as the target risk level;
[0051] The output unit is used to output defense prompt information corresponding to the target risk level.
[0052] In some embodiments, the apparatus further comprises:
[0053] A training unit is used to respectively train the surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model before respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected, so as to obtain the corresponding trained surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model.
[0054] According to a third aspect of the present disclosure, there is provided an electronic device, including:
[0055] at least one processor; and
[0056] a memory communicatively connected to the at least one processor; wherein,
[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.
[0058] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.
[0059] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.
[0060] The present disclosure provides a method, device, electronic device and storage medium for predicting the risk of dam break in a tailings pond, which collects at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data and rainfall data; respectively inputs the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected; and determines that the tailings pond has a risk of dam break based on the identification results of the prediction data corresponding to the at least two types of data to be detected. The embodiments of the present application make up for the limitations of relying on a single failure mode for prediction and evaluation through the prediction results of at least two types of data to be detected, which has important guiding significance for preventing tailings pond disasters and reducing the serious consequences caused by tailings pond disasters.
[0061] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.
[0063] Figure 1 A schematic diagram of a flow chart of a method for predicting the risk of tailings dam breach provided by an embodiment of the present disclosure;
[0064] Figure 2 A schematic diagram of the structure of a device for predicting the risk of tailings dam breach provided by an embodiment of the present disclosure;
[0065] Figure 3 A schematic diagram of the structure of another device for predicting the risk of tailings dam breach provided by an embodiment of the present disclosure;
[0066] Figure 4 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION
[0067] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0068] The following describes the method, device, electronic device and storage medium for predicting the risk of tailings dam breach according to the embodiments of the present disclosure with reference to the accompanying drawings.
[0069] Figure 1 A schematic flow chart of a method for predicting the risk of tailings dam breach provided in an embodiment of the present disclosure.
[0070] like Figure 1 As shown, the method comprises the following steps:
[0071] Step 101, collecting at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0072] According to the "Technical Specification for Engineering Online Safety Monitoring System of Tailings Ponds" (GB51108-2015) and the "Design Specification for Tailings Facilities" (GB50863-2013), a tailings pond dam displacement monitoring plan is determined, the locations of monitoring points are determined and sensors are buried, and at least two types of data to be detected related to the tailings pond are collected based on each sensor. In an embodiment of the present application, the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data.
[0073] It should be noted that the embodiments of the present application do not limit the locations of monitoring points and the number of sensors, and they can be flexibly set according to actual needs.
[0074] Step 102: input the at least two types of data to be detected into corresponding prediction models respectively to obtain prediction data corresponding to the at least two types of data to be detected.
[0075] In an embodiment of the present application, the prediction model is composed of multiple types of models, the number of which is related to the type of data to be detected. Assume that when there are three categories of data to be detected, three corresponding models in the prediction model are activated. In an embodiment of the present application, one type of data to be detected can only be input into the corresponding model.
[0076] Taking the case where the data to be detected is surface displacement data and internal displacement data, the surface displacement data can only be input into the surface displacement data prediction model, and the internal displacement data can only be input into the internal displacement prediction model. When the data to be detected is surface displacement data and internal displacement data, the surface displacement data prediction model and the internal displacement prediction model in the preset model are activated, and other types of models are in a waiting state.
[0077] It should be clear that the above examples are merely illustrative descriptions for ease of understanding, and do not limit the specific categories of the data to be detected and the prediction model.
[0078] The prediction model described in the embodiment of the present application is based on LSTM network unit structure, TensorFlow framework, Adam error optimization algorithm and other methods. According to the tailings dam displacement monitoring data, a neural network is constructed to establish a prediction model (tailings dam LSTM model) to predict at least two types of data to be detected (at least two of the tailings dam surface displacement, internal displacement, infiltration line, reservoir water level, dry beach length, and rainfall).
[0079] Step 103: determining whether the tailings pond has a risk of dam breach based on the recognition results of the prediction data corresponding to the at least two types of data to be detected.
[0080] In the embodiment of the present application, prediction is performed based on the output result of step 102.
[0081] The present disclosure provides a method for predicting the risk of dam break in a tailings pond, which collects at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data; the at least two types of data to be detected are respectively input into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected; and the risk of dam break in the tailings pond is determined based on the recognition results of the prediction data corresponding to the at least two types of data to be detected. The embodiment of the present application makes up for the limitation of relying on a single failure mode for prediction and evaluation through the prediction results of at least two types of data to be detected, which has important guiding significance for preventing tailings pond disasters and reducing the serious consequences caused by tailings pond disasters.
[0082] In some embodiments, when determining that the tailings pond has a risk of dam break according to the recognition result of the prediction data corresponding to the at least two types of data to be detected, the following two methods can be used:
[0083] Method 1:
[0084] When at least two types of prediction data exceed their respective corresponding warning thresholds, it is determined that the tailings pond is at risk of dam break.
[0085] In one method, the prediction model is provided with warning thresholds corresponding to the respective prediction data. When two prediction data are greater than the warning thresholds, it is determined that the tailings pond is at risk of dam break; when only one prediction data is greater than the warning threshold, it is determined that the tailings pond is not at risk of dam break.
[0086] For example, when the predicted data is rainfall, the warning threshold is set to: 16mm precipitation within one hour; when the predicted data is the infiltration line, when the accumulation dam is less than 30 meters, the warning threshold is set to: 2m; when the accumulation dam is greater than 30 meters and less than 60, the warning threshold is set to: 2m-4m; the red warning threshold of the minimum safe superelevation and the minimum dry beach length of the tailings dam should be determined according to the design documents and the current national standards; the orange warning threshold of the minimum safe superelevation should be 1.2 to 1.5 times the red warning threshold, and the orange warning threshold of the minimum beach length should be 1.1 to 1.4 times the red warning threshold; the minimum safe superelevation and the minimum dry beach length should reach the warning threshold and an alarm should be issued; the red warning threshold of the reservoir water level should be determined according to the water level corresponding to the minimum safe superelevation and the minimum dry beach length of the tailings reservoir; displacement warning: the normal operating values of the displacement of the tailings dam and the displacement change rate should be determined according to the characteristics of the tailings reservoir, engineering analogy, statistical analysis of existing monitoring results, and experimental research. Specifically, the embodiments of this application do not limit the warning threshold.
[0087] Method 2:
[0088] According to the weighted calculation results of various prediction data, the prediction result of the risk of dam break in the tailings pond is obtained.
[0089] The specific determination process can be achieved in the following ways:
[0090] The risk prediction result is obtained by performing weighted calculation on the predicted result of the surface displacement and the first weight, the predicted result of the internal displacement and the second weight, the predicted result of the infiltration line and the third weight, the predicted result of the reservoir water level and the fourth weight, the predicted result of the dry beach length and the fifth weight, and the predicted result of the rainfall and the sixth weight, wherein the sum of the first weight, the second weight, the third weight, the fifth weight and the sixth weight is 1.
[0091] In some embodiments, when the at least two types of data to be detected include: surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data, respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected includes:
[0092] Inputting the surface displacement data into a surface displacement data prediction model to obtain a prediction result of the surface displacement;
[0093] Inputting the internal displacement data into an internal displacement prediction model to obtain a prediction result of the internal displacement;
[0094] Inputting the infiltration line data into an infiltration line prediction model to obtain an infiltration line prediction result;
[0095] Inputting the reservoir water level data into a reservoir water level prediction model to obtain a reservoir water level prediction result;
[0096] Inputting the dry beach length data into a dry beach length prediction model to obtain a prediction result of the dry beach length;
[0097] The rainfall data is input into a rainfall prediction model to obtain a rainfall prediction result.
[0098] In some embodiments, before respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected, the method further includes:
[0099] The surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model are trained separately to obtain the corresponding trained surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model.
[0100] Taking the rainfall prediction model as an example, the input features include the month, average temperature and precipitation of the past 12 months, and the month, average temperature and precipitation are preprocessed using standardization methods. In terms of model comparison, the LSTM model that selects monthly precipitation, monthly average temperature and month ordinal number as feature input is compared with the LSTM that only selects monthly precipitation as feature input to observe the effect of feature introduction on improving model performance.
[0101] The study used root mean square error (RMSE), mean absolute error (MAE) and Nash efficiency coefficient (NSE) as evaluation indicators to evaluate the accuracy of the model prediction results. The calculation formulas of each indicator are as follows.
[0102]
[0103] Where: p t is the precipitation forecast value; t is the corresponding measured precipitation value; is the mean of the measured precipitation; n is the number of precipitation samples in the data set; t is the sample ordinal number.
[0104] The smaller the RMSE and MAE values are, the smaller the model error is and the better the fit is; the larger the NSE coefficient value is, the higher the prediction accuracy of the model is.
[0105] The input data corresponding to the surface displacement data prediction model are: displacement increment of the current month, displacement increment of the previous two months, and displacement increment of the previous three months;
[0106] The input data corresponding to the internal displacement prediction model are: displacement increment of the current month, displacement increment of the previous two months, and displacement increment of the previous three months;
[0107] The input data corresponding to the infiltration line prediction model are: infiltration line height, infiltration line height change in the current month, infiltration line height change in the current month, infiltration line height change in the previous two months, and infiltration line height change in the previous three months;
[0108] The input data corresponding to the reservoir water level prediction model are: reservoir water level, reservoir water level change in the current month, reservoir water level change in the previous two months, and reservoir water level change in the previous three months;
[0109] The input data corresponding to the dry beach length prediction model are: dry beach length, change in dry beach length in the current month, change in dry beach length in the previous two months, and change in dry beach length in the previous three months;
[0110] The corresponding input data of the rainfall prediction model are: month, average temperature and precipitation in the past 12 months.
[0111] For other prediction models, their implementation principles are the same as those of the rainfall prediction model, and will not be repeated in the embodiments of this application.
[0112] In the specific training process, an LSTM neural network (prediction model) was built based on the TensorFlow framework, using 80% of the data as the training set for training and 20% of the data as the test set for testing. The model uses the Adam error optimization algorithm and the Relu activation function. Through repeated experimental tests, the learning rate was set to 0.001 to balance the convergence speed and training stability, and the time step was set to 50 training cycles to prevent the model from overfitting and hiding, and the optimal parameter setting results were obtained.
[0113] According to the LSTM long short-term memory neural network prediction model theory, the set program is imported into Python to predict the surface displacement, internal displacement, infiltration line, reservoir water level, dry beach length and rainfall of the tailings dam.
[0114] The technical idea of the embodiment of the present application is to establish a tailings pond prediction model under multi-source data fusion, and use long short-term memory neural network prediction algorithm to predict various indicators of the tailings dam body through exploration data and monitoring data, so as to provide a basis for further analyzing the deformation of the tailings dam and judging the safety status of the tailings dam body.
[0115] Corresponding to the above-mentioned method for predicting the risk of tailings dam breach, the present invention also proposes a device for predicting the risk of tailings dam breach. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.
[0116] Figure 2 A schematic diagram of a device for predicting the risk of tailings dam breach provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, including:
[0117] A collection unit 21 is used to collect at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0118] An input unit 22, used to input the at least two types of data to be detected into corresponding prediction models respectively, so as to obtain prediction data corresponding to the at least two types of data to be detected;
[0119] The prediction unit 23 is used to determine whether the tailings pond has a risk of dam breaking according to the recognition result of the prediction data corresponding to the at least two types of data to be detected.
[0120] The prediction device for the risk of dam break of a tailings pond provided by the present disclosure collects at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data; the at least two types of data to be detected are respectively input into the corresponding prediction model to obtain the prediction data corresponding to the at least two types of data to be detected; and the existence of the risk of dam break of the tailings pond is determined according to the recognition results of the prediction data corresponding to the at least two types of data to be detected. The embodiment of the present application makes up for the limitation of relying on a single failure mode for prediction and evaluation through the prediction results of at least two types of data to be detected, and has important guiding significance for preventing tailings pond disasters and reducing the serious consequences caused by tailings pond disasters.
[0121] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the prediction unit 23 is further used to determine that the tailings pond has a risk of dam break when at least two types of prediction data exceed their respective corresponding warning thresholds.
[0122] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the prediction unit 23 is also used to obtain a prediction result of the risk of dam break in the tailings pond based on the weighted calculation results of various prediction data.
[0123] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the at least two types of data to be detected include: surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data;
[0124] The input unit 22 is further used for:
[0125] Inputting the surface displacement data into a surface displacement data prediction model to obtain a prediction result of the surface displacement;
[0126] Inputting the internal displacement data into an internal displacement prediction model to obtain a prediction result of the internal displacement;
[0127] Inputting the infiltration line data into an infiltration line prediction model to obtain an infiltration line prediction result;
[0128] Inputting the reservoir water level data into a reservoir water level prediction model to obtain a reservoir water level prediction result;
[0129] Inputting the dry beach length data into a dry beach length prediction model to obtain a prediction result of the dry beach length;
[0130] The rainfall data is input into a rainfall prediction model to obtain a rainfall prediction result.
[0131] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the prediction unit 23 is further used for:
[0132] Performing weighted calculation on the predicted result of the surface displacement and a first weight, the predicted result of the internal displacement and a second weight, the predicted result of the infiltration line and a third weight, the predicted result of the reservoir water level and a fourth weight, the predicted result of the dry beach length and a fifth weight, and the predicted result of the rainfall and a sixth weight to obtain the risk prediction result;
[0133] The sum of the first weight, the second weight, the third weight, the fifth weight and the sixth weight is 1.
[0134] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the device also includes:
[0135] After obtaining the prediction result that the tailings pond has the risk of dam break according to the weighted calculation results of each prediction data, the device further includes:
[0136] A first determining unit 24 is used to determine whether the risk prediction result falls into a risk range corresponding to different levels of risk;
[0137] The second determining unit 25 is used to determine the level corresponding to the target risk range in which the risk prediction result falls as the target risk level;
[0138] The output unit 26 is used to output defense prompt information corresponding to the target risk level.
[0139] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 3 As shown, the device also includes:
[0140] The training unit 27 is used to respectively train the surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model before respectively inputting the at least two types of data to be detected into the corresponding prediction models to obtain the prediction data corresponding to the at least two types of data to be detected, so as to obtain the corresponding trained surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model.
[0141] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.
[0142] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0143] Figure 4 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0144] like Figure 4 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 302 or a computer program loaded from a storage unit 308 to a RAM (Random Access Memory) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.
[0145] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0146] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as a method for predicting the risk of a tailings dam breach. For example, in some embodiments, the method for predicting the risk of a tailings dam breach may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the aforementioned method for predicting the risk of tailings dam failure by any other appropriate means (for example, by means of firmware).
[0147] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a special purpose or general purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0148] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0149] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0151] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.
[0152] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.
[0153] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.
[0154] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0155] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for predicting the risk of tailings dam breach, characterized in that: include: Collect at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data; Inputting the at least two types of data to be detected into corresponding prediction models respectively to obtain prediction data corresponding to the at least two types of data to be detected; According to the identification results of the prediction data corresponding to the at least two types of data to be detected, it is determined that the tailings pond has a risk of dam break.
2. The method according to claim 1, characterized in that Determining that the tailings pond has a dam break risk according to the recognition result of the prediction data corresponding to the at least two types of data to be detected includes: When at least two types of prediction data exceed their respective corresponding warning thresholds, it is determined that the tailings pond is at risk of dam break.
3. The method according to claim 1, characterized in that Determining that the tailings pond has a dam break risk according to the recognition result of the prediction data corresponding to the at least two types of data to be detected includes: According to the weighted calculation results of various prediction data, the prediction result of the risk of dam break in the tailings pond is obtained.
4. The method according to claim 3, characterized in that The at least two types of data to be detected include: surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data; The step of respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected includes: Inputting the surface displacement data into a surface displacement data prediction model to obtain a prediction result of the surface displacement; Inputting the internal displacement data into an internal displacement prediction model to obtain a prediction result of the internal displacement; Inputting the infiltration line data into an infiltration line prediction model to obtain an infiltration line prediction result; Inputting the reservoir water level data into a reservoir water level prediction model to obtain a reservoir water level prediction result; Inputting the dry beach length data into a dry beach length prediction model to obtain a prediction result of the dry beach length; The rainfall data is input into a rainfall prediction model to obtain a rainfall prediction result.
5. The method according to claim 4, characterized in that The prediction result of the tailings storage dam breach risk obtained based on the weighted calculation results of various prediction data includes: Performing weighted calculation on the predicted result of the surface displacement and a first weight, the predicted result of the internal displacement and a second weight, the predicted result of the infiltration line and a third weight, the predicted result of the reservoir water level and a fourth weight, the predicted result of the dry beach length and a fifth weight, and the predicted result of the rainfall and a sixth weight to obtain the risk prediction result; The sum of the first weight, the second weight, the third weight, the fifth weight and the sixth weight is 1.
6. The method according to claim 3, characterized in that After obtaining the prediction result that the tailings pond has a dam break risk according to the weighted calculation results of each prediction data, the method further includes: Determining whether the risk prediction result falls into the risk range corresponding to different levels of risk; The level corresponding to the target risk range in which the risk prediction result falls is determined as the target risk level; Output defense prompt information corresponding to the target risk level.
7. The method according to claim 4, characterized in that Before respectively inputting the at least two types of data to be detected into corresponding prediction models to obtain prediction data corresponding to the at least two types of data to be detected, the method further includes: The surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model are trained separately to obtain the corresponding trained surface displacement data prediction model, the internal displacement prediction model, the infiltration line prediction model, the reservoir water level prediction model, the dry beach length prediction model and the rainfall prediction model.
8. A device for predicting the risk of tailings dam breach, characterized in that: include: A collection unit, used for collecting at least two types of data to be detected related to the tailings pond, wherein the data to be detected includes any one of surface displacement data, internal displacement data, infiltration line data, reservoir water level data, dry beach length data, and rainfall data; A processing unit, used for inputting the at least two types of data to be detected into corresponding prediction models respectively, so as to obtain prediction data corresponding to the at least two types of data to be detected; The prediction unit is used to perform weighted calculation on each prediction data to obtain the risk prediction result.
9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.