Mine remediation effect prediction method and system based on soil data analysis

Abstract

The invention discloses a mine remediation effect prediction method and system based on soil data analysis, and relates to the technical field of mine remediation, and the method comprises the steps: constructing a mine remediation database; acquiring soil data of the to-be-restored area in real time, and recording the soil data as real-time soil data; obtaining a plurality of similar soil data cases; constructing a restoration effect regression model of the to-be-restored area; determining repair process data through the repair effect regression model of the to-be-repaired area; performing mine restoration according to the restoration process data, and monitoring a real-time mine restoration effect; based on the real-time mine restoration effect, the restoration effect regression model for optimizing the to-be-restored area is fed back, and restoration process data are determined again based on the optimized restoration effect regression model of the to-be-restored area. The method has the advantages that the mine restoration work is carried out in a real-time optimization feedback mode, the restoration quality can be remarkably improved, and comprehensive and efficient restoration of the mine ecological environment is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of mine restoration, and in particular to a mine restoration effect prediction method and system based on soil data analysis. Background Art

[0002] Mine restoration, also known as mine ecological restoration, refers to the restoration of pollution in abandoned mining sites. It aims to restore and improve the ecological environment, land resources and social functions of the mined areas to reduce the impact of mining activities on the environment. Mine restoration work is of great significance to restoring the sustainable use of land resources and protecting the ecological environment.

[0003] Mine restoration methods include physical restoration, chemical restoration, biological restoration and other means. In the existing technology, mine restoration means are usually determined manually based on experience. Once the mine restoration means are determined, they will not be updated and learned according to the actual status. In the actual mine restoration process, the ideal mine restoration effect is often not achieved, resulting in a waste of resources. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for predicting mine restoration effects based on soil data analysis are provided. This technical solution solves the problem that in the above-mentioned prior art, the mine restoration means are usually determined manually based on experience. Once the mine restoration means are determined, they will not be updated and learned according to the actual status. In the actual mine restoration process, the ideal mine restoration effect cannot be achieved, resulting in a waste of resources.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] The mine restoration effect prediction method based on soil data analysis includes:

[0007] Based on all known mine restoration cases, a mine restoration database is constructed, wherein the mine restoration database includes initial soil data, restoration effect data and restoration process data of the mine restoration cases;

[0008] Collect soil data of the area to be repaired in real time and record it as real-time soil data;

[0009] Based on matching the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database, a number of similar soil data cases are obtained;

[0010] The restoration effect data and restoration process data of similar soil data cases are used as sample data to build a restoration effect regression model for the area to be restored.

[0011] Determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determine the repair process data through a repair effect regression model of the area to be repaired;

[0012] Carry out mine restoration according to restoration process data and monitor the real-time mine restoration effect;

[0013] Based on the real-time mine restoration effect, the restoration effect regression model of the area to be restored is fed back and optimized, and the restoration process data is re-determined based on the optimized restoration effect regression model of the area to be restored.

[0014] Preferably, the matching of the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database to obtain a number of similar soil data cases specifically includes:

[0015] Based on the real-time index value of each soil index in the collected real-time soil data and the index value of each soil index in the initial soil data of the mine remediation case, a comprehensive similarity index between the collected real-time soil data and the initial soil data of the mine remediation case is calculated;

[0016] Determine whether the comprehensive similarity index is less than a preset value. If so, the mine restoration case is regarded as a similar soil data case. If not, the mine restoration case is not regarded as a similar soil data case.

[0017] The calculation formula of the comprehensive similarity index is:

[0018]

[0019] In the formula, L is the comprehensive similarity index, A k0 is the real-time index value of the kth soil index in the real-time soil data, A k is the index value of the kth soil index in the initial soil data of the mine remediation case, and n is the total number of soil indicators.

[0020] Preferably, the method of using the restoration effect data and restoration process data of similar soil data cases as sample data to construct a restoration effect regression model for the area to be restored specifically includes:

[0021] According to the influencing factors of each restoration effect of the area to be restored, a regression equation for each restoration effect is established;

[0022] Based on the regression equation of each repair effect, a loss function of each repair effect is established;

[0023] Based on the mini-batch gradient descent method, the parameter update equation of the regression equation is established;

[0024] According to the actual test situation, adjust the value of the learning rate and the number of samples in each iteration.

[0025] Preferably, the regression equation of the repair effect is specifically:

[0026]

[0027] Among them, f(γ) u is the predicted value of the repair effect of the u-th repair effect, θ0 is the error constant term, θ g Model coefficients for the g-th repair process, γ g is the parameter value of the g-th repair process, α g is the model index of the g-th repair process;

[0028] The loss function of the repair effect is:

[0029]

[0030] Among them, F θ is the relationship between the predicted value and the actual value of the repair effect, m is the number of samples in the small batch sample data, is the predicted value of the repair effect of the i-th data in the sample data, f i is the actual value of the repair effect of the i-th data in the sample data;

[0031] The parameter update equation of the regression equation is:

[0032]

[0033] in, is the update parameter of the jth influencing factor of the i-th sample data, is the parameter of the jth influencing factor of the i-th sample data, α is the learning rate, is the value of the jth influencing factor of the i-th sample data.

[0034] Preferably, the repair process data is determined based on the repair effect requirement of the area to be repaired by using a repair effect regression model of the area to be repaired, specifically including:

[0035] Based on the restoration effect requirement of the area to be restored, an inequality for the restoration effect requirement of the area to be restored is constructed;

[0036] Solve the repair effect requirement inequality of the area to be repaired, and obtain the parameter range of the repair process of the area to be repaired;

[0037] A repair evaluation model is constructed, and within the parameter range of the repair process of the area to be repaired, the parameters of the repair process corresponding to the maximum value of the repair evaluation model are taken as the repair process data.

[0038] Preferably, the repair effect requirement inequality is specifically:

[0039] f(γ) u ≥f u0 , u=1、2、…、U

[0040] In the formula, f u0 is the required value of the repair effect of the u-th repair effect, and U is the total number of repair effect items;

[0041] The repair evaluation model is specifically:

[0042]

[0043] In the formula, β u is the emphasis weight of the u-th repair effect, P jug Output values ​​for evaluating the model.

[0044] Preferably, the restoration effect regression model for feedback optimization of the area to be restored based on the real-time mine restoration effect specifically includes:

[0045] Calculate the deviation between the real-time mine restoration effect and the restoration effect predicted by the restoration effect regression equation;

[0046] Determine whether the deviation value is greater than the preset value. If so, remove the similar soil data case corresponding to the minimum value of the comprehensive similarity index, and add the real-time mine restoration effect and restoration process data to the sample data. If not, directly add the real-time mine restoration effect and restoration process data to the sample data.

[0047] The calculation formula of the deviation value is:

[0048]

[0049] Among them, f u is the restoration effect value of the u-th real-time mine restoration effect, and C is the deviation value.

[0050] Furthermore, a mine restoration effect prediction system based on soil data analysis is proposed, which is used to implement the mine restoration effect prediction method based on soil data analysis as mentioned above, including:

[0051] A storage module, the storage module is used to build a mine restoration database based on all known mine restoration cases;

[0052] A soil data collection module, which is used to collect soil data of the area to be repaired in real time, recorded as real-time soil data;

[0053] A data similarity matching module, the data similarity matching module is electrically connected to the soil data acquisition module and the storage module, and the data similarity matching module is used to match the initial soil data of the mine restoration case in the mine restoration database based on the real-time soil data to obtain a number of similar soil data cases;

[0054] A model building module, the model building module is electrically connected to the model building module and the storage module, and the model building module is used to use the restoration effect data and restoration process data of similar soil data cases as sample data to build a restoration effect regression model for the area to be restored;

[0055] A repair prediction analysis module, the repair prediction analysis module is electrically connected to the model building module, the repair prediction analysis module is used to determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determine the repair process data through a repair effect regression model of the area to be repaired;

[0056] A feedback optimization module is electrically connected to the repair prediction and analysis module, and is used to perform mine repair according to the repair process data, monitor the real-time mine repair effect, and based on the real-time mine repair effect, feedback optimize the repair effect regression model of the area to be repaired, and re-determine the repair process data based on the optimized repair effect regression model of the area to be repaired.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention proposes a mine restoration effect prediction scheme based on soil data analysis, based on the restoration performance index obtained in real time, and compares it with the data in the parameter training data set in detail. According to the comparison results, the parameter training data is updated as necessary. On this basis, the regression equation between the restoration performance and the restoration parameters is recalculated using the updated parameter training data to obtain a more optimized regression equation. This optimized model will serve as a guide to output a more sophisticated mine restoration process strategy. During the restoration process, this step-by-step update calculation process is continuously executed to ensure that the regression equation can continue to reflect the current restoration status. In this way, the optimal mine restoration process parameters can be accurately determined. Using these optimized parameters for mine restoration work can significantly improve the restoration quality and ensure the comprehensive and efficient restoration of the mine ecological environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flow chart of the mine restoration effect prediction method based on soil data analysis proposed by the present invention;

[0060] Figure 2A flow chart of a method for obtaining similar soil data cases in the present invention;

[0061] Figure 3 A flow chart of the method for constructing a restoration effect regression model of the area to be restored in the present invention;

[0062] Figure 4 A flow chart of a method for determining repair process data in the present invention;

[0063] Figure 5 A flow chart of the method for feedback optimization of the restoration effect regression model of the area to be restored in the present invention;

[0064] Figure 6 A schematic diagram of the architecture of the electronic device proposed by the present invention;

[0065] Figure 7 This is a schematic diagram of the computer-readable storage medium structure proposed by the present invention. DETAILED DESCRIPTION

[0066] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0067] Reference Figure 1 As shown in the figure, the mine restoration effect prediction method based on soil data analysis includes:

[0068] Based on all known mine restoration cases, a mine restoration database is constructed. The mine restoration database includes the initial soil data, restoration effect data and restoration process data of the mine restoration cases.

[0069] Collect soil data of the area to be repaired in real time and record it as real-time soil data;

[0070] Based on matching the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database, a number of similar soil data cases are obtained;

[0071] The restoration effect data and restoration process data of similar soil data cases are used as sample data to build a restoration effect regression model for the area to be restored.

[0072] Determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determine the repair process data through a repair effect regression model of the area to be repaired;

[0073] Carry out mine restoration according to restoration process data and monitor the real-time mine restoration effect;

[0074] Based on the real-time mine restoration effect, the restoration effect regression model of the area to be restored is fed back and optimized, and the restoration process data is re-determined based on the optimized restoration effect regression model of the area to be restored.

[0075] The feedback value is calculated through the feedback training model according to the repair performance index obtained according to the real-time repair, and compared with the data in the parameter training data. The parameter training data is updated according to the comparison result, and then the mapping model between the repair performance and the repair parameters is calculated according to the updated parameter training data. After the updated learning, the mapping model between the repair performance and the repair parameters in a more optimized state is obtained, and a more optimized mine repair process strategy is output. By gradually updating the calculation during the repair process, the optimal mine repair process parameters can be obtained according to the actual repair state. Mine repair can be carried out with these parameters, which can effectively ensure the quality of mine repair.

[0076] Reference Figure 2 As shown, based on matching the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database, several similar soil data cases are obtained, including:

[0077] Based on the real-time index value of each soil index in the collected real-time soil data and the index value of each soil index in the initial soil data of the mine remediation case, a comprehensive similarity index between the collected real-time soil data and the initial soil data of the mine remediation case is calculated;

[0078] Determine whether the comprehensive similarity index is less than a preset value. If so, the mine restoration case is regarded as a similar soil data case. If not, the mine restoration case is not regarded as a similar soil data case.

[0079] Among them, the calculation formula of the comprehensive similarity index is:

[0080]

[0081] In the formula, L is the comprehensive similarity index, A k0 is the real-time index value of the kth soil index in the real-time soil data, A k is the index value of the kth soil index in the initial soil data of the mine remediation case, and n is the total number of soil indicators.

[0082] This scheme combines actual soil environmental factors and, through similar calculation, selects several known mine restoration cases that are close to the soil environment of the mine area to be restored as similar soil data cases to design the initial restoration data. It then designs the mine restoration means in combination with actual similar situations, effectively ensuring the adaptability of the mine restoration means to the actual soil environment.

[0083] Reference Figure 3 As shown in the figure, the restoration effect data and restoration process data of similar soil data cases are used as sample data to construct a restoration effect regression model for the area to be restored, which specifically includes:

[0084] According to the influencing factors of each restoration effect of the area to be restored, a regression equation for each restoration effect is established;

[0085] Based on the regression equation of each repair effect, a loss function of each repair effect is established;

[0086] Based on the mini-batch gradient descent method, the parameter update equation of the regression equation is established;

[0087] According to the actual test situation, adjust the value of the learning rate and the number of samples in each iteration.

[0088] The regression equation of the repair effect is as follows:

[0089]

[0090] Among them, f(γ) u is the predicted value of the repair effect of the u-th repair effect, θ0 is the error constant term, θ g Model coefficients for the g-th repair process, γ g is the parameter value of the g-th repair process, α g is the model index of the g-th repair process;

[0091] The loss function of the repair effect is:

[0092]

[0093] Among them, F θ is the relationship between the predicted value and the actual value of the repair effect, m is the number of samples in the small batch sample data, is the predicted value of the repair effect of the i-th data in the sample data, f i is the actual value of the repair effect of the i-th data in the sample data;

[0094] The parameter update equation of the regression equation is:

[0095]

[0096] in, is the update parameter of the jth influencing factor of the i-th sample data, is the parameter of the jth influencing factor of the i-th sample data, α is the learning rate, γ j i is the value of the jth influencing factor of the i-th sample data.

[0097] Among them, αg The value range of α is any value among 1, 2, and 3. It can be understood that g The larger the value of , the higher the fitting power index relative to the influencing factors, the higher the fitting accuracy, and correspondingly, the higher the fitting complexity. In some embodiments, in order to reduce the difficulty of fitting, a linear regression fitting method is adopted to set α g All values ​​are 1.

[0098] Reference Figure 4 As shown, based on the repair effect requirements of the area to be repaired, the repair process data is determined by the repair effect regression model of the area to be repaired, including:

[0099] Based on the restoration effect requirement of the area to be restored, an inequality for the restoration effect requirement of the area to be restored is constructed;

[0100] Solve the repair effect requirement inequality of the area to be repaired, and obtain the parameter range of the repair process of the area to be repaired;

[0101] A repair evaluation model is constructed, and within the parameter range of the repair process of the area to be repaired, the parameters of the repair process corresponding to the maximum value of the repair evaluation model are taken as the repair process data.

[0102] The repair effect requirement inequality is as follows:

[0103] f(γ) u ≥f u0 , u=1、2、…、U

[0104] In the formula, f u0 is the required value of the repair effect of the u-th repair effect, and U is the total number of repair effect items;

[0105] The repair evaluation model is as follows:

[0106]

[0107] In the formula, β u is the emphasis weight of the u-th repair effect, P jug Output values ​​for evaluating the model.

[0108] In this scheme, on the basis that all repair prediction values ​​are greater than the repair effects, a focused evaluation method is adopted to further determine the specific repair process parameter values. That is, during the repair, a higher emphasis weight will be added to the repair effect with a higher emphasis, so that the repair direction with a higher emphasis can obtain a better repair effect, and then the determined repair parameters can better match the actual repair needs.

[0109] Reference Figure 5As shown in the figure, based on the real-time mine restoration effect, the restoration effect regression model of the area to be restored is optimized by feedback, which specifically includes:

[0110] Calculate the deviation between the real-time mine restoration effect and the restoration effect predicted by the restoration effect regression equation;

[0111] Determine whether the deviation value is greater than the preset value. If so, remove the similar soil data case corresponding to the minimum value of the comprehensive similarity index, and add the real-time mine restoration effect and restoration process data to the sample data. If not, directly add the real-time mine restoration effect and restoration process data to the sample data.

[0112] The calculation formula of the deviation value is:

[0113]

[0114] Among them, f u is the restoration effect value of the u-th real-time mine restoration effect, and C is the deviation value.

[0115] In this scheme, the real-time restoration data is fed back to optimize the model. If the deviation between the real-time mine restoration effect and the restoration effect predicted by the restoration effect regression equation is too large, it means that the current regression equation may be difficult to accurately reflect the current soil restoration status. In order to further optimize the model, the data with the largest difference from the actual soil data in the sample data is eliminated, and then the regression equation is further trained in combination with the actual modification effect to ensure that the regression equation is compatible with the actual soil data.

[0116] Furthermore, since soil data undergoes real-time dynamic changes during the mine restoration process, this solution uses a dynamic approach to optimize and update the training data.

[0117] Based on the same inventive concept as the above-mentioned mine restoration effect prediction method based on soil data analysis, this solution proposes a mine restoration effect prediction system based on soil data analysis, including:

[0118] A storage module, which is used to build a mine restoration database based on all known mine restoration cases;

[0119] A soil data collection module is used to collect soil data of the area to be repaired in real time, which is recorded as real-time soil data;

[0120] A data similarity matching module, the data similarity matching module is electrically connected to the soil data acquisition module and the storage module, and the data similarity matching module is used to match the initial soil data of the mine restoration case in the mine restoration database based on the real-time soil data to obtain a number of similar soil data cases;

[0121] A model building module, the model building module is electrically connected to the model building module and the storage module, and the model building module is used to use the restoration effect data and restoration process data of similar soil data cases as sample data to build a restoration effect regression model for the area to be restored;

[0122] A repair prediction analysis module, the repair prediction analysis module is electrically connected to the model building module, and the repair prediction analysis module is used to determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, the repair process data is determined through a repair effect regression model of the area to be repaired;

[0123] Feedback optimization module, the feedback optimization module is electrically connected to the repair prediction and analysis module, the feedback optimization module is used to perform mine repair according to the repair process data, and monitor the real-time mine repair effect, and based on the real-time mine repair effect, feedback optimize the repair effect regression model of the area to be repaired, and re-determine the repair process data based on the optimized repair effect regression model of the area to be repaired.

[0124] The working process of the above system is:

[0125] Step 1: The soil data collection module collects soil data of the area to be repaired in real time, which is recorded as real-time soil data;

[0126] Step 2: The data similarity matching module matches the initial soil data of the mine restoration case in the mine restoration database based on the real-time soil data to obtain several similar soil data cases;

[0127] Step 3: The model building module uses the restoration effect data and restoration process data of similar soil data cases as sample data to build a restoration effect regression model for the area to be restored;

[0128] Step 4: The repair prediction analysis module determines the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determines the repair process data through the repair effect regression model of the area to be repaired;

[0129] Step 5: The feedback optimization module performs mine restoration according to the restoration process data, monitors the real-time mine restoration effect, and based on the real-time mine restoration effect, feedback optimizes the restoration effect regression model of the area to be restored, and re-determines the restoration process data based on the optimized restoration effect regression model of the area to be restored.

[0130] Furthermore, the method according to the embodiment of the present application can also be performed by Figure 6 The electronic device architecture shown in FIG. Figure 6As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a mine restoration effect prediction method based on soil data analysis provided in the present application. The electronic device 500 may also include a user interface 508. Of course, Figure 6 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 6 One or more components of an electronic device are shown.

[0131] Figure 7 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 7 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the mine restoration effect prediction method based on soil data analysis according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0132] In summary, the advantages of the present invention are: the use of real-time optimization feedback to carry out mine restoration work can significantly improve the restoration quality and ensure the comprehensive and efficient restoration of the mine ecological environment.

[0133] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A mine restoration effect prediction method based on soil data analysis, characterized in that: include: Based on all known mine restoration cases, a mine restoration database is constructed, wherein the mine restoration database includes initial soil data, restoration effect data and restoration process data of the mine restoration cases; Collect soil data of the area to be repaired in real time and record it as real-time soil data; Based on matching the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database, a number of similar soil data cases are obtained; The restoration effect data and restoration process data of similar soil data cases are used as sample data to build a restoration effect regression model for the area to be restored. Determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determine the repair process data through a repair effect regression model of the area to be repaired; Carry out mine restoration according to restoration process data and monitor the real-time mine restoration effect; Based on the real-time mine restoration effect, the restoration effect regression model of the area to be restored is fed back to optimize the restoration effect regression model, and the restoration process data is re-determined based on the optimized restoration effect regression model of the area to be restored.

2. The mine restoration effect prediction method based on soil data analysis according to claim 1 is characterized in that: The method of matching the real-time soil data with the initial soil data of the mine restoration case in the mine restoration database to obtain several similar soil data cases specifically includes: Based on the real-time index value of each soil index in the collected real-time soil data and the index value of each soil index in the initial soil data of the mine remediation case, a comprehensive similarity index between the collected real-time soil data and the initial soil data of the mine remediation case is calculated; Determine whether the comprehensive similarity index is less than a preset value. If so, the mine restoration case is taken as a similar soil data case. If not, the mine restoration case is not taken as a similar soil data case. The calculation formula of the comprehensive similarity index is: In the formula, L is the comprehensive similarity index, A k0 is the real-time index value of the kth soil index in the real-time soil data, A k is the index value of the kth soil index in the initial soil data of the mine remediation case, and n is the total number of soil indicators.

3. The mine restoration effect prediction method based on soil data analysis according to claim 2 is characterized in that: The restoration effect data and restoration process data of similar soil data cases are used as sample data to construct a restoration effect regression model for the area to be restored, which specifically includes: According to the influencing factors of each restoration effect of the area to be restored, a regression equation for each restoration effect is established; Based on the regression equation of each repair effect, a loss function of each repair effect is established; Based on the mini-batch gradient descent method, the parameter update equation of the regression equation is established; According to the actual test situation, adjust the value of the learning rate and the number of samples in each iteration.

4. The mine restoration effect prediction method based on soil data analysis according to claim 3 is characterized in that: The regression equation of the repair effect is specifically: Among them, f(γ) u is the predicted value of the repair effect of the uth repair effect, θ0 is the error constant term, θ g Model coefficients for the g-th repair process, γ g is the parameter value of the g-th repair process, α g is the model index of the g-th repair process; The loss function of the repair effect is: Among them, F θ is the relationship between the predicted value and the actual value of the repair effect, m is the number of samples in the small batch sample data, is the predicted value of the repair effect of the i-th data in the sample data, f i is the actual value of the repair effect of the i-th data in the sample data; The parameter update equation of the regression equation is: in, is the update parameter of the jth influencing factor of the i-th sample data, is the parameter of the jth influencing factor of the i-th sample data, α is the learning rate, is the value of the jth influencing factor of the i-th sample data.

5. The mine restoration effect prediction method based on soil data analysis according to claim 4 is characterized in that: The repair process data determined based on the repair effect requirements of the area to be repaired by using the repair effect regression model of the area to be repaired specifically includes: Based on the restoration effect requirement of the area to be restored, an inequality for the restoration effect requirement of the area to be restored is constructed; Solve the repair effect requirement inequality of the area to be repaired, and obtain the parameter range of the repair process of the area to be repaired; A repair evaluation model is constructed, and within the parameter range of the repair process of the area to be repaired, the parameters of the repair process corresponding to the maximum value of the repair evaluation model are taken as the repair process data.

6. The mine restoration effect prediction method based on soil data analysis according to claim 5 is characterized in that: The repair effect requirement inequality is specifically: f(γ) u ≥f u0 ,u=1、2、…、U In the formula, f u0 is the required value of the repair effect of the u-th repair effect, and U is the total number of repair effect items; The repair evaluation model is specifically: In the formula, β u is the emphasis weight of the u-th repair effect, P jug Output values ​​for evaluating the model.

7. The mine restoration effect prediction method based on soil data analysis according to claim 6 is characterized in that: The restoration effect regression model based on real-time mine restoration effect and feedback optimization of the restoration area to be restored specifically includes: Calculate the deviation between the real-time mine restoration effect and the restoration effect predicted by the restoration effect regression equation; Determine whether the deviation value is greater than the preset value. If so, remove the similar soil data case corresponding to the minimum value of the comprehensive similarity index, and add the real-time mine restoration effect and restoration process data to the sample data. If not, directly add the real-time mine restoration effect and restoration process data to the sample data. The calculation formula of the deviation value is: Among them, f u is the restoration effect value of the u-th real-time mine restoration effect, and C is the deviation value.

8. A mine restoration effect prediction system based on soil data analysis, characterized in that: The method for predicting the effect of mine restoration based on soil data analysis according to any one of claims 1 to 7 comprises: A storage module, the storage module is used to build a mine restoration database based on all known mine restoration cases; A soil data collection module, which is used to collect soil data of the area to be repaired in real time, recorded as real-time soil data; A data similarity matching module, the data similarity matching module is electrically connected to the soil data acquisition module and the storage module, and the data similarity matching module is used to match the initial soil data of the mine restoration case in the mine restoration database based on the real-time soil data to obtain a number of similar soil data cases; A model building module, the model building module is electrically connected to the model building module and the storage module, and the model building module is used to use the restoration effect data and restoration process data of similar soil data cases as sample data to build a restoration effect regression model for the area to be restored; A repair prediction analysis module, the repair prediction analysis module is electrically connected to the model building module, the repair prediction analysis module is used to determine the repair effect requirements of the area to be repaired, and based on the repair effect requirements of the area to be repaired, determine the repair process data through a repair effect regression model of the area to be repaired; A feedback optimization module is electrically connected to the repair prediction and analysis module, and is used to perform mine repair according to the repair process data, monitor the real-time mine repair effect, and based on the real-time mine repair effect, feedback optimize the repair effect regression model of the area to be repaired, and re-determine the repair process data based on the optimized repair effect regression model of the area to be repaired.

9. An electronic device, characterized in that: include: at least one processor; and 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 so that the at least one processor can execute the mine restoration effect prediction method based on soil data analysis as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer-readable program stored thereon, characterized in that: When the computer-readable program is executed by a processor, the method for predicting the effect of mine restoration based on soil data analysis described in any one of claims 1 to 7 is implemented.

Images