Prediction Method for Deep Foundation Pit Monitoring Parameters Based on Neural Network

Abstract

The present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network, which relates to the technical field of deep foundation pit parameter prediction. The method includes: obtaining risk factors of the deep foundation pit and determining deep foundation pit monitoring parameters; setting the deep foundation pit monitoring frequency, obtaining deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and performing data preprocessing; obtaining a neural network algorithm for the deep foundation pit monitoring parameters, constructing a deep foundation pit monitoring parameter prediction model and training the model according to the deep foundation pit monitoring data completed by data preprocessing to obtain deep foundation pit prediction parameters, and determining a matching algorithm for the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit; obtaining the deep foundation pit prediction parameters corresponding to the matching algorithm, determining the toughness level of the deep foundation pit and implementing a deep foundation pit maintenance strategy; realizing the accurate prediction of the deep foundation pit monitoring parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of deep foundation pit parameter prediction, and particularly to a prediction method for deep foundation pit monitoring parameters based on a neural network. Background Art

[0002] With the rapid development of infrastructure construction in China, the scale of foundation pit projects is deeper and larger; deep foundation pits have problems such as complex environments, long construction periods, numerous risk factors, and high probabilities of accidents, and deep foundation pit accidents often result in serious losses; existing prediction technologies have many limitations and are difficult to accurately predict deep foundation pit monitoring parameters. In addition, there are many existing neural network algorithms, and different neural networks require different adaptation conditions.

[0003] Therefore, the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. Summary of the Invention

[0004] The present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. By obtaining the risk factors of a deep foundation pit, the deep foundation pit monitoring parameters are determined; the deep foundation pit monitoring frequency is set, and deep foundation pit monitoring data is obtained according to the deep foundation pit monitoring parameters and data preprocessing is performed; a neural network algorithm for the deep foundation pit monitoring parameters is obtained, a deep foundation pit monitoring parameter prediction model is constructed and model training is performed according to the deep foundation pit monitoring data completed by data preprocessing to obtain deep foundation pit prediction parameters, and a matching algorithm for the deep foundation pit monitoring parameters is determined according to the actual parameters of the deep foundation pit; the deep foundation pit prediction parameters corresponding to the matching algorithm are obtained, the deep foundation pit toughness level is determined and a deep foundation pit maintenance strategy is executed; accurate prediction of deep foundation pit monitoring parameters is achieved.

[0005] The present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network, including:

[0006] Step 1: Obtain the risk factors of a deep foundation pit and determine the deep foundation pit monitoring parameters;

[0007] Step 2: Set the deep foundation pit monitoring frequency, obtain deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and perform data preprocessing;

[0008] Step 3: Obtain a neural network algorithm for the deep foundation pit monitoring parameters, construct a deep foundation pit monitoring parameter prediction model and perform model training according to the deep foundation pit monitoring data completed by data preprocessing to obtain deep foundation pit prediction parameters, and determine a matching algorithm for the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit;

[0009] Step 4: Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the deep foundation pit toughness level and execute a deep foundation pit maintenance strategy.

[0010] According to the prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention, risk factors of the deep foundation pit are obtained, and deep foundation pit monitoring parameters are determined, including:

[0011] Risk factors of the deep foundation pit are obtained, and measurable parameters of the deep foundation pit are determined, where the measurable parameters include: enclosure structure deformation parameters, support force characteristics parameters, settlement parameters around the foundation pit, groundwater level change parameters, foundation pit heave parameters, and foundation pit surrounding condition parameters;

[0012] Part of the measurable parameters are selected from the measurable parameters of the deep foundation pit according to the actual monitoring equipment of the deep foundation pit and recorded as deep foundation pit monitoring parameters, where the deep foundation pit monitoring parameters include: deep foundation pit settlement monitoring parameters, deep foundation pit support end horizontal displacement monitoring parameters, and deep foundation pit support axial force monitoring parameters.

[0013] According to the prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention, the deep foundation pit monitoring frequency is set, and deep foundation pit monitoring data is obtained based on the deep foundation pit monitoring parameters and data preprocessing is performed, including:

[0014] The deep foundation pit monitoring accuracy requirement is obtained, the deep foundation pit monitoring frequency is set, and deep foundation pit monitoring data is obtained based on the deep foundation pit monitoring parameters and the actual monitoring equipment of the deep foundation pit;

[0015] Data preprocessing is performed on the deep foundation pit monitoring data, where the data preprocessing includes: data cleaning processing, data standardization processing, and data formatting processing.

[0016] According to the prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention, the neural network algorithm for deep foundation pit monitoring parameters is obtained, a deep foundation pit monitoring parameter prediction model is constructed, and model training is performed according to the deep foundation pit monitoring data completed by data preprocessing, including:

[0017] The neural network algorithm for deep foundation pit monitoring parameters is obtained, where the neural network algorithm includes: BP neural network algorithm, GA-BP neural network algorithm, NARX dynamic neural network algorithm, and Elman neural network algorithm;

[0018] A deep foundation pit monitoring parameter prediction model is constructed, and model training is respectively performed on the deep foundation pit monitoring parameter prediction model according to the deep foundation pit monitoring data completed by data preprocessing and the model parameters of the deep foundation pit monitoring parameter prediction model determined based on the neural network algorithm;

[0019] The deep foundation pit monitoring data completed by data preprocessing is sorted according to the data acquisition time of the deep foundation pit monitoring data completed by data preprocessing;

[0020] According to the data sorting result, a preset proportion of the deep foundation pit monitoring data completed by data preprocessing is selected as the training sample;

[0021] Train the prediction model of deep foundation pit monitoring parameters according to the training samples.

[0022] The prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention further includes:

[0023] Select the remaining data of the training samples in the data sorting result as the verification samples for the preprocessed deep foundation pit monitoring data, verify the prediction model of the deep foundation pit monitoring parameters, and obtain the prediction accuracy of the prediction model of the deep foundation pit monitoring parameters;

[0024] When the prediction accuracy of the prediction model of the deep foundation pit monitoring parameters is not lower than the set accuracy, it is determined that the model training of the prediction model of the deep foundation pit monitoring parameters is completed.

[0025] According to the prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention, obtain the deep foundation pit prediction parameters, and determine the matching algorithm of the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit, including:

[0026] Predict the deep foundation pit monitoring parameters according to the prediction model of the deep foundation pit monitoring parameters with completed model training, and obtain the deep foundation pit prediction parameters;

[0027] Obtain the actual parameters of the deep foundation pit according to the training samples and the verification samples, determine the error value between the actual parameters of the deep foundation pit and the predicted parameters of the deep foundation pit, and select the neural network algorithm corresponding to the smallest error value, which is recorded as the matching algorithm of the deep foundation pit monitoring parameters.

[0028] According to the prediction method of deep foundation pit monitoring parameters based on neural network provided by the present invention, obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the toughness level of the deep foundation pit and execute the deep foundation pit maintenance strategy, including:

[0029] Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm;

[0030] Obtain the parameter increment of the actual parameters of the deep foundation pit, and record the parameter increment as an independent parameter according to the parameter type of the deep foundation pit monitoring parameters and perform a normality test;

[0031] Obtain the parameter test value of the normality test. When the parameter test value is not lower than the preset test value, it is determined that the corresponding independent parameter conforms to the normal distribution;

[0032] Perform interval division analysis on the corresponding independent parameters that conform to the normal distribution to obtain the toughness influencing factors of the deep foundation pit, where the toughness influencing factors include: robustness influencing factors, redundancy influencing factors, restorability influencing factors, intelligence influencing factors, and adaptability influencing factors;

[0033] Obtain the predicted expected value and predicted standard deviation of the deep foundation pit prediction parameters according to the normality test;

[0034] Divide the interval levels according to the predicted expected value and predicted standard deviation, and record the interval corresponding to plus or minus 1 times the predicted standard deviation near the predicted expected value as the level 1 interval;

[0035] Record the interval corresponding to plus or minus 2 times the predicted standard deviation near the predicted expected value as the level 2 interval;

[0036] Record the interval corresponding to plus or minus 3 times the predicted standard deviation near the predicted expected value as the level 3 interval;

[0037] Record the interval outside the 3 intervals as the level 4 interval;

[0038] Determine the toughness level of the deep foundation pit according to the toughness influencing factors of the deep foundation pit and the deep foundation pit prediction parameters, and implement the deep foundation pit maintenance strategy.

[0039] According to the prediction method of the deep foundation pit monitoring parameters provided by the present invention, it further includes:

[0040] Determine the toughness evaluation index of the deep foundation pit according to the measurable parameters of the deep foundation pit, establish an evaluation index matrix, and conduct a comprehensive toughness evaluation of the deep foundation pit. Among them, the toughness evaluation index of the deep foundation pit includes: the evaluation index of the deformation of the retaining structure, the evaluation index of the stress characteristics of the support, the evaluation index of the settlement around the foundation pit, the evaluation index of the change of the groundwater level, the evaluation index of the foundation pit heave, and the evaluation index of the surrounding conditions of the foundation pit;

[0041] Perform dimensionless processing on the evaluation index matrix;

[0042] According to the weight scoring of the toughness evaluation index of the deep foundation pit by experts, determine the subjective weight of the toughness evaluation index of the deep foundation pit;

[0043] Obtain the coefficient of variation value according to the predicted expected value and predicted standard deviation, and determine the objective weight of the toughness evaluation index of the deep foundation pit;

[0044] Set the weight coefficient of the subjective weight for the index weight and the weight coefficient of the objective weight for the index weight, and determine the index weight of the toughness evaluation index of the deep foundation pit;

[0045] Obtain the toughness evaluation distance according to the toughness evaluation index of the deep foundation pit and the index weight of the toughness evaluation index of the deep foundation pit, and conduct dimensionless processing to determine the final toughness evaluation distance;

[0046] ; where d represents the final toughness evaluation distance; a1 represents the weight coefficient of the subjective weight for the index weight; w1i1 represents the subjective weight of the i1th toughness evaluation index of the deep foundation pit; It represents the objective weight of the i1-th deep foundation pit resilience evaluation index; si1 represents the average value of the i1-th deep foundation pit resilience evaluation index; ui1 represents the variance of the i1-th deep foundation pit resilience evaluation index; xi1j1 represents the quantization value of the j1-th level of the i1-th deep foundation pit resilience evaluation index; j1 represents the interval level, taking values 1, 2, 3, 4; u1 represents the predicted expected value; It represents the predicted standard deviation; n1 represents the number of deep foundation pit resilience evaluation indexes;

[0047] According to the actual parameters of the deep foundation pit, the final resilience evaluation distance is corresponded with the deep foundation pit resilience level to determine the final resilience evaluation distance - deep foundation pit resilience level mapping table;

[0048] Obtain the predicted final resilience evaluation distance corresponding to the deep foundation pit prediction parameters and the predicted deep foundation pit resilience level, and make a corresponding determination according to the final resilience evaluation distance - deep foundation pit resilience level mapping table. If it is determined that the predicted final resilience evaluation distance corresponds to the predicted deep foundation pit resilience level, then the deep foundation pit resilience level determined according to the deep foundation pit prediction parameters is accurate.

[0049] Compared with the prior art, the beneficial effects of the present application are as follows:

[0050] By obtaining the risk factors of the deep foundation pit, determine the deep foundation pit monitoring parameters; set the deep foundation pit monitoring frequency, obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and perform data preprocessing; obtain the neural network algorithm for the deep foundation pit monitoring parameters, construct the deep foundation pit monitoring parameter prediction model and perform model training according to the deep foundation pit monitoring data completed by the data preprocessing, obtain the deep foundation pit prediction parameters, determine the matching algorithm of the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit; obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the deep foundation pit resilience level and execute the deep foundation pit maintenance strategy; realize the accurate prediction of the deep foundation pit monitoring parameters.

[0051] Other features and advantages of the present invention will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0052] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0053] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0054] Figure 1It is a schematic flowchart of a prediction method for deep foundation pit monitoring parameters based on a neural network provided by an embodiment of the present invention. Detailed implementation manners

[0055] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for illustrating and explaining the present invention, and are not used to limit the present invention.

[0056] Embodiment 1:

[0057] An embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. As Figure 1 shown, it includes:

[0058] Step 1: Obtain the risk factors of the deep foundation pit and determine the deep foundation pit monitoring parameters;

[0059] Step 2: Set the deep foundation pit monitoring frequency, and obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and perform data preprocessing;

[0060] Step 3: Obtain the neural network algorithm for the deep foundation pit monitoring parameters, construct a deep foundation pit monitoring parameter prediction model, and perform model training according to the deep foundation pit monitoring data completed by data preprocessing to obtain the deep foundation pit prediction parameters, and determine the matching algorithm for the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit;

[0061] Step 4: Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the deep foundation pit toughness level, and execute the deep foundation pit maintenance strategy.

[0062] In this embodiment, the risk factor refers to the factor that affects the toughness of the deep foundation pit.

[0063] In this embodiment, the deep foundation pit monitoring parameter refers to the measurable parameter for analyzing the toughness of the deep foundation pit, and is the parameter obtained by selecting part of the measurable parameters from the measurable parameters of the deep foundation pit.

[0064] In this embodiment, the deep foundation pit monitoring frequency refers to the frequency of monitoring the deep foundation pit monitoring parameters.

[0065] In this embodiment, the deep foundation pit monitoring data refers to the data obtained according to the deep foundation pit monitoring parameters and the actual monitoring equipment of the deep foundation pit.

[0066] In this embodiment, the neural network algorithm refers to the algorithm used for predicting the deep foundation pit monitoring parameters.

[0067] In this embodiment, the deep foundation pit monitoring parameter prediction model refers to the model used for predicting the deep foundation pit monitoring parameters.

[0068] In this embodiment, the deep foundation pit prediction parameter refers to the prediction data obtained by predicting the deep foundation pit monitoring parameters using the deep foundation pit monitoring parameter prediction model completed by model training.

[0069] In this embodiment, the matching algorithm refers to the optimal neural network algorithm for predicting the monitoring parameters of deep foundation pits.

[0070] In this embodiment, the toughness level of the deep foundation pit refers to the level of stable operation of the deep foundation pit.

[0071] In this embodiment, the maintenance strategy of the deep foundation pit refers to the strategy for ensuring the stable operation of the deep foundation pit.

[0072] The working principle and beneficial effects of the above technical solution are as follows: By obtaining the risk factors of the deep foundation pit, the monitoring parameters of the deep foundation pit are determined; the monitoring frequency of the deep foundation pit is set, and the monitoring data of the deep foundation pit are obtained according to the monitoring parameters of the deep foundation pit and data preprocessing is performed; the neural network algorithm for the monitoring parameters of the deep foundation pit is obtained, a prediction model for the monitoring parameters of the deep foundation pit is constructed and the model is trained according to the monitoring data of the deep foundation pit completed by data preprocessing to obtain the prediction parameters of the deep foundation pit, and the matching algorithm for the monitoring parameters of the deep foundation pit is determined according to the actual parameters of the deep foundation pit; the prediction parameters of the deep foundation pit corresponding to the matching algorithm are obtained, the toughness level of the deep foundation pit is determined and the maintenance strategy of the deep foundation pit is executed; accurate prediction of the monitoring parameters of the deep foundation pit is achieved.

[0073] Embodiment 2:

[0074] The embodiment of the present invention provides a method for predicting the monitoring parameters of a deep foundation pit based on a neural network, which obtains the risk factors of the deep foundation pit and determines the monitoring parameters of the deep foundation pit, including:

[0075] Obtain the risk factors of the deep foundation pit and determine the measurable parameters of the deep foundation pit. Among them, the measurable parameters include: the deformation parameters of the retaining structure, the stress characteristic parameters of the support, the settlement parameters around the foundation pit, the change parameters of the groundwater level, the heave parameters of the foundation pit, and the condition parameters around the foundation pit;

[0076] Select some monitoring parameters from the measurable parameters of the deep foundation pit according to the actual monitoring equipment of the deep foundation pit, and record them as the monitoring parameters of the deep foundation pit. Among them, the monitoring parameters of the deep foundation pit include: the settlement monitoring parameters of the deep foundation pit, the horizontal displacement monitoring parameters of the support end of the deep foundation pit, and the axial force monitoring parameters of the support of the deep foundation pit.

[0077] In this embodiment, the risk factor refers to the factor that affects the toughness of the deep foundation pit.

[0078] In this embodiment, the measurable parameter refers to the measurable parameter determined according to the risk factor, that is, the specific risk factor of the deep foundation pit is determined through the measurable parameter.

[0079] In this embodiment, the monitoring parameter of the deep foundation pit refers to the measurable parameter for analyzing the toughness of the deep foundation pit, which is the parameter obtained by selecting some monitoring parameters from the measurable parameters of the deep foundation pit.

[0080] In this embodiment, the deep foundation pit settlement monitoring parameters belong to the settlement parameters around the foundation pit; the horizontal displacement monitoring parameters at the end of the deep foundation pit support belong to the deformation parameters of the retaining structure; the axial force monitoring parameters of the deep foundation pit support belong to the support force characteristic parameters.

[0081] In this embodiment, some monitoring parameters are selected from the measurable parameters of the deep foundation pit. Among them, the deep foundation pit settlement monitoring parameters, the horizontal displacement monitoring parameters at the end of the deep foundation pit support, and the axial force monitoring parameters of the deep foundation pit support are the key parameters affecting the toughness of the deep foundation pit. Only the above parameters are selected for simplified analysis, and monitoring parameters can be added according to the analysis requirements later.

[0082] The working principle and beneficial effects of the above technical solution are: by obtaining the risk factors of the deep foundation pit and determining the deep foundation pit monitoring parameters, it lays a data foundation for subsequent prediction of the deep foundation pit monitoring parameters.

[0083] Embodiment 3:

[0084] The embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. Set the deep foundation pit monitoring frequency, obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and perform data preprocessing, including:

[0085] Obtain the deep foundation pit monitoring accuracy requirement, set the deep foundation pit monitoring frequency, and obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and the actual deep foundation pit monitoring equipment;

[0086] Perform data preprocessing on the deep foundation pit monitoring data. Among them, the data preprocessing includes: data cleaning processing, data standardization processing, and data formatting processing.

[0087] In this embodiment, the deep foundation pit monitoring accuracy requirement refers to the accuracy requirement for monitoring the deep foundation pit monitoring parameters.

[0088] In this embodiment, the deep foundation pit monitoring frequency refers to the frequency of monitoring the deep foundation pit monitoring parameters, which is determined according to the deep foundation pit monitoring accuracy. For example, the deep foundation pit monitoring frequency is once every two days.

[0089] In this embodiment, the actual deep foundation pit monitoring equipment refers to the equipment used to monitor the deep foundation pit monitoring parameters. For example, an infrared monitoring device.

[0090] In this embodiment, the deep foundation pit monitoring data refers to the data obtained according to the deep foundation pit monitoring parameters and the actual deep foundation pit monitoring equipment. Usually, 1 year of monitoring data is obtained.

[0091] The working principle and beneficial effects of the above technical solution are: by setting the deep foundation pit monitoring frequency, obtaining the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and performing data preprocessing, the accuracy of the deep foundation pit monitoring data is ensured.

[0092] Embodiment 4:

[0093] The embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. The neural network algorithm for deep foundation pit monitoring parameters is obtained, a deep foundation pit monitoring parameter prediction model is constructed, and model training is performed according to the deep foundation pit monitoring data completed by data preprocessing, including:

[0094] Obtain the neural network algorithm for deep foundation pit monitoring parameters, where the neural network algorithm includes: BP neural network algorithm, GA-BP neural network algorithm, NARX dynamic neural network algorithm, and Elman neural network algorithm;

[0095] Construct a deep foundation pit monitoring parameter prediction model, and perform model training on the deep foundation pit monitoring parameter prediction model respectively according to the deep foundation pit monitoring data completed by data preprocessing and the model parameters of the deep foundation pit monitoring parameter prediction model determined based on the neural network algorithm;

[0096] Sort the deep foundation pit monitoring data completed by data preprocessing according to the data acquisition time of the deep foundation pit monitoring data completed by data preprocessing;

[0097] Select a preset proportion of the deep foundation pit monitoring data completed by data preprocessing as training samples according to the data sorting result;

[0098] Perform model training on the deep foundation pit monitoring parameter prediction model according to the training samples.

[0099] In this embodiment, for the neural network algorithm for deep foundation pit monitoring parameters, different neural networks require different adaptation conditions. Therefore, 4 neural network algorithms are selected to determine the optimal neural network algorithm for deep foundation pit monitoring parameter prediction.

[0100] In this embodiment, the deep foundation pit monitoring parameter prediction model refers to the model used for deep foundation pit monitoring parameter prediction.

[0101] In this embodiment, based on the neural network algorithm, the model parameters of the deep foundation pit monitoring parameter prediction model are determined, and model training is performed on the deep foundation pit monitoring parameter prediction model respectively. Different neural network algorithms correspond to different model parameters, and the model training results are also different.

[0102] In this embodiment, the model parameters refer to the parameters of the deep foundation pit monitoring parameter prediction model, such as input layer parameters, hidden layer parameters, and output layer parameters.

[0103] In this embodiment, data sorting refers to sorting according to the data acquisition time. The longer the data acquisition time, the higher the sorting.

[0104] In this embodiment, the training samples refer to the samples used for model training of the deep foundation pit monitoring parameter prediction model.

[0105] In this embodiment, a preset proportion of the deep foundation pit monitoring data that has completed data preprocessing is selected as the training sample according to the data sorting result. For example, the first 0.7 proportion of the deep foundation pit monitoring data for one year, that is, the deep foundation pit monitoring data for the first 245 days, is selected as the training sample.

[0106] The working principle and beneficial effects of the above technical solution are: By obtaining the neural network algorithm for deep foundation pit monitoring parameters, a prediction model for deep foundation pit monitoring parameters is constructed and the model is trained according to the deep foundation pit monitoring data that has completed data preprocessing, laying a model foundation for subsequent prediction of deep foundation pit monitoring parameters.

[0107] Embodiment 5:

[0108] The embodiment of the present invention provides a method for predicting deep foundation pit monitoring parameters based on a neural network, further including:

[0109] The remaining deep foundation pit monitoring data that has completed data preprocessing selected from the data sorting result is used as a validation sample to verify the prediction model for deep foundation pit monitoring parameters, and the prediction accuracy of the prediction model for deep foundation pit monitoring parameters is obtained;

[0110] When the prediction accuracy of the prediction model for deep foundation pit monitoring parameters is not lower than the set accuracy, it is determined that the model training of the prediction model for deep foundation pit monitoring parameters is completed.

[0111] In this embodiment, the validation sample refers to the sample used to verify the prediction model for deep foundation pit monitoring parameters.

[0112] In this embodiment, the remaining deep foundation pit monitoring data that has completed data preprocessing selected from the data sorting result is used as a validation sample. For example, the last 0.3 proportion of the deep foundation pit monitoring data for one year, that is, the deep foundation pit monitoring data for the last 105 days, is selected as the validation sample.

[0113] In this embodiment, the prediction accuracy refers to the accuracy of the prediction model for deep foundation pit monitoring parameters in predicting deep foundation pit monitoring parameters, which is determined according to the ratio of the output value of the prediction model for deep foundation pit monitoring parameters to the data of the validation sample. That is, the closer the output value is to the validation sample, the higher the prediction accuracy.

[0114] In this embodiment, the set accuracy refers to the set value used to determine whether the model training of the prediction model for deep foundation pit monitoring parameters is completed.

[0115] The working principle and beneficial effects of the above technical solution are: By obtaining the validation sample and verifying the prediction model for deep foundation pit monitoring parameters, the effectiveness and accuracy of the model training of the prediction model for deep foundation pit monitoring parameters are ensured.

[0116] Embodiment 6:

[0117] An embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. The method includes obtaining deep foundation pit prediction parameters and determining a matching algorithm for the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit, including:

[0118] Predicting the deep foundation pit monitoring parameters using the deep foundation pit monitoring parameter prediction model that has completed model training to obtain deep foundation pit prediction parameters;

[0119] Obtaining the actual parameters of the deep foundation pit according to the training samples and validation samples, determining the error value between the actual parameters of the deep foundation pit and the predicted parameters of the deep foundation pit, and selecting the neural network algorithm corresponding to the smallest error value as the matching algorithm for the deep foundation pit monitoring parameters.

[0120] In this embodiment, the deep foundation pit prediction parameters refer to the prediction data obtained by predicting the deep foundation pit monitoring parameters using the deep foundation pit monitoring parameter prediction model that has completed model training.

[0121] In this embodiment, the deep foundation pit prediction parameters obtained by different neural network algorithms are different.

[0122] In this embodiment, the actual parameters of the deep foundation pit refer to the monitoring parameters during the actual operation of the deep foundation pit, which can be obtained according to the training samples and validation samples.

[0123] In this embodiment, the matching algorithm refers to the optimal neural network algorithm for predicting the deep foundation pit monitoring parameters. For example, if the error value between the deep foundation pit prediction parameters corresponding to the GA-BP neural network algorithm and the actual parameters of the deep foundation pit is the smallest, then the GA-BP neural network algorithm is recorded as the matching algorithm for the deep foundation pit monitoring parameters.

[0124] The working principle and beneficial effects of the above technical solution are: By obtaining the deep foundation pit prediction parameters and determining the matching algorithm for the deep foundation pit monitoring parameters according to the actual parameters of the deep foundation pit, it lays a neural network algorithm foundation for subsequent prediction of the deep foundation pit monitoring parameters.

[0125] Example 7:

[0126] An embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network. The method includes obtaining the deep foundation pit prediction parameters corresponding to the matching algorithm, determining the toughness level of the deep foundation pit, and implementing the deep foundation pit maintenance strategy, including:

[0127] Obtaining the deep foundation pit prediction parameters corresponding to the matching algorithm;

[0128] Obtaining the parameter increment of the actual parameters of the deep foundation pit, recording the parameter increment as an independent parameter according to the parameter type of the deep foundation pit monitoring parameters, and performing a normality test;

[0129] Obtaining the parameter test value of the normality test. When the parameter test value is not lower than the preset test value, it is determined that the corresponding independent parameter conforms to the normal distribution;

[0130] Perform interval division analysis on the corresponding independent parameters that conform to the normal distribution to obtain the toughness influencing factors of the deep foundation pit. Among them, the toughness influencing factors include: robustness influencing factors, redundancy influencing factors, restorability influencing factors, intelligence influencing factors, and adaptability influencing factors;

[0131] Obtain the predicted expected value and predicted standard deviation of the deep foundation pit prediction parameters according to the normality test;

[0132] Divide the interval levels according to the predicted expected value and predicted standard deviation, and record the interval corresponding to plus or minus 1 times the predicted standard deviation near the predicted expected value as the level 1 interval;

[0133] Record the interval corresponding to plus or minus 2 times the predicted standard deviation near the predicted expected value as the level 2 interval;

[0134] Record the interval corresponding to plus or minus 3 times the predicted standard deviation near the predicted expected value as the level 3 interval;

[0135] Record the interval outside the 3 intervals as the level 4 interval;

[0136] Determine the toughness level of the deep foundation pit according to the toughness influencing factors of the deep foundation pit and the deep foundation pit prediction parameters, and implement the deep foundation pit maintenance strategy.

[0137] In this embodiment, the parameter type refers to the type of deep foundation pit monitoring parameters. For example, the deep foundation pit settlement monitoring parameter type, the deep foundation pit support end horizontal displacement monitoring parameter type, and the deep foundation pit support axial force monitoring parameter type.

[0138] In this embodiment, the parameter increment refers to the parameter value determined according to the difference between the deep foundation pit prediction parameter and the deep foundation pit actual parameter.

[0139] In this embodiment, the independent parameter refers to the parameter increment of the deep foundation pit actual parameter determined by the parameter type of the deep foundation pit monitoring parameter. For example, the deep foundation pit settlement monitoring independent parameter, the deep foundation pit support end horizontal displacement monitoring independent parameter, and the deep foundation pit support axial force monitoring independent parameter.

[0140] In this embodiment, the normality test refers to testing whether the independent parameter conforms to the normal distribution, and performing the normality test according to the expected value and standard deviation of the independent parameter.

[0141] In this embodiment, the parameter test value refers to the value obtained according to the expected value and standard deviation of the independent parameter for determining whether the independent parameter conforms to the normal distribution. When the parameter test value is not lower than the preset test value, for example, the parameter test value is not lower than 0.05, it is determined that the corresponding independent parameter conforms to the normal distribution.

[0142] In this embodiment, the interval division analysis of the corresponding independent parameters conforming to the normal distribution refers to dividing the interval levels and analyzing the interval levels where the independent parameters are located.

[0143] In this embodiment, the toughness influencing factors refer to the factors that affect the toughness level of the deep foundation pit.

[0144] In this embodiment, the predicted expected value refers to the expected value obtained by the deep foundation pit prediction parameters according to the normality test; the predicted standard deviation refers to the standard deviation obtained by the deep foundation pit prediction parameters according to the normality test.

[0145] In this embodiment, the interval level refers to the level determined according to the predicted expected value and the predicted standard deviation, and is used to determine the toughness level of the deep foundation pit subsequently.

[0146] In this embodiment, the toughness level of the deep foundation pit refers to the level of the stable operation of the deep foundation pit. The higher the toughness level of the deep foundation pit, the safer and more stable the operation of the deep foundation pit.

[0147] In this embodiment, the level 1 interval refers to the interval corresponding to the poor operation of the deep foundation pit; the level 2 interval refers to the interval corresponding to the relatively poor operation of the deep foundation pit; the level 3 interval refers to the interval corresponding to the relatively good operation of the deep foundation pit; the level 4 interval refers to the interval corresponding to the excellent operation of the deep foundation pit.

[0148] In this embodiment, the toughness level of the deep foundation pit is determined according to the toughness influencing factors of the deep foundation pit and the deep foundation pit prediction parameters. For example, the corresponding deep foundation pit prediction parameters are obtained according to the toughness influencing factors of the deep foundation pit. If the deep foundation pit prediction parameters are in the level 1 interval, the toughness level of the deep foundation pit is level 1; if the deep foundation pit prediction parameters are in the level 2 interval, the toughness level of the deep foundation pit is level 2.

[0149] In this embodiment, the deep foundation pit maintenance strategy refers to the strategy used to ensure the stable operation of the deep foundation pit.

[0150] The working principle and beneficial effects of the above technical solution are: by obtaining the deep foundation pit prediction parameters corresponding to the matching algorithm, determining the toughness level of the deep foundation pit and executing the deep foundation pit maintenance strategy, the accurate prediction of the deep foundation pit monitoring parameters is realized, and the safe operation of the deep foundation pit is ensured.

[0151] Embodiment 8:

[0152] The embodiment of the present invention provides a prediction method for deep foundation pit monitoring parameters based on a neural network, further including:

[0153] Determine the toughness evaluation index of the deep foundation pit according to the measurable parameters of the deep foundation pit, establish an evaluation index matrix, and conduct a comprehensive toughness evaluation of the deep foundation pit. Among them, the toughness evaluation index of the deep foundation pit includes: the evaluation index of the deformation of the retaining structure, the evaluation index of the stress characteristics of the support, the evaluation index of the settlement around the foundation pit, the evaluation index of the change in the groundwater level, the evaluation index of the foundation pit heave, and the evaluation index of the surrounding conditions of the foundation pit;

[0154] Dimensionalize the evaluation index matrix;

[0155] According to the weights scored by experts for the deep foundation pit toughness evaluation indexes, determine the subjective weights of the deep foundation pit toughness evaluation indexes;

[0156] Obtain the coefficient of variation value according to the predicted expected value and the predicted standard deviation, and determine the objective weights of the deep foundation pit toughness evaluation indexes;

[0157] Set the weight coefficient of the subjective weight for the index weight and the weight coefficient of the objective weight for the index weight, and determine the index weight of the deep foundation pit toughness evaluation index;

[0158] Obtain the toughness evaluation distance according to the deep foundation pit toughness evaluation index and the index weight of the deep foundation pit toughness evaluation index, and perform dimensionless processing to determine the final toughness evaluation distance;

[0159] ; where d represents the final toughness evaluation distance; a1 represents the weight coefficient of the subjective weight for the index weight; w1i1 represents the subjective weight of the i1-th deep foundation pit toughness evaluation index; represents the objective weight of the i1-th deep foundation pit toughness evaluation index; si1 represents the average value of the i1-th deep foundation pit toughness evaluation index; ui1 represents the variance of the i1-th deep foundation pit toughness evaluation index; xi1j1 represents the quantization value of the j1-th level of the i1-th deep foundation pit toughness evaluation index; j1 represents the interval level, taking values 1, 2, 3, 4; u1 represents the predicted expected value; represents the predicted standard deviation; n1 represents the number of deep foundation pit toughness evaluation indexes;

[0160] Correspond the final toughness evaluation distance with the deep foundation pit toughness level according to the actual parameters of the deep foundation pit, and determine the final toughness evaluation distance - deep foundation pit toughness level mapping table;

[0161] Obtain the predicted final toughness evaluation distance corresponding to the deep foundation pit prediction parameters and the predicted deep foundation pit toughness level, and perform corresponding determination according to the final toughness evaluation distance - deep foundation pit toughness level mapping table. If it is determined that the predicted final toughness evaluation distance corresponds to the predicted deep foundation pit toughness level, then the deep foundation pit toughness level determined according to the deep foundation pit prediction parameters is accurate.

[0162] In this embodiment, the deep foundation pit toughness evaluation index refers to the index used to evaluate the toughness of the deep foundation pit, which is determined according to the measurable parameters of the deep foundation pit, including: the evaluation index of the enclosure structure deformation, the evaluation index of the support force characteristics, the evaluation index of the settlement around the foundation pit, the evaluation index of the groundwater level change, the evaluation index of the foundation pit heave, and the evaluation index of the surrounding conditions of the foundation pit.

[0163] In this embodiment, the evaluation index matrix refers to the matrix determined according to the deep foundation pit toughness evaluation indexes and is used for subsequent calculations.

[0164] In this embodiment, the evaluation index matrix is dimensionless processed to simplify the calculation.

[0165] In this embodiment, the subjective weight refers to the index weight value determined according to the weight scores given by experts for the deep foundation pit toughness evaluation indexes.

[0166] In this embodiment, the objective weight refers to the index weight value determined according to the coefficient of variation value.

[0167] In this embodiment, the coefficient of variation value refers to the absolute value reflecting the data dispersion degree of the deep foundation pit prediction parameters and is determined according to the prediction expected value and the prediction standard deviation.

[0168] In this embodiment, the weight coefficient refers to the influence value of the subjective weight and the objective weight on the index weight.

[0169] In this embodiment, the index weight refers to the influence weight value of the deep foundation pit toughness evaluation indexes.

[0170] In this embodiment, the toughness evaluation distance refers to the distance value obtained according to the deep foundation pit toughness evaluation indexes and the index weights of the deep foundation pit toughness evaluation indexes for the deep foundation pit toughness evaluation. It refers to the relative distance between the evaluation value and the optimal value. The deep foundation pit toughness is reflected according to the toughness evaluation distance, that is, the smaller the toughness evaluation distance, the higher the corresponding deep foundation pit toughness.

[0171] In this embodiment, the final toughness evaluation distance refers to the data determined by dimensionless processing the toughness evaluation distance.

[0172] In this embodiment, the final toughness evaluation distance - deep foundation pit toughness grade mapping table refers to the mapping table obtained by corresponding the final toughness evaluation distance with the deep foundation pit toughness grade according to the actual parameters of the deep foundation pit and is used to determine whether the deep foundation pit toughness grade determined according to the deep foundation pit prediction parameters is accurate.

[0173] In this embodiment, the predicted final toughness evaluation distance refers to the final toughness evaluation distance obtained according to the deep foundation pit prediction parameters; the predicted deep foundation pit toughness grade refers to the deep foundation pit toughness grade obtained according to the deep foundation pit prediction parameters.

[0174] In this embodiment, corresponding determination is made according to the mapping table of the distance to the toughness level of the deep foundation pit for the final toughness evaluation. For example, when predicting the final toughness evaluation distance d1, corresponding determination is made according to the mapping table of the distance to the toughness level of the deep foundation pit for the final toughness evaluation, and the corresponding toughness level of the deep foundation pit is determined to be level 1. If the predicted toughness level of the deep foundation pit is level 1, it is determined that the predicted final toughness evaluation distance corresponds to the predicted toughness level of the deep foundation pit, and thus the toughness level of the deep foundation pit determined according to the predicted parameters of the deep foundation pit is accurate; if the predicted toughness level of the deep foundation pit is not level 1, it is determined that the predicted final toughness evaluation distance does not correspond to the predicted toughness level of the deep foundation pit, and thus the toughness level of the deep foundation pit determined according to the predicted parameters of the deep foundation pit is inaccurate. The toughness level of the deep foundation pit corresponding to the predicted final toughness evaluation distance is used as the toughness level of the deep foundation pit determined according to the predicted parameters of the deep foundation pit.

[0175] The working principle and beneficial effects of the above technical solution are as follows: By determining the toughness evaluation index of the deep foundation pit, establishing an evaluation index matrix, and determining the final toughness evaluation distance, the accuracy of the toughness level of the deep foundation pit determined according to the predicted parameters of the deep foundation pit is ensured.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A prediction method for deep foundation pit monitoring parameters based on neural network, characterized in that: include: Step 1: Obtain risk factors of deep foundation pits and determine monitoring parameters of deep foundation pits; Step 2: Set the deep foundation pit monitoring frequency, obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters, and perform data preprocessing; Step 3: Obtain the neural network algorithm of deep foundation pit monitoring parameters, build a deep foundation pit monitoring parameter prediction model and perform model training based on the deep foundation pit monitoring data after data preprocessing, obtain the deep foundation pit prediction parameters, and determine the matching algorithm of the deep foundation pit monitoring parameters based on the actual parameters of the deep foundation pit; Step 4: Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the deep foundation pit toughness level and implement the deep foundation pit maintenance strategy; Among them, risk factors refer to factors that affect the toughness of deep foundation pits. Deep foundation pit monitoring parameters refer to the parameters that can be monitored for analyzing the toughness of deep foundation pits, and are obtained by selecting some monitoring parameters from the monitorable parameters of deep foundation pits; Among them, the neural network algorithm for obtaining deep foundation pit monitoring parameters, building a deep foundation pit monitoring parameter prediction model and performing model training based on the deep foundation pit monitoring data after data preprocessing, including: A neural network algorithm for obtaining deep foundation pit monitoring parameters, wherein the neural network algorithm includes: BP neural network algorithm, GA-BP neural network algorithm, NARX dynamic neural network algorithm and Elman neural network algorithm; A deep foundation pit monitoring parameter prediction model is constructed, and model parameters of the deep foundation pit monitoring parameter prediction model are determined based on the deep foundation pit monitoring data after data preprocessing and the neural network algorithm, and model training is performed on the deep foundation pit monitoring parameter prediction model; sorting the deep foundation pit monitoring data after data preprocessing according to the data acquisition time of the deep foundation pit monitoring data after data preprocessing; According to the data sorting results, the deep foundation pit monitoring data with a preset proportion of data preprocessing is selected as training samples; The deep foundation pit monitoring parameter prediction model is trained based on the training samples.

2. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 1 is characterized in that: Obtain risk factors for deep foundation pits and determine monitoring parameters for deep foundation pits, including: Obtain risk factors for deep foundation pits and determine the monitorable parameters of deep foundation pits, including deformation parameters of retaining structures, stress characteristic parameters of supports, settlement parameters around foundation pits, groundwater level change parameters, foundation pit uplift parameters, and parameters of conditions around foundation pits; According to the actual monitoring equipment of the deep foundation pit, some monitoring parameters are selected from the monitorable parameters of the deep foundation pit and recorded as deep foundation pit monitoring parameters, wherein the deep foundation pit monitoring parameters include: deep foundation pit settlement monitoring parameters, deep foundation pit support end horizontal displacement monitoring parameters and deep foundation pit support axial force monitoring parameters.

3. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 1 is characterized in that: Set the deep foundation pit monitoring frequency, obtain the deep foundation pit monitoring data according to the deep foundation pit monitoring parameters and perform data preprocessing, including: Obtain the deep foundation pit monitoring accuracy requirements, set the deep foundation pit monitoring frequency, and obtain the deep foundation pit monitoring data based on the deep foundation pit monitoring parameters and the actual deep foundation pit monitoring equipment; The deep foundation pit monitoring data is preprocessed, wherein the data preprocessing includes: data cleaning processing, data standardization processing and data formatting processing.

4. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 1 is characterized in that: Also includes: The deep foundation pit monitoring data after data preprocessing of the remaining training samples in the data sorting results are selected as verification samples, and the deep foundation pit monitoring parameter prediction model is verified to obtain the prediction accuracy of the deep foundation pit monitoring parameter prediction model; When the prediction accuracy of the deep foundation pit monitoring parameter prediction model is not lower than the set accuracy, it is determined that the model training of the deep foundation pit monitoring parameter prediction model is completed.

5. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 4 is characterized in that: Obtain the predicted parameters of deep foundation pits and determine the matching algorithm of deep foundation pit monitoring parameters according to the actual parameters of deep foundation pits, including: The deep foundation pit monitoring parameters are predicted according to the deep foundation pit monitoring parameter prediction model after model training, so as to obtain the deep foundation pit prediction parameters; The actual parameters of the deep foundation pit are obtained according to the training samples and the verification samples, the error value between the actual parameters of the deep foundation pit and the predicted parameters of the deep foundation pit is determined, and the neural network algorithm corresponding to the smallest error value is selected, which is recorded as the matching algorithm of the deep foundation pit monitoring parameters.

6. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 1 is characterized in that: Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm, determine the deep foundation pit toughness level and implement the deep foundation pit maintenance strategy, including: Obtain the deep foundation pit prediction parameters corresponding to the matching algorithm; Obtain the parameter increment of the actual parameters of the deep foundation pit, record the parameter increment as an independent parameter according to the parameter type of the deep foundation pit monitoring parameters, and perform a normality test; Obtain the parameter test value of the normality test. When the parameter test value is not lower than the preset test value, it is determined that the corresponding independent parameter conforms to the normal distribution; The corresponding independent parameters that conform to the normal distribution are divided into intervals for analysis to obtain the toughness influencing factors of the deep foundation pit, among which the toughness influencing factors include: robustness influencing factors, redundancy influencing factors, recovery influencing factors, wisdom influencing factors and adaptability influencing factors; The predicted expected value and predicted standard deviation of deep foundation pit prediction parameters are obtained according to the normality test; The interval level is divided according to the predicted expected value and the predicted standard deviation, and the interval corresponding to plus or minus 1 times the predicted standard deviation near the predicted expected value is recorded as the level 1 interval; The intervals corresponding to plus or minus 2 times the predicted standard deviation near the predicted expected value are recorded as level 2 intervals; The intervals corresponding to plus or minus three times the predicted standard deviation around the predicted expected value are recorded as level 3 intervals; The corresponding intervals outside the three intervals are recorded as level 4 intervals; According to the influencing factors of deep foundation pit toughness and the prediction parameters of deep foundation pit, the deep foundation pit toughness grade is determined and the deep foundation pit maintenance strategy is implemented.

7. The method for predicting deep foundation pit monitoring parameters based on neural network according to claim 6 is characterized in that: Also includes: According to the monitorable parameters of deep foundation pit, the deep foundation pit toughness assessment index is determined, and the assessment index matrix is ​​established to conduct a comprehensive assessment of the toughness of the deep foundation pit. The deep foundation pit toughness assessment index includes: the deformation assessment index of the retaining structure, the support force characteristic assessment index, the settlement assessment index around the foundation pit, the groundwater level change assessment index, the foundation pit uplift assessment index and the foundation pit surrounding condition assessment index; The evaluation index matrix is ​​dimensionless; According to the experts' weighted scoring of deep foundation pit toughness assessment indicators, the subjective weights of deep foundation pit toughness assessment indicators are determined; Obtain the coefficient of variation value based on the predicted expected value and the predicted standard deviation, and determine the objective weight of the deep foundation pit toughness evaluation index; The weight coefficient of the subjective weight to the indicator weight and the weight coefficient of the objective weight to the indicator weight are set to determine the indicator weight of the deep foundation pit toughness assessment indicator; According to the deep foundation pit toughness assessment index and the index weight of the deep foundation pit toughness assessment index, the toughness assessment distance is obtained and dimensionless processed to determine the final toughness assessment distance; ; Where d represents the final toughness assessment distance; a1 represents the weight coefficient of subjective weight to indicator weight; w1i1 represents the subjective weight of the i1th deep foundation pit toughness assessment indicator; represents the objective weight of the i1th deep foundation pit toughness assessment index; si1 represents the average value of the i1th deep foundation pit toughness assessment index; ui1 represents the variance of the i1th deep foundation pit toughness assessment index; xi1j1 represents the j1th level quantitative value of the i1th deep foundation pit toughness assessment index; j1 represents the interval level, with values ​​of 1, 2, 3, and 4; u1 represents the predicted expected value; represents the prediction standard deviation; n1 represents the number of deep foundation pit toughness evaluation indicators; According to the actual parameters of the deep foundation pit, the final toughness assessment distance is matched with the deep foundation pit toughness grade, and a mapping table of the final toughness assessment distance and the deep foundation pit toughness grade is determined; The predicted final toughness assessment distance and the predicted deep foundation pit toughness grade corresponding to the deep foundation pit prediction parameters are obtained, and a corresponding judgment is made according to the final toughness assessment distance-deep foundation pit toughness grade mapping table. If it is determined that the predicted final toughness assessment distance corresponds to the predicted deep foundation pit toughness grade, then the deep foundation pit toughness grade determined according to the deep foundation pit prediction parameters is accurate.

Images