Stratum identification method and system based on construction parameters

Abstract

The invention discloses a stratum identification method and system based on construction parameters. The stratum identification method comprises the steps that parameter information of an existing shield tunneling machine in the construction process and corresponding stratum information are obtained and preprocessed; the preprocessed data information is converted to obtain a Gramb angle sum field matrix and a Gramb angle difference field matrix, and a training data set is constructed; constructing a stratum identification initial model based on a CNN network and an LSTM network, and training to obtain a stratum identification model; and parameter information of the shield tunneling machine in the construction process is obtained in real time, and stratum recognition based on construction parameters is completed through the stratum recognition model. According to the invention, the obtained parameter information of the shield tunneling machine construction process is processed, the Grubm angle and field matrix and the Grubm angle difference field matrix are calculated to construct the training data set, and then the stratum identification model constructed by the CNN network and the LSTM network is trained, so that real-time stratum identification based on construction parameters can be realized; and the reliability is higher, and the accuracy is better.

Description

Technical Field

[0001] The present invention belongs to the field of civil engineering, and particularly relates to a formation identification method and system based on construction parameters. Background Technique

[0002] Shield tunneling construction is widely used in infrastructure construction such as urban rail transit, highway tunnels, and water conservancy projects. Due to the complexity of the underground formation, the shield machine may encounter various formations during tunneling, such as soft soil layers, sandy pebble layers, clay layers, rock layers, etc. The physical and mechanical properties of these formations vary greatly, which will have a significant impact on the propulsion performance of the shield machine, cutter head torque, penetration degree, and soil discharge efficiency of the screw conveyor. Therefore, real-time identification of the formation type during shield tunneling is of great significance for optimizing construction parameters, reducing construction risks, and improving construction efficiency.

[0003] At present, the formation identification schemes in shield construction mainly include geological exploration schemes and construction experience judgment schemes. Traditional geological exploration methods, such as drilling and geophysical exploration, can provide formation information before construction; however, due to the complexity of the underground environment, there are certain deviations in the exploration data, and such schemes are prior schemes and cannot provide real-time formation change information during construction. The construction experience scheme generally involves construction personnel making artificial formation judgments based on current tunneling parameters and experience; however, such schemes are highly subjective, and their accuracy and reliability are relatively poor. Summary of the Invention

[0004] One of the purposes of the present invention is to provide a formation identification method based on construction parameters with high reliability, good accuracy, and good real-time performance.

[0005] Another purpose of the present invention is to provide a system for implementing the formation identification method based on construction parameters.

[0006] The formation identification method based on construction parameters provided by the present invention includes the following steps: S1. Obtain the parameter information and corresponding formation information of the existing shield machine construction process; S2. Preprocess the data information obtained in step S1; S3. Based on the Gram angular field transform, transform the preprocessed data information to obtain the Gram angle and field matrix and the Gram angle difference field matrix; S4. Construct a training data set according to the data information obtained in step S2 and step S3; S5. Based on the CNN network and the LSTM network, construct an initial formation identification model; The constructed initial model for stratum identification includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module and a stratum classification module; the 2D feature extraction module is used to extract the time series and spatial information features in the obtained Gram angle sum field matrix and the Gram angle difference field matrix; the 1D feature extraction module is used to extract the time features in the pre-processed construction process parameter information; the time modeling module is used to extract the time series data features in the output of the 2D feature extraction module and the output of the 1D feature extraction module; the stratum classification module is used to classify and identify strata according to the time series data features output by the time modeling module; S6. Using the training data set constructed in step S4, the initial formation recognition model constructed in step S5 is trained to obtain a formation recognition model; S7. Acquire parameter information of the shield machine construction process in real time, and use the stratum identification model obtained in step S6 to complete stratum identification based on the construction parameters.

[0007] The step S1 specifically includes the following steps: The obtained parameter information of the shield machine construction process includes thrust, cutter head speed, torque, penetration, shield tail gap, earth pressure balance, screw conveyor discharge rate and shield posture data; the shield posture data includes shield inclination data and shield offset data.

[0008] The step S2 specifically includes the following steps: Preprocessing the data information obtained in step S1; the preprocessing includes data segmentation, data normalization and outlier detection; A sliding window scheme is used to segment the acquired time series data to ensure the temporal continuity of the data; The min-max normalization method was used to standardize the data; The Z-score method is used to detect outliers in the data, and the data judged as outliers are eliminated.

[0009] The step S3 specifically includes the following steps: Use the following formula to convert the preprocessed data into angle information: In the formula is the angle information at the i-th time point; is the preprocessed data at the i-th time point; The Gram angle and field matrix data are calculated using the following formula: In the formula is the data of the jth row and kth column in the Gram angle and field matrix; The data of the Gram angle difference field matrix is ​​calculated using the following formula: In the formula is the data at the m-th row and n-th column in the Gram angle difference field matrix.

[0010] The step S5 includes the following steps: Construct a 2D feature extraction module based on the CNN network; the 2D feature extraction module is used to extract the temporal and spatial information features of the Gram angle and field matrix and the Gram angle difference field matrix in the input data; Construct a 1D feature extraction module based on the CNN network; the 1D feature extraction module is used to extract the time features of the preprocessed data information in the input data; Construct a time modeling module based on the BiLSTM network; splice the extracted temporal and spatial information features and time features, and input them into the time modeling module to extract time series data features; Construct a formation classification module based on the softmax classifier, which is used to classify and identify the formation according to the obtained time series data features.

[0011] The 2D feature extraction module specifically includes the following content: The 2D feature extraction module includes a number of convolutional layers connected in series and a max pooling layer; among them, the convolutional kernel of the convolutional layer is , and the stride is 1; the max pooling layer is max pooling layer.

[0012] The 1D feature extraction module specifically includes the following content: The 1D feature extraction module includes a number of convolutional layers connected in series and a max pooling layer; among them, the convolutional kernel of the convolutional layer is , and the stride is 1; the max pooling layer is max pooling layer.

[0013] The time modeling module specifically includes the following content: The calculation unit of the time modeling module is expressed as: , , , , , In the formula is the output result of the forget gate; is the activation function; is the weight matrix of the forget gate; is the hidden state at the current moment; is the input data at the current moment; represents the hidden state at the previous moment and the current input; is the bias vector of the forget gate; is the output result of the input gate; is the weight of the input gate; is the bias of the input gate; is the candidate state; is the candidate state weight; is the candidate state bias; is the cell state at the current time; is the element-wise multiplication between vectors; is the activation value of the output gate; is the output gate weight; is the output gate bias.

[0014] The described formation classification module specifically includes the following: The calculation process of the formation classification module is expressed as: In the formula represents the probability of being classified as the k-th type of formation under the condition of the given input feature X; is the weight vector corresponding to the k-th category; X is the input feature vector; is the bias term corresponding to the k-th category; K is the total number of formation categories; is the weight vector corresponding to the j-th category; is the bias term corresponding to the j-th category.

[0015] The present invention also provides a system for implementing the above-mentioned formation identification method based on construction parameters, which includes a data acquisition module, a data processing module, a matrix calculation module, a data set construction module, a network construction module, a network training module, and a formation identification module. The data acquisition module, the data processing module, the matrix calculation module, the data set construction module, the network construction module, the network training module, and the formation identification module are connected in series in sequence. The data acquisition module is used to acquire the parameter information and corresponding formation information during the construction process of an existing shield machine, and upload the data information to the data processing module. The data processing module is used to preprocess the acquired data information according to the received data information, and upload the data information to the matrix calculation module. The matrix calculation module is used to transform the preprocessed data information based on the Gram Angular Field Transform according to the received data information, to obtain a Gram Angular and Field Matrix and a Gram Angular Difference Field Matrix, and upload the data information to the data set construction module. The data set construction module is used to construct a training data set according to the received data information and the obtained data information, and upload the data information to the network construction module. The network construction module is used to construct an initial formation identification model based on a CNN network and an LSTM network according to the received data information, and upload the data information to the network training module. Among them, the constructed initial formation identification model includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module, and a formation classification module. The 2D feature extraction module is used to extract the temporal and spatial information features in the obtained Gram Angular and Field Matrix and Gram Angular Difference Field Matrix. The 1D feature extraction module is used to extract the time features in the preprocessed construction process parameter information. The time modeling module is used to extract the time series data features in the outputs of the 2D feature extraction module and the 1D feature extraction module. The formation classification module is used to perform formation classification and identification according to the time series data features output by the time modeling module. The network training module is used to train the constructed initial formation identification model with the constructed training data set according to the received data information, to obtain a formation identification model, and upload the data information to the formation identification module. The formation identification module is used to acquire the parameter information during the construction process of the shield machine in real time according to the received data information, and complete the formation identification based on construction parameters by using the obtained formation identification model.

[0016] The formation identification method and system based on construction parameters provided by the present invention can not only realize real-time formation identification based on construction parameters, but also have higher reliability and better accuracy by processing the parameter information during the construction process of the shield machine, calculating the Gram Angular and Field Matrix and the Gram Angular Difference Field Matrix to construct a training data set, and then training the formation identification model constructed by the CNN network and the LSTM network. Description of the Drawings

[0017] Figure 1The figure is a schematic diagram of the method flow of the present invention.

[0018] Figure 2 Schematic diagram of the functional modules of the system of the present invention. DETAILED DESCRIPTION

[0019] like Figure 1 The method flow chart of the method of the present invention is shown as follows: The method for identifying formations based on construction parameters disclosed in the present invention comprises the following steps: S1. Obtaining parameter information of the existing shield machine construction process and corresponding stratum information; specifically comprising the following steps: The obtained parameter information of the shield machine construction process includes thrust, cutterhead speed, torque, penetration, shield tail gap, earth pressure balance, screw conveyor discharge rate and shield posture data, etc.; the shield posture data includes shield inclination data and shield offset data; these parameters can characterize the operating status of the shield machine in different strata.

[0020] S2. Preprocessing the data information obtained in step S1; specifically comprising the following steps: Due to the influence of factors such as sensor accuracy and environmental noise, the acquired raw data has certain discreteness and outliers, so data preprocessing is required; Preprocessing the data information obtained in step S1; the preprocessing includes data segmentation, data normalization and outlier detection; A sliding window scheme is used to segment the acquired time series data to ensure the temporal continuity of the data; The min-max normalization method is used to standardize the data so that the data is normalized; The Z-score method is used to detect outliers in the data, and the data judged as outliers are removed; The data of XX is removed, among which is the mean of the data, is the variance of the data.

[0021] S3. Based on the Gram angle field transform, the preprocessed data information is transformed to obtain the Gram angle and field matrix and the Gram angle difference field matrix; specifically comprising the following steps: Since construction parameters have time series characteristics, directly inputting them into the neural network may lead to the loss of time series dependent information. Therefore, the Gram angular field transform is used to convert the time series data into a two-dimensional matrix to enhance the feature representation capability. Use the following formula to convert the preprocessed data into angle information: In the formula is the angle information at the i-th time point; is the preprocessed data at the i-th time point; The data of the Gram angle and field matrix is calculated using the following formula to represent the overall trend of the data: In the formula is the data at the j-th row and k-th column in the Gram angle and field matrix; The data of the Gram angle difference field matrix is calculated using the following formula to characterize the dynamic change pattern of the data: In the formula is the data at the m-th row and n-th column in the Gram angle difference field matrix.

[0022] S4. Construct a training dataset based on the data information obtained in steps S2 and S3.

[0023] S5. Based on the CNN network and the LSTM network, construct an initial formation recognition model; The constructed initial formation recognition model includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module, and a formation classification module; the 2D feature extraction module is used to extract the temporal and spatial information features in the obtained Gram angle and field matrix and Gram angle difference field matrix; the 1D feature extraction module is used to extract the time features in the preprocessed construction process parameter information; the time modeling module is used to extract the time series data features in the outputs of the 2D feature extraction module and the 1D feature extraction module; the formation classification module is used to perform formation classification and recognition based on the time series data features output by the time modeling module.

[0024] Specifically, in implementation: It includes the following steps: Construct a 2D feature extraction module based on the CNN network; the 2D feature extraction module is used to extract the temporal and spatial information features in the Gram angle and field matrix and Gram angle difference field matrix of the input data; the 2D feature extraction module includes a number of convolutional layers connected in series and a max pooling layer; among them, the convolutional kernel of the convolutional layer is , and the stride is 1; the max pooling layer is max pooling layer to reduce the data dimension and retain key features; Construct a 1D feature extraction module based on the CNN network; the 1D feature extraction module is used to extract the time features of the preprocessed data information in the input data; the 1D feature extraction module includes a number of convolutional layers connected in series and a max pooling layer; among them, the convolutional kernel of the convolutional layer is , and the stride is 1; the max pooling layer is max pooling layer to reduce the computational complexity; Construct a time modeling module based on the BiLSTM network; splice the extracted temporal and spatial information features and time features, and input them into the time modeling module to extract time series data features; the calculation unit of the time modeling module is expressed as: , , , , , In the formula is the output result of the forget gate; is the activation function; is the weight matrix of the forget gate; is the hidden state at the current moment; is the input data at the current moment; represents the hidden state at the previous moment and the current input; is the bias vector of the forget gate; is the output result of the input gate; is the weight of the input gate; is the bias of the input gate; is the candidate state; is the candidate state weight; is the candidate state bias; is the cell state at the current moment; is the element-wise multiplication between vectors; is the activation value of the output gate; is the output gate weight; is the output gate bias; Construct a formation classification module based on the softmax classifier to perform formation classification and recognition according to the obtained time series data features; the calculation process of the formation classification module is expressed as: In the formula represents the probability of being classified as the k-th formation under the condition of the given input feature X; is the weight vector corresponding to the k-th category; X is the input feature vector; is the bias term corresponding to the k-th category; K is the total number of formation categories; is the weight vector corresponding to the j-th category; is the bias term corresponding to the j-th category.

[0025] S6. Use the training dataset constructed in step S4 to train the initial formation recognition model constructed in step S5 to obtain a formation recognition model.

[0026] S7. Real-time obtain the parameter information of the shield machine construction process, and use the formation recognition model obtained in step S6 to complete the formation recognition based on the construction parameters.

[0027] The effects of the method of the present invention will be described below in conjunction with an embodiment: The total length of a certain project is 3099.452 m, and the overburden depth of the interval tunnel is about 8.84 - 27.17 m. The main strata passed through are silty clay , (mud-containing) fine and medium sand , residual sandy clay , completely weathered granite , (sand-containing) silty clay , silty clay , massive strongly weathered granite , moderately weathered granite , (mud-containing) coarse and medium sand , (muddy) fine and medium sand , silty clay and fine and medium sand .

[0028] To verify the effectiveness of the method of the present invention, a dataset was constructed using the shield tunneling data of an actual project and compared with the rule-based parameter threshold judgment method, traditional LSTM model, and CNN-LSTM model. The accuracy (Accuracy), F1-score, and recognition time were used as evaluation criteria.

[0029] Accuracy is used to measure the overall correct recognition of the model, representing the proportion of correctly classified samples in the total samples and reflecting the global recognition ability result of the model; F1-score is an index that comprehensively considers "Precision" and "Recall", especially suitable for the case of unbalanced class distribution, and can more comprehensively evaluate the recognition effect of the model on each stratum type; the recognition time refers to the average calculation time required for the model to classify each data for the stratum, reflecting the real-time performance and calculation efficiency of the model in actual project deployment.

[0030] The experimental data is shown in Table 1 below: Table 1 Schematic table of experimental data

[0031] As can be seen from Table 1, the method proposed by the present invention is significantly superior to the other three methods in terms of accuracy and F1-score, indicating that it performs optimally in terms of recognition accuracy and classification stability. At the same time, its average recognition time is only 35 seconds, which is better than the traditional LSTM and CNN-LSTM methods, demonstrating good real-time performance and engineering application value. In contrast, the rule-based parameter threshold method has a slow calculation speed, and both the recognition accuracy and F1-score are significantly insufficient. Although LSTM and CNN-LSTM have improved in terms of accuracy, they are still inferior to the method of the present invention. This shows that the present invention has significant advantages in balancing recognition accuracy and calculation efficiency.

[0032] As Figure 2The following is a schematic diagram of the functional modules of the system of the present invention: The system for implementing the method for identifying strata based on construction parameters disclosed in the present invention includes a data acquisition module, a data processing module, a matrix calculation module, a dataset construction module, a network construction module, a network training module, and a strata identification module; the data acquisition module, the data processing module, the matrix calculation module, the dataset construction module, the network construction module, the network training module, and the strata identification module are connected in series in sequence; the data acquisition module is used to acquire the parameter information of the existing shield machine construction process and the corresponding strata information, and upload the data information to the data processing module; the data processing module is used to preprocess the acquired data information according to the received data information, and upload the data information to the matrix calculation module; the matrix calculation module is used to transform the preprocessed data information based on the Gram angle field transformation according to the received data information to obtain a Gram angle and field matrix and a Gram angle difference field matrix, and upload the data information to the dataset construction module; the dataset construction module is used to construct a training dataset according to the received data information and the obtained data information, and upload the data information to the network construction module; the network construction module is used to construct an initial strata identification model based on the CNN network and the LSTM network according to the received data information, and upload the data information to the network training module; wherein, the constructed initial strata identification model includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module, and a strata classification module; the 2D feature extraction module is used to extract the temporal and spatial information features in the obtained Gram angle and field matrix and Gram angle difference field matrix; the 1D feature extraction module is used to extract the time features in the preprocessed construction process parameter information; the time modeling module is used to extract the time series data features in the output of the 2D feature extraction module and the output of the 1D feature extraction module; the strata classification module is used to classify and identify the strata according to the time series data features output by the time modeling module; the network training module is used to train the constructed initial strata identification model using the constructed training dataset according to the received data information to obtain a strata identification model, and upload the data information to the strata identification module; the strata identification module is used to acquire the parameter information of the shield machine construction process in real time according to the received data information, and complete the strata identification based on construction parameters using the obtained strata identification model.

Claims

1. A method for identifying strata based on construction parameters, characterized in that The steps include: S1. Obtaining parameter information of the existing shield machine construction process and corresponding stratum information; S2 preprocesses the data information obtained in step S1; S3. Based on the Gram angle field transform, the preprocessed data information is transformed to obtain the Gram angle sum field matrix and the Gram angle difference field matrix; S4. Construct a training data set based on the data information obtained in step S2 and step S3; S5. Construct an initial model for stratum identification based on CNN network and LSTM network; The constructed initial model for stratum identification includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module and a stratum classification module; the 2D feature extraction module is used to extract the time series and spatial information features in the obtained Gram angle sum field matrix and the Gram angle difference field matrix; the 1D feature extraction module is used to extract the time features in the pre-processed construction process parameter information; the time modeling module is used to extract the time series data features in the output of the 2D feature extraction module and the output of the 1D feature extraction module; the stratum classification module is used to classify and identify strata according to the time series data features output by the time modeling module; S6. Using the training data set constructed in step S4, the initial formation recognition model constructed in step S5 is trained to obtain a formation recognition model; S7. Acquire parameter information of the shield machine construction process in real time, and use the stratum identification model obtained in step S6 to complete stratum identification based on the construction parameters.

2. The method for identifying strata based on construction parameters according to claim 1, characterized in that The step S1 specifically includes the following steps: The obtained parameter information of the shield machine construction process includes thrust, cutter head speed, torque, penetration, shield tail gap, earth pressure balance, screw conveyor discharge rate and shield posture data; the shield posture data includes shield inclination data and shield offset data.

3. The method for identifying strata based on construction parameters according to claim 1, characterized in that The step S2 specifically includes the following steps: Preprocessing the data information obtained in step S1; the preprocessing includes data segmentation, data normalization and outlier detection; A sliding window scheme is used to segment the acquired time series data to ensure the temporal continuity of the data; The min-max normalization method was used to standardize the data; The Z-score method is used to detect outliers in the data, and the data judged as outliers are eliminated.

4. The method for identifying strata based on construction parameters according to claim 1, characterized in that The step S3 specifically includes the following steps: Use the following formula to convert the preprocessed data into angle information: In the formula is the angle information at the i-th time point; is the preprocessed data at the i-th time point; The Gram angle and field matrix data are calculated using the following formula: In the formula is the data of the jth row and kth column in the Gram angle and field matrix; The data of the Gram angle difference field matrix is ​​calculated using the following formula: In the formula is the data in the mth row and nth column of the Gram angle difference field matrix.

5. The method for identifying strata based on construction parameters according to claim 4, characterized in that The step S5 comprises the following steps: Construct a 2D feature extraction module based on the CNN network; The 2D feature extraction module is used to extract the temporal and spatial information features of the Gram angle sum field matrix and the Gram angle difference field matrix in the input data; A 1D feature extraction module is constructed based on the CNN network; the 1D feature extraction module is used to extract the temporal features of the preprocessed data information in the input data; A time modeling module is constructed based on the BiLSTM network; the extracted time series and spatial information features are concatenated with the time features and input into the time modeling module to extract the time series data features; A stratum classification module is constructed based on the softmax classifier to classify and identify strata according to the characteristics of the obtained time series data.

6. The method for identifying strata based on construction parameters according to claim 5, characterized in that The 2D feature extraction module specifically includes the following contents: The 2D feature extraction module includes several convolutional layers and a maximum pooling layer connected in series. The convolution kernel of the convolutional layer is , the step size is 1; the maximum pooling layer is The maximum pooling layer.

7. The method for identifying strata based on construction parameters according to claim 6, characterized in that The 1D feature extraction module specifically includes the following contents: The 1D feature extraction module includes several convolutional layers and a maximum pooling layer connected in series. The convolution kernel of the convolutional layer is , the step size is 1; the maximum pooling layer is The maximum pooling layer.

8. The method for identifying strata based on construction parameters according to claim 7, characterized in that The time modeling module specifically includes the following contents: The computational unit of the temporal modeling module is expressed as: , , , , , In the formula is the output result of the forget gate; is the activation function; is the weight matrix of the forget gate; is the hidden state at the current moment; is the input data at the current moment; Indicates the hidden state at the previous moment and the current input; is the bias vector of the forget gate; is the output result of the input gate; is the weight of the input gate; is the bias of the input gate; is a candidate status; is the candidate state weight; Bias for candidate states; is the unit state at the current moment; is the element-by-element multiplication between vectors; is the activation value of the output gate; is the output gate weight; Bias for the output gate.

9. The method for identifying strata based on construction parameters according to claim 8, characterized in that The stratum classification module specifically includes the following contents: The calculation process of the stratigraphic classification module is expressed as: In the formula It represents the probability of being classified as the kth type of stratum under the condition of given input feature X; is the weight vector corresponding to the kth category; X is the input feature vector; is the bias item corresponding to the kth category; K is the total number of stratum categories; is the weight vector corresponding to the jth category; is the bias term corresponding to the jth category.

10. A system for implementing the method for identifying strata based on construction parameters as claimed in any one of claims 1 to 9, characterized in that It includes a data acquisition module, a data processing module, a matrix calculation module, a data set construction module, a network construction module, a network training module and a stratum identification module; the data acquisition module, the data processing module, the matrix calculation module, the data set construction module, the network construction module, the network training module and the stratum identification module are connected in series in sequence; the data acquisition module is used to obtain the parameter information and the corresponding stratum information of the existing shield machine construction process, and upload the data information to the data processing module; The data processing module is used to pre-process the acquired data information according to the received data information, and upload the data information to the matrix calculation module; The matrix calculation module is used to transform the pre-processed data information based on the received data information and the Gram angle field transformation to obtain the Gram angle sum field matrix and the Gram angle difference field matrix, and upload the data information to the data set construction module; The data set construction module is used to construct a training data set based on the received data information and upload the data information to the network construction module; The network construction module is used to construct an initial model for stratum identification based on the CNN network and the LSTM network according to the received data information, and upload the data information to the network training module; wherein the constructed initial model for stratum identification includes a 2D feature extraction module, a 1D feature extraction module, a time modeling module and a stratum classification module; the 2D feature extraction module is used to extract the time series and spatial information features in the obtained Gram angle and field matrix and the Gram angle difference field matrix; the 1D feature extraction module is used to extract the time features in the pre-processed construction process parameter information; the time modeling module is used to extract the time series data features in the output of the 2D feature extraction module and the output of the 1D feature extraction module; the stratum classification module is used to classify and identify strata according to the time series data features output by the time modeling module; the network training module is used to train the constructed initial model for stratum identification according to the received data information using the constructed training data set to obtain a stratum identification model, and upload the data information to the stratum identification module; The stratum identification module is used to obtain parameter information of the shield machine construction process in real time according to the received data information, and use the obtained stratum identification model to complete the stratum identification based on the construction parameters.

Images