Simulation test method and system for coal mining machine control system

Abstract

The present disclosure relates to a simulation test method for a coal mining machine control system, which is applied to a test host computer, wherein the test host computer is connected to the control system via an interface module. The method comprises: receiving a control instruction sent by the control system, wherein the control instruction is generated by the control system in response to a status signal sent by the test host computer, wherein the status signal is generated based on a pre-configured test case; controlling a simulation object model according to the control instruction and obtaining operating data of the simulation object model; inputting the operating data into a pre-trained test verification model to obtain test results; and generating a test report based on the test results. This method can effectively implement hardware-in-the-loop simulation testing of the coal mining machine control system, ensuring the safety performance of the coal mining machine control system in actual application.

Description

Technical Field

[0001] The present disclosure relates to the field of coal mining machines, and in particular, to a simulation test method and system for a coal mining machine control system. Background Art

[0002] The increasing complexity of shearer onboard control systems necessitates rigorous and comprehensive testing, particularly under extreme operating conditions and fault conditions. However, testing these systems with a live shearer can be prohibitively expensive and often difficult to achieve. Summary of the Invention

[0003] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] According to a first aspect of an embodiment of the present disclosure, a simulation test method for a coal mining machine control system is provided, which is applied to a test host computer, wherein the test host computer is connected to the control system via an interface module, and the method comprises:

[0005] receiving a control instruction sent by the control system, wherein the control instruction is generated by the control system in response to a status signal sent by the test host computer, wherein the status signal is generated based on a preconfigured test case;

[0006] Controlling the simulation object model according to the control instruction and obtaining operation data of the simulation object model;

[0007] Inputting the operating data into a pre-trained test verification model to obtain a test result;

[0008] A test report is generated according to the test results.

[0009] Optionally, the test verification model includes a data vectorization module and an anomaly discrimination module; the method includes:

[0010] Inputting multiple sets of example operation data including a target simulation object model into the data vectorization module to obtain an example data vector for each example operation data in the multiple sets of example operation data; each example operation data includes annotation information indicating the true confidence level of the target simulation object model as an abnormal object model;

[0011] Inputting the example data vector into the abnormality discrimination module to obtain a first confidence level that the target simulation object model in each example operation data is an abnormal object model;

[0012] determining a second confidence level that the target simulation object model in each example operation data is a normal object model based on a Euclidean distance between the example data vector and each vector in a typical data vector set, wherein each vector is a first data vector of the first example operation data having a true confidence level of zero represented by the annotated information;

[0013] Perform parameter iteration on the test verification model according to the first confidence level, the second confidence level, and the true confidence level.

[0014] Optionally, the typical data vector set is a vector array; and the method further comprises, after determining the second confidence level that the target simulation object model in each example operation data is a normal object model:

[0015] iterating the representative data vector set using the example data vector of the second example operating data in the plurality of sets of example operating data,

[0016] The true confidence level represented by the labeling information of the second example running data is zero.

[0017] Optionally, determining the second confidence level that the target simulation object model in each example operation data is a normal object model includes:

[0018] determining a distance distribution between the example data vector and the typical data vector set based on a scalar product between the example data vector and each vector in the typical data vector set; wherein the scalar value of each distance element in the distance distribution represents a confidence level that the target simulation object model in each example operation data and the target simulation object model in the first example operation data are in the same abnormal state; and

[0019] A maximum scalar in the distance distribution is determined as a second confidence level that the target simulation object model in each example operation data is a normal object model.

[0020] Optionally, the data vectorization module includes a data dimension reduction unit and a data normalization unit; inputting multiple sets of example operation data including the target simulation object model into the data vectorization module to obtain example data vectors for each example operation data in the multiple sets of example operation data includes:

[0021] Inputting the plurality of sets of example operation data into the data dimension reduction unit to obtain an original feature vector of each example operation data in the plurality of sets of example operation data; and

[0022] The original feature vectors of the respective example operating data are input into the data standardization unit to obtain the example data vectors of the respective example operating data.

[0023] Optionally, performing parameter iteration on the test verification model includes:

[0024] Determining a training cost value of the test validation model using a maximum likelihood estimation of the training cost value based on the first confidence level, the second confidence level, and the true confidence level; and

[0025] Perform parameter iteration on the test validation model according to the training cost value.

[0026] Optionally, the method comprises:

[0027] pass The simulation object model is built in Simulink and compiled into real-time code by Matlab's automatic code generation tool. In.

[0028] Optionally, before receiving the control instruction sent by the control system, the method further includes:

[0029] injecting a target fault into the control system through a fault injection module;

[0030] Inputting the operating data into a pre-trained test verification model to obtain a test result includes:

[0031] A test result corresponding to the target fault is obtained.

[0032] Optionally, the simulation object model includes at least one of the following:

[0033] Coupling model of the force and temperature field of the cutting part of the coal mining machine, the action model of the cutting part mechanism, the response model of the cutting part hydraulic system, the electrical signal response model of the main power supply circuit, the force and current coupling model of the cutting motor, and the data analysis model.

[0034] According to a second aspect of an embodiment of the present disclosure, a simulation test system for a coal mining machine control system is provided. The simulation test system includes a control system and a test host computer. The test host computer is connected to the control system via an interface module. The test host computer is used to:

[0035] receiving a control instruction sent by the control system, wherein the control instruction is generated by the control system in response to a status signal sent by the test host computer, wherein the status signal is generated based on a preconfigured test case;

[0036] Controlling the simulation object model according to the control instruction and obtaining operation data of the simulation object model;

[0037] Inputting the operating data into a pre-trained test verification model to obtain a test result;

[0038] A test report is generated according to the test result, and the test report is in a target file format.

[0039] Through the above technical solution, by receiving the control instructions sent by the control system; controlling the simulation object model according to the control instructions, and obtaining the operating data of the simulation object model; inputting the operating data into the pre-trained test verification model to obtain the test results; and generating a test report based on the test results, the hardware-in-the-loop simulation test of the coal mining machine control system can be effectively realized, and based on the pre-trained test verification model, the operating data of the simulation object model can be effectively verified, and then it is determined whether the coal mining machine control system can reliably control the coal mining machine, thereby ensuring the safety performance of the coal mining machine control system in actual application.

[0040] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale. In the drawings:

[0042] Figure 1 The present invention is a flowchart of a simulation test method of a coal mining machine control system according to an exemplary embodiment.

[0043] Figure 2 It is a schematic diagram of a simulation test system for a coal mining machine control system shown as an exemplary embodiment.

[0044] Figure 3 The figure is a schematic diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0045] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0046] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0047] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0048] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0049] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0050] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0051] Figure 1 The present invention is a flowchart of a simulation test method for a coal mining machine control system according to an exemplary embodiment. The method can be applied to a test host computer, wherein the test host computer is connected to the control system via an interface module. The method includes:

[0052] S101: Receive a control instruction sent by the control system, where the control instruction is generated by the control system in response to a status signal sent by the test host computer, and the status signal is generated based on a pre-configured test case.

[0053] Status signals can include, for example, operational data for each module in the shearer's traction system, the execution method for shearer traction, the computational channels of each sensor, control of the controlled object model, and the alarm method and execution sequence of the onboard control system's ECU module. Correspondingly, control instructions can include, for example, control instructions for models such as the cutting unit, power supply circuit, and traction unit.

[0054] S102: Control the simulation object model according to the control instruction, and obtain operation data of the simulation object model.

[0055] In one embodiment, the simulation object model includes at least one of the following: a force and temperature field coupling model of the coal mining machine cutting part, a cutting part mechanism action model, a cutting part hydraulic system response model, a main power supply circuit electrical signal response model, a cutting motor force and current coupling model, and a data analysis model.

[0056] Among them, the simulation object model is established for the electric traction drum coal mining machine, and can specifically include: a data analysis model, which mainly converts the format of the original MMA format data of the coal mining machine, such as converting hexadecimal to decimal, etc.; a force and temperature field coupling model of the coal mining machine cutting part, which can be used to input the load state of the coal mining machine cutting part and output real-time simulation of load torque and temperature state data; a cutting part mechanism action model, which can be used to output the coal mining machine rocker arm height and rocker arm error range; a cutting part hydraulic system response model, which can output hydraulic system pressure, oil temperature and other state parameters according to the rocker arm lifting instruction and load data; a main power supply circuit electrical signal response model, which can be used to simulate the response state of the power supply signal under typical loads; a force and current coupling model of the cutting motor, which can simulate the current response state of the cutting motor under typical loads, etc.

[0057] Furthermore, the test host computer can control the above-mentioned simulation object models based on control instructions, so that these simulation models execute actions corresponding to the control instructions. In addition, the test host computer can also collect relevant data of these simulation object models executing these actions, such as the coal mining machine instruction speed, running direction, rocker arm mining height, motor temperature, etc.

[0058] S103: Input the operating data into a pre-trained test verification model to obtain a test result.

[0059] Specifically, the test results can be used to characterize whether an anomaly exists after the simulation object model executes the control instructions sent by the control system. For example, the test results can include the confidence level of each simulation object model as an abnormal object model or a normal object model after executing the control instructions. The test results can include the control system's test results for each simulation object model. If the test results indicate that the control system fails a particular simulation object model, this indicates that an anomaly exists in the operating data generated by the simulation object model during the control system's execution of the simulation object model. In other words, the test results can be used to characterize whether the control instructions received by the simulation object model are reliable.

[0060] S104: Generate a test report according to the test results.

[0061] The test report can be stored in a preset file format, for example, it can be a file in Excel format. Furthermore, the relevant staff can adjust the coal mining machine control system based on the test report so that the coal mining machine control system can reliably control each simulation object model. For example, when the test results indicate that a certain simulation object model has failed the simulation test, for example, the confidence level of the simulation object model being an abnormal object model is higher than a preset threshold, the control instructions received by the simulation object model can be adjusted so that the control system can send more reliable control instructions to ensure that the coal mining machine can be reliably controlled.

[0062] In the embodiment of the present disclosure, by receiving control instructions sent by the control system; controlling the simulation object model according to the control instructions and obtaining the operating data of the simulation object model; inputting the operating data into a pre-trained test verification model to obtain test results; and generating a test report based on the test results, the hardware-in-the-loop simulation test of the coal mining machine control system can be effectively implemented, and based on the pre-trained test verification model, the operating data of the simulation object model can be effectively verified, and then it is determined whether the coal mining machine control system can reliably control the coal mining machine, thereby ensuring the safety performance of the coal mining machine control system in actual application.

[0063] In some optional embodiments, the method includes:

[0064] pass The simulation object model is built in Simulink and compiled into real-time code by Matlab's automatic code generation tool. In.

[0065] in, It is a software environment for configuring real-time test applications. Simulink is a visual simulation tool in Matlab. Simulink is a block diagram environment for multi-domain simulation and model-based design. It supports system design, simulation, automatic code generation, and continuous testing and verification of embedded systems. Simulink provides a graphical editor, a customizable module library, and a solver, which can model and simulate dynamic systems. Specifically, the automatic compilation tool in Matlab can be used to generate a real-time code file with the suffix dll from the established simulation object model and update it to the in-the-loop test environment.

[0066] In some other optional embodiments, before receiving the control instruction sent by the control system, the method further includes:

[0067] injecting a target fault into the control system through a fault injection module;

[0068] Inputting the operating data into a pre-trained test verification model to obtain a test result includes:

[0069] A test result corresponding to the target fault is obtained.

[0070] Target faults can include, for example, open circuits, short circuits to ground, and short circuits between pins. The fault injection module can be used to simulate hardware circuit faults that may occur in sensors or actuators during operation of the coal mining machine. These faults, such as open circuits, short circuits to ground, and short circuits between pins, can be observed. This allows the control system to determine its fault response strategy or emergency response by observing its operation under fault conditions or extreme operating conditions.

[0071] In some optional embodiments, the test verification model may include a data vectorization module and an anomaly discrimination module, and the method further includes the following steps:

[0072] Step 210 : Input multiple sets of example operating data including the target simulation object model into a data vectorization module to obtain example data vectors of each example operating data in the multiple sets of example operating data.

[0073] In some optional embodiments, multiple groups of operating data corresponding to the target simulation object model can be obtained from historical operating data, wherein the target simulation object model can be any one of the above-mentioned simulation object models, and annotation information can be added to the multiple groups of operating data based on the predetermined judgment results. The added annotation information can be information that characterizes the actual category of the target simulation object model in the operating data. For example, if the actual category is an abnormal object model, the annotation information "1" is added to the operating data, otherwise the annotation information "0" is added to the operating data. The annotation information can also characterize the true confidence that the target simulation object model in the operating data is an abnormal object model. For example, if the annotation information is "1", the true confidence is 1, and if the annotation information is "0", the true confidence is 0. It can be understood that the added annotation information is only used as an example to facilitate understanding of the present disclosure, and the present disclosure does not limit this.

[0074] Multiple sets of operating data with annotated information can be used as example operating data. For example, the example operating data can be divided into multiple groups, each group of example operating data including a predetermined number of example operating data. Each group of example operating data is used as a batch of training data and simultaneously input into a data vectorization module, thereby obtaining example data vectors for each example operating data in each group of example operating data. The predetermined number can be set based on actual needs and is not limited in this disclosure.

[0075] Step 220 : Input the example data vector into the abnormality identification module to obtain a first confidence level that the target simulation object model in each example operation data is an abnormal object model.

[0076] Among them, the abnormal object model can be a simulation object model that has an abnormality after executing the control instruction, and correspondingly, the normal object model can be a simulation object model that does not have an abnormality after executing the control instruction. When the confidence level that the target simulation object model is an abnormal object model is high, it can be characterized as a high possibility that the target simulation object has an abnormality after executing the control instruction, that is, the current coal mining machine control system is less likely to be able to reliably control the target simulation object. It can be understood that there can be a negative correlation between the confidence level that the target simulation object model is an abnormal object model and the confidence level that the target simulation object model is a normal object model.

[0077] According to an embodiment of the present disclosure, the abnormality discrimination module can be, for example, a fully connected network. The input of the abnormality discrimination module is the example data vector output by the data vectorization module. For example, if the number of example operation data in a batch of training data is X, and the feature vector corresponding to each group of example operation data includes D elements, then the input of the abnormality discrimination module can be an X×Y feature matrix. The output of the abnormality discrimination module is a probability vector. The probability vector includes X distance elements, which respectively represent the predicted probability that the target simulation object model included in each example operation data in the X example operation data is an abnormal object model. Therefore, through processing by the abnormality discrimination module, the first confidence that the target simulation object model in each example operation data is an abnormal object model can be obtained.

[0078] In one embodiment, the abnormality identification module may be configured with multiple weight parameters, which form a weight vector. The abnormality identification module may calculate the dot product of the example data vector for each example operation data and the weight vector to obtain the predicted probability that the target simulation object model is an abnormal object model in each example operation data. In this manner, the number of weight parameters in the weight vector may be equal to the number of elements in the feature vector described above.

[0079] Step 230 : Determine a second confidence level that the target simulation object model in each example operation data is a normal object model based on the Euclidean distance between the example data vector and each vector in the typical data vector set.

[0080] In some embodiments, by calculating the Euclidean distance between the example data vector and each vector in the typical data vector set, a distance distribution can be obtained, wherein the number of distance elements in the distance distribution is equal to the number of eigenvectors in the typical data vector set. In this embodiment, the average value, root mean square value, maximum scalar value, minimum scalar value, etc. of each distance element in the distance distribution, or multiple groups of distance elements can be used as a second confidence level that the target simulation object model in the example operation data is a normal object model.

[0081] In one embodiment, after obtaining the example data vectors of each example operation data, the scalar product between the example data vector and each vector in the typical data vector set can be calculated, and the calculated scalar product can be used to represent the Euclidean distance between the example data vector and each vector. For each example data vector, a distance distribution between the example data vector and the typical data vector set can be obtained. The scalar of each distance element in the distance distribution can represent the confidence that the target simulation object model in the example operation data and the target simulation object model in the operation data corresponding to each vector are in the same abnormal state. After obtaining the distance distribution, this embodiment can use the maximum scalar in the distance distribution as the second confidence level that the target simulation object model in the example operation data is a normal object model.

[0082] In some embodiments, each vector in the typical data vector set can be a first data vector of a first example operating data having a true confidence level of zero represented by the annotated information. For example, before training the test verification model, this embodiment can pre-screen multiple groups of example operating data (i.e., negative samples) in which the target simulation object model is a normal object model from multiple groups of operating data with annotated information added. Subsequently, the aforementioned data vectorization module is used to obtain an example data vector for each negative sample, and the example data vectors of multiple negative samples constitute the typical data vector set.

[0083] Step 240 : performing parameter iteration on the test verification model according to the first confidence level, the second confidence level, and the true confidence level.

[0084] According to an embodiment of the present disclosure, the training cost value of the test verification model can be determined based on the difference between the first confidence and the true confidence, and the difference between the second confidence and the true confidence, and the parameters in the test verification model can be adjusted using the backpropagation algorithm to reduce the training cost value of the test verification model.

[0085] In this embodiment, since multiple sets of example operation data are input, a confidence set can be obtained for each set of example operation data, resulting in a total of multiple confidence sets. Each confidence set includes a first confidence level, a second confidence level, and a true confidence level. In this embodiment, a training cost value can be obtained based on each confidence level set, resulting in a total of multiple sets of training cost values. These multiple sets of training cost values are superimposed to obtain the training cost value of the test verification model.

[0086] According to an embodiment of the present disclosure, after the example operation data is divided into multiple groups, the parameters of the test verification model can be iterated in sequence according to the multiple groups of example operation data until the training cost of the test verification model is less than a predetermined value, or the number of training times of the test verification model reaches a predetermined number.

[0087] According to an embodiment of the present disclosure, in the process of iterating parameters of the test verification model, the scalar of each weight parameter in the abnormal discrimination module can be adjusted according to the training cost value of the test verification model, so that the quantitative product between the weight vector composed of multiple groups of weight parameters and the positive sample, that is, the example running data of the target simulation object model as the abnormal object model, increases, and the quantitative product between the weight vector and the example data vector of the negative sample decreases. In this way, the example data vectors of the positive sample can be concentrated at the same center, while the example data vectors of the negative sample are far away from the center. Thereby, the test verification model can accurately distinguish the target simulation object model of the abnormal object model from the target simulation object model of the normal object model.

[0088] In summary, the test verification model training method of the disclosed embodiment constructs a typical data vector set based on negative samples, and determines a second confidence level that the target simulation object model is a normal object model based on the Euclidean distance between the example data vector of the example operation data and each vector in the typical data vector set. This can distinguish between normal object models and abnormal object models, thereby improving the accuracy of the obtained second confidence level. By iterating the parameters of the test verification model with reference to this second confidence level, supervision of negative sample features can be achieved, improving model accuracy and generalization ability.

[0089] In some optional embodiments, the abnormality discrimination module outputs a confidence vector, wherein each element in the confidence vector represents a first confidence level that the target simulation object model in a sample operation data is an abnormal object model. Further, a second confidence level that the target simulation object model in each sample operation data is a normal object model can be obtained. Finally, the training cost value of the test verification model is calculated based on the first confidence level, the second confidence level, and the true confidence level represented by the annotation information of the sample operation data. Subsequently, the parameters of the test verification model can be iterated based on the training cost value.

[0090] In some optional embodiments, a training cost value for the test-validation model may be determined using a maximum likelihood estimation of the training cost value based on the first confidence level, the second confidence level, and the true confidence level. Specifically, the first confidence level, the second confidence level, and the true confidence level may be substituted into a preset loss function for calculation, and the calculated training cost value may be used as the training cost value for the test-validation model.

[0091] Among them, the features in the typical data vector set can be dynamically iterated, for example. For example, the typical data vector set can be a vector queue. During the training process of the test verification model, after obtaining the second confidence based on the current typical data vector set, the example data vector of the second example operation data in the multiple sets of example operation data can be used to iterate the current typical data vector set. Among them, the second example operation data is a sample with a true confidence of zero represented by the annotation information, that is, the aforementioned negative sample. When iterating the typical data vector set, the feature that first enters the queue in the typical data vector set (that is, the feature at the head of the queue) can be deleted, and the example data vector of the second example operation data can be inserted into the tail of the typical data vector set. By dynamically iterating the typical data vector set, the generalization ability and detection accuracy of the test verification model obtained can be improved during the model training process.

[0092] In one embodiment, the test verification model includes a data vectorization module and an anomaly identification module. The data vectorization module may include a data dimensionality reduction unit and a data normalization unit. The data dimensionality reduction unit may be used to extract feature vectors of each example operation data. The data normalization unit may be used to perform data normalization processing on the features extracted by the data dimensionality reduction unit so that the values of each element in the output feature vector are within a certain range.

[0093] According to an embodiment of the present disclosure, the aforementioned example data vector obtained may be a feature obtained after being processed by a data standardization unit. That is, the operation of obtaining the example data vector described above may first input multiple sets of example operation data into a data dimensionality reduction unit to obtain the original feature vector of each example operation data in the multiple sets of example operation data. Subsequently, the original feature vector of each example operation data is input into a data standardization unit, and the data standardization unit outputs the example data vector of each example operation data. This is because the difference in operation data in different data domains may be large. If the unstandardized feature vector is directly used for verification, there may be a problem of inaccurate verification results due to the same verification standards for different data domains.

[0094] Based on the same inventive concept, the embodiment of the present disclosure also provides a simulation test system for the coal mining machine control system 21, referring to Figure 2The simulation test system 20 includes a control system 21 and a test host computer 22. The test host computer 22 is connected to the control system 21 through an interface module. The test host computer 22 is used to:

[0095] receiving a control instruction sent by the control system 21, wherein the control instruction is generated by the control system 21 in response to a status signal sent by the test host computer 22, wherein the status signal is generated according to a pre-configured test case;

[0096] Controlling the simulation object model according to the control instruction and obtaining operation data of the simulation object model;

[0097] Inputting the operating data into a pre-trained test verification model to obtain a test result;

[0098] A test report is generated according to the test result, and the test report is in a target file format.

[0099] Optionally, the test verification model includes a data vectorization module and an abnormality discrimination module; the test host computer 22 is further used to:

[0100] Inputting multiple sets of example operation data including a target simulation object model into the data vectorization module to obtain an example data vector for each example operation data in the multiple sets of example operation data; each example operation data includes annotation information indicating the true confidence level of the target simulation object model as an abnormal object model;

[0101] Inputting the example data vector into the abnormality discrimination module to obtain a first confidence level that the target simulation object model in each example operation data is an abnormal object model;

[0102] determining a second confidence level that the target simulation object model in each example operation data is a normal object model based on a Euclidean distance between the example data vector and each vector in a typical data vector set, wherein each vector is a first data vector of the first example operation data having a true confidence level of zero represented by the labeled information; and

[0103] Perform parameter iteration on the test verification model according to the first confidence level, the second confidence level, and the true confidence level.

[0104] Optionally, the typical data vector set is a vector queue; the test host computer 22 is further configured to:

[0105] iterating the representative data vector set using the example data vector of the second example operating data in the plurality of sets of example operating data,

[0106] The true confidence level represented by the labeling information of the second example running data is zero.

[0107] Optionally, the test host computer 22 is further used to:

[0108] determining a distance distribution between the example data vector and the typical data vector set based on a scalar product between the example data vector and each vector in the typical data vector set; wherein the scalar value of each distance element in the distance distribution represents a confidence level that the target simulation object model in each example operation data and the target simulation object model in the first example operation data are in the same abnormal state; and

[0109] A maximum scalar in the distance distribution is determined as a second confidence level that the target simulation object model in each example operation data is a normal object model.

[0110] Optionally, the data vectorization module includes a data dimension reduction unit and a data standardization unit, and the test host computer 22 is further used to:

[0111] Inputting the plurality of sets of example operation data into the data dimension reduction unit to obtain an original feature vector of each example operation data in the plurality of sets of example operation data; and

[0112] The original feature vectors of the respective example operating data are input into the data standardization unit to obtain the example data vectors of the respective example operating data.

[0113] Optionally, the test host computer 22 is further used to:

[0114] Determining a training cost value of the test validation model using a maximum likelihood estimation of the training cost value based on the first confidence level, the second confidence level, and the true confidence level; and

[0115] Perform parameter iteration on the test validation model according to the training cost value.

[0116] Optionally, the test host computer 22 is further used to:

[0117] pass The simulation object model is built in Simulink and compiled into real-time code by Matlab's automatic code generation tool. In.

[0118] Optionally, the test host computer 22 is further used to:

[0119] Injecting a target fault into the control system 21 through a fault injection module;

[0120] A test result corresponding to the target fault is obtained.

[0121] Optionally, the simulation object model includes at least one of the following:

[0122] Coupling model of the force and temperature field of the cutting part of the coal mining machine, the action model of the cutting part mechanism, the response model of the cutting part hydraulic system, the electrical signal response model of the main power supply circuit, the force and current coupling model of the cutting motor, and the data analysis model.

[0123] Reference below Figure 3 , which shows an electronic device (eg Figure 1 Schematic diagram of the structure of the test host computer 300. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0124] like Figure 3 As shown, electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage device 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for the operation of electronic device 300. Processing device 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0125] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0126] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0127] It should be noted that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0128] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0129] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0130] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the steps involved in the above method embodiment.

[0131] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The modules described in the embodiments of the present disclosure may be implemented in software or hardware, wherein the name of a module does not necessarily limit the module itself.

[0134] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0135] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the scope of the above disclosure. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0137] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0138] Although the subject matter has been described using language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. Regarding the apparatus in the above-described embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be elaborated upon here.

Claims

1. A simulation test method for a coal mining machine control system, characterized in that: Applied to a test host computer, the test host computer is connected to the control system via an interface module, and the method includes: receiving a control instruction sent by the control system, wherein the control instruction is generated by the control system in response to a status signal sent by the test host computer, wherein the status signal is generated based on a pre-configured test case; Controlling the simulation object model according to the control instruction and obtaining operation data of the simulation object model; Inputting the operating data into a pre-trained test verification model to obtain a test result; Generate a test report based on the test results, The test verification model includes a data vectorization module and an anomaly discrimination module; the method includes: Inputting multiple sets of example operation data including a target simulation object model into the data vectorization module to obtain an example data vector for each example operation data in the multiple sets of example operation data; each example operation data includes annotation information indicating the true confidence level of the target simulation object model as an abnormal object model; Inputting the example data vector into the abnormality discrimination module to obtain a first confidence level that the target simulation object model in each example operation data is an abnormal object model; determining a second confidence level that the target simulation object model in each example operation data is a normal object model based on a Euclidean distance between the example data vector and each vector in a typical data vector set, wherein each vector is a first data vector of the first example operation data having a true confidence level of zero represented by the annotated information; Perform parameter iteration on the test verification model according to the first confidence level, the second confidence level, and the true confidence level.

2. The method according to claim 1, characterized in that The typical data vector set is a vector array; the method further includes, after determining a second confidence level that the target simulation object model in each example operation data is a normal object model: iterating the typical data vector set using the example data vector of the second example operation data in the multiple sets of example operation data, The true confidence level of the labeling information representation of the second example running data is zero.

3. The method according to claim 1 or 2, characterized in that Determining the second confidence level that the target simulation object model in each example operation data is a normal object model includes: determining a distance distribution between the example data vector and the typical data vector set based on a scalar product between the example data vector and each vector in the typical data vector set; wherein the scalar value of each distance element in the distance distribution represents a confidence level that the target simulation object model in each example operation data and the target simulation object model in the first example operation data are in the same abnormal state; and A maximum scalar in the distance distribution is determined as a second confidence level that the target simulation object model in each example operation data is a normal object model.

4. The method according to claim 1 or 2, wherein The data vectorization module includes a data dimension reduction unit and a data normalization unit; the step of inputting multiple sets of example operation data including the target simulation object model into the data vectorization module to obtain example data vectors of each example operation data in the multiple sets of example operation data includes: Inputting the plurality of sets of example operation data into the data dimension reduction unit to obtain an original feature vector of each example operation data in the plurality of sets of example operation data; and The original feature vectors of the respective example operating data are input into the data standardization unit to obtain the example data vectors of the respective example operating data.

5. The method according to claim 1 or 2, wherein Performing parameter iteration on the test verification model includes: Determining a training cost value of the test validation model using a maximum likelihood estimation of the training cost value based on the first confidence level, the second confidence level, and the true confidence level; and Perform parameter iteration on the test validation model according to the training cost value.

6. The method according to claim 1 or 2, characterized in that The method comprises: An in-the-loop test environment of the simulation object model is built by NI Veristand. The simulation object model is established in Simulink and compiled into real-time code by an automatic code generation tool in Matlab and imported into NI Veristand.

7. The method according to claim 1 or 2, characterized in that Before receiving the control instruction sent by the control system, the method further includes: injecting a target fault into the control system through a fault injection module; Inputting the operating data into a pre-trained test verification model to obtain a test result includes: A test result corresponding to the target fault is obtained.

8. The method according to claim 1 or 2, characterized in that The simulation object model includes at least one of the following: Coupling model of the force and temperature field of the cutting part of the coal mining machine, the action model of the cutting part mechanism, the response model of the cutting part hydraulic system, the electrical signal response model of the main power supply circuit, the force and current coupling model of the cutting motor, and the data analysis model.

9. A simulation test system for a coal mining machine control system, characterized in that: The simulation test system includes a control system and a test host computer, wherein the test host computer is connected to the control system via an interface module, and the test host computer is used to: receiving a control instruction sent by the control system, wherein the control instruction is generated by the control system in response to a status signal sent by the test host computer, wherein the status signal is generated based on a pre-configured test case; Controlling the simulation object model according to the control instruction and obtaining operation data of the simulation object model; Inputting the operating data into a pre-trained test verification model to obtain a test result; Generate a test report according to the test results, wherein the test report is in a target file format; The test verification model includes a data vectorization module and an abnormality discrimination module; the test host computer is also used to: Inputting multiple sets of example operation data including a target simulation object model into the data vectorization module to obtain an example data vector for each example operation data in the multiple sets of example operation data; each example operation data includes annotation information indicating the true confidence level of the target simulation object model as an abnormal object model; Inputting the example data vector into the abnormality discrimination module to obtain a first confidence level that the target simulation object model in each example operation data is an abnormal object model; determining a second confidence level that the target simulation object model in each example operation data is a normal object model based on a Euclidean distance between the example data vector and each vector in a typical data vector set, wherein each vector is a first data vector of the first example operation data having a true confidence level of zero represented by the annotated information; Perform parameter iteration on the test verification model according to the first confidence level, the second confidence level, and the true confidence level.

Images