Simulation training method and system for operation process of gas extraction drilling machine

Abstract

The invention relates to the field of simulation training, in particular to a simulation training method and system for the operation process of a gas extraction drilling machine. According to the invention, the training condition of each employee is collected through the completed simulation training system, that is, the training condition of each employee during completion of all simulation training items is collected, that is, the training score is collected, and then according to the preset training period, the training score is calculated. The simulation training system calculates an important score according to the training score and the basic score of each employee in each simulation training item in the last training period, then calculates a selection probability according to the important score and the continuous number of times that the simulation training items are not selected, and determines whether the simulation training items are selected or not according to whether the selection probability is 1. Selecting different selection methods to select the simulation training items meeting the selection number, and training the to-be-trained personnel; the problem that an existing simulation training system is difficult to train weak items which are not mastered by different employees yet, so that the training efficiency of the simulation training system on the employees is insufficient is solved.

Description

Technical Field

[0001] The invention relates to the field of simulation training, and in particular to a simulation training method and system for an operation process of a gas extraction drilling rig. Background Art

[0002] Gas extraction is the foundation of safe production in coal mines. Strengthening gas extraction is of great significance to safe production in mines. The job training of gas extraction drill operators also highlights its importance. Due to the special environmental limitations of coal mines, the effectiveness and efficiency of practical training are lacking. The use of virtual reality technology can truly restore the working environment of the gas extraction drill, and simulate all its job operation standards in a digital way, simulating the functional operation of the gas extraction drill for employees, which is not restricted by location and time, and is both safe and reliable and can achieve training results.

[0003] However, in actual use, it was found that when employees conduct training and study on their own in the traditional simulation training system, the simulation training topics obtained are random, or the employees are specified to study a certain project. However, since gas extraction is seriously related to coal mine safety production, employees are required to master each job operation standard proficiently. The existing simulation training system makes it difficult to train different employees on weak points that they have not yet mastered, resulting in insufficient training efficiency for employees by the simulation training system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a simulation training method and system for the operation process of a gas extraction drilling rig, which solves the problem that the existing simulation training system is difficult to train different employees on weak points that they have not yet mastered, resulting in insufficient training efficiency for employees by the simulation training system.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A simulation training method for a gas extraction drilling rig operation process, the simulation training method specifically comprises the following steps:

[0007] S1. Setting up several simulation training projects including the operation process of gas extraction drilling rigs in the simulation training system;

[0008] S2. The simulation training system obtains personal data of the trainee in the previous training cycle, wherein the personal data includes identity information of the trainee, completed simulation training projects and corresponding training scores;

[0009] S3, judging whether the trainee has completed all simulation training items;

[0010] If yes, proceed to step S4;

[0011] If not, a number of unfinished simulation training projects will be randomly selected for training of the trainees, and then the training will end;

[0012] S4. Select several simulation training projects to repeat the training for the trainees according to the training scores of the previous training cycle.

[0013] Preferably, in step S4, the following steps are specifically included:

[0014] S41. Classify simulation training items into several importance levels and assign basic points according to the importance levels;

[0015] S42, setting the maximum repetition period of each simulation training project;

[0016] S43, calculating the important score according to the training score and basic score of each simulation training project in the previous training cycle, wherein the important score is negatively correlated with the training score and positively correlated with the basic score;

[0017] S44, obtaining the consecutive number of times each simulation training item is not selected;

[0018] S45, determining whether the number of times each simulation training item is not selected is greater than or equal to the maximum repetition period;

[0019] If yes, the selection probability of the simulation training item is set to 1, and then the process goes to step S46;

[0020] If not, proceed to step S46;

[0021] S46, setting the number of simulation training items to be selected, and calculating the difference between the number of selections and the number of simulation training items with a selection probability of 1;

[0022] If the quantity difference is 0, then all simulation training items with a selection probability of 1 are output to train the trainees, and then the process ends;

[0023] If the quantity difference is less than 0, then randomly select simulation training projects with the selection number from the simulation training projects with the selection probability of 1 to train the trainees, and then end;

[0024] If the quantity difference is greater than 0, proceed to step S47;

[0025] S47, marking the simulation training project with a selection probability of 1 as a selected project, and marking the remaining simulation training projects as pending projects;

[0026] S48, calculating the selection probability positively correlated with each simulation training item marked as a candidate item according to its importance score;

[0027] S49, normalizing the selection probabilities of the simulation training items marked as candidate items, and selecting a number of simulation training items according to the normalized selection probabilities, and training the candidates after mixing them with the selected items.

[0028] Preferably, in step S41, the following steps are specifically included:

[0029] S411. Setting several importance levels and corresponding evaluation indexes;

[0030] S412, constructing a grading matrix according to the importance level and evaluation index of any simulation training project relative to the other simulation training projects; the expression of the grading matrix is:

[0031]

[0032] In the above formula, B represents the hierarchical matrix, B i′j′ It represents the evaluation index of the i′th simulation training project corresponding to the j′th simulation training project;

[0033] S413, calculating the weight of any simulation training project according to the grading matrix; the calculation formula of the weight of any simulation training project is:

[0034]

[0035] In the above formula, ω i′ represents the weight of the i'th simulation training project, n 3 represents the number of simulation training projects, B i'j' It represents the evaluation index of the i'th simulation training project corresponding to the j'th simulation training project;

[0036] S414, normalizing the weights of the simulation training items; the calculation formula for the weight of any simulation training item after normalization is:

[0037]

[0038] In the above formula, ω' i' represents the normalized weight of the ith simulation training item, ω i′ represents the weight of the ith simulation training item before normalization, n 3 represents the number of simulation training programs;

[0039] S415, calculating the random consistency ratio of the grading matrix, and determining whether the consistency ratio is less than a consistency ratio threshold;

[0040] If yes, then the normalized weights of each simulation training item are output and the process goes to step S416;

[0041] If not, return to step S411;

[0042] S416. According to the normalized weights of each simulation training item, each simulation training item is respectively assigned a basic score that is positively correlated with the weight.

[0043] Preferably, in step S416, the following steps are specifically included:

[0044] S4161, constructing a weight sequence by normalizing the weights of each simulation training project in ascending order of value, and arranging weights of equal value randomly;

[0045] S4162, set the assignment function to assign positive integers For the weight sequence For any two adjacent weights, if ω i-1 =ω i ,have If i-1 <ω i ,have and For all 1≤i≤n 3 Satisfy the conditions;

[0046] S4163. Calculate the difference between the maximum and minimum values ​​of the weight sequence after different assignment functions are assigned to obtain the function span: the calculation formula of the function span is:

[0047]

[0048] In the above formula, Indicates the function span;

[0049] S4164. Select an assignment function with the smallest function span, and assign a value to each simulation training item according to a weight sequence to obtain a basic score for each simulation training item.

[0050] Preferably, in step S42, the following steps are specifically included:

[0051] S421, setting the maximum repetition period of each simulation training project, and calculating the average value of the maximum repetition period of each simulation training project;

[0052] S422, obtaining the total number of simulation training projects and the number of simulation training projects selected for each training, that is, the number of trainings;

[0053] S423, calculating the quotient of the total number of simulation training items and the number of trainings to obtain the standard number of trainings;

[0054] S424. Calculate the median number of times according to the standard training times; the calculation formula for the median number of times is:

[0055]

[0056] In the above formula, N' represents the median number, N 1 represents the number of standard training times, j represents the number of training times;

[0057] S425, determining whether the average value of the maximum repetition period of each simulation training project is greater than or equal to the median number of times;

[0058] If yes, proceed to step S43;

[0059] If not, return to step S421.

[0060] Preferably, in step S43, the following steps are specifically included:

[0061] S431, obtaining the numerical range of the basic score of each simulation training project and the theoretical distribution range of the training score;

[0062] S432, mapping the training score to the numerical range of the basic score;

[0063] S433, calculating the first important score of each simulation training item according to the mapped training score and the basic score; the calculation formula of the first important score is:

[0064] y 3 =μ 2 y 2 -μ 1 y' 1

[0065] In the above formula, y 3 Indicates the first important score, μ 1 and μ 2 denote the first scale factor and the second scale factor respectively, y′1 denotes the training score after mapping, and y2 denotes the basic score;

[0066] S434. Map the first importance score to a numerical range greater than 0 to obtain an importance score.

[0067] Preferably, in step S48, the following steps are specifically included:

[0068] S481, set S-shaped curve function y = Sigmoid (y ′ 3 ), Sigmoid(y′ 3 ) indicates that the independent variable is y′ 3 Sigmoid function, the range of which is (0,1);

[0069] S482, substituting the importance of each simulation training item marked as a candidate item into the S-shaped curve function to obtain the selection probability of each simulation training item.

[0070] Preferably, in step S432, the expression of the mapping function for mapping the training score to the numerical range of the basic score is:

[0071]

[0072] In the above formula, y′1 and y1 represent the training scores after and before mapping, respectively. and Respectively represent the maximum and minimum values ​​of the theoretical distribution interval, and Respectively represent the maximum and minimum values ​​of the basic score range.

[0073] Preferably, in step S434, the calculation formula of the importance score is:

[0074]

[0075] In the above formula, y′3 and y3 represent the importance score and the first importance score of each simulation training item respectively.

[0076] The technical solution also provides a system for implementing a simulation training method for a gas extraction drilling rig operation process, the system comprising: a processor and a memory, the memory being used to store a computer program, and the computer program implementing the simulation training method when executed by the processor.

[0077] Compared with the prior art, the present invention provides a simulation training method and system for the operation process of a gas extraction drilling rig, which has the following beneficial effects:

[0078] 1. The present invention collects the training status of each employee through a completed simulation training system, that is, first collects the training status of each employee when completing all simulation training projects, that is, the training score, and then according to the preset training cycle, the simulation training system calculates the importance score according to the training score and basic score of each employee in each simulation training project in the previous training cycle, and then calculates the selection probability according to the importance score and the consecutive number of times the simulation training project has not been selected, and according to whether the selection probability is 1, selects different selection methods to select simulation training projects that meet the selection quantity, and trains the trainees.

[0079] 2. The present invention classifies the items according to the severity of the harm caused when errors occur, and distinguishes them by assigning basic points according to the levels. Since the number of simulation training items may be large, the accuracy of grading each simulation training item purely based on personal subjectivity may be relatively low. In order to more accurately judge the importance level of each simulation training item, the weight of each simulation training item is calculated more clearly by constructing a grading matrix and calculating the weight. The larger the weight, the more important the simulation training item.

[0080] 3. In order to ensure that all simulation training projects can be learned by the trainees within one training cycle, the present invention sets a maximum repetition cycle and the consecutive number of times each simulation training project is not selected, thereby ensuring that the knowledge contained in each simulation training project is repeatedly learned by the trainees to avoid forgetting.

[0081] 4. The present invention ensures that the numerical range of the basic scores obtained is smaller and the difference between adjacent basic scores is smaller by setting a unique assignment function, thereby ensuring the uniformity of the basic scores obtained and avoiding the occurrence of extremely individual maximum or minimum values ​​that affect the calculation of subsequent important scores.

[0082] 5. The present invention realizes the calculation of selection probability by setting Sigmoid function, so that the selection probability corresponding to the importance score can be polarized. Therefore, when selecting simulation training projects, simulation training projects with higher importance scores can be selected with a higher probability, so as to achieve more targeted training for trainees, help employees better master unfamiliar content, and improve training effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0084] Figure 1 The present invention is a flow chart of a simulation training method for a gas extraction drilling rig operation process. DETAILED DESCRIPTION

[0085] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0086] Those skilled in the art can understand that all or part of the steps in the following embodiments can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0087] After preliminary investigation, according to the requirements of regulations and manuals such as the "Coal Mine Safety Regulations" and the "Technical Manual for Mine Disaster Prevention", the relevant technical information and knowledge of laws, regulations and standards were sorted out to further clarify the specific needs of the gas extraction drill operator job simulation training system. Combined with the coal mine gas extraction worker operating procedures and the working principle of the gas extraction drill, the operation process was disassembled and differentiated, and the entire gas extraction drill operator job process was reproduced in a virtual environment for specific process flows, and digital development was carried out. Based on key technologies such as Unity3D technology, industrial simulation system and C4D modeling tools, the actual working environment of the gas extraction drill operator was carefully modeled, the gas extraction drill equipment (including main engine, pump station, operating table, explosion-proof computer, flow meter, electromagnetic starting cabinet, emergency stop switch and other components), underground tunnels, working environment, etc., and various production conditions that appeared in various operating conditions in the system were simulated through algorithms. Finally, the system completed the full process of job standardization training through virtual teacher guidance to immersive simulation practical assessment.

[0088] Based on the developed simulation training system, the present invention further solves the problem that the existing simulation training system is difficult to train different employees for weak items that they have not yet mastered, resulting in insufficient training efficiency of the simulation training system for employees. A simulation training method for the operation process of a gas extraction drilling rig is provided. According to the training records of the employees, simulation training items are selected from the weak items that the employees have not yet mastered with a set probability to train the employees. The selected simulation training items are uncertain, making it difficult for the employees to study individual items before the training to ensure the training score, so that the employees can fully master all the simulation training items. The simulation training method specifically includes the following steps:

[0089] S1. Several simulation training projects including the operation process of gas extraction drilling rigs are set up in the simulation training system. The simulation training projects are simulation modeling of the standardized operations of each process position stated in the previous article.

[0090] S2. The simulation training system obtains the personal data of the trainees in the previous training cycle; the personal data includes the identity information of the trainees, the completed simulation training projects and the corresponding training scores. During the training process, the employee's operation will be compared with the operation standard to score the training score. During the training process, in order to prevent employees from forgetting after learning, all simulation training projects will be re-learned and consolidated within a certain period (i.e., training cycle), which can be uniformly set to half a year or one year, or can be set separately according to the employee's own learning situation and position.

[0091] S3, judging whether the trainee has completed all the simulation training projects. The trainee, i.e. the employee being trained, has completed all the simulation training projects after using the simulation training system. In order to ensure a full assessment of the employee's weak projects, if all the simulation training projects have not been completed, the employee will be asked to continue to complete the unfinished simulation training projects. After the employee has completed all the simulation training projects, training will be conducted on the weak projects.

[0092] If yes, proceed to step S4;

[0093] If not, a number of unfinished simulation training projects will be randomly selected for training of the trainees, and then the training will end;

[0094] S4. Select several simulation training projects for repeated training of the trainees according to the training scores of the previous training cycle. You can directly select the simulation training projects with lower training scores in the previous training process to train the employees again this time. However, this method may make the employees predict the simulation training projects of this training in advance, so as to temporarily memorize them to cope with the training. After the training, they may still forget them quickly. Therefore, in order to stimulate the self-learning ability of employees and make them more firmly remember the weak simulation training projects, the weak projects of employees can be trained repeatedly until the employees truly master the corresponding knowledge content to fully ensure mining safety. The selection of simulation training projects specifically includes the following steps:

[0095] S41. Classify the simulation training projects into several levels of importance, and assign basic points according to the importance levels. Different simulation training projects are graded according to the size of the harm caused by errors, and basic points are assigned according to the levels. Since there may be a large number of simulation training projects, the accuracy of grading each simulation training project purely based on personal subjectivity may be relatively low. In order to more accurately judge the importance level of each simulation training project, the following steps are used to grade and assign basic points:

[0096] S411. Setting several importance levels and corresponding evaluation indexes, as shown in Table 1, is a method for setting importance levels;

[0097]

[0098] S412, constructing a grading matrix according to the importance level and evaluation index of any simulation training project relative to the other simulation training projects; the expression of the grading matrix is:

[0099]

[0100] In the above formula, B represents the hierarchical matrix, B i′j′ It represents the evaluation index of the i'th simulation training project corresponding to the j'th simulation training project;

[0101] S413, calculating the weight of any simulation training project according to the grading matrix; the calculation formula of the weight of any simulation training project is:

[0102]

[0103] In the above formula, ω i' represents the weight of the i'th simulation training project, n 3 represents the number of simulation training projects, B i'j' It represents the evaluation index of the i'th simulation training project corresponding to the j'th simulation training project;

[0104] S414, normalizing the weights of the simulation training items; the calculation formula for the weight of any simulation training item after normalization is:

[0105]

[0106] In the above formula, ω' i' represents the normalized weight of the ith simulation training item, ω i' represents the weight of the i'th simulation training item before normalization, n 3 represents the number of simulation training programs;

[0107] S415, calculating the random consistency ratio of the grading matrix, and determining whether the consistency ratio is less than a consistency ratio threshold;

[0108] If yes, then the normalized weights of each simulation training item are output and the process goes to step S416;

[0109] If not, return to step S411;

[0110] S416. According to the normalized weights of the simulation training items, basic scores that are positively correlated with the weights are assigned to the simulation training items. The higher the weight of the simulation training item, the higher the importance of the simulation training item, and the higher the probability that the simulation training item will be selected for employee training in subsequent training. When assigning the benchmark score, a higher basic score is assigned to the item. However, in order to ensure that the basic scores of the simulation training items corresponding to weights with closer values ​​are relatively closer, a basic score assignment method is provided, which specifically includes the following steps:

[0111] S4161. Construct a weight sequence from the normalized weights of each simulation training project in ascending order, and randomly arrange weights of equal value. For example, there are several weights 1, 2, 3, 3, 5, and the weight sequence they constitute is {1, 2, 3, 3, 5}. Among them, the weight value of two simulation training projects is 3. The positions of these two simulation training projects with the weight value of 3 are randomly arranged in sequence.

[0112] S4162, set the assignment function to assign positive integers For the weight sequence For any two adjacent weights, if ω i-1 =ω i ,have If i-1 <ω i ,have and For all 1≤i≤n 3 Satisfy the conditions;

[0113] S4163. Calculate the difference between the maximum value and the minimum value after different assignment functions are assigned to the weight sequence to obtain the function span: the calculation formula of the function span is:

[0114]

[0115] In the above formula, Indicates the function span;

[0116] S4164. Select the assignment function with the smallest function span, and assign values ​​to each simulation training item according to the weight sequence to obtain the basic score of each simulation training item, so as to ensure that the difference between the values ​​of the basic scores is minimized on the basis of being able to distinguish the importance, thereby minimizing the numerical range of the basic scores, avoiding individual extremely large or extremely small values ​​in the basic scores, and making the distribution of the basic scores more uniform, thereby facilitating the credibility of the important scores calculated in step S43.

[0117] S42, setting the maximum repetition period of each simulation training project, the maximum repetition period is the maximum number of times the simulation training project is not selected, which can be preset in the background in advance. When the maximum number is reached, the simulation training project will be selected according to the method recorded in the subsequent steps. As for the maximum repetition period, in order to avoid a large number of simulation training projects reaching the maximum repetition period together, which makes the setting of the basic score meaningless, it is judged whether the maximum repetition period of each simulation training project is reasonable to ensure the significance of the setting of the basic score, so as to better select the simulation training projects that the employees have not fully mastered through subsequent calculations. The method specifically includes the following steps:

[0118] S421, setting the maximum repetition period of each simulation training project, and calculating the average value of the maximum repetition period of each simulation training project;

[0119] S422, obtaining the total number of simulation training projects and the number of simulation training projects selected for employee training in each training, that is, the number of trainings;

[0120] S423, calculating the quotient of the total number of simulation training items and the number of trainings, that is, dividing the total number of simulation training items by the number of trainings to obtain the standard number of trainings;

[0121] S424. Calculate the median number of times according to the standard training times; the calculation formula for the median number of times is:

[0122]

[0123] In the above formula, N' represents the median number, N 1 represents the number of standard training times, j represents the number of training times;

[0124] S425, determining whether the average value of the maximum repetition period of each simulation training project is greater than or equal to the median number of times;

[0125] If yes, proceed to step S43;

[0126] If not, return to step S421 to reset the maximum repetition period of each simulation training item.

[0127] S43. Calculate the importance score based on the training scores and basic scores of each simulation training project in the previous training cycle. The importance score is negatively correlated with the training score and positively correlated with the basic score. At this time, the numerical ranges of the basic score and the training score may be extremely different. For example, if the basic score is a four-digit number and the training score is a single-digit number, the training score has a very small impact on the importance score. Therefore, it is necessary to convert them so that the basic score and the training score have the same impact on the importance score. Then, according to daily experience, the impact ratio is set again, that is, the first proportional factor and the second proportional factor recorded later, so as to calculate the importance score more scientifically. The calculation of the important score specifically includes the following steps:

[0128] S431. Obtain the numerical range of the basic score of each simulation training project and the theoretical distribution range of the training score. The numerical range of the basic score is the numerical range between the maximum value and the minimum value of the basic score, and includes the maximum value and the minimum value of the basic score. For the theoretical distribution range of the training score, if the full score of the training score is set to 100 points, then in general, the theoretical distribution range of the training score is [0,100].

[0129] S432, mapping the training score to the numerical range of the basic score; the expression of the mapping function is:

[0130]

[0131] In the above formula, y' 1 and 1 denote the training scores after and before mapping, respectively, and Respectively represent the maximum and minimum values ​​of the theoretical distribution interval, and Respectively represent the maximum and minimum values ​​of the basic score range;

[0132] S433, calculating the first important score of each simulation training item according to the mapped training score and the basic score; the calculation formula of the first important score is:

[0133] y 3 =μ 2 y 2 -μ 1 y' 1

[0134] In the above formula, y 3 Indicates the first important score, μ 1 and μ 2 Represent the first scale factor and the second scale factor, y' 1 represents the training score after mapping, y 2 Indicates basic score;

[0135] S434, mapping the first importance score to a numerical range greater than 0 to obtain an importance score; the calculation formula of the importance score is:

[0136]

[0137] In the above formula, y' 3 and 3 Respectively represent the importance score and the first important score of each simulation training item.

[0138] S44, obtaining the consecutive number of times each simulation training item is not selected;

[0139] S45, determining whether the number of times each simulation training item is not selected is greater than or equal to the maximum repetition period;

[0140] If yes, the selection probability of the simulation training item is set to 1, and then the process goes to step S46;

[0141] If not, proceed to step S46;

[0142] S46, setting the selection quantity of the simulation training items, and calculating the difference between the selection quantity and the quantity of the simulation training items with a selection probability of 1, that is, subtracting the number of simulation training items with a selection probability of 1 from the selection quantity, thereby obtaining the quantity difference;

[0143] If the quantity difference is 0, then all simulation training items with a selection probability of 1 are output to train the trainees, and then the process ends;

[0144] If the quantity difference is less than 0, then randomly select simulation training projects with the selection number from the simulation training projects with the selection probability of 1 to train the trainees, and then end;

[0145] If the quantity difference is greater than 0, the process proceeds to step S47. At this time, in addition to training the trainee with all the simulation training projects with a selection probability of 1, it is also necessary to select some from the simulation training projects with a selection probability of not 1, so that the total number of simulation training projects for training the trainee is the preset selection number, that is, the simulation training projects for training the trainee may include both simulation training projects with a selection probability of 1 and simulation training projects with a selection probability of not 1. Of course, the number of simulation training projects with a selection probability of 1 can be 0, while the number of simulation training projects with a selection probability of not 1 is greater than 0.

[0146] S47, marking the simulation training project with a selection probability of 1 as a selected project, and marking the remaining simulation training projects as pending projects;

[0147] S48. Calculate the selection probability positively correlated with the important scores of each simulation training project marked as a candidate project. In order to make the selection probability of the important scores in the middle part of the important score value range present a large difference, so that when selecting simulation training projects, the weak simulation training projects that employees have not fully mastered can be given a greater selection probability, so that the probability of being selected in this selection of simulation training projects is greater, so as to better achieve the training effect on employees. Therefore, the calculation of the selection probability specifically includes the following steps:

[0148] S481, set the S-shaped curve function y = Sigmoid (y' 3 ), Sigmoid(y' 3 ) indicates that the independent variable is y' 3 The Sigmoid function has a range of (0,1); the function value of the Sigmoid function is positively correlated with the importance score of each simulation training project marked as a candidate item. When designing the score of the simulation training project, about 60 points are generally set as the qualified score, which is exactly in the middle value area of ​​the training score. Therefore, this function can be used to comprehensively consider the basic score and use the important score as the dependent variable to calculate the selection probability through this function. On the basis of considering the importance of the simulation training project, the selection probability of the simulation training project with poor mastery and the simulation training project with good mastery can be further polarized, so that the content of the simulation training project that the employees have not mastered well can be better selected in the future;

[0149] S482, substituting the importance of each simulation training item marked as a candidate item into the S-shaped curve function to obtain the selection probability of each simulation training item.

[0150] S49. Normalize the selection probability of each simulation training project marked as a candidate project. The normalized selection probability is the selection probability of each simulation training project before normalization divided by the sum of the selection probabilities of each simulation training project before normalization. Select a number of simulation training projects based on the normalized selection probability, and mix them with the selected projects to train the trainees. The number of mixed simulation training projects is the selection number, that is, the total number of simulation training projects that meet the preset requirement for training the trainees.

[0151] When the present invention is actually running, the training situation of each employee is first collected through the completed simulation training system, that is, the training situation of each employee when completing all simulation training projects, that is, the training score, is first collected. Then, according to the preset training cycle, the simulation training system calculates the importance score according to the training score and basic score of each simulation training project in the previous training cycle of each employee, and then calculates the selection probability according to the importance score and the number of consecutive times that the simulation training project has not been selected, and according to whether the selection probability is 1, different selection methods are selected to select simulation training projects that meet the selection quantity, and train the trainees.

[0152] Corresponding to the simulation training method for the gas extraction drilling rig operating process provided in the above-mentioned embodiment, the present embodiment also provides a system for implementing the simulation training method for the gas extraction drilling rig operating process. Since the simulation training system for the gas extraction drilling rig operating process provided in the present embodiment corresponds to the simulation training method for the gas extraction drilling rig operating process provided in the above-mentioned embodiment, the implementation method of the simulation training method for the aforementioned gas extraction drilling rig operating process is also applicable to the simulation training system for the gas extraction drilling rig operating process provided in the present embodiment, and will not be described in detail in the present embodiment.

[0153] The system comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, a simulation training method for the operation process of a gas extraction drilling rig is realized.

[0154] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A simulation training method for the operation process of a gas extraction drilling rig, characterized in that: The simulation training method specifically includes the following steps: S1. Setting up several simulation training projects including the operation process of gas extraction drilling rigs in the simulation training system; S2. The simulation training system obtains personal data of the trainee in the previous training cycle, wherein the personal data includes identity information of the trainee, completed simulation training projects and corresponding training scores; S3, judging whether the trainee has completed all simulation training items; If yes, proceed to step S4; If not, a number of unfinished simulation training projects will be randomly selected for training of the trainees, and then the training will end; S4. Select several simulation training projects to repeat the training for the trainees according to the training scores of the previous training cycle.

2. The simulation training method according to claim 1, characterized in that: In step S4, the following steps are specifically included: S41. Classify simulation training items into several importance levels and assign basic points according to the importance levels; S42, setting the maximum repetition period of each simulation training project; S43, calculating the important score according to the training score and basic score of each simulation training project in the previous training cycle, wherein the important score is negatively correlated with the training score and positively correlated with the basic score; S44, obtaining the consecutive number of times each simulation training item is not selected; S45, determining whether the number of times each simulation training item is not selected is greater than or equal to the maximum repetition period; If yes, the selection probability of the simulation training item is set to 1, and then the process goes to step S46; If not, proceed to step S46; S46, setting the number of simulation training items to be selected, and calculating the difference between the number of selections and the number of simulation training items with a selection probability of 1; If the quantity difference is 0, then all simulation training items with a selection probability of 1 are output to train the trainees, and then the process ends; If the quantity difference is less than 0, then randomly select simulation training projects with the selection number from the simulation training projects with the selection probability of 1 to train the trainees, and then end; If the quantity difference is greater than 0, proceed to step S47; S47, marking the simulation training project with a selection probability of 1 as a selected project, and marking the remaining simulation training projects as pending projects; S48, calculating the selection probability positively correlated with each simulation training item marked as a candidate item according to its importance score; S49, normalizing the selection probabilities of the simulation training items marked as candidate items, and selecting a number of simulation training items according to the normalized selection probabilities, and training the candidates after mixing them with the selected items.

3. The simulation training method according to claim 2, characterized in that: In step S41, the following steps are specifically included: S411. Setting several importance levels and corresponding evaluation indexes; S412, constructing a grading matrix according to the importance level and evaluation index of any simulation training project relative to the other simulation training projects; the expression of the grading matrix is: In the above formula, B represents the hierarchical matrix, B i′j′ It represents the evaluation index of the i′th simulation training project corresponding to the j′th simulation training project; S413, calculating the weight of any simulation training project according to the grading matrix; the calculation formula of the weight of any simulation training project is: In the above formula, ω i' represents the weight of the i'th simulation training project, n3 represents the number of simulation training projects, B i'j' It represents the evaluation index of the i'th simulation training project corresponding to the j'th simulation training project; S414, normalizing the weights of the simulation training items; the calculation formula for the weight of any simulation training item after normalization is: In the above formula, ω' i' represents the normalized weight of the ith simulation training item, ω i' represents the weight of the i'th simulation training project before normalization, and n3 represents the number of simulation training projects; S415, calculating the random consistency ratio of the grading matrix, and determining whether the consistency ratio is less than a consistency ratio threshold; If yes, then the normalized weights of each simulation training item are output and the process goes to step S416; If not, return to step S411; S416. According to the normalized weights of each simulation training item, each simulation training item is respectively assigned a basic score that is positively correlated with the weight.

4. The simulation training method according to claim 3, characterized in that: In step S416, the following steps are specifically included: S4161, constructing a weight sequence by normalizing the weights of each simulation training project in ascending order of value, and arranging weights of equal value randomly; S4162, set the assignment function to assign positive integers For the weight sequence For any two adjacent weights, if ω i-1 =ω i ,have If i-1 <ω i ,have and For all 1≤i≤n3, the condition is satisfied; S4163. Calculate the difference between the maximum value and the minimum value after different assignment functions are assigned to the weight sequence to obtain the function span: the calculation formula of the function span is: In the above formula, Indicates the function span; S4164. Select an assignment function with the smallest function span, and assign a value to each simulation training item according to a weight sequence to obtain a basic score for each simulation training item.

5. The simulation training method according to claim 1, characterized in that: In step S42, the following steps are specifically included: S421, setting the maximum repetition period of each simulation training project, and calculating the average value of the maximum repetition period of each simulation training project; S422, obtaining the total number of simulation training projects and the number of simulation training projects selected for each training, that is, the number of trainings; S423, calculating the quotient of the total number of simulation training items and the number of trainings to obtain the standard number of trainings; S424. Calculate the median number of times according to the standard training times; the calculation formula for the median number of times is: In the above formula, N' represents the median number, N 1 represents the number of standard training times, j represents the number of training times; S425, determining whether the average value of the maximum repetition period of each simulation training project is greater than or equal to the median number of times; If yes, proceed to step S43; If not, return to step S421.

6. The simulation training method according to claim 1, characterized in that: In step S43, the following steps are specifically included: S431, obtaining the numerical range of the basic score of each simulation training project and the theoretical distribution range of the training score; S432, mapping the training score to the numerical range of the basic score; S433, calculating the first important score of each simulation training item according to the mapped training score and the basic score; the calculation formula of the first important score is: y3=μ2y2-μ1y′1 In the above formula, y3 represents the first important score, μ1 and μ2 represent the first scale factor and the second scale factor respectively, y′1 represents the training score after mapping, and y2 represents the basic score; S434. Map the first importance score to a numerical range greater than 0 to obtain an importance score.

7. The simulation training method according to claim 1, characterized in that: In step S48, the following steps are specifically included: S481, setting the S-shaped curve function y=Sigmoid(y′3), where Sigmoid(y′3) represents the Sigmoid function with the independent variable y′3, and the value range of the function is (0,1); S482, substituting the importance of each simulation training item marked as a candidate item into the S-shaped curve function to obtain the selection probability of each simulation training item.

8. The simulation training method according to claim 6, characterized in that: In step S432, the expression of the mapping function for mapping the training score to the numerical range of the basic score is: In the above formula, y′1 and y1 represent the training scores after and before mapping, respectively. and Respectively represent the maximum and minimum values ​​of the theoretical distribution interval, and Respectively represent the maximum and minimum values ​​of the basic score range.

9. The simulation training method according to claim 6, characterized in that: In step S434, the calculation formula of the importance score is: In the above formula, y′3 and y3 represent the importance score and the first importance score of each simulation training item respectively.

10. A system for implementing the simulation training method according to any one of claims 1 to 9, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the simulation training method according to any one of claims 1 to 9 is implemented.

Images