An intelligent prediction method and system for the service life of positive displacement motor

Abstract

The present invention provides an intelligent method and system for predicting the service life of a positive displacement motor, relating to the technical field of predicting the service life of a positive displacement motor. The method includes collecting historical service life data of positive displacement motors, performing clustering division based on the characteristics of the usage duration to form service life data sets with different duration characteristics; for the service life data sets with different duration characteristics, performing data extraction and analysis based on the usage characteristics and establishing corresponding clustering service life prediction models; performing consistency analysis on different clustering service life prediction models to determine a service life prediction model for the positive displacement motor; obtaining the current usage data of the target positive displacement motor, and determining the effective remaining service life of the target positive displacement motor according to the service life prediction model. This method realizes the prediction of the service life of the positive displacement motor by using historical usage big data to perform reasonable service life prediction analysis and establish a reasonable and accurate service life prediction model.

Description

Technical Field

[0001] The present invention relates to the technical field of life prediction of positive displacement downhole motors, and more particularly, to an intelligent method and system for predicting the life of positive displacement downhole motors. Background Art

[0002] A positive displacement downhole motor is a positive displacement downhole power drill that uses drilling fluid as power to convert liquid pressure energy into mechanical energy. Since the positive displacement downhole motor works in a high-pressure and high-temperature working environment, it causes great damage to the drill itself, especially the fatigue damage caused by different factors. After long-term accumulation, it affects the service life of the positive displacement downhole motor. At the same time, the positive displacement downhole motor is a high-value drilling tool. Therefore, reasonable storage and use of it are effective methods to improve its utilization rate.

[0003] Predicting the life of the positive displacement downhole motor can provide enterprises with reasonable cost planning and operation arrangements. Currently, there is no established method that can reasonably and accurately predict the life of the positive displacement downhole motor. At present, the life prediction of the positive displacement downhole motor is basically based on visual observation by experience, and the prediction results have a large deviation.

[0004] Therefore, designing an intelligent method and system for predicting the life of the positive displacement downhole motor, and establishing a reasonable and accurate life prediction model through reasonable life prediction analysis using historical usage big data to achieve the prediction of the remaining life of the positive displacement downhole motor is an urgent problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent method for predicting the life of a positive displacement downhole motor. By obtaining the big data of historical positive displacement downhole motors and conducting life prediction model analysis based on the factors affecting the life of the positive displacement downhole motor, a life prediction model for these factors affecting the life of the positive displacement downhole motor is established, so as to achieve reasonable and accurate prediction of the remaining life of the positive displacement downhole motor. This method is based on big data analysis and processing, and uses the method of cluster analysis, which can reasonably and accurately predict the life under different usage conditions to a certain extent, covering a large range of life prediction scenarios of the positive displacement downhole motor. At the same time, with big data as a reference, it greatly improves the accuracy of the life prediction of the positive displacement downhole motor, providing a more reasonable and accurate reference basis for the planning of the use of the positive displacement downhole motor.

[0006] The purpose of the present invention is also to provide an intelligent system for predicting the life of a positive displacement downhole motor. This system is a complete system that can predict the life of the positive displacement downhole motor by configuring a life prediction model analysis that can use historical big data for clustering, fully ensuring the efficient and accurate implementation of the life prediction of the positive displacement downhole motor, and is an important material basis for achieving reasonable and accurate life prediction of the positive displacement downhole motor.

[0007] In a first aspect, the present invention provides an intelligent method for predicting the service life of a positive displacement motor, including: collecting historical service life data of positive displacement motors, performing clustering division based on the characteristics of the usage duration to form service life data sets with different duration characteristics; for the service life data sets with different duration characteristics, performing data extraction and analysis based on usage characteristics to establish corresponding clustering service life prediction models; performing consistency analysis on different clustering service life prediction models to determine the service life prediction model of the positive displacement motor; obtaining the current usage data of the target positive displacement motor, and determining the effective remaining service life of the target positive displacement motor according to the service life prediction model of the positive displacement motor.

[0008] In the present invention, this method analyzes the service life prediction model based on the factors affecting the service life of the positive displacement motor by obtaining the big data of historical positive displacement motors, and then establishes the service life prediction models of these factors affecting the service life of the positive displacement motor, so as to realize a reasonable and accurate prediction of the remaining service life of the positive displacement motor. This method is based on big data analysis and processing, and adopts the method of cluster analysis, which can reasonably and accurately predict the service life under different usage conditions to a certain extent, covering a large range of service life prediction scenarios of positive displacement motors. At the same time, with big data as a reference, the accuracy of the service life prediction of the positive displacement motor is greatly improved, providing a more reasonable and accurate reference basis for the planning of the use of positive displacement motors.

[0009] As a possible implementation, collecting historical service life data of positive displacement motors, performing clustering division based on the characteristics of the usage duration to form service life data sets with different duration characteristics, includes: extracting the usage duration characteristic information of different historical positive displacement motors according to the historical service life data of positive displacement motors; performing clustering division on different historical positive displacement motors according to the usage duration characteristic information of different historical positive displacement motors to form service life data sets with different duration characteristics.

[0010] In the present invention, the historical service life data of positive displacement motors includes the data during the entire effective service life of different positive displacement motors from the start of use to the inability to perform normal operations. Considering that the impact on the service life of the positive displacement motor is closely related to the usage situation, before establishing the prediction model for the service life of the positive displacement motor, it is necessary to reasonably cluster and divide the data according to different usage situations, so that the subsequent obtained service life prediction model is more targeted and accurate. Of course, a more reasonable way is to perform another clustering on the specific product form of the positive displacement motor, which can more accurately ensure the service life prediction of different types of positive displacement motor products. It should be noted that for the clustering division according to different usage situations of positive displacement motors, since the impact on the service life of the positive displacement motor is caused by the main factors acting over a certain time dimension span, the clustering division can be carried out with reference to the usage duration characteristics to ensure the rationality and correctness of the clustering.

[0011] As a possible implementation, according to the historical service life data of screw drill tools, extract the usage duration characteristic information of different historical screw drill tools, including: for different historical screw drill tools, determine the historical single - use duration each time they are used within the historical service life and the historical single - idle duration , represents the number of usage times within the corresponding historical service life, represents the number of idle times within the corresponding historical service life; according to the historical single - idle duration , determine the single - average idle duration corresponding to the historical screw drill tool , where ; according to the historical single - use duration , determine the single - average use duration corresponding to the historical screw drill tool , where .

[0012] In the present invention, based on the duration characteristic information of the screw drill tool, the characteristics in the time dimension to be considered for clustering and dividing the screw drill tool according to the usage conditions of different screw drill tools mainly include three aspects. The first aspect is the working use duration characteristic of the operation carried out by the screw drill tool within the effective service life cycle. Considering that the environmental conditions during the operation of the screw drill tool are completely different from those during non - use and idle, and the impact of the operation on the service life of the screw drill tool is much greater than that during idle, the use duration characteristic information within the entire service life cycle needs to be considered first. It can be understood that the use duration of the screw drill tool will occur multiple times within the entire service life cycle, and the use duration each time is not the same. Representing the overall use duration through the average duration of each use has a certain representativeness for the impact of the use duration on the service life of the screw drill tool. Therefore, the single - average use duration needs to be considered. The second aspect is the duration characteristic of the screw drill tool when it is idle without operation within the entire service life cycle. In the case of idleness, different storage methods and environmental conditions will cause different degrees of impact on the service life of the screw drill tool. After all, the humidity, temperature, etc. of the environment during idle can affect the performance of the screw drill tool, thereby affecting its service life. Similarly, within the entire service life cycle of the screw drill tool, its idle situation will occur multiple times and intersect with the operation duration. The single - average idle duration can, to a certain extent, reflect the degree to which the service life of the screw drill tool is affected by the idle duration. Therefore, the single - average idle duration needs to be considered. The third aspect is the utilization rate of the screw drill tool. It can be understood that the more times the screw drill tool is used, the shorter its service life. Therefore, the number of uses is also an important factor determining the screw drill tool. And for both the number of operations and the number of idle times, they need to be considered to accurately define the usage situation of the screw drill tool reasonably.

[0013] As a possible implementation, according to the usage duration characteristic information of different historical positive displacement motors, different historical positive displacement motors are clustered and divided to form different duration characteristic life data sets, including: setting a clustering idle time difference threshold , a clustering usage time difference threshold , a clustering number difference threshold , and performing clustering and division in the following manner: For any two different historical positive displacement motors, if the following four conditions are simultaneously satisfied, the historical life data of the corresponding two historical positive displacement motors are taken as the same class: The difference in the single - time average idle duration between two different historical positive displacement motors does not exceed the clustering idle time difference threshold ; the difference in the single - time average usage duration between two different historical positive displacement motors does not exceed the clustering usage time difference threshold ; the difference in the number of uses between two different historical positive displacement motors does not exceed the clustering number difference threshold ; the difference in the number of idle times between two different historical positive displacement motors does not exceed the clustering number difference threshold ; The historical life data of all historical positive displacement motors to be taken as the same class are clustered to form the corresponding duration characteristic life data.

[0014] In the present invention, it should be noted that the usage situations of different positive displacement motors in a timely manner are generally the same, and it is impossible to maintain a high degree of consistency or even sameness in the single - time average usage duration, single - time average idle duration, and the number of idle and use times. Therefore, when clustering and dividing different positive displacement motors based on these duration characteristics, it is a reasonable clustering method to determine whether to cluster by determining the difference in the duration characteristics of different positive displacement motors. The clustering idle time difference threshold, clustering usage time difference threshold, and clustering number difference threshold can be set according to actual needs or determined based on big data analysis.

[0015] As a possible implementation, for different duration characteristic life data sets, data extraction and analysis based on usage characteristics are performed to establish corresponding clustering life prediction models, including: For different duration characteristic life data sets, the usage duration characteristic information and usage characteristic information of different historical positive displacement motors are extracted to form corresponding life prediction relationships; According to the life prediction relationships corresponding to different historical positive displacement motors, relationship confirmation analysis is performed to form the clustering life prediction models corresponding to the duration characteristic life data sets.

[0016] In the present invention, after the clustering and classification of different historical positive displacement motors are completed, targeted life prediction analysis can be carried out on different clustering data, and a reasonable life prediction model can be established. To establish a prediction model for predicting the life of a positive displacement motor, factors affecting the life of the positive displacement motor need to be considered. Therefore, a comprehensive life prediction model is established by determining the influence amount of these factors on the life. Therefore, for the analysis of these factors, extraction needs to be carried out from the usage characteristic information.

[0017] As a possible implementation method, for different duration characteristic life data sets, the usage duration characteristic information and usage characteristic information of different historical positive displacement motors are extracted to form corresponding life prediction relationships, including: for different historical positive displacement motors, the corresponding single - time average idle duration and the number of idle times are extracted, and an idle - life influence relationship is established, where: , represents the idle life influence factor, and , represents the idle life influence factor, and k takes 1, 2, 3; for different historical positive displacement motors, the corresponding single - time average usage duration and the number of idle times are extracted, and a usage - life influence relationship is established, where: , represents the service life influence factor, and , represents the service life influence factor; for different historical positive displacement motors, the total working duration , the total working duration corresponding environmental temperature change factor as well as the total working duration corresponding drill temperature change factor are extracted, and a temperature - life influence relationship is established, where: , , represents the working temperature life influence factor, represents the temperature conversion life influence factor; for different historical positive displacement motors, the total working duration and the total working duration corresponding working load life influence factor are extracted, and a load - life influence relationship is established, where: , represents the compliance conversion life influence factor; for different historical positive displacement motors, the total working duration , the total working duration The corresponding environmental humidity change factor and the total working duration The corresponding humidity change factor of the drill tool , and establish the humidity-life impact relationship , where: , , represents the working humidity life impact factor, represents the humidity conversion life impact factor; According to the idle-life impact relationship , the use-life impact relationship , the temperature-life impact relationship , the load-life impact relationship and the humidity-life impact relationship , establish the following life prediction relationship: , represents the predicted life value, represents the total number of factors of the life impact factors included in the life prediction relationship, and γ represents the predicted adjusted life impact factor.

[0018] In the present invention, it can be understood that the service life of a positive displacement motor mainly refers to the process of functional failure of the positive displacement motor. The main factors affecting the function of the positive displacement motor include the environmental factors and operating factors of the positive displacement motor. In this application, for the environmental factors, mainly two factors, namely humidity and temperature, are considered. For the operating factors, the working load is considered. It should be noted that there may be multiple factors affecting the service life of the positive displacement motor, and the influence magnitudes and degrees of different factors on the service life of the positive displacement motor are different. Among these factors, some are indirect and some are direct. For example, the regional factor mainly affects the service life of the positive displacement motor through different humidity and temperature. Therefore, through observation and analysis, it is reasonable to use humidity and temperature as the two most important direct influencing factors for life prediction analysis. Of course, for the working load, it can be a direct operating force load or a combination of various static and dynamic forces acting on the positive displacement motor during operation. In addition, when establishing the life prediction relationship, considering that different factors affecting the service life of the positive displacement motor have different effects on its service life, it is necessary to first establish the corresponding influence relationships separately before comprehensively forming the life prediction relationship of the positive displacement motor. Here, for the idle time and usage time, since these time lengths do not have an equal influence relationship on the service life of the positive displacement motor, there is a conversion relationship between life and time length. In order to avoid overly complex data processing and to ensure that this conversion relationship can be determined more accurately, the life influence factors under the established influence relationship are all characterized by quadratic polynomials. Similarly, for humidity, temperature, and working load, their influences on life are not equal, so conversion is required. Therefore, different conversion life influence factors are provided for different influencing factors. Of course, for humidity and temperature, since the changes in humidity and temperature during operation are much greater than the environmental humidity and temperature, the environmental temperature and environmental humidity do not need to be considered, and the influence of environmental temperature and environmental humidity will not have an obvious impact on life during the operation process. The actual temperature and humidity obtained during operation are the result of the superposition of environmental conditions. Therefore, the influence of environmental conditions needs to be removed when establishing the influence factors. For temperature, humidity, and working load, the cumulative situations of these factors can all be obtained based on historical data, but these factors also change with the time dimension.

[0019] As a possible implementation manner, according to the life prediction relationships corresponding to different historical positive displacement motors, relationship confirmation analysis is performed to form a clustering life prediction model for the duration feature life data set, including: with the total number of factors +1 is the quantity unit of grouping. Different historical life data in the duration feature life dataset are randomly extracted to form different duration feature life data groups. For different duration feature life data groups, all life influencing factors are determined according to the life prediction relationships corresponding to different historical life data in the group. For all life influencing factors determined for different duration feature life data groups, the average value of the same life influencing factors on different groups is obtained. The average value of different life influencing factors is used as the value of the corresponding life influencing factor in the life prediction relationship, forming a clustering life prediction model corresponding to the duration feature life dataset.

[0020] In the present invention, after establishing its corresponding clustering life prediction model, it is necessary to determine the life influencing factors set in the established model, so as to form a life prediction model without unknown quantities. The number of clustering life prediction models established in the dataset is greater than the size of the unknown quantities. Therefore, as long as the minimum number of models capable of determining the life influencing factors is provided, the determination of the life influencing factors in the model can be achieved. Here, it should be noted that in the clustering life prediction relationship, it can be considered that different life prediction values are the same, which is used as the standard reference for the total life under the corresponding usage conditions. Since the prediction using the prediction model is always carried out when the positive displacement motor has not reached the life limit, the prediction result obtained using the prediction model is numerically less than the life prediction value. However, the remaining effective life of the positive displacement motor can be determined by combining the life prediction value and the prediction result obtained by analyzing the prediction model.

[0021] As a possible implementation manner, consistency analysis is performed on different clustering life prediction models to determine the positive displacement motor life prediction model, including: for different clustering life prediction models, extracting the corresponding different life influencing factors to form the corresponding clustering life influencing factor set; for different clustering life influencing factor sets, performing model consistency judgment in the following manner: setting the factor consistency judgment threshold and the total factor deviation threshold , where x takes α, β, w, f, c; randomly extract two clustering life influencing factor sets and determine the cumulative factor difference of the corresponding influencing factors at the corresponding duration ; if for any cumulative factor difference all satisfy: and ≤ , it is determined that the two clustering life prediction models are consistent. The life influence factor with the largest cumulative factor of the same clustering life influence factor at the corresponding time duration is used as the representative life influence factor of the two clustering life prediction models, and a new life prediction model is formed based on different representative life influence factors. The newly formed life prediction model is also used as the object of consistency judgment and continues to be judged for consistency until no new life prediction model is formed. All the life prediction models after consistency judgment are determined as the life prediction models of the positive displacement motor.

[0022] In the present invention, different clustering life prediction models represent the conditions of the positive displacement motor under different usage conditions. However, considering that similar life development situations may also occur under different usage conditions, in order to improve the applicability of the life prediction model, it is necessary to perform consistency analysis on different clustering life prediction models to complete comprehensive merging. This consistency analysis mainly considers that different influencing factors may have similarities in predicting life under overall conditions. Therefore, the consistency judgment is also made based on the closeness of the cumulative amounts of all influencing factors in the time dimension. Of course, considering fully ensuring the accuracy of the prediction results of the prediction model, the present application also performs separate difference judgment on different influencing factors as one of the conditions to be considered in the consistency analysis. For the factor consistency judgment threshold and the total factor deviation threshold, they can be set according to the actual situation or obtained based on big data analysis. In addition, for the prediction models with consistency here, the factor with the largest cumulative factor is used as the representative factor, which can achieve a relatively conservative life estimation.

[0023] As a possible implementation, obtaining the current usage data of the target positive displacement motor and determining the effective remaining life of the target positive displacement motor according to the positive displacement motor life prediction model includes: according to the current usage data of the target positive displacement motor, determining the temperature cumulative value at the current working duration , the humidity cumulative value and the workload cumulative value ; according to the current working duration , determining the following equivalent cumulative values corresponding to all positive displacement motor life prediction models: the equivalent temperature life cumulative value of the working temperature life influence factor at the current working duration , where i represents the number of different positive displacement motor life prediction models; the equivalent humidity life cumulative value of the working humidity life influence factor at the current working duration ; the equivalent load life cumulative value of the working load life influence factor at the current working duration ; according to the temperature cumulative value and the equivalent temperature life cumulative value , determine the coincidence ratio affected by temperature , where ; according to the humidity accumulation value and the equivalent humidity life accumulation value , determine the coincidence ratio affected by humidity , where ; according to the workload accumulation value and the equivalent load life accumulation value , determine the coincidence ratio affected by load , where ; according to the coincidence ratio affected by temperature , the coincidence ratio affected by humidity and the coincidence ratio affected by load , determine the total ratio , where ; determine the screw drill life prediction model corresponding to the target screw drill by taking the maximum total ratio among different total ratios ; according to the determined screw drill life prediction model and combined with the current usage data, determine the effective remaining life of the target screw drill.

[0024] In the present invention, after obtaining the screw drill life prediction model, reasonable and accurate life prediction can be carried out on the screw drill being used. The life prediction of the target screw drill first requires determining that the usage conditions of the target screw drill conform to the corresponding screw drill life prediction model, and then using the determined corresponding screw drill life prediction model to carry out reasonable and accurate life prediction. Here, the matching of the screw torque life prediction model is mainly judged by the coincidence degree of the cumulative amounts of different factors in the time dimension and the cumulative amounts corresponding to different models, that is, the closer the cumulative amounts are on all factors, the more capable of matching the usage conditions of the current target screw drill. Of course, after determining the matching screw drill prediction model, the consumption of life can be determined using the current usage data, and then the effective remaining life can be determined based on the life prediction value provided by the model.

[0025] In a second aspect, the present invention provides an intelligent screw drill life prediction system, configured to: collect historical screw drill life data, perform clustering division based on usage duration characteristics to form different duration characteristic life data sets; perform data extraction and analysis based on usage characteristics on different duration characteristic life data sets to establish corresponding clustering life prediction models; perform consistency analysis on different clustering life prediction models to determine the screw drill life prediction model; obtain the current usage data of the target screw drill, and determine the effective remaining life of the target screw drill according to the screw drill life prediction model.

[0026] In the present invention, the system is a complete system that can predict the life of a positive displacement motor by analyzing a life prediction model configured to utilize historical big data for clustering, which fully ensures the efficient and accurate implementation of the life prediction of the positive displacement motor and is an important material basis for realizing a reasonable and accurate life prediction of the positive displacement motor.

[0027] The beneficial effects of an intelligent positive displacement motor life prediction method and system provided by the present invention are as follows:

[0028] This method analyzes a life prediction model based on factors affecting the life of a positive displacement motor by obtaining big data of historical positive displacement motors, and then establishes a life prediction model for these factors affecting the life of the positive displacement motor, so as to realize a reasonable and accurate prediction of the remaining life of the positive displacement motor. This method is based on big data analysis and processing, and uses the method of cluster analysis, which can, to a certain extent, make a reasonable and accurate life prediction for different usage situations, cover a large range of life prediction scenarios of positive displacement motors, and at the same time, with big data as a reference, greatly improves the accuracy of the life prediction of positive displacement motors, providing a more reasonable and accurate reference basis for the planning of the use of positive displacement motors.

[0029] The system is a complete system that can predict the life of a positive displacement motor by analyzing a life prediction model configured to utilize historical big data for clustering, which fully ensures the efficient and accurate implementation of the life prediction of the positive displacement motor and is an important material basis for realizing a reasonable and accurate life prediction of the positive displacement motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a step diagram of an intelligent positive displacement motor life prediction method provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention.

[0033] A positive displacement downhole motor is a kind of downhole motor that uses drilling fluid as power to convert the liquid pressure energy into mechanical energy. Since the positive displacement downhole motor works in a high-pressure and high-temperature environment, it causes relatively large damage to the motor itself, especially the fatigue damage caused by different factors. After long-term accumulation, it affects the service life of the positive displacement downhole motor. At the same time, the positive displacement downhole motor is a high-value drilling tool. Therefore, reasonable storage and use of it are effective ways to improve its utilization rate.

[0034] The life prediction of the positive displacement downhole motor can provide enterprises with reasonable cost planning and operation arrangements. Currently, there is no established method that can reasonably and accurately predict the life of the positive displacement downhole motor. At present, the life prediction of the positive displacement downhole motor is basically based on visual observation and judgment by experience, and the prediction results have a large deviation.

[0035] Reference Figure 1 In view of this, the embodiment of the present invention provides an intelligent method for predicting the life of a positive displacement downhole motor. This method analyzes the life prediction model based on the factors affecting the life of the positive displacement downhole motor by obtaining the big data of historical positive displacement downhole motors, and then establishes the life prediction models of these factors affecting the life of the positive displacement downhole motor, so as to realize reasonable and accurate prediction of the remaining life of the positive displacement downhole motor. This method is based on big data analysis and processing, and uses the method of cluster analysis, which can reasonably and accurately predict the life under different usage conditions to a certain extent, covering a large range of life prediction scenarios of positive displacement downhole motors. At the same time, with big data as a reference, it greatly improves the accuracy of the life prediction of the positive displacement downhole motor, providing a more reasonable and accurate reference basis for the planning of the use of the positive displacement downhole motor.

[0036] The intelligent method for predicting the life of a positive displacement downhole motor specifically includes the following steps:

[0037] S1: Collect the historical life data of the positive displacement downhole motor, conduct cluster division based on the usage duration characteristics, and form different life data sets with duration characteristics.

[0038] Collect the historical life data of the positive displacement downhole motor, conduct cluster division based on the usage duration characteristics, and form different life data sets with duration characteristics, including: extracting the usage duration characteristic information of different historical positive displacement downhole motors according to the historical life data of the positive displacement downhole motor; conducting cluster division on different historical positive displacement downhole motors according to the usage duration characteristic information of different historical positive displacement downhole motors, and forming different life data sets with duration characteristics.

[0039] Historical screw drill life data includes data during the entire effective service life of different screw drills from the start of use until they can no longer perform operations normally. Considering that the impact on the life of screw drills is closely related to the usage situation, before establishing a prediction model for the life of screw drills, it is necessary to reasonably cluster and divide the data according to different usage situations, so that the subsequent life prediction model is more targeted and accurate. Of course, a more reasonable approach is to perform another clustering on the specific product forms of screw drills, which can more accurately ensure the life prediction of different types of screw drill products. It should be noted that for the clustering and division carried out according to different usage situations of screw drills, since the impact on the life of screw drills is caused by the main factors acting over a certain time dimension span, clustering and division can be carried out with reference to the usage duration characteristics to ensure the rationality and correctness of the clustering.

[0040] Extract the usage duration characteristic information of different historical screw drills from the historical screw drill life data, including: for different historical screw drills, determine the historical single - use duration each time during the historical life and the historical single - idle duration , represent the number of usage times during the corresponding historical life, represent the number of idle times during the corresponding historical life; according to the historical single - idle duration , determine the corresponding single - average idle duration of the historical screw drill, where ; according to the historical single - use duration , determine the corresponding single - average use duration of the historical screw drill, where .

[0041] When clustering and classifying screw drill tools according to the duration characteristic information of screw drill tools for different usage situations of screw drill tools, the characteristics in the time dimension to be considered mainly include three aspects. The first aspect is the working usage duration characteristic of the screw drill tool during its effective service life cycle. Considering that the environmental conditions during the operation of the screw drill tool are completely different from those during non - use and idle periods, and the impact on the life of the screw drill tool during operation is much greater than that during idle periods, the usage duration characteristic information throughout the entire service life cycle needs to be considered first. It can be understood that the usage duration of the screw drill tool will occur multiple times during the entire service life cycle, and each usage duration is not the same. Characterizing the overall usage duration through the average duration of each use has a certain representativeness for the impact of usage duration on the life of the screw drill tool. Therefore, the average usage duration per single time needs to be considered. The second aspect is the duration characteristic of the screw drill tool during the idle period throughout its entire service life cycle. In the idle situation, different storage methods and environmental conditions will cause different degrees of impact on the life of the screw drill tool. After all, the humidity, temperature, etc. of the environment during idle periods can affect the performance of the screw drill tool, and thus affect the life of the screw drill tool. Similarly, during the entire service life cycle of the screw drill tool, the idle situation will occur multiple times and intersect with its operation duration. The average idle duration per single time can reflect to a certain extent the degree to which the life of the screw drill tool is affected during the idle duration. Therefore, the average idle duration per single time needs to be considered. The third aspect is the utilization rate of the screw drill tool. It can be understood that the more times the screw drill tool is used, the shorter its life. Therefore, the number of uses is also an important factor determining the screw drill tool. And for both the number of operations and the number of idle times, they need to be considered in order to accurately define the usage situation of the screw drill tool reasonably.

[0042] According to the usage duration characteristic information of different historical screw drill tools, cluster and classify different historical screw drill tools to form different duration characteristic life data sets, including: setting the cluster idle time difference threshold , the cluster usage time difference threshold , and the cluster number difference threshold , and perform cluster classification in the following way: For any two different historical screw drill tools, if the following four conditions are simultaneously met, then the historical life data of the corresponding two historical screw drill tools are taken as the same class: The difference between the average idle duration per single time of two different historical screw drill tools does not exceed the cluster idle time difference threshold ; The difference between the average usage duration per single time of two different historical screw drill tools does not exceed the cluster usage time difference threshold ; The difference between the number of uses of two different historical screw drill tools does not exceed the cluster number difference threshold ; The number of idle times of two different historical positive displacement motors The difference does not exceed the clustering time difference threshold ; Cluster the historical life data of all historical positive displacement motors that will be regarded as the same class to form corresponding duration characteristic life data.

[0043] It should be noted that the usage situations of different positive displacement motors in a timely manner are generally the same. It is impossible to maintain a high degree of consistency or even sameness in the single - time average usage duration, single - time average idle duration, and the number of idle and usage times. Therefore, when clustering and dividing different positive displacement motors based on these duration characteristics, determining whether to cluster by determining the difference in the duration characteristics of different positive displacement motors is a reasonable clustering method. The clustering idle time difference threshold, clustering usage time difference threshold, and clustering number difference threshold can be set according to actual needs or determined based on big data analysis.

[0044] S2: Perform data extraction and analysis based on usage characteristics for different duration characteristic life data sets, and establish corresponding clustering life prediction models.

[0045] Performing data extraction and analysis based on usage characteristics for different duration characteristic life data sets and establishing corresponding clustering life prediction models includes: extracting the usage duration characteristic information and usage characteristic information of different historical positive displacement motors from different duration characteristic life data sets to form corresponding life prediction relationships; performing relationship confirmation analysis based on the life prediction relationships corresponding to different historical positive displacement motors to form clustering life prediction models corresponding to the duration characteristic life data sets.

[0046] After completing the clustering and division of different historical positive displacement motors, targeted life prediction analysis can be carried out on different clustering data to establish a reasonable life prediction model. To establish a prediction model for predicting the life of a positive displacement motor, factors that affect the life of the positive displacement motor need to be considered. Therefore, a comprehensive life prediction model is established by determining the influence amount of these factors on the life. Therefore, the analysis of these factors needs to be extracted from the usage characteristic information.

[0047] Extracting the usage duration characteristic information and usage characteristic information of different historical positive displacement motors from different duration characteristic life data sets to form corresponding life prediction relationships includes: extracting the corresponding single - time average idle duration and the number of idle times for different historical positive displacement motors, and establishing an idle - life influence relationship where: , represents the idle life influence factor, and , Denote the idle life impact factor, where k takes 1, 2, 3; for different historical positive displacement motors, extract the corresponding single average service duration and the number of idle times , and establish the usage-life impact relationship , where: , Denote the service life impact factor, and , Denote the service life impact factor; for different historical positive displacement motors, extract the total working duration , the total working duration corresponding environmental temperature change factor as well as the total working duration corresponding drill temperature change factor , and establish the temperature-life impact relationship , where: , , Denote the working temperature life impact factor, Denote the temperature conversion life impact factor; for different historical positive displacement motors, extract the total working duration and the total working duration corresponding working load life impact factor , and establish the load-life impact relationship , where: , Denote the compliance conversion life impact factor; for different historical positive displacement motors, extract the total working duration , the total working duration corresponding environmental humidity change factor as well as the total working duration corresponding drill humidity change factor , and establish the humidity-life impact relationship , where: , , Denote the working humidity life impact factor, Denote the humidity conversion life impact factor; according to the idle-life impact relationship , the usage-life impact relationship , the temperature-life impact relationship , the load-life impact relationship as well as the humidity-life impact relationship , establish the following life prediction relationship: , Denote the predicted life value, The total number of factors representing the life impact factors included in the life prediction relationship, and γ represents the predicted adjusted life impact factor.

[0048] It can be understood that the life of the positive displacement motor mainly refers to the process of functional failure of the positive displacement motor. The main factors affecting the function of the positive displacement motor are the environmental factors and operating factors of the positive displacement motor. In this application, for environmental factors, mainly two factors, humidity and temperature, are considered. For operating factors, the working load is considered. It should be noted that there may be multiple factors affecting the life of the positive displacement motor, and the magnitudes and degrees of influence of different factors on the life of the positive displacement motor are different. Among these factors, some are indirect and some are direct. For example, geographical factors mainly affect the life of the positive displacement motor through different humidity and temperature. Therefore, through observation and analysis, it is reasonable to use humidity and temperature as the two most important direct factors for life prediction analysis. Of course, for the working load, it can be the direct operating force load or the combination of various static and dynamic forces received during the operation of the positive displacement motor. In addition, when establishing the life prediction relationship, considering that different factors affecting the life of the positive displacement motor have different influences on the life of the positive displacement motor, it is necessary to first establish the corresponding influence relationships separately before comprehensively forming the life prediction relationship of the positive displacement motor. Here, for the idle time and usage time, since these times do not have an equal influence relationship on the life of the positive displacement motor, there is a conversion relationship between life and time. To avoid overly complex data processing and to ensure that this conversion relationship can be determined more accurately, the life impact factors in the established influence relationship are all represented by quadratic polynomials. Similarly, for humidity, temperature, and working load, their influences on life are not equal either, so conversions are required. Therefore, different converted life impact factors are provided for different influencing factors. Of course, for humidity and temperature, since the changes in humidity and temperature during operation are much greater than the environmental humidity and temperature, the environmental temperature and environmental humidity do not need to be considered, and the influences of environmental temperature and environmental humidity will not have an obvious impact on life during the operation process. The actual temperature and humidity obtained during operation are the result of the superposition of environmental conditions. Therefore, the influence of environmental conditions needs to be removed when establishing the influence factors. For temperature, humidity, and working load, the cumulative situations of these factors can all be obtained based on historical data, but these factors also change with the time dimension.

[0049] According to the life prediction relationships corresponding to different historical positive displacement motors, perform relationship confirmation analysis to form a clustering life prediction model for the duration characteristic life data set, including: the total number of factors +1 is the quantity unit of grouping. Randomly extract different historical life data from the duration feature life dataset to form different duration feature life data groups. For different duration feature life data groups, determine all life influencing factors according to the life prediction relationships corresponding to different historical life data in the group. For all life influencing factors determined for different duration feature life data groups, obtain the average value of the same life influencing factors on different groups. Use the average values of different life influencing factors as the values of the corresponding life influencing factors in the life prediction relationship to form a clustering life prediction model corresponding to the duration feature life dataset.

[0050] After establishing its corresponding clustering life prediction model, it is necessary to determine the life influencing factors set in the established model so as to form a life prediction model without unknown quantities. The number of clustering life prediction models established in the dataset is greater than the size of the unknown quantities. Therefore, as long as the minimum number of models capable of determining the life influencing factors is provided, the determination of the life influencing factors in the model can be achieved. Here, it should be noted that in the clustering life prediction relationship, it can be considered that different life prediction values are the same, which serves as the standard reference for the total life under the corresponding usage conditions. Since the prediction using the prediction model is always carried out when the positive displacement motor has not reached the life limit, the prediction result obtained using the prediction model is numerically less than the life prediction value. However, the remaining effective life of the positive displacement motor can be determined by combining the life prediction value and the prediction result obtained by analyzing the prediction model.

[0051] S3: Conduct consistency analysis on different clustering life prediction models to determine the life prediction model of the positive displacement motor.

[0052] Conduct consistency analysis on different clustering life prediction models to determine the life prediction model of the positive displacement motor, including: for different clustering life prediction models, extract the corresponding different life influencing factors to form the corresponding clustering life influencing factor sets; for different clustering life influencing factor sets, conduct model consistency judgment in the following way: set the factor consistency judgment threshold and the total factor deviation threshold , where x takes α, β, w, f, c; randomly extract two clustering life influencing factor sets and determine the cumulative factor difference of the corresponding influencing factors at the corresponding duration ; if for any cumulative factor difference all satisfy: and ≤ , it is determined that the two clustering life prediction models are consistent. The life influence factor with the largest cumulative factor amount of the same clustering life influence factor at the corresponding time duration is used as the representative life influence factor of the two clustering life prediction models, and a new life prediction model is formed based on different representative life influence factors. The newly formed life prediction model is also used as an object for consistency judgment and continues to be judged for consistency until no new life prediction model is formed. All life prediction models after consistency judgment are determined as the life prediction models of the positive displacement motor.

[0053] Different clustering life prediction models represent the conditions of the positive displacement motor under different usage conditions. However, considering that similar life development situations may also occur under different usage conditions, in order to improve the applicability of the life prediction model, it is necessary to conduct consistency analysis on different clustering life prediction models to complete comprehensive merging. This consistency analysis mainly considers that different influencing factors may have similarities in predicting life under overall conditions. Therefore, the consistency judgment is also made based on the closeness of the cumulative amounts of all influencing factors in the time dimension. Of course, considering fully ensuring the accuracy of the prediction results of the prediction model, the present application also conducts separate difference judgment on different influencing factors as one of the conditions to be considered in consistency analysis. For the factor consistency judgment threshold and the total factor deviation threshold, they can be set according to actual situations or obtained based on big data analysis. In addition, for the prediction models with consistency here, the factor with the largest cumulative factor amount is used as the representative factor, which can achieve a relatively conservative life estimation.

[0054] S4: Obtain the current usage data of the target positive displacement motor, and determine the effective remaining life of the target positive displacement motor according to the life prediction model of the positive displacement motor.

[0055] Obtain the current usage data of the target positive displacement motor, and determine the effective remaining life of the target positive displacement motor according to the life prediction model of the positive displacement motor, including: according to the current usage data of the target positive displacement motor, determine the temperature cumulative value at the current working duration , the humidity cumulative value and the working load cumulative value ; according to the current working duration , determine the following equivalent cumulative values corresponding to all life prediction models of the positive displacement motor: the equivalent temperature life cumulative value of the working temperature life influence factor at the current working duration , where i represents the number of different life prediction models of the positive displacement motor; the equivalent humidity life cumulative value of the working humidity life influence factor at the current working duration ; the equivalent working load life cumulative value of the working load life influence factor at the current working duration Equivalent load life cumulative value under ; According to the temperature cumulative value and the equivalent temperature life cumulative value , determine the temperature influence coincidence ratio , where ; According to the humidity cumulative value and the equivalent humidity life cumulative value , determine the humidity influence coincidence ratio , where ; According to the working load cumulative value and the equivalent load life cumulative value , determine the load influence coincidence ratio , where ; According to the temperature influence coincidence ratio , the humidity influence coincidence ratio and the load influence coincidence ratio , determine the total ratio , where ; Among different total ratios , determine the screw drill life prediction model corresponding to the maximum total ratio as the screw drill life prediction model corresponding to the target screw drill; According to the determined screw drill life prediction model and combined with the current usage data, determine the effective remaining life of the target screw drill.

[0056] After obtaining the screw drill life prediction model, reasonable and accurate life prediction can be carried out for the screw drill being used. For the life prediction of the target screw drill, it is first necessary to determine that the usage conditions of the target screw drill conform to the corresponding screw drill life prediction model, and then use the determined corresponding screw drill life prediction model to carry out reasonable and accurate life prediction. Here, the matching of the screw torque life prediction model is mainly judged by the coincidence degree between the cumulative amount of different factors in the time dimension and the cumulative amount corresponding to different models, that is, the closer the cumulative amounts are in all factors, the more suitable it is for the usage conditions of the current target screw drill. Of course, after determining the matching screw drill prediction model, the life consumption can be determined using the current usage data, and then the effective remaining life can be determined based on the life prediction value provided by the model.

[0057] The present invention also provides an intelligent prediction system for the service life of a screw drill tool, which is configured to: collect historical service life data of screw drill tools, perform clustering division based on the characteristics of the usage duration to form service life data sets with different duration characteristics; for the service life data sets with different duration characteristics, perform data extraction and analysis based on usage characteristics to establish corresponding clustering service life prediction models; perform consistency analysis on different clustering service life prediction models to determine a service life prediction model for the screw drill tool; obtain the current usage data of the target screw drill tool, and determine the effective remaining service life of the target screw drill tool according to the service life prediction model of the screw drill tool.

[0058] In summary, the beneficial effects of the intelligent prediction method and system for the service life of the screw drill tool provided by the embodiments of the present invention are as follows:

[0059] This method analyzes the service life prediction model based on the factors affecting the service life of the screw drill tool by obtaining the big data of historical screw drill tools, and then establishes a service life prediction model for these factors affecting the service life of the screw drill tool, so as to realize a reasonable and accurate prediction of the remaining service life of the screw drill tool. This method is based on big data analysis and processing, and uses the method of cluster analysis, which can reasonably and accurately predict the service life of different usage situations to a certain extent, covering a large range of service life prediction scenarios of screw drill tools. At the same time, taking big data as a reference greatly improves the accuracy of the service life prediction of the screw drill tool, providing a more reasonable and accurate reference basis for the planning of the use of the screw drill tool.

[0060] This system is a complete system that can predict the service life of the screw drill tool by configuring a service life prediction model capable of clustering using historical big data, which fully ensures the efficient and accurate implementation of the service life prediction of the screw drill tool and is an important material basis for realizing a reasonable and accurate service life prediction of the screw drill tool.

[0061] In the embodiments of the present application, "indicating" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain piece of information is called the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc. It is also possible to indirectly indicate the information to be indicated by indicating other information, where there is an association relationship between the other information and the information to be indicated. It is also possible to only indicate a part of the information to be indicated, while the other parts of the information to be indicated are known or pre-agreed. For example, it is also possible to realize the indication of specific information by means of the arrangement order of each piece of information pre-agreed (such as protocol regulations), so as to reduce the indication overhead to a certain extent. At the same time, the common parts of each piece of information can be identified and indicated uniformly to reduce the indication overhead caused by separately indicating the same information.

[0062] In addition, the specific indication method can also be various existing indication methods, such as but not limited to, the above-mentioned indication methods and their various combinations, etc. The specific details of various indication methods can refer to the prior art and will not be elaborated herein. As can be seen from the above description, for example, when multiple pieces of information of the same type need to be indicated, it may occur that the indication methods of different pieces of information are different. In the specific implementation process, the required indication method can be selected according to specific needs, and the indication method selected in the embodiments of the present application is not limited. In this way, the indication methods involved in the embodiments of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0063] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending periods and / or sending times of these sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. Among them, the sending periods and / or sending times of these sub-information can be predefined, such as predefined according to a protocol, or can be configured by the sending device by sending configuration information to the receiving device.

[0064] "Predefined" or "pre-configured" can be implemented by pre-saving corresponding codes, tables or other ways that can be used to indicate relevant information in the device, and the specific implementation method thereof is not limited in the embodiments of the present application. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partly set separately and partly integrated in a decoder, a processor, or a communication device. The type of the memory can be any form of storage medium, which is not limited in the embodiments of the present application.

[0065] The "protocol" involved in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol with a frame structure similar to that of a protocol family, or a relevant protocol applied to a future communication system. The embodiments of the present application do not make specific limitations on this.

[0066] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if", and "when" all refer to that the device will perform corresponding processing under a certain objective situation, which does not limit the time, and does not require the device to have a judgment action when implementing, nor does it mean other limitations exist.

[0067] In the description of the embodiments of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B may represent A or B. The "and / or" in the embodiments of the present application is merely a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Also, in the description of the embodiments of the present application, unless otherwise specified, "a plurality of" means two or more than two. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of a single item or plural items. For example, at least one (item) of a, b, or c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple. Additionally, for the convenience of clearly describing the technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish between identical or similar items with basically the same functions and roles. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner for easy understanding.

[0068] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and this processor may also be other general - purpose processors, digital signal processors (DSPs), application - specific integrated circuits (ASICs), field - programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general - purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0069] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0070] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0071] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context before and after.

[0072] In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0073] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0074] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0075] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0076] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, the functional units in each embodiment of this application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0079] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0080] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An intelligent method for predicting the life of a screw drill, characterized in that: include: Collect historical screw drill life data, perform clustering based on usage time characteristics, and form characteristic life data sets of different durations; For different time characteristic life data sets, the use time characteristic information and use characteristic information of different historical screw drill tools are extracted to form corresponding life prediction relationships: , represents the predicted life span value, The total number of factors of life impact factors included in the life prediction relationship, γ represents the predicted adjusted life impact factor, and the idle-life impact relationship is established based on the single average idle time, the number of idle times, the idle life impact factor, and the idle life impact factor. , establish the usage-life impact relationship based on the average single usage time, number of uses, life impact factors, and life impact factors , establish the temperature-life influence relationship based on the total working time, working temperature life influence factor, and temperature conversion life influence factor , establish the load-life impact relationship based on the total working time, workload life impact factor, and load conversion life impact factor , establish the humidity-life impact relationship based on the total working time, working humidity life impact factor, and humidity conversion life impact factor ; According to the life prediction relationship corresponding to different historical screw drill tools, relationship confirmation analysis is performed to form a cluster life prediction model corresponding to the time characteristic life data set, including: The total number of factors +1 is the unit of number of groups, and different historical life data in the duration characteristic life data set are arbitrarily extracted to form different duration characteristic life data groups; For different groups of the time-length characteristic life data, all life influencing factors are determined according to the life prediction relationships corresponding to different historical life data in the groups; For all lifespan influencing factors determined for different groups of characteristic lifespan data, obtaining average values ​​of the same lifespan influencing factors in different groups; Taking the average values ​​of different life-span influencing factors as the values ​​of the corresponding life-span influencing factors in the life-span prediction relationship, forming the cluster life-span prediction model corresponding to the duration characteristic life-span data set; Performing consistency analysis on different cluster life prediction models to determine a screw drill tool life prediction model; The current usage data of the target screw drill is obtained, and the effective remaining life of the target screw drill is determined according to the screw drill life prediction model.

2. The intelligent screw drill tool life prediction method according to claim 1 is characterized in that: The historical screw drill life data is collected and clustered based on the usage time characteristics to form characteristic life data sets of different time lengths, including: Extracting usage time characteristic information of different historical screw drill tools according to the historical screw drill tool life data; According to the usage time characteristic information of different historical screw drill tools, different historical screw drill tools are clustered and divided to form different time characteristic life data sets.

3. The intelligent screw drill tool life prediction method according to claim 2 is characterized in that: The extracting of usage time characteristic information of different historical screw drill tools according to the historical screw drill tool life data includes: For different historical screw drill tools, determine the historical single use duration of each use within the historical lifespan. And historical single idle time , Indicates the number of times it has been used within the corresponding historical lifespan. Indicates the number of times the idle state is left idle within the corresponding historical lifespan; According to the historical single idle time , determine the single average idle time corresponding to the historical screw drill ,in, ; According to the historical single use duration , determine the average single use time of the historical screw drill ,in, .

4. The intelligent screw drill tool life prediction method according to claim 3 is characterized in that: According to the usage time characteristic information of different historical screw drill tools, different historical screw drill tools are clustered and divided to form different time characteristic life data sets, including: Set cluster idle time difference threshold , Clustering using time difference threshold , Clustering times difference threshold , and perform clustering in the following way: For any two different historical screw drill tools, if the following four conditions are met at the same time, the historical life data of the corresponding two historical screw drill tools are regarded as the same category: The single average idle time of two different historical screw drilling tools The difference does not exceed the cluster idle time difference threshold ; The average single use time of two different historical screw drilling tools The difference does not exceed the clustering time difference threshold ; The usage times of two different historical screw drill tools The difference does not exceed the clustering number difference threshold ; The idle times of two different historical screw drilling tools The difference does not exceed the clustering number difference threshold ; The historical life data of all the historical screw drill tools of the same type are clustered to form the corresponding time-length characteristic life data.

5. The intelligent screw drill tool life prediction method according to claim 4 is characterized in that: The extracting the usage time characteristic information and usage characteristic information of different historical screw drill tools from different time characteristic life data sets to form corresponding life prediction relationships includes: For different historical screw drill tools, extract the corresponding single average idle time and the number of idle times , and establish the idle-life impact relationship ,in: , represents the idle life influencing factor, and , represents the idle life impact factor, k is 1, 2, 3; For different historical screw drill tools, extract the corresponding single average usage time and the number of times used , and establish the use-life impact relationship ,in: , represents the service life influencing factor, and , represents the service life influencing factor; For different historical screw drill tools, extract the total working time , the total working time The corresponding ambient temperature change factor is and the total working hours The corresponding drill temperature change factor is , and establish the temperature-life effect relationship ,in: , , Indicates the factor affecting the operating temperature life, Indicates the temperature conversion life impact factor; For different historical screw drill tools, extract the total working time and the total working hours The corresponding workload lifespan influence factor is , and establish the load-life influence relationship ,in: , Indicates the load conversion life influencing factor; For different historical screw drill tools, extract the total working time , the total working time The corresponding environmental humidity change factor is and the total working hours The corresponding drilling tool humidity change factor is , and establish the humidity-lifespan relationship .

6. The intelligent screw drill tool life prediction method according to claim 5 is characterized in that: The consistency analysis of different cluster life prediction models is performed to determine the life prediction model of the screw drill, including: For different cluster life prediction models, extracting corresponding different life influencing factors to form a corresponding cluster life influencing factor set; For different sets of factors influencing the cluster life span, the following model consistency judgment is performed: Set the factor consistency judgment threshold corresponding to different influencing factors and factored total deviation threshold , x takes α, β, w, f, c; Extract any two sets of factors affecting the life span of the clusters, and determine the cumulative difference of the factors of the corresponding factors under the corresponding time lengths. ; If the cumulative difference for any factor All meet the following requirements: ,and ≤ , it is determined that the two cluster life prediction models are consistent, and the life influence factor with the largest factor accumulation of the same cluster life influence factor in the corresponding time length is used as the representative life influence factor of the two cluster life prediction models, and a new life prediction model is formed according to the different representative life influence factors; The newly formed life prediction model is also taken as the object of consistency judgment, and the consistency judgment is continued until no new life prediction model is formed; All the life prediction models after consistency judgment are determined as the screw drill tool life prediction models.

7. The intelligent screw drill tool life prediction method according to claim 6 is characterized in that: The obtaining of current usage data of the target screw drill and determining the effective remaining life of the target screw drill according to the screw drill life prediction model includes: According to the current usage data of the target screw drill, determine the current working time The accumulated temperature value under , Humidity cumulative value and workload accumulation ; According to the current working hours , determine the following equivalent cumulative values ​​corresponding to all the screw drill tool life prediction models: The operating temperature life influence factor is the current working time Equivalent temperature life accumulation value under , i represents the serial number of the different screw drill tool life prediction models; The influence factor of working humidity on life is as follows: Equivalent humidity life accumulation value under ; The workload lifespan factor is the current working time Cumulative value of equivalent load life under ; According to the temperature accumulation value and the equivalent temperature life accumulation value , determine the temperature influence overlap ratio ,in, ; According to the humidity accumulation value and the equivalent humidity life accumulation value , determine the humidity impact overlap ratio ,in, ; According to the workload accumulation value and the equivalent load life cumulative value , determine the load impact overlap ratio ,in, ; According to the temperature, the overlap ratio 、The humidity affects the overlap ratio And the load impact overlap ratio , determine the total proportion ,in, ; The total proportion of different The largest proportion of the total The corresponding screw drill tool life prediction model is determined as the screw drill tool life prediction model corresponding to the target screw drill tool; The effective remaining life of the target screw drill is determined based on the determined screw drill life prediction model and combined with the current usage data.

8. An intelligent screw drill life prediction system, characterized in that: is configured as: Collect historical screw drill life data, perform clustering based on usage time characteristics, and form characteristic life data sets of different durations; For different time characteristic life data sets, the use time characteristic information and use characteristic information of different historical screw drill tools are extracted to form corresponding life prediction relationships: , represents the predicted life span value, The total number of factors of life impact factors included in the life prediction relationship, γ represents the predicted adjusted life impact factor, and the idle-life impact relationship is established based on the single average idle time, the number of idle times, the idle life impact factor, and the idle life impact factor. , establish the usage-life impact relationship based on the average single usage time, number of uses, life impact factors, and life impact factors , establish the temperature-life influence relationship based on the total working time, working temperature life influence factor, and temperature conversion life influence factor , establish the load-life impact relationship based on the total working time, workload life impact factor, and load conversion life impact factor , establish the humidity-life impact relationship based on the total working time, working humidity life impact factor, and humidity conversion life impact factor ; According to the life prediction relationship corresponding to different historical screw drill tools, relationship confirmation analysis is performed to form a cluster life prediction model corresponding to the time characteristic life data set, including: The total number of factors +1 is the unit of number of groups, and different historical life data in the duration characteristic life data set are arbitrarily extracted to form different duration characteristic life data groups; For different groups of the time-length characteristic life data, all life influencing factors are determined according to the life prediction relationships corresponding to different historical life data in the groups; For all lifespan influencing factors determined for different groups of characteristic lifespan data, obtaining average values ​​of the same lifespan influencing factors in different groups; Taking the average values ​​of different life-span influencing factors as the values ​​of the corresponding life-span influencing factors in the life-span prediction relationship, forming the cluster life-span prediction model corresponding to the duration characteristic life-span data set; Performing consistency analysis on different cluster life prediction models to determine a screw drill tool life prediction model; The current usage data of the target screw drill is obtained, and the effective remaining life of the target screw drill is determined according to the screw drill life prediction model.

Images