Big data processing method for intelligent operation and maintenance

Abstract

The invention discloses a big data processing method for intelligent operation and maintenance, and relates to the technical field of data processing. According to the method, a historical fault database is established, all fault information of equipment is stored, when equipment operation parameters exceed a reference range and lasts for a set duration, an anomaly evaluation signaling is triggered, the similarity between an abnormal polygon and a historical polygon is calculated from the three dimensions of angle, side length proportion and area by establishing a radar map, an accurate disease index is obtained, and the fault assessment accuracy is improved. The correlation between the current equipment operation state and the historical fault is accurately analyzed, the equipment operation parameter change trend, the relative size relation between the parameters and the overall parameter distribution condition are comprehensively considered, misjudgment of single-dimension judgment is effectively avoided, the fault hidden danger is accurately evaluated, and the possible fault of the equipment is predicted in advance.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular, to a big data processing method for intelligent operation and maintenance. Background Art

[0002] With the development of intelligent manufacturing, the amount of operation data generated by equipment has increased sharply. How to effectively utilize this data for equipment fault prediction and intelligent operation and maintenance has become an urgent problem to be solved.

[0003] However, the big data processing methods of the existing technologies still have the following deficiencies in the actual application process: It can only perform simple threshold judgment on the equipment operation parameters and issue an alarm, and cannot deeply analyze the correlation between the current operation state of the equipment and historical faults, resulting in the inability to accurately predict the possible fault hidden dangers of the equipment in advance, and it is difficult to meet the requirements of manufacturing enterprises for high-reliability operation of equipment; In addition, there is a lack of a scientific evaluation system in selecting maintenance personnel to handle faults, and different evaluation systems cannot be executed to select corresponding maintenance personnel according to the correlation results between the current operation state of the equipment and historical faults, and the degree of intelligence is low.

[0004] Therefore, a big data processing method for intelligent operation and maintenance is introduced. Summary of the Invention

[0005] In order to solve the problems raised in the background art, the present application provides a big data processing method for intelligent operation and maintenance.

[0006] A big data processing method for intelligent operation and maintenance provided by the present application adopts the following technical solutions: A big data processing method for intelligent operation and maintenance, including: Data processing: Using various sensors to collect the operation parameters of different production equipment in real time and perform preprocessing; the operation parameters are represented by the number a, where a = 1, 2,..., b, where b represents the total number of operation parameters required to be collected for different production equipment; for the operation parameters of different production equipment, set the reference operation range and allowable duration for different operation parameters; Historical index: Establish a historical fault database to store all the fault information that has occurred in the history of each production equipment. If in the operation parameters collected in real time by any production equipment, there is one or more groups of operation parameters that fail to match the corresponding reference operation range and the duration reaches the corresponding set allowable duration, an abnormal evaluation signal is triggered, and the corresponding steps are executed to determine the certainty index certa between the production equipment that currently triggers the abnormal evaluation signal and the corresponding groups of historical fault information.

[0007] Optionally, triggering the abnormal evaluation signal and executing the corresponding steps are specifically: S1: Set independent coordinate axes for each group of operating parameters of the currently triggered abnormal evaluation signaling production device, construct a radar chart, map the value Ra of each group of operating parameters to the corresponding set coordinate axes, and connect the points in sequence according to the preset connection order of the operating parameters to form a polygon, denoted as the abnormal polygon; S2: Similarly to step S1 for each group of historical fault information, form the polygon corresponding to each group of historical fault information, denoted as the historical polygon.

[0008] Optionally, determine the certainty index certa between the currently triggered abnormal evaluation signaling production device and the corresponding groups of historical fault information, specifically: S3: Arrange the vertex sequences of the abnormal polygon and each group of historical polygons in the same operating parameter order, and obtain the interior angles Uea and Uqa at each vertex, where e represents the number of the abnormal polygon and q represents the number of the historical polygon; According to the formula Calculate the angle evaluation value M1 between the abnormal polygon and each group of historical polygons; Obtain the lengths of each side of the abnormal polygon and each group of historical polygons, and mark them as Kea and Kqa. According to the formula Calculate the ratio evaluation value M2 between the abnormal polygon and each group of historical polygons; Obtain the areas of the abnormal polygon and each group of historical polygons, and calculate the ratio respectively to obtain the area evaluation value M3 between the abnormal polygon and each group of historical polygons; Extract the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 of the abnormal polygon and each group of historical polygons, and substitute them into the formula Perform weighted calculation to obtain the certainty index certa between the currently triggered abnormal evaluation signaling production device and the corresponding groups of historical fault information; where Are the weight coefficients set for the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 respectively.

[0009] Optionally, it further includes: Result generation: Based on the certainty index certa between the currently triggered abnormal evaluation signaling production device and each group of historical fault information, selectively trigger the excellent path signaling or excellent treatment signaling; Operation and maintenance push: According to the triggered excellent path signaling or excellent treatment signaling, comprehensively evaluate the status information of each operation and maintenance personnel, and perform corresponding operations to select an operation and maintenance personnel as the processing personnel for the currently triggered abnormal evaluation signaling production device; The status information includes the location and work log.

[0010] Optionally, selectively trigger the excellent path signaling or excellent treatment signaling, specifically: Preset the reference index of the certa index corresponding to each production device, compare the certa index of each group of historical fault information with the corresponding reference index, and screen out the historical fault information with the certa index higher than the reference index as the possible fault information of the production device that currently triggers the abnormal evaluation signal, and at the same time trigger the excellent path signal; If the certa index of each group of historical fault information is lower than the corresponding reference index, directly trigger the excellent handling signal.

[0011] Optionally, according to the triggered excellent path signal, comprehensively evaluate the status information of each operation and maintenance personnel, and perform corresponding operations to select an operation and maintenance personnel as the handler of the production device that currently triggers the abnormal evaluation signal. Specifically: Taking the location of the production device that currently triggers the abnormal evaluation signal as the starting point, send a location feedback signal to the mobile terminals of each operation and maintenance personnel. Each operation and maintenance personnel receives the sent location feedback signal and makes a determination. After determination, obtain the location of each operation and maintenance personnel at the current time point, calculate the distance of the location of each operation and maintenance personnel from the starting point, select the operation and maintenance personnel with the shortest distance as the handler of the production device that currently triggers the abnormal evaluation signal, and send the possible fault information of the production device that currently triggers the abnormal evaluation signal to the mobile terminal of the handler.

[0012] Optionally, according to the triggered excellent handling signal, comprehensively evaluate the status information of each operation and maintenance personnel, and perform corresponding operations to select an operation and maintenance personnel as the handler of the production device that currently triggers the abnormal evaluation signal. Specifically: Search the work logs of each operation and maintenance personnel for the device code of the production device that currently triggers the abnormal evaluation signal, extract the number of times of handling corresponding to the device code, analyze the number of times of handling of each operation and maintenance personnel, classify according to the type of signal triggered during each handling, and obtain the number of times of handling corresponding to the excellent path signal and the excellent handling signal of each operation and maintenance personnel, denoted as the excellent path times and the excellent handling times; Set an experience bonus point corresponding to the excellent path signal and the excellent handling signal respectively; multiply the excellent path times and the excellent handling times of each operation and maintenance personnel by the corresponding set experience bonus points respectively, and then sum to obtain the ability accumulation value ut1 of each operation and maintenance personnel at the current time point; Obtain the time used for each time corresponding to the excellent path times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent path of each operation and maintenance personnel; obtain the time used for each time corresponding to the excellent handling times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent handling of each operation and maintenance personnel; Preset the time intervals corresponding to the average time consumed for excellent routes and the average time consumed for excellent locations respectively. Each time interval corresponding to the average time consumed for excellent routes corresponds to a group of excellent route efficiency scores; each time interval corresponding to the average time consumed for excellent locations corresponds to a group of excellent location efficiency scores; convert the average time consumed for excellent routes and the average time consumed for excellent locations of each operation and maintenance personnel into excellent route efficiency scores and excellent location efficiency scores respectively, and then accumulate to obtain the efficiency accumulation value ut2 of each operation and maintenance personnel; Obtain the number of failures in the number of processes handled by each operation and maintenance personnel, calculate the proportion of the number of failures in the number of processes handled, and record it as the failure proportion ut3; Comprehensively analyze the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 of each operation and maintenance personnel, so as to determine the operation and maintenance evaluation index kder of each operation and maintenance personnel. Extract the three operation and maintenance personnel with the highest rankings of the operation and maintenance evaluation index kder, and obtain the distance between the three operation and maintenance personnel and the starting point. Select the operation and maintenance personnel with the shorter distance among the three operation and maintenance personnel as the processing personnel for the currently triggered abnormal evaluation signaling production equipment. After the processing personnel maintain the production equipment, update the historical fault database.

[0013] Optionally, the comprehensive analysis of the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 of each operation and maintenance personnel is specifically as follows: Preset the ability passing value and the efficiency passing value corresponding to the ability accumulation value ut1 and the efficiency accumulation value ut2 respectively, and mark them as uh1 and uh2; Perform normalization processing on the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 of each operation and maintenance personnel and then substitute them into the formula Perform weighted calculation to obtain the operation and maintenance evaluation index kder of each operation and maintenance personnel; where Are the influence weight factors of the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 respectively.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: The present invention stores all fault information of the device by establishing a historical fault database. When the device operation parameters exceed the reference range and continue for a set duration, an abnormal evaluation signaling is triggered. By constructing a radar chart, the similarity degree between the abnormal polygon and the historical polygon is calculated from three dimensions: angle, side length ratio, and area, and the confirmed disease index is obtained. The relationship between the current device operation state and historical faults is accurately analyzed, and the change trend of device operation parameters, the relative size relationship between parameters, and the overall parameter distribution are comprehensively considered, effectively avoiding misjudgment of single-dimensional judgment, accurately evaluating potential faults, and predicting possible faults of the device in advance; The present invention selectively triggers an optimal path signaling or an optimal processing signaling according to a confirmed disease index. Under the optimal path signaling, the person closest to the location of the operation and maintenance personnel is selected to handle the fault; under the optimal processing signaling, the number of processing times, the processing duration, and the number of failures in the operation and maintenance personnel's work logs are analyzed, the ability accumulation value, the efficiency accumulation value, and the failure ratio are calculated, and the operation and maintenance evaluation index is obtained through comprehensive evaluation, and a suitable person is selected to handle the fault, solving the problem that the prior art lacks a scientific evaluation system in selecting operation and maintenance personnel. Under the optimal path signaling, the present invention can quickly reach the site to handle known possible faults by selecting the nearest operation and maintenance personnel; under the optimal processing signaling, the abilities of operation and maintenance personnel are comprehensively evaluated, and personnel with strong processing capabilities are selected to improve the success rate and quality of fault handling. After processing, the historical fault database is updated to accumulate experience and provide reference for subsequent operation and maintenance, further improving the operation and maintenance efficiency. The present invention constructs a historical polygon by using historical fault data, compares and analyzes it with the current abnormal polygon, excavates potential connections, improves the intelligent level of data processing, and provides strong support for intelligent operation and maintenance. Brief Description of the Drawings

[0015] In the following description of exemplary embodiments in conjunction with the drawings, more details, features, and advantages of the present application are disclosed. In the drawings: Figure 1 It is a flowchart of the present invention. Detailed Embodiments

[0016] The following will describe several embodiments of the present application in more detail with reference to the drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided so that the present application is comprehensive and complete, and fully conveys the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0017] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of the present specification, and will not be interpreted in an idealized or overly formal sense unless clearly defined herein.

[0018] Please refer to Figure 1 As shown, a big data processing method for intelligent operation and maintenance includes: Data processing: Use various sensors to collect the operating parameters of different production equipment in real time and perform preprocessing; the operating parameters include but are not limited to temperature, pressure, rotational speed, vibration amplitude, etc., which are specifically defined according to the equipment type. These sensors transmit the collected real-time operating parameters at a set frequency (such as once per second); the operating parameters are represented by the number a, where a = 1, 2,......, b, and b represents the total number of operating parameters to be collected for different production equipment; for the operating parameters of different production equipment, set the reference operating range and allowable duration for different operating parameters; the threshold is determined comprehensively based on the design specifications of the equipment, historical operating data, and industry standards, etc. It should be noted that the preprocessing includes using moving average or wavelet transform to filter out high-frequency noise and converting parameters with different dimensions (such as temperature in °C and pressure in MPa) into dimensionless values. Dynamically correct the preset threshold range according to the equipment aging degree and environmental changes. For example, after a certain injection molding machine has been used for 3 years, the temperature reference operating range is adjusted from 50 - 70 °C to 45 - 65 °C, and the allowable duration is adjusted from 2 minutes to 1 minute and 30 seconds.

[0019] Historical index: Establish a historical fault database to store all the fault information that has occurred in the history of each production equipment. Each fault record includes the time of fault occurrence, fault type, fault description, and the corresponding operating parameters of the equipment when the fault occurred. Classify and index the historical fault data for subsequent quick retrieval and call; if in the operating parameters collected in real time by any production equipment, there is one or more groups of operating parameters that fail to match the corresponding reference operating range and the duration reaches the corresponding set allowable duration, then trigger an abnormal evaluation signaling and execute the corresponding steps to determine the certainty index certa between the production equipment that currently triggers the abnormal evaluation signaling and the corresponding groups of historical fault information. Specifically: S1: Set independent coordinate axes for each group of operating parameters of the production equipment that currently triggers the abnormal evaluation signaling, construct a radar chart, and set the scale range of the coordinate axes based on the normal operating range of the equipment and the parameter extreme values in the historical fault data; for example, the scale of the temperature coordinate axis can be set to 0 °C - 150 °C, covering all possible temperature ranges of the equipment. Such a setting can ensure that the change range of the parameters is fully presented on the radar chart, and the parameter values in both normal operating states and fault states can be accurately marked; map the numerical value Ra of each group of operating parameters to the corresponding set coordinate axes, and connect the points in sequence according to the preset connection order of the operating parameters to form a polygon denoted as the abnormal polygon. For example, if the current temperature is 85 °C, pressure is 0.65 MPa, rotational speed is 1450 revolutions per minute, and vibration amplitude is 6 mm / s, mark and connect these points on the radar chart to form the polygon of the current equipment. S2: Similarly to step S1 for each group of historical fault information, form a polygon corresponding to each group of historical fault information, denoted as the historical polygon; Map the corresponding operating parameter values in each piece of information to the corresponding coordinate axes, and connect the points in sequence to form a polygon. For example, in a certain historical mechanical fault record, the temperature is 80°C, the pressure is 0.6 MPa, the rotational speed is 1500 revolutions per minute, and the vibration amplitude is 5 mm / s. Locate the scale points on the corresponding coordinate axes on the radar chart, and then connect these points in sequence with line segments to form a polygon representing the historical fault; S3: Arrange the vertex sequences of the abnormal polygon and each group of historical polygons in the same operating parameter order, and obtain the interior angles Uea and Uqa at each vertex, where e represents the number of the abnormal polygon and q represents the number of the historical polygon; According to the formula Calculate the angle evaluation value M1 between the abnormal polygon and each group of historical polygons; Obtain the side lengths of the abnormal polygon and each group of historical polygons, and mark them as Kea and Kqa. According to the formula Calculate the ratio evaluation value M2 between the abnormal polygon and each group of historical polygons; Obtain the areas of the abnormal polygon and each group of historical polygons, and calculate the ratio to obtain the area evaluation value M3 between the abnormal polygon and each group of historical polygons; The ratio calculation uses the area of the abnormal polygon as the numerator and the areas of each group of historical polygons as the denominator; Extract the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 of the abnormal polygon and each group of historical polygons, and substitute them into the formula Perform weighted calculation to obtain the certainty index certa between the currently triggered abnormal evaluation signaling production equipment and the corresponding groups of historical fault information; where Are the weight coefficients set corresponding to the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 respectively; It should be noted that the similarity degree is calculated from three dimensions: angle, side length ratio, and area. The angle evaluation value M1 takes into account the differences in the interior angles of the polygon vertices and reflects the similarity of the change trends of the equipment operating parameters; The ratio evaluation value M2 focuses on the side length ratio and reflects the consistency of the relative magnitude relationship between different parameters; The area evaluation value M3 comprehensively considers the overall parameter distribution. The dimension evaluation can comprehensively and accurately judge the similarity degree between the current equipment operating state and the historical fault state, effectively avoiding misjudgment caused by single-dimension judgment and improving the accuracy of fault hidden danger evaluation; Make full use of historical fault data to construct historical polygons, and through comparative analysis with the current abnormal polygon, explore the potential connection between the equipment operating state and historical faults, improving the intelligence level of data processing.

[0020] Suppose that in an automobile engine production plant, an abnormal situation occurs in a key engine assembly equipment. The following is the specific process of fault analysis for this equipment: The production plant has established a detailed historical fault database, which stores all the past fault information of this engine assembly equipment; For example, once a fault occurred at a time point P1. The fault type was a mechanical fault, and the fault description was that the joint of the assembly arm was worn, resulting in a decrease in assembly accuracy. At that time, the operating parameters of the equipment were: temperature 65°C, pressure 0.55 MPa, rotational speed 1200 revolutions per minute, and vibration amplitude 3 mm / s; the database classifies these fault data according to the fault type; This engine assembly equipment collects its own operating parameters in real time. The temperature sensor, pressure sensor, rotational speed sensor, and vibration sensor transmit the collected data to the data processing system every second; The system sets the normal operating range of temperature as 50°C - 70°C, the normal range of pressure as 0.5 MPa - 0.6 MPa, the normal range of rotational speed as 1100 revolutions per minute - 1300 revolutions per minute, and the normal range of vibration amplitude as 0 - 4 mm / s; the allowable duration of abnormal temperature is 15 minutes, the allowable duration of abnormal pressure is 10 minutes, the allowable duration of abnormal rotational speed is 8 minutes, and the allowable duration of abnormal vibration amplitude is 12 minutes; At a time point P2, the system monitors that the temperature of the equipment is 75°C, exceeding the normal range, and the duration reaches the allowable duration of 15 minutes, triggering an abnormal evaluation signal; Construct a radar chart with temperature, pressure, rotational speed, and vibration amplitude as coordinate axes. The scale of the temperature coordinate axis is set as 0°C - 150°C, the scale of the pressure coordinate axis is set as 0 MPa - 1 MPa, the scale of the rotational speed coordinate axis is set as 0 revolutions per minute - 2000 revolutions per minute, and the scale of the vibration amplitude coordinate axis is set as 0 mm / s - 10 mm / s; The operating parameters of the current equipment when triggering the abnormal evaluation signal are temperature 75°C, pressure 0.58 MPa, rotational speed 1250 revolutions per minute, and vibration amplitude 5 mm / s. Map these parameter values to the corresponding coordinate axes and connect the points in sequence to form an abnormal polygon; Extract relevant historical fault information from the historical fault database, such as the mechanical fault at the above-mentioned time point P1. Map the operating parameters at that time (temperature 65°C, pressure 0.55 MPa, rotational speed 1200 revolutions per minute, and vibration amplitude 3 mm / s) to the radar chart coordinate axes as well, and connect the points to form a historical polygon; Perform calculations according to steps S1 - S3 to determine the certainty index certa between the current production equipment triggering the abnormal evaluation signal and the corresponding groups of historical fault information.

[0021] Result generation: Based on the certainty index certa between the currently triggered abnormal evaluation signaling production device and each group of historical fault information, selectively trigger the excellent path signaling or the excellent treatment signaling; Specifically: Preset the reference index of the certainty index certa corresponding to each production device, compare the certainty index certa of each group of historical fault information with the corresponding reference index, and screen out the historical fault information with the certainty index certa higher than the reference index as the possible fault information of the currently triggered abnormal evaluation signaling production device, and at the same time trigger the excellent path signaling; If the certainty index certa of each group of historical fault information is lower than the corresponding reference index, directly trigger the excellent treatment signaling; Operation and maintenance push: According to the triggered excellent path signaling or excellent treatment signaling, comprehensively evaluate the status information of each operation and maintenance personnel, and perform corresponding operations to select one operation and maintenance personnel as the handler of the currently triggered abnormal evaluation signaling production device; the status information includes the location and work log; Specifically: If the excellent path signaling is triggered, starting from the location of the currently triggered abnormal evaluation signaling production device, send a location feedback signaling to the mobile terminals of each operation and maintenance personnel. Each operation and maintenance personnel receives the sent location feedback signaling and makes a determination. After determination, obtain the location of each operation and maintenance personnel at the current time point, calculate the distance from the location of each operation and maintenance personnel to the starting point, select the operation and maintenance personnel with the shortest distance as the handler of the currently triggered abnormal evaluation signaling production device, and send the possible fault information of the currently triggered abnormal evaluation signaling production device to the mobile terminal of the handler; If the excellent treatment signaling is triggered, search the work logs of each operation and maintenance personnel for the device code of the currently triggered abnormal evaluation signaling production device, and extract the number of times of handling corresponding to the device code. Analyze the number of times of handling of each operation and maintenance personnel, classify them according to the type of signaling triggered during each handling, and obtain the number of times of handling corresponding to the excellent path signaling and the excellent treatment signaling of each operation and maintenance personnel, denoted as the excellent path times and the excellent treatment times; Set an experience bonus point corresponding to the excellent path signaling and the excellent treatment signaling respectively; the experience bonus point of the excellent path signaling is lower than that of the excellent treatment signaling. For example, they can be set to 1.5 and 2 respectively; Multiply the excellent path times and the excellent treatment times of each operation and maintenance personnel by the corresponding set experience bonus points respectively, and then sum to obtain the ability accumulation value ut1 of each operation and maintenance personnel at the current time point; Obtain the duration of each time corresponding to the excellent path times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent path of each operation and maintenance personnel; obtain the duration of each time corresponding to the excellent treatment times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent treatment of each operation and maintenance personnel; Preset the time intervals corresponding to the average time consumed for excellent routes and the average time consumed for excellent locations respectively. Each time interval corresponding to the average time consumed for excellent routes corresponds to a set of excellent route efficiency scores; the range is set from 1 to 10 and is a positive integer. The shorter the average time consumed for excellent routes, the higher the corresponding excellent route efficiency score; each time interval corresponding to the average time consumed for excellent locations corresponds to a set of excellent location efficiency scores; the range is set from 1 to 10 and is a positive integer. The shorter the average time consumed for excellent locations, the higher the corresponding excellent location efficiency score; convert the average time consumed for excellent routes and the average time consumed for excellent locations of each operation and maintenance personnel into excellent route efficiency scores and excellent location efficiency scores respectively, and then accumulate to obtain the efficiency accumulation value ut2 of each operation and maintenance personnel; Obtain the number of failures in the number of processes handled by each operation and maintenance personnel, calculate the proportion of the number of failures in the number of processes handled, and record it as the failure proportion ut3; Preset the ability passing values and efficiency passing values corresponding to the ability accumulation value ut1 and the efficiency accumulation value ut2 respectively, and mark them as uh1 and uh2; Perform normalization processing on the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 of each operation and maintenance personnel, and then substitute them into the formula Perform weighted calculation to obtain the operation and maintenance evaluation index kder of each operation and maintenance personnel; where Are the influence weight factors of the ability accumulation value ut1, the efficiency accumulation value ut2, and the failure proportion ut3 respectively; Extract the top three operation and maintenance personnel with the highest operation and maintenance evaluation index kder, and obtain the distance between the three operation and maintenance personnel and the starting point. Select the operation and maintenance personnel with the shorter distance among the three operation and maintenance personnel as the processing personnel for the current production equipment that triggers the abnormal evaluation signaling. After the processing personnel maintain the production equipment, update the historical fault database; It should be noted that according to different signaling (excellent route signaling and excellent location signaling), different strategies are flexibly adopted to select operation and maintenance personnel; when the excellent route signaling is triggered, since the possible fault information of the production equipment has been initially understood, more emphasis is placed on considering the location of the operation and maintenance personnel to ensure that they can quickly reach the fault site and conduct troubleshooting and maintenance according to the possible fault information; When the excellent location signaling is triggered, since the possible fault information of the production equipment abnormality cannot be initially understood, by analyzing the work logs, comprehensively considering the processing experience (the number of excellent routes and the number of excellent locations), the processing efficiency (the average time consumed for excellent routes and the average time consumed for excellent locations), and the failure situation (the failure proportion) of the operation and maintenance personnel, the ability of the operation and maintenance personnel is more comprehensively evaluated, so as to select the personnel with better processing ability at the current time point, improve the success rate and quality of fault handling, and update the historical fault database, so that the historical fault database can continuously accumulate new fault handling experience and information.

[0022] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments only. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A big data processing method for intelligent operation and maintenance, characterized in that Including: Data processing: Utilize various sensors to collect the operating parameters of different production equipment in real time and perform preprocessing; the operating parameters are represented by the number a, where a = 1, 2,......, b, and b represents the total number of operating parameters to be collected for different production equipment; for the operating parameters of different production equipment, set the reference operating range and allowable duration for different operating parameters. Historical index: Establish a historical fault database to store all the fault information that has occurred in the history of each production equipment. If, among the operating parameters collected in real time by any production equipment, there is one or more groups of operating parameters that fail to match the corresponding reference operating range and the duration reaches the corresponding set allowable duration, then trigger an abnormal evaluation signaling, and execute the corresponding steps to determine the certainty index certa between the production equipment that currently triggers the abnormal evaluation signaling and the corresponding groups of historical fault information.

2. The big data processing method for intelligent operation and maintenance according to claim 1, wherein Trigger the abnormal evaluation signaling and execute the corresponding steps, specifically: S1: Set independent coordinate axes for each group of operating parameters of the production equipment that currently triggers the abnormal evaluation signaling, construct a radar chart, map the value Ra of each group of operating parameters to the corresponding set coordinate axes, and connect the points in sequence according to the preset connection order of the operating parameters to form a polygon denoted as the abnormal polygon. S2: Similarly to step S1 for each group of historical fault information, form the polygon corresponding to each group of historical fault information, denoted as the historical polygon.

3. The method for processing big data for intelligent operation and maintenance according to claim 2, wherein, Determine the certainty index certa between the production equipment that currently triggers the abnormal evaluation signaling and the corresponding groups of historical fault information, specifically: S3: Arrange the vertex sequences of the abnormal polygon and each group of historical polygons in the same operating parameter order, and obtain the interior angles Uea and Uqa at each vertex, where e represents the number of the abnormal polygon and q represents the number of the historical polygon; According to the formula Calculate the angle evaluation value M1 between the abnormal polygon and each group of historical polygons; Obtain the lengths of each side of the abnormal polygon and the historical polygons of each group, and mark them as Kea and Kqa. According to the formula Calculate the proportional evaluation value M2 of the abnormal polygon and the historical polygons of each group; Obtain the areas of the abnormal polygon and each group of historical polygons, calculate the ratio respectively to obtain the area evaluation value M3 between the abnormal polygon and each group of historical polygons. Extract the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 of the abnormal polygon and each group of historical polygons, and substitute them into the formula Perform weighted calculation to obtain the certainty index certa between the currently triggered abnormal evaluation signaling production device and the corresponding groups of historical fault information; where Are the weight coefficients set corresponding to the angle evaluation value M1, ratio evaluation value M2, and area evaluation value M3 respectively.

4. A big data processing method for intelligent operation and maintenance according to claim 3, characterized in that, Also including: Result generation: Based on the certainty index certa between the production equipment that currently triggers the abnormal evaluation signaling and each group of historical fault information, selectively trigger the excellent path signaling or the excellent treatment signaling. Operation and maintenance push: According to the triggered excellent path signaling or excellent treatment signaling, comprehensively evaluate the status information of each operation and maintenance personnel, and perform the corresponding operations to select one operation and maintenance personnel as the handler of the production equipment that currently triggers the abnormal evaluation signaling; the status information includes the location and work log.

5. A big data processing method for intelligent operation and maintenance according to claim 4, characterized in that, Selectively trigger the excellent path signaling or the excellent treatment signaling, specifically: Preset the reference index of the certainty index certa corresponding to each production equipment, compare the certainty index certa of each group of historical fault information with the corresponding reference index, screen out the historical fault information with the certainty index certa higher than the reference index as the possible fault information of the production equipment that currently triggers the abnormal evaluation signaling, and at the same time trigger the excellent path signaling. If the certainty index certa of each group of historical fault information is lower than the corresponding reference index, then directly trigger the excellent treatment signaling.

6. A big data processing method for intelligent operation and maintenance according to claim 5, characterized in that According to the triggered excellent path signaling, comprehensively evaluate the status information of each operation and maintenance personnel, and perform the corresponding operations to select one operation and maintenance personnel as the handler of the production equipment that currently triggers the abnormal evaluation signaling, specifically: Starting from the location of the current signaling production device that triggered an exception, send a location feedback signal to the mobile terminals of each operation and maintenance personnel. Each operation and maintenance personnel receives the sent location feedback signal and makes a determination. After determination, obtain the location of each operation and maintenance personnel at the current time point, calculate the distance of the journey from the location of each operation and maintenance personnel to the starting point, select the operation and maintenance personnel with the shortest journey distance as the handler for the current signaling production device that triggered an exception, and send the possible fault information of the current signaling production device that triggered an exception to the mobile terminal of the handler.

7. A big data processing method for intelligent operation and maintenance according to claim 6, characterized in that Comprehensively evaluate the status information of each operation and maintenance personnel according to the triggered excellent signaling, and perform corresponding operations to select one operation and maintenance personnel as the handler for the current signaling production device that triggered an exception. Specifically: Search for the device code of the current signaling production device that triggered an exception in the work logs of each operation and maintenance personnel, and extract the number of times of handling the corresponding device code from it. Analyze the number of times of handling of each operation and maintenance personnel, and classify them according to the type of signaling triggered during each handling, to obtain the number of times of handling corresponding to the excellent path signaling and the excellent handling signaling of each operation and maintenance personnel, denoted as the excellent path times and the excellent handling times; Set an experience bonus score corresponding to the excellent path signaling and the excellent handling signaling respectively; Multiply the excellent path times and the excellent handling times of each operation and maintenance personnel by the corresponding set experience bonus scores respectively, and then sum them to obtain the ability accumulation value ut1 of each operation and maintenance personnel at the current time point; Obtain the duration of each time corresponding to the excellent path times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent path of each operation and maintenance personnel; obtain the duration of each time corresponding to the excellent handling times of each operation and maintenance personnel, and calculate the average value to obtain the average time consumed for the excellent handling of each operation and maintenance personnel; Preset the time range intervals corresponding to the average time consumed for the excellent path and the average time consumed for the excellent handling respectively. Each time range interval of the average time consumed for the excellent path corresponds to a set of excellent path efficiency scores; each time range interval of the average time consumed for the excellent handling corresponds to a set of excellent handling efficiency scores; convert the average time consumed for the excellent path and the average time consumed for the excellent handling of each operation and maintenance personnel into excellent path efficiency scores and excellent handling efficiency scores respectively, and then accumulate them to obtain the efficiency accumulation value ut2 of each operation and maintenance personnel; Obtain the number of failure times in the number of times of handling of each operation and maintenance personnel, calculate the proportion of the number of failure times in the number of times of handling, denoted as the failure proportion ut3; Comprehensively analyze the ability accumulation value ut1, the efficiency accumulation value ut2 and the failure proportion ut3 of each operation and maintenance personnel, so as to determine the operation and maintenance evaluation index kder of each operation and maintenance personnel, extract the top three operation and maintenance personnel with the highest kder ranking of the operation and maintenance evaluation index, and obtain the journey distance between the three operation and maintenance personnel and the starting point. Select the operation and maintenance personnel with the shorter journey distance among the three operation and maintenance personnel as the handler for the current signaling production device that triggered an exception. After the handler maintains the production device, update the historical fault database.

8. A big data processing method for intelligent operation and maintenance according to claim 7, characterized in that Comprehensively analyze the ability accumulation value ut1, the efficiency accumulation value ut2 and the failure proportion ut3 of each operation and maintenance personnel. Specifically: The ability passing values and efficiency passing values corresponding to the preset ability accumulation value ut1 and efficiency accumulation value ut2 are marked as uh1 and uh2 respectively; Normalize the ability accumulation value ut1, efficiency accumulation value ut2, and failure ratio ut3 of each operation and maintenance personnel, and then substitute them into the formula Perform weighted calculation to obtain the operation and maintenance evaluation index kder of each operation and maintenance personnel; where Are the influence weight factors of the ability accumulation value ut1, efficiency accumulation value ut2, and failure ratio ut3 respectively.

Images