Abnormal warning method and device, storage medium, and computer equipment
By processing and scoring the machine's operating data, the machine's abnormal warning is achieved, and the problem of difficulty in time discovering abnormalities is solved by traditional analysis methods, which improves the service life and maintenance efficiency of the machine.
Patent Information
- Application Number
- CN202110719533.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-06-28
AI Technical Summary
Traditional industrial big data analysis methods are difficult to detect abnormalities in time, resulting in untimely repair and maintenance of the machine, affecting its service life.
By obtaining the actual data of each operation of the machine, processing and calculating each startup time and success times, and scoring based on the model's abnormality judgment criteria and average number of startup times, the machine's abnormality warning is achieved.
It realizes timely abnormal warning of the machine, extends the service life of the machine, and improves the efficiency of maintenance.
Smart Images

Figure CN113407597B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of abnormal warning technology, and in particular to an abnormal warning method for machine operation, a computer-readable storage medium, a computer device, and an abnormal warning device for machine operation. Background Art
[0002] Industrial big data refers to a large amount of data generated by industrial equipment at high speed, corresponding to the equipment status at different times, and is the information in the Internet of Things. Currently, most applications based on industrial big data are in the stage of statistical analysis of the numerical display of the current status, such as the display of the current position of the machine, real-time operation data, and the statistical summation of the machine's current operating time, fuel consumption, and alarm information. The traditional analysis method of industrial big data requires the reader of the final report to synthesize multiple reports, which is very troublesome and not conducive to the timely repair and maintenance of the machine. Summary of the invention
[0003] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present invention is to provide an abnormal warning method during machine operation, which can warn the machine of abnormalities, and then timely repair and maintain the machine, thereby fully improving the service life of the machine.
[0004] A second object of the present invention is to provide a computer-readable storage medium.
[0005] A third object of the present invention is to provide a computer device.
[0006] A fourth objective of the present invention is to provide an abnormality warning device for machine operation.
[0007] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present invention proposes a method for abnormal warning during machine operation, the method comprising: obtaining actual operation data of the machine each time it runs; processing the actual operation data to obtain each startup time of the machine and the total number of successful startups; determining the model of the machine, determining the single abnormality judgment standard of the model according to the startup time of all machines of the model, and determining the average number of startups per day according to the total number of successful startups, and assigning a value to each startup time of the machine according to the single abnormality judgment standard of the model and the average number of startups per day to obtain a scoring result of the machine; and issuing an abnormal warning to the machine according to the scoring result of the machine.
[0008] The abnormal warning method for the operation of a machine in an embodiment of the present invention first obtains the actual operation data of the machine each time it operates, then obtains the startup time of each machine and the total number of successful startups based on the operation data, and then determines the single abnormal judgment standard of the machine model based on the startup time of each machine and the total number of successful startups, and determines the average number of startups per day based on the total number of successful startups, and then assigns and calculates each startup time of the machine based on the single abnormal judgment standard of the machine model and the average number of startups per day, thereby obtaining the scoring result of the machine, and finally issues an abnormal warning to the machine based on the scoring result of the machine. Therefore, the abnormal warning method for the operation of the machine can issue an abnormal warning to the machine, and then timely repair and maintain the machine, thereby fully improving the service life of the machine.
[0009] In some examples of the present invention, the actual operation data is processed to obtain each startup time of the machine, including: each time the machine is started, determining the startup start time and the startup success time according to the actual operation data; determining each startup time of the machine according to the startup start time and the startup success time.
[0010] In some examples of the present invention, the actual operation data includes the actual speed of the machine, the set speed of the machine, the load of the machine and the data collection time point, wherein determining the startup start time and the startup success time based on the actual operation data includes: determining the startup start time based on the set speed of the machine, the load of the machine and the data collection time point; determining the startup success time based on the actual speed of the machine and the data collection time point.
[0011] In some examples of the present invention, the startup start time is determined according to the set speed of the machine, the load of the machine and the data collection time point, including: when the set speed of the machine changes from zero to the set rated speed of the machine and the load of the machine is zero, the time period to be screened for this processing is determined according to the data collection time point, and when the load of the machine is greater than zero for the first time, the startup start time is determined according to the data collection time point.
[0012] In some examples of the present invention, the startup success time is determined based on the actual rotational speed of the machine and the data collection time point, including: when a preset relationship is satisfied between the actual rotational speed of the machine and the set rotational speed of the machine, it is determined that the machine has been successfully started, and when the data collection time point when the machine is successfully started is within the time period to be screened for this processing, the data collection time point when the machine is successfully started is used as the startup success time.
[0013] In some examples of the present invention, the actual operating data includes the operating current of the machine and the data collection time point, wherein the startup start time and the startup success time are determined based on the actual operating data, including: determining the startup start time based on the data collection time point when the value of the operating current of the machine starts to change from 0; and determining the data collection time when the value of the operating current of the machine reaches the rated value.
[0014] In some examples of the present invention, a single abnormality judgment standard of the model is determined based on each startup time of all machines of the model, including: determining the startup time average value and standard deviation of the model based on each startup time of all machines of the model; determining the single abnormality judgment standard of the model based on the startup time average value and standard deviation of the model.
[0015] In some examples of the present invention, a value is assigned to each startup time of the machine according to the single abnormality judgment standard of the machine model and the average number of startups per day to obtain a scoring result of the machine, including: judging whether each startup time of the machine is abnormal according to the single abnormality judgment standard of the machine model, obtaining a judgment result, and determining an assignment baseline according to the average number of startups per day; determining the assignment and abnormality baseline of the machine at each time according to the judgment result and the assignment baseline; and calculating the scoring result of the machine according to the assignment of the machine at each time within a preset period and the weight of the machine at each time.
[0016] In some examples of the present invention, the assignment and abnormal baseline of the machine at each time are determined according to the judgment result and the assignment baseline, including: distinguishing whether the judgment result is abnormal according to the assignment baseline; when the judgment result is abnormal, determining the abnormal startup assignment of the machine this time; when the judgment result is normal, determining the normal startup assignment of the machine this time; for the same model, each abnormal startup assignment is the same, each normal startup assignment is the same, the abnormal startup assignment and the normal startup assignment are located on both sides of the assignment baseline and the abnormal baseline is the abnormal startup assignment.
[0017] In some examples of the present invention, within a preset period, when the weight of each startup of the machine within a day is the same, the assignment of each time within the day and the weight within the day are calculated to obtain the weighted score value for each day, and the score result of the machine is calculated by the weight of the machine on each day and the weighted score value for each day.
[0018] In some examples of the present invention, an abnormal warning is issued to the machine based on the scoring result of the machine, including: within the preset period, the scoring result is compared with the assigned baseline and the abnormal baseline respectively, and then an abnormal warning is issued to the machine.
[0019] In some examples of the present invention, before calculating the scoring result of the machine according to the value assigned to the machine each time within a preset period and the weight of the machine each time, it also includes: assigning a value to the weight of the machine each time within the preset period, wherein within the preset period, the closer to the current date, the higher the assigned weight, and the farther from the current date, the lower the assigned weight.
[0020] To achieve the above-mentioned purpose, the second aspect of the present invention proposes a computer-readable storage medium, on which an abnormal warning program for machine operation is stored. When the abnormal warning program for machine operation is executed by a processor, the abnormal warning method for machine operation as described in the above embodiment is implemented.
[0021] The computer-readable storage medium of the embodiment of the present invention can issue an abnormal warning to the machine by executing the abnormal warning program stored thereon during the operation of the machine, thereby performing maintenance on the machine in a timely manner and fully improving the service life of the machine.
[0022] To achieve the above-mentioned purpose, an embodiment of the third aspect of the present invention proposes a computer device, which includes a memory, a processor, and a machine operation abnormality warning program stored in the memory and executable on the processor, and when the processor executes the machine operation abnormality warning program, the machine operation abnormality warning method as described in the above embodiment is implemented.
[0023] The computer device of the embodiment of the present invention can issue an abnormal warning to the machine by executing the abnormal warning program stored in the memory during the operation of the machine, and then perform maintenance on the machine in time, thereby fully improving the service life of the machine.
[0024] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes an abnormal warning device for machine operation, which includes: an acquisition module, used to obtain actual operation data of the machine each time it runs; a processing module, used to process the actual operation data to obtain each startup time of the machine; a determination module, used to determine the model of the machine, and determine the single abnormality judgment standard of the model according to the startup time of all machines of the model; an assignment calculation module, used to assign a value to each startup time of the machine according to the single abnormality judgment standard of the model to obtain a scoring result of the machine; an abnormal warning module, used to give an abnormal warning to the machine according to the scoring result of the machine.
[0025] The abnormal warning device for the operation of the machine of the embodiment of the present invention comprises an acquisition module, a processing module, a determination module, an assignment calculation module and an abnormal warning module, wherein each time the machine is operated, the acquisition module is used to acquire its actual operation data, and then the processing module is used to process the actual operation data to obtain each startup time of the machine and the total number of successful startups, and then the abnormal judgment standard of each time of the machine model is determined by the determination module according to each startup time of all machines of the same machine model, and the average number of startups per day is determined according to the total number of successful startups, and then according to the single abnormal judgment standard of the machine model, the stock index calculation module is used to calculate the stock index and the average number of startups per day for each startup time of the machine, and then the scoring result of the machine is obtained, and finally the abnormal warning module is used to give an abnormal warning to the machine according to the scoring result of the machine. Therefore, the abnormal warning device for the operation of the machine can give an abnormal warning to the machine, and then timely repair and maintain the machine, and fully improve the service life of the machine.
[0026] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 is a flow chart of an abnormality warning method during machine operation according to an embodiment of the present invention;
[0028] Figure 2 is a flow chart of an abnormality warning method during machine operation according to an embodiment of the present invention;
[0029] Figure 3 is a flow chart of an abnormality warning method during machine operation according to an embodiment of the present invention;
[0030] Figure 4 is a flow chart of an abnormality warning method during machine operation according to an embodiment of the present invention;
[0031] Figure 5 is a flow chart of an abnormality warning method during machine operation according to an embodiment of the present invention;
[0032] Figure 6 is a structural block diagram of a computer device according to an embodiment of the present invention;
[0033] Figure 7 It is a structural block diagram of an abnormality warning device during machine operation according to an embodiment of the present invention. DETAILED DESCRIPTION
[0034] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0035] The following describes, with reference to the accompanying drawings, an abnormality warning method and apparatus during machine operation, a computer-readable storage medium, and a computer device according to an embodiment of the present invention.
[0036] S10, obtaining actual operation data of the machine each time it is running.
[0037] Specifically, the actual operating data in this embodiment may include the actual speed of the machine, the set speed of the machine, the load of the machine and the data collection time point. It can be understood that in this embodiment, the speed detector, timer, etc. can be used in combination to obtain the actual operating data of the machine during each operation.
[0038] S20, processing the actual operation data to obtain each startup time of the machine and the total number of successful startups.
[0039] Specifically, after obtaining the actual operation data of each machine operation, the data can be uploaded to the database. When the data needs to be processed, the corresponding actual operation data can be extracted from the database and then processed to obtain each startup time of the machine and the total number of successful startups.
[0040] In some embodiments of the present invention, Figure 2 As shown, the actual operation data is processed to obtain each startup time of the machine and the total number of successful startups, including:
[0041] S201, each time the machine is started, determining the start time and the start success time according to the actual operation data.
[0042] Specifically, each time the machine is started, the start time and the start success time can be determined based on the actual operating data of the machine, such as speed, load, current, signal, pressure, etc., which can express the machine state change data.
[0043] More specifically, in this embodiment, the actual operation data may include the actual speed of the machine, the set speed of the machine, the load of the machine and the data collection time point, wherein the startup start time and the startup success time are determined based on the actual operation data, including: determining the startup start time based on the set speed of the machine, the load of the machine and the data collection time point.
[0044] Specifically, the start time in this embodiment is generally not directly obtained, but is calculated and determined according to the set speed of the machine, the load of the machine and the data collection time point. More specifically, taking the diesel engine as an example, the start time of the current start of the diesel engine can be determined according to the change of the set speed of the diesel engine, that is, the set speed changes from zero to the preset rated value. After the start time of the diesel engine passes through a self-check procedure of several seconds (such as 3 seconds), the start time of the diesel engine can be determined when the diesel engine load changes from zero to the preset rated value. It can be understood that if the diesel engine load changes from zero, it can be determined that the diesel engine has started, and it should be noted that the preset rated values of diesel engines of different models are not the same, and the time required for the self-check procedure is also different. In some embodiments of the present invention, the startup start time is determined based on the set speed of the machine, the load of the machine and the data collection time point, including: when the set speed of the machine changes from zero to the set rated speed of the machine and the load of the machine is zero, the time period to be screened for this processing is determined based on the data collection time point, and when the load of the machine is greater than zero for the first time, the startup start time is determined based on the data collection time point.
[0045] Specifically, in this embodiment, when the set speed of the machine changes from zero to the rated speed set for the machine, the current time can be determined as the starting time T0, and when the load of the machine is zero, the starting time T0 plus the set time (for example, 40 seconds) is used as the time period to be screened for this analysis. During this time period, if the load of the machine is greater than zero for the first time, the start time T1 of the machine can be determined.
[0046] In this embodiment, the startup success time can be determined according to the actual rotation speed of the machine and the data collection time point.
[0047] Specifically, after the machine starts to start, it is not certain whether the current startup of the machine can be successful. In this embodiment, whether the machine is successfully started is determined based on the actual rotation speed of the machine and the data collection time point, and after the machine starts successfully, the startup success time is determined.
[0048] In some embodiments of the present invention, the successful startup time is determined based on the actual rotation speed of the machine and the data collection time point, including: when a preset relationship is satisfied between the actual rotation speed of the machine and the set rated speed of the machine, it is determined that the machine has been successfully started, and when the data collection time point when the machine is successfully started is within the time period to be screened for this processing, the data collection time point when the machine is successfully started is used as the successful startup time.
[0049] Specifically, in the time period to be screened (e.g., T0+40 seconds), after determining the start time T1 of the machine startup, after a period of time, the actual speed of the machine can be compared with the set rated speed of the machine to determine whether the machine has started successfully, and the current time is used as the successful startup time T2. It is understandable that if in the time period to be screened, after determining the start time T1 of the machine startup, if the actual speed of the machine returns to zero before reaching the set rated speed, that is, it cannot start and directly shuts down, then it can be determined that the machine has failed to start; if in the time period to be screened, after determining the start time T1 of the machine startup, if the actual speed of the machine cannot reach the set rated speed, then it can also be determined that the machine has failed to start.
[0050] S203, determining each startup time of the machine according to the startup start time and the startup success time.
[0051] Specifically, after determining the start start time T1 and the start success time T2, the start start time T1 can be subtracted from the start success time T2 to determine each start time of the machine. For example, the data collection time point is 8:22:08 on July 19, 2020, and the diesel engine speed is set to 0 revolutions per second. At 8:22:09 on July 19, 2020, the set value becomes 1300 revolutions per second and the current diesel engine load is 0 (when the start button is clicked to start, the controller will issue a command to change the speed to the set 1300 revolutions per second or other specified value). It should be noted that 8:22:09 on July 19, 2020 to 8:22:49 on July 19, 2020 can be set as the time period to be screened for this analysis. In the time period to be screened, assuming that the first diesel engine load greater than 0 is found from 8:22:09 on July 19, 2020, which occurs at 8:22:12 on July 19, 2020 (these 3 seconds can correspond to the self-test process), then 8:22:12 on July 19, 2020 can be set as the start time T1 of the diesel engine, and the actual speed of the diesel engine is checked in chronological order from T1. When the actual speed of the diesel engine is greater than 1279 revolutions, it is determined that the diesel engine is started successfully, and the current time 8:22:17 on July 19, 2020 is obtained, which is recorded as T2. T2-T1=5 seconds, when this start is successful, it takes 5 seconds, that is, the current start time of the diesel engine is 5 seconds. It should be noted that, considering the speed error of the diesel engine itself, the speed of the diesel engine may not be stable at 1300 revolutions per second. In this example, the speed error of the diesel engine is set to 21 revolutions per second. When the actual speed of the diesel engine reaches 1279 revolutions, it can be determined that the diesel engine is started successfully. It can be understood that the startup data of all machines in the database can be obtained, that is, whether the startup is successful or not, and the time of each successful startup.
[0052] In some embodiments, the self-checking time can be 0 or a fixed value. When the self-checking time is 0, the time T0 of the set speed change can be directly used as the start time, and there is no need to check the diesel engine load. When the self-checking time is a fixed value n, T0+n is directly used as T1, and there is no need to check the diesel engine load.
[0053] In some other embodiments, the power source may not be a diesel engine, but may be replaced by an electric motor or other power sources, and the actual operation data includes the operating current of the machine and the data collection time point, wherein determining the start start time and the start success time according to the actual operation data includes:
[0054] The startup start time is determined according to the data collection time point when the value of the running current of the machine changes from 0; the startup success time is determined according to the data collection time point when the value of the running current of the machine reaches the rated value.
[0055] In some other embodiments, the actual operation data may also include a status code and a data collection time point, and the startup start time and the startup success time are determined by the status code and the data collection time point.
[0056] In some other embodiments, the actual operation data may also include data such as container pressure, as long as the parameters can determine the startup start time and the startup success time.
[0057] Each successful startup of the machine is recorded as 1 successful startup, and the total number of successful startups within the preset period is calculated.
[0058] S30, determine the model of the machine, and determine the single abnormality judgment standard of the model according to each startup time of all machines of the model, and determine the average number of startups per day according to the total number of successful startups, and assign a value to each startup time of the machine according to the single abnormality judgment standard of the model and the average number of startups per day to obtain a scoring result of the machine.
[0059] Specifically, different machine models have different startup times. For example, some machine models have a startup time of 5 seconds, and some machine models have a startup time of 10 seconds. If they are not divided and compared using a unified standard, it is very likely that some machines have no startup obstacles, but are still classified as having obstacles, because it is easy to cause misjudgment. Therefore, in this embodiment, the machine model can be determined first, and then the single abnormality judgment standard and the average number of startups per day of the machine model can be determined based on the startup time of all machines of the model to improve the judgment accuracy, and each startup time of the machine is assigned a value according to the single abnormality judgment standard of the machine model to obtain the scoring result of the machine.
[0060] In some specific embodiments, Figure 3 As shown, the single abnormality judgment standard of the model is determined according to each startup time of all machines of the model, and the average number of startups per day is determined according to the total number of successful startups, including:
[0061] S301, determining an average startup time and a standard deviation of a machine model according to each startup time of all machines of the machine model.
[0062] Specifically, in order to more accurately determine whether the machine needs intervention for repair or maintenance, historical data can be statistically scored, and the historical data is the historical data of the same machine model. More specifically, the average and standard deviation of the startup time of the machine model, as well as the average number of startups per day, are determined based on each startup time of all machines of the same model. It should be noted that, based on experience, in this embodiment, only the relevant data of the machine in the last 30 days can be obtained. The data outside 30 days is of little reference value to the current machine status and is not considered here.
[0063] For example, the average startup time of all machines of a certain model in the past 30 days may be 3.24, the standard deviation may be 0.78, and the number of startups per day may be [4, 5, 5, 4, 6, 6, ...]. The total number of successful startups is calculated by summing the number of successful startups and then dividing it by the preset period to calculate the average number of startups per day, such as 5 times.
[0064] S302, determining a single abnormality judgment standard of the model according to the average startup time and standard deviation of the model.
[0065] Specifically, although the startup time of the machine does not conform to the Gaussian distribution, due to the value interval problem, the startup time of the machine is a set of discrete data, which can be approximately treated as a general Gaussian distribution. For general Gaussian distribution data, in this embodiment, the average value plus three times the standard deviation can be used as the demarcation line of the abnormality. Since the standard deviation value in the above example is generally smaller than the sampling interval (assuming that the sampling interval in this embodiment is 1 second), the smallest integer greater than the average value plus three times the standard deviation can be approximately used as the distinction standard for single abnormalities. For example, when the average startup time of a certain model is 3.24 seconds and the standard deviation is 0.78, then 3.24+0.78*3=5.58, and the smallest integer greater than 5.58 is 6, then 6s is used as the demarcation line of the abnormality, that is, greater than 6s is regarded as a single startup abnormality. After determining the single abnormality judgment standard of the model, the machine startup time can be assigned and calculated according to the single abnormality judgment standard of the model to obtain the scoring result of the machine.
[0066] In this embodiment, if Figure 4As shown in the figure, the machine startup time is assigned a value based on the single abnormality judgment standard of the machine model and the average number of startups per day to obtain the scoring results of the machine, including:
[0067] S401, judging whether each startup time of the machine is abnormal according to the single abnormality judgment standard of the machine model, obtaining the judgment result, and determining the assignment baseline according to the average number of startups per day. S402, determining the assignment and abnormality baseline of the machine at each time according to the judgment result and the assignment baseline.
[0068] Specifically, after obtaining the single abnormality judgment standard, all startup times can be divided into normal and abnormal, and then assigned a value, wherein the assigned value depends on the average number of daily startups. After determining the assigned value, the current weighted score of the machine can be calculated based on the assigned value. For example, the average number of startups of a certain model per day is 5, and the startup time data of a certain machine under this model on a certain day is [7, 5, 4, 5, 7]. Based on the above calculation, the abnormal judgment time is greater than 6s, and because the startup performance of the machine will be poor in the cold state, but the impact on the evaluation of the overall performance of the machine will be relatively small. Therefore, when assigning values, ensure that a single occasional poor startup performance will not cause the single-day score to be greater than the assignment baseline of 0 (that is, one startup abnormality can be tolerated every day). Therefore, the normal startup situation can be assigned a value of -1, and the abnormal startup is assigned a value of 4 to ensure that the assignment baseline 0 can correctly distinguish between the abnormal and normal of a single day (-1×4+1×4=0), and the value is assigned to [4, -1, -1, -1, 4]; when the weight of each startup in a single day is set to the same, the weighted score value of the day is 4-1-1-1+4=5; in addition, the abnormal startup is assigned a value of 4 as the abnormal baseline.
[0069] In this embodiment, if Figure 5 As shown, the assignment and abnormal baseline of the machine at each time are determined according to the judgment result and the assignment baseline, including: S501, distinguishing whether the judgment result is abnormal according to the assignment baseline. S502, when the judgment result is abnormal, determining the abnormal startup assignment of the machine this time. S503, when the judgment result is normal, determining the normal startup assignment of the machine this time. S504, for the same machine model, each abnormal startup assignment is the same, each normal startup assignment is the same, the abnormal startup assignment and the normal startup assignment are on both sides of the assignment baseline, and the abnormal baseline is the abnormal startup assignment.
[0070] Specifically, it can be understood that the above method can be used to calculate the weighted score values of all working days of the machine in the past 30 days in turn, wherein, when the judgment result is abnormal, it can be determined that the abnormal startup value of the machine is greater than the assignment baseline, and optionally, it is assigned a value of 4; when the judgment result is normal, it can be determined that the normal startup value of the machine is less than the assignment baseline, and optionally, it is assigned a value of -1. For the same model, each abnormal startup value is the same, and each normal startup value is the same. The abnormal startup value and the normal startup value are on both sides of the assignment baseline and the abnormal baseline is the abnormal startup value, that is, 4 is the abnormal baseline.
[0071] It should be noted that the abnormal startup value and the normal startup value are located on both sides of the assignment baseline, including the following two situations: (1) the abnormal startup value is greater than the assignment baseline, and the normal startup value is less than the assignment baseline; (2) the abnormal startup value is less than the assignment baseline, and the normal startup value is greater than the assignment baseline. In this embodiment, the first situation (1) is adopted, that is, the abnormal startup value is 4, and the normal startup value is -1.
[0072] S403, calculating the scoring result of the machine according to the value assigned by the machine each time and the weight of the machine each time within a preset period.
[0073] Specifically, the preset period in this embodiment can be 30 days. During these 30 days, the scoring result of the machine can be calculated based on the value assigned by the machine each time and the weight of the machine at each time. For example, for each machine, a comprehensive total score is obtained based on the value assigned each time and the time weight of each time, and then the scoring result can be obtained. The specific calculation formula of the total score is as follows: V all is the total score, i is the total number of starts, V i For a single assignment, P i When the weight of each startup of the machine is the same within the preset period, the daily weight and the daily weight are calculated to obtain the daily weighted score value. The score result of the machine is calculated by the daily weight and the daily weighted score value. At this time, the specific calculation formula of the total score is as follows: Among them, V all is the total score, Vd i is the daily score of the i-th day from today, P i is the daily weight of the i-th day from today. For example, the scores of machine a in the last 30 days are [5, -1, -1, 3, -1, -1, -1, ...], with different weight values for each day. The scores of each day are multiplied by the weight values and added together to get a final score of 4.3; machine b performs the same operation and the final score is 0.5; machine c's final score is -0.87.
[0074] S40, issuing an abnormal warning to the machine according to the scoring result of the machine.
[0075] Specifically, within the preset period, by comparing the scoring result with the assigned baseline and the abnormal baseline, the machine is given an abnormal warning. In this embodiment, after obtaining the final score of each machine, the final score can be compared with the comparison value. For example, in this embodiment, 0 is set as the baseline, and the critical value is the current score of any machine when the score is 0. When there is a latest abnormal state, the value is 4, 4 is the abnormal baseline, and the weight is 1, because the total score of the remaining startup times is 0, then 4 becomes a new critical state, that is, when it is less than 4, it can be confirmed that the machine state has been improved, and when it is greater than or equal to 4, it means that the machine state has not been improved and intervention maintenance is required. In this example, the final score of machine a is 4. Since 4.3>4, its scoring result can be marked as requiring maintenance; the final score of machine b is 0.5. Since 4>0.5>0, its scoring result can be marked as not requiring maintenance for the time being, but requiring continuous attention; the final score of machine c is -0.87. Since -0.87<0, it is marked as normal and does not require maintenance.
[0076] Optionally, the machines can be sorted from high to low according to their final weighted total scores, and the list can be provided to maintenance engineers or customers, and a visual chart can be provided to facilitate maintenance or browsing by engineers or customers.
[0077] In some embodiments of the present invention, before calculating the scoring result of the machine based on the weighted scoring value of the machine on each day within a preset period and the weight of the machine on each day, it also includes: assigning a weight to the machine on each day within the preset period, wherein, within the preset period, the closer to the current date, the higher the assigned weight, and the farther from the current date, the lower the assigned weight.
[0078] Specifically, since the closer to the current date, the greater the impact of the abnormality, this embodiment assigns different values to the weight of each day of the machine according to the distance from the current date, wherein the closer to the current date, the higher the assigned weight, and the farther from the current date, the lower the assigned weight. In this embodiment, the weight of the date closest to the current time can be assigned to 1, and the weight of the date farthest from the current time, such as the 30th day, is assigned to be infinitely close to 0. Optionally, the weights of each day from the 1st day to the 30th day can be evenly divided from 1 to 0.
[0079] In some embodiments of the present invention, within a preset period, if the consecutive preset weighted score values adjacent to the current date are all less than the assigned baseline, it is directly determined that the machine is currently normal and is reflected by the weight function value.
[0080] Specifically, this embodiment is described by taking the above-mentioned specific embodiment of an average of 5 startups per day as an example, wherein the worst score for a single day is 4*5=20, and a single-day score less than 0 is uniformly determined to be qualified, so it is uniformly corrected to -1 point (i.e. -2, -3, -4, -5 are uniformly corrected to -1), so the highest score range for a single day is -1 to 20. If the machine's consecutive preset weighted score values adjacent to the current date are all less than the assigned baseline, it can be directly determined that the machine is currently normal, wherein the preset weighted score values can be 3. In addition, according to actual application experience, if there is no startup abnormality for consecutive preset days, it can be considered that if there was an abnormality before, no matter how bad the machine is on the current date, it can be considered that it has been repaired, then It should be noted that if there is no worse case than the above machine, it can be expressed as V all >0.
[0081] In summary, the abnormality warning method during machine operation of the embodiment of the present invention can provide abnormality warning for the machine, and then perform maintenance on the machine in a timely manner, thereby fully improving the service life of the machine.
[0082] Furthermore, the present invention proposes a computer-readable storage medium on which a machine operation abnormality warning program is stored. When the machine operation abnormality warning program is executed by a processor, the machine operation abnormality warning method in the above embodiment is implemented.
[0083] The computer-readable storage medium of the embodiment of the present invention can issue abnormal warnings to the machine by executing the abnormal warning program stored in the memory during machine operation through the processor, thereby timely repairing and maintaining the machine and fully improving the service life of the machine.
[0084] Figure 6 is a structural block diagram of a computer device according to an embodiment of the present invention.
[0085] Furthermore, if Figure 6 As shown, the present invention proposes a computer device 10, which includes a memory 11, a processor 12, and a machine operation abnormality warning program stored in the memory 11 and executable on the processor 12. When the processor 12 executes the machine operation abnormality warning program, the machine operation abnormality warning method in the above-mentioned embodiment is implemented.
[0086] The computer device of the embodiment of the present invention includes a memory and a processor. The processor executes the abnormal warning program stored in the memory during the operation of the machine, which can provide abnormal warning for the machine, and then perform maintenance on the machine in time to fully improve the service life of the machine.
[0087] Figure 7 It is a structural block diagram of an abnormality warning device during machine operation according to an embodiment of the present invention.
[0088] Furthermore, if Figure 7 As shown, the present invention proposes an abnormality warning device 100 during machine operation, and the abnormality warning device 100 includes an acquisition module 101, a processing module 102, a determination module 103, a value assignment calculation module 104 and an abnormality warning module 105.
[0089] Among them, the acquisition module 101 is used to obtain the actual operation data of the machine each time it runs; the processing module 102 is used to process the actual operation data to obtain the startup time of each machine and the average number of startups per day; the determination module 103 is used to determine the model of the machine, and determine the single abnormality judgment standard of the model according to the startup time of each machine of the model, and determine the average number of startups per day according to the total number of successful startups; the assignment calculation module 104 is used to assign a value to the startup time of each machine according to the single abnormality judgment standard of the model and the average number of startups per day, and obtain the scoring result of the machine; the abnormal warning module 105 is used to issue an abnormal warning to the machine according to the scoring result of the machine.
[0090] Specifically, the actual operation data in this embodiment may include the actual speed of the machine, the set rated speed of the machine, the load of the machine and the data collection time point. It can be understood that in this embodiment, the acquisition module 101 may include a speed detector, a timer, etc. to cooperate to acquire the actual operation data of the machine at each operation. After the acquisition module 101 acquires the actual operation data of the machine at each operation, the data can be uploaded to the database. When the data needs to be processed, the corresponding actual operation data can be extracted from the database, and then the processing module 102 is used to process it, so as to obtain the startup time of each machine and the total number of successful startups. Due to different machine models, the startup time is also different. For example, the startup time of some machine models is 5 seconds, and the startup time of some machine models is 10 seconds. If they are not divided and compared with a unified standard, it is very likely that some machines have no startup obstacles, but are still classified as having obstacles, because it is easy to cause misjudgment. Therefore, in this embodiment, the determination module 103 can be used to first determine the model of the machine, and then the single abnormality judgment standard of the machine of the model can be determined according to the startup time of each machine of the model, and the average number of startups per day can be determined according to the total number of successful startups to improve the judgment accuracy, and the assignment calculation module 104 can also be used to assign a value to each startup time of the machine according to the single abnormality judgment standard of the model and the average number of startups per day to obtain the scoring result of the machine. More specifically, within a preset period, the scoring result is compared with the assigned baseline and the abnormal baseline respectively, and then an abnormal warning is issued for the machine. In this embodiment, after obtaining the final score of each machine, the final score can be compared with the comparison value. For example, this embodiment sets 0 as the baseline, and for any machine, the current score of 0 is the critical value. When there is a latest abnormal state, it is assigned 4, 4 is the abnormal baseline, and the weight is 1. Because the total score of the remaining startup times is 0, then 4 becomes a new critical state, that is, when it is less than 4, it can be confirmed that the machine state has been improved, and when it is greater than or equal to 4, it means that the machine state has not been improved. The abnormal warning module 105 can issue an early warning reminder to the machine to indicate that the machine needs intervention and maintenance. For example, machine a finally scores 4. Since 4.3>4, its score can be marked as requiring maintenance; machine b finally scores 0.5. Since 4>0.5>0, its score can be marked as not requiring maintenance for the time being, but requiring continued attention; machine c finally scores -0.87. Since -0.87<0, it is marked as normal and does not require maintenance.
[0091] In some embodiments of the present invention, the processing module 102 processes the actual operation data to obtain each startup time of the machine, including: determining the startup start time and the startup success time according to the actual operation data each time the machine starts; determining each startup time of the machine according to the startup start time and the startup success time.
[0092] In some embodiments of the present invention, the processing module 102 determines the startup start time and the startup success time based on the actual operation data, including: determining the startup start time based on the set speed of the machine, the load of the machine and the data collection time point; determining the startup success time based on the actual speed of the machine and the data collection time.
[0093] In some embodiments of the present invention, the processing module 102 determines the startup start time according to the set speed of the machine, the load of the machine and the data collection time point, including: when the set speed of the machine changes from zero to the set rated speed of the machine and the load of the machine is zero, the time period to be screened for this processing is determined according to the data collection time, and when the load of the machine is greater than zero for the first time, the startup start time is determined according to the data collection time.
[0094] In some embodiments of the present invention, the processing module 102 determines the successful startup time based on the actual rotation speed of the machine and the data collection time point, including: when a preset relationship is satisfied between the actual rotation speed of the machine and the set rated speed of the machine, it is determined that the machine has been successfully started, and when the data collection time point when the machine is successfully started is within the time period to be screened for this processing, the data collection time point when the machine is successfully started is used as the successful startup time.
[0095] In some embodiments of the present invention, the actual operating data includes the operating current of the machine and the data collection time point, wherein the processing module 102 determines the startup start time and the startup success time based on the actual operating data, including: determining the startup start time based on the data collection time point when the value of the machine's operating current starts to change from 0; determining the startup success time based on the data collection time point when the value of the machine's operating current reaches the rated value.
[0096] In some embodiments of the present invention, the determination module 103 determines the single abnormality judgment standard of the model based on the startup time of each time all machines of the model, and determines the average number of startups per day based on the total number of successful startups, including: determining the startup time average value and standard deviation of the model based on the startup time of each time all machines of the model; determining the single abnormality judgment standard of the model based on the startup time average value and standard deviation of the model.
[0097] In some embodiments of the present invention, the assignment calculation module 104 assigns a value to each startup time of the machine according to the single abnormality judgment standard of the machine model and the average number of startups per day to obtain a scoring result of the machine, including: judging whether each startup time of the machine is abnormal according to the single abnormality judgment standard of the machine model, obtaining a judgment result, and determining an assignment baseline according to the average number of startups per day; determining the machine's assignment and abnormality baseline each time according to the judgment result and the assignment baseline; calculating the scoring result of the machine according to the machine's assignment each time within a preset period and the machine's weight each time.
[0098] In some embodiments of the present invention, the assignment calculation module 104 determines the machine's assignment and abnormal baseline at each time based on the judgment result and the assignment baseline, including: distinguishing whether the judgment result is abnormal based on the assignment baseline, and when the judgment result is abnormal, determining the machine's abnormal startup assignment this time; when the judgment result is normal, determining the machine's normal startup assignment this time; for the same model, each abnormal startup assignment is the same, each normal startup assignment is the same, the abnormal startup assignment and the normal startup assignment are on both sides of the assignment baseline and the abnormal baseline is the abnormal startup assignment.
[0099] In some embodiments of the present invention, within a preset period, when the weight of each startup of the machine within a day is the same, the assignment calculation module 104 calculates the assignment and the daily weight for each day to obtain a weighted score value for each day, and calculates the scoring result of the machine through the machine's daily weight and the daily weighted score value.
[0100] In some embodiments of the present invention, the abnormal warning module 105 is also used to compare the scoring result with the assigned baseline and the abnormal baseline respectively within a preset period, and then issue an abnormal warning to the machine.
[0101] In some embodiments of the present invention, the assignment calculation module 104, before calculating the scoring result of the machine according to the machine's assignment at each time and the machine's weight at each time within a preset period, further includes: assigning a weight to the machine at each time within a preset period, wherein, within the preset period, the closer to the current date, the higher the assigned weight, and the farther from the current date, the lower the assigned weight.
[0102] In some embodiments of the present invention, the abnormality warning module 105 directly determines that the machine is currently free of abnormalities if the consecutive preset weighted score values immediately adjacent to the current date are all less than the assigned baseline within a preset period.
[0103] It should be noted that, for other specific implementations of the abnormality warning device during machine operation according to an embodiment of the present invention, reference can be made to the specific implementations of the abnormality warning method during machine operation in the above embodiment, which will not be described in detail here.
[0104] In summary, the abnormality warning device during machine operation of the embodiment of the present invention can warn the machine of abnormalities, and then perform maintenance on the machine in a timely manner, thereby fully improving the service life of the machine.
[0105] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0106] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0107] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0108] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.
[0109] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.
[0110] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.
[0111] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.
[0112] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A method for abnormal warning during machine operation, characterized in that: include: Get the actual operation data of the machine every time it runs; Processing the actual operation data to obtain each startup time and the total number of successful startups of the machine; Determine the model of the machine, determine the single abnormality judgment standard of the machine model according to each startup time of all machines of the model, determine the average number of startups per day according to the total number of successful startups, and assign a value to each startup time of the machine according to the single abnormality judgment standard of the machine model and the average number of startups per day to obtain a scoring result of the machine; Providing an abnormal warning to the machine according to the scoring result of the machine; The actual operation data is processed to obtain each startup time and the total number of successful startups of the machine, including: determining the startup start time and the successful startup time according to the actual operation data each time the machine is started; determining each startup time of the machine according to the startup start time and the successful startup time; Wherein, determining the single abnormality judgment standard of the machine model according to each startup time of all machines of the machine model, and determining the average number of startups per day according to the total number of successful startups, including: determining the average startup time and standard deviation of the machine model according to each startup time of all machines of the machine model; determining the single abnormality judgment standard of the machine model according to the average startup time and standard deviation of the machine model; A value is assigned and calculated for each startup time of the machine according to the single abnormality judgment standard of the machine model and the average number of startups per day to obtain a scoring result of the machine, including: judging whether each startup time of the machine is abnormal according to the single abnormality judgment standard of the machine model, obtaining a judgment result, and determining an assignment baseline according to the average number of startups per day; determining the assignment and abnormality baseline of the machine at each time according to the judgment result and the assignment baseline; and calculating the scoring result of the machine according to the assignment of the machine at each time within a preset period and the weight of the machine at each time.
2. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: The actual operation data includes the actual speed of the machine, the set speed of the machine, the load of the machine and the data collection time point, wherein determining the startup start time and the startup success time according to the actual operation data includes: Determining the start time according to the set speed of the machine, the load of the machine and the data collection time point; The startup success time is determined according to the actual rotation speed of the machine and the data collection time.
3. The abnormal warning method for machine operation as claimed in claim 2, characterized in that: Determining the start time according to the set speed of the machine, the load of the machine and the data collection time point includes: When the set speed of the machine changes from zero to the rated speed set for the machine and the load of the machine is zero, the time period to be screened for this processing is determined according to the data collection time point, and when the load of the machine is greater than zero for the first time, the startup start time is determined according to the data collection time point.
4. The abnormal warning method for machine operation as claimed in claim 3, characterized in that: Determining the startup success time according to the actual rotation speed of the machine and the data collection time point includes: When a preset relationship is satisfied between the actual rotation speed of the machine and the set rotation speed of the machine, it is determined that the machine is started successfully, and when the data collection time point when the machine is started successfully is within the time period to be screened for this processing, the data collection time point when the machine is started successfully is used as the startup success time.
5. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: The actual operation data includes the operation current of the machine and the data collection time point, wherein determining the startup start time and the startup success time according to the actual operation data includes: Determine the start start time according to the data collection time point when the value of the running current of the machine starts to change from 0; The startup success time is determined according to the data collection time point when the value of the running current of the machine reaches the rated value.
6. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: Determining the value assignment and abnormality baseline of the machine at each time according to the judgment result and the value assignment baseline, including: Distinguishing whether the judgment result is abnormal according to the assigned reference line; When the judgment result is abnormal, determining the current abnormal startup assignment of the machine; When the judgment result is normal, determining the normal startup value of the machine; For the same model, each abnormal startup value is the same, and each normal startup value is the same. The abnormal startup value and the normal startup value are located on both sides of the value baseline, and the abnormal baseline is the abnormal startup value.
7. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: Within the preset period, when the weight of each startup of the machine within a day is the same, the assignment of each time within the day and the weight within the day are calculated to obtain the weighted score value for each day, and the score result of the machine is calculated by the weight of the machine on each day and the weighted score value for each day.
8. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: According to the scoring result of the machine, an abnormal warning is given to the machine, including: During the preset period, the scoring result is compared with the assigned baseline and the abnormal baseline respectively, and then an abnormal warning is issued to the machine.
9. The abnormal warning method for machine operation as claimed in claim 1, characterized in that: Before calculating the scoring result of the machine according to the value assigned by the machine each time and the weight of the machine each time within a preset period, the method further includes: The weight of the machine is assigned each time within the preset period, wherein within the preset period, the closer to the current date, the higher the assigned weight, and the farther from the current date, the lower the assigned weight.
10. A computer-readable storage medium, characterized in that: An abnormality warning program for machine operation is stored thereon, and when the abnormality warning program for machine operation is executed by the processor, the abnormality warning method for machine operation as described in any one of claims 1-9 is implemented.
11. A computer device, characterized in that: The invention comprises a memory, a processor and a machine operation abnormality warning program stored in the memory and executable on the processor. When the processor executes the machine operation abnormality warning program, the machine operation abnormality warning method as described in any one of claims 1 to 9 is implemented.
12. An abnormal warning device for machine operation, characterized in that: include: An acquisition module is used to obtain actual operation data of the machine each time it is run; A processing module, used for processing the actual operation data to obtain each startup time and the total number of successful startups of the machine; A determination module, used to determine the model of the machine, determine the single abnormality judgment standard of the model according to each startup time of all machines of the model, and determine the average number of startups per day according to the total number of successful startups; An assignment calculation module, used to assign a value to each startup time of the machine according to the single abnormality judgment standard of the machine model and the average number of startups per day, to obtain a scoring result of the machine; An abnormal warning module, used for issuing an abnormal warning to the machine according to the scoring result of the machine; The processing module is specifically used to: determine the startup start time and the startup success time according to the actual operation data each time the machine is started; determine each startup time of the machine according to the startup start time and the startup success time; The determination module is specifically used to: determine the average startup time and standard deviation of the model according to each startup time of all machines of the model; determine the single abnormality judgment standard of the model according to the average startup time and standard deviation of the model; The assignment calculation module is specifically used for: judging whether each startup time of the machine is abnormal according to the single abnormality judgment standard of the machine model, obtaining a judgment result, and determining an assignment baseline according to the average number of startups per day; determining the assignment and abnormality baseline of the machine at each time according to the judgment result and the assignment baseline; and calculating the scoring result of the machine according to the assignment of the machine at each time within a preset period and the weight of the machine at each time.
