Intelligent factory management method and system

Abstract

The application relates to an intelligent factory management method and system, and relates to the field of intelligent factory management technology, which comprises the following steps: step 100: collecting an execution parameter of an execution device; step 101: judging whether a fault exists in response to the execution parameter and a preset fault interval; step 102: when the fault exists, determining a fault parameter in combination with the execution parameter and the preset fault interval; step 103: determining a fault type according to the fault parameter; and step 104: generating and sending fault prompt information based on the fault type. The application has the effects of improving the management efficiency of a factory on an execution device and accurately analyzing the cause of a fault when the fault occurs.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of factory intelligent management technology, and in particular to an intelligent factory management method and system. BACKGROUND

[0002] The control cabinet is a device that integrates data acquisition, communication interaction, intelligent analysis, remote monitoring and other digital capabilities, can realize precise control, state monitoring, fault warning and collaborative management of production equipment, and is used to connect field devices and factory management systems.

[0003] In the prior art, the current of the execution device is recorded in real time by the control cabinet, so that when the execution device fails, the fault data is fed back to the DCS through the control cabinet, and the DCS analyzes the fault reason to inform the relevant staff. Limited by the data exchange speed of the control cabinet and the DCS, the data fed back to the DCS by the control cabinet is limited.

[0004] When the execution device fails, the DCS cannot accurately determine the cause of the failure based on limited data, so the staff needs to arrive at the scene to determine the cause of the failure again, which reduces the management efficiency of the factory to the execution device. SUMMARY

[0005] In order to improve the management efficiency of the factory to the execution device and accurately analyze the cause of the failure, the present application provides an intelligent factory management method and system.

[0006] In a first aspect, the present application provides an intelligent factory management method, which adopts the following technical solution:

[0007] An intelligent factory management method, comprising:

[0008] Step 100: collecting execution parameters of an execution device;

[0009] Step 101: determining whether there is a failure in response to the execution parameters and a preset failure interval;

[0010] Step 102: when there is a failure, determining a failure parameter in combination with the execution parameters and the preset failure interval;

[0011] Step 103: determining a failure type according to the failure parameter;

[0012] Step 104: generating and sending a failure prompt information based on the failure type.

[0013] By adopting the technical scheme, the current and other parameters of the execution equipment are monitored in real time on the control cabinet, so that when an abnormal parameter of the execution equipment occurs, the cause of the fault of the execution equipment is analyzed in combination with the real-time parameters such as the current, and then the analyzed cause of the fault is fed back to the DCS, thereby improving the accuracy of the analysis of the cause of the fault and improving the management efficiency of the execution equipment of the factory.

[0014] Optionally, the method further comprises:

[0015] Step 105: When there is a fault, historical parameters are retrieved based on the fault parameters, and a peak threshold is determined based on the fault parameters;

[0016] Step 106: A peak point is determined in response to the historical parameters and the peak threshold;

[0017] Step 107: A peak fluctuation curve is generated based on the peak point;

[0018] Step 108: A fluctuation slope is read from the peak fluctuation curve, and a fluctuation threshold is determined according to the fault category;

[0019] Step 109: When the fluctuation slope is less than the fluctuation threshold, a fault prompt information is generated and sent based on the fault category.

[0020] By adopting the technical scheme, when an abnormal parameter of the execution equipment occurs, the historical data of the abnormal parameter of the execution equipment is retrieved, so that the damage speed of the execution equipment is viewed, and when the damage speed is slow, the cause of the parameter abnormality is determined to be normal mechanical wear.

[0021] Optionally, the method further comprises:

[0022] Step 110: When the fluctuation slope is less than the fluctuation threshold, a same-category number is retrieved according to the fault category;

[0023] Step 111: A same-category parameter is retrieved based on the same-category number;

[0024] Step 112: A same-category fluctuation point is determined in combination with the same-category parameter and the peak threshold;

[0025] Step 113: A same-category slope is calculated based on the same-category fluctuation point;

[0026] Step 114: If the same-category slope is consistent with the fluctuation slope, a fault duration is determined in response to the same-category fluctuation point and the peak point;

[0027] Step 115: A fault risk information is generated and sent in combination with the same-category number and the fault duration.

[0028] By adopting the technical scheme, the service life of the same equipment in the same environment is similar, when the executing equipment fails due to mechanical wear, the similar parameters of the similar equipment with the same mechanical structure are checked, and when the change of the similar parameters is similar to that of the executing equipment, the time to failure of the similar equipment is estimated, so as to early warn the staff.

[0029] Optionally, the method further comprises a fault positioning method, wherein the fault positioning method comprises:

[0030] Step 200: reading a fluctuation interval based on the peak point when the fluctuation slope is less than a fluctuation threshold value;

[0031] Step 201: calculating an interval mean value based on the fluctuation interval;

[0032] Step 202: calculating an interval difference value in combination with the fluctuation interval and the interval mean value, and determining a period threshold value based on the peak point;

[0033] Step 203: if the interval difference value is not greater than the period threshold value, querying a closest mechanical period in response to the interval mean value;

[0034] Step 204: matching a fault position based on the mechanical period;

[0035] Step 205: updating the fault prompt information based on the fault position and a fault parameter.

[0036] By adopting the technical scheme, when the damage speed of the executing equipment is slow, it is checked whether the abnormal parameter has periodic fluctuation, and when the parameter has periodic fluctuation, it is judged that the reason for the parameter abnormality is related to the mechanical activity of the executing equipment, so that when the fault information is fed back, the related mechanical position is informed to the staff, and the accuracy of fault identification is improved.

[0037] Optionally, the fault positioning method further comprises:

[0038] Step 206: if the interval difference value is greater than the period threshold value, determining an approximate interval and a deviation interval in combination with the fluctuation interval and the interval mean value;

[0039] Step 207: calculating an approximate mean value according to the approximate interval, and calculating a deviation mean value according to the deviation interval;

[0040] Step 208: calculating a quotient of the deviation mean value and the approximate mean value, and defining the quotient as a mean value multiplier;

[0041] Step 209: calculating a multiplier deviation according to the mean value multiplier;

[0042] Step 210: If the ratio deviation falls within a preset error interval, an approximate difference value is calculated in combination with the approximate mean value and the approximate interval;

[0043] Step 211: When the approximate difference value is not greater than a period threshold, a deviation difference value is calculated in combination with the deviation mean value and the deviation interval;

[0044] Step 212: If the deviation difference value is not greater than the period threshold, the closest mechanical period is queried in response to the approximate mean value.

[0045] By adopting the above technical solution, when the cause of the parameter anomaly is related to the mechanical activity of the execution device, the fluctuation of the parameter is easily affected by the degree of the mechanical activity, so that when the degree of the mechanical activity is low, the fluctuation of the parameter is small or even does not occur. When the time intervals of the parameter fluctuation are inconsistent, it is compared whether there is a ratio relationship between the time intervals, so that when the ratio relationship exists, it is judged that the parameter has periodic fluctuation.

[0046] Optionally, the fault positioning method further comprises:

[0047] Step 213: When the fluctuation slope is not less than a fluctuation threshold, a mechanical range is determined based on the fault category;

[0048] Step 214: An investigation route is planned according to the mechanical range;

[0049] Step 215: Investigation images are collected according to the investigation route, and a fault feature is matched based on the fault category;

[0050] Step 216: If the fault feature exists in the investigation images, a fault demonstration animation is generated in combination with the fault feature and the fault category;

[0051] Step 217: The fault prompt information is updated in response to the fault demonstration animation.

[0052] By adopting the above technical solution, when the speed of the damaged execution device is too fast, it is judged that the mechanical structure of the execution device has a sudden fault such as jamming and fracture. At this time, the image of the related mechanical structure is collected, so that the condition of the mechanical structure is recognized through visual technology, and the staff is shown through the demonstration animation, thereby improving the accuracy of fault identification.

[0053] Optionally, it further comprises a data separation method, and the data separation method comprises:

[0054] Step 300: When there is a fault, an interval length is determined based on the fault parameter;

[0055] Step 301: The number of intervals is determined in response to the interval length and the peak fluctuation curve;

[0056] Step 302: determining high-frequency intervals according to the number of intervals;

[0057] Step 303: determining high-frequency parameters and basic parameters in combination with the high-frequency intervals and the peak fluctuation curve;

[0058] Step 304: updating the fluctuation slope based on the basic parameters and updating the fluctuation interval based on the high-frequency parameters.

[0059] By adopting the technical solution, when the parameter abnormality is caused by multiple reasons, the parameter fluctuation condition is relatively complex, at this time, the parameter needs to be split to facilitate the analysis of the fault reason, since the abnormal parameters affected by mechanical activities are affected by the degree of mechanical activities, the fluctuation condition of the parameters is similar, therefore, the parameters with similar fluctuation degrees and high-frequency parameters are regarded as high-frequency parameters affected by mechanical activities, and the remaining parameters are regarded as basic parameters affected by mechanical wear, thereby improving the accuracy of fault identification.

[0060] Optionally, the data separation method further comprises:

[0061] Step 305: if the interval difference is greater than the cycle threshold, calculating adjacent intervals according to the fluctuation interval;

[0062] Step 306: calculating adjacent multiples according to the adjacent intervals and the fluctuation interval, and calculating adjacent deviations in response to the adjacent multiples;

[0063] Step 307: when the adjacent deviation falls within a preset error interval, determining an error parameter based on the adjacent interval;

[0064] Step 308: defining the error parameter as the basic parameter.

[0065] By adopting the technical solution, the time intervals of adjacent high-frequency parameters are added, and the added time intervals are compared with the time intervals of other high-frequency parameters, so that when the added time intervals and the time intervals of any high-frequency parameter all have a multiple relationship, i.e., the added time intervals meet the cycle relationship, the high-frequency parameter is determined as a basic parameter, thereby improving the accuracy of fault identification.

[0066] Optionally, the data separation method further comprises:

[0067] Step 309: generating a fluctuation fitting curve based on the basic parameters;

[0068] Step 310: determining large parameters and small parameters in combination with the basic parameters and the fluctuation fitting curve;

[0069] Step 311: determining a correction parameter according to the large parameters and the high-frequency intervals;

[0070] Step 312: determining a correction slope in response to the under-estimation parameter and the correction parameter, and determining an under-estimation slope in response to the under-estimation parameter;

[0071] Step 313: calculating a difference between the under-estimation slope and the correction slope, and defining as a slope difference;

[0072] Step 314: if the slope difference is less than a preset composite threshold, defining the over-estimation parameter as a composite parameter;

[0073] Step 315: updating the high-frequency parameter and the base parameter according to the composite parameter.

[0074] By adopting the technical solution, when the fluctuation degree of the base parameter is too large, the fluctuation of the base parameter is subtracted from the high-frequency parameter, and the fluctuation change is determined based on the subtracted base parameter, so that when the fluctuation change is consistent with the fluctuation affected by wear, it is determined that the base parameter is affected by wear and mechanical activity, thereby improving the accuracy of fault identification.

[0075] In a second aspect, the present application provides an intelligent factory management system, which adopts the following technical solution:

[0076] An intelligent factory management system, comprising:

[0077] A collection module for collecting execution parameters and troubleshooting images;

[0078] A memory for storing the program of any of the intelligent factory management methods;

[0079] A processor, the program in the memory can be loaded and executed by the processor.

[0080] By adopting the above technical solution, the current and other parameters of the execution device are monitored in real time on the control cabinet, so that when a certain parameter of the execution device is abnormal, the fault reason of the execution device is analyzed in combination with the real-time parameters such as current, and then the analyzed fault reason is fed back to the DCS, thereby improving the accuracy of fault reason analysis and improving the management efficiency of the factory on the execution device.

[0081] In summary, the present application includes at least one of the following beneficial technical effects:

[0082] 1. The current and other parameters of the execution device are monitored in real time on the control cabinet, so that when a certain parameter of the execution device is abnormal, the fault reason of the execution device is analyzed in combination with the real-time parameters such as current, and then the analyzed fault reason is fed back to the DCS, thereby improving the accuracy of fault reason analysis and improving the management efficiency of the factory on the execution device;

[0083] 2. When the parameter of the execution equipment is abnormal, the historical data of the abnormal parameter of the execution equipment is called to view the damage speed of the execution equipment, and when the damage speed is slow, the cause of the parameter abnormality is normal mechanical wear;

[0084] 3. When the damage speed of the execution equipment is slow, whether the parameter that is abnormal has periodic fluctuation is viewed, and when the parameter has periodic fluctuation, the cause of the parameter abnormality is related to the mechanical activity of the execution equipment, so that the related mechanical part is informed to the worker when the fault information is fed back, and the accuracy of fault identification is improved. BRIEF DESCRIPTION OF DRAWINGS

[0085] Figure 1 It is a flow chart of an intelligent factory management method;

[0086] Figure 2 It is a flow chart of a fault positioning method;

[0087] Figure 3 It is a flow chart of a data separation method. DETAILED DESCRIPTION

[0088] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0089] Referring to Figure 1 An intelligent factory management method comprises:

[0090] Step 100: collecting execution parameters of an execution equipment.

[0091] The execution parameters refer to various parameters when the execution equipment is running. For example, when the execution equipment is a motor, the execution parameters include voltage parameters, current parameters, rotation speed parameters, rotation direction parameters and stall parameters and the like. The execution parameters can be collected by corresponding sensors integrated on the control cabinet. The collection method of the execution parameters is selected by the worker according to the actual situation, which is not described herein.

[0092] Step 101: judging whether there is a fault in response to the execution parameters and a preset fault interval.

[0093] The fault interval refers to the execution parameter range when the execution equipment is normally running. Each type of execution parameter has a corresponding fault interval. When the execution parameter does not fall into the corresponding fault interval, it is judged that the execution equipment has a fault. The fault interval can be preset by the worker, which is not described herein.

[0094] Step 102: when there is a fault, determining a fault parameter in combination with the execution parameters and the preset fault interval.

[0095] The fault represents a jump in the data of the execution parameter, at which time the execution parameter needs to be further analyzed to determine the cause of the jump in the data, the fault parameter is the execution parameter that does not fall into the corresponding fault interval, and the determination method of the fault parameter is the common knowledge of the person skilled in the art, which is not described here.

[0096] Step 103: determining a fault category according to the fault parameter.

[0097] The fault category refers to the cause of the failure of the execution device, which can be determined by the inspection rules set by the staff in advance. For example, when the execution device is a motor, if the current parameter continuously exceeds 1.2 times of the upper limit of the fault interval (for example, the upper limit of the fault interval is 10A, and more than 12A is monitored), it may be mechanical jamming (such as pump impeller being jammed by foreign matter), excessive load (such as conveyor belt overload) or motor winding short circuit. The judgment method of the fault category is the common knowledge of the person skilled in the art, which is not described here.

[0098] Step 104: generating and sending a fault prompt information based on the fault category.

[0099] The fault prompt information refers to the data packet including the related information of the fault of the execution device such as the fault category sent to the DCS, and the generation method of the fault prompt information is the common knowledge of the person skilled in the art, which is not described here.

[0100] The current and other parameters of the execution device are monitored on the control cabinet in real time, so that when an abnormal parameter of the execution device occurs, the cause of the failure of the execution device is analyzed in combination with the real-time parameters such as current, and then the analyzed failure cause is fed back to the DCS, thereby improving the accuracy of the analysis of the failure cause and improving the management efficiency of the factory to the execution device.

[0101] An intelligent factory management method further comprises:

[0102] Step 105: when there is a fault, retrieving historical parameters based on the fault parameter, and determining a peak threshold based on the fault parameter.

[0103] The historical parameter refers to the historical data of the fault parameter, which is recorded in the pre-set database after the control cabinet detects the execution parameter in real time. The corresponding historical parameter can be retrieved from the database according to the fault parameter, and the retrieval method of the historical parameter is the common knowledge of the person skilled in the art, which is not described here.

[0104] The peak threshold refers to the highest value of the fault parameter when the executing device is in normal operation and is affected by environmental factors and the like. The greater the value of the fault parameter in normal operation, the more likely it is to fluctuate, and the greater the peak threshold. The peak threshold corresponding to the fault parameter can be queried from a peak relationship table, and the peak relationship table refers to a table recording different fault parameters and their corresponding peak thresholds.

[0105] Step 106: determining a peak point in response to the historical parameter and the peak threshold.

[0106] The peak point is a data point in the historical parameter that exceeds the peak threshold. The determination method of the peak point is known to those skilled in the art and will not be described here.

[0107] Step 107: generating a peak fluctuation curve based on the peak point.

[0108] The peak fluctuation curve refers to a curve for showing the fluctuation of the historical parameter. The difference between the data of the peak point and the peak threshold can be calculated as a fluctuation difference, and the fluctuation difference can be arranged in chronological order and fitted to form a peak fluctuation curve. The generation method of the peak fluctuation curve is known to those skilled in the art and will not be described here.

[0109] Step 108: reading a fluctuation slope from the peak fluctuation curve and determining a fluctuation threshold according to the fault type.

[0110] The fluctuation slope refers to the slope of the peak fluctuation curve, i.e., data for showing the change of the fluctuation of the historical parameter. The greater the fluctuation slope, the faster the change of the fluctuation. The reading method of the fluctuation slope is known to those skilled in the art and will not be described here.

[0111] The fluctuation threshold refers to the maximum value of the fluctuation slope of the historical parameter when the fault of the fault type occurs, i.e., the maximum value of the fluctuation change speed of the historical parameter. The fluctuation threshold corresponding to the fault type can be queried from a threshold relationship table, and the threshold relationship table refers to a table recording different fault types and their corresponding fluctuation thresholds.

[0112] Step 109: generating and sending a fault prompt message based on the fault type when the fluctuation slope is less than the fluctuation threshold.

[0113] The fluctuation slope being less than the fluctuation threshold means that the fluctuation change speed of the historical parameter before the fault occurs conforms to the fault type, i.e., there is a gradual deterioration process before the fault occurs. At this time, the cause of the parameter anomaly is determined to be wear caused by normal use.

[0114] An intelligent factory management method further comprises:

[0115] Step 110: retrieving a same type number according to the fault type when the fluctuation slope is less than the fluctuation threshold.

[0116] The same kind of number refers to the number of other devices with the same mechanical structure as the fault part of the execution device, each number corresponds to a device, and the mechanical structure where the fault is located can be determined according to the fault type, and then the same kind of number corresponding to the mechanical structure can be queried from the structure relationship table. The structure relationship table refers to a data table recording different same kind of numbers and the mechanical structures corresponding thereto.

[0117] Step 111: retrieving same kind of parameters based on the same kind of number.

[0118] The same kind of parameter is the execution parameter of the device with the same kind of number, and the same kind of parameter retrieval method is well known to those skilled in the art, which will not be repeated here.

[0119] Step 112: determining same kind of fluctuation points in combination with the same kind of parameters and peak threshold.

[0120] The same kind of fluctuation point is a numerical point in the same kind of parameter whose value is higher than the peak threshold, and the determination method of the same kind of fluctuation point is well known to those skilled in the art, which will not be repeated here.

[0121] Step 113: calculating same kind of slope based on the same kind of fluctuation point.

[0122] The same kind of slope is the slope of the curve formed according to the same kind of fluctuation point, and the determination method of the same kind of slope refers to steps 107 and 108 described above, which will not be repeated here.

[0123] Step 114: determining fault duration in response to the same kind of fluctuation point and peak point if the same kind of slope is consistent with the fluctuation slope.

[0124] The same kind of slope consistent with the fluctuation slope represents that the wear change of the same kind of device is consistent with the execution device, and the fault duration refers to the duration of the same kind of device from the fault predicted according to the wear process of the execution device. The highest point in the same kind of fluctuation point can be retrieved, and the duration required for the same kind of fluctuation point not to fall into the corresponding fault interval is calculated in combination with the fluctuation slope as the fault duration.

[0125] Step 115: generating and sending fault risk information in combination with the same kind of number and fault duration.

[0126] The fault risk information refers to a data packet including the same kind of number and fault duration and other related information of the same kind of device prone to failure, which is sent to the DCS. The generation method of the fault risk information is well known to those skilled in the art, which will not be repeated here.

[0127] The service life of the same device under the same environment is similar, when the execution device fails due to mechanical wear, the same kind of parameters of the same kind of device with the same mechanical structure are checked, and when the change of the same kind of parameters is similar to the execution device, the duration of the same kind of device from the fault is estimated, so as to early warn the workers.

[0128] Referring to Figure 2 The fault positioning method comprises the following steps:

[0129] Step 200: When the fluctuation slope is less than the fluctuation threshold, reading a fluctuation interval based on the peak point.

[0130] The fluctuation interval refers to the time interval between adjacent peak points, and the reading method of the fluctuation interval is known to those skilled in the art and will not be described here.

[0131] Step 201: Calculating an interval mean value based on the fluctuation interval.

[0132] The interval mean value refers to the average value of the fluctuation interval, and the overall situation of the fluctuation interval is shown by the interval mean value. The calculation method of the interval mean value is known to those skilled in the art and will not be described here.

[0133] Step 202: Calculating an interval difference value in combination with the fluctuation interval and the interval mean value, and determining a period threshold based on the peak point.

[0134] The interval difference value refers to the absolute value of the difference between the fluctuation interval and the interval mean value. The deviation of each fluctuation interval is shown by the interval difference value. The calculation method of the interval difference value is known to those skilled in the art and will not be described here.

[0135] The period threshold refers to the maximum interval difference value when the fluctuation intervals are similar. The more the number of peak points is, the smaller the period threshold is. The number of peaks can be counted first, and then the period threshold corresponding to the number of peaks can be queried from a period relationship table. The period relationship table refers to a data table recording different numbers of peaks and their corresponding period thresholds.

[0136] Step 203: If the interval difference value is not greater than the period threshold, querying the closest mechanical period in response to the interval mean value.

[0137] The interval difference value not being greater than the period threshold represents that the fluctuation intervals are similar, i.e., the peak points appear periodically. The mechanical period refers to the activity period of a mechanical structure on an execution device, such as the rotation period of a motor or the switching period of a valve. The mechanical period corresponding to the interval mean value can be queried from a mechanical relationship table. The mechanical relationship table refers to a data table recording different mechanical structures and their corresponding mechanical periods.

[0138] Step 204: Matching a fault site based on the mechanical period.

[0139] The fault site is the mechanical structure site corresponding to the mechanical period, which can be queried from the mechanical relationship table as the fault site.

[0140] Step 205: updating the fault prompt information based on the fault location and fault parameter.

[0141] When the damage speed of the execution device is slow, it is checked whether the parameter that occurs an anomaly has a periodic fluctuation, and it is judged that the cause of the parameter anomaly is related to the mechanical activity of the execution device when the parameter has a periodic fluctuation, so that the related mechanical part is notified to the worker when the fault information is fed back, and the accuracy of fault identification is improved.

[0142] The fault positioning method further comprises:

[0143] Step 206: If the interval difference is greater than the cycle threshold, the approximate interval and the deviation interval are determined in combination with the fluctuation interval and the interval mean.

[0144] The interval difference greater than the cycle threshold represents that the difference of the fluctuation interval is large, the approximate interval refers to the fluctuation interval less than the interval mean, and the deviation interval refers to the fluctuation interval not less than the interval mean. The determination method of the approximate interval and the deviation interval is the common knowledge of the person skilled in the art, and will not be repeated here.

[0145] Step 207: The approximate mean is calculated according to the approximate interval, and the deviation mean is calculated according to the deviation interval.

[0146] The approximate mean refers to the average value of the approximate interval, and the deviation mean refers to the average value of the deviation interval. The calculation method of the approximate mean and the deviation mean is the common knowledge of the person skilled in the art, and will not be repeated here.

[0147] Step 208: The quotient of the deviation mean and the approximate mean is calculated and defined as the mean ratio.

[0148] The mean ratio refers to a value for showing the difference between the deviation mean and the approximate mean. The calculation method of the mean ratio is the common knowledge of the person skilled in the art, and will not be repeated here.

[0149] Step 209: The ratio deviation is calculated according to the mean ratio.

[0150] The ratio deviation refers to the difference between the mean ratio and the nearest integer. For example, when the mean ratio is 1.9, the ratio deviation is 0.1, and when the mean ratio is 2.4, the ratio deviation is 0.4. The calculation method of the ratio deviation is the common knowledge of the person skilled in the art, and will not be repeated here.

[0151] Step 210: If the ratio deviation falls within a preset error interval, the approximate difference is calculated in combination with the approximate mean and the approximate interval.

[0152] The error interval refers to the maximum ratio deviation when the data has an allowable error. The error interval can be set by the worker in advance, and will not be repeated here.

[0153] The ratio deviation falling into the error interval represents that the deviation mean and the approximate mean are in a ratio relationship, the approximate difference is an absolute value of a difference between the approximate interval and the approximate mean, and the approximate difference shows the deviation condition of each approximate interval. The calculation method of the approximate difference is well known to those skilled in the art, and thus is not described herein.

[0154] Step 211: When the approximate difference is not greater than the period threshold, a deviation difference is calculated in combination with the deviation mean and the deviation interval.

[0155] The approximate difference not being greater than the period threshold represents that the approximate intervals are close, that is, the peak points corresponding to the approximate intervals periodically occur. The deviation difference is an absolute value of a difference between the deviation interval and the deviation mean, and the deviation difference shows the deviation condition of each deviation interval. The calculation method of the deviation difference is well known to those skilled in the art, and thus is not described herein.

[0156] Step 212: If the deviation difference is not greater than the period threshold, a closest mechanical period is queried in response to the approximate mean.

[0157] The deviation difference not being greater than the period threshold represents that the deviation intervals are close, that is, the peak points corresponding to the deviation intervals periodically occur. When the cause of the parameter anomaly is related to the mechanical activity of the execution device, the fluctuation condition of the parameter is easily affected by the degree of the mechanical activity, so that the fluctuation condition of the parameter is smaller or even does not occur when the degree of the mechanical activity is low. When the fluctuation time intervals of the parameter are inconsistent, whether there is a ratio relationship between the time intervals is compared, so that it is determined that the parameter has periodic fluctuation when the ratio relationship exists.

[0158] The fault positioning method further includes:

[0159] Step 213: When the fluctuation slope is not less than the fluctuation threshold, a mechanical range is determined based on the fault category.

[0160] The fluctuation slope not being less than the fluctuation threshold represents that the fluctuation change speed of the historical parameter before the fault occurs is too fast, that is, the execution parameter mutates, and the execution device has a sudden fault. The mechanical range refers to an external range of a mechanical structure corresponding to the fault category, and the mechanical range corresponding to the fault category can be queried from an external relationship table. The external relationship table refers to a data table recording different fault categories and the mechanical ranges corresponding thereto.

[0161] Step 214: An investigation route is planned according to the mechanical range.

[0162] The investigation route is a route for investigating the mechanical range by the intelligent device. Generally, a camera preset on a two-dimensional linear guide rail on the unmanned aerial vehicle or the top of the factory is selected as the intelligent device. The determination method of the investigation route and the intelligent device are selected by the staff according to the actual situation, and thus are not described herein.

[0163] Step 215: Collecting troubleshooting images according to the troubleshooting route, and matching out fault features based on the fault category.

[0164] The troubleshooting image is an image of the mechanical structure of the executing device collected by the intelligent device according to the troubleshooting route. The collection method of the troubleshooting image is selected by the staff according to the actual situation, and is not described here.

[0165] The fault feature refers to the object that easily causes the fault category to cause a sudden fault. For example, when the fault category is motor jamming, the fault feature is cloth and other objects that easily cause motor jamming. The fault feature is related to the environment of the executing device. The fault feature can be selected by the staff according to the actual situation, and the fault feature corresponding to the fault category can be queried from the feature data table. The feature data table refers to a data table recording different fault categories and their corresponding fault features.

[0166] Step 216: If the troubleshooting image contains the fault feature, generate a fault demonstration animation combining the fault feature and the fault category.

[0167] The presence of the fault feature in the troubleshooting image means that the object causing the fault can be found from the appearance of the executing device. The fault demonstration animation is a scene simulation image that shows the fault feature causing the fault category. Different fault features causing the fault category corresponding to the fault demonstration animation can be generated in advance and stored in the animation database, and the fault demonstration animation corresponding to the fault feature can be retrieved from the animation database after the fault feature is identified.

[0168] Step 217: Update the fault prompt information in response to the fault demonstration animation.

[0169] When the executing device is damaged too quickly, it is determined that the mechanical structure of the executing device has a sudden fault such as jamming and breaking. At this time, the image of the related mechanical structure is collected, so that the condition of the mechanical structure is identified through visual technology, and the staff is shown through the demonstration animation, thereby improving the accuracy of fault identification.

[0170] Referring to Figure 3 , the data separation method comprises:

[0171] Step 300: When there is a fault, determine the interval length based on the fault parameter.

[0172] The interval length refers to the range used to determine the distribution of the peak point. The greater the value of the fault parameter changes, the greater the interval length needs to be. The interval length corresponding to the fault parameter can be queried from the interval relationship table. The interval relationship table refers to a data table recording different fault parameter categories and their corresponding interval lengths.

[0173] Step 301: determining the interval number in response to the interval length and the peak fluctuation curve.

[0174] The interval number is the number of data points in the peak fluctuation curve that differ from the peak value by less than the interval length. The determination method of the interval number is known to those skilled in the art and will not be described here.

[0175] Step 302: determining the high-frequency interval according to the interval number.

[0176] The high-frequency interval refers to the data value interval corresponding to the maximum interval number, i.e. the range from (peak point-interval length) to (peak point+interval length), wherein the peak point corresponds to the interval number. The determination method of the high-frequency interval is known to those skilled in the art and will not be described here.

[0177] Step 303: determining the high-frequency parameter and the basic parameter in combination with the high-frequency interval and the peak fluctuation curve.

[0178] The high-frequency parameter is the peak point in the peak fluctuation curve that falls within the high-frequency interval, and the basic parameter is the peak point in the peak fluctuation curve that does not fall within the high-frequency interval. The determination method of the high-frequency parameter and the basic parameter is known to those skilled in the art and will not be described here.

[0179] Step 304: updating the fluctuation slope based on the basic parameter and updating the fluctuation interval based on the high-frequency parameter.

[0180] When the abnormality of a parameter is caused by multiple reasons, it is easy to cause the fluctuation of the parameter to be complex. At this time, the parameter needs to be split to facilitate the analysis of the fault reason. Since the abnormal parameters affected by mechanical activities are affected by the degree of mechanical activities, the fluctuation of the parameters is similar. Therefore, the parameters with similar fluctuation degrees and high-frequency parameters are considered to be affected by mechanical activities, and the remaining parameters are considered to be affected by mechanical wear. This improves the accuracy of fault identification.

[0181] The data separation method further comprises:

[0182] Step 305: if the interval difference is greater than the cycle threshold, calculating the adjacent interval according to the fluctuation interval.

[0183] The adjacent interval refers to the sum of the current fluctuation interval and the adjacent fluctuation interval in front. The calculation method of the adjacent interval is known to those skilled in the art and will not be described here.

[0184] Step 306: calculating the adjacent ratio according to the adjacent interval and the fluctuation interval, and calculating the adjacent deviation in response to the adjacent ratio.

[0185] The adjacent ratio is used to show the difference between the adjacent interval and the fluctuation interval, and the calculation method of the adjacent ratio is well known to those skilled in the art, and will not be repeated here.

[0186] The adjacent deviation refers to the difference between the adjacent ratio and the nearest integer, and the calculation method of the adjacent deviation is referred to step 209, and will not be repeated here.

[0187] Step 307: When the adjacent deviation falls within the preset error interval, determine the error parameter based on the adjacent interval.

[0188] The adjacent deviation falling within the error interval means that both the adjacent interval and the fluctuation interval are in a multiple relationship, and the error parameter is the peak point between the two fluctuation intervals corresponding to the adjacent interval. The determination method of the error parameter is well known to those skilled in the art, and will not be repeated here.

[0189] Step 308: Define the error parameter as the basic parameter.

[0190] The time intervals of the adjacent high-frequency parameters are added, and the added time interval is compared with the time intervals of other high-frequency parameters, so that when the added time interval and the time interval of any high-frequency parameter have a multiple relationship, i.e. the added time interval meets the periodic relationship, the high-frequency parameter is determined as the basic parameter, thereby improving the accuracy of fault identification.

[0191] The data separation method further comprises:

[0192] Step 309: Generate a fluctuation fitting curve based on the basic parameter.

[0193] The fluctuation fitting curve is a curve fitted according to the basic parameter, and the generation method of the fluctuation fitting curve is well known to those skilled in the art, and will not be repeated here.

[0194] Step 310: Determine the large parameter and the small parameter in combination with the basic parameter and the fluctuation fitting curve.

[0195] The large parameter refers to the basic parameter located above the fluctuation fitting curve, i.e. greater than the fluctuation fitting curve, and the small parameter refers to the basic parameter located below the fluctuation fitting curve, i.e. not greater than the fluctuation fitting curve. The determination method of the large parameter and the small parameter is well known to those skilled in the art, and will not be repeated here.

[0196] Step 311: Determine the correction parameter according to the large parameter and the high-frequency interval.

[0197] The correction parameter is a value obtained by subtracting the center of the high-frequency interval from the large parameter, and the center of the high-frequency interval represents a value point with the highest frequency, i.e., a value of the execution parameter affected by mechanical activity. The correction parameter represents the value of the execution parameter not affected by mechanical activity. The calculation method of the correction parameter is well known to those skilled in the art, and thus is not described herein.

[0198] Step 312: determining a correction slope in response to the small parameter and the correction parameter, and determining a small slope in response to the small parameter.

[0199] The correction slope is a slope value of a curve fitted according to the small parameter and the correction parameter, and the small slope is a slope value of a curve fitted according to the small parameter. The determination methods of the correction slope and the small slope are well known to those skilled in the art, and thus are not described herein.

[0200] Step 313: calculating a difference between the small slope and the correction slope, and defining the difference as a slope difference.

[0201] The slope difference is a value used to represent the difference between the small slope and the correction slope. The calculation method of the slope difference is well known to those skilled in the art, and thus is not described herein.

[0202] Step 314: if the slope difference is less than a preset composite threshold, defining the large parameter as a composite parameter.

[0203] The composite threshold is a value of the influence of the maximum fluctuation of the execution parameter on the slope when the execution device is simultaneously affected by mechanical activity and mechanical wear. The composite threshold can be preset by a worker, and thus is not described herein. The slope difference less than the composite threshold represents that the correction parameter is consistent with the change of the small parameter, i.e., the change of the large parameter excluding the influence of mechanical activity is consistent with the change of mechanical wear. The composite parameter is the large parameter corresponding to the correction parameter. The determination method of the composite parameter is well known to those skilled in the art, and thus is not described herein.

[0204] Step 315: updating the high-frequency parameter and the base parameter according to the composite parameter.

[0205] When the fluctuation degree of the base parameter is too large, the base parameter is subtracted by the fluctuation of the high-frequency parameter, and the fluctuation of the subtracted base parameter is determined, so that when the fluctuation is consistent with the fluctuation affected by wear, it is determined that the base parameter is simultaneously affected by mechanical wear and mechanical activity, and one base parameter is divided into a base parameter affected only by mechanical wear and a high-frequency parameter affected only by mechanical activity, thereby improving the accuracy of fault identification.

[0206] Based on the same inventive concept, the embodiments of the present application provide an intelligent factory management system, comprising:

[0207] The acquisition module is configured to acquire the execution parameter and the troubleshooting image.

[0208] The memory is configured to store the program of any of the intelligent factory management methods.

[0209] The processor, the program in the memory can be loaded and executed by the processor.

[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0211] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments only. Any technical solution falling within the concept of the present application shall be deemed to fall within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application shall also be deemed to fall within the protection scope of the present application.

Claims

1. An intelligent factory management method characterized by, Comprising: Step 100: Collecting execution parameters of an execution device; Step 101: Determining whether there is a fault in response to the execution parameters and a preset fault interval; Step 102: When there is a fault, determining a fault parameter in combination with the execution parameters and the preset fault interval; Step 103: Determining a fault category according to the fault parameter; Step 104: Generating and sending fault prompt information based on the fault category; Further comprising: Step 105: When there is a fault, calling historical parameters based on the fault parameter, and determining a peak threshold value based on the fault parameter; Step 106: Determining a peak point in response to the historical parameters and the peak threshold value; Step 107: Generating a peak fluctuation curve based on the peak point; Step 108: Reading a fluctuation slope from the peak fluctuation curve, and determining a fluctuation threshold value according to the fault category; Step 109: When the fluctuation slope is less than the fluctuation threshold value, generating and sending fault prompt information based on the fault category; Further comprising: Step 110: When the fluctuation slope is less than the fluctuation threshold value, calling a same-category number according to the fault category; Step 111: Calling a same-category parameter based on the same-category number; Step 112: Determining a same-category fluctuation point in combination with the same-category parameter and the peak threshold value; Step 113: Calculating a same-category slope based on the same-category fluctuation point; Step 114: If the same-category slope is consistent with the fluctuation slope, determining a fault duration in response to the same-category fluctuation point and the peak point; Step 115: Generating and sending fault risk information in combination with the same-category number and the fault duration.

2. The intelligent factory management method of claim 1, wherein, Further comprising a fault positioning method, the fault positioning method comprising: Step 200: When the fluctuation slope is less than the fluctuation threshold value, reading a fluctuation interval based on the peak point; Step 201: Calculating an interval mean value based on the fluctuation interval; Step 202: Calculating an interval difference value in combination with the fluctuation interval and the interval mean value, and determining a period threshold value based on the peak point; Step 203: If the interval difference value is not greater than the period threshold value, querying a closest mechanical period in response to the interval mean value; Step 204: Matching a fault site based on the mechanical period; Step 205: Updating the fault prompt information based on the fault site and the fault parameter.

3. The intelligent factory management method of claim 2, wherein, The fault positioning method further comprises: Step 206: If the interval difference value is greater than the period threshold value, determining an approximate interval and a deviation interval in combination with the fluctuation interval and the interval mean value; Step 207: Calculating an approximate mean value according to the approximate interval, and calculating a deviation mean value according to the deviation interval; Step 208: Calculating a quotient of the deviation mean value and the approximate mean value, and defining it as a mean value multiplier; Step 209: Calculating a multiplier deviation according to the mean value multiplier; Step 210: If the multiplier deviation falls within a preset error interval, calculating an approximate difference value in combination with the approximate mean value and the approximate interval; Step 211: When the approximate difference value is not greater than the period threshold value, calculating a deviation difference value in combination with the deviation mean value and the deviation interval; Step 212: If the deviation difference value is not greater than the period threshold value, querying a closest mechanical period in response to the approximate mean value.

4. The intelligent factory management method of claim 3, wherein, The fault positioning method further comprises: Step 213: determining a mechanical range based on the fault category when the fluctuation slope is not less than the fluctuation threshold value; Step 214: planning an investigation route according to the mechanical range; Step 215: collecting investigation images according to the investigation route and matching fault features based on the fault category; Step 216: generating a fault demonstration animation in combination with the fault features and the fault category if the fault features exist in the investigation images; Step 217: updating the fault prompt information in response to the fault demonstration animation.

5. The intelligent factory management method of claim 4, wherein, The data separation method comprises: Step 300: determining an interval length based on the fault parameter when there is a fault; Step 301: determining an interval number in response to the interval length and the peak fluctuation curve; Step 302: determining a high-frequency interval according to the interval number; Step 303: determining a high-frequency parameter and a basic parameter in combination with the high-frequency interval and the peak fluctuation curve; Step 304: updating the fluctuation slope based on the basic parameter and updating the fluctuation interval based on the high-frequency parameter.

6. The intelligent factory management method of claim 5, wherein, The data separation method further comprises: Step 305: calculating adjacent intervals according to the fluctuation interval if the interval difference is greater than a period threshold value; Step 306: calculating an adjacent ratio according to the adjacent intervals and the fluctuation interval and calculating an adjacent deviation in response to the adjacent ratio; Step 307: determining an error parameter based on the adjacent interval when the adjacent deviation falls within a preset error interval; Step 308: defining the error parameter as the basic parameter.

7. The intelligent factory management method of claim 6, wherein, The data separation method further comprises: Step 309: generating a fluctuation fitting curve based on the basic parameter; Step 310: determining a larger parameter and a smaller parameter in combination with the basic parameter and the fluctuation fitting curve; Step 311: determining a correction parameter according to the larger parameter and the high-frequency interval; Step 312: determining a correction slope in response to the smaller parameter and the correction parameter and determining a smaller slope in response to the smaller parameter; Step 313: calculating a difference between the smaller slope and the correction slope and defining it as a slope difference; Step 314: defining the larger parameter as a composite parameter if the slope difference is less than a preset composite threshold value; Step 315: updating the high-frequency parameter and the basic parameter according to the composite parameter.

8. An intelligent factory management system, characterized by, The system comprises: a collection module for collecting execution parameters and investigation images; a memory for storing a program of an intelligent factory management method according to any one of claims 1 to 7; a processor, and the program in the memory can be loaded and executed by the processor.

Images