An intelligent equipment management system and method based on data analysis

Abstract

The present invention discloses an intelligent equipment management system and method based on data analysis, which belongs to the field of remote control warning technology. The present invention collects the number and position of equipment that needs to be managed in the visual environment of a visual sensor, establishes a coordinate system to locate and mark each equipment; searches for target detection data, calculates the target detection data threshold; constructs a normal working data set of the equipment, searches for the implicated data types between the equipment to construct the implicated data set, and calculates the implicated data threshold; uses the target detection data threshold to determine whether the equipment needs to be adjusted and sends an abnormal warning signal to the remote control; determines the type of data that needs to be adjusted and the adjusted data value, and sends the calculated data type and adjusted data value to the remote control; uses the implicated data set to determine whether the data that needs to be adjusted is implicated data, calculates whether the data value that needs to be adjusted will affect the normal working equipment according to the implicated data threshold, and sends a danger warning to the remote control.

Description

Technical Field

[0001] The present invention relates to the technical field of remote control early warning, and in particular to an intelligent equipment management system and method based on data analysis. Background Art

[0002] With the development of modern science and technology, the control and management of equipment in various industries are becoming more and more intelligent. Among them, the Internet of Things technology is the basis for connecting and managing intelligent devices. Through various sensors, communication technologies and cloud computing platforms, the interconnection between devices is realized, providing data support and communication basis for equipment management and control. Sensor technology is the key for intelligent devices to obtain environmental information. Various types of sensors (such as temperature sensors, humidity sensors, motion sensors, etc.) can monitor the status and environmental parameters around the equipment in real time, providing data support for intelligent control. Cloud computing and big data technologies provide powerful data storage, processing and analysis capabilities for intelligent device management. Through the cloud platform, large-scale equipment data can be collected, stored, analyzed and visualized, providing support for equipment management and optimization. Various technologies play a vital role in the intelligent control of equipment; however, when controlling equipment, there are some working environments that are affected by data such as distance and current. When managing and controlling a device, the normal operation of other devices is affected; it is easy to cause unnecessary losses and accidents; therefore, for the intelligent control of equipment, it is equally important to judge the impact of abnormal equipment adjustment on other devices while making early warning adjustments to abnormal equipment. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent equipment management system and method based on data analysis to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] An intelligent equipment management method based on data analysis, the method comprising the following steps:

[0006] S100, collecting the number and location of devices that need to be managed in the visual environment of the visual sensor, and establishing a coordinate system to locate and mark each device;

[0007] Furthermore, the specific steps of establishing a coordinate system to locate and mark each device are as follows:

[0008] S101, using a visual sensor to collect the positions and number of all devices in the working environment, assuming the number of devices is c, establishing a plane rectangular coordinate system with the visual sensor as the origin, with the north direction as the positive direction of the y-axis and the east direction as the positive direction of the x-axis;

[0009] S102, collect the distances between each device and the visual sensor in the working environment {L1, L2, L3...L c}, L1, L2, L3...L c represents the distance between the 1st, 2nd, 3rd...cth device and the visual sensor in the working environment, where c is a positive integer; the angle of each device in the plane rectangular coordinate system is {J1, J2, J3...J c}, J1, J2, J3...J c It is expressed as the angle of the 1st, 2nd, 3rd...cth device in the working environment in the plane rectangular coordinate system, and the angle of all devices is the angle between the line connecting the device and the visual sensor and the positive direction of the x-axis; when the device is in the positive direction of the y-axis, the angle is positive, and when the device is in the negative direction of the y-axis, the angle is negative;

[0010] S103, calculating the position coordinates of each device according to the collected distance between each device and the visual sensor and the angle of each device in the plane rectangular coordinate system, the formula is:

[0011] x=L×cosJ

[0012] y=L×sinJ

[0013] In the formula, x represents the horizontal coordinate of the device in the plane coordinate system, y represents the vertical coordinate of the device in the plane coordinate system, L represents the distance between each device and the visual sensor, and J represents the angle of each device in the plane coordinate system;

[0014] S104, calculate the position coordinates of the c devices, and obtain the coordinate set of the c devices as {(x1, y1), (x2, y2), (x3, y3)...(x c ,y c )}, (x1, y1), (x2, y2), (x3, y3)...(x c ,y c ) represents the position coordinates of the 1st, 2nd, 3rd...cth devices in the plane coordinate system in the working environment. After calculating the position coordinates of each device, each device is marked as Indicates the labeling of the 1st, 2nd, 3rd...cth devices, x represents the horizontal coordinate of each device, and y represents the vertical coordinate of each device.

[0015] After all devices in the working environment are located, each device can be accurately monitored and tracked, and the relative distance between devices can be calculated based on the specific location of each device to control the distance between devices.

[0016] S200, collecting device data when adjusting the device in history, searching for target detection data, and calculating a target detection data threshold;

[0017] Furthermore, the specific steps for calculating the target detection data threshold are:

[0018] S201, collect equipment data {S1, S2, S3...S n}, S1, S2, S3...S n It represents the 1st, 2nd, 3rd...type data collected when adjusting the abnormal equipment, where n is a positive integer; it represents the equipment data {S'1, S'2, S'3...S'1 in the history of equipment when it is not adjusted}. n}, S'1, S'2, S'3...S' n It represents the 1st, 2nd, 3rd...nth equipment data of the equipment in the collected history when no adjustment is performed; the equipment that is adjusted is an abnormal equipment, and the equipment that is not adjusted is a normal equipment;

[0019] S202, compare the collected device data when adjusted and when not adjusted, and extract the changed device data {S_b1, S_b2, S_b3...S_b1} from the device data of the abnormal device adjusted. m}, S_b1, S_b2, S_b3...S_b m Indicates the 1st, 2nd, 3rd, ... pieces of equipment data that have changed in the equipment data set for adjusting the abnormal equipment, where m is a positive integer; the change amount of the m pieces of equipment data that have changed is calculated using the formula:

[0020] S_b_c=|S_b-S_b′|

[0021] In the formula, S_b_c represents the amount of change in the changed device data, S_b represents the device data when the abnormal device is adjusted, and S_b' represents the device data when the device is not adjusted;

[0022] S203, calculate the m changed device data, and obtain the changed amount of the device data as {S_b_c1, S_b_c2, S_b_c3...S_b_c m}, S_b_c1, S_b_c2, S_b_c3...S_b_c m Indicates the 1st, 2nd, 3rd, ...mth changed device data changes; selects the device data type corresponding to the maximum value among the m changed device data changes as the target detection data S_J;

[0023] S204, calculating the target detection data threshold according to the target detection data collected during the work of adjusting the abnormal equipment, assuming that there are d target detection data collected during the work of adjusting the abnormal equipment, and calculating the average value and standard deviation of the collected target detection data, the formula is: In the formula, S_J_p represents the average value of the collected target detection data, S_J_z represents the standard deviation of the collected target detection data, and d represents the total number of the collected target detection data. The collected target detection data are graded using the calculated average value and standard deviation, and the graded standard data value of each level is calculated. The formula is:

[0024]

[0025] In the formula, S_f represents the standard data value of each level, T represents half of the number of target detection data to be classified, and the average value is used as the first level, S_f -T Indicates the Tth level less than the average value, S_f +T Indicates the Tth level greater than the average value, T is a positive integer and increases by 1 until S_f +end >maxS_J i And S_f -end <minS_J i , S_f -end and S_f +end Indicates the last grading standard data value calculated, maxS_J i Indicates the maximum value of the collected target detection data, minS_J i represents the minimum value of the collected target detection data, i ranges from 1 to d; the final calculated target detection data classification standard data value is {S_f -T 、S_f -(T-1) 、S_f -(T-2) ...S_f -1 , S_J_p, S_f +1 ...S_f +(T-2) 、S_f +(T-1) 、S_f +T},S_f -T 、S_f -(T-1) 、S_f -(T-2) ...S_f -1 represents the T, T-1, T-2...1st classification standard data value that is less than the average value, S_J_p represents the average value of the target detection data, S_f +1 ...S_f +(T-2) 、S_f +(T-1) 、S_f +TRepresent the 1st... T-2nd, T-1st, and Tth classification standard data values greater than the average value;

[0026] S205. According to the calculated 2T + 1 classification standard data values, divide the target detection data in the collected history. Two adjacent classification standard data values form a classification interval. Compare the target detection data in the collected history with each classification standard data value. The specific method is as follows:

[0027] When comparing S_J with {S_f -T , S_f -(T-1) , S_f -(T-2) ... S_f -1 , S_J_p}, if |S_J - S_f e | < S_J_z and S_J - S_f e > 0, it is determined that S_J is in the interval [S_f e , S_f e-1 , and if S_J - S_f e < 0, it is determined that S_J is in the interval [S_f e+1 , S_f e ; e takes values from 1 to T;

[0028] When comparing S_J with {S_J_p, S_f +1 ... S_f +(T-2) , S_f +(T-1) , S_f +T}, if |S_J - S_f e | < S_J_z and S_J - S_f e > 0, it is determined that S_J is in the interval [S_f e , S_f e+1 , and if S_J - S_f e < 0, it is determined that S_J is in the interval [S_f e-1 , S_f e ; e takes values from 1 to T;

[0029] Judge all d target detection data to obtain the number of target detection data in each interval. Select the interval with the largest number of target detection data and calculate the average value of the target detection data in the interval with the largest number of target detection data. Let the number of target detection data in the interval with the largest number of target detection data be g. The formula is: S_J_y represents the average value of the target detection data in the interval with the largest number of target detection data, and take the calculated S_J_y as the target detection data threshold.

[0030] The target detection data when abnormal equipment is adjusted in history is collected, and after being graded according to the mean value and standard deviation, the interval with the most target detection data in all levels is found, and the mean value of the target detection data therein is calculated. This can eliminate the excessively large or small values ​​in the historical target detection data and reduce the error of the target detection data threshold.

[0031] S300, collecting the data of all devices working in history, constructing a normal working data set of the devices, finding the implicated data types between the devices to construct an implicated data set, and calculating the implicated data threshold;

[0032] Furthermore, the specific steps for calculating the threshold of implicated data are:

[0033] S301, collect the equipment data types in the history when the equipment is not adjusted and works normally, {Z1, Z2, Z3...Z v}, Z1, Z2, Z3...Z v It means the collected equipment data of the 1st, 2nd, 3rd, ... vth equipment when they are working normally. The data is collected u times and the average value of each equipment data is calculated. The formula is: In the formula, Z_sp is the average value of each device data, Z_s represents the data value of each device data collected, and u represents the number of each device data collected; the average value of each device data is calculated as {Z_sp1, Z_sp2, Z_sp3...Z_sp v}, Z_sp1, Z_sp2, Z_sp3...Z_sp v It represents the average value of the 1st, 2nd, 3rd, ... vth types of equipment data collected when the equipment is working normally, where v is a positive integer; the set of average values ​​of each type of equipment data is used as the normal working data set of the equipment;

[0034] S302, collecting the records of the impact of abnormal equipment on equipment that does not need to be adjusted when adjusting the abnormal equipment in the history, extracting the data types of abnormal equipment changed when adjusting the abnormal equipment in all records as {Q1, Q2, Q3...Q w}, Q1, Q2, Q3...Q w Indicates the 1st, 2nd, 3rd...wth data types that change when the abnormal device is adjusted, where w is a positive integer; collects all the records of the data types that change when the abnormal device is adjusted, including {P1, P2, P3...P q}, P1, P2, P3...P q It indicates the 1st, 2nd, 3rd, ... qth data type of the device that does not need to be adjusted when the abnormal device is adjusted, where q is a positive integer;

[0035] S303. Compare the devices in the two sets extracted in S302, select the data of the same type in the two sets as the implicated data, and construct the implicated data set as {Im1, Im2, Im3... Im j}, Im1, Im2, Im3... Im j represent the 1st, 2nd, 3rd... jth types of implicated data; collect the average device distance when the abnormal device is adjusted and it affects the non-adjusted devices, collect the adjustment values of the implicated data when the abnormal device is adjusted in D historical records, and calculate the implicated data threshold. The formula is:

[0036]

[0037] In the formula, K is the average device distance when the abnormal device is adjusted and it affects the non-adjusted devices, Im_y is the implicated data threshold, j is the number of types of implicated data, D is the number of each type of implicated data collected, and Im_t represents the adjustment value of the implicated data when the device is adjusted in the collected history.

[0038] S400. Collect the target detection data of the devices in real time, and use the target detection data threshold to judge whether the device needs to be adjusted and send an abnormal warning signal to the remote controller;

[0039] Furthermore, the specific steps of using the target detection data threshold to judge whether the device needs to be adjusted and send an abnormal warning signal to the remote controller are as follows:

[0040] S401. Collect the target detection data of all devices during work in real time as {S_J_s1, S_J_s2, S_J_s3... S_J_s c}, S_J_s1, S_J_s2, S_J_s3... S_J_s c represent the target detection data of the 1st, 2nd, 3rd... cth devices collected in real time during work, and c is a positive integer;

[0041] S402. When S_J_s ≥ S_J_y, judge that the working device needs to be adjusted and generate an abnormal warning signal to send to the remote controller. When S_J_s < S_J_y, judge that the device is working normally and does not need to be adjusted, and the device continues to work.

[0042] S500. Compare all the data of the device that issues the abnormal warning with the normal working data set, judge the types of data that need to be adjusted and the adjustment data values, and send the calculated data types and adjustment data values to the remote controller;

[0043] Furthermore, the specific steps of judging the types of data that need to be adjusted and the adjustment data values are as follows:

[0044] S501, when it is determined that an abnormality occurs in a working device and adjustment is required, all types of data values ​​of the early warning device are collected in real time {β1, β2, β3...β v}, β1, β2, β3...β v It is represented by the first, second, third, ... real-time data values ​​collected from the early warning device. The difference is calculated using the real-time data values ​​collected from the early warning device and the data in the normal working data set of the device. The formula is:

[0045] β_c=β-Z_sp

[0046] In the formula, β_c is the difference between the real-time data collected by the early warning device and the data in the normal working data set of the device, β represents all kinds of data values ​​collected by the early warning device in real time, and Z_sp represents all kinds of data values ​​when the device is working normally; the difference of v kinds of data is calculated, and finally v data differences are obtained as {β_c1, β_c2, β_c3...β_c v}, β_c1, β_c2, β_c3...β_c v It is expressed as the calculated data differences of the 1st, 2nd, 3rd, ...vth types;

[0047] S502, when β_c=0, it is determined that the corresponding data type is normal and does not need to be adjusted. When β_c≠0, it is determined that the corresponding data type is abnormal and needs to be adjusted, and the adjustment data value is β_c. After judgment and screening, the adjustment data value of the adjustment data type that generates an early warning is {β_c1, β_c2, β_c3...β_c G}, β_c1, β_c2, β_c3...β_c G Indicates the adjustment data values ​​of the 1st, 2nd, 3rd ... Gth data types that need to be adjusted in the early warning device, where G is a positive integer; the calculated adjustment data types and adjustment data values ​​are sent to the remote control.

[0048] S600: Use the implicated data set to determine whether the data to be adjusted is implicated data, calculate whether the data value to be adjusted will affect normal working equipment according to the implicated data threshold, and send a danger warning to the remote controller.

[0049] Furthermore, the specific steps of calculating whether the data value to be adjusted will affect the normal working equipment according to the implicated data threshold and sending a danger warning to the remote controller are:

[0050] S601, suppose that the data type set that needs to be adjusted by the early warning device after judgment is {Z_t1, Z_t2, Z_t3...Z_t G}, Z_t1, Z_t2, Z_t3...Z_t GIt represents the 1st, 2nd, 3rd... Gth types of data that need to be adjusted for the warning device as determined by the judgment. Compare the G types of data that need to be adjusted with the implicated data set, and extract the data whose types are the same as those in the implicated data set among the data types that need to be adjusted for the real-time warning device as the real-time implicated data in the data types that need to be adjusted for the real-time warning device. Let the extracted real-time implicated data be {Im_s1, Im_s2, Im_s3... Im_s α}, Im_s1, Im_s2, Im_s3... Im_s α It represents the 1st, 2nd, 3rd... αth types of real-time implicated data extracted, where α is a positive integer and α ≤ G;

[0051] S602. Calculate the real-time implicated index using the extracted real-time implicated data. The formula is:

[0052]

[0053] In the formula, Im_z is the calculated real-time implicated index, x y and y y are respectively the horizontal and vertical coordinates of the warning device in the coordinate system, x other and y other are respectively the devices other than the warning device, β_Im_s is the data value corresponding to the real-time implicated data, and β_Im_c represents the data difference that the real-time implicated data needs to be adjusted;

[0054] When calculating the influence index of the warning device on other devices, it is necessary to calculate the relative distance. There are some implicated data that only have an impact when the distance is relatively close. After calculating and judging the implicated indexes of the warning device and all other devices, it is possible to rule out the situation where adjusting the warning device will instead affect the other normal devices, causing greater losses and accidents.

[0055] S603. When Im_z ≥ Im_y, it is judged that adjusting the warning device will affect the devices other than the warning device, and send a danger warning to the remote control. When Im_z < Im_y, it is judged that adjusting the warning device will not affect the devices other than the warning device;

[0056] S604. When the remote control receives the danger warning, stop adjusting the implicated data, and only adjust the non-implicated data in the data types that need to be adjusted, and the adjusted data value is β_c; when the remote control does not receive the danger warning, perform remote adjustment control on the warning device according to all the data types to be adjusted and the adjusted data values.

[0057] An intelligent device management system based on data analysis. The intelligent device management system includes a data collection module, a positioning module, a threshold calculation module, a central warning module, and a remote control module;

[0058] The data collection module is used to collect data on the operation and adjustment of the equipment in history;

[0059] The positioning module is used to locate each device after establishing a plane rectangular coordinate system, and then mark it;

[0060] The threshold calculation module is used to search for target detection data and implicated data in the device, and calculate the target detection data threshold and the implicated data threshold;

[0061] The central warning module is used to collect target detection data of the equipment in real time, determine whether the equipment has an abnormality and needs to be adjusted, and calculate the implicated data index in the adjustment data to determine whether the adjustment of the warning equipment will affect equipment other than the warning equipment;

[0062] The remote control module is used to adjust the warning device after receiving the warning signal, adjusting the data type and adjusting the data value when it is determined that the device is abnormal and needs to be adjusted.

[0063] The threshold calculation module includes a target detection data threshold calculation unit and an implicated data threshold calculation unit;

[0064] The target detection data threshold calculation unit is used to analyze the data when the equipment is adjusted in the history, determine the type of target detection data that reflects the abnormality of the equipment, and then collect the target detection data in the history to calculate the target detection data threshold;

[0065] The involved data threshold calculation unit is used to analyze the data of two devices when the adjustment of the device in the history affects the device other than the adjusted device, extract the data that changes simultaneously as the involved data type, and then calculate the involved data threshold according to the distance between the two devices and the involved data.

[0066] The central warning module includes an equipment abnormality warning unit and a danger warning unit;

[0067] The device abnormality warning unit is used to collect real-time target detection data in the device, judge the real-time target detection data according to the target detection data threshold, whether the device in real-time working is abnormal, and send a warning signal to the remote control module;

[0068] The danger warning unit is used to calculate the data that needs to be adjusted for the warning device and the adjustment data value after determining that an abnormality has occurred in the equipment and issuing a warning, extract the involvement data in the adjustment data, calculate the involvement index between the warning device and the equipment other than the warning device, determine whether the adjustment of the warning device will have an impact on the equipment other than the warning device, and send a danger warning to the remote control module.

[0069] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0070] 1. The present invention establishes a plane rectangular coordinate system in the working environment, positions all devices, calculates the position coordinates of each device, realizes the tracking and monitoring of the devices, and can calculate the relative distance between each device in real time, and control the relative distance between the devices in real time.

[0071] 2. The present invention extracts the target detection data of the device based on the data adjusted when the device has abnormalities in history, and calculates the target detection threshold. The target detection data can be used to detect whether the device has abnormalities, thereby reducing resource consumption when judging device abnormalities.

[0072] 3. The present invention searches for involved data and calculates thresholds when the equipment is adjusted. When it is determined that an abnormality occurs in the equipment and adjustment is required, it is further determined whether the adjustment of the early warning equipment will have an impact on other equipment. When an impact occurs, a danger warning is issued. When the remote control adjusts the early warning equipment, the data is selectively adjusted according to the danger warning, thereby avoiding greater losses and accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0074] Figure 1 It is a module distribution diagram of an intelligent equipment management system based on data analysis of the present invention;

[0075] Figure 2 It is a schematic diagram of the steps of an intelligent equipment management method based on data analysis of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0078] An intelligent equipment management method based on data analysis, the method comprising the following steps:

[0079] S100, collecting the number and location of devices that need to be managed in the visual environment of the visual sensor, and establishing a coordinate system to locate and mark each device;

[0080] The specific steps to establish a coordinate system to locate and mark each device are:

[0081] S101, using a visual sensor to collect the positions and number of all devices in the working environment, assuming the number of devices is c, establishing a plane rectangular coordinate system with the visual sensor as the origin, with the north direction as the positive direction of the y-axis and the east direction as the positive direction of the x-axis;

[0082] S102, collect the distances between each device and the visual sensor in the working environment {L1, L2, L3...L c}, L1, L2, L3...L c represents the distance between the 1st, 2nd, 3rd...cth device and the visual sensor in the working environment, where c is a positive integer; the angle of each device in the plane rectangular coordinate system is {J1, J2, J3...J c}, J1, J2, J3...J c It is expressed as the angle of the 1st, 2nd, 3rd...cth device in the working environment in the plane rectangular coordinate system, and the angle of all devices is the angle between the line connecting the device and the visual sensor and the positive direction of the x-axis; when the device is in the positive direction of the y-axis, the angle is positive, and when the device is in the negative direction of the y-axis, the angle is negative;

[0083] S103, calculating the position coordinates of each device according to the collected distance between each device and the visual sensor and the angle of each device in the plane rectangular coordinate system, the formula is:

[0084] x=L×cosJ

[0085] y=L×sinJ

[0086] In the formula, x represents the horizontal coordinate of the device in the plane coordinate system, y represents the vertical coordinate of the device in the plane coordinate system, L represents the distance between each device and the visual sensor, and J represents the angle of each device in the plane coordinate system;

[0087] S104, calculate the position coordinates of the c devices, and obtain the coordinate set of the c devices as {(x1, y1), (x2, y2), (x3, y3)...(x c ,y c )}, (x1, y1), (x2, y2), (x3, y3)...(x c ,y c) represents the position coordinates of the 1st, 2nd, 3rd...cth devices in the plane coordinate system in the working environment. After calculating the position coordinates of each device, each device is marked as Indicates the labeling of the 1st, 2nd, 3rd...cth devices, x represents the horizontal coordinate of each device, and y represents the vertical coordinate of each device.

[0088] After all devices in the working environment are located, each device can be accurately monitored and tracked, and the relative distance between devices can be calculated based on the specific location of each device to control the distance between devices.

[0089] S200, collecting device data when adjusting the device in history, searching for target detection data, and calculating a target detection data threshold;

[0090] The specific steps for calculating the target detection data threshold are:

[0091] S201, collect equipment data {S1, S2, S3...S n}, S1, S2, S3...S n It represents the 1st, 2nd, 3rd...type data collected when adjusting the abnormal equipment, where n is a positive integer; it represents the equipment data {S'1, S'2, S'3...S'1 in the history of equipment when it is not adjusted}. n}, S'1, S'2, S'3...S' n It represents the 1st, 2nd, 3rd...nth equipment data of the equipment in the collected history when no adjustment is performed; the equipment that is adjusted is an abnormal equipment, and the equipment that is not adjusted is a normal equipment;

[0092] S202, compare the collected device data when adjusted and when not adjusted, and extract the changed device data {S_b1, S_b2, S_b3...S_b1} from the device data of the abnormal device adjusted. m}, S_b1, S_b2, S_b3...S_b m Indicates the 1st, 2nd, 3rd, ... pieces of equipment data that have changed in the equipment data set for adjusting the abnormal equipment, where m is a positive integer; the change amount of the m pieces of equipment data that have changed is calculated using the formula:

[0093] S_b_c=|S_b-S_b'|

[0094] In the formula, S_b_c represents the amount of change in the changed device data, S_b represents the device data when the abnormal device is adjusted, and S_b' represents the device data when the device is not adjusted;

[0095] S203, calculate the m changed device data, and obtain the changed amount of the device data as {S_b_c1, S_b_c2, S_b_c3...S_b_c m}, S_b_c1, S_b_c2, S_b_c3...S_b_c m Indicates the 1st, 2nd, 3rd, ...mth changed device data changes; selects the device data type corresponding to the maximum value among the m changed device data changes as the target detection data S_J;

[0096] S204, calculating the target detection data threshold according to the target detection data collected during the work of adjusting the abnormal equipment, assuming that there are d target detection data collected during the work of adjusting the abnormal equipment, and calculating the average value and standard deviation of the collected target detection data, the formula is: In the formula, S_J_p represents the average value of the collected target detection data, S_J_z represents the standard deviation of the collected target detection data, and d represents the total number of the collected target detection data. The collected target detection data are graded using the calculated average value and standard deviation, and the graded standard data value of each level is calculated. The formula is:

[0097]

[0098] In the formula, S_f represents the standard data value of each level, T represents half of the number of target detection data to be classified, and the average value is used as the first level, S_f -T Indicates the Tth level less than the average value, S_f +T Indicates the Tth level greater than the average value, T is a positive integer and increases by 1 until S_f +end >maxS_J i And S_f -end <minS_J i , S_f -end and S_f +end Indicates the last grading standard data value calculated, maxS_J i Indicates the maximum value of the collected target detection data, minS_J i represents the minimum value of the collected target detection data, i ranges from 1 to d; the final calculated target detection data classification standard data value is {S_f -T 、S_f -(T-1) 、S_f -(T-2) ...S_f -1 , S_J_p, S_f +1 ...S_f +(T-2) 、S_f +(T-1) 、S_f+T}, S_f -T , S_f -(T-1) , S_f -(T-2) ...S_f -1 represent the Tth, (T - 1)th, (T - 2)th... 1st classification standard data values less than the average value, S_J_p represents the average value of the target detection data, S_f +1 ...S_f +(T-2) , S_f +(T-1) , S_f +T represent the 1st... (T - 2)th, (T - 1)th, Tth classification standard data values greater than the average value;

[0099] S205. According to the calculated 2T + 1 classification standard data values, divide the target detection data in the collected history. Two adjacent classification standard data values form a classification interval, and compare the target detection data in the collected history with each classification standard data value. The specific method is as follows:

[0100] When S_J and {S_f -T , S_f -(T-1) , S_f -(T-2) ...S_f -1 , S_J_p} are compared, |S_J - S_f e | < S_J_z, and S_J - S_f e > 0, it is judged that S_J is in the interval [S_f e , S_f e-1 , and when S_J - S_f e < 0, it is judged that S_J is in the interval [S_f e+1 , S_f e ; e takes values from 1 to T;

[0101] When S_J and {S_J_p, S_f +1 ...S_f +(T-2) , S_f +(T-1) , S_f +T} are compared, |S_J - S_f e | < S_J_z, and S_J - S_f e > 0, it is judged that S_J is in the interval [S_f e , S_f e+1 , and when S_J - S_f e < 0, it is judged that S_J is in the interval [S_f e-1 , S_f e ; e takes values from 1 to T;

[0102] The d target detection data are judged to obtain the number of target detection data in each interval, and the interval with the largest number of target detection data is selected, and the average value of the target detection data in the interval with the largest number of target detection data is calculated. Assuming that the number of target detection data in the interval with the largest number of target detection data is g, the formula is: S_J_y is represented by the average value of the target detection data in the interval with the most target detection data, and the calculated S_J_y is used as the target detection data threshold.

[0103] The target detection data when abnormal equipment is adjusted in history is collected, and after being graded according to the mean value and standard deviation, the interval with the most target detection data in all levels is found, and the mean value of the target detection data therein is calculated. This can eliminate the excessively large or small values ​​in the historical target detection data and reduce the error of the target detection data threshold.

[0104] S300, collecting the data of all devices working in history, constructing a normal working data set of the devices, finding the implicated data types between the devices to construct an implicated data set, and calculating the implicated data threshold;

[0105] The specific steps for calculating the threshold of implicated data are:

[0106] S301, collect the equipment data types in the history when the equipment is not adjusted and works normally, {Z1, Z2, Z3...Z v}, Z1, Z2, Z3...Z v It means the collected equipment data of the 1st, 2nd, 3rd, ... vth equipment when they are working normally. The data is collected u times and the average value of each equipment data is calculated. The formula is: In the formula, Z_sp is the average value of each device data, Z_s represents the data value of each device data collected, and u represents the number of each device data collected; the average value of each device data is calculated as {Z_sp1, Z_sp2, Z_sp3...Z_sp v}, Z_sp1, Z_sp2, Z_sp3...Z_sp v It represents the average value of the 1st, 2nd, 3rd, ... vth types of equipment data collected when the equipment is working normally, where v is a positive integer; the set of average values ​​of each type of equipment data is used as the normal working data set of the equipment;

[0107] S302, collecting the records of the impact of abnormal equipment on equipment that does not need to be adjusted when adjusting the abnormal equipment in the history, extracting the data types of abnormal equipment changed when adjusting the abnormal equipment in all records as {Q1, Q2, Q3...Q w}, Q1, Q2, Q3...Q wIndicates the 1st, 2nd, 3rd...wth data types that change when the abnormal device is adjusted, where w is a positive integer; collects all the records of the data types that change when the abnormal device is adjusted, including {P1, P2, P3...P q}, P1, P2, P3...P q It indicates the 1st, 2nd, 3rd, ... qth data type of the device that does not need to be adjusted when the abnormal device is adjusted, where q is a positive integer;

[0108] S303, compare the devices in the two sets extracted in S302, select the data of the same type in the two sets as implicated data, and construct an implicated data set as {Im1, Im2, Im3...Im j}, Im1, Im2, Im3...Im j Expressed as the 1st, 2nd, 3rd...jth implicated data; collect the average distance of the equipment when the abnormal equipment is adjusted to affect the unadjusted equipment, collect the adjustment value of the implicated data when the abnormal equipment is adjusted in D times of history, and calculate the implicated data threshold. The formula is:

[0109]

[0110] In the formula, K is the average distance between devices when the abnormal device affects the unadjusted device when it is adjusted, Im_y is the threshold of implicated data, j is the number of types of implicated data, D is the number of each type of implicated data collected, and Im_t represents the adjustment value of implicated data when the device is adjusted in the collected history.

[0111] S400, collecting target detection data of the device in real time, using the target detection data threshold to determine whether the device needs to be adjusted and sending an abnormal warning signal to the remote controller;

[0112] The specific steps for using the target detection data threshold to determine whether the device needs to be adjusted and sending an abnormal warning signal to the remote controller are:

[0113] S401, collect the target detection data of all devices in real time as {S_J_s1, S_J_s2, S_J_s3...S_J_s c}, S_J_s1, S_J_s2, S_J_s3...S_J_s c It represents the 1st, 2nd, 3rd, ...cth device target detection data collected in real time during work, where c is a positive integer;

[0114] S402. When \(S_{J_s}\geq S_{J_y}\), it is determined that the working device needs to be adjusted, and an abnormal warning signal is generated and sent to the remote controller. When \(S_{J_s}<S_{J_y}\), it is determined that the device is working normally and no adjustment is required, and the device continues to work.

[0115] S500. Collect all the data of the device that issues an abnormal warning and compare it with the normal working data set to determine the types of data that need to be adjusted and the adjusted data values, and send the calculated data types and adjusted data values to the remote controller.

[0116] The specific steps for determining the types of data that need to be adjusted and the adjusted data values are as follows:

[0117] S501. When it is determined that the device in operation is abnormal and needs to be adjusted, all types of data values of the warning device are collected in real time as \(\{\beta_1,\beta_2,\beta_3,\cdots,\beta_{}\) v \}\), where \(\beta_1,\beta_2,\beta_3,\cdots,\beta_{}\) v represent the 1st, 2nd, 3rd, \(\cdots\) kinds of real-time data values in the collected warning device. Calculate the difference between the real-time data values in the collected warning device and the data in the normal working data set of the device. The formula is:

[0118] \(\beta_c=\beta - Z_{sp}\)

[0119] In the formula, \(\beta_c\) is the difference between the real-time data in the collected warning device and the data in the normal working data set of the device, \(\beta\) represents all types of data values of the real-time collected warning device, and \(Z_{sp}\) represents all types of data values when the device is working normally. Calculate the differences for \(v\) types of data, and finally obtain \(v\) data differences as \(\{\beta_{c1},\beta_{c2},\beta_{c3},\cdots,\beta_{c}\) v \}\), where \(\beta_{c1},\beta_{c2},\beta_{c3},\cdots,\beta_{c}\) v represent the 1st, 2nd, 3rd, \(\cdots\), \(v\)th kinds of calculated data differences.

[0120] S502. When \(\beta_c = 0\), it is determined that the corresponding data type is normal and no adjustment is required. When \(\beta_c\neq0\), it is determined that the corresponding data type is abnormal and needs to be adjusted, and the adjusted data value is \(\beta_c\). After judgment and screening, the adjusted data values of the adjusted data types that issue warnings are \(\{\beta_{c1},\beta_{c2},\beta_{c3},\cdots,\beta_{c}\) G \}\), where \(\beta_{c1},\beta_{c2},\beta_{c3},\cdots,\beta_{c}\) G represent the adjusted data values of the 1st, 2nd, 3rd, \(\cdots\), \(G\)th types of data that need to be adjusted in the warning device, and \(G\) is a positive integer. Send the calculated adjusted data types and adjusted data values to the remote controller.

[0121] S600: Use the implicated data set to determine whether the data to be adjusted is implicated data, calculate whether the data value to be adjusted will affect normal working equipment according to the implicated data threshold, and send a danger warning to the remote controller.

[0122] The specific steps for calculating whether the data value to be adjusted will affect the normal working equipment according to the implicated data threshold and sending a danger warning to the remote controller are:

[0123] S601, suppose that the data type set that needs to be adjusted by the early warning device after judgment is {Z_t1, Z_t2, Z_t3...Z_t G}, Z_t1, Z_t2, Z_t3...Z_t G It indicates that the 1st, 2nd, 3rd...Gth data types that need to be adjusted by the early warning device are judged, and the G data types that need to be adjusted are compared with the implicated data set, and the data types that need to be adjusted are the same as the data types in the implicated data set, and the data implicated in the data types that need to be adjusted are extracted as the real-time implicated data in the data types that need to be adjusted by the real-time early warning device. Let the extracted real-time implicated data be {Im_s1, Im_s2, Im_s3...Im_s α}, Im_s1, Im_s2, Im_s3...Im_s α represents the extracted 1st, 2nd, 3rd, ..., αth real-time implicated data, α is a positive integer, and α≤G;

[0124] S602: Calculate the real-time involvement index using the extracted real-time involvement data, using the formula:

[0125]

[0126] In the formula, Im_z is the calculated real-time implicated index, x y and y Early warning equipment The horizontal and vertical coordinates in the coordinate system, x other and other are the devices other than the early warning device, β_Im_s is the data value corresponding to the real-time implicated data, and β_Im_c represents the data difference that needs to be adjusted for the real-time implicated data;

[0127] When calculating the impact index of the early warning device on other equipment, the relative distance needs to be calculated. Some involved data only have an impact when the distance is close. After calculating and judging the involvement index of the early warning device and all other equipment, it can be ruled out that when the early warning device is adjusted, it will affect other normal equipment, causing greater losses and accidents.

[0128] S603. When Im_z ≥ Im_y, it is determined that adjusting the warning device will affect devices other than the warning device, and a danger warning is sent to the remote control. When Im_z < Im_y, it is determined that adjusting the warning device will not affect devices other than the warning device;

[0129] S604. When the remote control receives a danger warning, it stops adjusting the implicated data and only adjusts the non-implicated data in the data types that need to be adjusted, and the adjusted data value is β_c. When the remote control does not receive a danger warning, it remotely adjusts and controls the warning device according to all the data types to be adjusted and the adjusted data values.

[0130] An intelligent device management system based on data analysis. The intelligent device management system includes a data collection module, a positioning module, a threshold calculation module, a central warning module, and a remote control module;

[0131] The data collection module is used to collect data when the device is working and being adjusted in history;

[0132] The positioning module is used to establish a plane rectangular coordinate system and then position each device and mark it;

[0133] The threshold calculation module is used to find the target detection data and implicated data in the device, and calculate the target detection data threshold and the implicated data threshold;

[0134] The central warning module is used to collect the target detection data of the device in real time, determine whether the device has an abnormality that needs to be adjusted, calculate the implicated data index in the adjusted data, and determine whether adjusting the warning device will affect devices other than the warning device;

[0135] The remote control module is used to adjust the warning device after receiving a warning signal, the data types to be adjusted, and the adjusted data values when it is determined that the device has an abnormality that needs to be adjusted.

[0136] The threshold calculation module includes a target detection data threshold calculation unit and an implicated data threshold calculation unit;

[0137] The target detection data threshold calculation unit is used to analyze the data when the device is adjusted in history, determine the types of target detection data reflecting the device abnormality, and then collect the target detection data in history to calculate the target detection data threshold;

[0138] The implicated data threshold calculation unit is used to analyze the data of two devices when the adjustment of a device other than the adjusted device has an impact in history, extract the data that changes simultaneously as the implicated data types, and then calculate the implicated data threshold according to the distance between the two devices and the implicated data.

[0139] The central warning module includes an equipment abnormality warning unit and a danger warning unit;

[0140] The device abnormality warning unit is used to collect real-time target detection data in the device, judge the real-time target detection data according to the target detection data threshold, whether the device in real-time working is abnormal, and send a warning signal to the remote control module;

[0141] The danger warning unit is used to calculate the data that needs to be adjusted for the warning device and the adjustment data value after determining that an abnormality has occurred in the equipment and issuing a warning, extract the involvement data in the adjustment data, calculate the involvement index between the warning device and the equipment other than the warning device, determine whether the adjustment of the warning device will have an impact on the equipment other than the warning device, and send a danger warning to the remote control module.

[0142] Example 1

[0143] Suppose there are three devices in an automated production factory. After locating the three devices, the position coordinates of each device are calculated to be (4,8), (6,7), and (13,4). The three devices are marked according to the position coordinates.

[0144] The data when the equipment was adjusted in history was calculated, and the target detection data was speed. The target detection data collected in history was 5, 6, 12, 7, 19, 10, and 15. The average value was calculated to be 10.5, and the standard deviation was 4.7. The classification intervals were calculated to be (1.1, 5.8), (5.8, 10.5), (10.5, 15.2), and (15.2, 19.9). After judgment, the target detection data in the interval (5.8, 10.5) were at most 6, 7, and 10. The average value of the three data was calculated to be 7.7, and the target detection threshold was 7.7.

[0145] After collecting and analyzing the data of the equipment in history, the implicated data types are obtained as data 2 current, data 4 temperature, and data 8 voltage. Assume that there are 8 types of data in the equipment, and the data value of each type is 5, 3, 44, 56, 21, 34, 12, and 220 during normal operation; according to historical calculations, the implicated data threshold is 250;

[0146] The target detection data of three devices are collected in real time, which are 6, 2, and 8. An exception occurs, collect All data values ​​in the device are 8, 7, 44, 82, 21, 31, 18, and 220. It is further determined that the data that need to be adjusted are data 1 speed, data 2 current, data 4 temperature, data 6 vibration, and data 7 intermittent time, and the adjusted data values ​​are 3, 4, 26, 3, and 6 respectively. The real-time implicated data is determined using the implicated data set, and the implicated data index is calculated. The formula is:

[0147]

[0148] Calculate the equipment and The involvement index is 294 and 228.5. After comparing with the involvement data threshold, it is judged that It will have an impact and send a danger warning to the remote control. The remote control only adjusts data 1 current, data 6 vibration, and data 7 interval time, and the adjustment values ​​are 3, 3, and 6.

[0149] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0150] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent equipment management method based on data analysis, characterized in that: The method comprises the following steps: S100, collecting the number and location of devices that need to be managed in the visual environment of the visual sensor, and establishing a coordinate system to locate and mark each device; S200, collecting device data when adjusting the device in history, searching for target detection data, and calculating a target detection data threshold; The specific steps for calculating the target detection data threshold are: S201, collect equipment data {S1, S2, S3...S n }, S1, S2, S3...S n It represents the 1st, 2nd, 3rd...type data collected when adjusting the abnormal equipment, where n is a positive integer; it represents the equipment data {S′1, S′2, S′3...S′ in the history of collecting equipment when it is not adjusted. n }, S′1, S′2, S′3...S′ n It represents the 1st, 2nd, 3rd...nth equipment data of the equipment in the collected history when no adjustment is made; the equipment that is adjusted is an abnormal equipment, and the equipment that is not adjusted is a normal equipment; S202, compare the collected device data when adjusted and when not adjusted, and extract the changed device data {S_b1, S_b2, S_b3...S_b1} from the device data of the abnormal device adjusted. m }, S_b1, S_b2, S_b3...S_b m Indicates the 1st, 2nd, 3rd, ... pieces of equipment data that have changed in the equipment data set for adjusting the abnormal equipment, where m is a positive integer; the change amount of the m pieces of equipment data that have changed is calculated using the formula: S_b_c=|S_b-S_b′| In the formula, S_b_c represents the amount of change in the changed device data, S_b represents the device data when the abnormal device is adjusted, and S_b′ represents the device data when the device is not adjusted; S203, calculate the m changed device data, and obtain the changed amount of the device data as {S_b_c1, S_b_c2, S_b_c3...S_b_c m }, S_b_c1, S_b_c2, S_b_c3...S_b_c m Indicates the 1st, 2nd, 3rd, ...mth changed device data changes; selects the device data type corresponding to the maximum value among the m changed device data changes as the target detection data S_J; S204, calculating the target detection data threshold according to the target detection data collected during the work of adjusting the abnormal equipment, assuming that there are d target detection data collected during the work of adjusting the abnormal equipment, and calculating the average value and standard deviation of the collected target detection data, the formula is: In the formula, S_J_p represents the average value of the collected target detection data, S_J_z represents the standard deviation of the collected target detection data, and d represents the total number of the collected target detection data. The collected target detection data are graded using the calculated average value and standard deviation, and the graded standard data value of each level is calculated. The formula is: In the formula, S_f represents the standard data value of each level, T represents half of the number of target detection data to be classified, and the average value is used as the first level, S_f -T Indicates the Tth level less than the average value, S_f +T Indicates the Tth level greater than the average value, T is a positive integer and increases by 1 until S_f +end >maxS_J i And S_f -end <minS_J i , S_f -end and S_f +end Indicates the last grading standard data value calculated, maxS_J i Indicates the maximum value of the collected target detection data, minS_J i represents the minimum value of the collected target detection data, i ranges from 1 to d; the final calculated target detection data classification standard data value is {S_f -T 、S_f -(T-1) 、S_f -(T-2) ...S_f -1 , S_J_p, S_f +1 ...S_f +(T-2) 、S_f +(T-1) 、S_f +T },S_f -T 、S_f -(T-1) 、S_f -(T-2) ...S_f -1 represents the T, T-1, T-2...1st classification standard data value that is less than the average value, S_J_p represents the average value of the target detection data, S_f +1 ...S_f +(T-2) 、S_f +(T-1) 、S_f +T Indicates the 1st...T-2, T-1, T grading standard data values ​​greater than the average value; S205, according to the calculated 2T+1 classification standard data values, the collected historical target detection data is divided, two adjacent classification standard data values ​​constitute a classification interval, and the collected historical target detection data is compared with each classification standard data value. The specific method is: When S_J and {S_f -T , S_f -(T-1) , S_f -(T-2) ...S_f -1 , S_J_p } are compared, |S_J - S_f e | < S_J_z, and when S_J - S_f e > 0, it is determined that S_J is in the interval [S_f e , S_f e-1 , and when S_J - S_f e < 0, it is determined that S_J is in the interval [S_f e+1 , S_f e ; e takes values from 1 to T; When comparing \(S_J\) with \(\{S_{J_p}, S_f\) +1 ... \(S_f\) +(T-2) , \(S_f\) +(T-1) , \(S_f\) +T \}, if \(|S_J - S_f|\) e \(< S_{J_z}\), and \(S_J - S_f\) e \(> 0\), it is determined that \(S_J\) is in the interval \([S_f\) e , \(S_f\) e+1 ; if \(S_J - S_f\) e \(< 0\), it is determined that \(S_J\) is in the interval \([S_f\) e-1 , \(S_f\) e ; \(e\) takes values from 1 to \(T\); The d target detection data are judged to obtain the number of target detection data in each interval, and the interval with the largest number of target detection data is selected, and the average value of the target detection data in the interval with the largest number of target detection data is calculated. Assuming that the number of target detection data in the interval with the largest number of target detection data is g, the formula is: S_J_y is represented by the average value of the target detection data in the interval with the most target detection data, and the calculated S_J_y is used as the target detection data threshold; S300, collecting the data of all devices working in history, constructing a normal working data set of the devices, finding the implicated data types between the devices to construct an implicated data set, and calculating the implicated data threshold; The specific steps for calculating the threshold of implicated data are: S301, collect the equipment data types in the history when the equipment is not adjusted and works normally, {Z1, Z2, Z3...Z v }, Z1, Z2, Z3...Z v It represents the device data collected when the 1st, 2nd, 3rd, ... vth devices are working normally. The data is collected u times and the average value of each device data is calculated. The formula is: In the formula, Z_sp is the average value of each device data, Z_s represents the data value of each device data collected, and u represents the number of each device data collected; the average value of each device data is calculated as {Z_sp1, Z_sp2, Z_sp3...Z_sp v }, Z_sp1, Z_sp2, Z_sp3...Z_sp v It represents the average value of the 1st, 2nd, 3rd, ... vth types of equipment data collected when the equipment is working normally, where v is a positive integer; the set of average values ​​of each type of equipment data is used as the normal working data set of the equipment; S302, collecting the records of the impact of abnormal equipment on equipment that does not need to be adjusted when adjusting the abnormal equipment in the history, extracting the data types of abnormal equipment changed when adjusting the abnormal equipment in all records as {Q1, Q2, Q3...Q w }, Q1, Q2, Q3...Q w Indicates the 1st, 2nd, 3rd...wth data types that change when the abnormal device is adjusted, where w is a positive integer; collects all the records of the data types that change when the abnormal device is adjusted, including {P1, P2, P3...P q }, P1, P2, P3...P q It indicates the 1st, 2nd, 3rd, ... qth data type of the device that does not need to be adjusted when the abnormal device is adjusted, where q is a positive integer; S303, compare the devices in the two sets extracted in S302, select the data of the same type in the two sets as implicated data, and construct an implicated data set as {Im1, Im2, Im3...Im j }, Im1, Im2, Im3...Im j Expressed as the 1st, 2nd, 3rd...jth implicated data; collect the average distance of the equipment when the abnormal equipment is adjusted to affect the unadjusted equipment, collect the adjustment value of the implicated data when the abnormal equipment is adjusted in D times of history, and calculate the implicated data threshold. The formula is: In the formula, K is the average distance between devices when the abnormal device is adjusted and affects the unadjusted device, Im_y is the threshold of implicated data, j is the number of implicated data types, D is the number of each implicated data collected, and Im_t represents the adjustment value of implicated data when the device is adjusted in the collected history; S400, collecting target detection data of the device in real time, using the target detection data threshold to determine whether the device needs to be adjusted and sending an abnormal warning signal to the remote controller; S500, collecting all data of the device that issues the abnormal warning and comparing them with the normal working data set, determining the data type and adjustment data value that need to be adjusted, and sending the calculated data type and adjustment data value to the remote controller; S600: Use the implicated data set to determine whether the data to be adjusted is implicated data, calculate whether the data value to be adjusted will affect normal working equipment according to the implicated data threshold, and send a danger warning to the remote controller.

2. The intelligent equipment management method based on data analysis according to claim 1 is characterized in that: The specific steps of establishing a coordinate system in S100 to locate and mark each device are: S101, using a visual sensor to collect the positions and number of all devices in the working environment, assuming the number of devices is c, establishing a plane rectangular coordinate system with the visual sensor as the origin, with the north direction as the positive direction of the y-axis and the east direction as the positive direction of the x-axis; S102, collect the distances between each device and the visual sensor in the working environment {L1, L2, L3...L c }, L1, L2, L3...L c represents the distance between the 1st, 2nd, 3rd...cth device and the visual sensor in the working environment, where c is a positive integer; the angle of each device in the plane rectangular coordinate system is {J1, J2, J3...J c }, J1, J2, J3...J c It is expressed as the angle of the 1st, 2nd, 3rd...cth device in the plane rectangular coordinate system in the working environment, and the angle of all devices is the angle between the line connecting the device and the visual sensor and the positive direction of the x-axis; when the device is in the positive direction of the y-axis, the angle is positive, and when the device is in the negative direction of the y-axis, the angle is negative; S103, calculating the position coordinates of each device according to the collected distance between each device and the visual sensor and the angle of each device in the plane rectangular coordinate system, the formula is: x=L×cosJ y=L×sinJ In the formula, x represents the horizontal coordinate of the device in the plane coordinate system, y represents the vertical coordinate of the device in the plane coordinate system, L represents the distance between each device and the visual sensor, and J represents the angle of each device in the plane coordinate system; S104, calculate the position coordinates of the c devices, and obtain the coordinate set of the c devices as {(x1, y1), (x2, y2), (x3, y3)...(x c ,y c )}, (x1, y1), (x2, y2), (x3, y3)...(x c ,y c ) represents the position coordinates of the 1st, 2nd, 3rd...cth devices in the plane coordinate system in the working environment. After calculating the position coordinates of each device, each device is marked as Indicates the labeling of the 1st, 2nd, 3rd...cth devices, x represents the horizontal coordinate of each device, and y represents the vertical coordinate of each device.

3. The intelligent equipment management method based on data analysis according to claim 1 is characterized in that: The specific steps of using the target detection data threshold to determine whether the device needs to be adjusted and sending an abnormal warning signal to the remote controller in S400 are: S401, collect the target detection data of all devices in real time as {S_J_s1, S_J_s2, S_J_s3...S_J_s c }, S_J_s1, S_J_s2, S_J_s3...S_J_s c It represents the 1st, 2nd, 3rd, ...cth device target detection data collected in real time during work, where c is a positive integer; S402. When S_J_s ≥ S_J_y, it is determined that the working device needs to be adjusted, and an abnormal warning signal is generated and sent to the remote controller. When S_J_s < S_J_y, it is determined that the device is working normally and no adjustment is required, and the device continues to work.

4. The intelligent equipment management method based on data analysis according to claim 1 is characterized in that: The specific steps for determining the types of data that need to be adjusted and the adjusted data values in S500 are as follows: S501, when it is determined that an abnormality occurs in a working device and adjustment is required, all types of data values ​​of the early warning device are collected in real time {β1, β2, β3...β v }, β1, β2, β3...β v It is represented by the first, second, third, ... real-time data values ​​collected from the early warning device. The difference is calculated using the real-time data values ​​collected from the early warning device and the data in the normal working data set of the device. The formula is: β_c = β - Z_sp In the formula, β_c is the difference between the real-time data collected by the early warning device and the data in the normal working data set of the device, β represents all kinds of data values ​​collected by the early warning device in real time, and Z_sp represents all kinds of data values ​​when the device is working normally; the difference of v kinds of data is calculated, and finally v data differences are obtained as {β_c1, β_c2, β_c3...β_c v }, β_c1, β_c2, β_c3...β_c v It is expressed as the calculated data differences of the 1st, 2nd, 3rd, ...vth types; S502, when β_c=0, it is determined that the corresponding data type is normal and does not need to be adjusted. When β_c≠0, it is determined that the corresponding data type is abnormal and needs to be adjusted, and the adjustment data value is β_c. After judgment and screening, the adjustment data value of the adjustment data type that generates an early warning is {β_c1, β_c2, β_c3...β_c G }, β_c1, β_c2, β_c3...β_c G Indicates the adjustment data values ​​of the 1st, 2nd, 3rd ... Gth data types that need to be adjusted in the early warning device, where G is a positive integer; the calculated adjustment data types and adjustment data values ​​are sent to the remote control.

5. The intelligent equipment management method based on data analysis according to claim 1 is characterized in that: The specific steps for calculating whether the adjusted data value will affect the normal working device according to the entrainment data threshold in S600 and sending a danger warning to the remote controller are as follows: S601, suppose that the data type set that needs to be adjusted by the early warning device after judgment is {Z_t1, Z_t2, Z_t3...Z_t G }, Z_t1, Z_t2, Z_t3...Z_t G It indicates that the 1st, 2nd, 3rd...Gth data types that need to be adjusted by the early warning device are judged, and the G data types that need to be adjusted are compared with the implicated data set, and the data types that need to be adjusted are the same as the data types in the implicated data set, and the data implicated in the data types that need to be adjusted are extracted as the real-time implicated data in the data types that need to be adjusted by the real-time early warning device. Let the extracted real-time implicated data be {Im_s1, Im_s2, Im_s3...Im_s α }, Im_s1, Im_s2, Im_s3...Im_s α represents the extracted 1st, 2nd, 3rd, ..., αth real-time implicated data, α is a positive integer, and α≤G; S602. Calculate the real-time entrainment index using the extracted real-time entrainment data. The formula is: In the formula, Im_z is the calculated real-time implicated index, x y and y Early warning equipment The horizontal and vertical coordinates in the coordinate system, x other and other They are the devices other than the early warning device, and β_Im_c represents the data difference that needs to be adjusted for the real-time implicated data; S603. When Im_z ≥ Im_y, it is determined that adjusting the warning device will affect the devices other than the warning device, and a danger warning is sent to the remote controller. When Im_z < Im_y, it is determined that adjusting the warning device will not affect the devices other than the warning device. S604. When the remote controller receives the danger warning, it stops adjusting the entrainment data and only adjusts the non-entrainment data in the types of data that need to be adjusted, and the adjusted data value is β_c. When the remote controller does not receive the danger warning, it remotely adjusts and controls the warning device according to all the types of adjusted data and the adjusted data values.

6. An intelligent equipment management system based on data analysis using an intelligent equipment management method based on data analysis as claimed in any one of claims 1 to 5, characterized in that: The intelligent device management system includes a data collection module, a positioning module, a threshold calculation module, a central warning module, and a remote control module. The data collection module is used to collect the data of the device during work and adjustment in history. The positioning module is used to establish a plane rectangular coordinate system and then position each device and mark it. The threshold calculation module is used to find the target detection data and entrainment data in the device and calculate the target detection data threshold and the entrainment data threshold. The central warning module is used to collect the target detection data of the device in real time, determine whether the device is abnormal and needs to be adjusted, calculate the entrainment data index in the adjusted data, and determine whether adjusting the warning device will affect the devices other than the warning device. The remote control module is used to adjust the warning device after receiving the warning signal, the types of adjusted data, and the adjusted data values when it is determined that the device is abnormal and needs to be adjusted.

7. The intelligent equipment management system based on data analysis according to claim 6 is characterized by: The threshold calculation module includes a target detection data threshold calculation unit and an entrainment data threshold calculation unit. The target detection data threshold calculation unit is used to analyze the data of the device during adjustment in history, determine the types of target detection data reflecting the device abnormality, and then collect the target detection data in history to calculate the target detection data threshold. The entrainment data threshold calculation unit is used to analyze the data of two devices when the adjustment of a device affects other devices outside the adjusted device in history, extract the data that changes simultaneously as the types of entrainment data, and then calculate the entrainment data threshold according to the distance between the two devices and the entrainment data.

8. The intelligent equipment management system based on data analysis according to claim 6 is characterized by: The central warning module includes a device abnormality warning unit and a danger warning unit. The device abnormality warning unit is used to collect real-time target detection data in the device, judge the real-time target detection data according to the target detection data threshold, whether the device in real-time working is abnormal, and send a warning signal to the remote control module; The danger warning unit is used to calculate the data that needs to be adjusted for the warning device and the adjustment data value after determining that an abnormality has occurred in the equipment and issuing a warning, extract the involvement data in the adjustment data, calculate the involvement index between the warning device and the equipment other than the warning device, determine whether the adjustment of the warning device will have an impact on the equipment other than the warning device, and send a danger warning to the remote control module.

Images