Big data processing analysis method and system, electronic equipment and storage medium

Abstract

The invention discloses a big data processing analysis method and system, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring layout positions and a technological process sequence of a plurality of pieces of production equipment; according to each layout position, constructing a spatial incidence matrix, and according to each process flow sequence, constructing a process incidence matrix; determining a plurality of associated equipment groups based on the space association matrix and the process association matrix, and acquiring vibration data, temperature data and current data of each production equipment in each associated equipment group; for each associated equipment group, determining an equipment state value of the associated equipment group in combination with vibration data, temperature data and current data of each production equipment; and when the equipment state value of any associated equipment group exceeds the standard state value range, generating early warning information of the corresponding associated equipment group. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of big data processing analysis is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and particularly relates to a big data processing and analysis method, system, electronic device, and storage medium. Background Art

[0002] With the development of the industrial field, the degree of digitization and networking of production equipment has been continuously improved, and the massive data generated during the operation of the equipment provides an important data basis for intelligent manufacturing. By deeply analyzing and mining this industrial big data, abnormal equipment operation can be discovered in a timely manner, and equipment failures can be prevented, thereby ensuring the progress of production.

[0003] Currently, the existing big data processing and analysis methods in the industrial field mainly rely on collecting data from different production equipment and separately analyzing the data of the equipment to discover abnormal production equipment for early warning. However, in actual applications, due to the mutual influence between equipment during the production process, the abnormal state of one equipment often spreads and affects other equipment. Only using the existing method of separately processing and analyzing the data of individual equipment often easily ignores the influence situation between equipment, resulting in low accuracy of big data processing and analysis. Summary of the Invention

[0004] The present application provides a big data processing and analysis method, system, electronic device, and storage medium, which can improve the accuracy of big data processing and analysis.

[0005] In a first aspect, the present application provides a big data processing and analysis method, including: Obtaining the layout positions and technological process sequences of multiple production equipment; Constructing a spatial association matrix according to each of the layout positions, and constructing a process association matrix according to each of the technological process sequences; Based on the spatial association matrix and the process association matrix, determining multiple associated equipment groups, and obtaining vibration data, temperature data, and current data of each production equipment in each of the associated equipment groups; For each of the associated equipment groups, combining the vibration data, temperature data, and current data of each production equipment to determine the equipment state value of the associated equipment group; When the equipment state value of any associated equipment group exceeds the standard state value range, generating a warning message for the corresponding associated equipment group.

[0006] In a second aspect of the present application, there is provided a big data processing and analysis system, the system including: A data acquisition module, configured to obtain the layout positions and technological process sequences of multiple production equipment; An association matrix construction module, configured to construct a spatial association matrix according to each of the layout positions, and construct a process association matrix according to the sequence of each of the process flows; An equipment status value determination module, configured to determine a plurality of associated equipment groups based on the spatial association matrix and the process association matrix, and obtain vibration data, temperature data, and current data of each production equipment in each of the associated equipment groups; for each of the associated equipment groups, combine the vibration data, temperature data, and current data of each production equipment to determine the equipment status value of the associated equipment group; An early warning module, configured to generate an early warning information for a corresponding associated equipment group when the equipment status value of any associated equipment group exceeds the standard status value range.

[0007] In a third aspect of the present application, an electronic device is provided, including a memory, a processor, and a program stored on the memory and executable on the processor, and the program can be loaded and executed by the processor to implement a big data processing and analysis method.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement a big data processing and analysis method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, the layout positions and process flow sequences of multiple production equipments are obtained, and a spatial association matrix and a process association matrix are constructed, realizing a comprehensive analysis of the physical and process relationships between equipments. Based on the spatial association matrix and the process association matrix, the solution can accurately determine a plurality of associated equipment groups, and obtain the vibration data, temperature data, and current data of each production equipment in these equipment groups in real time. By comprehensively analyzing multi-dimensional data such as vibration, temperature, and current, the solution effectively calculates the equipment status value of each associated equipment group. When the equipment status value of a certain associated equipment group exceeds the preset standard status value range, the system can generate corresponding early warning information in time. This method takes into account the mutual influence and dependence relationships between equipments, avoids the problem of inaccurate early warning caused by only analyzing a single equipment in isolation, and can accurately perform anomaly detection and timely early warning through the fusion analysis of multi-dimensional data, thereby achieving the effect of improving the accuracy of big data processing and analysis. Description of the Drawings

[0010] Figure 1 is a flowchart of a big data processing and analysis method provided by an embodiment of the present application; Figure 2It is a schematic structural diagram of a big data processing and analysis system provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0011] Explanation of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed implementation manners

[0012] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0014] In the description of the embodiments of the present application, the meaning of the term "a plurality of" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise particularly emphasized in other ways.

[0015] The embodiments of the present application provide a big data processing and analysis method. In one embodiment, please refer to Figure 1 , Figure 1 It is a schematic flowchart of the big data processing and analysis method provided by the embodiments of the present application. This method can be implemented depending on a computer program, which can be integrated in an application or run as an independent tool application. This method can also be implemented depending on a single-chip microcomputer and can also run on a big data processing and analysis system based on the von Neumann architecture. Specifically, this method can include the following steps: Step 101: Obtain the layout positions and technological process sequences of a plurality of production devices.

[0016] Among them, the production equipment in the embodiments of the present application refers to various types of machinery and equipment that undertake specific processing, assembly, or inspection functions during the product manufacturing process. For example, in a machining production line, it includes machining equipment such as lathes, milling machines, grinders, and machining centers; in an assembly production line, it includes assembly equipment such as robots, conveyor belts, and assembly workstations; in an inspection line, it includes inspection equipment such as vision inspection equipment and dimensional measurement equipment.

[0017] The layout position in the embodiments of the present application refers to the actual installation position coordinates of each production equipment in the production workshop.

[0018] The technological process sequence in the embodiments of the present application refers to the processing flow sequence of the product among various production equipment. The entire production process can be divided into multiple processes, each process corresponding to one or more specific production equipment, and the sequence between processes is determined according to the product processing requirements.

[0019] Specifically, in the actual production process, due to the mutual influence of the spatial positions and the continuous relationship of the technological processes among production equipment, it is necessary to first obtain the basic data reflecting these correlation relationships. The layout position information of each production equipment can be obtained through the equipment layout diagram of the production workshop. The layout position can be represented in the form of two-dimensional or three-dimensional coordinates to indicate the specific spatial position of each equipment. At the same time, the technological process sequence information is obtained according to the product production process flow diagram, and this technological process sequence reflects the processing flow sequence of the product among various production equipment. For example, in a machining production line, the specific installation coordinate positions of equipment such as lathes, milling machines, and grinders can be obtained, as well as the sequence of processes during the machining of parts. By obtaining this basic information, it provides data support for subsequent analysis of the spatial correlation and process correlation between equipment, and further realizes the accurate division of equipment groups. This data acquisition method based on layout position and technological process sequence breaks through the limitation of traditional analysis only for individual equipment, can comprehensively grasp the correlation relationship between equipment from two dimensions of space and process, and provides a more comprehensive and accurate data basis for subsequent group analysis and early warning.

[0020] Step 102: Construct a spatial correlation matrix according to each layout position, and construct a process correlation matrix according to each technological process sequence.

[0021] Among them, the spatial correlation matrix in the embodiments of the present application refers to a two-dimensional matrix of N×N, where N is the total number of production equipment. Each element in the matrix represents the degree of spatial correlation between the corresponding two pieces of equipment. The rows and columns of this matrix respectively correspond to each production equipment, and the element in the i-th row and j-th column of the matrix represents the spatial correlation relationship between the equipment numbered i and the equipment numbered j.

[0022] The process correlation matrix is also a two-dimensional N×N matrix in the embodiments of the present application, which is used to represent the degree of correlation between production devices in the process flow. The rows and columns of this matrix also correspond to each production device, and the element in the i-th row and j-th column of the matrix represents the process correlation relationship between the device numbered i and the device numbered j.

[0023] Specifically, first, an initial spatial matrix of N×N is constructed based on the total number N of production devices, and the first reference positions corresponding to the device types of each production device are determined in this initial spatial matrix. Then, according to the layout position coordinates of each production device, the spatial distance between any two production devices is calculated. When the spatial distance between two devices is less than a preset distance threshold, the corresponding first reference position in the initial spatial matrix is set to a first preset value (for example, 1), indicating that these two devices are strongly correlated in space; when the spatial distance is greater than or equal to the distance threshold, the corresponding first reference position is set to a second preset value (for example, 0), indicating that the correlation between these two devices in space is weak. In this way, the setting of all first reference positions in the initial spatial matrix is completed, and finally the spatial correlation matrix is obtained. Similarly, when constructing the process correlation matrix based on the process flow sequence, first, the process numbers of each production device in the process flow are determined, then an initial process matrix of N×N is constructed, and the difference in process numbers between any two production devices is calculated. When the difference in process numbers is less than a preset difference threshold, an association identifier is marked at the corresponding second reference position in the initial process matrix, indicating that these two devices are closely related in the process flow; when the difference in process numbers is greater than or equal to the difference threshold, a non-association identifier is marked. Through this construction method, the obtained spatial correlation matrix and process correlation matrix can quantitatively describe the degree of correlation between devices from two dimensions of spatial distance and process sequence respectively, providing a reliable data basis for subsequent determination of associated device groups. This matrix-based expression method is not only convenient for computer processing, but also can intuitively reflect the multi-dimensional correlation relationship between devices, which helps to more accurately identify device groups that may have the risk of fault conduction.

[0024] Based on the above embodiments, as an optional embodiment, in step 102: constructing a spatial correlation matrix according to each layout position, this step may further include the following steps: Step 201: Construct an initial spatial matrix based on the total number of production devices, and determine the first reference positions corresponding to the device types of each production device in the initial spatial matrix.

[0025] Specifically, based on the equipment situation on the production line, it is first necessary to count the total number of production equipment N. For example, on a machining production line, there are a total of 10 pieces of equipment, including 3 lathes, 2 milling machines, 2 grinding machines, 2 machining centers, and 1 inspection device. Subsequently, an initial space matrix of N×N is constructed, where the rows and columns of the matrix both represent these N production equipment. In this initial space matrix, the rows and columns are respectively labeled from 1 to N to distinguish different production equipment. For each position in the matrix, its corresponding first reference position is determined. For example, the position in the i-th row and j-th column is the first reference position for the association relationship between equipment i and equipment j. In the initial stage, all first reference positions can be set to null values or default values to prepare for the subsequent setting of association relationships. This matrix construction method provides a basic framework for establishing the spatial association relationship between equipment in the future.

[0026] Step 202: Calculate the spatial distance between any two production equipment based on each layout position.

[0027] Specifically, after determining the structure of the initial space matrix, it is necessary to calculate the actual spatial distance between any two production equipment. Based on the obtained layout position coordinates (x, y, z) of each production equipment, a spatial distance calculation formula is used to calculate the distance between equipment. Specifically, for the coordinates (xi, yi, zi) of equipment i and the coordinates (xj, yj, zj) of equipment j, the spatial distance between them can be calculated by the Euclidean distance formula in three-dimensional space: distance = √[(xi - xj)² + (yi - yj)² + (zi - zj)²]. For example, if the coordinates of equipment 1 are (0, 0, 0) and the coordinates of equipment 2 are (3, 4, 0), then the spatial distance between them is 5 meters. In this way, the spatial distance between any two pieces of equipment on the production line can be accurately calculated, providing a quantitative basis for subsequent judgment of the spatial correlation between equipment.

[0028] Step 203: For any two production equipment, when the spatial distance is less than the distance threshold, set the corresponding first reference position in the initial space matrix to the first preset value; when the spatial distance is greater than or equal to the distance threshold, set the corresponding first reference position in the initial space matrix to the second preset value, until all first reference positions in the initial space matrix are set, obtaining a spatial association matrix.

[0029] Specifically, after calculating the spatial distance, it is necessary to determine the spatial correlation degree between each pair of devices according to a preset distance threshold (for example, 5 meters). In specific implementation, each first reference position in the initial spatial matrix is processed in sequence: when the spatial distance between the corresponding two devices is less than the distance threshold, it indicates that the two devices are relatively close in spatial position and may have an impact on each other. At this time, the corresponding first reference position is set to a first preset value (for example, 1); when the spatial distance is greater than or equal to the distance threshold, it indicates that the two devices are far apart in spatial position and have little impact on each other. At this time, the corresponding first reference position is set to a second preset value (for example, 0). In this way, the setting of all first reference positions in the initial spatial matrix is gradually completed, and finally a complete spatial correlation matrix is formed. For example, in a 5×5 spatial correlation matrix, if the spatial distance between device 1 and device 2 is 3 meters (less than the threshold of 5 meters), the positions in the first row and second column and the second row and first column of the matrix will both be set to 1, indicating that these two devices have spatial correlation. This matrix form can not only intuitively display the spatial correlation relationship between devices, but also facilitate subsequent data processing and analysis, providing a basis for identifying potential fault conduction paths.

[0030] Based on the above embodiments, as an optional embodiment, in step 102: constructing a process correlation matrix according to the sequence of each process flow, this step may further include the following steps: Step 204: Based on the sequence of each process flow, determine the process numbers of each production device in the process flow.

[0031] Specifically, to accurately describe the sequence relationship of production devices in the process flow, it is necessary to first assign process numbers to each device according to the process flow sequence. In specific implementation, the devices are numbered in sequence from the starting process according to the process flow sequence of product processing. For example, on a mechanical part processing production line, rough machining is first performed on lathe A (numbered 1), then the plane is machined on milling machine B (numbered 2), then finish machining is performed on grinder C (numbered 3), and finally quality inspection is performed on inspection device D (numbered 4). Through this numbering method, the processing sequence of each production device in the entire process flow can be clearly expressed, providing a basis for subsequent analysis of the process correlation between devices.

[0032] Step 205: Based on the total number of production devices, construct an initial process matrix, and determine the second reference positions corresponding to each process number in the initial process matrix; calculate the difference in process numbers between any two production devices.

[0033] Specifically, after completing the operation number assignment, based on the total number of production equipment N (for example, N = 4 in the case), an N×N initial process matrix is constructed. In this initial process matrix, the rows and columns correspond to each production equipment respectively, and each position in the matrix is the second reference position of the process association relationship between two equipment. Then, calculate the difference in operation numbers between any two production equipment, and this difference reflects the interval degree of the two equipment in the process flow. For example, for lathe A (number 1) and grinder C (number 3) in the above case, the difference in operation numbers between them is |3 - 1| = 2; while the difference in operation numbers between lathe A (number 1) and inspection equipment D (number 4) is |4 - 1| = 3. This way of calculating the difference can quantitatively represent the relative position relationship of any two pieces of equipment in the process flow.

[0034] Step 206: For any two production equipment, when the difference in operation numbers is less than the difference threshold, mark the association identifier at the corresponding second reference position in the initial process matrix; when the difference in operation numbers is greater than or equal to the difference threshold, mark the non - association identifier at the corresponding second reference position in the initial process matrix until all the second reference positions in the initial process matrix are marked, obtaining the process association matrix.

[0035] Specifically, based on a preset difference threshold (for example, set to 2), judge the process association degree between each pair of equipment. In specific implementation, process each second reference position in the initial process matrix in turn: when the difference in operation numbers between two equipment is less than the difference threshold, it indicates that these two equipment are closely related in the process flow and may have a process - related impact. At this time, mark the association identifier (for example, 1) at the corresponding second reference position; when the difference in operation numbers is greater than or equal to the difference threshold, it indicates that these two equipment have a large interval in the process flow and the process association is weak. At this time, mark the non - association identifier (for example, 0). In the above case, the difference in operation numbers between lathe A and milling machine B is 1 (less than the threshold 2), so the corresponding position in the process association matrix is marked as 1; while the difference in operation numbers between lathe A and inspection equipment D is 3 (greater than the threshold 2), and the corresponding position is marked as 0. In this way, all the second reference positions in the initial process matrix are marked, and finally a complete process association matrix is formed. This association matrix based on the difference in operation numbers can not only intuitively reflect the process association degree between equipment, but also provide an important basis for subsequent analysis of process - related fault conduction. For example, when a certain piece of equipment fails, the subsequent process equipment that may be affected can be quickly identified through the process association matrix, so as to take preventive measures in time.

[0036] Step 103: Based on the spatial association matrix and the process association matrix, determine multiple associated equipment groups, and obtain the vibration data, temperature data, and current data of each production equipment in each associated equipment group.

[0037] Among them, the associated device group in the embodiments of the present application refers to a set of devices with a close association relationship determined by analyzing the spatial association matrix and the process association matrix.

[0038] In the embodiments of the present application, vibration data refers to vibration-related parameters generated by production equipment during operation, mainly including: time-series data such as the vibration frequency, vibration amplitude, and vibration acceleration of each key component of the equipment (such as bearings, spindles, machine frames, etc.). For example, for a lathe, its vibration data may include parameters such as the radial vibration frequency of the spindle, the axial vibration amplitude of the bearing, and the vibration acceleration of the machine tool base.

[0039] In the embodiments of the present application, temperature data refers to the temperature change conditions of each key part of production equipment during operation, mainly including: time-series data such as the spindle temperature, bearing temperature, motor temperature, and processing area temperature of the equipment. For example, for a milling machine, its temperature data may include parameters such as the temperature rise value of the spindle box, the real-time temperature of the bearing seat, and the temperature change in the cutting area.

[0040] In the embodiments of the present application, current data refers to the current parameters of each electrical component of production equipment during operation, mainly including: time-series data such as the operating current of the spindle motor, the current value of the feed motor, and the working current of the control system. For example, for a machining center, its current data may include parameters such as the real-time current value of the spindle motor, the current change of the X / Y / Z axis feed motor, and the working current of the cooling system.

[0041] Specifically, after obtaining the spatial association matrix and the process association matrix, it is necessary to determine the equipment groups with close association relationships through matrix analysis and collect the key operation data of these equipment groups for subsequent fault conduction analysis. In specific implementation, first, the spatial association matrix and the process association matrix are comprehensively analyzed. When the value at the corresponding position of two devices in the spatial association matrix is the first preset value (e.g., 1), or is marked with an association identifier (e.g., 1) at the corresponding position in the process association matrix, then these two devices are classified into the same associated equipment group. For example, on a machining production line, if the spatial distance between lathe A and milling machine B is less than the distance threshold, or the difference in their process numbers is less than the difference threshold, then these two devices will be classified into the same associated equipment group. In this way, multiple equipment groups containing mutually associated devices can be formed. The devices in these equipment groups are either close in spatial position or closely connected in the process flow. For each determined associated equipment group, the operation parameters such as vibration data (such as equipment vibration frequency, vibration amplitude), temperature data (such as temperature changes of key components), and current data (such as motor operating current) of each production device in it are collected respectively. For example, for the associated equipment group where lathe A and milling machine B are located, it is necessary to simultaneously monitor parameters such as the bearing vibration frequency, spindle temperature, and motor current of these two devices. This equipment grouping method based on association and comprehensive data collection strategy can more specifically monitor the equipment groups that may have the risk of fault conduction, provide complete data support for subsequent extraction of fault conduction characteristics and early warning, and thus improve the accuracy and timeliness of fault early warning.

[0042] Based on the above embodiments, as an alternative embodiment, in step 102: determining multiple associated equipment groups based on the spatial association matrix and the process association matrix, this step may further include the following steps: Step 301: Obtain the spatial association weight of the first preset value in the spatial association matrix and the process association weight of the association identifier in the process association matrix.

[0043] Specifically, to comprehensively consider the influence of spatial association and process association on the degree of equipment association, it is necessary to first determine the corresponding weight coefficients. For the first preset value in the spatial association matrix (e.g., the position with a value of 1), set its spatial association weight as w1 (e.g., 0.4); for the association identifier in the process association matrix (e.g., the position with a value of 1), set its process association weight as w2 (e.g., 0.6). This weight setting method reflects that in actual production, the relevance of the process flow may have a more important influence than the spatial position association. These weight values can be set based on historical data and can be dynamically adjusted according to the actual application effect.

[0044] Step 302: Perform weighted summation on the spatial association matrix and the process association matrix according to the spatial association weight and the process association weight to obtain a weighted association matrix.

[0045] Specifically, after obtaining the weight coefficients, it is necessary to perform weighted combination on the spatial association matrix and the process association matrix to obtain a weighted association matrix that comprehensively reflects the degree of equipment association. For any two devices i and j, the corresponding element value in the weighted association matrix can be calculated by the following formula: weighted value = w1 × spatial association matrix (i, j) + w2 × process association matrix (i, j). For example, if the values of device 1 and device 2 in the spatial association matrix are both 1, and the values in the process association matrix are also both 1, then the corresponding element value in the weighted association matrix is 0.4×1 + 0.6×1 = 1. Through this weighted calculation method, a new N×N matrix can be obtained, where the element values range from 0 to 1, and the larger the value, the higher the comprehensive association degree between the two devices.

[0046] Step 303: Determine the association threshold based on the element values corresponding to each production device in the weighted association matrix; when the element values corresponding to any two production devices in the weighted association matrix are greater than the association threshold, divide any two production devices into the same associated device group.

[0047] Specifically, after obtaining the weighted association matrix, it is necessary to determine a suitable association threshold based on the distribution of element values in the matrix for dividing the associated device groups. The distribution characteristics of each element value in the weighted association matrix can be statistically analyzed, and an appropriate threshold (such as 0.5) can be selected. When the element values corresponding to any two devices i and j in the weighted association matrix are greater than this association threshold, it indicates that these two devices have a strong association both in terms of spatial position and process flow. Therefore, they are divided into the same associated device group. For example, if the weighted association value of device 1 and device 2 is 0.7 (greater than the threshold 0.5), the weighted association value of device 2 and device 3 is 0.6 (greater than the threshold 0.5), and the weighted association value of device 1 and device 3 is 0.3 (less than the threshold 0.5), then device 1, device 2, and device 3 can be divided into the same associated device group because they form an indirect association relationship through device 2. This grouping method based on weighted association values can more accurately identify the set of devices with close association relationships, provide a more reliable basis for subsequent fault conduction analysis, and at the same time avoid the grouping deviation that may be caused by only considering a single association factor.

[0048] Based on the above embodiments, as an alternative embodiment, in step 303: determining the association threshold based on the element values corresponding to each production device in the weighted association matrix, this step may further include the following steps: Step 313: Based on the element values corresponding to each production device, construct a numerical distribution curve.

[0049] Specifically, to determine the correlation threshold, it is necessary to first analyze the distribution law of the element values in the weighted correlation matrix. In specific implementation, all non-zero element values are extracted from the weighted correlation matrix and sorted in ascending order according to the numerical size. Then, with the element value as the ordinate and the corresponding serial number as the abscissa, a numerical distribution curve is constructed. For example, on a production line with 10 devices, the weighted correlation matrix may contain 45 non-zero element values (because the matrix is symmetric and diagonal elements are usually not considered). After sorting these values from small to large, an increasing curve can be obtained. This curve can intuitively reflect the overall distribution characteristics of the correlation degree between devices, and the position where the slope changes significantly often represents the natural demarcation point of the correlation degree.

[0050] Step 323: Obtain the inflection point value in the numerical distribution curve and use the inflection point value as the correlation threshold.

[0051] Specifically, based on the constructed numerical distribution curve, it is necessary to find the critical point that can effectively distinguish high correlation degree and low correlation degree. In specific implementation, by analyzing the slope change of the numerical distribution curve, the slope change rate between adjacent points on the curve is calculated. When the slope change rate reaches the maximum value, the corresponding numerical value is the inflection point value, and this inflection point value is used as the correlation threshold. For example, if it is found that the slope changes most significantly at 0.45 on the numerical distribution curve, it means that at this position, the correlation degree between devices has an obvious jump. At this time, 0.45 can be determined as the correlation threshold. This method of determining the threshold based on the data distribution characteristics can reflect the natural demarcation point of the correlation relationship between devices. When the threshold is determined to be 0.45, device pairs with weighted correlation values greater than 0.45 will be considered to have significant correlation characteristics and should be classified into the same associated device group, while device pairs with correlation values less than 0.45 can be classified into different associated device groups, thus realizing a more reasonable device grouping.

[0052] Step 104: For each associated device group, combine the vibration data, temperature data, and current data of each production device to determine the device state value of the associated device group.

[0053] Among them, the device state value in the embodiments of the present application refers to the state evaluation index obtained by comprehensively analyzing the operation parameters of each production device in the associated device group.

[0054] Specifically, after determining the associated equipment group, to evaluate the overall operating status of each equipment group, it is necessary to comprehensively analyze the vibration data, temperature data, and current data of each production equipment within the group, so as to obtain an equipment status value that reflects the operating condition of the entire equipment group. During specific implementation, first, the operating parameters of each production equipment are normalized, and the vibration data (such as spindle vibration frequency, bearing vibration amplitude, etc.), temperature data (such as spindle temperature, bearing temperature, etc.), and current data (such as spindle motor current, feed motor current, etc.) are uniformly mapped to the interval from 0 to 1. Then, based on these normalized data, the comprehensive status index of each equipment is calculated by means of weighted average. For example, for a lathe in the equipment group, the normalized vibration index, temperature index, and current index can be respectively assigned weights (such as 0.4, 0.3, 0.3), and the status index of the equipment is obtained by weighted summation. Finally, the status indexes of all equipment within the associated equipment group are weighted averaged again to obtain the equipment status value of the entire equipment group. Among them, different weights can be set according to the importance of each equipment in the process flow. This multi-level weighted calculation method not only considers the influence of various operating parameters of a single equipment but also reflects the contribution degree of different equipment to the status of the entire equipment group, thus being able to more comprehensively and accurately reflect the overall operating condition of the associated equipment group.

[0055] Based on the above embodiments, as an alternative embodiment, in step 104: Combining the vibration data, temperature data, and current data of each production equipment to determine the equipment status value of the associated equipment group, this step may further include the following steps: Step 401: For each production equipment, based on the vibration data, determine the vibration frequency within a preset time window, based on the temperature data, determine the temperature change rate within a preset time window, and based on the current data, determine the current change rate within a preset time window.

[0056] Specifically, to accurately evaluate the operating status of each production equipment, it is necessary to analyze the key operating parameters of the equipment within a preset time window (such as 10 minutes). First, based on the vibration data collected by the vibration sensor, the main vibration frequency components of the equipment within this time window are calculated through fast Fourier transform. For example, the fundamental frequency (such as 50 Hz) of the spindle and its harmonic frequencies can be identified. Secondly, using the temperature data collected by the temperature sensor, the change rate of temperature with time is calculated, that is, the speed of temperature rise or fall, which can be calculated by the formula (T2 - T1) / Δt, where T2 and T1 are the temperature values at the end and start of the time window respectively, and Δt is the length of the time window. Similarly, based on the current data collected by the current sensor, the change rate of current (I2 - I1) / Δt is calculated, where I2 and I1 are the current values at the end and start of the time window respectively. The calculation results of these parameters can reflect the performance change trend of the equipment during dynamic operation.

[0057] Step 402: Perform weighted calculations on the vibration frequency, temperature change rate, and current change rate of each production device to obtain the device status value of the associated device group.

[0058] Specifically, after obtaining each parameter, a reasonable weighted calculation method is required to synthesize these parameters with different dimensions into a unified state evaluation value. First, normalize the vibration frequency, temperature change rate, and current change rate, and map them to the interval of 0 - 1. For example, assume that the vibration frequency of a certain device is 45 Hz (the normal range is 40 - 60 Hz), and its normalized value can be set to 0.8; the temperature change rate is 2 °C / min (the normal range is 0 - 5 °C / min), and the normalized value is 0.6; the current change rate is 0.5 A / min (the normal range is 0 - 2 A / min), and the normalized value is 0.75. Then, according to the influence degree of each parameter on the device status, assign corresponding weight coefficients respectively (for example, the weight of the vibration frequency is 0.4, the weight of the temperature change rate is 0.3, and the weight of the current change rate is 0.3). By the method of weighted summation, the status value of this device is calculated as 0.4×0.8 + 0.3×0.6 + 0.3×0.75 = 0.725. Finally, perform weighted averaging on the status values of all devices in the associated device group again, and the weight of each device can be determined according to its importance in the production process, so as to obtain the device status value of the entire associated device group. This multi-level weighted calculation method not only considers the importance differences of different operating parameters but also reflects the contribution degree of each device to the overall status of the device group, and can more accurately reflect the operating conditions of the associated device group.

[0059] Step 105: When the device status value of any associated device group exceeds the standard status value range, generate a warning message for the corresponding associated device group.

[0060] Among them, the standard status value range refers to a normal operating interval determined based on the device historical operation data and technical specifications in the embodiments of the present application, and is used to judge whether the operating status of the associated device group is at a normal level. This range is usually expressed as an interval value, such as [0.6, 0.8], where 0.6 is the lower limit value and 0.8 is the upper limit value. When the device status value of the associated device group is maintained within this range, it indicates that the device group is in a normal operating state; if it exceeds this range, it indicates that the device group may have abnormal or failure risks.

[0061] The warning information in the embodiments of the present application refers to the warning information automatically generated by the system when the device status value of the associated device group exceeds the standard status value range. The warning information includes the following key contents: the unique identifier of the associated device group (such as the device group number), the current device status value, the specific situation of exceeding the range (whether it is lower than the lower limit or higher than the upper limit), the key operating parameters of each production device in the group (including vibration frequency, temperature change rate, current change rate, etc.), as well as possible abnormal reasons and recommended maintenance measures.

[0062] Specifically, to detect and prevent equipment failures in a timely manner, it is necessary to monitor the operating status of the associated device group in real time. First, it is necessary to set the standard status value range, which can be determined based on historical operation data and equipment technical specifications. For example, the range from 0.6 to 0.8 is set as the standard status value range. Then, the device status values of each associated device group are monitored in real time, and the currently calculated device status value is compared with the preset standard status value range. When it is detected that the device status value of a certain associated device group exceeds the standard range (for example, lower than 0.6 or higher than 0.8), the warning mechanism is triggered, and the system automatically generates the warning information of this associated device group. The warning information includes the number of the associated device group, the current device status value, the specific situation of exceeding the range (higher or lower), and the key parameters of each production device in the group (vibration frequency, temperature change rate, current change rate), etc. For example, when the device status value of an associated device group composed of a lathe and a milling machine drops to 0.45, the system will generate a warning information including "The status of device group A001 is abnormal, the current status value is 0.45, lower than the standard lower limit of 0.6, it is recommended to check the vibration frequency of the lathe (the current value is 58 Hz) and the temperature change rate of the milling machine (the current value is 4.2 °C / min)". This warning mechanism based on the overall status of the device group can not only detect potential equipment failures in a timely manner, but also help determine the propagation path and influence range of the failure through correlation analysis, so as to provide more targeted maintenance suggestions for equipment maintenance personnel and effectively prevent the occurrence of chain failures.

[0063] On the basis of the above embodiments, as an alternative embodiment, in step 105: after generating the warning information of the corresponding associated device group, the following steps may further be included: Step 106: Obtain the historical warning records of the associated device group; based on the historical warning records, determine the warning frequency of the associated device group.

[0064] Specifically, to analyze the operation status trend of the associated equipment group and take timely maintenance measures, it is necessary to statistically analyze the early warning situations of the equipment group. The system first reads the historical early warning records of the associated equipment group in the past period (such as the recent 30 days) from the database. These records contain information such as the time of each early warning, the equipment status values at the time of triggering the early warning, and specific abnormal parameters. By analyzing these historical early warning records, calculate the number of times the equipment group triggers early warnings within this time period, that is, the early warning frequency. For example, if an associated equipment group triggered 15 early warnings in the past 30 days, its early warning frequency is 15 times / month.

[0065] Step 107: When the early warning frequency of the associated equipment group is greater than the frequency threshold, increase the data acquisition frequency of the associated equipment group and send maintenance suggestion information of the associated equipment group to the target department.

[0066] Specifically, after determining the early warning frequency of the associated equipment group, the system compares this early warning frequency with a preset frequency threshold (such as 10 times / month). When the early warning frequency exceeds the frequency threshold, it indicates that there may be relatively serious potential fault hazards or performance degradation trends in this equipment group. At this time, the system will take two measures: First, increase the data acquisition frequency of this associated equipment group. For example, increase the original frequency of collecting data once per minute to once every 30 seconds. This can obtain more detailed equipment operation data and help analyze the cause of the fault more accurately. Second, the system will automatically generate and send maintenance suggestion information to the target department (such as the equipment maintenance department). This suggestion information includes the basic information of the associated equipment group (such as equipment group number, composition of equipment within the group), early warning frequency statistical data (such as the distribution of early warning times in the recent 30 days), abnormal parameter analysis (such as which parameters often exceed the limit and their change trends), and recommended maintenance plans (such as recommended equipment components for maintenance and maintenance cycles). For example: "The early warning frequency of equipment group A001 in the recent 30 days reached 15 times, exceeding the threshold of 10 times. It is recommended to conduct a comprehensive inspection on the lathe spindle and the milling machine cooling system, and the recommended maintenance cycle is no more than 7 days". In this way, not only can the monitoring intensity of high-risk equipment groups be strengthened, but also it can guide maintenance personnel to carry out maintenance work targeted, thereby improving the reliability and production efficiency of the equipment.

[0067] Refer to Figure 2 , a big data processing and analysis system provided by an embodiment of the present application. The system includes: a data acquisition module, an association matrix construction module, an equipment status value determination module, and an early warning module, where: The data acquisition module is used to obtain the layout positions and technological process sequences of multiple production equipment; The association matrix construction module is used to construct a spatial association matrix according to each layout position and construct a technological association matrix according to each technological process sequence; The device status value determination module is used to determine multiple associated device groups based on the spatial association matrix and the process association matrix, and obtain the vibration data, temperature data, and current data of each production device in each associated device group; for each associated device group, combine the vibration data, temperature data, and current data of each production device to determine the device status value of the associated device group. The warning module is used to generate a warning message for the corresponding associated device group when the device status value of any associated device group exceeds the standard status value range.

[0068] Based on the above embodiments, the association matrix construction module is further used to construct an initial spatial matrix based on the total number of production devices, and determine the first reference position corresponding to the device type of each production device in the initial spatial matrix; calculate the spatial distance between any two production devices based on each layout position; for any two production devices, when the spatial distance is less than the distance threshold, set the corresponding first reference position in the initial spatial matrix to the first preset value, and when the spatial distance is greater than or equal to the distance threshold, set the corresponding first reference position in the initial spatial matrix to the second preset value until all the first reference positions in the initial spatial matrix are set to obtain the spatial association matrix.

[0069] Based on the above embodiments, the association matrix construction module is further used to determine the process number of each production device in the process flow based on the sequence of each process flow; construct an initial process matrix based on the total number of production devices, and determine the second reference position corresponding to each process number in the initial process matrix; calculate the difference in process numbers between any two production devices; for any two production devices, when the difference in process numbers is less than the difference threshold, mark the associated identifier at the corresponding second reference position in the initial process matrix, and when the difference in process numbers is greater than or equal to the difference threshold, mark the non-associated identifier at the corresponding second reference position in the initial process matrix until all the second reference positions in the initial process matrix are marked to obtain the process association matrix.

[0070] Based on the above embodiments, the device status value determination module is further used to obtain the spatial association weight of the first preset value in the spatial association matrix, and the process association weight of the associated identifier in the process association matrix; perform weighted summation on the spatial association matrix and the process association matrix according to the spatial association weight and the process association weight to obtain a weighted association matrix; determine the association threshold based on the element values corresponding to each production device in the weighted association matrix; when the element values corresponding to any two production devices in the weighted association matrix are greater than the association threshold, divide the two production devices into the same associated device group.

[0071] Based on the above embodiments, the device status value determination module is further configured to construct a numerical distribution curve based on the element values corresponding to each production device; obtain the inflection point value in the numerical distribution curve, and use the inflection point value as the correlation threshold.

[0072] Based on the above embodiments, for each production device, the device status value determination module is further configured to determine the vibration frequency within a preset time window based on the vibration data, determine the temperature change rate within the preset time window based on the temperature data, and determine the current change rate within the preset time window based on the current data; perform weighted calculation on the vibration frequency, temperature change rate, and current change rate of each production device to obtain the device status value of the associated device group.

[0073] Based on the above embodiments, the early warning module is further configured to obtain the historical early warning records of the associated device group; determine the early warning frequency of the associated device group based on the historical early warning records; when the early warning frequency of the associated device group is greater than the frequency threshold, increase the data collection frequency of the associated device group, and send the maintenance suggestion information of the associated device group to the target department.

[0074] It should be noted that when the device provided in the above embodiments implements its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to 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. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be elaborated here.

[0075] This application also discloses an electronic device. Refer to Figure 3 , Figure 3 which is a schematic structural diagram of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0076] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0077] Among them, the user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0078] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0079] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server using various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface graphics, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0080] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a big data processing and analysis method.

[0081] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 301 can be used to call an application program stored in the memory 305 for a big data processing and analysis method. When executed by one or more processors 301, the electronic device 300 executes the method in one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be adopted in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0082] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In several implementation manners provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0084] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0086] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0087] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other implementation manners of the present disclosure after considering the specification and the practice of the disclosure.

[0088] This application aims to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary.

Claims

1. A method for processing and analyzing big data, characterized in that: include: Obtain the layout location and process sequence of multiple production equipment; According to each of the layout positions, a spatial correlation matrix is ​​constructed, and according to each of the process flow sequences, a process correlation matrix is ​​constructed; Based on the spatial association matrix and the process association matrix, a plurality of associated equipment groups are determined, and vibration data, temperature data, and current data of each production equipment in each of the associated equipment groups are acquired; For each of the associated equipment groups, combining the vibration data, temperature data and current data of each of the production equipment, determining the equipment status value of the associated equipment group; When the device status value of any associated device group exceeds the standard status value range, an early warning message of the corresponding associated device group is generated.

2. The big data processing and analysis method according to claim 1, characterized in that: The step of constructing a spatial association matrix according to each of the layout positions includes: Based on the total number of devices of each of the production devices, an initial space matrix is ​​constructed, and a first reference position corresponding to a device type of each of the production devices is determined in the initial space matrix; Based on each of the layout positions, calculating the spatial distance between any two production equipments; For any two production devices, when the spatial distance is less than the distance threshold, the corresponding first reference position in the initial spatial matrix is ​​set to a first preset value; when the spatial distance is greater than or equal to the distance threshold, the corresponding first reference position in the initial spatial matrix is ​​set to a second preset value, until the setting of all first reference positions in the initial spatial matrix is ​​completed to obtain a spatial association matrix.

3. The big data processing and analysis method according to claim 1, characterized in that: According to the sequence of each process flow, a process correlation matrix is ​​constructed, including: Based on the sequence of each process flow, determining the process number of each production equipment in the process flow; Based on the total number of equipment of each of the production equipment, an initial process matrix is ​​constructed, and a second reference position corresponding to each of the process numbers is determined in the initial process matrix; Calculate the difference in process numbers between any two production equipment; For any two production equipment, when the difference in process numbers is less than a difference threshold, the corresponding second reference positions in the initial process matrix are marked with an associated identifier; when the difference in process numbers is greater than or equal to the difference threshold, the corresponding second reference positions in the initial process matrix are marked with an unassociated identifier, until all second reference positions in the initial process matrix are marked to obtain a process association matrix.

4. The big data processing and analysis method according to claim 1, characterized in that: The step of determining a plurality of associated equipment groups based on the spatial association matrix and the process association matrix comprises: Obtaining a spatial association weight of a first preset value in the spatial association matrix and a process association weight of an association identifier in the process association matrix; Performing weighted summation on the spatial association matrix and the process association matrix according to the spatial association weight and the process association weight to obtain a weighted association matrix; Determining an association threshold based on the element value corresponding to each production equipment in the weighted association matrix; When the element values ​​corresponding to any two production devices in the weighted association matrix are greater than the association threshold, the any two production devices are divided into the same associated device group.

5. The big data processing and analysis method according to claim 4, characterized in that: The determining of the association threshold based on the element value corresponding to each production equipment in the weighted association matrix includes: Constructing a numerical distribution curve based on the element values ​​corresponding to each of the production equipment; An inflection point value in the numerical distribution curve is obtained, and the inflection point value is used as a correlation threshold.

6. The big data processing and analysis method according to claim 1, characterized in that: The combining the vibration data, the temperature data and the current data of each of the production equipment to determine the equipment status value of the associated equipment group includes: For each of the production equipment, based on the vibration data, determine the vibration frequency within a preset time window, based on the temperature data, determine the temperature change rate within the preset time window, and based on the current data, determine the current change rate within the preset time window; The vibration frequency, temperature change rate and current change rate of each of the production equipment are weightedly calculated to obtain the equipment status value of the associated equipment group.

7. The big data processing and analysis method according to claim 1, characterized in that: After the warning information of the corresponding associated device group is generated, the method further includes: Obtaining historical warning records of the associated device group; Determining the warning frequency of the associated device group based on the historical warning records; When the warning frequency of the associated equipment group is greater than the frequency threshold, the data collection frequency of the associated equipment group is increased, and maintenance suggestion information of the associated equipment group is sent to the target department.

8. A big data processing and analysis system, characterized in that: The system comprises: A data acquisition module is used to obtain the layout positions and process flow sequences of multiple production equipment; An association matrix construction module is used to construct a spatial association matrix according to each of the layout positions, and to construct a process association matrix according to each of the process flow sequences; An equipment status value determination module is used to determine a plurality of associated equipment groups based on the spatial association matrix and the process association matrix, and obtain vibration data, temperature data and current data of each production equipment in each of the associated equipment groups; for each of the associated equipment groups, determine the equipment status value of the associated equipment group in combination with the vibration data, temperature data and current data of each of the production equipment; The early warning module is used to generate early warning information of the corresponding associated device group when the device status value of any associated device group exceeds the standard status value range.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the big data processing and analysis method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the big data processing and analysis method as described in any one of claims 1 to 7 is executed.

Images