A method and system for intelligent monitoring of production environment in a digital workshop

Abstract

The present invention relates to the field of intelligent monitoring technology, and specifically discloses a digital workshop production environment intelligent monitoring method and system, including: monitoring the operating status of production equipment, obtaining abnormal operating data of the production equipment, and calculating an abnormal coefficient based on the abnormal operating data; based on the abnormal coefficient, evaluating the operating status of the production equipment, and generating a status evaluation signal; also including: monitoring the production environment during the operation of the production equipment, specifically: based on the past operating data of the production equipment, evaluating the correlation between the production environment and the operating status of the production equipment, and generating a correlation evaluation signal; based on the high correlation signal, analyzing different production environments in each monitoring cycle during the abnormal operation of the equipment, and evaluating the priority monitoring environment of each monitoring cycle, so as to facilitate the subsequent production equipment in the operation process, in each monitoring cycle to focus on the priority detection environment, thereby improving the monitoring efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method and system for a digital workshop production environment. Background Art

[0002] The digital workshop is a digital production workshop built on the basis of modern information, network, database, automatic identification and other technologies, through the integration of intelligence, digitization, MES system informatization and other means, to precisely manage production resources, production equipment and production processes.

[0003] However, existing technologies usually rely on manual inspections or regular maintenance to detect abnormal conditions of production equipment, resulting in the failure to promptly detect and handle problems, thereby affecting the stability and efficiency of the production process. In addition, existing technologies often only focus on the monitoring of a single parameter, ignoring the impact of different environmental factors on production equipment at different stages of the production process. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for intelligently monitoring a production environment of a digital workshop, so as to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for intelligently monitoring a production environment of a digital workshop, comprising:

[0007] Step 1: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data;

[0008] The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality;

[0009] Step 2: Based on the abnormality coefficient, the operating status of the production equipment is evaluated to determine whether the operation of the production equipment is in an abnormal state, and a status evaluation signal is generated;

[0010] The status assessment signal includes: a normal operation status signal and an abnormal operation status signal;

[0011] It also includes monitoring the production environment during the operation of production equipment, specifically:

[0012] S1: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operation status of the production equipment is evaluated, and a correlation evaluation signal is generated;

[0013] The correlation evaluation signals include: high correlation signal and low correlation signal;

[0014] S2: Based on the high correlation signal, analyze the different production environments in each monitoring cycle during the abnormal operation of the equipment, and evaluate the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of the subsequent production equipment and improve the monitoring efficiency.

[0015] As a further solution of the present invention: the process of obtaining the abnormal coefficient is:

[0016] During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the real-time operation parameters of the production equipment are obtained, and based on the real-time operation parameters of the production equipment, the cycle offset value of the production equipment within the monitoring cycle is obtained;

[0017] Based on the periodic deviation values ​​of each monitoring period, the total parameter deviation value and the parameter abnormality occurrence characterization value are calculated respectively;

[0018] By formula: Calculate the anomaly coefficient YC, where a 1 、a 2 are preset proportional factors, and are all greater than 0, PY is the total value of parameter offset, and FS is the characterization value of parameter abnormality.

[0019] As a further solution of the present invention: the process of obtaining the periodic offset value is:

[0020] Based on the real-time operation parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time operation parameters as the Y-axis to draw a real-time operation parameter curve and a preset operation parameter curve;

[0021] The lengths of the real-time operating parameter curve and the preset operating parameter curve within the monitoring period are respectively extracted to obtain the real-time operating parameter characterization value and the preset operating parameter characterization value;

[0022] The difference between the real-time operating parameter characterization value and the preset operating parameter characterization value is calculated, and the absolute value is taken to obtain the operating parameter offset characterization value, and then the operating parameter offset characterization value is calculated to be ratioed with the preset operating parameter characterization value to obtain the period offset value.

[0023] As a further solution of the present invention: the process of obtaining the abnormal operation data is as follows:

[0024] Preset a cycle offset threshold, and compare and analyze the cycle offset value of each monitoring cycle with the cycle offset threshold;

[0025] If the periodic offset value is less than or equal to the periodic offset threshold, a parameter offset normal signal is generated;

[0026] If the cycle offset value is greater than the cycle offset threshold, a parameter offset abnormality signal is generated, and the corresponding monitoring period is marked as a parameter abnormality period;

[0027] Extract the periodic offset values ​​of all parameter abnormal periods, and perform sum calculation to obtain the total parameter offset value;

[0028] Extract the number of all abnormal cycles to obtain the total number of abnormal cycles, and calculate the ratio of the total number of abnormal cycles to the total number of monitoring cycles to obtain the abnormal cycle number ratio;

[0029] At the same time, all adjacent abnormal cycles are merged to obtain one or more abnormal events, and the total number of abnormal events is calculated to be a ratio of the total number of abnormal cycles to obtain the abnormal event number ratio;

[0030] Then, the ratio of the number of abnormal cycles and the ratio of the number of abnormal events are summed up and calculated to obtain the parameter abnormality occurrence characterization value.

[0031] As a further solution of the present invention: the process of generating the state evaluation signal is:

[0032] Preset an abnormal coefficient threshold, and compare and analyze the abnormal coefficient with the abnormal coefficient threshold;

[0033] If the abnormal coefficient is less than or equal to the abnormal coefficient threshold, a normal operation status signal is generated;

[0034] If the abnormal coefficient is greater than the abnormal coefficient threshold, an operation status abnormal signal is generated.

[0035] As a further solution of the present invention: the process of generating the relevance evaluation signal is:

[0036] Extract the production equipment operation process that generates abnormal operation status signals from the past operation data of the production equipment, and mark it as the abnormal operation process of the equipment;

[0037] Based on the abnormal operation process of the equipment, obtain the environmental offset value of the production environment in each monitoring cycle and the cycle offset value of the production equipment;

[0038] Based on the environmental offset value and cycle offset value of each monitoring period, the correlation coefficient between the production environment and the operating status of the production equipment is calculated;

[0039] Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold;

[0040] If the correlation coefficient is less than or equal to the correlation coefficient threshold, a low correlation signal is generated;

[0041] If the correlation coefficient is greater than the correlation coefficient threshold, a high correlation signal is generated.

[0042] As a further solution of the present invention: the process of obtaining the environmental offset value is:

[0043] Obtain the real-time production environment value during the abnormal operation of the equipment, and establish a two-dimensional coordinate system with time as the X-axis and the real-time production environment value as the Y-axis to draw a real-time production environment value curve and a preset production environment value curve;

[0044] Respectively extract the lengths of the real-time production environment value curve and the preset production environment value curve within the monitoring period to obtain the real-time production environment characterization value and the preset production environment characterization value;

[0045] The difference between the real-time production environment characterization value and the preset production environment characterization value is calculated, and the absolute value is taken to obtain the environment offset characterization value, and then the ratio of the environment offset characterization value to the preset production environment characterization value is calculated to obtain the environment offset value.

[0046] As a further solution of the present invention: the process of obtaining the correlation coefficient is:

[0047] The environmental offset values ​​of all monitoring periods are calculated separately from the period offset values, and the absolute values ​​are taken to obtain the correlation difference values ​​of each monitoring period;

[0048] By formula: Calculate the period correlation value G between the environmental offset value and the period offset value of each monitoring period respectively, where Δmin is the minimum value of the correlation difference in each monitoring period, Δmax is the maximum value of the correlation difference in each monitoring period, ΔJ is the correlation difference, ρ is the resolution coefficient, and ρ∈(0,1);

[0049] Then, the cycle correlation values ​​of all monitoring cycles in the abnormal operation process of the equipment are averaged to obtain the correlation coefficient.

[0050] As a further solution of the present invention: the process of evaluating the priority monitoring environment of each monitoring cycle is:

[0051] Based on the highly correlated signals, the linkage coefficients of different production environments in each monitoring period during the abnormal operation of all equipment are obtained;

[0052] Extract the production environment corresponding to the linkage coefficient with the highest value in the monitoring cycle, and mark it as the priority detection environment in this monitoring cycle, so that in the subsequent operation of production equipment, the priority detection environment can be focused on in each monitoring cycle to improve monitoring efficiency;

[0053] The process of obtaining the linkage coefficient is as follows:

[0054] Based on any production environment, extract the cycle correlation value of the production environment in each monitoring period during the abnormal operation of the equipment;

[0055] The cycle correlation values ​​of each corresponding monitoring period during the abnormal operation of all equipment are averaged to obtain the linkage coefficient.

[0056] In a second aspect, the present invention provides a digital workshop production environment intelligent monitoring system, the system comprising:

[0057] Data processing module: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data;

[0058] The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality;

[0059] Status evaluation module: Based on the abnormality coefficient, it evaluates the operating status of the production equipment, determines whether the operation of the production equipment is in an abnormal state, and generates a status evaluation signal;

[0060] The status assessment signal includes: a normal operation status signal and an abnormal operation status signal;

[0061] It also includes monitoring the production environment during the operation of production equipment, specifically:

[0062] Correlation evaluation module: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operating status of the production equipment is evaluated, and a correlation evaluation signal is generated;

[0063] The correlation evaluation signals include: high correlation signal and low correlation signal;

[0064] Intelligent monitoring module: Based on highly correlated signals, it analyzes the different production environments in each monitoring cycle during the abnormal operation of the equipment and evaluates the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of subsequent production equipment and improve monitoring efficiency.

[0065] Beneficial effects of the present invention:

[0066] (1) The present invention realizes intelligent evaluation of the operating status of production equipment by real-time monitoring of the operating parameters of production equipment, calculating the cycle offset value, the total value of parameter offset and the parameter abnormality occurrence characterization value, and then calculating the abnormality coefficient. The present invention can timely discover the abnormal situation of production equipment, and provide strong guarantee for the stability and efficiency of the production process. Through the preset threshold and signal generation mechanism, the present invention can automatically determine and report the operating status of the equipment, and provide decision support for production management personnel;

[0067] (2) The present invention further improves the accuracy and efficiency of the intelligent monitoring system of the digital workshop production environment by introducing the correlation evaluation between the production environment and the operating status of the production equipment, and determining the priority monitoring environment based on the correlation evaluation results. It not only helps to timely discover and deal with abnormal situations in the operation of production equipment, but also effectively guides the optimization and management of the production environment, providing strong guarantee for the stable operation and efficient production of the digital workshop. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Figure 1 is a flowchart of Embodiment 1 of the present invention;

[0070] Figure 2 is a flowchart of Embodiment 2 of the present invention;

[0071] Figure 3 It is a system block diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0072] 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.

[0073] Embodiment 1:

[0074] See also Figure 1 As shown, a method for intelligently monitoring a digital workshop production environment according to an embodiment of the present invention comprises the following steps:

[0075] Step 1: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data;

[0076] The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality;

[0077] In some implementation schemes, during the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the real-time operation parameters of the production equipment are obtained, and based on the real-time operation parameters of the production equipment, the cycle offset value of the production equipment within the monitoring period is obtained;

[0078] It should be explained that the real-time operating parameters include but are not limited to: equipment temperature, equipment pressure, equipment vibration;

[0079] It should be explained that the monitoring period can be 10 minutes or 30 minutes;

[0080] Based on the periodic deviation values ​​of each monitoring period, the total parameter deviation value and the parameter abnormality occurrence characterization value are calculated respectively;

[0081] By formula: Calculate the anomaly coefficient YC, where a 1 、a 2 is the preset proportional factor, and both are greater than 0, PY is the total value of parameter offset, and FS is the parameter abnormality characterization value;

[0082] First, specifically, the process of obtaining the period offset value is:

[0083] Based on the real-time operation parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time operation parameters as the Y-axis to draw a real-time operation parameter curve and a preset operation parameter curve;

[0084] It should be explained that the preset operating parameters are operating parameters pre-set by those skilled in the art based on the production equipment in the electronic workshop, and the value is an empirical value;

[0085] The lengths of the real-time operating parameter curve and the preset operating parameter curve within the monitoring period are respectively extracted to obtain the real-time operating parameter characterization value and the preset operating parameter characterization value;

[0086] The real-time operating parameter characterization value and the preset operating parameter characterization value are calculated for difference, and the absolute value is taken to obtain the operating parameter offset characterization value, and then the operating parameter offset characterization value is calculated for ratio with the preset operating parameter characterization value to obtain the period offset value;

[0087] It should be explained that the operating parameter offset representation value represents the difference between the real-time operating parameter representation value and the preset operating parameter representation value, that is, the operating parameter offset representation value represents the difference between the length of the real-time operating parameter curve and the preset operating parameter curve within the monitoring period, reflecting the offset between the real-time operating parameter and the preset operating parameter. The higher the value of the operating parameter offset representation value, the greater the offset between the real-time operating parameter and the preset operating parameter, or the more frequent the fluctuation of the real-time operating parameter.

[0088] Second, specifically, the process of obtaining the total value of the parameter offset is:

[0089] Preset a cycle offset threshold, and compare and analyze the cycle offset value of each monitoring cycle with the cycle offset threshold;

[0090] If the cycle offset value is less than or equal to the cycle offset threshold, it means that the real-time operating parameter corresponding to the cycle offset value in the monitoring period is less offset from the preset value, that is, a parameter offset normal signal is generated;

[0091] If the cycle offset value is greater than the cycle offset threshold, it means that the real-time operating parameter in the monitoring period corresponding to the cycle offset value is greatly offset from the preset value, that is, a parameter offset abnormality signal is generated, and the corresponding monitoring period is marked as a parameter abnormality period;

[0092] Extract the periodic offset values ​​of all parameter abnormal periods, and perform sum calculation to obtain the total parameter offset value;

[0093] It should be explained that the total parameter deviation value represents the overall fluctuation of the operating parameters of the production equipment during the monitoring period. The higher the total parameter deviation value, the greater the overall fluctuation of the operating parameters during the monitoring period, and the worse the operating status of the production equipment.

[0094] Third, specifically, the process of obtaining the parameter abnormality characterization value is as follows:

[0095] Extract the number of all abnormal cycles to obtain the total number of abnormal cycles, and calculate the ratio of the total number of abnormal cycles to the total number of monitoring cycles to obtain the abnormal cycle number ratio;

[0096] At the same time, all adjacent abnormal cycles are merged to obtain one or more abnormal events, and the total number of abnormal events is calculated to be a ratio of the total number of abnormal cycles to obtain the abnormal event number ratio;

[0097] It should be explained that the basis for merging all adjacent abnormal cycles is: based on merging any abnormal cycle with the adjacent monitoring cycle, if there is an abnormal cycle in the adjacent monitoring cycle, the abnormal cycle is merged with the adjacent abnormal cycle and marked as the first merged abnormal cycle;

[0098] According to the above method, the combined abnormal cycle is combined with the adjacent monitoring cycle. If the adjacent monitoring cycle is an abnormal cycle, the combined abnormal cycle is combined with the adjacent abnormal cycle and marked as the second combined abnormal cycle.

[0099] The above operation is repeated until there are no abnormal cycles in the monitoring cycles adjacent to the n-th combined abnormal cycle, and the n-th combined abnormal cycle is recorded as an abnormal event;

[0100] If there is no abnormal cycle in the adjacent monitoring cycles, no merging process is performed, and the abnormal cycle is recorded as an abnormal event;

[0101] It needs to be further explained that the total number of abnormal events indicates the number of events that lead to abnormal real-time operating parameters in all monitoring cycles. The larger the total number of abnormal events, the more events lead to abnormal real-time operating parameters and the worse the operating status of the production equipment.

[0102] Then the ratio of the number of abnormal cycles and the ratio of the number of abnormal events are summed up and calculated to obtain the parameter abnormality occurrence characterization value;

[0103] Step 2: Based on the abnormality coefficient, the operating status of the production equipment is evaluated to determine whether the operation of the production equipment is in an abnormal state, and a status evaluation signal is generated;

[0104] The status assessment signal includes: a normal operation status signal and an abnormal operation status signal;

[0105] In some implementation schemes, an abnormal coefficient threshold is preset, and the abnormal coefficient is compared and analyzed with the abnormal coefficient threshold;

[0106] If the abnormal coefficient is less than or equal to the abnormal coefficient threshold, the equipment operation status is determined to be normal, and a normal operation status signal is generated;

[0107] If the abnormal coefficient is greater than the abnormal coefficient threshold, the equipment operation state is determined to be abnormal, and an abnormal operation state signal is generated;

[0108] The technical solution of the embodiment of the present invention is mainly as follows: the embodiment of the present invention realizes intelligent evaluation of the operating status of the production equipment by real-time monitoring of the operating parameters of the production equipment, calculating the cycle offset value, the total value of the parameter offset and the parameter abnormality occurrence characterization value, and then calculating the abnormality coefficient. The present invention can timely discover the abnormal situation of the production equipment and provide strong guarantee for the stability and efficiency of the production process. Through the preset threshold value and signal generation mechanism, the present invention can automatically determine and report the operating status of the equipment and provide decision support for production management personnel.

[0109] Embodiment 2:

[0110] Based on Example 1, please refer to Figure 2 As shown, the method for intelligently monitoring the production environment of a digital workshop according to an embodiment of the present invention, in order to prevent the production equipment in the digital workshop from generating abnormal operation status signals during operation, also includes monitoring the production environment during the operation of the production equipment, specifically:

[0111] S1: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operation status of the production equipment is evaluated, and a correlation evaluation signal is generated;

[0112] The production environment includes but is not limited to: temperature, humidity, and number of dust particles;

[0113] The correlation evaluation signals include: high correlation signal and low correlation signal;

[0114] In some implementation schemes, the production equipment operation process that generates an abnormal operation status signal is extracted from the past operation data of the production equipment and marked as an abnormal equipment operation process;

[0115] Based on the abnormal operation process of the equipment, obtain the environmental offset value of the production environment in each monitoring cycle and the cycle offset value of the production equipment;

[0116] Based on the environmental offset value and cycle offset value of each monitoring period, the correlation coefficient between the production environment and the operating status of the production equipment is calculated;

[0117] Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold;

[0118] If the correlation coefficient is less than or equal to the correlation coefficient threshold, it means that the correlation between the production environment and the operating status of the production equipment is low, that is, a low correlation signal is generated;

[0119] If the correlation coefficient is greater than the correlation coefficient threshold, it means that the production environment and the operating status of the production equipment are highly correlated, that is, a high correlation signal is generated;

[0120] First, specifically, the process of obtaining the environmental offset value is:

[0121] Obtain the real-time production environment value during the abnormal operation of the equipment, and establish a two-dimensional coordinate system with time as the X-axis and the real-time production environment value as the Y-axis to draw a real-time production environment value curve and a preset production environment value curve;

[0122] It should be explained that the preset production environment value is a production environment value pre-set by a person skilled in the art based on the production equipment in the electronic workshop, and the value is an empirical value;

[0123] Respectively extract the lengths of the real-time production environment value curve and the preset production environment value curve within the monitoring period to obtain the real-time production environment characterization value and the preset production environment characterization value;

[0124] The real-time production environment characterization value and the preset production environment characterization value are calculated for difference, and the absolute value is taken to obtain an environment offset characterization value, and then the environment offset characterization value is calculated for ratio with the preset production environment characterization value to obtain an environment offset value;

[0125] Second, specifically, the process of obtaining the correlation coefficient is:

[0126] The environmental offset values ​​of all monitoring periods are calculated separately from the period offset values, and the absolute values ​​are taken to obtain the correlation difference values ​​of each monitoring period;

[0127] By formula: Calculate the period correlation value G between the environmental offset value and the period offset value of each monitoring period respectively, where Δmin is the minimum value of the correlation difference in each monitoring period, Δmax is the maximum value of the correlation difference in each monitoring period, ΔJ is the correlation difference, ρ is the resolution coefficient, and ρ∈(0,1);

[0128] Then, the cycle correlation values ​​of all monitoring cycles in the abnormal operation process of the equipment are averaged to obtain the correlation coefficient;

[0129] S2: Based on the high correlation signal, analyze the different production environments in each monitoring cycle during the abnormal operation of the equipment, and evaluate the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of the subsequent production equipment and improve the monitoring efficiency;

[0130] In some implementation schemes, based on the high correlation signal, the linkage coefficients of different production environments in each monitoring period during the abnormal operation of all equipment are obtained;

[0131] Extract the production environment corresponding to the linkage coefficient with the highest value in the monitoring cycle, and mark it as the priority detection environment in this monitoring cycle, so that in the subsequent operation of production equipment, the priority detection environment can be focused on in each monitoring cycle to improve monitoring efficiency;

[0132] Specifically, the process of obtaining the linkage coefficient is:

[0133] Based on any production environment, extract the cycle correlation value of the production environment in each monitoring period during the abnormal operation of the equipment;

[0134] The cycle correlation values ​​of each corresponding monitoring period during the abnormal operation of all equipment are averaged to obtain the linkage coefficient;

[0135] Exemplarily, different production environments are marked as a first production environment, a second production environment, ... respectively;

[0136] Mark the monitoring periods in each abnormal operation of the equipment in sequence as the first monitoring period, the second monitoring period, ...;

[0137] Extract the periodic correlation value of the first monitoring period during the abnormal operation of all devices in the first production environment, calculate the mean, obtain the linkage coefficient, and mark it as the linkage coefficient of the first environment in the first monitoring period;

[0138] Extract the periodic correlation value of the first monitoring period during the abnormal operation of all equipment in the second production environment, calculate the mean, obtain the linkage coefficient, and mark it as the linkage coefficient of the second environment in the first monitoring period;

[0139] The linkage coefficients of the production environments in the first monitoring cycle are calculated in turn, the maximum value is extracted, and the production environment corresponding to the maximum value is marked as the priority detection environment in the first monitoring cycle;

[0140] Obtain the priority detection environment of each monitoring cycle in sequence, so that in the subsequent operation of production equipment, focus on the priority detection environment in each monitoring cycle to improve monitoring efficiency;

[0141] The technical solution of the embodiment of the present invention is mainly as follows: the embodiment of the present invention further improves the accuracy and efficiency of the intelligent monitoring system of the digital workshop production environment by introducing the correlation evaluation between the production environment and the operating status of the production equipment, and determining the priority monitoring environment based on the correlation evaluation results. It not only helps to timely discover and deal with abnormal situations in the operation of production equipment, but also can effectively guide the optimization and management of the production environment, providing strong guarantee for the stable operation and efficient production of the digital workshop.

[0142] Embodiment 3:

[0143] Based on Example 1 and Example 2, please refer to Figure 3 As shown, a digital workshop production environment intelligent monitoring system according to an embodiment of the present invention includes:

[0144] Data processing module: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data;

[0145] The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality;

[0146] Status evaluation module: Based on the abnormality coefficient, it evaluates the operating status of the production equipment, determines whether the operation of the production equipment is in an abnormal state, and generates a status evaluation signal;

[0147] The status assessment signal includes: a normal operation status signal and an abnormal operation status signal;

[0148] It also includes monitoring the production environment during the operation of production equipment, specifically:

[0149] Correlation evaluation module: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operating status of the production equipment is evaluated, and a correlation evaluation signal is generated;

[0150] The correlation evaluation signals include: high correlation signal and low correlation signal;

[0151] Intelligent monitoring module: Based on highly correlated signals, it analyzes the different production environments in each monitoring cycle during the abnormal operation of the equipment and evaluates the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of subsequent production equipment and improve monitoring efficiency.

[0152] The above thresholds are set for the convenience of comparison. The thresholds depend on the amount of sample data and the number of bases set by technicians in this field for each set of sample data.

[0153] The above formulas are obtained by collecting a large amount of data and performing software simulation to select a formula close to the actual value. The factors in the formula are set by technicians in this field according to actual conditions; for example: Formula A technician in this field collects multiple sets of abnormal operation data and sets a corresponding abnormal coefficient for each set of abnormal operation data; substitutes the set abnormal coefficient and the collected abnormal operation data into the formula, any two formulas form a binary linear equation system, and the calculated factors are screened and averaged to obtain a 1 、a 2 The values ​​of are 1.47 and 2.23 respectively;

[0154] The size of the factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the factor depends on the amount of abnormal operation data and the initial setting of the corresponding abnormal coefficient for each set of abnormal operation data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the abnormal coefficient is proportional to the total value of the parameter offset.

[0155] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for intelligent monitoring of a digital workshop production environment, characterized in that: include: Step 1: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data; The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality; Step 2: Based on the abnormality coefficient, the operating status of the production equipment is evaluated to determine whether the operation of the production equipment is in an abnormal state, and a status evaluation signal is generated; The status assessment signal includes: a normal operation status signal and an abnormal operation status signal; It also includes monitoring the production environment during the operation of production equipment, specifically: S1: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operation status of the production equipment is evaluated, and a correlation evaluation signal is generated; The correlation evaluation signals include: high correlation signal and low correlation signal; S2: Based on the high correlation signal, analyze the different production environments in each monitoring cycle during the abnormal operation of the equipment, and evaluate the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of the subsequent production equipment and improve the monitoring efficiency.

2. A digital workshop production environment intelligent monitoring method according to claim 1, characterized in that: The process of obtaining the anomaly coefficient is: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the real-time operation parameters of the production equipment are obtained, and based on the real-time operation parameters of the production equipment, the cycle offset value of the production equipment within the monitoring cycle is obtained; Based on the periodic deviation values ​​of each monitoring period, the total parameter deviation value and the parameter abnormality occurrence characterization value are calculated respectively; By formula: Calculate the abnormal coefficient YC, where a1 and a2 are preset proportional factors, both greater than 0, PY is the total value of parameter offset, and FS is the characterization value of parameter abnormality.

3. A method for intelligent monitoring of a digital workshop production environment according to claim 2, characterized in that: The process of obtaining the period offset value is as follows: Based on the real-time operation parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time operation parameters as the Y-axis to draw a real-time operation parameter curve and a preset operation parameter curve; The lengths of the real-time operating parameter curve and the preset operating parameter curve within the monitoring period are respectively extracted to obtain the real-time operating parameter characterization value and the preset operating parameter characterization value; The difference between the real-time operating parameter characterization value and the preset operating parameter characterization value is calculated, and the absolute value is taken to obtain the operating parameter offset characterization value, and then the operating parameter offset characterization value is calculated to be ratioed with the preset operating parameter characterization value to obtain the period offset value.

4. A method for intelligent monitoring of a digital workshop production environment according to claim 3, characterized in that: The process of obtaining operation abnormality data is as follows: Preset a cycle offset threshold, and compare and analyze the cycle offset value of each monitoring cycle with the cycle offset threshold; If the periodic offset value is less than or equal to the periodic offset threshold, a parameter offset normal signal is generated; If the cycle offset value is greater than the cycle offset threshold, a parameter offset abnormality signal is generated, and the corresponding monitoring period is marked as a parameter abnormality period; Extract the periodic offset values ​​of all parameter abnormal periods, and perform sum calculation to obtain the total parameter offset value; Extract the number of all abnormal cycles to obtain the total number of abnormal cycles, and calculate the ratio of the total number of abnormal cycles to the total number of monitoring cycles to obtain the abnormal cycle number ratio; At the same time, all adjacent abnormal cycles are merged to obtain one or more abnormal events, and the total number of abnormal events is calculated to be a ratio of the total number of abnormal cycles to obtain the abnormal event number ratio; Then, the ratio of the number of abnormal cycles and the ratio of the number of abnormal events are summed up and calculated to obtain the parameter abnormality occurrence characterization value.

5. The method for intelligent monitoring of a digital workshop production environment according to claim 1, characterized in that: The process of generating the status evaluation signal is: Preset an abnormal coefficient threshold, and compare and analyze the abnormal coefficient with the abnormal coefficient threshold; If the abnormal coefficient is less than or equal to the abnormal coefficient threshold, a normal operation status signal is generated; If the abnormal coefficient is greater than the abnormal coefficient threshold, an operation status abnormal signal is generated.

6. The method for intelligent monitoring of a digital workshop production environment according to claim 1, characterized in that: The process of generating the relevance evaluation signal is: Extract the production equipment operation process that generates abnormal operation status signals from the past operation data of the production equipment, and mark it as the abnormal operation process of the equipment; Based on the abnormal operation process of the equipment, obtain the environmental offset value of the production environment in each monitoring cycle and the cycle offset value of the production equipment; Based on the environmental offset value and cycle offset value of each monitoring period, the correlation coefficient between the production environment and the operating status of the production equipment is calculated; Preset a correlation coefficient threshold, and compare and analyze the correlation coefficient with the correlation coefficient threshold; If the correlation coefficient is less than or equal to the correlation coefficient threshold, a low correlation signal is generated; If the correlation coefficient is greater than the correlation coefficient threshold, a high correlation signal is generated.

7. A method for intelligent monitoring of a digital workshop production environment according to claim 6, characterized in that: The process of obtaining the environmental offset value is: Obtain the real-time production environment value during the abnormal operation of the equipment, and establish a two-dimensional coordinate system with time as the X-axis and the real-time production environment value as the Y-axis to draw a real-time production environment value curve and a preset production environment value curve; Respectively extract the lengths of the real-time production environment value curve and the preset production environment value curve within the monitoring period to obtain the real-time production environment characterization value and the preset production environment characterization value; The difference between the real-time production environment characterization value and the preset production environment characterization value is calculated, and the absolute value is taken to obtain the environment offset characterization value, and then the ratio of the environment offset characterization value to the preset production environment characterization value is calculated to obtain the environment offset value.

8. A method for intelligent monitoring of a digital workshop production environment according to claim 6, characterized in that: The process of obtaining the correlation coefficient is: The environmental offset values ​​of all monitoring periods are calculated separately from the period offset values, and the absolute values ​​are taken to obtain the correlation difference values ​​of each monitoring period; By formula: Calculate the period correlation value G between the environmental offset value and the period offset value of each monitoring period respectively, where Δmin is the minimum value of the correlation difference in each monitoring period, Δmax is the maximum value of the correlation difference in each monitoring period, ΔJ is the correlation difference, ρ is the resolution coefficient, and ρ∈(0,1); Then, the cycle correlation values ​​of all monitoring cycles in the abnormal operation process of the equipment are averaged to obtain the correlation coefficient.

9. The method for intelligently monitoring a digital workshop production environment according to claim 1, characterized in that: The process for assessing the priority monitoring environment for each monitoring cycle is: Based on the highly correlated signals, the linkage coefficients of different production environments in each monitoring period during the abnormal operation of all equipment are obtained; Extract the production environment corresponding to the linkage coefficient with the highest value in the monitoring cycle, and mark it as the priority detection environment in this monitoring cycle, so that in the subsequent operation of production equipment, the priority detection environment can be focused on in each monitoring cycle to improve monitoring efficiency; The process of obtaining the linkage coefficient is as follows: Based on any production environment, extract the cycle correlation value of the production environment in each monitoring period during the abnormal operation of the equipment; The cycle correlation values ​​of each corresponding monitoring period during the abnormal operation of all equipment are averaged to obtain the linkage coefficient.

10. A digital workshop production environment intelligent monitoring system, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data processing module: During the operation of the production equipment in the digital workshop, the operation status of the production equipment is monitored, the operation abnormality data of the production equipment is obtained, and the abnormality coefficient is calculated based on the operation abnormality data; The abnormal operation data include: the total value of parameter deviation and the value representing the occurrence of parameter abnormality; Status evaluation module: Based on the abnormality coefficient, it evaluates the operating status of the production equipment, determines whether the operation of the production equipment is in an abnormal state, and generates a status evaluation signal; The status assessment signal includes: a normal operation status signal and an abnormal operation status signal; It also includes monitoring the production environment during the operation of production equipment, specifically: Correlation evaluation module: Based on the past operation data of the production equipment, the production environment during the past operation of the production equipment is detected, the correlation between the production environment and the operating status of the production equipment is evaluated, and a correlation evaluation signal is generated; The correlation evaluation signals include: high correlation signal and low correlation signal; Intelligent monitoring module: Based on highly correlated signals, it analyzes the different production environments in each monitoring cycle during the abnormal operation of the equipment and evaluates the priority monitoring environment in each monitoring cycle, so as to focus on the priority detection environment in each monitoring cycle during the operation of subsequent production equipment and improve monitoring efficiency.

Images