An industrial big data processing system based on artificial intelligence algorithm

Abstract

The present invention discloses an industrial big data processing system based on an artificial intelligence algorithm, relates to the technical field of industrial big data processing, and solves the technical problem that fault location analysis cannot be performed based on equipment data, corresponding risk analysis cannot be performed in combination with big data, and further, it is inconvenient to perform equipment adjustment. The present invention performs a comprehensive analysis on industrial big data, generates a corresponding state judgment interval based on big data, and facilitates subsequent corresponding equipment state judgment according to the data. Secondly, when analyzing the abnormal equipment state, comprehensive processing is performed based on the real-time parameters of the equipment and in combination with industrial big data to achieve risk analysis of the abnormal equipment state, and corresponding equipment adjustment is performed according to the obtained risk information, so that operators can perform timely adjustment and analysis to avoid damage to the equipment caused by existing potential risks.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial big data processing, and in particular to an industrial big data processing system based on an artificial intelligence algorithm. Background Art

[0002] Industrial big data refers to the massive amount of data generated in the application of information technology in the industrial field. It is a basic strategic resource for the digitalization, networking and intelligent development of the manufacturing industry. In recent years, with the continuous innovation and development of information technology and technological industrialization, people have proposed a production concept based on intelligent technology, and also applied artificial intelligence technology to industry to promote the modernization and high-quality development of industrial enterprises.

[0003] According to the patent application with publication number CN114817739A, an industrial big data processing system based on artificial intelligence algorithm is disclosed, including: a data acquisition module, a data storage module, a data analysis module and a data management module; the data acquisition module collects data from industrial equipment to obtain industrial big data, and transmits the industrial big data to the data analysis module and the data storage module; the data analysis module analyzes and processes the industrial big data transmitted by the data acquisition module through an artificial intelligence algorithm to obtain industrial big data analysis results; the data management module performs industrial big data processing information exchange and transmits industrial big data analysis results; the data storage module stores the industrial big data obtained by the data acquisition module, and provides data information to the data analysis module.

[0004] The above patent uses artificial intelligence algorithms to process industrial big data, efficiently and quickly obtain valuable information from massive industrial big data for use and management, and effectively improve the value of industrial big data. However, the above patent has the problem of incomplete analysis when performing equipment fault analysis. It cannot accurately locate the fault according to the equipment parameters, and cannot perform corresponding risk analysis based on industrial big data, which will result in the inability to make corresponding equipment adjustments based on risk results, affecting the overall equipment work efficiency. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides an industrial big data processing system based on artificial intelligence algorithms, which solves the problem that fault location analysis cannot be performed based on equipment data, corresponding risk analysis cannot be performed in combination with big data, and further inconveniences in equipment adjustment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an industrial big data processing system based on artificial intelligence algorithm, comprising:

[0007] The data comprehensive arrangement and processing module is used to analyze the historical industrial data transmitted by the industrial big data acquisition module, and generate corresponding equipment status judgment intervals based on the same type of historical industrial data, and transmit the generated equipment status judgment intervals to the equipment status analysis module;

[0008] The equipment status analysis module is used to obtain the real-time parameters transmitted by the real-time data acquisition module, match the real-time parameters with the equipment status judgment interval, identify the equipment status and generate status identification results, including normal monitoring results and abnormal analysis results, and transmit the normal monitoring results to the equipment processing information output module, process the abnormal analysis results, perform feature matching based on the abnormal characteristics of the equipment to generate secondary analysis signals and normal monitoring results, and transmit the secondary analysis signals to the comprehensive adjustment analysis module;

[0009] The comprehensive adjustment and analysis module is used to process the acquired secondary analysis signals, match the abnormal parameters corresponding to the secondary analysis signals with the abnormal conditions in the historical industrial big data, and generate corresponding risk results based on the associated parameters of the abnormal parameters. At the same time, it generates corresponding adjustment information according to the risk results and transmits the generated adjustment information to the equipment processing information output module.

[0010] As a further solution of the present invention: it also includes an industrial big data acquisition module, a real-time data acquisition module and an equipment processing information output module;

[0011] Industrial big data collection module, used to collect historical industrial data and transmit the historical industrial data to the data comprehensive processing module, where the historical industrial data includes equipment operation parameters, production environment parameters and product quality index parameters;

[0012] The real-time data acquisition module is used to transmit the real-time parameters to the equipment status analysis module, and the real-time parameters include: equipment temperature, voltage, and current;

[0013] The equipment processing information output module is used to display the acquired normal monitoring results and adjustment information to the corresponding operators.

[0014] As a further solution of the present invention: the specific method in which the data comprehensive processing module analyzes the acquired historical industrial data is:

[0015] Acquire all historical industrial data, and acquire the same type of industrial data, and acquire the equipment parameters corresponding to the same production environment data. Organize and generate the corresponding normal area based on the acquired equipment parameters, and record the generated normal interval as the equipment status judgment interval. Then analyze the abnormal parameter conditions within the equipment status judgment interval.

[0016] As a further solution of the present invention: the specific method in which the data comprehensive processing module analyzes the abnormal parameter situation in the equipment status judgment interval is:

[0017] If there are abnormal parameters in the device status judgment interval, the corresponding abnormal parameters are obtained and the number of times the abnormal parameters appear is determined. If the abnormal parameters appear once, no processing is performed. On the contrary, if the abnormal parameters appear multiple times, a regularity result is generated, and then the generated device status judgment interval is transmitted to the device status analysis module.

[0018] As a further solution of the present invention: the specific manner in which the device status analysis module matches the real-time parameters with the device status judgment interval is:

[0019] The real-time parameters of the equipment are obtained, and the obtained real-time parameters are matched with the equipment status judgment interval. The production environment parameters corresponding to the real-time parameters are obtained, and the corresponding equipment status judgment interval is obtained based on the production environment parameters. Then, it is determined whether the real-time parameters exist in the equipment status judgment interval. If the real-time parameters exist in the equipment status judgment interval, a normal monitoring result is generated. Otherwise, if the real-time parameters do not exist in the equipment status judgment interval, an abnormal analysis result is generated and processed at the same time.

[0020] As a further solution of the present invention: the specific manner in which the device status analysis module processes the abnormal analysis result is:

[0021] The corresponding abnormal parameters in the real-time parameters are obtained, and the abnormal features corresponding to the abnormal parameters are obtained at the same time. The change values ​​of the abnormal parameters within the time period t are obtained, and the obtained abnormal parameter change values ​​are used as the corresponding abnormal features. Then, the abnormal features are matched with the parameter features corresponding to the equipment status judgment interval to determine whether the abnormal features and the parameter features are the same. If the two are the same, a normal monitoring result is generated. Otherwise, if the two are different, a secondary analysis signal is generated.

[0022] As a further solution of the present invention: the specific manner in which the comprehensive adjustment and analysis module processes the secondary analysis signal is:

[0023] Acquire abnormal parameters, and at the same time acquire the corresponding abnormal situations in the historical industrial big data, and label the acquired abnormal situations as i, where i=1, 2, ..., j, where j represents the number of abnormal situations, acquire the production environment parameters corresponding to the equipment, and screen the abnormal situation i based on the production environment parameters to obtain the situation a to be analyzed, where a=1, 2, ..., b, where b represents the number of situations to be analyzed, and at the same time acquire the risk information corresponding to the situation a to be analyzed, then acquire the associated parameters corresponding to the abnormal parameters as the current associated parameters, and match and screen the situation a to be analyzed according to the associated parameters to obtain the specific abnormal situation;

[0024] Obtain the associated parameters corresponding to the abnormal parameters in the situation a to be analyzed and record them as abnormal associated parameters. Then match all the abnormal associated parameters with the current associated parameters. If the current associated parameters are the same as the abnormal associated parameters, the corresponding situation a to be analyzed is selected and recorded as the secondary analysis situation n, and n=1, 2, ..., m, where m represents the number of secondary analysis situations. Otherwise, if the current associated parameters are different from the abnormal associated parameters, the situation a to be analyzed is not selected, and the secondary analysis situation n is analyzed at the same time.

[0025] As a further solution of the present invention: the specific method in which the comprehensive adjustment analysis module analyzes the secondary analysis situation is:

[0026] Obtain the historical abnormal parameter value corresponding to the secondary analysis situation n, calculate the difference between the historical abnormal parameter value and the abnormal parameter value, select the secondary analysis situation corresponding to the smallest difference as the standard to generate the corresponding standard abnormal situation, and generate the risk result according to the risk information corresponding to the standard abnormal situation;

[0027] The generated risk results are analyzed to obtain the historical industrial big data that is the same as the risk results. Then, the corresponding adjustment methods in the historical industrial big data are obtained and recorded as o, and o=1, 2, ..., p, where p represents the number of adjustment methods. At the same time, the periodic change values ​​of the abnormal parameters are obtained, and the periodic change values ​​corresponding to the historical abnormal parameters in the adjustment methods are obtained. Then, the adjustment method with the smallest periodic change value of the abnormal parameter and the smallest periodic change value of the historical abnormal parameter is selected as the standard. At the same time, the adjustment information is generated with the corresponding adjustment method, and the adjustment information is transmitted to the equipment processing information output module. Beneficial Effects

[0028] The present invention provides an industrial big data processing system based on artificial intelligence algorithm. Compared with the prior art, it has the following beneficial effects:

[0029] The present invention conducts a comprehensive analysis of industrial big data and generates corresponding status judgment intervals based on the big data, which facilitates subsequent corresponding equipment status judgment according to the data. Secondly, when analyzing the abnormal equipment status, it realizes risk analysis of the abnormal equipment status by conducting comprehensive processing based on the real-time parameters of the equipment and combining with the industrial big data, and performs corresponding equipment adjustments based on the obtained risk information, which facilitates operators to conduct timely adjustment and analysis to avoid damage to the equipment caused by existing potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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.

[0032] For example, see Figure 1 The present application provides an industrial big data processing system based on artificial intelligence algorithm, including: an industrial big data acquisition module, a data comprehensive collation and processing module, an equipment status analysis module, a real-time data acquisition module, a comprehensive adjustment and analysis module and an equipment processing information output module, and the above-mentioned functional modules are connected by unidirectional wires.

[0033] Industrial big data collection module, which is used to collect historical industrial data and transmit the historical industrial data to the data comprehensive collation and processing module. The historical industrial data includes equipment operation parameters, production environment parameters and product quality indicator parameters, etc.

[0034] The data comprehensive arrangement and processing module is used to analyze the acquired historical industrial data and generate corresponding equipment status judgment intervals based on the same type of historical industrial data. At the same time, the generated equipment status judgment intervals are transmitted to the equipment status analysis module. The specific method of generating the equipment status judgment intervals is:

[0035] Acquire all historical industrial data, and acquire the same type of industrial data. The same type of data acquired here means to organize the equipment operation parameters and production environment parameters in the same type. At the same time, acquire the equipment parameters corresponding to the same production environment data. The equipment parameters acquired here are the corresponding equipment parameters under normal working conditions. The corresponding normal interval is generated based on the acquired equipment parameters. The specific normal interval value is composed of the maximum value and the minimum value. For example, when the working temperature corresponding to the environmental parameter is 30°C, the corresponding equipment parameters correspond to the temperatures of 35°C, 33°C, 36°C and 32°C, respectively. Therefore, the normal interval is [32°C, 36°C]. Similarly, the equipment parameters corresponding to different production environment parameters are organized. At the same time, the generated normal interval is recorded as the equipment status judgment interval. Then, the abnormal parameter situation within the equipment status judgment interval is analyzed.

[0036] If there are abnormal parameters in the device status judgment interval, the corresponding abnormal parameters are obtained, and the number of occurrences of the abnormal parameters is analyzed. The specific analysis method is: determine the number of times the abnormal parameters appear. If the abnormal parameters appear once, no processing is performed and an accidental result is generated. On the contrary, if the abnormal parameters appear multiple times, and multiple times here means the number of occurrences is three or more, a regular result is generated. The specific regular result indicates that the corresponding abnormal parameters appear regularly and do not affect the overall device status. Then the generated device status judgment interval is transmitted to the device status analysis module.

[0037] The equipment status analysis module is used to obtain the real-time parameters transmitted by the real-time data acquisition module, match the real-time parameters with the equipment status judgment interval, identify the equipment status and generate status identification results, including normal monitoring results and abnormal analysis results, and transmit the normal monitoring results to the equipment processing information output module, process the abnormal analysis results, perform feature matching based on the abnormal characteristics of the equipment to generate secondary analysis signals and normal monitoring results, and transmit the secondary analysis signals to the comprehensive adjustment analysis module. The specific feature matching method is as follows:

[0038] The real-time parameters of the equipment are acquired through a variety of sensors, and the real-time parameters acquired here include data such as the temperature, pressure, current and voltage of the equipment, which are specifically acquired through corresponding sensors, and the current and voltage are acquired through corresponding ammeters and voltmeters, and the acquired real-time parameters are matched with the equipment status judgment interval, and the specific matching method is: the production environment parameters corresponding to the real-time parameters are acquired, and the corresponding equipment status judgment interval is acquired based on the production environment parameters, and then it is determined whether the real-time parameters exist in the equipment status judgment interval. If the real-time parameters exist in the equipment status judgment interval, it indicates that the equipment status is normal, and a normal monitoring result is generated. On the contrary, if the real-time parameters do not exist in the equipment status judgment interval, it indicates that the equipment status is abnormal, and an abnormal analysis result is generated;

[0039] For example, when the production environment temperature is 25°C and the humidity is 40%, the corresponding equipment status judgment interval is obtained based on these production environment parameters. Taking the temperature parameter as an example, assuming that in the current production environment, the temperature judgment interval for normal operation of the equipment is 30°C to 50°C, if the real-time temperature obtained by the temperature sensor is 45°C, since the temperature value exists in the equipment status judgment interval, the temperature status of the equipment is normal at this time, and a normal monitoring result is generated. For another example, assuming that the pressure judgment interval of the equipment during normal operation is 1.5MPa to 2MPa, the real-time pressure obtained by the pressure sensor is 1.8MPa, which is also within the equipment status judgment interval, indicating that the equipment pressure status is normal.

[0040] Then, the generated abnormal analysis results are processed to obtain the corresponding abnormal parameters in the real-time parameters, and the abnormal features corresponding to the abnormal parameters are obtained. The abnormal features are obtained in the following way: the change value of the abnormal parameter within the time period t is obtained, and the obtained abnormal parameter change value is used as the corresponding abnormal feature. Then, the abnormal feature is matched with the parameter feature corresponding to the equipment status judgment interval, and the parameter feature here represents the corresponding abnormal data situation. For example, the corresponding abnormal parameter in the equipment status judgment interval is temperature. According to the analysis of the data comprehensive processing module, it is found that when the temperature is abnormal, it does not affect the overall working state of the equipment. Further, the temperature is used as a parameter feature to determine whether the abnormal feature is the same as the parameter feature. If the two are the same, it means that the abnormal parameter is normal and a normal monitoring result is generated. Otherwise, if the two are different, it means that the abnormal parameter is abnormal and a secondary analysis signal is generated.

[0041] The equipment processes the information output module, which is used to display the acquired normal monitoring results to the corresponding operator.

[0042] Embodiment 2, as Embodiment 2 of the present invention, is implemented on the basis of Embodiment 1, and differs from Embodiment 1 in that.

[0043] The comprehensive adjustment analysis module is used to process the acquired secondary analysis signal, match the abnormal parameters corresponding to the secondary analysis signal with the abnormal conditions in the historical industrial big data, and generate corresponding risk results based on the associated parameters of the abnormal parameters. At the same time, the corresponding adjustment information is generated according to the risk results, and the generated adjustment information is transmitted to the equipment processing information output module. The specific method of generating the adjustment information is:

[0044] Acquire abnormal parameters, and at the same time acquire the corresponding abnormal situations in the historical industrial big data, and label the acquired abnormal situations as i, where i=1, 2, ..., j, where j represents the number of abnormal situations, acquire the production environment parameters corresponding to the equipment, and screen the abnormal situation i based on the production environment parameters to obtain the situation a to be analyzed, where a=1, 2, ..., b, where b represents the number of situations to be analyzed, and the specific method of screening according to the production environment parameters here is to screen the abnormal situations that are the same as the current equipment production environment parameters. For example, when the production environment temperature corresponding to the current equipment production environment parameters is 25°C and the humidity is 40%, the abnormal situations with the same production environment temperature of 25°C and humidity of 40% are further screened, and the risk information corresponding to the situation a to be analyzed is obtained, and the risk information here is represented by the subsequent occurrence of the equipment The fault is then obtained, and the associated parameters corresponding to the abnormal parameters are recorded as the current associated parameters. The associated parameters here represent parameters that change with the change of the abnormal parameters, specifically including data that are proportional to the abnormal parameters or inversely proportional to the abnormal parameters. The situation a to be analyzed is matched and screened according to the associated parameters to obtain a specific abnormal situation. The specific matching and screening method is: the associated parameters corresponding to the abnormal parameters in the situation a to be analyzed are obtained and recorded as abnormal associated parameters. Then all abnormal associated parameters are matched with the current associated parameters. If the current associated parameters are the same as the abnormal associated parameters, the corresponding situation a to be analyzed is selected and recorded as the secondary analysis situation n, and n=1, 2, ..., m, where m represents the number of secondary analysis situations. Otherwise, if the current associated parameters are not the same as the abnormal associated parameters, the situation a to be analyzed is not selected.

[0045] For example, suppose the current abnormal parameter is that the equipment pressure rises to 1.8MPa (the normal pressure range is 1.5MPa to 2MPa), and the current associated parameter is that the equipment flow rate decreases to 10m³ / h (the normal flow rate range is 12m³ / h to 15m³ / h). Among the situations to be analyzed, if there is an abnormal situation whose abnormal parameter is also the pressure rises to 1.8MPa, and its associated parameter is the flow rate decreases to 10m³ / h, then this situation to be analyzed will be selected as the secondary analysis situation.

[0046] The historical abnormal parameter value corresponding to the obtained secondary analysis situation n is obtained, and the difference between the historical abnormal parameter value and the abnormal parameter value is calculated, and the secondary analysis situation corresponding to the smallest difference is selected as the standard to generate the corresponding standard abnormal situation, and the risk result is generated according to the risk information corresponding to the standard abnormal situation;

[0047] For example, there are three secondary analysis cases, and the corresponding historical abnormal parameter values ​​are 1.75MPa, 1.82MPa, and 1.78MPa, respectively, and the current abnormal parameter value is 1.8MPa. The calculated differences are 0.05MPa, 0.02MPa, and 0.02MPa, respectively. The secondary analysis case corresponding to the smallest difference of 1.82MPa is selected as the standard abnormal case. If the risk information corresponding to this standard abnormal case is that the equipment seal may be damaged, then the generated risk result is that there is a risk of damage to the equipment seal.

[0048] The generated risk results are analyzed to obtain historical industrial big data that is the same as the risk results, and the historical industrial big data obtained here is the historical industrial big data under abnormal conditions. Then, the corresponding adjustment method in the historical industrial big data is obtained and recorded as o, and o=1, 2, ..., p, where p represents the number of adjustment methods. At the same time, the periodic change value of the abnormal parameter is obtained, and the periodic change value corresponding to the historical abnormal parameter in the adjustment method is obtained. Then, the adjustment method with the smallest periodic change value of the abnormal parameter and the historical periodic change value of the abnormal parameter is selected as the standard, and the adjustment information is generated with the corresponding adjustment method, and the adjustment information is transmitted to the equipment processing information output module.

[0049] For example, assuming that the periodic change value of the abnormal parameter is increased by 0.1MPa per hour, there are three historical adjustment methods, and the corresponding historical abnormal parameter periodic change values ​​are increased by 0.08MPa per hour, 0.12MPa per hour, and 0.09MPa per hour. The adjustment method corresponding to the increase of 0.09MPa per hour, which is closest to the current abnormal parameter periodic change value, is selected as the standard, and adjustment information is generated, such as adjusting the opening of a certain valve of the equipment or increasing the power of the cooling system, and the adjustment information is transmitted to the equipment processing information output module so that the staff can take timely measures to make adjustments.

[0050] The equipment processes the information output module, which is used to display the acquired adjustment information to the corresponding operator.

[0051] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0052] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0053] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An industrial big data processing system based on artificial intelligence algorithm, characterized in that: include: The data comprehensive arrangement and processing module is used to analyze the historical industrial data transmitted by the industrial big data acquisition module, and generate the corresponding equipment status judgment interval based on the same type of historical industrial data, and transmit the generated equipment status judgment interval to the equipment status analysis module. The specific method of generating the equipment status judgment interval is: If there are abnormal parameters in the device status judgment interval, and the device status judgment interval is a normal parameter interval, the corresponding abnormal parameters are obtained, and the number of times the abnormal parameters appear is determined. If the number of times the abnormal parameters appear is once, no processing is performed. On the contrary, if the abnormal parameters appear multiple times, a regularity result is generated. The specific regularity result indicates that the corresponding abnormal parameters appear regularly and do not affect the overall device status. Then the generated device status judgment interval is transmitted to the device status analysis module; The equipment status analysis module is used to obtain the real-time parameters transmitted by the real-time data acquisition module, match the real-time parameters with the equipment status judgment interval, identify the equipment status and generate status identification results, including normal monitoring results and abnormal analysis results, and transmit the normal monitoring results to the equipment processing information output module, process the abnormal analysis results, perform feature matching based on the abnormal characteristics of the equipment to generate secondary analysis signals and normal monitoring results, and transmit the secondary analysis signals to the comprehensive adjustment analysis module; The specific method for matching the real-time parameters with the device status judgment interval is: Acquire the production environment parameters corresponding to the real-time parameters, and acquire the corresponding equipment status judgment interval based on the production environment parameters, acquire the real-time parameters of the equipment, and match the acquired real-time parameters with the equipment status judgment interval, and then determine whether the real-time parameters exist in the equipment status judgment interval. If the real-time parameters exist in the equipment status judgment interval, generate a normal monitoring result. Otherwise, if the real-time parameters do not exist in the equipment status judgment interval, generate an abnormal analysis result, and process the abnormal analysis result at the same time; The specific method for processing abnormal analysis results is: Acquire the corresponding abnormal parameters in the real-time parameters, and at the same time acquire the abnormal features corresponding to the abnormal parameters, acquire the change values ​​of the abnormal parameters within the time period t, and use the acquired abnormal parameter change values ​​as the corresponding abnormal features, then match the abnormal features with the parameter features corresponding to the equipment status judgment interval, and determine whether the abnormal features and the parameter features are the same. If the two are the same, a normal monitoring result is generated, otherwise if the two are not the same, a secondary analysis signal is generated; The comprehensive adjustment analysis module is used to process the acquired secondary analysis signal, match the abnormal parameters corresponding to the secondary analysis signal with the abnormal conditions in the historical industrial big data, and generate corresponding risk results based on the associated parameters of the abnormal parameters. The associated parameters here represent the parameters that change with the changes of the abnormal parameters. At the same time, the corresponding adjustment information is generated according to the risk results, and the generated adjustment information is transmitted to the equipment processing information output module. The specific method of processing the secondary analysis signal is as follows: Acquire abnormal parameters, and at the same time acquire the corresponding abnormal situations in the historical industrial big data, and label the acquired abnormal situations as i, where i=1, 2, ..., j, where j represents the number of abnormal situations, acquire the production environment parameters corresponding to the equipment, and screen the abnormal situation i based on the production environment parameters to obtain the situation a to be analyzed, where a=1, 2, ..., b, where b represents the number of situations to be analyzed, and at the same time acquire the risk information corresponding to the situation a to be analyzed, then acquire the associated parameters corresponding to the abnormal parameters as the current associated parameters, and match and screen the situation a to be analyzed according to the associated parameters to obtain the specific abnormal situation; Obtain the associated parameters corresponding to the abnormal parameters in the situation a to be analyzed and record them as abnormal associated parameters. Then match all abnormal associated parameters with the current associated parameters. If the current associated parameters are the same as the abnormal associated parameters, the corresponding situation a to be analyzed is selected and recorded as the secondary analysis situation n, and n=1, 2, ..., m, where m represents the number of secondary analysis situations. Otherwise, if the current associated parameters are different from the abnormal associated parameters, the situation a to be analyzed is not selected, and the secondary analysis situation n is analyzed. At the same time, the risk result is generated according to the risk information corresponding to the standard abnormal situation.

2. The industrial big data processing system based on artificial intelligence algorithm according to claim 1 is characterized in that: It also includes industrial big data acquisition module, real-time data acquisition module and equipment processing information output module; Industrial big data collection module, used to collect historical industrial data and transmit the historical industrial data to the data comprehensive processing module, where the historical industrial data includes equipment operation parameters, production environment parameters and product quality index parameters; The real-time data acquisition module is used to transmit the real-time parameters to the equipment status analysis module, and the real-time parameters include: equipment temperature, voltage, and current; The equipment processing information output module is used to display the acquired normal monitoring results and adjustment information to the corresponding operators.

3. The industrial big data processing system based on artificial intelligence algorithm according to claim 1 is characterized in that: The specific method in which the data comprehensive arrangement and processing module analyzes the acquired historical industrial data is as follows: Acquire all historical industrial data, and acquire the same type of industrial data, and acquire the equipment parameters corresponding to the same production environment data. Organize and generate the corresponding normal area based on the acquired equipment parameters, and record the generated normal interval as the equipment status judgment interval. Then analyze the abnormal parameter conditions within the equipment status judgment interval.

4. The industrial big data processing system based on artificial intelligence algorithm according to claim 1 is characterized in that: The specific way in which the comprehensive adjustment analysis module analyzes the secondary analysis situation is as follows: Obtain the historical abnormal parameter value corresponding to the secondary analysis situation n, calculate the difference between the historical abnormal parameter value and the abnormal parameter value, select the secondary analysis situation corresponding to the smallest difference as the standard to generate the corresponding standard abnormal situation, and generate the risk result according to the risk information corresponding to the standard abnormal situation; The generated risk results are analyzed to obtain the historical industrial big data that is the same as the risk results. Then, the corresponding adjustment methods in the historical industrial big data are obtained and recorded as o, and o=1, 2, ..., p, where p represents the number of adjustment methods. At the same time, the periodic change values ​​of the abnormal parameters are obtained, and the periodic change values ​​corresponding to the historical abnormal parameters in the adjustment methods are obtained. Then, the adjustment method with the smallest periodic change value of the abnormal parameter and the smallest periodic change value of the historical abnormal parameter is selected as the standard. At the same time, the adjustment information is generated with the corresponding adjustment method, and the adjustment information is transmitted to the equipment processing information output module.

Images