Digital management and control platform based on Internet of Things and big data

Abstract

The invention discloses a digital management and control platform based on Internet of Things and big data, relates to the technical field of digital management, and solves the technical problems that a unified analysis framework and data support are lacked, the selection randomness of a processing scheme is high, and the processing effect cannot be quantitatively evaluated. According to the method, the fault risk is converted into a quantifiable probability index, hierarchical response is supported, associated parameters are automatically expanded in combination with physical rules and data correlation, one-sidedness of single parameter analysis is avoided, and the real-time fault analysis efficiency is improved through similarity calculation of a parameter change template of a historical fault case and real-time data. Automatic screening and sorting of abnormal reasons are achieved, the positioning accuracy is improved, meanwhile, the effective rate is calculated through weighting of multi-dimensional indexes such as the same-type indexes, the application ratio and the recurrence rate, scientific screening of processing modes is achieved in combination with the processing efficiency, a processing mode knowledge base is established, a standard processing flow is automatically generated in combination with an AI algorithm, and the manual decision making cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of digital management technology, and in particular to a digital management and control platform based on the Internet of Things and big data. Background Art

[0002] The digital management and control platform is a comprehensive platform that integrates advanced technologies. This platform achieves precise management and efficient operation of different production equipment by utilizing modern information technologies such as the Internet of Things, artificial intelligence, and big data analysis.

[0003] According to the patent application with publication number CN118863473A, a modern agricultural digital management and control platform based on the Internet of Things and big data is disclosed, including a digital management and control module, which is communicatively connected to a subordinate equipment management and control unit and a data collection and processing unit respectively; the subordinate equipment management and control unit includes a mobile terminal registration unit, an equipment digital storage repository and an equipment display unit; the data collection and processing unit includes a data collection platform, a twin display processing unit and an autonomous management and control setting unit; the autonomous management and control setting unit includes an independent variable selection unit, a first logic control module, an independent variable value setting / modification unit, a pre-determination unit, a dependent variable selection unit, a second logic control module and a dependent variable value setting / modification unit.

[0004] However, some existing digital management and control platforms lack in-depth analysis of historical data, making it difficult to predict potential risks through parameter change trends. Most of them are in a "post-maintenance" mode, resulting in large downtime losses. Data from different equipment and systems are difficult to communicate with each other. There is a lack of a unified analysis framework, making it difficult to achieve cross-departmental collaborative management and scientific decision-making. The analysis of abnormal causes relies on manual experience and lacks data support. The selection of treatment solutions is highly random, and the treatment effects cannot be quantitatively evaluated. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a digital management and control platform based on the Internet of Things and big data, which solves the problems of lack of a unified analysis framework and data support, strong randomness in the selection of treatment solutions, and inability to quantitatively evaluate the treatment effects.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a digital management and control platform based on the Internet of Things and big data, comprising:

[0007] The sensor data analysis module is used to match the acquired sensor data with the normal state data. If the two match, a normal monitoring signal is generated; otherwise, an abnormal analysis signal is generated and both are transmitted simultaneously;

[0008] The normal situation analysis module is used to analyze the acquired normal monitoring signals, obtain the parameter changes of the sensor data within the time period, and compare them with the data changes in the pre-abnormal stage. If the two match, a fault warning message is generated; otherwise, normal monitoring information is generated, and both are transmitted to the digital control output module at the same time;

[0009] The abnormal situation analysis module is used to analyze the acquired abnormal analysis signal, determine the abnormal parameters and related parameters, and obtain the abnormal causes corresponding to the two. At the same time, the abnormal causes are screened according to the changes in the parameters of the two to obtain standard abnormal causes, generate standard abnormal information, and transmit it to the processing method screening unit;

[0010] The processing method screening unit is used to screen the processing methods according to the standard exception information, determine the relationship between the exception cause corresponding to the standard exception information and the data collection, generate data collection exception information or processing solution information, analyze the processing solution information, calculate the efficiency index and processing efficiency index corresponding to the processing method respectively, and sum them to obtain the selected value of the processing method, generate standard processing information based on the processing method with the smallest selected value, and transmit it to the digital control output module at the same time.

[0011] As a further solution of the present invention, the sensor data analysis module matches the acquired sensor data with the normal state data in the following specific manner:

[0012] The sensor data is compared with the normal status data determined based on the normal working data of different devices. If the sensor data is within the normal working data range, it indicates that the device is working normally and a normal monitoring signal is generated; if it is not within the range, it indicates that the device is working abnormally and an abnormal analysis signal is generated.

[0013] As a further solution of the present invention, the normal situation analysis module analyzes the acquired normal monitoring signal in the following specific manner:

[0014] Acquire sensor data with a time period of T and monitor the changes in its periodic parameters. At the same time, retrieve the changes in the data before the abnormal state corresponding to the historical data and compare and analyze them with the current sensor data;

[0015] If the two match, it indicates that the current working state has a fault risk and a fault warning message is generated; if they do not match, it indicates that the working state is normal and normal monitoring information is generated. The two types of information are then transmitted to the digital control output module.

[0016] As a further solution of the present invention, the abnormal situation analysis module analyzes the acquired abnormal analysis signal in the following specific manner:

[0017] Obtain the abnormal causes corresponding to the abnormal parameters and associated parameters, screen out the common abnormal causes and number them as i, where i=1, 2, ..., j, where j is the number of common abnormal causes. Then obtain the parameter changes corresponding to these common abnormal causes, compare them with the changes in the abnormal parameters and associated parameters, select the one with the closest change as the standard abnormal cause, generate standard abnormal information, and transmit it to the processing method screening unit.

[0018] As a further solution of the present invention, the specific method of the processing method screening unit generating data collection exception information or processing solution information is:

[0019] Obtain the corresponding processing method for standard exception information and number it as a, where a=1, 2, ..., b, and b is the number of processing methods. Analyze the abnormal cause of the standard exception information and determine whether the abnormality is caused by data collection.

[0020] If so, data collection exception information is generated and transmitted to the digital control output module, and data is re-collected. If not, processing and solution information is generated and analyzed at the same time.

[0021] As a further solution of the present invention, the specific method of the processing method screening unit analyzing the processing solution information is:

[0022] The generated processing solution information is analyzed to obtain all processing methods a, and the effectiveness and processing efficiency corresponding to the processing methods a are analyzed respectively, and the corresponding effectiveness index and processing efficiency index are calculated.

[0023] As a further solution of the present invention, the specific method for the processing method screening unit to calculate the efficiency index of the processing method is:

[0024] Obtain the number of treatments of the same type and the total number of treatments for treatment method a, calculate the same type index using the formula "same type index = number of treatments of the same type ÷ total number of treatments", and then calculate the percentage of times treatment method a is applied using the formula "applicable percentage = number of applications ÷ total number of treatments". Also obtain the number of recurrences of the same type and calculate the recurrence rate using the formula "recurrence rate = number of recurrences of the same type ÷ number of treatments of the same type".

[0025] The calculated indicators of the same type, applicable proportion and recurrence rate are summed up and the effectiveness index is calculated according to the formula: effectiveness index = indicator of the same type × q1 + applicable proportion × q2 + recurrence rate × q3, where q1, q2 and q3 are the corresponding weights, and the specific values ​​are set by the operator.

[0026] As a further solution of the present invention, the specific method for the processing method screening unit to calculate the processing efficiency index of the processing method is:

[0027] Get the total processing time corresponding to processing method a, and get the completion time in the total processing time. According to the formula processing efficiency = completion time ÷ total time, get the total number of processing times corresponding to processing method a, and calculate the processing efficiency in turn. Then sum the processing efficiencies and calculate the average value to obtain the processing efficiency index.

[0028] As a further solution of the present invention, the specific method in which the processing method screening unit generates standard processing information based on the processing method with the smallest value is as follows:

[0029] The calculated efficiency index and processing efficiency index are summed, and the selected value is calculated according to the formula = efficiency index × c1 + processing efficiency index × c2 to obtain the selected value corresponding to processing method a. The processing method a corresponding to the smallest selected value is used as the standard to generate a standard processing method. At the same time, standard processing information is generated and transmitted to the digital control output module.

[0030] The present invention provides a digital management and control platform based on the Internet of Things and big data. Compared with the existing technology, it has the following advantages:

[0031] The present invention collects multi-type sensor data in real time through the Internet of Things, combines statistical analysis to construct the normal working data interval of the equipment, realizes the dual judgment of "whether the parameter exceeds the limit" and "whether the trend is abnormal", dynamically adjusts the normal interval based on the historical data of the equipment, adapts to factors such as equipment aging and working condition changes, avoids the hysteresis of static thresholds, converts fault risks into quantifiable probability indicators, supports hierarchical response, combines physical rules and data correlation, automatically expands related parameters, avoids the one-sidedness of single parameter analysis, and calculates the similarity between parameter change templates of historical fault cases and real-time data to realize automatic screening and sorting of abnormal causes, improve positioning accuracy, and at the same time, through the weighted calculation efficiency of multi-dimensional indicators such as "same type indicators", "applicable proportion", and "recurrence rate", combined with processing efficiency, realizes scientific screening of processing methods, establishes a processing method knowledge base, and automatically generates standard processing procedures in combination with AI algorithms to reduce manual decision-making costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0034] Example 1

[0035] See also Figure 1 This application provides a digital control platform based on the Internet of Things and big data, including: sensor data analysis module, normal situation analysis module, abnormal situation analysis module, processing method screening module and digital control output module, and combined with Figure 1 It can be known that the functional modules are electrically connected in a unidirectional manner.

[0036] Sensor data analysis module, which is used to obtain different sensor data through the Internet of Things and analyze the obtained sensor data.

[0037] Establish a stable and efficient connection with the IoT system to acquire data collected by different types of sensors. Perform preliminary cleaning and preprocessing on the acquired raw sensor data. For different types of equipment, collect historical data from their normal operating conditions. Apply statistical analysis methods to analyze and process the collected normal operating data and determine the normal operating data range for each operating parameter. This range should reflect the parameter fluctuation range of the equipment under normal operating conditions. The determined normal operating data range is stored in the database for subsequent comparison and analysis.

[0038] The preprocessed sensor data is compared point by point with the corresponding normal state data. During the comparison process, it is determined whether the sensor data falls within the normal working data range. If the sensor data exists within the normal working data range, the equipment working state is determined to be normal, and a normal monitoring signal is generated. The signal should include the equipment identification information, data collection time, a brief description of the normal state, etc. If the sensor data does not exist within the normal working data range, the equipment working state is determined to be abnormal, and an abnormal analysis signal is generated. In addition to the equipment identification information and data collection time, the signal should also record in detail the abnormal parameter name, abnormal value, degree of deviation from the normal range and other information.

[0039] The generated normal monitoring signal is transmitted to the normal situation analysis module, and the generated abnormal analysis signal is transmitted to the abnormal situation analysis module.

[0040] Normal situation analysis module, which is used to analyze the acquired normal monitoring signals and receive normal monitoring information from relevant data sources. This information includes real-time data collected by sensors. A time period T is set, which can be flexibly adjusted according to the characteristics of the equipment and actual needs. Within each time period T, statistical analysis is performed on key parameters of the sensor data, including but not limited to the average value, maximum value, minimum value, and change rate of the parameters. The parameter changes of the sensor data in the current period are carefully compared with the changes in the pre-abnormal stage data corresponding to the abnormal state in the historical data. A similarity threshold is set. If the similarity between the current sensor data and the historical pre-abnormal stage data exceeds the threshold, the two are determined to match and detailed fault warning information is generated; otherwise, it is determined to be mismatched and normal monitoring information is generated;

[0041] For example, let's assume that the time period T is 1 hour. The historical database records that before an overheating fault occurred, the motor's current value continued to rise by more than 10% within an hour. Starting at a certain point, the module monitors the motor's current sensor data on a 1-hour basis. During the nth 1-hour period, it finds that the motor current value has increased from an initial 50A to 56A, a 12% increase. This exceeds the characteristic of current increases exceeding 10% in the historical data before the abnormality.

[0042] Because the current sensor data (current increase amplitude) matches the historical data before the abnormality (current increase amplitude before the overheating fault), the module determines that there is a risk of overheating fault in the current working state of the motor.

[0043] Digital control output module, which is used to display the acquired fault warning information and normal monitoring information to the corresponding operators.

[0044] Example 2

[0045] As the second embodiment of the present invention, it is implemented on the basis of the first embodiment, and differs from the first embodiment in the following aspects:

[0046] The abnormal situation analysis module is used to process the acquired abnormal analysis signal, obtain the abnormal parameters in the sensor data, and obtain the associated parameters of the abnormal parameters. The associated parameters here are represented by the changes in parameters caused by the abnormal parameters. The corresponding changed parameters are marked as associated parameters. The abnormal cause is determined by combining the abnormal parameters and the associated parameters. The specific determination method is as follows:

[0047] Extract core abnormal parameters (such as excessive temperature or sudden current surge) from abnormal analysis signals and record their abnormal values, deviation from the normal range, duration, and other characteristics. Based on the device's operating principles, automatically match physical parameters related to the abnormal parameters (for example, a temperature anomaly may be associated with current, vibration frequency, or cooling fan speed). Calculate the Pearson correlation coefficient or mutual information value between parameters using historical data, and select parameters with a correlation greater than 0.7 as associated parameters.

[0048] Monitor related parameters in real time, marking their changing trends (increase / decrease), change rates (e.g., current increases by 2A per minute), and whether they exceed the normal range when an anomaly occurs. Establish a "parameter-cause" mapping rule base, including:

[0049] Threshold trigger reason: For example, "Temperature > 90°C" corresponds to "Cooling system failure" and "Excessive load".

[0050] Trend triggering reasons: For example, "current continues to rise and exceeds the rated value" corresponds to "winding short circuit" and "mechanical jam";

[0051] Take the intersection of the abnormal parameters and the cause sets of associated parameters to generate a list of common abnormal causes (numbered i = 1, 2, ..., j). For each common cause i, extract its corresponding parameter change template from historical fault cases (including the timing curves, fluctuation amplitude, duration, and other features of the abnormal parameters and associated parameters). Use the dynamic time warping (DTW) algorithm or convolutional neural network (CNN) to calculate the similarity (ranging from 0 to 1) between the change pattern of the current abnormal parameters and associated parameters and each template. Select the common cause with the highest similarity as the standard abnormal cause.

[0052] The processing method screening unit is used to screen the processing method based on the obtained standard exception information, and the specific screening methods are as follows:

[0053] Obtain all processing methods corresponding to standard exception information and number them as a, where a=1, 2, ..., b, where b represents the number of processing methods. Conduct in-depth analysis of the abnormal causes corresponding to the standard exception information to determine whether the abnormality is caused by data collection.

[0054] If the anomaly is caused by data collection, a data collection anomaly message will be generated. This message will be directly transmitted to the digital control output module and the process of re-collecting data will be started.

[0055] If the anomaly is not caused by data collection, processing and resolution information is generated for further analysis of the processing method.

[0056] For each treatment method a, obtain the corresponding number of same-type treatments and the total number of treatments. The number of same-type treatments refers to the number of times the current standard exception information is resolved. According to the formula "same-type index = same-type treatment number ÷ total number of treatments", calculate the same-type index for each treatment method, count the number of applicable times corresponding to treatment method a, and calculate its quantitative proportion. The calculation formula is "applicable proportion = applicable times ÷ total number of treatments", obtain the number of same-type recurrences corresponding to treatment method a, and calculate the recurrence rate. The formula for calculating the recurrence rate is "recurrence rate = same-type recurrence number ÷ same-type treatment number";

[0057] The calculated same-type index, applicable proportion, and recurrence rate are weighted and summed, and the effectiveness index is calculated according to the formula "effectiveness index = same-type index × q1 + applicable proportion × q2 + recurrence rate × q3", where q1, q2, and q3 are the corresponding weights, and the specific values ​​are set by the operator according to actual conditions;

[0058] For each processing method a, obtain its corresponding total processing time and completion time. Completion time refers to the length of time for specific processing adjustments, excluding response time, also known as effective time. According to the formula "Processing efficiency = Completion time ÷ Total processing time", calculate the processing efficiency of each processing method in turn, sum the processing efficiency of the same type of processing methods, and calculate the average value to obtain the processing efficiency index;

[0059] The calculated efficiency index and processing efficiency index are weighted and summed, and the selection value corresponding to each processing method a is calculated according to the formula "selection value = efficiency index × c1 + processing efficiency index × c2", where c1 and c2 are the weights of the efficiency index and processing efficiency index respectively, which can be set by the operator. The processing method a with the smallest selection value is used as the standard to generate a standard processing method, and standard processing information is generated according to the standard processing method and transmitted to the digital control output module.

[0060] In a specific example, the following three processing methods are shown in the table below:

[0061]

[0062] Assume that the operator sets q1=0.5, q2=0.3, q3=0.2, c1=0.6, c2=0.4, and then calculates the indicators of different processing methods respectively.

[0063] Treatment method 1, the same type index is 0.67, the usage ratio is 0.83, the recurrence rate is 0.1, the further calculated effectiveness index is 0.624, and the treatment efficiency index is 0.8;

[0064] Treatment method 2, the same type index is 0.75, the usage ratio is 0.9, the recurrence rate is 0.07, the further calculated effectiveness index is 0.709, and the treatment efficiency index is 0.75;

[0065] Treatment method 3, the same type index is 0.67, the usage ratio is 0.8, the recurrence rate is 0, the further calculated effectiveness index is 0.625, and the treatment efficiency index is 0.83;

[0066] The selected values ​​were further calculated based on the values ​​obtained by the above calculations. The selected value of processing method 1 was calculated to be 0.6944, the selected value of processing method 2 was calculated to be 0.7254, and the selected value of processing method 3 was calculated to be 0.707.

[0067] Since the selection value of processing method 1 is the smallest, processing method 1 is the standard processing method, and the corresponding standard processing information is generated and transmitted to the digital control output module.

[0068] Digital control output module, which is used to display the generated standard processing information to the corresponding operators.

[0069] Embodiment 3, as the third embodiment of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2.

[0070] Some of the data in the above formulas are calculated based on their numerical values ​​and are not substituted into parameter units for calculation. At the same time, the contents not described in detail in this specification belong to the existing technologies well known to those skilled in the art.

[0071] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. 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. A digital management and control platform based on the Internet of Things and big data, characterized by: include: The sensor data analysis module is used to match the acquired sensor data with the normal state data. If the two match, a normal monitoring signal is generated; otherwise, an abnormal analysis signal is generated and both are transmitted simultaneously; The normal situation analysis module is used to analyze the acquired normal monitoring signals, obtain the parameter changes of the sensor data within the time period, and compare them with the data changes in the pre-abnormal stage. If the two match, a fault warning message is generated; otherwise, normal monitoring information is generated, and both are transmitted to the digital control output module at the same time; The abnormal situation analysis module is used to analyze the acquired abnormal analysis signal, determine the abnormal parameters and related parameters, and obtain the abnormal causes corresponding to the two. At the same time, the abnormal causes are screened according to the changes in the parameters of the two to obtain standard abnormal causes, generate standard abnormal information, and transmit it to the processing method screening unit; The processing method screening unit is used to screen the processing methods according to the standard exception information, determine the relationship between the exception cause corresponding to the standard exception information and the data collection, generate data collection exception information or processing solution information, analyze the processing solution information, calculate the efficiency index and processing efficiency index corresponding to the processing method respectively, and sum them to obtain the selected value of the processing method, generate standard processing information based on the processing method with the smallest selected value, and transmit it to the digital control output module at the same time.

2. A digital management and control platform based on the Internet of Things and big data according to claim 1, characterized in that: The specific manner in which the sensor data analysis module matches the acquired sensor data with the normal state data is as follows: Compare the sensor data with the normal state data determined based on the normal working data of different devices. If the sensor data is within the normal working data range, it indicates that the device is working normally and a normal monitoring signal is generated; If it is not within this range, it indicates that the equipment is working abnormally and an abnormal analysis signal is generated.

3. The digital management and control platform based on the Internet of Things and big data according to claim 1 is characterized in that: The specific method in which the normal situation analysis module analyzes the acquired normal monitoring signal is as follows: Acquire sensor data with a time period of T and monitor the changes in its periodic parameters. At the same time, retrieve the changes in the data before the abnormal state corresponding to the historical data and compare and analyze them with the current sensor data; If the two match, it indicates that the current working state has a fault risk, and a fault warning message is generated; If there is no match, it indicates that the working status is normal, normal monitoring information is generated, and then the two types of information are transmitted to the digital control output module.

4. The digital management and control platform based on the Internet of Things and big data according to claim 1, characterized in that: The specific method in which the abnormal situation analysis module analyzes the acquired abnormal analysis signal is as follows: Obtain the abnormal causes corresponding to the abnormal parameters and associated parameters, screen out the common abnormal causes and number them as i, where i=1, 2, ..., j, where j is the number of common abnormal causes. Then obtain the parameter changes corresponding to these common abnormal causes, compare them with the changes in the abnormal parameters and associated parameters, select the one with the closest change as the standard abnormal cause, generate standard abnormal information, and transmit it to the processing method screening unit.

5. The digital management and control platform based on the Internet of Things and big data according to claim 1 is characterized in that: The specific method for the processing method screening unit to generate data collection exception information or processing solution information is: Obtain the corresponding processing method for standard exception information and number it as a, where a=1, 2, ..., b, and b is the number of processing methods. Analyze the abnormal cause of the standard exception information and determine whether the abnormality is caused by data collection. If so, data collection exception information is generated and transmitted to the digital control output module, and data is re-collected. If not, processing and solution information is generated and analyzed at the same time.

6. The digital management and control platform based on the Internet of Things and big data according to claim 5, characterized in that: The specific method of analyzing the processing solution information by the processing method screening unit is: The generated processing solution information is analyzed to obtain all processing methods a, and the effectiveness and processing efficiency corresponding to the processing methods a are analyzed respectively, and the corresponding effectiveness index and processing efficiency index are calculated.

7. The digital management and control platform based on the Internet of Things and big data according to claim 6, characterized in that: The specific method for the processing method screening unit to calculate the efficiency index of the processing method is: Obtain the number of treatments of the same type and the total number of treatments for treatment method a. Calculate the same type index using the formula "same type index = number of treatments of the same type ÷ total number of treatments." Then calculate the percentage of treatment method a's applicable times using the formula "applicable percentage = number of applicable times ÷ total number of treatments." Also obtain the number of recurrences of the same type and calculate the recurrence rate using the formula "recurrence rate = number of recurrences of the same type ÷ number of treatments of the same type." The calculated indicators of the same type, applicable proportion and recurrence rate are summed up and the effectiveness index is calculated according to the formula: effectiveness index = indicator of the same type × q1 + applicable proportion × q2 + recurrence rate × q3, where q1, q2 and q3 are the corresponding weights, and the specific values ​​are set by the operator.

8. The digital management and control platform based on the Internet of Things and big data according to claim 6, characterized in that: The specific method for the processing method screening unit to calculate the processing efficiency index of the processing method is: Get the total processing time corresponding to processing method a, and get the completion time in the total processing time. According to the formula processing efficiency = completion time ÷ total time, get the total number of processing times corresponding to processing method a, and calculate the processing efficiency in turn. Then sum the processing efficiencies and calculate the average value to obtain the processing efficiency index.

9. The digital management and control platform based on the Internet of Things and big data according to claim 1, characterized in that: The specific method of the processing method screening unit generating standard processing information based on the processing method with the smallest selected value is as follows: The calculated efficiency index and processing efficiency index are summed, and the selected value is calculated according to the formula = efficiency index × c1 + processing efficiency index × c2 to obtain the selected value corresponding to processing method a. The processing method a corresponding to the smallest selected value is used as the standard to generate a standard processing method. At the same time, standard processing information is generated and transmitted to the digital control output module.

Images