Instrument remote intelligent control method and system based on Internet of Things

Abstract

The invention relates to the technical field of instrument and meter control, and discloses an instrument and meter remote intelligent control method and system based on the Internet of Things. The method comprises the following steps: acquiring real-time data and historical data of an instrument; calculating a factor influence value according to the real-time data, the historical data and a preset weight value; according to the real-time data and the historical data, carrying out life prediction to obtain a life prediction value; calculating an influence degree real-time value according to the preset weight value, the factor influence value and the life prediction value; and when the influence degree real-time value is greater than or equal to a preset early warning threshold value, generating a maintenance early warning signal, so that an operation and maintenance end monitors and maintains the instrument according to the maintenance early warning signal. According to the method, the timeliness of fault detection and processing can be effectively improved, the possibility of production interruption is reduced, and the maintenance efficiency and the product quality are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of instrument control, and in particular to a remote intelligent control method and system for instruments based on the Internet of Things. Background Art

[0002] Instruments are devices or devices used to detect, measure, record, control, display or analyze various physical, chemical, biological and other parameters. They are widely used in industry, science, engineering, medicine and other fields, mainly for the measurement and control of parameters such as temperature, pressure, flow, current, voltage, gas composition, physical displacement, etc. Many instruments can display the current measurement value, or record and store the data for later analysis and use. Some instruments can process and analyze the measured data to generate more meaningful results, such as gas analyzers, spectrometers, etc. Instruments play an important role in various scenarios. By measuring and controlling key parameters, they can ensure the stability of the production process, improve product quality, and monitor and ensure environmental safety.

[0003] In the existing instrumentation fault detection technology, the operating status of the instrumentation is usually sent to the platform. After receiving the operating status information, the platform will issue an alarm based on the status information, and the staff will go to the site to handle it. This processing method is not timely and the on-site maintenance is difficult. At the same time, manual inspections also have the problems of long inspection cycles, inability to understand the operating status of the instrumentation in real time, and untimely fault detection, which leads to production interruptions and reduced product quality.

[0004] In summary, the existing instrumentation fault detection has the problems of long inspection cycle and untimely fault detection, which in turn leads to production interruption or deterioration of product quality. Summary of the invention

[0005] The present invention provides an instrument remote intelligent control method and system based on the Internet of Things, which can understand the operating status of the instrument in real time, perform data analysis and predictive maintenance, discover faults in time, and improve the timeliness of fault handling.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a remote intelligent control method for instruments based on the Internet of Things, comprising: Obtain real-time and historical data of instruments; Calculating factor impact values ​​according to the real-time data, the historical data and preset weight values; Performing life prediction based on the real-time data and the historical data to obtain a life prediction value; Calculate the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value; When the real-time value of the impact degree is greater than or equal to a preset warning threshold, a maintenance warning signal is generated, so that the operation and maintenance end monitors and maintains the instrument according to the maintenance warning signal.

[0007] Preferably, the real-time data includes real-time temperature value, real-time humidity value, real-time air pressure value and real-time gas concentration value; The historical data includes historical temperature values, historical humidity values, historical air pressure values, and historical gas concentration values.

[0008] Preferably, the calculating the factor influence value according to the real-time data, the historical data and the preset weight value includes: Calculate the change rate of each data according to the real-time data and the historical data to obtain the factor change rate; The factor impact value is calculated according to the factor change rate and the preset weight value.

[0009] Preferably, the calculating of the change rate of each data according to the real-time data and the historical data to obtain the factor change rate includes: The factor change rate is calculated by the following formula: In the formula, For real-time data Class collection value; is the i-th type of collected value in historical data; is the rate of change of the factor.

[0010] Preferably, the calculating the factor impact value according to the factor change rate and the preset weight value includes: According to the factor change rate and the preset weight value, the single factor impact value is calculated; wherein the calculation formula of the single factor impact value is: In the formula, is the weight of the change rate of the i-th factor; is the factor change rate; is the single factor influence value; According to the single factor influence values, summation is performed to obtain the factor influence value. Preferably, performing life prediction based on the real-time data and the historical data to obtain a life prediction value includes: Performing time series processing on the real-time data and the historical data to obtain time series data; Inputting the time series data into a pre-trained long short-term memory neural network for prediction to obtain a predicted value of pending life span; Calculating the prediction accuracy based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy; When the prediction accuracy is greater than a preset threshold, the undetermined life prediction value is used as the life prediction value.

[0011] Preferably, the prediction accuracy is calculated based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy, including: The prediction accuracy is calculated by the following formula: In the formula, For prediction accuracy; is the predicted value of the pending life span; The preset standard lifespan; is a natural constant.

[0012] Preferably, the calculating of the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value includes: The real-time value of the impact degree is calculated by the following formula: In the formula, is the predicted value of the pending life span; is the weight of the change rate of the i-th factor; is the factor influence value; It is the real-time value of the impact degree.

[0013] In a second aspect, the present invention provides an instrument remote intelligent control system based on the Internet of Things, comprising: Data acquisition module, used to obtain real-time data and historical data of instruments; A factor calculation module, used to calculate the factor impact value according to the real-time data, the historical data and the preset weight value; A life prediction module, used to perform life prediction based on the real-time data and the historical data to obtain a life prediction value; An impact calculation module, used to calculate a real-time value of the impact degree according to the preset weight value, the factor impact value and the life prediction value; The warning generation module is used to generate a maintenance warning signal when the real-time value of the impact degree is greater than or equal to a preset warning threshold, so that the operation and maintenance end can monitor and maintain the instrument according to the maintenance warning signal.

[0014] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for remote intelligent control of instruments and meters based on the Internet of Things.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned remote intelligent control methods for instruments based on the Internet of Things.

[0016] Compared with the prior art, the present invention has the following beneficial effects: the embodiment of the present invention provides a remote intelligent control method and system for instruments and meters based on the Internet of Things. The method includes: obtaining real-time data and historical data of instruments and meters; calculating factor influence values ​​according to the real-time data, the historical data and the preset weight value; performing life prediction according to the real-time data and the historical data to obtain a life prediction value; calculating the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value; when the real-time value of the degree of influence is greater than or equal to the preset warning threshold, generating a maintenance warning signal, so that the operation and maintenance end monitors and maintains the instruments and meters according to the maintenance warning signal.

[0017] In the present invention, the method can obtain the real-time data and historical data of the instrument, calculate the factor influence value in combination with the preset weight value, perform life prediction in combination with the real-time data and historical data, and calculate the life prediction value. Then, the real-time value of the degree of influence is calculated according to the obtained factor influence value, life prediction value and preset weight value. The real-time value of the degree of influence can be used to determine whether the instrument needs maintenance at this time, so as to generate a maintenance warning signal, thereby realizing real-time monitoring and predictive maintenance of the instrument. The method effectively improves the timeliness of fault detection and processing, reduces the possibility of production interruption, and improves maintenance efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a remote intelligent control method for instruments and meters based on the Internet of Things provided by the first embodiment of the present invention; Figure 2 It is a structural diagram of an instrument remote intelligent control system based on the Internet of Things provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] Reference Figure 1 The first embodiment of the present invention provides a remote intelligent control method for instruments and meters based on the Internet of Things, comprising the following steps: S11, obtain real-time data and historical data of instruments.

[0021] S12, calculating the factor influence value according to the real-time data, the historical data and the preset weight value.

[0022] S13, performing life prediction based on the real-time data and the historical data to obtain a life prediction value.

[0023] S14, calculating a real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value.

[0024] S15, when the real-time value of the impact degree is greater than or equal to a preset warning threshold, a maintenance warning signal is generated, so that the operation and maintenance end monitors and maintains the instrument according to the maintenance warning signal.

[0025] It is worth mentioning that instruments are devices or equipment used to detect, measure, record, control, display or analyze various physical, chemical, biological and other parameters. They are widely used in the fields of industry, science, engineering, medicine, etc., mainly for the measurement and control of parameters such as temperature, pressure, flow, current, voltage, gas composition, physical displacement, etc.

[0026] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0027] In step S11, real-time data and historical data of instruments are obtained.

[0028] Optionally, the real-time data includes a real-time temperature value, a real-time humidity value, a real-time air pressure value, and a real-time gas concentration value. The historical data includes a historical temperature value, a historical humidity value, a historical air pressure value, and a historical gas concentration value.

[0029] Specifically, each real-time data can be obtained through different types of sensors. Optionally, the real-time temperature value can be collected through a temperature sensor (such as a thermocouple, a thermistor, an infrared temperature sensor). These sensors are usually connected to instruments and provide accurate readings of the current environment or the temperature inside the device, and the data is transmitted to the system through a data acquisition module. The real-time humidity value uses a humidity sensor (such as a capacitive humidity sensor, an impedance humidity sensor) to obtain the current environmental humidity information. The humidity data output by the sensor will be transmitted to the control system in real time through a data interface or a communication module. The atmospheric pressure or the internal pressure value of the device is collected in real time through a pressure sensor (such as an absolute pressure sensor, a differential pressure sensor). This type of sensor is usually installed inside the instrument or in the environment to measure and output pressure values. A gas sensor (such as a gas concentration detection module, an electrochemical gas sensor, an infrared gas detector) is used to detect the concentration of a specified gas. The gas concentration data detected by the sensor will be transmitted to the system in real time for monitoring and analysis.

[0030] Specifically, each historical data can be obtained by extracting it from the storage space. Optionally, the historical temperature values ​​are recorded and stored for a long time through a storage mechanism for real-time temperature data (such as a database or a data recording module). The historical data can be read from the storage module for trend analysis and fault diagnosis. The real-time humidity data is recorded and stored as historical humidity data through the data acquisition module. These data are saved in a database or storage system for subsequent analysis and prediction. The real-time pressure data collected by the pressure sensor is stored as historical data and saved in a dedicated data storage system or database. The data storage cycle and update frequency can be adjusted according to demand. The data collected by the gas sensor in real time is stored as historical data for analyzing the changing trend of gas concentration. The storage method of historical gas concentration data includes cloud storage or local database, which is determined according to the needs of the system.

[0031] It is worth noting that the various measurement values ​​included in the real-time data and the historical data are the factors described below. The factor change rate can be obtained by calculating the change rate of each data based on the real-time data and the historical data.

[0032] In step S12, factor influence values ​​are calculated based on the real-time data, the historical data and preset weight values.

[0033] Preferably, the calculating the factor influence value according to the real-time data, the historical data and the preset weight value includes: Calculate the change rate of each data according to the real-time data and the historical data to obtain the factor change rate; The factor impact value is calculated according to the factor change rate and the preset weight value.

[0034] Preferably, the calculating of the change rate of each data according to the real-time data and the historical data to obtain the factor change rate includes: The factor change rate is calculated by the following formula: In the formula, For real-time data Class collection value; is the i-th type of collected value in historical data; is the rate of change of the factor.

[0035] Preferably, the calculating the factor impact value according to the factor change rate and the preset weight value includes: According to the factor change rate and the preset weight value, the single factor impact value is calculated; wherein the calculation formula of the single factor impact value is: In the formula, is the weight of the change rate of the i-th factor; is the factor change rate; is the single factor influence value; According to the single factor influence values, summation is performed to obtain the factor influence value.

[0036] Specifically, firstly, the change rate of each data is calculated to obtain the factor change rate. The purpose is to calculate the change rate (factor change rate) by comparing the difference between real-time data and historical data, reflecting the degree of change of the system state. The meaning of the calculation formula is to calculate the ratio of the difference between the current real-time value and the historical benchmark value and convert it into a percentage. Through this calculation, the degree of deviation between the current state and the historical state is obtained, thereby providing a basis for the calculation of the subsequent impact value. Secondly, the single factor impact value is calculated. Based on the calculated factor change rate and the corresponding preset weight value, the individual impact value of each factor is calculated to indicate the degree of influence of the factor on the overall system. Finally, after calculating all the single factor impact values, they are summed up to obtain the overall factor impact value, reflecting the state change and possible impact of the overall system. By accumulating the impact values ​​of all single factors, an overall system impact assessment value is formed. This value is used for subsequent system monitoring, prediction and early warning functions. In the present invention, the steps can derive the change trend of the system by comparing the real-time data with the historical data, and calculate the degree of influence of each factor in combination with the preset weight value. Through this comprehensive evaluation method, the system can comprehensively evaluate and monitor the status of instruments and meters, thereby providing data support for subsequent predictive maintenance and fault warning.

[0037] Optionally, the weight of the change rate of the i-th factor can be determined by analyzing historical data and using historical data and statistical methods to determine the degree of influence of each factor on system performance. For example, correlation analysis, regression analysis and other methods are used to evaluate the influence of changes in each factor on system output or overall performance. Weight values ​​are assigned according to the analysis results. A higher correlation or degree of influence means that the factor is more important, so a higher weight value can be assigned. When making the determination, a multi-objective optimization algorithm can be used to comprehensively determine the weight values ​​of each factor based on multiple objectives of the system (such as stability, reliability, cost, etc.). Various constraints and priorities may be involved in the optimization objective function to obtain a combination of weight values ​​that makes the system perform best. Optionally, in some complex systems, machine learning methods (such as regression models, neural networks) can be used to train the model to automatically learn and adjust the weight values ​​of each factor based on the input-output relationship of historical data and system status. For example, by constructing a training model, the system can automatically optimize the weight value through a large amount of historical data to minimize errors or achieve specific performance goals.

[0038] It is worth noting that the main purpose of calculating the factor change rate is to reflect the degree of change of the current system state by comparing the difference between real-time data and historical data, so as to provide a basis for further system analysis and decision-making. By calculating the factor change rate, the change range of the current real-time data relative to the historical benchmark data can be quantified, so as to determine whether the system state has changed significantly. For example, sudden changes in parameters such as temperature, humidity, and air pressure may mean potential equipment failure or environmental abnormality. When calculating the factor impact value, the change rate is an important intermediate variable, which needs to be combined with the preset weight value to further calculate the single factor impact value. This helps to weight the comprehensive impact of the changes in different factors on the system. By combining with the weight, the change rate can better reflect the degree of impact of different factors on the overall system. For factors with a large change range, the impact on the system may be more significant, and the application of weights can more accurately amplify or suppress this impact. In the process of data analysis, the change trend of the system state is an important reference for optimizing decisions. By calculating the change rate, the system can capture short-term and long-term trend changes, providing basic data for subsequent predictive maintenance, system optimization, and data modeling. The calculation of the change rate helps the system make different operational decisions when the data changes drastically or tends to be stable. For example, when the rate of change is close to zero, the system may consider the state to be stable and no intervention is required; when the rate of change is large, adjustment measures may be required. In complex systems, real-time data alone may not accurately identify abnormal situations. However, by comparing with historical data, the calculated rate of change can reveal potential abnormal situations, such as trend changes or mutations. When the rate of change exceeds the set threshold, it can be considered that the system is abnormal. Such a threshold monitoring mechanism helps the system identify faults in advance, predict future trends or potential fault points, and thus provide early warning or maintenance.

[0039] In step S13, life prediction is performed based on the real-time data and the historical data to obtain a life prediction value.

[0040] Preferably, performing life prediction based on the real-time data and the historical data to obtain a life prediction value includes: Performing time series processing on the real-time data and the historical data to obtain time series data; Inputting the time series data into a pre-trained long short-term memory neural network for prediction to obtain a predicted value of pending life span; Calculating the prediction accuracy based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy; When the prediction accuracy is greater than a preset threshold, the undetermined life prediction value is used as the life prediction value.

[0041] Preferably, the prediction accuracy is calculated based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy, including: The prediction accuracy is calculated by the following formula: In the formula, For prediction accuracy; is the predicted value of the pending life span; The preset standard lifespan; is a natural constant.

[0042] Specifically, life prediction can help the system identify potential problems before equipment failure occurs and take maintenance measures in time, thereby avoiding sudden damage to the equipment or major failures. In the subsequent steps of the present invention, the impact value is an important parameter used by the system to determine whether the current status of the instrument requires maintenance or intervention measures. The calculation of the impact value involves a comprehensive evaluation of multiple factors, and the life prediction value is one of the key factors. By predicting the future life of the equipment, the system can more accurately assess the potential risks of the equipment or the upcoming changes in status, and use it as one of the evaluation criteria.

[0043] It is worth mentioning that LSTM, the full name of which is Long Short-Term Memory, is a special recurrent neural network (RNN) designed to solve the limitations of ordinary RNN in long time series tasks. When processing long sequence data, RNN is prone to the problems of gradient vanishing and gradient explosion, resulting in poor ability to capture long-term dependencies, while LSTM overcomes this by introducing special structural units. The basic unit of LSTM consists of the following main parts: Cell State: responsible for storing and transmitting long-term context information. The cell state can be regarded as a "memory" throughout the entire time series, which is updated and operated in different time steps. Input Gate: controls whether the current input information can be updated to the cell state. The input gate determines the importance of new information and what information is allowed to enter the memory. Forget Gate: controls whether the information in the cell state needs to be "forgotten" or retained. It can decide whether to "forget" the information of the previous time step, thereby preventing useless or old information from interfering with the prediction. Output Gate: controls whether the information in the cell state is output to the current time step as the output of the LSTM unit.

[0044] In the present invention, the role of LSTM (Long Short-Term Memory Network) is to perform deep learning modeling on the historical data of instruments and meters, so as to predict the life of the equipment. The main task of LSTM is to use the input time series data to predict the life of the equipment and obtain a pending life prediction value. Through the long short-term memory unit, LSTM can "remember" important historical status information and "forget" irrelevant or unimportant information, so as to better capture the changing trend of the equipment operation status over a long period of time.

[0045] Specifically, life prediction needs to be analyzed based on the historical and real-time data of the equipment, which often has time dependence and trend. Through historical time series processing, the time series characteristics of the data can be extracted, making the prediction more accurate and valuable for reference. Specifically, the training of the LSTM model mainly includes: before model training, the LSTM network needs to initialize the weights and bias values. The parameter initialization of the model will affect the final training effect. The model receives input data and performs forward propagation, gradually calculating the output at each time step. At each time step, the LSTM unit uses its internal "memory unit" and "gate mechanism" to decide which information needs to be remembered, forgotten or output. By comparing the predicted output of the model with the actual label (i.e., the target life value), the loss function is calculated. The loss function can use the mean square error (MSE). Using the backpropagation algorithm, the gradient of the loss function for each parameter is calculated, and then the weight of the model is updated using gradient descent or other optimization algorithms. This process is repeated in multiple training iterations until the model achieves the expected performance. After training, the LSTM model can receive new time series data input and predict the pending life value of the equipment. The model analyzes the input time series data and uses its "memory" characteristics and time dependency to derive the future trend and possible life status of the equipment. The output of the LSTM model is the predicted value of pending life. This value represents the estimated remaining life of the equipment under the current state and historical trends, providing a reference for subsequent system maintenance, management, and optimization.

[0046] It is worth noting that after the predicted value of the pending life is calculated, in order to ensure the reliability of the model prediction, the predicted value of the pending life will be compared with the preset standard life, and the accuracy of the prediction will be calculated. Only when the prediction accuracy is greater than the set threshold, the prediction result will be used as a valid life prediction value.

[0047] Specifically, the core of the calculation formula for prediction accuracy is to calculate the difference between the predicted value of the pending life and the preset standard life. The formula first calculates the relative difference between the predicted value of the pending life and the preset standard life, that is, , this relative difference indicates the degree of deviation between the predicted value and the standard value, and is a normalized difference. Put this relative difference into the negative exponent of the exponential function. The effect of this is that when the predicted value is close to the standard value, the difference is small and the exponent value is close to 0; therefore, the prediction accuracy is close to 1, indicating that the prediction effect is very good. Conversely, when the difference is large, the negative exponent causes the prediction accuracy value to decrease rapidly, approaching 0, indicating that the prediction accuracy is low. The advantage of using natural constants for exponential calculations is its sensitivity to changes. Even small changes in differences can be quickly reflected in changes in prediction accuracy by the exponential function, making the calculation more sensitive and accurate.

[0048] In step S14, a real-time value of the degree of influence is calculated according to the preset weight value, the factor influence value and the life prediction value.

[0049] Preferably, the calculating of the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value includes: The real-time value of the impact degree is calculated by the following formula: In the formula, is the predicted value of the pending life span; is the weight of the change rate of the i-th factor; is the factor influence value; It is the real-time value of the impact degree.

[0050] Specifically, the formula is the weight of the change rate of the i-th factor. This weight value reflects the different degrees of influence of each factor on the system. A higher weight means that the factor has a greater overall impact on the system. By assigning weights to each factor, the calculation results can be flexibly adjusted so that the system can make differentiated treatments on the impact of different factors according to actual needs. For example, for devices that are more sensitive to temperature changes, the weight of the temperature factor can be set higher to ensure that it contributes more to the degree of influence.

[0051] Specifically, The factor impact value is the value calculated in the previous step, which reflects the comprehensive impact of each factor on the system. The factor impact value combines the changes in real-time data and historical data, and combines it with the preset weight value to express the impact of each factor on the system. By multiplying the weight value and the factor impact value, the formula can quantify the actual impact of each factor into a weighted impact value as a component of the system status assessment.

[0052] At the same time, the inverse of the life prediction value is introduced into the formula in order to relate the life prediction result to the degree of impact, so that when the predicted life is shorter, the contribution to the degree of impact is greater. The smaller the life prediction value, the equipment is about to reach its service life or may face a higher risk of failure. Therefore, by introducing As an adjustment factor, it can amplify or reduce the effect of the factor's impact value, ensuring that the system can respond more sensitively to potential risks in the short term of the equipment's life. For example, if it is predicted that the equipment's life is about to end (i.e. is smaller), then the will increase, thereby improving The value of makes the system pay more attention to the current status and potential impact of the device.

[0053] Specifically, the formula obtains a comprehensive real-time value of the degree of influence by weighting and summing the influence values ​​of all factors. This cumulative calculation method can comprehensively reflect the degree to which the system is affected by the combined influence of multiple factors. The larger the value, the greater the risk or impact the system may face, and timely maintenance or adjustment is required. By combining the impact of various factors and the life prediction results, the system can fully evaluate the current status and take corresponding measures.

[0054] In step S15, when the real-time value of the impact degree is greater than or equal to the preset warning threshold, a maintenance warning signal is generated, so that the operation and maintenance end monitors and maintains the instrument according to the maintenance warning signal.

[0055] Specifically, when the real-time value of the impact is greater than or equal to the preset warning threshold, the system will generate a maintenance warning signal to notify the operation and maintenance end to take corresponding monitoring and maintenance measures. As described in the above steps, the real-time value of the impact is an indicator calculated by combining multiple factors (such as real-time data, historical data, preset weight values, and life prediction values, etc.) to measure the degree of impact of the current equipment or system. The larger the value, the higher the risk or possibility of failure that the system may face. The process of calculating this value takes into account the current status, historical trends, and future estimated life, thereby providing a comprehensive risk assessment result.

[0056] Specifically, the preset warning threshold is a system-defined threshold value used to determine whether a device or system needs to issue a warning. The setting of this threshold can be based on the device's operating data, historical fault data, or system risk assessment. When the real-time value of the impact degree exceeds or equals this threshold, it means that the system has entered a state where a failure may occur or require attention. Therefore, the system needs to respond to this and trigger corresponding maintenance measures.

[0057] Specifically, once the triggering condition is met, the system will generate a maintenance warning signal. This signal can be in the form of electronic notification, flashing alarm light, alarm sound, digital information sent to the operation and maintenance platform, etc., to remind the operation and maintenance end to pay attention and take action. The warning signal can contain current status information, possible risk sources, recommended maintenance actions, etc., with the purpose of helping the operation and maintenance personnel to quickly understand the problem and deal with it. By generating warning signals and performing maintenance in a timely manner, the system can intervene before the problem develops to a serious stage, thereby preventing the expansion of equipment failures and reducing the risk of equipment downtime. Exemplarily, in industrial production, if the real-time value of the comprehensive impact degree of the equipment, such as temperature, pressure, vibration, etc., exceeds the threshold, the system will generate a maintenance warning signal to prompt the operation and maintenance personnel to check the operating status of the equipment, and may need to adjust the load, lubricate the equipment, or replace parts. In the present invention, by comparing the real-time value of the monitoring impact degree with the preset warning threshold, the system can determine in real time whether the equipment needs maintenance or attention. Generating a maintenance warning signal can remind the operation and maintenance end to intervene in time, prevent possible failures and accidents, and thus improve the service life, stability and safety of the equipment.

[0058] The following describes the working process of the present invention by taking a relatively common scenario as an example. The working process is as follows: In an industrial production environment, there are several key instruments used to monitor and control production parameters (such as temperature, humidity, air pressure, gas concentration, etc.). In order to ensure the stable operation of equipment and the continuity of production, the system needs to monitor these instruments in real time and predict and warn of possible failures.

[0059] The system obtains real-time data through various sensors (such as temperature sensors, humidity sensors, air pressure sensors, and gas concentration sensors), and reads historical data through the history record module. Real-time data reflects the current equipment status, and historical data provides a benchmark for past operating conditions. The combination of the two is used to analyze the difference between the current status and the historical status.

[0060] The system calculates the change rate of each data (factor change rate) based on the acquired real-time data and historical data, and calculates the factor impact value in combination with the preset weight value. The factor impact value quantifies the influence of each parameter on the overall state of the system, and can reflect which factors have changed most significantly, thereby providing data support for subsequent comprehensive evaluation.

[0061] The processed time series data is input into the long short-term memory neural network (LSTM) for prediction to obtain the predicted value of the equipment's pending life. Then, the system calculates the accuracy of the prediction, and only when the accuracy reaches the set threshold will the predicted value be used as a valid life prediction value.

[0062] The system combines the preset weight value, factor impact value and life prediction value to calculate the real-time impact value. This value reflects the comprehensive impact of the current equipment status. The real-time impact value is a key indicator for judging whether the equipment status requires intervention. When the value is high, it indicates that the system may face a greater risk and needs to take corresponding countermeasures.

[0063] When the real-time value of the impact degree is greater than or equal to the preset warning threshold, the system generates a maintenance warning signal to notify the operation and maintenance end to perform equipment inspection and maintenance. By generating warning signals, the system can promptly remind the operation and maintenance personnel to intervene, thereby avoiding equipment failure escalation and ensuring the continuity and stability of production.

[0064] In summary, the present invention provides a remote intelligent control method for instruments and meters based on the Internet of Things, including: acquiring real-time data and historical data of instruments and meters; calculating factor influence values ​​according to the real-time data, the historical data and preset weight values; performing life prediction according to the real-time data and the historical data to obtain a life prediction value; calculating a real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value; when the real-time value of the degree of influence is greater than or equal to a preset warning threshold, generating a maintenance warning signal, so that the operation and maintenance end monitors and maintains the instruments and meters according to the maintenance warning signal.

[0065] In the present invention, the method can obtain the real-time data and historical data of the instrument, calculate the factor influence value in combination with the preset weight value, perform life prediction in combination with the real-time data and historical data, and calculate the life prediction value. Then, the real-time value of the degree of influence is calculated according to the obtained factor influence value, life prediction value and preset weight value. The real-time value of the degree of influence can be used to determine whether the instrument needs maintenance at this time, so as to generate a maintenance warning signal, thereby realizing real-time monitoring and predictive maintenance of the instrument. The method effectively improves the timeliness of fault detection and processing, reduces the possibility of production interruption, and improves maintenance efficiency and product quality.

[0066] Reference Figure 2 The second embodiment of the present invention provides an instrument remote intelligent control system based on the Internet of Things, including: Data acquisition module, used to obtain real-time data and historical data of instruments; A factor calculation module, used to calculate the factor impact value according to the real-time data, the historical data and the preset weight value; A life prediction module, used to perform life prediction based on the real-time data and the historical data to obtain a life prediction value; An impact calculation module, used to calculate a real-time value of the impact degree according to the preset weight value, the factor impact value and the life prediction value; The warning generation module is used to generate a maintenance warning signal when the real-time value of the impact degree is greater than or equal to a preset warning threshold, so that the operation and maintenance end can monitor and maintain the instrument according to the maintenance warning signal.

[0067] In an optional implementation, the data acquisition module is specifically used to: Acquire real-time data and historical data of instruments and meters; the real-time data includes real-time temperature value, real-time humidity value, real-time air pressure value and real-time gas concentration value; the historical data includes historical temperature value, historical humidity value, historical air pressure value and historical gas concentration value.

[0068] In an optional implementation, the factor calculation module is specifically used to: Calculate the change rate of each data according to the real-time data and the historical data to obtain the factor change rate; The factor impact value is calculated according to the factor change rate and the preset weight value.

[0069] In an optional implementation, the factor calculation module is specifically used to: The factor change rate is calculated by the following formula: In the formula, For real-time data Class collection value; is the i-th type of collected value in historical data; is the rate of change of the factor.

[0070] In an optional implementation, the factor calculation module is specifically used to: According to the factor change rate and the preset weight value, the single factor impact value is calculated; wherein the calculation formula of the single factor impact value is: In the formula, is the weight of the change rate of the i-th factor; is the factor change rate; is the single factor influence value; According to the single factor influence values, summation is performed to obtain the factor influence value.

[0071] In an optional implementation, the life prediction module is specifically used to: Performing time series processing on the real-time data and the historical data to obtain time series data; Inputting the time series data into a pre-trained long short-term memory neural network for prediction to obtain a predicted value of pending life span; Calculating the prediction accuracy based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy; When the prediction accuracy is greater than a preset threshold, the undetermined life prediction value is used as the life prediction value.

[0072] In an optional implementation, the life prediction module is specifically used to: The prediction accuracy is calculated by the following formula: In the formula, For prediction accuracy; is the predicted value of the pending life span; The preset standard lifespan; is a natural constant.

[0073] In an optional implementation manner, the impact calculation module is specifically used to: The real-time value of the impact degree is calculated by the following formula: In the formula, is the predicted value of the pending life span; is the weight of the change rate of the i-th factor; is the factor influence value; It is the real-time value of the impact degree.

[0074] It should be noted that the remote intelligent control system for instruments and meters based on the Internet of Things provided in an embodiment of the present invention is used to execute all the process steps of the remote intelligent control method for instruments and meters based on the Internet of Things in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0075] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a program for a remote intelligent control method for an instrument based on the Internet of Things. When the processor executes the computer program, the steps in the above-mentioned embodiments of the remote intelligent control method for an instrument based on the Internet of Things are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the impact calculation module.

[0076] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0077] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0078] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0079] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0080] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0081] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0082] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A remote intelligent control method for instruments and meters based on the Internet of Things, characterized in that: include: Obtain real-time and historical data of instruments; Calculating factor impact values ​​according to the real-time data, the historical data and preset weight values; Performing life prediction based on the real-time data and the historical data to obtain a life prediction value; Calculate the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value; When the real-time value of the impact degree is greater than or equal to a preset warning threshold, a maintenance warning signal is generated, so that the operation and maintenance end monitors and maintains the instrument according to the maintenance warning signal.

2. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 1 is characterized in that: The real-time data includes real-time temperature value, real-time humidity value, real-time air pressure value and real-time gas concentration value; The historical data includes historical temperature values, historical humidity values, historical air pressure values, and historical gas concentration values.

3. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 1 is characterized in that: The calculating the factor influence value according to the real-time data, the historical data and the preset weight value includes: Calculate the change rate of each data according to the real-time data and the historical data to obtain the factor change rate; The factor impact value is calculated according to the factor change rate and the preset weight value.

4. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 3 is characterized in that: The step of calculating the change rate of each data according to the real-time data and the historical data to obtain the factor change rate includes: The factor change rate is calculated by the following formula: In the formula, For real-time data Class collection value; is the i-th type of collected value in historical data; is the rate of change of the factor.

5. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 4 is characterized in that: The calculating the factor influence value according to the factor change rate and the preset weight value includes: According to the factor change rate and the preset weight value, the single factor impact value is calculated; wherein the calculation formula of the single factor impact value is: In the formula, is the weight of the change rate of the i-th factor; is the factor change rate; is the single factor influence value; According to the single factor influence values, summation is performed to obtain the factor influence value.

6. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 1 is characterized in that: The performing life prediction according to the real-time data and the historical data to obtain a life prediction value includes: Performing time series processing on the real-time data and the historical data to obtain time series data; Inputting the time series data into a pre-trained long short-term memory neural network for prediction to obtain a predicted value of pending life span; Calculating the prediction accuracy based on the undetermined life prediction value and the preset standard life to obtain the prediction accuracy; When the prediction accuracy is greater than a preset threshold, the undetermined life prediction value is used as the life prediction value.

7. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 6 is characterized in that: The step of calculating the prediction accuracy based on the predicted life value to be determined and the preset standard life to obtain the prediction accuracy includes: The prediction accuracy is calculated by the following formula: In the formula, For prediction accuracy; is the predicted value of the pending life span; The preset standard lifespan; is a natural constant.

8. The remote intelligent control method for instruments and meters based on the Internet of Things according to claim 6 is characterized in that: The calculating the real-time value of the degree of influence according to the preset weight value, the factor influence value and the life prediction value comprises: The real-time value of the impact degree is calculated by the following formula: In the formula, is the predicted value of the pending life span; is the weight of the change rate of the i-th factor; is the factor influence value; It is the real-time value of the impact degree.

9. A remote intelligent control system for instruments and meters based on the Internet of Things, characterized in that: include: Data acquisition module, used to obtain real-time data and historical data of instruments; A factor calculation module, used to calculate the factor impact value according to the real-time data, the historical data and the preset weight value; A life prediction module, used to perform life prediction based on the real-time data and the historical data to obtain a life prediction value; An impact calculation module, used to calculate a real-time value of the impact degree according to the preset weight value, the factor impact value and the life prediction value; The warning generation module is used to generate a maintenance warning signal when the real-time value of the impact degree is greater than or equal to a preset warning threshold, so that the operation and maintenance end can monitor and maintain the instrument according to the maintenance warning signal.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the remote intelligent control method of instruments and meters based on the Internet of Things as described in any one of claims 1 to 8.

Images