An ozone generator adaptive adjustment method and system based on the Internet of Things

Abstract

This invention relates to the field of intelligent control technology, and in particular to an adaptive adjustment method and system for an ozone generator based on the Internet of Things (IoT). The method includes: monitoring the operating status of the ozone generator using an IoT terminal; performing three-dimensional mesh segmentation of the ozone generator's interior and using a deep sequence learning algorithm to predict abnormal states of the ozone generator; the IoT terminal sending an abnormal operating status message transmission request to a monitoring center; the monitoring center providing feedback on the quality of the predicted abnormal states of the ozone generator and outputting adjusted decision parameters using a feedback loop algorithm; and the control center adaptively adjusting the ozone generator according to the updated rule settings. This method enables comprehensive monitoring of the internal state of the ozone generator and automatic adjustment of its operating actions, thereby improving the stability, fault tolerance, and operating efficiency of the ozone generator.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to an adaptive adjustment method and system for an ozone generator based on the Internet of Things. Background Technology

[0002] Ozone, as a strong oxidant, has highly efficient functions such as sterilization, disinfection, and deodorization. Large ozone generators consist of one or more ozone generating units. Each ozone generating unit uses DBS glass dielectric discharge technology, in which a high voltage is applied between a high-voltage electrode and a grounding electrode. The gas ionizes to form plasma, and oxygen molecules dissociate and recombine to generate ozone. The generated ozone can be applied in fields such as wastewater treatment and waste gas treatment.

[0003] However, large ozone generators face numerous challenges during operation. Because they operate under high current and voltage, they generate high temperatures. This high-temperature environment can easily damage the glass media inside the ozone generator, significantly shortening its lifespan and causing the entire generator to stop operating, thus impacting wastewater and waste gas treatment.

[0004] Larger ozone generators are more susceptible to dielectric damage. As generator size increases, maintaining electric field uniformity within the discharge region becomes extremely difficult. In large electrode structures, edge effects become more pronounced, leading to greater differences in discharge intensity between the edge and center regions. This reduces ozone generation efficiency and may cause problems such as localized overheating, affecting the normal operation and lifespan of the ozone generator, thus limiting the manufacture of ozone generators reaching a certain weight.

[0005] Existing technologies have significant shortcomings. Firstly, monitoring methods are relatively limited, currently relying mainly on collecting temperature information from reactors and transformers, cooling water temperature, and internal temperatures to monitor the ozone generator's operating status. Merely relying on temperature changes makes it difficult to determine if other potential internal problems exist, easily leading to misjudgments or missed diagnoses. Secondly, while existing internal monitoring devices can monitor operation by collecting visual information from inside the ozone generator, they lack automatic control and adjustment capabilities, often requiring manual intervention. Existing technical solutions also lack effective predictive technologies, failing to detect and prevent abnormal symptoms in advance. In short, although some methods have been developed to address the overheating problem of ozone generators, these methods still have limitations. Relying solely on temperature monitoring is insufficient to handle the complex and ever-changing conditions inside an ozone generator. While visual information monitoring can provide some operational information, it cannot automatically adjust equipment operations and cannot fundamentally solve the problem.

[0006] In summary, there is a need for a system and method that can comprehensively monitor the internal state of an ozone generator, not only automatically adjust the equipment's operation, but also predict and prevent abnormal symptoms in advance, thereby improving the stability, fault tolerance, and operating efficiency of the ozone generator. Summary of the Invention

[0007] To address the aforementioned problems, this invention provides an adaptive adjustment method and system for ozone generators based on the Internet of Things (IoT).

[0008] In a first aspect, the present invention provides an adaptive adjustment method and system for an ozone generator based on the Internet of Things, which adopts the following technical solution:

[0009] An adaptive adjustment method for an ozone generator based on the Internet of Things (IoT) includes:

[0010] Utilize IoT terminals to monitor the operating status of ozone generators;

[0011] The interior of the ozone generator is divided into three-dimensional meshes, the increasing and decreasing trends of temperature changes are extracted, and the abnormal state of the ozone generator is predicted using a deep sequence learning algorithm.

[0012] Based on the temperature change configuration of the three-dimensional grid segmentation, the incoming voltage demand characteristics are configured, and the IoT terminal sends an ozone generator abnormal operation status message transmission request to the monitoring center.

[0013] The monitoring center provides feedback on the quality of the predicted abnormal state of the ozone generator, and uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results.

[0014] The control center adaptively adjusts the ozone generator according to the updated rules.

[0015] Furthermore, the three-dimensional mesh segmentation includes parsing the temperature measurement data to generate a temperature distribution, identifying each region based on the distribution of the glass medium to generate a first identification constraint, identifying each region within the ozone generator based on the voltage result compensation to generate a second identification constraint, configuring constraint transformation, normalizing the first and second identification constraints using the constraint transformation, randomly distributing cluster centers, performing region-continuous constraint aggregation, setting a minimum aggregation granularity, performing dependency planning on the aggregation results using the minimum aggregation granularity, and realizing three-dimensional mesh segmentation based on the dependency planning results.

[0016] Furthermore, the extraction of the increasing or decreasing trend of temperature change includes configuring standard test data, performing multi-point temperature measurement within the ozone generator under the standard test data, compensating for the incoming voltage result based on the temperature measurement result, and measuring the rate of temperature change over time by differentiating the temperature change of each three-dimensional grid segment within the ozone generator within a preset unit time.

[0017] Furthermore, the prediction of abnormal states of the ozone generator includes collecting temperature change rate data, incoming line voltage data, reactor and transformer temperature data, and historical operating status data in a three-dimensional grid segmentation, organizing the data according to the time series, constructing a model using a long short-term memory network, training the model using the organized data, and using the trained model to predict abnormal states of the ozone generator.

[0018] Furthermore, the configuration of the incoming voltage demand feature based on the temperature change of the three-dimensional mesh segmentation includes performing network initialization of the temperature control decision network with the incoming voltage demand feature, setting trigger nodes and feedback space, and when the increasing or decreasing trend of temperature change is input into the initialized decision network, using an improved clustering algorithm to analyze the abnormal state of the ozone generator, generating decision results, and synchronously generating a feedback supervision space based on the decision results.

[0019] Furthermore, the feedback on the quality of predicting abnormal states of the ozone generator includes setting up an interface to receive historical data for analyzing the prediction results. The historical data includes success rate, task execution time, and sensor utilization efficiency, forming a real-time performance data stream. The real-time performance data stream is analyzed using data analysis algorithms to calculate the indicators of prediction quality. The adjusted decision parameters are output using a feedback loop algorithm to update the rule settings of the feedback supervision space.

[0020] Furthermore, the step of using a feedback loop algorithm to output adjusted decision parameters includes determining the target performance index, using a PID algorithm as a feedback loop algorithm, determining the initial values ​​of the proportional coefficient, integral coefficient, and derivative coefficient of the PID algorithm, obtaining the operating status data of the ozone generator, calculating the error between the current state and the target performance index, and updating the decision parameters based on the calculated control quantity.

[0021] Furthermore, the target performance indicators include the operating temperature range of the medium tube inside the ozone generator, the fluctuation range of the incoming line voltage, the range of gas supply per unit time, and the range of cooling water pressure.

[0022] Furthermore, the adaptive adjustment includes adjusting the incoming voltage of different medium pipe areas, adjusting the gas supply of different medium pipe areas, and adjusting the pressure of the cooling water in the ozone generator, so as to keep the ozone generator operating within the normal range.

[0023] Furthermore, the monitoring center's feedback on the quality of predicting abnormal states of the ozone generator also includes recording multiple rounds of feedback results. Each round of feedback result has a decision effect indicator. The adaptive adjustment effect is optimized based on the multiple rounds of feedback results to generate control optimization results. A new round of adaptive adjustment of the ozone generator is then performed based on the control optimization results.

[0024] Secondly, an adaptive adjustment system for an ozone generator based on the Internet of Things includes:

[0025] IoT terminals are used to monitor the operating status of ozone generators.

[0026] The operation status analysis module is used to perform three-dimensional mesh segmentation inside the ozone generator, extract the increasing and decreasing trends of temperature changes, and use deep sequence learning algorithms to predict abnormal states of the ozone generator.

[0027] The request decision module is used to configure the incoming voltage demand characteristics based on the temperature change of the three-dimensional grid segmentation, and to send an ozone generator abnormal operation status message transmission request from the Internet of Things terminal to the monitoring center.

[0028] The monitoring center is used to predict abnormal states of ozone generators and provide feedback on the quality. It uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results.

[0029] The control center is used to adaptively adjust the ozone generator based on updated rule settings.

[0030] In summary, the present invention has the following beneficial technical effects:

[0031] 1. This invention proposes an adaptive adjustment method and system for ozone generators based on the Internet of Things (IoT). The method monitors the operating status of the ozone generator via an IoT terminal, introducing multi-point temperature measurement and three-dimensional grid segmentation. By differentiating the temperature change of each three-dimensional grid segment within the ozone generator within a preset unit time, the method can accurately grasp the temperature change trend in different areas, providing data support for subsequent analysis of prediction results. Simultaneously, the success rate, task execution time, and sensor utilization efficiency are analyzed at the monitoring center to adjust decision parameters, avoiding potential misjudgments or omissions that may occur when relying solely on a single type of data for monitoring, thus improving the accuracy and reliability of adaptive adjustment.

[0032] 2. The system of this invention has the function of automatically adjusting equipment operation. The control center adaptively adjusts the ozone generator according to updated rule settings, regulating the incoming voltage, gas supply, and cooling water pressure of different medium pipe areas, and responding promptly to abnormal situations during equipment operation. Utilizing deep sequence learning algorithms and improved clustering algorithms for abnormal state prediction and analysis, it is possible to detect and prevent potential abnormal symptoms in the ozone generator in advance, helping to reduce high-temperature damage to the glass medium and providing an effective solution for the manufacturing and stable operation of large ozone generators.

[0033] 3. This invention achieves optimized decision-making. The monitoring center provides multiple rounds of feedback on the quality of predicting abnormal states of the ozone generator. By recording the results of these multiple rounds of feedback and adaptively adjusting to optimize the effect, a control optimization result is generated. This enables the system to continuously optimize the decision-making process and improve the accuracy of judging abnormal states. Attached Figure Description

[0034] Figure 1 This is a flowchart of an adaptive adjustment method for an ozone generator based on the Internet of Things, according to Embodiment 1 of the present invention. Detailed Implementation

[0035] The present invention will be further described in detail below with reference to the accompanying drawings.

[0036] Example 1

[0037] Reference Figure 1 This embodiment of an adaptive adjustment method and system for an ozone generator based on the Internet of Things includes:

[0038] Utilize IoT terminals to monitor the operating status of ozone generators;

[0039] The detection of IoT terminals mainly relies on sensors installed in the ozone generator. These sensors include multiple temperature sensors, which wirelessly transmit the monitored temperature data to the IoT terminals.

[0040] The interior of the ozone generator is divided into three-dimensional meshes, the increasing and decreasing trends of temperature changes are extracted, and the abnormal state of the ozone generator is predicted using a deep sequence learning algorithm.

[0041] The three-dimensional mesh segmentation includes parsing the temperature measurement data to generate a temperature distribution, identifying each region based on the distribution of the glass medium to generate a first identification constraint, identifying each region within the ozone generator based on the voltage result compensation to generate a second identification constraint, configuring constraint transformation, normalizing the first and second identification constraints using the constraint transformation, randomly distributing cluster centers, performing region-continuous constraint aggregation, setting a minimum aggregation granularity, performing dependency planning on the aggregation results using the minimum aggregation granularity, and realizing three-dimensional mesh segmentation based on the dependency planning results.

[0042] First, outliers were removed and data smoothing was performed on the multi-point temperature measurement data acquired by temperature sensors to ensure data accuracy and reliability. Based on the processed temperature data, a temperature distribution model of the ozone generator's interior was constructed. Since the presence of the glass medium can affect temperature conduction and distribution, the internal space of the ozone generator was divided according to the distribution of the glass medium. The generated first identifier constraint reflects the division and restriction of the region by the glass medium, providing a physically-based constraint for subsequent mesh segmentation. Using data compensated for by the incoming line voltage, changes in the incoming line voltage can affect the temperature and other characteristics of different regions within the ozone generator. The internal space of the ozone generator was further divided based on the voltage compensation results, and a new identifier was generated for each region. The second identifier constraint, based on the voltage factor, further divides the region, providing more comprehensive constraints for mesh segmentation together with the first identifier constraint.

[0043] Through constraint transformation, the first and second identifier constraints are normalized, allowing them to be analyzed and processed on the same basis. Considering the physical continuity and similarity of adjacent regions, each region is aggregated. If two adjacent regions are similar in terms of temperature, glass medium distribution, and voltage compensation, they can be aggregated together. A minimum aggregation granularity is set, which determines the minimum size of the aggregated region. If the aggregated region is smaller than the minimum aggregation granularity, further adjustments or merging are required. Dependency planning is performed on the aggregation results based on the minimum aggregation granularity to determine which regions can be merged and which need to remain independent. Finally, based on the dependency planning results, a three-dimensional mesh is segmented, dividing the internal space of the ozone generator into multiple three-dimensional mesh regions with specific attributes and constraints.

[0044] The extraction of the increasing or decreasing trend of temperature change includes configuring standard test data, performing multi-point temperature measurement within the ozone generator under the standard test data, compensating for the incoming voltage result based on the temperature measurement result, and measuring the rate of temperature change over time by differentiating the temperature change of each three-dimensional grid segment within the ozone generator within a preset unit time.

[0045] Standardized test data is configured to provide a unified standard for subsequent temperature measurements and other analyses. Multiple temperature sensors are placed at different locations within the ozone generator to obtain more comprehensive temperature distribution information. Temperature measurement results may be affected by the input voltage; fluctuations in the input voltage can cause temperature changes within the ozone generator. By compensating for the input voltage in the temperature measurement results, the interference of the input voltage on temperature measurements can be eliminated, improving the accuracy of the temperature data. By differentiating the temperature change within a preset unit time for each three-dimensional grid segment within the ozone generator, the rate of temperature change reflects the speed of temperature change and is one of the important indicators for determining whether the ozone generator is in an abnormal state.

[0046] The method for predicting abnormal states of the ozone generator includes collecting temperature change rate data, incoming line voltage data, reactor and transformer temperature data, and historical operating status data in a three-dimensional grid segmentation. The data is then organized according to a time series, a model is constructed using a long short-time memory network, the model is trained using the organized data, and the trained model is used to predict abnormal states of the ozone generator.

[0047] The feedback on the quality of predicting abnormal states of the ozone generator includes setting up an interface to receive historical data for analyzing the prediction results. The historical data includes success rate, task execution time, and sensor utilization efficiency, forming a real-time performance data stream. The real-time performance data stream is analyzed using data analysis algorithms to calculate the indicators of prediction quality. The adjusted decision parameters are output using a feedback loop algorithm to update the rule settings of the feedback supervision space.

[0048] The temperature control decision network is a neural network used to determine the adjustment strategy of the ozone generator's input voltage. The input voltage demand characteristics are used as the initial input to initialize the temperature control decision network. The input voltage demand characteristics need to be transformed into the initial weights and biases of the network so that the network can make preliminary decisions based on the input voltage demand characteristics when it starts running.

[0049] The feedback space is used to store and process the output of the decision network. During the operation of the decision network, information such as decision results, temperature change trends, and incoming voltage adjustments is continuously stored in the feedback space. This information can be used for subsequent analysis and optimization, and also serves as feedback signals input into the decision network to adjust the network's weights and biases, thereby improving the accuracy of the decisions.

[0050] An improved clustering algorithm can classify the operating status of ozone generators based on multiple factors such as temperature change trends and incoming line voltage adjustments. The operating status can be categorized into normal, slightly abnormal, and severely abnormal states. Through cluster analysis, the type and severity of the ozone generator's abnormal state can be determined more accurately. Based on the analysis results of the improved clustering algorithm, decision results are generated. These decisions include whether the incoming line voltage needs adjustment and the magnitude of the adjustment. Simultaneously, a feedback monitoring space is generated based on the decision results. This feedback monitoring space is used to monitor and adjust the decision results, allowing for correction and optimization based on actual conditions.

[0051] Based on the temperature change configuration of the three-dimensional grid segmentation, the incoming voltage demand characteristics are configured, and the IoT terminal sends an ozone generator abnormal operation status message transmission request to the monitoring center.

[0052] The monitoring center provides feedback on the quality of the predicted abnormal state of the ozone generator, and uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results.

[0053] The feedback on the quality of predicting abnormal states of the ozone generator includes setting up an interface to receive historical data for analyzing the prediction results. The historical data includes success rate, task execution time, and sensor utilization efficiency, forming a real-time performance data stream. The real-time performance data stream is analyzed using data analysis algorithms to calculate the indicators of prediction quality. The adjusted decision parameters are output using a feedback loop algorithm to update the rule settings of the feedback supervision space.

[0054] The method of using a feedback loop algorithm includes determining the target performance index, using a PID algorithm as the feedback loop algorithm, determining the initial values ​​of the proportional coefficient, integral coefficient, and derivative coefficient of the PID algorithm, obtaining the operating status data of the ozone generator, calculating the error between the current state and the target performance index, and updating the decision parameters based on the calculated control quantity.

[0055] The PID algorithm is a classic control algorithm. Its basic principle is to adjust the control input based on the system error, thereby bringing the system to a target state. In this ozone generator adaptive regulation, operating status data includes various parameters such as temperature, voltage, and flow rate. After acquiring this data through IoT devices such as sensors, it is compared with the target performance indicators, and the error between the target and the actual values ​​is calculated. This error calculation is the basis for the PID algorithm to adjust the control input. Based on the PID algorithm's calculation formula, combined with the proportional, integral, and derivative coefficients and the calculated error, a control input is obtained. This control input can be an adjustment to the incoming line voltage, a regulation of the cooling water flow rate, or a change in other control parameters. This control input is then used to update the decision parameters, which are used to control the actual operation of the ozone generator, such as adjusting the voltage regulator setpoint or changing the cooling water pump speed, thereby making the ozone generator's operating state closer to the target performance indicators.

[0056] After receiving messages from the IoT terminals, the monitoring center will provide feedback on the quality of the predicted abnormal states of the ozone generator. The monitoring center will then assess the accuracy and effectiveness of the predictions regarding the abnormal states of the ozone generator.

[0057] The target performance indicators include the operating temperature range of the medium tube inside the ozone generator, the fluctuation range of the incoming line voltage, the range of gas supply per unit time, and the range of cooling water pressure.

[0058] The monitoring center's feedback on the quality of predicting abnormal states of the ozone generator also includes recording multiple rounds of feedback results. Each round of feedback result has a decision effect indicator. The adaptive adjustment effect is optimized based on the multiple rounds of feedback results to generate control optimization results. A new round of adaptive adjustment of the ozone generator is then performed based on the control optimization results.

[0059] After each prediction and adjustment of the ozone generator's abnormal condition, the monitoring center records the feedback results for that round. The feedback results include information such as the predicted type of abnormal condition, the adjustment measures taken, and the operating status of the ozone generator after the adjustment.

[0060] The effectiveness of this round of decision-making is evaluated based on pre-set assessment indicators, and corresponding decision effectiveness labels are assigned. The decision effectiveness label is determined by comparing the degree of agreement between predicted and actual abnormal states, and the time it takes for the ozone generator to return to normal operation after adjustments. Over time, the monitoring center continuously accumulates feedback results from multiple rounds. These results can be stored in a database for subsequent analysis and processing.

[0061] Multiple rounds of feedback results were retrieved from the database and analyzed comprehensively to determine the effectiveness of different adjustment strategies under various abnormal conditions. This included statistically analyzing metrics such as the success rate and average recovery time of various adjustment strategies under different abnormal conditions.

[0062] When a new abnormal state is detected in the ozone generator, the control center takes corresponding adjustment measures based on the recommendations in the control optimization results. For example, if the ozone generator temperature is detected to be too high, and the control optimization results indicate that a combination of reducing the incoming voltage and increasing the gas supply is more effective under similar conditions, then the control center will reduce the incoming voltage and increase the cooling water pressure to adjust the ozone generator's operating status. During the adjustment process, the ozone generator's operating status is continuously monitored to evaluate the effectiveness of the adjustment measures. If the ozone generator still does not return to normal operation after adjustment, or if new problems arise, the multi-round feedback results can be re-analyzed based on the actual situation to further optimize the adjustment strategy.

[0063] The control center adaptively adjusts the ozone generator according to the updated rules.

[0064] The adaptive adjustment includes adjusting the incoming voltage of different medium pipe areas, adjusting the gas supply of different medium pipe areas, and adjusting the pressure of cooling water in the ozone generator, so as to keep the ozone generator operating within the normal range.

[0065] Example 2

[0066] This embodiment provides an IoT-based adaptive adjustment system for an ozone generator, including:

[0067] IoT terminals are used to monitor the operating status of ozone generators.

[0068] The operation status analysis module is used to perform three-dimensional mesh segmentation inside the ozone generator, extract the increasing and decreasing trends of temperature changes, and use deep sequence learning algorithms to predict abnormal states of the ozone generator.

[0069] The request decision module is used to configure the incoming voltage demand characteristics based on the temperature change of the three-dimensional grid segmentation, and to send an ozone generator abnormal operation status message transmission request from the Internet of Things terminal to the monitoring center.

[0070] The monitoring center is used to predict abnormal states of ozone generators and provide feedback on the quality. It uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results.

[0071] The control center is used to adaptively adjust the ozone generator based on updated rule settings.

[0072] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. An adaptive adjustment method for an ozone generator based on the Internet of Things, characterized in that, include: Utilize IoT terminals to monitor the operating status of ozone generators; The interior of the ozone generator is divided into three-dimensional meshes, the increasing and decreasing trends of temperature changes are extracted, and the abnormal state of the ozone generator is predicted using a deep sequence learning algorithm. The extraction of the increasing or decreasing trend of temperature change includes configuring standard test data and performing multi-point temperature measurement within the ozone generator under the standard test data, compensating for the incoming voltage result based on the temperature measurement result, and measuring the rate of temperature change over time by differentiating the temperature change of each three-dimensional grid segment within the ozone generator in a preset unit time. The process of performing three-dimensional mesh segmentation includes parsing the temperature measurement data, generating a temperature distribution, identifying each region based on the distribution of the glass medium, generating a first identification constraint, identifying each region within the ozone generator based on the voltage result compensation, generating a second identification constraint, configuring constraint transformation, normalizing the first and second identification constraints using the constraint transformation, randomly distributing cluster centers, performing constraint aggregation of continuous regions, setting a minimum aggregation granularity, performing dependency planning on the aggregation results using the minimum aggregation granularity, and realizing three-dimensional mesh segmentation based on the dependency planning results. Based on the temperature change configuration of the three-dimensional grid segmentation, the incoming voltage demand characteristics are configured, and the IoT terminal sends an ozone generator abnormal operation status message transmission request to the monitoring center. The monitoring center provides feedback on the quality of the predicted abnormal state of the ozone generator, and uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results. The feedback on the quality of predicting abnormal states of ozone generators includes setting an interface to receive historical data for analyzing prediction results. The historical data includes success rate, task execution time, and sensor utilization efficiency, forming a real-time performance data stream. The real-time performance data stream is analyzed using data analysis algorithms to calculate prediction quality indicators. The adjusted decision parameters are output using a feedback loop algorithm to update the rule settings of the feedback supervision space. The control center adaptively adjusts the ozone generator according to the updated rules.

2. The adaptive adjustment method for an ozone generator based on the Internet of Things according to claim 1, characterized in that, The method for predicting abnormal states of the ozone generator includes collecting temperature change rate data, incoming line voltage data, reactor and transformer temperature data, and historical operating status data in a three-dimensional grid segmentation. The data is then organized according to a time series, a model is constructed using a long short-time memory network, the model is trained using the organized data, and the trained model is used to predict abnormal states of the ozone generator.

3. The adaptive adjustment method for an ozone generator based on the Internet of Things according to claim 2, characterized in that, The configuration of the incoming voltage demand features based on the temperature change of the three-dimensional mesh segmentation includes performing network initialization of the temperature control decision network with the incoming voltage demand features, setting trigger nodes and feedback space, and when the increasing or decreasing trend of temperature change is input into the initialized decision network, using an improved clustering algorithm to analyze the abnormal state of the ozone generator, generating decision results, and synchronously generating a feedback supervision space based on the decision results.

4. The adaptive adjustment method for an ozone generator based on the Internet of Things according to claim 1, characterized in that, The process of using a feedback loop algorithm to output adjusted decision parameters includes determining the target performance index, using a PID algorithm as the feedback loop algorithm, determining the initial values ​​of the proportional coefficient, integral coefficient, and derivative coefficient of the PID algorithm, obtaining the operating status data of the ozone generator, calculating the error between the current state and the target performance index, and updating the decision parameters based on the calculated control quantity.

5. The adaptive adjustment method for an ozone generator based on the Internet of Things according to claim 4, characterized in that, The adaptive adjustment includes adjusting the incoming voltage of different medium pipe areas, adjusting the gas supply of different medium pipe areas, and adjusting the pressure of cooling water in the ozone generator, so as to keep the ozone generator operating within the normal range.

6. The adaptive adjustment method for an ozone generator based on the Internet of Things according to claim 5, characterized in that, The monitoring center's feedback on the quality of predicting abnormal states of the ozone generator also includes recording multiple rounds of feedback results. Each round of feedback result has a decision effect indicator. The adaptive adjustment effect is optimized based on the multiple rounds of feedback results to generate control optimization results. A new round of adaptive adjustment of the ozone generator is then performed based on the control optimization results.

7. An IoT-based adaptive adjustment system for an ozone generator, executing the IoT-based adaptive adjustment method for an ozone generator as described in claim 1, characterized in that, include: IoT terminals are used to monitor the operating status of ozone generators. The operation status analysis module is used to perform three-dimensional mesh segmentation inside the ozone generator, extract the increasing and decreasing trends of temperature changes, and use deep sequence learning algorithms to predict abnormal states of the ozone generator. The request decision module is used to configure the incoming voltage demand characteristics based on the temperature change of the three-dimensional grid segmentation, and to send an ozone generator abnormal operation status message transmission request from the Internet of Things terminal to the monitoring center. The monitoring center is used to predict abnormal states of ozone generators and provide feedback on the quality. It uses a feedback loop algorithm to output adjusted decision parameters and update the rule settings for analyzing the prediction results. The control center is used to adaptively adjust the ozone generator based on updated rule settings.

Images