Sludge power generation system fault monitoring method

Abstract

The invention relates to the technical field of sludge power generation systems, in particular to a sludge power generation system fault monitoring method. The method comprises the following steps of firstly completing monitoring data acquisition, completing monitoring data judgment according to the monitoring data, completing equipment data acquisition, judging the state of data acquisition equipment according to the equipment data, then constructing an early warning model, and completing early warning in future specified time according to an output value of the early warning model. Finally, when the sludge power generation system breaks down, intelligent decision making is conducted through the intelligent decision making module preferentially. According to the sludge power generation system fault monitoring method, future objective factors are included in an early warning system, an early warning floating threshold value is generated through a future objective factor collection module in an early warning module in combination with parameters such as environment temperature and humidity in prediction time, and prospective early warning is achieved in cooperation with a double-prediction model; the future generating capacity prediction model is based on multi-source operation data and environmental factors, and further can give out early warning in a fault germination stage.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sludge power generation system, in particular to a sludge power generation system fault monitoring method. BACKGROUND

[0002] With the acceleration of urbanization, the annual output of sludge in China continues to rise. This kind of solid waste with the properties of pollutants and carbon resources has long been facing the treatment difficulties of high moisture content, low utilization rate of organic matter, and complex carbon emission path. In the traditional treatment method, land use is limited due to excessive heavy metals and organic pollutants, incineration requires a large amount of energy to reduce the moisture content, and sanitary landfill is restricted by the shortage of land resources caused by urban development, which cannot meet the current environmental protection and resource utilization needs. At the same time, the demand for clean energy is increasingly urgent due to the adjustment of China's energy structure, and the strict policy requirements for the collaborative transformation of sludge treatment from harmless to resource and carbon neutralization. Sludge power generation technology emerges as the times require. This technology converts organic matter in sludge into electric energy through anaerobic fermentation, pyrolysis, incineration and other processes, which can realize sludge reduction and harmless treatment, and also recover energy. Since the 1990s, foreign countries have begun to research and apply this technology, and it has been introduced into China since the early 21st century and has developed rapidly and gradually matured. However, it still faces challenges such as complex sludge composition, high treatment cost, and difficulty in emission control, and needs to be further optimized to expand the application scale.

[0003] The prior art sludge power generation system has single monitoring dimension during power generation operation, which is often monitored by sensors, resulting in single monitoring dimension. Due to the single monitoring dimension, the early warning is lagging behind, and the power generation equipment is often idle after abnormal data appears.

[0004] Therefore, the present application is proposed. SUMMARY

[0005] The present application aims to provide a sludge power generation system fault monitoring method to solve the problem of single monitoring dimension in the background art, which is often monitored by sensors, resulting in single monitoring dimension. Due to the single monitoring dimension, the early warning is lagging behind, and the power generation equipment is often idle after abnormal data appears.

[0006] To achieve the above-mentioned purpose, one of the purposes of the present application is to provide a sludge power generation system fault monitoring method, comprising the following steps:

[0007] S1: The data monitoring system contained in the sludge power generation system fault monitoring system completes monitoring data collection;

[0008] S2: The data monitoring system contained in the sludge power generation system fault monitoring system completes monitoring data judgment with monitoring data.

[0009] S3: The equipment state monitoring module contained in the sludge power generation system fault monitoring system completes equipment data acquisition;

[0010] S4: The equipment state monitoring module contained in the sludge power generation system fault monitoring system judges the state of the collected data equipment with equipment data;

[0011] S5: The pre-warning module collects the data generated by the data monitoring system and the equipment state monitoring module, and constructs a pre-warning model;

[0012] S6: The pre-warning model output value completes the pre-warning within a specified future time;

[0013] S7: Finally, when the sludge power generation system fails, the intelligent decision module is used for intelligent decision-making.

[0014] As a further improvement of the technical solution, the sludge power generation system fault monitoring system comprises a data monitoring system, an equipment state monitoring module, a pre-warning module and an intelligent decision module, the data monitoring system comprises a data acquisition module, a dynamic writing module and a data judgment module;

[0015] The equipment state monitoring module comprises a vibration monitoring module, an oil analysis module and an equipment strength detection module, and the vibration monitoring module, the oil analysis module and the equipment strength detection module are electrically connected with the pre-warning module;

[0016] The pre-warning module comprises a future objective factor acquisition module and a prediction model, and the future objective factor acquisition module is electrically connected with the prediction model.

[0017] The pre-warning module is electrically connected with the data monitoring system, the equipment state monitoring module and the pre-warning module.

[0018] As a further improvement of the technical solution, the data acquisition module functions to collect the monitoring data generated by all sensors of the equipment and the process nodes in real time through the sensors installed on the equipment and the process nodes, the monitoring data at least comprises temperature parameter data, pressure parameter data, flow parameter data and liquid level parameter data, and the data acquisition module is electrically connected with the dynamic writing module;

[0019] The dynamic writing module functions to complete the collection of different types of monitoring parameter data, and complete the writing of the monitoring parameter data into the running data database, the data judgment module and the pre-warning module according to the number of writing threshold and the time of writing threshold set by the dynamic writing module.

[0020] As a further improvement of the technical solution, the dynamic writing module is electrically connected with the data judgment module, the data judgment module receives the monitoring data batch-transmitted by the dynamic writing module, and judges whether each batch of monitoring data is normally completed, and the expression of judging whether each batch of monitoring data is normally completed is as follows:

[0021]

[0022] In the formula, Jud represents the judgment value of each batch of monitoring data, Mon 01 +Mon 02 +Mon 03 +Mon 0n represents several monitoring data of the same type, a represents the number of each batch of monitoring data, and x represents the floating threshold value.

[0023] When upva≥Jud≥lova, it indicates that the device or process node associated with the current monitoring data is running normally, otherwise the device and process node are not running normally, upva represents the upper value of the set monitoring data of this type, lova represents the lower value of the set monitoring data of this type, and upva and lova both incorporate the floating threshold value.

[0024] As a further improvement of the technical solution, the floating threshold value at least includes sludge moisture content parameter data, organic matter content parameter data, component complexity parameter data, temperature parameter data and humidity parameter data, the moisture content parameter data, organic matter content parameter data, component complexity parameter data, temperature parameter data and humidity parameter data are compared with the set moisture content standard parameter data, organic matter content standard parameter data, component complexity standard parameter data, temperature standard parameter data and humidity standard parameter data, the corresponding floating threshold value is obtained, and the floating threshold value is aggregated to obtain x.

[0025] As a further improvement of the technical solution, the function of the early warning module is the function of the vibration monitoring module, which is to collect vibration signal parameter data by using a vibration sensor for the generator equipment, fan equipment, pump body equipment and rotating equipment contained in the sludge power generation system, and to obtain vibration frequency parameter data and vibration floating parameter data by analyzing the collected vibration signal parameter data, and to judge whether the equipment is abnormal according to the obtained vibration frequency parameter data and vibration floating parameter data.

[0026] The oil liquid analysis module is used to periodically extract the lubricating oil sample in the equipment according to the detection time threshold, detect the lubricating oil sample, obtain the metal particles, moisture and viscosity indexes in the lubricating oil sample, judge the equipment operation condition parameter data of the collected lubricating oil sample according to the metal particles, moisture and viscosity indexes, and interact the operation condition parameter data to the operation terminal.

[0027] The equipment strength detection module is used to detect the strength of the pipeline, valve and pressure container through the ultrasonic equipment according to the detection time threshold, obtain the strength parameter data of the pipeline, valve and pressure container, judge the strength condition parameter data of the detected pressure container according to the strength parameter data of the pressure container, and interact the strength condition parameter data to the operation terminal.

[0028] As a further improvement of the technical solution, the future objective factor acquisition module is used to acquire the current sludge power generation system environmental factors in the time factor according to the required prediction time factor, the sludge power generation system environmental factors include temperature parameter data and humidity parameter data, and generate a warning floating threshold according to the current sludge power generation system environmental factors in the time factor.

[0029] As a further improvement of the technical solution, the prediction model includes a future power generation capacity prediction model and an equipment health prediction model, the prediction model is used to receive the monitoring parameter data transmitted by the dynamic writing module, receive the current sludge power generation system environmental factor parameter data in the time factor from the future objective factor acquisition module, construct the prediction model, obtain the future power generation capacity prediction model, receive all the equipment vibration frequency parameter data and vibration floating parameter data, equipment operation condition parameter data and strength condition parameter data detected by the vibration monitoring module, oil liquid analysis module and equipment strength detection module, predict the change trend of the characteristic frequency according to the vibration frequency parameter data and vibration floating parameter data, and the equipment operation condition parameter data and strength condition parameter data, and judge the fault occurrence time in advance.

[0030] As a further improvement of the technical solution, the specific steps of the warning module are as follows:

[0031] Step one: real-time acquisition and integration of multi-source data;

[0032] Step two: data preprocessing;

[0033] Step three: construction and training of future power generation capacity prediction model;

[0034] Step four: construction and training of equipment health prediction model;

[0035] Step five: double model collaborative prediction and warning triggering;

[0036] Step six: early warning response and model iteration.

[0037] As a further improvement of the technical solution, the intelligent decision module includes an intelligent decision database, and the role of the intelligent decision module is to automatically generate an emergency handling plan when the data monitoring system, the equipment state monitoring module and the early warning module monitor or warn of a fault, the logic of generating the emergency handling plan is to match the type of fault monitored or warned by the data monitoring system, the equipment state monitoring module and the early warning module with the past fault handling methods stored in the intelligent decision database, and to complete optimization according to the parameters of the type of fault monitored or warned by the data monitoring system, the equipment state monitoring module and the early warning module.

[0038] Compared with the prior art, the present application has the following advantages:

[0039] 1. In the sludge power generation system fault monitoring method, by breaking through the limitation of traditional single monitoring relying on sensors, a double-core monitoring system of data monitoring system and equipment state monitoring module is constructed, the data monitoring system collects temperature, pressure, flow, liquid level and other process parameters in real time through sensors, and the dynamic writing module can also perform integrity screening and classification integration on the data to ensure the comprehensiveness of the basic data, and the equipment state monitoring module further monitors from three key dimensions of vibration, oil and strength, vibration monitoring captures abnormal vibration signals for rotating equipment such as generators and fans, oil analysis judges equipment wear condition by periodically detecting metal particles, moisture and other indicators in lubricating oil, and equipment strength detection ensures the structural safety of key components such as pipelines and pressure vessels by means of ultrasonic technology, the multi-dimensional monitoring data are mutually verified, effectively avoiding fault omission caused by missing monitoring dimensions, and the system operation state is fully mastered.

[0040] 2. In the sludge power generation system fault monitoring method, by including future objective factors into the early warning system, through the future objective factor acquisition module in the early warning module, combining environmental temperature, humidity and other parameters within the prediction time to generate a floating threshold for early warning, and combining the double prediction model to realize forward-looking early warning, the future power generation prediction model is based on multi-source operation data and environmental factors, and thus can issue an early warning at the fault germination stage, leaving sufficient time for operation and maintenance, and effectively avoiding the problem of idle power generation equipment caused by late warning.

[0041] 3. In the sludge power generation system fault monitoring method, when the system monitors or warns of a fault, the intelligent decision module can rely on the built-in intelligent decision database to realize rapid response, the core logic is to first match the current fault type with the historical fault handling methods stored in the database, then optimize the matched handling method according to the specific parameters of this fault, and automatically generate a targeted emergency handling plan, which improves the practicality of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 The specific steps of the present application are schematically shown in the figure;

[0043] Figure 2 The module structure of the sludge power generation system fault monitoring system of the present application is schematically shown in the figure;

[0044] Figure 3 The specific steps of the early warning module in the present application are schematically shown in the figure. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0046] Embodiment 1

[0047] Please refer to Figure 1 The present embodiment aims to provide a sludge power generation system fault monitoring method, which comprises the following steps:

[0048] S1: The data monitoring system contained in the sludge power generation system fault monitoring system completes monitoring data collection;

[0049] S2: The data monitoring system contained in the sludge power generation system fault monitoring system completes monitoring data judgment with monitoring data;

[0050] S3: The equipment state monitoring module contained in the sludge power generation system fault monitoring system completes equipment data collection;

[0051] S4: The equipment state monitoring module contained in the sludge power generation system fault monitoring system judges the state of the collected data equipment with equipment data;

[0052] S5: The early warning module collects the data generated by the data monitoring system and the equipment state monitoring module, and constructs an early warning model;

[0053] S6: The early warning in the future specified time is completed according to the output value of the early warning model;

[0054] S7: Finally, when the sludge power generation system fails, the intelligent decision module is used for intelligent decision.

[0055] Embodiment 2

[0056] Please refer to Figure 2The embodiment shown aims to provide a sludge power generation system fault monitoring method, which comprises a sludge power generation system fault monitoring system, the sludge power generation system fault monitoring system comprising a data monitoring system, an equipment state monitoring module, an early warning module and an intelligent decision module, the data monitoring system comprising a data acquisition module, a dynamic writing module and a data judgment module;

[0057] The equipment state monitoring module comprises a vibration monitoring module, an oil analysis module and an equipment strength detection module, and the vibration monitoring module, the oil analysis module and the equipment strength detection module are electrically connected with the early warning module.

[0058] The early warning module comprises a future objective factor acquisition module and a prediction model, and the future objective factor acquisition module is electrically connected with the prediction model.

[0059] The early warning module is electrically connected with the data monitoring system, the equipment state monitoring module and the early warning module.

[0060] The data acquisition module is used to collect monitoring data generated by sensors of all equipment and process nodes in real time, and the monitoring data at least comprises temperature parameter data, pressure parameter data, flow parameter data and liquid level parameter data, and the data acquisition module is electrically connected with the dynamic writing module.

[0061] The dynamic writing module is used to complete collection of different types of monitoring parameter data, and complete writing of the monitoring parameter data into the running data database, the data judgment module and the early warning module according to a number writing threshold value and a time writing threshold value set by the dynamic writing module.

[0062] When the dynamic writing module collects the same type of parameter data to reach the number writing threshold value set, the dynamic writing module writes all the collected same type of parameter data into the running data database, the data judgment module and the early warning module.

[0063] When the dynamic writing module collects the same type of parameter data to not reach the writing threshold value set but reaches the time writing threshold value set, the dynamic writing module writes all the collected same type of parameter data into the running data database, the data judgment module and the early warning module, and the number writing threshold value is reset after the writing operation of the time writing threshold value is completed, and the time writing threshold value is reset after the writing operation of the number writing threshold value is completed.

[0064] The dynamic writing module detects the integrity of the monitoring parameter data during the collection of different types of monitoring parameter data, removes incomplete parameter data and retains complete parameter data.

[0065] The dynamic writing module is electrically connected with the data judging module. The data judging module receives the monitoring data batch-transmitted by the dynamic writing module, and judges whether each batch of monitoring data is normally completed. The expression of judging whether each batch of monitoring data is normally completed is as follows:

[0066]

[0067] In the formula, Jud represents the judging value of each batch of monitoring data, Mon represents the monitoring data, a represents the number of each batch of monitoring data, and x represents the floating threshold value. 01 +Mon 02 +Mon 03 +Mon 0n represents several monitoring data of the same type, a represents the number of each batch of monitoring data, and x represents the floating threshold value.

[0068] When upva≥Jud≥lova, it is indicated that the device or process node associated with the current monitoring data is running normally, otherwise, the device and the process node are running abnormally. upva represents the upper value of the monitoring data, lova represents the lower value of the monitoring data, and upva and lova both incorporate the floating threshold value.

[0069] The floating threshold value at least includes sludge water content parameter data, organic matter content parameter data, component complexity parameter data, temperature parameter data and humidity parameter data. The water content parameter data, the organic matter content parameter data, the component complexity parameter data, the temperature parameter data and the humidity parameter data are compared with the set water content standard parameter data, the organic matter content standard parameter data, the component complexity standard parameter data, the temperature standard parameter data and the humidity standard parameter data to obtain the corresponding floating threshold value, and the floating threshold value is aggregated to obtain x.

[0070] The organic matter content parameter data is the energy source of organic matter in sludge, and the higher the content is, the higher the energy production per unit mass of sludge is.

[0071] The component complexity parameter data is the content of heavy metals, pathogenic bacteria and persistent organic pollutants contained in sludge.

[0072] The function of the early warning module is the function of the vibration monitoring module. The vibration monitoring module uses a vibration sensor to collect vibration signal parameter data of the generator equipment, the fan equipment, the pump body equipment and the rotating equipment contained in the sludge power generation system. The vibration monitoring module obtains vibration frequency parameter data and vibration floating parameter data by analyzing the collected vibration signal parameter data, and judges whether the equipment is abnormal according to the obtained vibration frequency parameter data and vibration floating parameter data.

[0073] The vibration frequency parameter data and the vibration floating parameter data are used to determine whether the equipment has an abnormality, and the abnormality at least includes problems such as imbalance, misalignment, bearing damage and the like.

[0074] The oil analysis module is configured to periodically extract a lubricating oil sample from the equipment according to a detection time threshold, detect the lubricating oil sample to obtain metal particles, moisture and viscosity indexes in the lubricating oil sample, determine equipment operation condition parameter data of the collected lubricating oil sample according to the metal particles, moisture and viscosity indexes, and interact the operation condition parameter data to the operation terminal.

[0075] The equipment strength detection module is configured to perform strength detection on the pipeline, valve and pressure container by an ultrasonic device according to a detection time threshold to obtain strength parameter data of the pipeline, valve and pressure container, determine pressure container strength condition parameter data according to the pressure container strength parameter data, and interact the strength condition parameter data to the operation terminal.

[0076] The future objective factor collection module is configured to collect current sludge power generation system environmental factors in a time factor according to a required prediction time factor, the sludge power generation system environmental factors including temperature parameter data and humidity parameter data, and generate a warning floating threshold according to the current sludge power generation system environmental factors in the time factor.

[0077] When the collection of the current sludge power generation system environmental factors in the time factor is completed, a device operation optimization instruction is generated according to the temperature parameter data and the humidity parameter data, and the device operation optimization instruction is transmitted to the operation terminal.

[0078] The prediction model includes a future power generation capacity prediction model and a device health prediction model, and is configured to receive the monitoring parameter data transmitted by the dynamic writing module, receive the current sludge power generation system environmental factor parameter data in the time factor collected by the future objective factor collection module, construct the prediction model, obtain the future power generation capacity prediction model, receive all equipment vibration frequency parameter data and vibration floating parameter data, and equipment operation condition parameter data and strength condition parameter data detected by the vibration monitoring module, the oil analysis module and the equipment strength detection module, predict a change trend of a characteristic frequency according to the vibration frequency parameter data and the vibration floating parameter data, and the equipment operation condition parameter data and the strength condition parameter data, and determine a fault occurrence time in advance.

[0079] The prediction model is an algorithm model capable of capturing a parameter change trend, and for a linear change parameter, a linear regression model can be used to fit a change slope through historical data, predict a parameter value at a future time point, and for a rotating equipment, a vibration spectrum analysis is combined to extract a characteristic frequency, the change trend of the characteristic frequency is predicted through the model, and the fault occurrence time is determined in advance.

[0080] The intelligent decision module comprises an intelligent decision database, and the intelligent decision module functions to automatically generate an emergency treatment plan when the data monitoring system, the equipment state monitoring module and the early warning module monitor or warn of a fault. The logic for generating the emergency treatment plan is to match the type of fault monitored or warned of by the data monitoring system, the equipment state monitoring module and the early warning module with the past fault treatment methods stored in the intelligent decision database, and to complete optimization according to the parameters of the type of fault monitored or warned of by the data monitoring system, the equipment state monitoring module and the early warning module.

[0081] Embodiment 3

[0082] Referring to Figure 3 One of the purposes of the present embodiment is to provide a sludge power generation system fault monitoring method, which comprises an early warning module, and the specific steps of the early warning module are as follows:

[0083] Step 1: Real-time collection and integration of multi-source data;

[0084] Step 2: Data preprocessing;

[0085] Step 3: Construction and training of future power generation capacity prediction model;

[0086] Step 4: Construction and training of equipment health prediction model;

[0087] Step 5: Dual-model collaborative prediction and early warning triggering;

[0088] Step 6: Early warning response and model iteration.

[0089] In step 1, three types of core data are synchronously collected through a dynamic writing module, a future objective factor collection module, a vibration monitoring module, an oil analysis module and an equipment strength detection module.

[0090] In step 2, data preprocessing is performed on the parameter data obtained by the dynamic writing module, the future objective factor collection module, the vibration monitoring module, the oil analysis module and the equipment strength detection module, including data cleaning to eliminate abnormal values caused by sensor faults, standardization of the data, and feature extraction for power generation capacity prediction and equipment health prediction, respectively.

[0091] In step 3, a multivariate LSTM and attention mechanism combined model is used to capture the nonlinear correlation between sludge characteristics fluctuations, environmental changes and power generation capacity by taking system operation basic data and future environmental factor data as inputs, and the model is trained using historical 6-month operation data. By adjusting parameters such as the number of hidden layer neurons and the learning rate, the prediction error is minimized, and finally the output is completed.

[0092] In step four, a random forest and vibration spectrum analysis fusion model is adopted, the equipment vibration frequency, vibration floating parameters, oil indicators and intensity condition parameters are input, the potential fault mode is identified through characteristic frequency matching, the equipment state is converted into a health degree score, the corresponding relationship between the score and the fault is marked based on historical fault data, finally the model is trained through the equipment full life cycle data, the fault recognition accuracy is verified through the confusion matrix and the weight coefficient of the characteristic frequency is optimized.

[0093] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A fault monitoring method for a sludge power generation system, characterized in that: Includes the following steps: S1: The data monitoring system contained in the sludge power generation system fault monitoring system completes the monitoring data collection; S2: The data monitoring system contained in the sludge power generation system fault monitoring system completes the monitoring data judgment based on the monitoring data; S3: The equipment status monitoring module contained in the sludge power generation system fault monitoring system completes equipment data acquisition; S4: The equipment status monitoring module contained in the sludge power generation system fault monitoring system determines the status of the collected equipment based on the equipment data; S5: The early warning module collects data generated by the data monitoring system and equipment status monitoring module to build an early warning model; S6: Based on the output value of the early warning model, issue an early warning within a specified time period in the future; S7: Finally, when the sludge power generation system fails, intelligent decision-making will be prioritized through the intelligent decision-making module.

2. The fault monitoring method for a sludge power generation system according to claim 1, characterized in that: The sludge power generation system fault monitoring system includes a data monitoring system, an equipment status monitoring module, an early warning module, and an intelligent decision-making module. The data monitoring system includes a data acquisition module, a dynamic writing module, and a data judgment module. The equipment condition monitoring module includes a vibration monitoring module, an oil analysis module, and an equipment strength detection module, all of which are electrically connected to the early warning module. The early warning module includes a future objective factor collection module and a prediction model, and the future objective factor collection module and the prediction model are electrically connected. The early warning module is electrically connected to the data monitoring system, the equipment status monitoring module, and the early warning module.

3. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The data acquisition module is used to collect monitoring data generated by sensors installed on equipment and process nodes in real time. The monitoring data includes at least temperature parameter data, pressure parameter data, flow parameter data and liquid level parameter data. The data acquisition module is electrically connected to the dynamic writing module. The function of the dynamic writing module is to collect monitoring parameter data of different categories, and to write the monitoring parameter data into the running data database, data judgment module and early warning module according to the number of write thresholds and time write thresholds set by the dynamic writing module.

4. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The dynamic writing module is electrically connected to the data judgment module. The function of the data judgment module is to receive the monitoring data transmitted in batches by the dynamic writing module and to judge whether each batch of monitoring data has been completed normally. The expression for judging whether each batch of monitoring data has been completed normally is as follows: In the formula, Jud represents the judgment value of each batch of monitoring data, and Mon... 01 +Mon 02 +Mon 03 +Mon 0n This represents several monitoring data points of the same category, where 'a' represents the number of monitoring data points in each batch, and 'x' represents the floating threshold. When upva≥Jud≥lova, it indicates that the equipment or process node associated with the current monitoring data is operating normally; otherwise, the equipment and process node are not operating normally. Upva represents the upper value set for this type of monitoring data, and lova represents the lower value set for this type of monitoring data. Both upva and lova are combined with floating thresholds.

5. The fault monitoring method for a sludge power generation system according to claim 4, characterized in that: The floating threshold includes at least sludge moisture content parameter data, organic matter content parameter data, composition complexity parameter data, temperature parameter data, and humidity parameter data. The moisture content parameter data, organic matter content parameter data, composition complexity parameter data, temperature parameter data, and humidity parameter data are all compared with the set standard parameter data for moisture content, organic matter content, composition complexity, temperature, and humidity to obtain the corresponding floating threshold. The floating thresholds are then summed to obtain x.

6. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The function of the early warning module is to collect vibration signal parameter data from the generator equipment, fan equipment, pump equipment, and rotating equipment contained in the sludge power generation system using vibration sensors. The vibration monitoring module obtains vibration frequency parameter data and buoyancy parameter data by analyzing the collected vibration signal parameter data, and determines whether there is any abnormality in the equipment based on the obtained vibration frequency parameter data and buoyancy parameter data. The function of the oil analysis module is to periodically extract lubricating oil samples from the equipment according to the set detection time threshold, detect the lubricating oil samples, obtain the metal particles, moisture and viscosity indicators in the lubricating oil samples, determine the equipment operating status parameter data of the collected lubricating oil samples based on the metal particles, moisture and viscosity indicators, and exchange the operating status parameter data with the operation terminal. The function of the equipment strength detection module is to perform strength detection on pipelines, valves and pressure vessels using ultrasonic equipment according to the set detection time threshold, obtain strength parameter data of pipelines, valves and pressure vessels, determine the strength condition parameter data of the detected pressure vessel based on the pressure vessel strength parameter data, and exchange the strength condition parameter data with the operation terminal.

7. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The function of the future objective factor acquisition module is to collect the current environmental factors of the sludge power generation system within the time factor according to the required prediction time factor. The environmental factors of the sludge power generation system include temperature parameter data and humidity parameter data, and generate an early warning floating threshold based on the current environmental factors of the sludge power generation system within the time factor.

8. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The prediction model includes a future power generation prediction model and an equipment health prediction model. The function of the prediction model is to receive monitoring parameter data transmitted by the dynamic writing module and environmental factor parameter data of the current sludge power generation system within the time factor from the future objective factor acquisition module, construct a prediction model, obtain a future power generation prediction model, and receive all equipment vibration frequency parameter data and buoyancy parameter data, as well as equipment operating status parameter data and strength status parameter data detected by the vibration monitoring module, oil analysis module, and equipment strength detection module. Based on the vibration frequency parameter data, buoyancy parameter data, equipment operating status parameter data, and strength status parameter data, the model predicts the trend of characteristic frequency changes and predicts the time of failure in advance.

9. The fault monitoring method for a sludge power generation system according to claim 8, characterized in that: The specific steps of the early warning module are as follows: Step 1: Real-time acquisition and integration of multi-source data; Step 2: Data preprocessing; Step 3: Building and training the future power generation prediction model; Step 4: Building and training the equipment health prediction model; Step 5: Dual-model collaborative prediction and early warning triggering; Step Six: Early Warning Response and Model Iteration.

10. The fault monitoring method for a sludge power generation system according to claim 2, characterized in that: The intelligent decision-making module includes an intelligent decision-making database. The function of the intelligent decision-making module is to automatically generate an emergency response plan when the data monitoring system, equipment status monitoring module, and early warning module detect or warn of a fault. The logic for generating the emergency response plan is to match the types of faults detected or warn of by the data monitoring system, equipment status monitoring module, and early warning module with past fault handling methods stored in the intelligent decision-making database, and to optimize the plan based on the parameters of the types of faults detected or warn of by the data monitoring system, equipment status monitoring module, and early warning module.

Images