Water treatment equipment remote monitoring and operation and maintenance system and method

Abstract

The present invention relates to the field of water treatment technology, and discloses a remote monitoring and operation and maintenance system and method for water treatment equipment. The system includes: an ultra-sensitive composite sensor matrix module, an intelligent edge collector module, a hybrid self-organizing network transmission module, a collaborative data processing hub module, a cloud-based fusion computing platform module, and a strategy generation module. By implementing the present invention, water quality parameters, equipment operating pressure parameters, and vibration signal parameters are collected in all directions, and intelligent operation and maintenance management of water treatment equipment is realized, effectively ensuring the stable operation and efficient processing capacity of the wastewater treatment system. The problem of how to accurately monitor water quality changes and equipment operating status, and to conduct in-depth analysis and effective utilization based on water quality, energy consumption, equipment operation and other data, thereby optimizing the treatment process and reducing energy consumption is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment, and in particular to a remote monitoring and operation and maintenance system and method for water treatment equipment. Background Art

[0002] Water treatment is a process of removing, separating or transforming impurities and pollutants in water through physical, chemical, biological and other methods in order to meet specific requirements for water quality. In the current field of water treatment, the efficiency and stability of wastewater treatment are crucial to environmental protection and resource utilization. Pollutants in water are usually removed or transformed with the help of chemical reactions. Common methods include coagulation and sedimentation, which adds coagulants to water to make colloids and tiny particles in the water condense into larger flocs for easy precipitation and removal. Neutralization is used to adjust the pH value of wastewater to meet the discharge standards or subsequent treatment requirements. Redox methods use oxidants or reductants to oxidize or reduce harmful substances in water into harmless substances.

[0003] Traditional water treatment systems often have difficulty accurately monitoring changes in water quality and equipment operating status. There is a time lag in the detection of water quality parameters, and it is impossible to detect sudden abnormalities in water quality in a timely manner. For example, in industrial wastewater treatment, when changes in the production process cause a sudden change in wastewater quality, traditional monitoring methods cannot detect it quickly, thus affecting the subsequent treatment effect. It is also difficult to conduct in-depth analysis and effective use of a large amount of water quality, energy consumption, equipment operation and other data. It is impossible to quickly and accurately find the inherent correlation between data, such as the relationship between wastewater composition and treatment energy consumption and treatment process effects. Therefore, there is a lack of scientific basis in optimizing treatment processes and reducing energy consumption, making it difficult to make accurate decisions. Summary of the invention

[0004] In view of this, the present invention provides a remote monitoring and operation and maintenance system and method for water treatment equipment to solve the problem of how to accurately monitor water quality changes and equipment operating status, conduct in-depth analysis and effective utilization based on water quality, energy consumption, equipment operation and other data, so as to optimize the treatment process and reduce energy consumption.

[0005] In the first aspect, the present invention provides a remote monitoring and operation and maintenance system for water treatment equipment, the system comprising: an ultra-sensitive composite sensor matrix module, used to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters; an intelligent edge collector module, used to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters returned by the ultra-sensitive composite sensor matrix unit, pre-process the water quality parameters, equipment operating pressure parameters and vibration signal parameters to obtain first processed data; a hybrid ad hoc network transmission module, used to transmit the first processed data to a collaborative data processing hub module based on an industrial Ethernet unit and a wireless communication unit; the collaborative data processing hub module, used to perform a convolutional neural network analysis on the first processed data to obtain second processed data, and perform a pre-processing on the first processed data, system energy consumption data and process effect data An association rule analysis is performed on the first processed data to obtain the fourth processed data. The system energy consumption data is collected by the energy consumption monitoring device and transmitted to the collaborative data processing central module. The system energy consumption data includes equipment energy consumption data and agent energy consumption data. The process effect data is collected by the on-site control layer equipment. The process effect data includes reaction time data, reaction temperature data and reaction pH value data. The cloud-based fusion computing platform module is used to use the optimization algorithm to process the second processed data to obtain the optimized process parameters, use regression analysis to process the third processed data to obtain the equipment operation parameters, and use the Bayesian network algorithm to process the fourth processed data to obtain the equipment maintenance parameters. The strategy generation module is used to generate operation and maintenance strategy parameters based on the optimized process parameters, equipment operation parameters and equipment maintenance parameters.

[0006] The remote monitoring and operation and maintenance system for water treatment equipment provided in this embodiment first collects water quality parameters, equipment operating pressure parameters and vibration signal parameters in all directions through a composite water quality sensor unit and a dual-mode sensor. The ability to capture key information in the wastewater treatment process is greatly improved, ensuring the comprehensiveness and accuracy of the acquired data. Whether it is a subtle change in water quality or a potential abnormality in the operating state of the equipment, it can be accurately perceived. Secondly, the intelligent edge collector module efficiently converges the signals output by the ultra-sensitive composite sensor matrix module according to the preset sensor priority and acquisition frequency, ensuring that key data can be collected in priority and in a timely manner, significantly improving data collection efficiency, and avoiding information delays caused by data collection confusion. The collected water quality, equipment operating pressure and vibration signal parameters are pre-processed to provide a reliable data source for subsequent in-depth analysis, greatly improving the accuracy and reliability of the data analysis results. Then, the hybrid ad hoc network transmission module: based on the combined design of the industrial Ethernet unit and the wireless communication unit, the flexible switching of the data transmission mode is realized. When the industrial Ethernet network conditions are good, the first processing data is quickly and stably transmitted to the collaborative data processing hub module by utilizing its high bandwidth and low latency characteristics to ensure that the data can be delivered in time for analysis and processing. When the industrial Ethernet fails or the network parameters do not meet the preset transmission conditions, the wireless communication unit starts quickly and determines the appropriate wireless transmission link according to the priority of the transmission link to ensure the continuity of data transmission, avoid data loss or transmission interruption due to network problems, and achieve stable data transmission in a complex network environment. Afterwards, the collaborative data processing central module uses convolutional neural networks to analyze the first processing data, which can accurately predict the changing trend parameters of water quality parameters under different process parameters, providing a scientific basis for optimizing the wastewater treatment process, avoiding the occurrence of poor treatment effects, and greatly improving the foresight and scientific nature of the wastewater treatment process. Through association rule analysis, the potential connection between the first processing data, system energy consumption data and process effect data is mined, and the target frequent item set combination is found, which helps to deeply understand the relationship between various factors in the wastewater treatment process, and provides strong support for optimizing equipment operation mode, reducing energy consumption and improving treatment effects, and improving the overall efficiency and benefits of system operation. Using support vector machines to analyze the first processing data, accurately predict the type of equipment failure and the probability of equipment failure, and be able to formulate maintenance plans in advance, take preventive maintenance measures, reduce the losses caused by sudden equipment failures, and improve the reliability and service life of equipment. Finally, the cloud-based fusion computing platform module uses an optimization algorithm to process the second processing data obtained by the convolutional neural network analysis and determines the optimized process parameters, which helps to achieve fine-grained adjustment of the wastewater treatment process, improve treatment efficiency, reduce treatment costs, ensure that the wastewater treatment effect always meets the standard requirements, and realize the intelligent optimization of the wastewater treatment process.The third processed data obtained by the association rule analysis is processed by regression analysis to obtain the equipment operation parameters, so that the equipment can work in the optimal operation mode, which not only improves the equipment operation efficiency, but also reduces energy consumption and equipment wear, prolongs the service life of the equipment, and realizes efficient energy saving of equipment operation. The fourth processed data obtained by the support vector machine analysis is processed by the Bayesian network algorithm to determine the equipment maintenance parameters, which provides a scientific basis for equipment maintenance, makes the maintenance work more accurate and efficient, avoids excessive maintenance or insufficient maintenance, and improves the management level of equipment maintenance. The strategy generation module comprehensively optimizes the process parameters, equipment operation parameters and equipment maintenance parameters, generates comprehensive operation and maintenance strategy parameters, organically integrates the optimization results of each link, and provides a set of systematic and scientific guidance schemes for the operation and maintenance of water treatment equipment, improves the coordination and operability of the entire water treatment equipment remote monitoring and operation and maintenance system, realizes the all-round and intelligent operation and maintenance management of water treatment equipment, and effectively guarantees the stable operation and efficient treatment capacity of the wastewater treatment system. It solves the problem of how to accurately monitor water quality changes and equipment operation status, and conducts in-depth analysis and effective utilization based on water quality, energy consumption, equipment operation and other data, so as to optimize the treatment process and reduce energy consumption.

[0007] In an optional embodiment, the remote monitoring and operation and maintenance system for water treatment equipment also includes a quantum encryption communication expansion module, which is used to deploy quantum key distribution devices between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing hub module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module.

[0008] In an optional embodiment, the ultra-sensitive composite sensor matrix module includes: an optical-electrochemical composite water quality sensor unit, used to collect water quality parameters, including: chemical oxygen demand parameters, biochemical oxygen demand parameters, colorimetry parameters, and heavy metal ion concentration parameters; a pressure-vibration dual-mode sensor, installed at the connection between the bearing seat and the pipeline of each target device, used to collect equipment operating pressure parameters and vibration signal parameters; an output unit, which outputs the water quality parameters, equipment operating pressure parameters, and vibration signal parameters in the form of digital signals or analog signals.

[0009] In an optional embodiment, the intelligent edge collector module includes: an acquisition unit, which is used to use the peripheral interface and the dedicated sensor interface to collect the analog signal or digital signal output by the ultra-sensitive composite sensor matrix module based on the priority of each sensor and the acquisition frequency of each sensor, and the sensor priority and the acquisition frequency of each sensor are preset by the system; a conversion unit, which is used to convert the analog signal into a digital signal using an analog-to-digital converter when the analog signal output by the ultra-sensitive composite sensor matrix module is collected; a preprocessing unit, which is used to perform noise filtering and feature extraction on water quality parameters, equipment operating pressure parameters and vibration signal parameters to obtain first processed data; a multi-core processor unit, which is used to perform abnormal analysis on the first processed data and determine abnormal results, and the abnormal results include abnormal judgments and abnormal parameters; a task scheduling mechanism unit, which is used to adjust the priority of each sensor and the acquisition frequency of each sensor based on the abnormal results.

[0010] In an optional embodiment, the hybrid ad hoc network transmission module includes: an industrial Ethernet unit, which is used to use an industrial Ethernet switch to monitor the network parameters of each link in the industrial Ethernet, the network parameters include connection status parameters, port traffic parameters and error packet number parameters, and determine the target transmission link in the industrial Ethernet based on the network parameters and preset transmission conditions; a wireless communication unit, which is used to determine the target transmission link in the wireless communication based on the transmission link priority when the network parameters of any link in the industrial Ethernet are not detected to meet the preset transmission conditions, and the wireless communication includes a 5G link, a LoRaWAN link and a satellite communication link; a network prediction unit, which is used to obtain and analyze the network parameters of the target transmission link and generate a network switching strategy; a link switching unit, which is used to switch the target transmission link based on the network switching strategy.

[0011] In an optional embodiment, the collaborative data processing central module includes: a convolutional neural network analysis unit, which is used to analyze the first processed data using a pre-trained convolutional neural network, predict the change trend parameters of water quality parameters under different process parameters, and obtain second processed data; an association rule analysis unit, which is used to mine the association rules between chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, agent energy consumption data, reaction time data, reaction temperature data and reaction pH data through a preset minimum support and a preset minimum confidence threshold, find the target frequent item set combination, and obtain third processed data; a support vector machine analysis unit, which is used to perform support vector machine analysis on the first processed data, predict the equipment failure type and equipment failure probability, and obtain fourth processed data.

[0012] In an optional implementation, the association rule analysis unit adjusts the preset minimum support and preset minimum confidence thresholds based on the water quality parameters, the equipment operating pressure parameters and the preset proportional relationship during the process of mining the association rules.

[0013] In an optional embodiment, the cloud-based fusion computing platform module includes: a process parameter strategy unit, which is used to use an optimization algorithm to analyze the second processing data, determine the optimal solution of the process parameters, and obtain optimized process parameters; a regression analysis unit, which is used to use regression analysis and a combination of the third processing data to establish a correlation between system energy consumption data and chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, reaction time data, reaction temperature data, and reaction pH data, simulate the system energy consumption data under different equipment operating parameters, determine the optimal solution for equipment operation, and obtain equipment operating parameters, which include equipment operating mode parameters and dosing equipment drug addition parameters; a Bayesian network algorithm unit, which is used to use a Bayesian network to establish a causal relationship between equipment failure type, equipment failure probability and equipment maintenance parameters based on the fourth processing data, and determine the equipment maintenance parameters based on the causal relationship.

[0014] In the second aspect, the present invention provides a method for remote monitoring and operation of water treatment equipment, the method comprising: controlling an ultra-sensitive composite sensor matrix module to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters; controlling an intelligent edge collector module to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters returned by an ultra-sensitive composite sensor matrix unit, pre-processing the water quality parameters, equipment operating pressure parameters and vibration signal parameters to obtain first processed data; controlling a hybrid ad hoc network transmission module to transmit the first processed data to a collaborative data processing hub module based on an industrial Ethernet unit and a wireless communication unit; controlling the collaborative data processing hub module to perform a convolutional neural network analysis on the first processed data to obtain second processed data, and pre-processing the first processed data, system energy consumption data and process effect data. The third processed data is obtained by performing association rule analysis, the fourth processed data is obtained by performing support vector machine analysis on the first processed data, the system energy consumption data is collected by the energy consumption monitoring device and transmitted to the collaborative data processing central module, the system energy consumption data includes equipment energy consumption data and agent energy consumption data, the process effect data is collected by the on-site control layer equipment, the process effect data includes reaction time data, reaction temperature data and reaction pH value data; the control cloud-based fusion computing platform module uses the optimization algorithm to process the second processed data to obtain the optimized process parameters, uses regression analysis to process the third processed data to obtain the equipment operation parameters, and uses the Bayesian network algorithm to process the fourth processed data to obtain the equipment maintenance parameters; the control strategy generation module generates operation and maintenance strategy parameters based on the optimized process parameters, equipment operation parameters and equipment maintenance parameters.

[0015] In an optional embodiment, the method also includes: controlling the quantum encryption communication extension module to deploy a quantum key distribution device between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing hub module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a principle block diagram of a specific example of a remote monitoring and operation and maintenance system for water treatment equipment according to an embodiment of the present invention;

[0018] Figure 2 It is a flowchart of a specific example of the method for remote monitoring and operation and maintenance of water treatment equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] Water treatment is a process of removing, separating or transforming impurities and pollutants in water through physical, chemical, biological and other methods in order to meet specific requirements for water quality. In the current field of water treatment, the efficiency and stability of wastewater treatment are crucial to environmental protection and resource utilization. Pollutants in water are usually removed or transformed with the help of chemical reactions. Common methods include coagulation and sedimentation, which adds coagulants to water to make colloids and tiny particles in the water condense into larger flocs for easy precipitation and removal. Neutralization is used to adjust the pH value of wastewater to meet the discharge standards or subsequent treatment requirements. Redox methods use oxidants or reductants to oxidize or reduce harmful substances in water into harmless substances.

[0021] Traditional water treatment systems often have difficulty accurately monitoring changes in water quality and equipment operating status. There is a time lag in the detection of water quality parameters, and it is impossible to detect sudden abnormalities in water quality in a timely manner. For example, in industrial wastewater treatment, when changes in the production process cause a sudden change in wastewater quality, traditional monitoring methods cannot detect it quickly, thus affecting the subsequent treatment effect. It is also difficult to conduct in-depth analysis and effective use of a large amount of water quality, energy consumption, equipment operation and other data. It is impossible to quickly and accurately find the inherent correlation between data, such as the relationship between wastewater composition and treatment energy consumption and treatment process effects. Therefore, there is a lack of scientific basis in optimizing treatment processes and reducing energy consumption, making it difficult to make accurate decisions.

[0022] In view of the technical problems mentioned in the background technology, the present application embodiment provides a remote monitoring and operation and maintenance system for water treatment equipment, see Figure 1 As shown, the system includes: an ultra-sensitive composite sensor matrix module, an intelligent edge collector module, a hybrid self-organizing network transmission module, a collaborative data processing hub module, a cloud-based fusion computing platform module and a strategy generation module. The functions of each of the above components are introduced below.

[0023] Ultra-sensitive composite sensor matrix module, used to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters.

[0024] Specifically, the ultra-sensitive composite sensor matrix module includes:

[0025] The optical-electrochemical composite water quality sensor unit is used to collect water quality parameters, including chemical oxygen demand parameters, biochemical oxygen demand parameters, colorimetric parameters, and heavy metal ion concentration parameters.

[0026] Furthermore, the optical-electrochemical composite water quality sensor unit combines the two detection technologies of optics and electrochemistry. In terms of optical detection, the chemical oxygen demand, biochemical oxygen demand and chromaticity are determined by using the differences in the absorption and scattering characteristics of different substances for light of a specific wavelength, such as by measuring the attenuation of light of a specific wavelength in wastewater. In terms of electrochemical detection, the concentration of heavy metal ions is accurately measured based on the change in current generated when heavy metal ions undergo redox reactions on the electrode surface. For example, for the detection of chemical oxygen demand, ultraviolet spectrophotometry is used, and the linear relationship between chemical oxygen demand and the absorption of ultraviolet rays of a specific wavelength is used to calculate the chemical oxygen demand value by measuring the absorbance; for the detection of heavy metal ion concentration, differential pulse voltammetry is used to apply a specific pulse voltage to the working electrode, and the type and concentration of heavy metal ions are determined based on the resulting voltammetric curve. This composite design overcomes the limitations of a single detection technology and achieves simultaneous, rapid and accurate detection of multiple water quality parameters. Compared with traditional water quality testing methods, it greatly improves the detection efficiency and accuracy, can timely and comprehensively reflect the water quality of wastewater, and provide a reliable basis for the adjustment and optimization of wastewater treatment processes.

[0027] The pressure-vibration dual-mode sensor is installed at the connection between the bearing seat and the pipeline of each target equipment to collect the equipment operating pressure parameters and vibration signal parameters.

[0028] Furthermore, the pressure-vibration dual-mode sensor is installed at the bearing seat and pipeline connection of each target equipment such as water pumps, fans, and agitators. The pressure and vibration changes in these parts can directly reflect the operating status of the equipment. For example, when the bearing of the equipment is worn or fails, its vibration signal will change significantly; and the abnormal pressure in the pipeline can also reflect the working efficiency of the equipment or whether there are problems such as blockage. The pressure-vibration dual-mode sensor integrates pressure detection and vibration detection functions. In terms of pressure detection, the piezoresistive effect is used to sense the pressure by measuring the resistance change of the pressure sensitive element; in terms of vibration detection, based on the piezoelectric effect, the mechanical energy generated by the vibration of the equipment is converted into an electrical signal output. For example, when the equipment is running, the pressure sensitive element will sense the pressure change in the pipeline in real time and convert it into an electrical signal; at the same time, the piezoelectric element will capture the vibration signal of the equipment, whether it is low-frequency periodic vibration or high-frequency impact vibration, it can be accurately detected. By collecting the operating pressure parameters and vibration signal parameters of the equipment in real time, the potential fault hazards of the equipment, such as bearing wear, imbalance, looseness, etc., can be discovered in time, providing an important basis for the preventive maintenance of the equipment, ensuring the stable operation of the equipment, and improving the reliability of the wastewater treatment system.

[0029] The output unit outputs water quality parameters, equipment operation pressure parameters and vibration signal parameters in the form of digital signals or analog signals.

[0030] Furthermore, the output unit outputs the water quality parameters collected by the optical-electrochemical composite water quality sensor unit and the equipment operation pressure parameters and vibration signal parameters collected by the pressure-vibration dual-mode sensor in the form of digital signals or analog signals. The analog signal output directly reflects the continuous change of the physical quantity measured by the sensor, which has advantages in some scenarios with high real-time requirements and short signal transmission distances; while digital signals have strong anti-interference ability, easy transmission and processing, and are suitable for long-distance transmission and situations where complex digital signal processing is required. The signal output of the output unit provides a data source for the intelligent edge collector module. The intelligent edge collector module can flexibly receive and process these digital signals or analog signals through the acquisition unit and the conversion unit according to actual needs, thereby realizing real-time monitoring and data collection of the entire water treatment system.

[0031] The intelligent edge collector module is used to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters returned by the ultra-sensitive composite sensor matrix unit, pre-process the water quality parameters, equipment operating pressure parameters and vibration signal parameters to obtain first processed data.

[0032] Specifically, the intelligent edge collector module includes:

[0033] The acquisition unit is used to utilize the peripheral interface and the dedicated sensor interface to acquire the analog signal or digital signal output by the ultra-sensitive composite sensor matrix module based on the priority of each sensor and the acquisition frequency of each sensor. The sensor priority and the acquisition frequency of each sensor are preset by the system.

[0034] Furthermore, the peripheral interface is a universal interface for connecting the intelligent edge collector to external devices. It has multiple communication protocols, such as USB, Ethernet, etc., and can adapt to different types of sensor devices. The dedicated sensor interface is an interface designed for specific sensors, supporting protocols such as SPI and I2C, to ensure stable and efficient connection with the ultra-sensitive composite sensor matrix module. For example, the SPI interface is characterized by high-speed serial communication and is suitable for transmitting large amounts of real-time data; the I2C interface supports multi-device connection and can mount multiple sensors on the same bus. The system presets the sensor priority and acquisition frequency according to the importance and real-time requirements of each parameter in wastewater treatment. For example, the chemical oxygen demand sensor, which reflects the key indicators of water quality, has a higher priority and a faster acquisition frequency, so as to monitor water quality changes in a timely manner; while some sensors of auxiliary parameters have relatively low priority and acquisition frequency. Based on these presets, the acquisition unit collects data in a targeted manner to improve the acquisition efficiency and data quality.

[0035] The conversion unit is used to convert the analog signal into a digital signal by using an analog-to-digital converter when the analog signal output by the ultra-sensitive composite sensor matrix module is collected.

[0036] Specifically, since the signal output by the ultra-sensitive composite sensor matrix module may be an analog signal, and the subsequent digital processing link requires the input of a digital signal, the conversion unit uses an analog-to-digital converter to convert the analog signal into a digital signal. The analog-to-digital converter converts the continuously changing analog quantity into a discrete digital quantity through steps such as sampling, quantization, and encoding. Taking a 24-bit high-precision ADC as an example, it can divide the amplitude range of the analog signal into 2 to the power of 24 quantization levels, so that the converted digital signal can accurately reflect the changes in the analog signal and reduce data loss.

[0037] The preprocessing unit is used to perform noise filtering processing and feature extraction processing on water quality parameters, equipment operation pressure parameters and vibration signal parameters to obtain first processed data.

[0038] Specifically, during the data acquisition process, sensor signals are easily interfered by environmental noise, such as electromagnetic interference generated by electrical equipment, noise caused by mechanical vibration, etc. The preprocessing unit uses a variety of filtering algorithms, such as adaptive filtering and Kalman filtering, to remove noise. The adaptive filtering algorithm can automatically adjust the filtering parameters according to the real-time characteristics of the signal, effectively filter out noise, and make water quality parameters, equipment operating pressure parameters and vibration signal parameters more accurate. Key features are extracted from the original data through algorithms such as Fourier transform and wavelet transform. For example, Fourier transform of the equipment vibration signal can convert the time domain signal into a frequency domain signal, from which the frequency components of the equipment vibration can be analyzed to help determine whether the equipment is abnormal. Wavelet transform of water quality parameters can analyze the changing characteristics of water quality data at different scales and discover potential trends in water quality changes.

[0039] The multi-core processor unit is used to perform an abnormality analysis on the first processed data to determine an abnormal result, where the abnormal result includes an abnormality determination and an abnormality parameter.

[0040] Specifically, the multi-core processor unit performs real-time analysis on the pre-processed first processed data, and determines whether the data is abnormal through preset algorithms and models. For example, for water quality parameters, a normal range of indicators such as chemical oxygen demand and biochemical oxygen demand is set. When the detection value exceeds the range, it is determined to be abnormal. For equipment operating pressure and vibration signal parameters, abnormal fluctuations are identified by comparing with historical data and parameters under normal operating conditions. Once an abnormality is found, the multi-core processor unit gives an abnormal determination result, such as "abnormal water quality" and "abnormal equipment vibration", and determines abnormal parameters, such as the specific chemical oxygen demand value that exceeds the normal range, the frequency and amplitude of abnormal equipment vibration, etc.

[0041] The task scheduling mechanism unit is used to adjust the priority of each sensor and the acquisition frequency of each sensor based on the abnormal result.

[0042] Specifically, when the multi-core processor unit determines an abnormal result, the task scheduling mechanism unit adjusts the working state of the sensor based on this result. For example, if a component of the equipment is found to vibrate abnormally, it may be a sign that the component is about to fail. At this time, the task scheduling mechanism unit increases the priority and acquisition frequency of the sensors related to the component in order to more closely monitor the operating status of the component and buy time for taking maintenance measures in advance. For example, when the water quality is abnormal, the acquisition frequency of key water quality sensors is increased to quickly obtain more water quality data, helping to adjust the wastewater treatment process in a timely manner.

[0043] The hybrid ad hoc network transmission module is used to transmit the first processed data to the collaborative data processing central module based on the industrial Ethernet unit and the wireless communication unit.

[0044] Specifically, the hybrid ad hoc network transmission module includes:

[0045] The industrial Ethernet unit is used to monitor the network parameters of each link in the industrial Ethernet using the industrial Ethernet switch. The network parameters include connection status parameters, port flow parameters and error packet quantity parameters. The target transmission link in the industrial Ethernet is determined based on the network parameters and preset transmission conditions.

[0046] Furthermore, the industrial Ethernet switch is the core device in the industrial Ethernet. Compared with the ordinary Ethernet switch, it has stronger reliability, stability and anti-interference ability to adapt to the stringent requirements of the industrial environment, connect multiple devices, and build the network topology of the industrial Ethernet, such as star type, bus type, etc. The connection status parameter is used to determine whether the link is in a normal connection state. The value is usually connected, unconnected or connection failure. By real-time monitoring of the connection status, the network interruption can be discovered in time so that repair measures can be taken quickly. The port traffic parameter reflects the rate of data transmission on the network port. By monitoring the port traffic, the load of the network can be understood. If the traffic is too high and close to or exceeds the upper limit of the port bandwidth, it may cause network congestion and affect the data transmission efficiency. Error packet number parameter: refers to the number of data packets that have errors during the data transmission process. The generation of error packets may be due to line interference, equipment failure, etc. Too many error packets will reduce the accuracy and reliability of data transmission, which needs to be checked and resolved in time. The preset transmission conditions are set according to the actual application requirements and network performance requirements. The pre-set standard is used to determine whether the network link is suitable for data transmission. For example, the connection state must be set to connected, the port traffic must be lower than a certain threshold, and the number of error packets must be within a certain range. Only links that meet these conditions are considered to be available target transmission links.

[0047] The wireless communication unit is used to determine the target transmission link in the wireless communication based on the transmission link priority when it is not detected that the network parameters of any link in the industrial Ethernet meet the preset transmission conditions. The wireless communication includes 5G link, LoRaWAN link and satellite communication link.

[0048] Furthermore, the transmission link priority is a priority order pre-set according to the performance characteristics of different wireless communication links and the requirements of application scenarios. 5G links have the advantages of high bandwidth and low latency. When the signal is good, they have a higher priority and are suitable for data transmission with extremely high real-time requirements, such as high-definition video surveillance data or real-time control command transmission. LoRaWAN links have the characteristics of low power consumption and wide coverage. They are suitable for scenarios with long transmission distances, small data volumes and relatively low real-time requirements, such as data transmission at remote water quality monitoring points, and their priority is second. Satellite communication links are used as a last resort when other links cannot be used, such as in remote areas or at sea, and have a relatively low priority. In wastewater treatment systems, 5G links can be used to quickly transmit large amounts of water quality monitoring data, high-definition images of equipment, etc. LoRaWAN links are suitable for data collection and transmission of wastewater treatment equipment distributed over a large area, such as data aggregation of multiple remote small sewage treatment sites. In areas where ground communication networks cannot cover, such as wastewater treatment equipment on offshore oil drilling platforms, or sewage treatment facilities in remote mountainous areas, satellite communication links can ensure data transmission.

[0049] The network prediction unit is used to obtain and analyze the network parameters of the target transmission link and generate a network switching strategy.

[0050] Specifically, the network prediction unit interacts with industrial Ethernet switches, wireless communication modules and other devices to obtain the network parameters of the target transmission link in real time, including the connection status, port traffic, number of error packets, etc. mentioned above, as well as parameters such as signal strength and signal-to-noise ratio of the wireless link. The acquired network parameters are analyzed using data analysis algorithms and machine learning models to predict the future state and performance change trend of the network. For example, by analyzing historical port traffic data, it is predicted whether the network traffic will reach a congested state in the future; based on the trend of changes in wireless signal strength, it is predicted whether the signal will weaken in the short term. Based on these prediction results, a network switching strategy is generated. For example, when it is predicted that the industrial Ethernet link will be severely congested within a few minutes, it will switch to a higher priority 5G link for data transmission in advance.

[0051] The link switching unit is used to switch the target transmission link based on the network switching strategy.

[0052] Furthermore, the link switching unit is responsible for performing actual switching operations between different transmission links according to the network switching strategy generated by the network prediction unit. For example, when an industrial Ethernet link fails or the network performance is seriously degraded, the link switching unit quickly cuts off the connection with the industrial Ethernet and connects to a qualified wireless communication link to ensure the continuity of data transmission. During the switching process, the link switching unit also performs a series of management tasks, such as reconfiguring network parameters, establishing new connection sessions, etc., to ensure that the switched link can transmit data normally and stably, and maintain good compatibility and collaborative working ability with other modules in the system.

[0053] The collaborative data processing central module is used to perform convolutional neural network analysis on the first processed data to obtain second processed data, perform association rule analysis on the first processed data, system energy consumption data and process effect data to obtain third processed data, and perform support vector machine analysis on the first processed data to obtain fourth processed data. The system energy consumption data is collected by the energy consumption monitoring device and transmitted to the collaborative data processing central module. The system energy consumption data includes equipment energy consumption data and agent energy consumption data. The process effect data is collected by the on-site control layer equipment, and the process effect data includes reaction time data, reaction temperature data and reaction pH value data.

[0054] Specifically, the collaborative data processing hub module includes:

[0055] The convolutional neural network analysis unit is used to analyze the first processed data using a pre-trained convolutional neural network, predict the change trend parameters of the water quality parameters under different process parameters, and obtain the second processed data.

[0056] Furthermore, the convolutional neural network is a deep learning model specially designed for processing data with a grid structure. In this system, the pre-trained convolutional neural network is trained with a large amount of data related to wastewater treatment. These training data contain water quality image data under different process parameters and the corresponding true values ​​of water quality parameters. Through training on a large-scale data set, the model can learn the complex relationship between water quality data and process parameters. For example, the model can extract information related to water quality parameters such as chemical oxygen demand and biochemical oxygen demand from the color, texture and other features of the water quality image. The first processed data obtained after preprocessing by the intelligent edge collector module is input into the pre-trained convolutional neural network. Since the first processed data contains some water quality related feature vectors after feature extraction, the convolutional neural network uses its unique convolutional layer, pooling layer and fully connected layer structure to perform deep feature mining on these data. The convolution kernel of the convolutional layer slides on the data to perform convolution operations and extract local features in the data; the pooling layer reduces the dimension of the features, reducing the amount of calculation while retaining key information. Finally, after the integration of the fully connected layer, the model can predict the changing trend parameters of water quality parameters under different process parameters.

[0057] The association rule analysis unit is used to mine the association rules between chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, agent energy consumption data, reaction time data, reaction temperature data and reaction pH value data by setting a preset minimum support and a preset minimum confidence threshold, find the target frequent item set combination, and obtain the third processed data.

[0058] Furthermore, in association rule mining, the minimum support refers to the proportion of the frequency of certain items appearing simultaneously in the data set to the total number of transactions. For example, if the minimum support is set to 0.1, it means that these items need to appear simultaneously in at least 10% of the wastewater treatment data records. The minimum confidence refers to the probability of the latter item appearing when the former item appears. For example, if the minimum confidence is set to 0.8, it means that when the chemical oxygen demand parameter is high, there is an 80% probability that the equipment energy consumption data is also high. These thresholds are preset to filter out meaningful association rules and avoid mining a large number of rules without practical value. Using classic association rule mining algorithms such as the Apriori algorithm, chemical oxygen demand parameters, biochemical oxygen demand parameters, color parameters, heavy metal ion concentration parameters, equipment energy consumption data, reagent energy consumption data, reaction time data, reaction temperature data, and reaction pH data are analyzed. The algorithm first generates frequent item sets based on the minimum support, that is, combinations of items that appear frequently in the data set. For example, a frequent item set such as "high chemical oxygen demand parameters and high reaction temperature" may be found. Then, based on these frequent item sets, association rules are generated according to the minimum confidence. For example, an association rule such as "If the chemical oxygen demand parameter is high and the reaction temperature is high, then the equipment energy consumption data is high" is obtained. Through continuous iteration and screening, the target frequent item set combination, that is, the third treatment data, is finally found. These combinations reflect the inherent connection between different parameters in the wastewater treatment process, providing strong support for optimizing equipment operation mode, reducing energy consumption and improving treatment effect.

[0059] The support vector machine analysis unit is used to perform support vector machine analysis on the first processed data, predict the equipment failure type and equipment failure probability, and obtain fourth processed data.

[0060] Furthermore, the support vector machine is a binary classification model, and its basic model is a linear classifier with the largest interval defined in the feature space. For linearly separable data, the support vector machine maximizes the distance from data points of different categories to the hyperplane by finding an optimal hyperplane, and this hyperplane is the classification decision boundary. For nonlinearly separable data, the data is mapped to a high-dimensional space through a kernel function, so that it becomes linearly separable in the high-dimensional space, and then the optimal hyperplane is found. In this system, the support vector machine is used for multi-classification problems to predict the type of equipment failure. The first processed data processed by the intelligent edge collector module is used as input, and these data contain equipment operating pressure parameters, vibration signal parameters and other features related to the equipment operating status. The support vector machine analysis unit uses these features to train the model, and the model learns the characteristic patterns of data under normal operating conditions and various fault conditions. When new first processed data is input, the model makes a judgment based on the learned pattern to predict the possible fault type of the equipment, such as bearing fault, motor fault, etc., as well as the probability of equipment failure. For example, if the model outputs a certain equipment failure probability of 0.8, it means that the equipment has an 80% probability of failure. These prediction results are the fourth processed data.

[0061] In an optional manner of some embodiments, the association rule analysis unit adjusts the preset minimum support and preset minimum confidence thresholds based on water quality parameters, equipment operating pressure parameters and a preset proportional relationship during the process of mining association rules.

[0062] Specifically, different water quality conditions, such as chemical oxygen demand, biochemical oxygen demand, and heavy metal ion concentration, have a significant impact on the association relationship in the wastewater treatment process. For example, when the chemical oxygen demand concentration in wastewater is high, it may be more closely associated with factors such as equipment energy consumption and reagent consumption. At this time, appropriately lowering the minimum support threshold can enable the algorithm to mine more association rules that may be ignored but actually exist under high chemical oxygen demand concentration conditions; increasing the minimum confidence threshold can ensure that the mined rules have higher reliability under such high chemical oxygen demand concentration conditions. The equipment operating pressure parameter reflects the operating status of the equipment. Different pressure values ​​mean that the equipment is in different working modes or faces different working conditions. For example, when the operating pressure of the water pump increases abnormally, it may imply pipeline blockage or equipment failure. At this time, the association relationship between other parameters related to the pressure change may change. Based on this, adjusting the threshold according to the equipment operating pressure parameter helps to mine accurate association rules under specific equipment operating conditions. For example, when the pressure exceeds the normal range, the minimum support threshold is appropriately relaxed to discover more potential association rules that may be related to pressure anomalies. The preset proportional relationship is a parameter relationship pre-set according to the process requirements, historical experience or expert knowledge of wastewater treatment. It can be a proportional relationship between water quality parameters and equipment operating parameters, or a proportional relationship between different water quality parameters. For example, it is preset that in a certain wastewater treatment process, when the ratio of the heavy metal ion concentration to the chemical oxygen demand concentration in the wastewater reaches a certain value, it will have a specific impact on the corrosion degree and energy consumption of the equipment. Adjusting the threshold based on this preset proportional relationship can guide the algorithm to focus on the mining of association rules related to the proportional relationship, thereby improving mining efficiency and accuracy. In the process of mining association rules, the association rule analysis unit obtains the latest water quality parameters and equipment operating pressure parameters in real time, and calculates according to the preset proportional relationship. The calculation results are input into the threshold adjustment model to obtain the minimum support and minimum confidence thresholds that should be used currently. For example, when the BOD concentration in the water quality is detected to be increased and the equipment operating pressure is in a certain range, the model calculates that the minimum support threshold needs to be reduced by 10% and the minimum confidence threshold needs to be increased by 5% according to the preset proportional relationship to adapt to the data characteristics at this time, thereby mining association rules that are more in line with the actual situation.

[0063] The cloud-based fusion computing platform module is used to use an optimization algorithm to process the second processed data to obtain optimized process parameters, use regression analysis to process the third processed data to obtain equipment operation parameters, and use a Bayesian network algorithm to process the fourth processed data to obtain equipment maintenance parameters.

[0064] Specifically, the cloud-based fusion computing platform module includes:

[0065] The process parameter strategy unit is used to analyze the second processing data using an optimization algorithm, determine the optimal solution of the process parameters, and obtain optimized process parameters.

[0066] Furthermore, the second processed data is obtained by the convolutional neural network analysis unit of the collaborative data processing central module, which includes the changing trends of water quality parameters under different process parameters. The optimization algorithm searches for the optimal solution among a large number of possible process parameter combinations based on these changing trends. For example, if the second processed data shows that increasing the aeration time can significantly reduce the chemical oxygen demand in the wastewater, but at the same time increases energy consumption, the optimization algorithm will find the optimal value of the aeration time while comprehensively considering factors such as energy consumption on the premise of meeting the water quality requirements. After multiple rounds of iterative calculations, the optimized process parameters that can achieve the best wastewater treatment effect and meet other constraints are finally obtained.

[0067] The regression analysis unit is used to establish the correlation between the system energy consumption data and the chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, reaction time data, reaction temperature data, and reaction pH value data by using regression analysis and the third processed data combination, simulate the system energy consumption data under different equipment operation parameters, determine the optimal solution for equipment operation, and obtain equipment operation parameters, which include equipment operation mode parameters and dosing equipment agent addition parameters.

[0068] Furthermore, regression analysis is a statistical method for determining the quantitative relationship between variables. In this system, a mathematical model is established to describe the relationship between system energy consumption data, chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, reaction time data, reaction temperature data, reaction pH value data, etc. and equipment operating parameters. The third processing data is obtained by the association rule analysis unit of the collaborative data processing central module, which contains association rules between various parameters and target frequent item set combinations. Regression analysis uses these data to determine the regression coefficient by fitting a large amount of historical data. For example, according to the chemical oxygen demand parameters, reaction temperature data and corresponding equipment operating parameters in the historical data, such as motor speed and reagent dosage, the least squares method and other methods are used to solve the regression coefficient. After obtaining the regression model, the current water quality parameters and other relevant data are input to predict the optimal equipment operating parameters under the working conditions, so as to achieve efficient operation of the equipment and reasonable control of energy consumption.

[0069] The Bayesian network algorithm unit is used to establish a causal relationship between the equipment failure type, the equipment failure probability and the equipment maintenance parameter based on the fourth processed data by using the Bayesian network, and determine the equipment maintenance parameter based on the causal relationship.

[0070] Further,

[0071] The Bayesian network is a graphical model based on probabilistic reasoning, which represents the causal relationship between variables in the form of a directed acyclic graph. When constructing a Bayesian network, the equipment failure type, equipment failure probability and equipment maintenance parameters are used as nodes, and the directed edges between the nodes are determined based on domain knowledge and historical data to represent the causal dependency between the variables. For example, it is known that a certain type of equipment failure is usually caused by factors such as too long equipment operation time and excessive vibration. In the Bayesian network, the equipment operation time and vibration parameter nodes will have directed edges pointing to the bearing wear fault type node. The fourth processing data is obtained by the support vector machine analysis unit of the collaborative data processing central module, which includes the equipment failure type and equipment failure probability. The Bayesian network algorithm uses these data and combines Bayes' theorem for probabilistic reasoning. When a certain type of failure or a certain probability of failure occurs in a known device, the Bayesian network can calculate the equipment maintenance parameters related to the failure, such as the parts that need to be replaced, the time node for maintenance, etc. For example, when it is detected that the equipment has a high probability of bearing wear failure, the Bayesian network determines that the bearing should be replaced immediately based on its causal relationship and probability distribution, and gives appropriate maintenance time recommendations to ensure the stable operation of the equipment and extend the equipment's service life.

[0072] The strategy generation module is used to generate operation and maintenance strategy parameters based on the optimized process parameters, equipment operation parameters and equipment maintenance parameters.

[0073] Furthermore, according to the optimized process parameters, the strategy generation module formulates a detailed process operation process. For example, if the optimized process parameters show that the optimal aeration time is X hours and the optimal reagent dosage is Y kg / m3, then the operation and maintenance strategy parameters will clearly stipulate that during the aeration stage of wastewater treatment, the equipment needs to run for X hours and the reagent dosage should be Y kg / m3. Taking into account the fluctuation of water quality in the actual wastewater treatment process, the strategy generation module will also formulate a process adjustment strategy. When the water quality parameters exceed a certain range, the corresponding process adjustment measures are determined according to the change trend of the optimized process parameters. For example, if the chemical oxygen demand of the influent suddenly increases, the operation and maintenance strategy parameters will stipulate that the reagent dosage should be increased according to a certain proportion, or the aeration time should be extended to ensure that the wastewater treatment effect is not affected. Based on the equipment operation parameters, the strategy generation module formulates the equipment operation plan. Determine the start and stop time of the equipment, as well as the operation mode under different working conditions. For example, according to the optimal speed and flow requirements of the motor in the equipment operation parameters, it is stipulated that when the wastewater flow is large, the equipment should adopt high-speed operation mode to ensure the treatment efficiency; when the wastewater flow is small, the equipment should switch to low-speed operation mode to reduce energy consumption. Energy consumption management strategies are formulated based on the equipment energy consumption data and the preset energy consumption threshold. When the equipment energy consumption data exceeds the preset energy consumption threshold, the task scheduling mechanism unit of the intelligent edge collector module will automatically reduce the collection frequency of non-critical sensors to give priority to the collection and transmission of energy consumption-related data. Based on this mechanism, the strategy generation module will stipulate in the operation and maintenance strategy parameters that when energy consumption is abnormal, the equipment operation status should be checked and adjusted in time, such as adjusting the load of the equipment, optimizing the operation combination of the equipment, etc., to reduce energy consumption. According to the equipment maintenance parameters, the strategy generation module formulates a detailed equipment maintenance plan. The content and time nodes of daily maintenance, regular maintenance and emergency maintenance of the equipment are clarified. For example, if the equipment maintenance parameters stipulate that a key component needs to be inspected and maintained every Z hours of operation, the operation and maintenance strategy parameters will include this maintenance task in the regular maintenance plan and notify the maintenance personnel in advance to prepare. Develop corresponding failure response strategies based on the possible failure types and failure probabilities of the equipment. Once a device fails, effective measures can be taken quickly to repair it and reduce the impact on the wastewater treatment system. For example, when the equipment maintenance parameters predict that a certain device has a high probability of failure, the operation and maintenance strategy parameters will stipulate that spare equipment should be prepared in advance and maintenance personnel should be arranged to be on standby at any time so that the equipment can be replaced or repaired in time when it fails. After generating the preliminary operation and maintenance strategy parameters, the strategy generation module will simulate and evaluate them. By establishing a virtual wastewater treatment system model and inputting various possible water quality and operating condition data, the execution effect of the operation and maintenance strategy is simulated. Evaluation indicators include whether the wastewater treatment effect meets the standards, equipment operation stability, energy consumption level, etc.Using the real-time feedback mechanism, the process parameter strategy unit dynamically fine-tunes the process parameters according to the difference between the actual treated water quality data and the preset water quality standards. The strategy generation module will continuously monitor the operation of the wastewater treatment system and adjust and optimize the operation and maintenance strategy parameters based on the real-time feedback data. For example, if it is found in actual operation that the wastewater treatment effect fails to meet the preset standards when operating according to the current operation and maintenance strategy, the strategy generation module will analyze the reasons, which may be unreasonable process parameter settings or poor equipment operation status, and then adjust the operation and maintenance strategy parameters accordingly to achieve the purpose of continuously optimizing the wastewater treatment process and ensure that the wastewater treatment effect always meets the requirements.

[0074] In some optional embodiments, the remote monitoring and operation and maintenance system for water treatment equipment also includes a quantum encryption communication expansion module, which is used to deploy quantum key distribution devices between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing hub module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module.

[0075] Specifically, the ultra-sensitive composite sensor matrix module is responsible for collecting key data such as water quality parameters, equipment operating pressure parameters and vibration signal parameters, which are the basis for the entire system to analyze and make decisions. Deploying a quantum key distribution device between it and the intelligent edge collector module can ensure the absolute security of data during transmission. Since quantum key distribution is based on the principles of quantum mechanics, any third party attempting to eavesdrop on the data will change the quantum state and thus be detected by both parties in communication. For example, when the sensor collects the chemical oxygen demand data of water quality at a certain moment and transmits it to the intelligent edge collector, the quantum key generated by the quantum key distribution device encrypts the data. Only the intelligent edge collector module holds the corresponding decryption key to correctly read the data, ensuring that the data is not stolen or tampered with during transmission. Wastewater treatment involves important information such as environmental monitoring and enterprise production operations. If the data is maliciously obtained, it may lead to serious consequences such as inaccurate environmental pollution risk assessment and interference with the enterprise production process. Through quantum encryption communication, the security of data is guaranteed from the source, effectively preventing the risk of data leakage and safeguarding the interests of enterprises and the environment. The collaborative data processing central module performs convolutional neural network analysis, association rule analysis and support vector machine analysis on the first processed data, and the second, third and fourth processed data obtained are the core data for the system to conduct in-depth analysis and decision-making. These data contain important information such as water quality change trends, equipment operation parameter associations and equipment failure predictions. When interacting with the cloud-based fusion computing platform module, the quantum key distribution device uses the non-cloning of quantum states and the uncertainty of measurement to provide high-intensity encryption protection for data transmission. For example, when the collaborative data processing central module transmits the predicted equipment failure type and probability data to the cloud-based fusion computing platform module, the quantum key generated by the quantum key distribution device ensures that the data will not be intercepted and cracked by a third party during the transmission process, ensuring the confidentiality of the data. The cloud-based fusion computing platform module is responsible for generating key decision-making data such as optimization process parameters, equipment operation parameters and equipment maintenance parameters. The accuracy and security of these data directly affect the operation effect and stability of the entire wastewater treatment system. By deploying quantum encryption communication between the two, the security of the system's core data interaction is improved, thereby enhancing the security and reliability of the entire water treatment equipment remote monitoring and operation and maintenance system. The cloud-based fusion computing platform module stores a large amount of historical data, analysis models, and various key parameters generated. Deploying a quantum key distribution device inside it can encrypt and protect this data during storage and sharing. For example, when different modules within the platform need to share optimized process parameters for comprehensive decision-making, the quantum key distribution device ensures the security of data transmission between modules. At the same time, for data stored in the cloud, quantum encryption technology prevents the data from being illegally accessed and stolen. Even if the data storage medium is compromised, valid data cannot be obtained without the correct quantum key.In today's strict data security regulatory environment, wastewater treatment companies need to ensure that their data processing and storage meet relevant security standards. The expansion of quantum encryption communication within the cloud-based fusion computing platform module helps companies meet these compliance requirements and avoid legal risks and reputation losses due to data security issues.

[0076] The remote monitoring and operation and maintenance system for water treatment equipment provided in this embodiment first collects water quality parameters, equipment operating pressure parameters and vibration signal parameters in all directions through a composite water quality sensor unit and a dual-mode sensor. The ability to capture key information in the wastewater treatment process is greatly improved, ensuring the comprehensiveness and accuracy of the acquired data. Whether it is a subtle change in water quality or a potential abnormality in the operating state of the equipment, it can be accurately perceived. Secondly, the intelligent edge collector module efficiently converges the signals output by the ultra-sensitive composite sensor matrix module according to the preset sensor priority and acquisition frequency, ensuring that key data can be collected in priority and in a timely manner, significantly improving data collection efficiency, and avoiding information delays caused by data collection confusion. The collected water quality, equipment operating pressure and vibration signal parameters are pre-processed to provide a reliable data source for subsequent in-depth analysis, greatly improving the accuracy and reliability of the data analysis results. Then, the hybrid ad hoc network transmission module: based on the combined design of the industrial Ethernet unit and the wireless communication unit, the flexible switching of the data transmission mode is realized. When the industrial Ethernet network conditions are good, the first processing data is quickly and stably transmitted to the collaborative data processing hub module by utilizing its high bandwidth and low latency characteristics to ensure that the data can be delivered in time for analysis and processing. When the industrial Ethernet fails or the network parameters do not meet the preset transmission conditions, the wireless communication unit starts quickly and determines the appropriate wireless transmission link according to the priority of the transmission link to ensure the continuity of data transmission, avoid data loss or transmission interruption due to network problems, and achieve stable data transmission in a complex network environment. Afterwards, the collaborative data processing central module uses convolutional neural networks to analyze the first processing data, which can accurately predict the changing trend parameters of water quality parameters under different process parameters, providing a scientific basis for optimizing the wastewater treatment process, avoiding the occurrence of poor treatment effects, and greatly improving the foresight and scientific nature of the wastewater treatment process. Through association rule analysis, the potential connection between the first processing data, system energy consumption data and process effect data is mined, and the target frequent item set combination is found, which helps to deeply understand the relationship between various factors in the wastewater treatment process, and provides strong support for optimizing equipment operation mode, reducing energy consumption and improving treatment effects, and improving the overall efficiency and benefits of system operation. Using support vector machines to analyze the first processing data, accurately predict the type of equipment failure and the probability of equipment failure, and be able to formulate maintenance plans in advance, take preventive maintenance measures, reduce the losses caused by sudden equipment failures, and improve the reliability and service life of equipment. Finally, the cloud-based fusion computing platform module uses an optimization algorithm to process the second processing data obtained by the convolutional neural network analysis and determines the optimized process parameters, which helps to achieve fine-grained adjustment of the wastewater treatment process, improve treatment efficiency, reduce treatment costs, ensure that the wastewater treatment effect always meets the standard requirements, and realize the intelligent optimization of the wastewater treatment process.The third processed data obtained by the association rule analysis is processed by regression analysis to obtain the equipment operation parameters, so that the equipment can work in the optimal operation mode, which not only improves the equipment operation efficiency, but also reduces energy consumption and equipment wear, prolongs the service life of the equipment, and realizes efficient energy saving of equipment operation. The fourth processed data obtained by the support vector machine analysis is processed by the Bayesian network algorithm to determine the equipment maintenance parameters, which provides a scientific basis for equipment maintenance, makes the maintenance work more accurate and efficient, avoids excessive maintenance or insufficient maintenance, and improves the management level of equipment maintenance. The strategy generation module comprehensively optimizes the process parameters, equipment operation parameters and equipment maintenance parameters, generates comprehensive operation and maintenance strategy parameters, organically integrates the optimization results of each link, and provides a set of systematic and scientific guidance schemes for the operation and maintenance of water treatment equipment, improves the coordination and operability of the entire water treatment equipment remote monitoring and operation and maintenance system, realizes the all-round and intelligent operation and maintenance management of water treatment equipment, and effectively guarantees the stable operation and efficient treatment capacity of the wastewater treatment system. It solves the problem of how to accurately monitor water quality changes and equipment operation status, and conducts in-depth analysis and effective utilization based on water quality, energy consumption, equipment operation and other data, so as to optimize the treatment process and reduce energy consumption.

[0077] The above is an embodiment of the remote monitoring and operation and maintenance system for water treatment equipment provided by the present application. The following describes other embodiments of the remote monitoring and operation and maintenance of water treatment equipment provided by the present application. Please refer to the following for details.

[0078] The embodiment of the present invention also discloses a method for remote monitoring and operation of water treatment equipment, such as Figure 2As shown, the method includes: controlling the ultra-sensitive composite sensor matrix module to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters; controlling the intelligent edge collector module to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters returned by the ultra-sensitive composite sensor matrix unit, pre-processing the water quality parameters, equipment operating pressure parameters and vibration signal parameters to obtain first processing data; controlling the hybrid ad hoc network transmission module to transmit the first processing data to the collaborative data processing central module based on the industrial Ethernet unit and the wireless communication unit; controlling the collaborative data processing central module to perform convolutional neural network analysis on the first processing data to obtain second processing data, and performing association rule analysis on the first processing data, system energy consumption data and process effect data to obtain third processing data Process data, support vector machine analysis is performed on the first processed data to obtain fourth processed data, system energy consumption data is collected by the energy consumption monitoring device and transmitted to the collaborative data processing central module, the system energy consumption data includes equipment energy consumption data and agent energy consumption data, process effect data is collected by the on-site control layer equipment, the process effect data includes reaction time data, reaction temperature data and reaction pH value data; the control cloud fusion computing platform module uses the optimization algorithm to process the second processed data to obtain optimized process parameters, uses regression analysis to process the third processed data to obtain equipment operating parameters, and uses the Bayesian network algorithm to process the fourth processed data to obtain equipment maintenance parameters; the control strategy generation module generates operation and maintenance strategy parameters based on the optimized process parameters, equipment operating parameters and equipment maintenance parameters.

[0079] In an optional embodiment, the method also includes: controlling the quantum encryption communication extension module to deploy a quantum key distribution device between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing hub module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module.

[0080] The technical solution of the present invention has the following advantages:

[0081] The remote monitoring and operation and maintenance method of water treatment equipment provided in this embodiment first collects water quality parameters, equipment operating pressure parameters and vibration signal parameters in all directions through a composite water quality sensor unit and a dual-mode sensor. The ability to capture key information in the wastewater treatment process is greatly improved, ensuring the comprehensiveness and accuracy of the acquired data. Whether it is a subtle change in water quality or a potential abnormality in the operating state of the equipment, it can be accurately perceived. Secondly, the intelligent edge collector module efficiently converges the signals output by the ultra-sensitive composite sensor matrix module according to the preset sensor priority and acquisition frequency, ensuring that key data can be collected in priority and in a timely manner, significantly improving data collection efficiency, and avoiding information delays caused by data collection confusion. The collected water quality, equipment operating pressure and vibration signal parameters are pre-processed to provide a reliable data source for subsequent in-depth analysis, greatly improving the accuracy and reliability of the data analysis results. Then, the hybrid ad hoc network transmission module: based on the combined design of the industrial Ethernet unit and the wireless communication unit, the flexible switching of the data transmission mode is realized. When the industrial Ethernet network conditions are good, the high bandwidth and low latency characteristics are used to quickly and stably transmit the first processing data to the collaborative data processing hub module to ensure that the data can be delivered in time for analysis and processing. When the industrial Ethernet fails or the network parameters do not meet the preset transmission conditions, the wireless communication unit starts quickly and determines the appropriate wireless transmission link according to the priority of the transmission link to ensure the continuity of data transmission, avoid data loss or transmission interruption due to network problems, and achieve stable data transmission in a complex network environment. Afterwards, the collaborative data processing central module uses convolutional neural networks to analyze the first processing data, which can accurately predict the changing trend parameters of water quality parameters under different process parameters, providing a scientific basis for optimizing the wastewater treatment process, avoiding the occurrence of poor treatment effects, and greatly improving the foresight and scientific nature of the wastewater treatment process. Through association rule analysis, the potential connection between the first processing data, system energy consumption data and process effect data is mined, and the target frequent item set combination is found, which helps to deeply understand the relationship between various factors in the wastewater treatment process, and provides strong support for optimizing equipment operation mode, reducing energy consumption and improving treatment effects, and improving the overall efficiency and benefits of system operation. Using support vector machines to analyze the first processing data, accurately predict the type of equipment failure and the probability of equipment failure, and be able to formulate maintenance plans in advance, take preventive maintenance measures, reduce the losses caused by sudden equipment failures, and improve the reliability and service life of equipment. Finally, the cloud-based fusion computing platform module uses an optimization algorithm to process the second processing data obtained by the convolutional neural network analysis and determines the optimized process parameters, which helps to achieve fine-grained adjustment of the wastewater treatment process, improve treatment efficiency, reduce treatment costs, ensure that the wastewater treatment effect always meets the standard requirements, and realize the intelligent optimization of the wastewater treatment process.The third processed data obtained by the association rule analysis is processed by regression analysis to obtain the equipment operation parameters, so that the equipment can work in the optimal operation mode, which not only improves the equipment operation efficiency, but also reduces energy consumption and equipment wear, prolongs the service life of the equipment, and realizes efficient energy saving of equipment operation. The fourth processed data obtained by the support vector machine analysis is processed by the Bayesian network algorithm to determine the equipment maintenance parameters, which provides a scientific basis for equipment maintenance, makes the maintenance work more accurate and efficient, avoids excessive maintenance or insufficient maintenance, and improves the management level of equipment maintenance. The strategy generation module comprehensively optimizes the process parameters, equipment operation parameters and equipment maintenance parameters, generates comprehensive operation and maintenance strategy parameters, organically integrates the optimization results of each link, and provides a set of systematic and scientific guidance schemes for the operation and maintenance of water treatment equipment, improves the coordination and operability of the entire water treatment equipment remote monitoring and operation and maintenance system, realizes the all-round and intelligent operation and maintenance management of water treatment equipment, and effectively guarantees the stable operation and efficient treatment capacity of the wastewater treatment system. It solves the problem of how to accurately monitor water quality changes and equipment operation status, and conducts in-depth analysis and effective utilization based on water quality, energy consumption, equipment operation and other data, so as to optimize the treatment process and reduce energy consumption.

[0082] The implementation methods of each step in the remote monitoring and operation and maintenance method for water treatment equipment provided by the embodiment of the present invention have been described in detail in any of the above system embodiments, so they will not be repeated here.

[0083] The remote monitoring and operation and maintenance system for water treatment equipment in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

Claims

1. A water treatment equipment remote monitoring and operation system, characterized in that: The system comprises: Ultra-sensitive composite sensor matrix module, used to collect water quality parameters, equipment operating pressure parameters and vibration signal parameters; An intelligent edge collector module is used to collect water quality parameters, equipment operation pressure parameters and vibration signal parameters returned by the ultra-sensitive composite sensor matrix unit, and pre-process the water quality parameters, equipment operation pressure parameters and vibration signal parameters to obtain first processed data; A hybrid ad hoc network transmission module, used for transmitting the first processed data to the collaborative data processing hub module based on an industrial Ethernet unit and a wireless communication unit; A collaborative data processing central module, used for performing a convolutional neural network analysis on the first processed data to obtain second processed data, performing an association rule analysis on the first processed data, system energy consumption data and process effect data to obtain third processed data, and performing a support vector machine analysis on the first processed data to obtain fourth processed data, wherein the system energy consumption data is collected by an energy consumption monitoring device and transmitted to the collaborative data processing central module, the system energy consumption data includes equipment energy consumption data and agent energy consumption data, the process effect data is collected by a field control layer device, and the process effect data includes reaction time data, reaction temperature data and reaction pH value data; A cloud-based fusion computing platform module, configured to process the second processed data using an optimization algorithm to obtain optimized process parameters, process the third processed data using regression analysis to obtain equipment operation parameters, and process the fourth processed data using a Bayesian network algorithm to obtain equipment maintenance parameters; A strategy generation module, used to generate operation and maintenance strategy parameters based on the optimized process parameters, equipment operation parameters and equipment maintenance parameters; The collaborative data processing hub module includes: A convolutional neural network analysis unit, configured to analyze the first processed data using a pre-trained convolutional neural network, predict the change trend parameters of the water quality parameters under different process parameters, and obtain second processed data; An association rule analysis unit is used to mine association rules between chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, agent energy consumption data, reaction time data, reaction temperature data and reaction pH value data by setting a preset minimum support and a preset minimum confidence threshold, find a target frequent item set combination, and obtain third processed data; The step of finding the target frequent item set combination includes: using an association rule mining algorithm to analyze chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, reagent energy consumption data, reaction time data, reaction temperature data, and reaction pH value data, generating frequent item sets according to minimum support, generating association rules based on the frequent item sets according to minimum confidence, and finding the target frequent item set combination through continuous iteration and screening; A support vector machine analysis unit, configured to perform support vector machine analysis on the first processed data, predict the equipment failure type and equipment failure probability, and obtain fourth processed data; In the process of mining association rules, the association rule analysis unit adjusts the preset minimum support and the preset minimum confidence thresholds based on the water quality parameters, the equipment operation pressure parameters and the preset proportional relationship.

2. The system according to claim 1, characterized in that The water treatment equipment remote monitoring and operation and maintenance system also includes a quantum encryption communication expansion module, which is used to deploy quantum key distribution equipment between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing center module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module.

3. The system according to claim 2, characterized in that The ultra-sensitive composite sensor matrix module comprises: An optical-electrochemical composite water quality sensor unit is used to collect water quality parameters, including chemical oxygen demand parameters, biochemical oxygen demand parameters, colorimetric parameters, and heavy metal ion concentration parameters; Pressure-vibration dual-mode sensor, installed at the connection between the bearing seat and the pipeline of each target equipment, is used to collect equipment operating pressure parameters and vibration signal parameters; The output unit outputs water quality parameters, equipment operation pressure parameters and vibration signal parameters in the form of digital signals or analog signals.

4. The system according to claim 3, characterized in that The intelligent edge collector module includes: The acquisition unit is used to collect the analog signal or digital signal output by the ultra-sensitive composite sensor matrix module based on the priority of each sensor and the acquisition frequency of each sensor by using the peripheral interface and the dedicated sensor interface, wherein the sensor priority and the acquisition frequency of each sensor are preset by the system; A conversion unit, used for converting the analog signal output by the ultra-sensitive composite sensor matrix module into a digital signal by using an analog-to-digital converter when the analog signal is collected; A preprocessing unit, used for performing noise filtering processing and feature extraction processing on the water quality parameter, the equipment operation pressure parameter and the vibration signal parameter to obtain first processed data; a multi-core processor unit, configured to perform an abnormality analysis on the first processed data to determine an abnormality result, wherein the abnormality result includes an abnormality determination and an abnormality parameter; The task scheduling mechanism unit is used to adjust the priority of each sensor and the acquisition frequency of each sensor based on the abnormal result.

5. The system according to claim 4, characterized in that The hybrid ad hoc network transmission module comprises: An industrial Ethernet unit, used to monitor network parameters of each link in the industrial Ethernet using an industrial Ethernet switch, wherein the network parameters include connection status parameters, port flow parameters, and error packet quantity parameters, and determine a target transmission link in the industrial Ethernet based on the network parameters and preset transmission conditions; A wireless communication unit, configured to determine a target transmission link in wireless communication based on a transmission link priority when it is not detected that the network parameters of any link in the industrial Ethernet meet the preset transmission conditions, wherein the wireless communication includes a 5G link, a LoRaWAN link, and a satellite communication link; A network prediction unit, used to obtain and analyze network parameters of a target transmission link and generate a network switching strategy; The link switching unit is used to switch the target transmission link based on the network switching strategy.

6. The system according to claim 5, characterized in that The cloud-based fusion computing platform module includes: A process parameter strategy unit, configured to analyze the second processing data using an optimization algorithm, determine an optimal solution for the process parameters, and obtain optimized process parameters; A regression analysis unit is used to establish a correlation between system energy consumption data and chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, reaction time data, reaction temperature data, and reaction pH value data by using regression analysis and a third processed data combination, simulate the system energy consumption data under different equipment operation parameters, determine the optimal solution for equipment operation, and obtain equipment operation parameters, wherein the equipment operation parameters include equipment operation mode parameters and drug dosing parameters for dosing equipment; The Bayesian network algorithm unit is used to establish a causal relationship between the equipment failure type, the equipment failure probability and the equipment maintenance parameter based on the fourth processed data using the Bayesian network, and determine the equipment maintenance parameter based on the causal relationship.

7. A water treatment equipment remote monitoring and operation method, characterized in that: The method comprises: Control the ultra-sensitive composite sensor matrix module to collect water quality parameters, equipment operation pressure parameters and vibration signal parameters; Controlling the intelligent edge collector module to collect water quality parameters, equipment operation pressure parameters, and vibration signal parameters returned by the ultra-sensitive composite sensor matrix unit, and pre-processing the water quality parameters, equipment operation pressure parameters, and vibration signal parameters to obtain first processed data; Controlling the hybrid ad hoc network transmission module to transmit the first processed data to the collaborative data processing hub module based on the industrial Ethernet unit and the wireless communication unit; The control collaborative data processing central module performs convolutional neural network analysis on the first processed data to obtain second processed data, performs association rule analysis on the first processed data, system energy consumption data and process effect data to obtain third processed data, and performs support vector machine analysis on the first processed data to obtain fourth processed data, wherein the system energy consumption data is collected by the energy consumption monitoring device and transmitted to the collaborative data processing central module, the system energy consumption data includes equipment energy consumption data and agent energy consumption data, the process effect data is collected by the field control layer equipment, and the process effect data includes reaction time data, reaction temperature data and reaction pH value data; Control the cloud-based fusion computing platform module to process the second processed data using an optimization algorithm to obtain optimized process parameters, process the third processed data using regression analysis to obtain equipment operation parameters, and process the fourth processed data using a Bayesian network algorithm to obtain equipment maintenance parameters; The control strategy generation module generates operation and maintenance strategy parameters based on the optimized process parameters, equipment operation parameters and equipment maintenance parameters; The collaborative data processing hub module includes: A convolutional neural network analysis unit, configured to analyze the first processed data using a pre-trained convolutional neural network, predict the change trend parameters of the water quality parameters under different process parameters, and obtain second processed data; An association rule analysis unit is used to mine association rules between chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, agent energy consumption data, reaction time data, reaction temperature data and reaction pH value data by setting a preset minimum support and a preset minimum confidence threshold, find a target frequent item set combination, and obtain third processed data; The step of finding the target frequent item set combination includes: using an association rule mining algorithm to analyze chemical oxygen demand parameters, biochemical oxygen demand parameters, chromaticity parameters, heavy metal ion concentration parameters, equipment energy consumption data, reagent energy consumption data, reaction time data, reaction temperature data, and reaction pH value data, generating frequent item sets according to minimum support, generating association rules based on the frequent item sets according to minimum confidence, and finding the target frequent item set combination through continuous iteration and screening; A support vector machine analysis unit, configured to perform support vector machine analysis on the first processed data, predict the equipment failure type and equipment failure probability, and obtain fourth processed data; In the process of mining association rules, the association rule analysis unit adjusts the preset minimum support and the preset minimum confidence thresholds based on the water quality parameters, the equipment operation pressure parameters and the preset proportional relationship.

8. The method according to claim 7, characterized in that The method further comprises: The control quantum encryption communication extension module deploys quantum key distribution equipment between the ultra-sensitive composite sensor matrix module and the intelligent edge collector module, between the collaborative data processing center module and the cloud-based fusion computing platform module, and inside the cloud-based fusion computing platform module.

Images